[11-22 15:50:17] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-22 15:50:17] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-22 15:50:17] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-22 15:50:19] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-22 15:50:19] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add branch : main } [11-22 15:50:19] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-22 15:50:22] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-22 15:50:22] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> [11-22 15:50:22] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-22 15:50:22] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> [11-22 15:50:22] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-22 15:50:22] (/home/user/VAR/train.py , line 65)=> [auto_resume] no ckpt found @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt*.pth [11-22 15:50:22] (/home/user/VAR/train.py , line 65)=> [auto_resume quit] [11-22 15:50:22] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-22 15:50:17] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-22 15:50:17] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-22 15:50:17] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-22 15:50:19] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-22 15:50:19] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-22 15:50:19] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-22 15:50:22] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-22 15:50:22] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> [11-22 15:50:22] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-22 15:50:22] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> [11-22 15:50:22] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-22 15:50:22] (/home/user/VAR/train.py , line 65)=> [auto_resume] no ckpt found @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt*.pth [11-22 15:50:22] (/home/user/VAR/train.py , line 65)=> [auto_resume quit] [11-22 15:50:22] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-22 15:50:17] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-22 15:50:17] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-22 15:50:17] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-22 15:50:19] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-22 15:50:19] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add } [11-22 15:50:19] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-22 15:50:22] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-22 15:50:22] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> [11-22 15:50:22] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-22 15:50:22] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> [11-22 15:50:22] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-22 15:50:22] (/home/user/VAR/train.py , line 65)=> [auto_resume] no ckpt found @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt*.pth [11-22 15:50:22] (/home/user/VAR/train.py , line 65)=> [auto_resume quit] [11-22 15:50:22] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-22 15:50:17] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-22 15:50:17] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-22 15:50:17] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-22 15:50:19] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-22 15:50:19] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-22 15:50:19] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-22 15:50:22] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-22 15:50:22] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> [11-22 15:50:22] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-22 15:50:22] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> [11-22 15:50:22] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-22 15:50:22] (/home/user/VAR/train.py , line 65)=> [auto_resume] no ckpt found @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt*.pth [11-22 15:50:22] (/home/user/VAR/train.py , line 65)=> [auto_resume quit] [11-22 15:50:22] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-22 15:50:17] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-22 15:50:17] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-22 15:50:17] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-22 15:50:19] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-22 15:50:19] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-22 15:50:19] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-22 15:50:22] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-22 15:50:22] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> [11-22 15:50:22] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-22 15:50:22] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> [11-22 15:50:22] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-22 15:50:22] (/home/user/VAR/train.py , line 65)=> [auto_resume] no ckpt found @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt*.pth [11-22 15:50:22] (/home/user/VAR/train.py , line 65)=> [auto_resume quit] [11-22 15:50:22] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-22 15:50:17] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-22 15:50:17] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-22 15:50:17] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-22 15:50:19] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-22 15:50:19] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-22 15:50:19] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-22 15:50:22] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-22 15:50:22] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> [11-22 15:50:22] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-22 15:50:22] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> [11-22 15:50:22] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-22 15:50:22] (/home/user/VAR/train.py , line 65)=> [auto_resume] no ckpt found @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt*.pth [11-22 15:50:22] (/home/user/VAR/train.py , line 65)=> [auto_resume quit] [11-22 15:50:22] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-22 15:50:17] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-22 15:50:17] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-22 15:50:17] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-22 15:50:19] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-22 15:50:19] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add branch : main } [11-22 15:50:19] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-22 15:50:22] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-22 15:50:22] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> [11-22 15:50:22] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-22 15:50:22] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> [11-22 15:50:22] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-22 15:50:22] (/home/user/VAR/train.py , line 65)=> [auto_resume] no ckpt found @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt*.pth [11-22 15:50:22] (/home/user/VAR/train.py , line 65)=> [auto_resume quit] [11-22 15:50:22] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-22 15:50:17] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-22 15:50:17] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-22 15:50:17] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-22 15:50:19] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-22 15:50:19] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add } [11-22 15:50:19] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-22 15:50:22] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-22 15:50:22] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> [11-22 15:50:22] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-22 15:50:22] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-22 15:50:22] (e/user/VAR/utils/data.py, line 51)=> [11-22 15:50:22] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-22 15:50:22] (/home/user/VAR/train.py , line 65)=> [auto_resume] no ckpt found @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt*.pth [11-22 15:50:22] (/home/user/VAR/train.py , line 65)=> [auto_resume quit] [11-22 15:50:22] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ... [dataloader multi processing](*) finished! (48.83s) [dataloader multi processing](*) finished! (48.97s) [dataloader multi processing](*) finished! (49.24s) [dataloader multi processing](*) finished! (49.39s) [dataloader multi processing](*) finished! (50.10s) [dataloader multi processing](*) finished! (50.14s) [11-22 15:51:11] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [dataloader multi processing](*) finished! (51.09s) [11-22 15:51:15] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-22 15:51:15] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-22 15:51:16] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [dataloader multi processing](*) finished! (54.66s) [11-22 15:51:11] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-22 15:51:16] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-22 15:51:16] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-22 15:51:17] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-22 15:51:11] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-22 15:51:16] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-22 15:51:16] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-22 15:51:18] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-22 15:51:12] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-22 15:51:17] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-22 15:51:17] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-22 15:51:18] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-22 15:51:12] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-22 15:51:17] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-22 15:51:17] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-22 15:51:18] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-22 15:51:11] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-22 15:51:16] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-22 15:51:16] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-22 15:51:18] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-22 15:51:13] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-22 15:51:18] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-22 15:51:18] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-22 15:51:19] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-22 15:51:17] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-22 15:51:21] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-22 15:51:21] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-22 15:51:22] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-22 15:51:20] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-22 15:51:50] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-22 15:51:50] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-22 15:51:50] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-22 15:51:50] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-22 15:51:50] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank0] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-22 15:51:25] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-22 15:51:50] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-22 15:51:50] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-22 15:51:50] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-22 15:51:50] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-22 15:51:50] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank8] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-22 15:51:22] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-22 15:51:50] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-22 15:51:50] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-22 15:51:50] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-22 15:51:50] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-22 15:51:51] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank16] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-22 15:51:21] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-22 15:51:50] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-22 15:51:50] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-22 15:51:50] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-22 15:51:50] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-22 15:51:51] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank24] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-22 15:51:21] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-22 15:51:50] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-22 15:51:50] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-22 15:51:50] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-22 15:51:50] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-22 15:51:51] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank32] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-22 15:51:20] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-22 15:51:50] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-22 15:51:50] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-22 15:51:50] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-22 15:51:50] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-22 15:51:51] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank40] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-22 15:51:21] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-22 15:51:50] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-22 15:51:50] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-22 15:51:50] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-22 15:51:50] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-22 15:51:51] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank48] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-22 15:51:21] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-22 15:51:50] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-22 15:51:50] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-22 15:51:50] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-22 15:51:50] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-22 15:51:51] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank56] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-22 15:51:51] (/VAR/utils/lr_control.py, line 105)=> [11-22 15:51:51] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-22 16:09:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 0/1669] eta: 20 days, 2:51:15 tlr: 1.2e-06 tnm: 0.43 Lm: 9.704 (9.704) Lt: 9.704 (9.704) Accm: 0.01 (0.01) Acct: 0.00 (0.00) proj_loss: 0.0005 (0.0005) time: 1041.5074 data: 0.0005 [11-22 15:51:51] (/VAR/utils/lr_control.py, line 105)=> [11-22 15:51:51] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-22 16:09:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 0/1669] eta: 20 days, 2:51:23 tlr: 1.2e-06 tnm: 0.43 Lm: 9.704 (9.704) Lt: 9.704 (9.704) Accm: 0.00 (0.00) Acct: 0.00 (0.00) proj_loss: 0.0005 (0.0005) time: 1041.5122 data: 0.0004 [11-22 15:51:51] (/VAR/utils/lr_control.py, line 105)=> [11-22 15:51:51] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-22 16:09:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 0/1669] eta: 20 days, 2:52:25 tlr: 1.2e-06 tnm: 0.43 Lm: 9.704 (9.704) Lt: 9.704 (9.704) Accm: 0.00 (0.00) Acct: 0.00 (0.00) proj_loss: -0.0007 (-0.0007) time: 1041.5492 data: 0.0005 [11-22 15:51:51] (/VAR/utils/lr_control.py, line 105)=> [11-22 15:51:51] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-22 16:09:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 0/1669] eta: 20 days, 2:53:20 tlr: 1.2e-06 tnm: 0.43 Lm: 9.704 (9.704) Lt: 9.704 (9.704) Accm: 0.00 (0.00) Acct: 0.00 (0.00) proj_loss: -0.0007 (-0.0007) time: 1041.5820 data: 0.0005 [11-22 15:51:51] (/VAR/utils/lr_control.py, line 105)=> [11-22 15:51:51] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-22 16:09:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 0/1669] eta: 20 days, 2:53:51 tlr: 1.2e-06 tnm: 0.43 Lm: 9.704 (9.704) Lt: 9.704 (9.704) Accm: 0.00 (0.00) Acct: 0.00 (0.00) proj_loss: -0.0002 (-0.0002) time: 1041.6004 data: 0.0005 [11-22 15:51:51] (/VAR/utils/lr_control.py, line 105)=> [11-22 15:51:51] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-22 16:09:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 0/1669] eta: 20 days, 2:54:00 tlr: 1.2e-06 tnm: 0.43 Lm: 9.704 (9.704) Lt: 9.704 (9.704) Accm: 0.00 (0.00) Acct: 0.00 (0.00) proj_loss: 0.0022 (0.0022) time: 1041.6059 data: 0.0005 [11-22 15:51:51] (/VAR/utils/lr_control.py, line 105)=> [11-22 15:51:51] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-22 16:09:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 0/1669] eta: 20 days, 2:29:13 tlr: 1.2e-06 tnm: 0.43 Lm: 9.704 (9.704) Lt: 9.704 (9.704) Accm: 0.01 (0.01) Acct: 0.03 (0.03) proj_loss: -0.0013 (-0.0013) time: 1040.7150 data: 0.0006 [11-22 15:51:51] (/VAR/utils/lr_control.py, line 105)=> [11-22 15:51:51] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-22 16:09:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 0/1669] eta: 20 days, 2:54:20 tlr: 1.2e-06 tnm: 0.43 Lm: 9.704 (9.704) Lt: 9.704 (9.704) Accm: 0.00 (0.00) Acct: 0.00 (0.00) proj_loss: 0.0002 (0.0002) time: 1041.6178 data: 0.0006 [11-22 16:24:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 417/1669] eta: 1:36:24 tlr: 9.7e-06 tnm: 0.10 Lm: 9.699 (9.699) Lt: 9.698 (9.698) Accm: 0.01 (0.01) Acct: 0.03 (0.03) proj_loss: -0.1489 (-0.1489) time: 0.9259 data: 0.0003 [11-22 16:24:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 417/1669] eta: 1:36:27 tlr: 9.7e-06 tnm: 0.10 Lm: 9.700 (9.700) Lt: 9.699 (9.699) Accm: 0.02 (0.02) Acct: 0.02 (0.02) proj_loss: -0.1372 (-0.1372) time: 0.9259 data: 0.0003 [11-22 16:24:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 417/1669] eta: 1:36:27 tlr: 9.7e-06 tnm: 0.10 Lm: 9.700 (9.700) Lt: 9.699 (9.699) Accm: 0.01 (0.01) Acct: 0.00 (0.00) proj_loss: -0.1417 (-0.1417) time: 0.9259 data: 0.0003 [11-22 16:24:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 417/1669] eta: 1:36:27 tlr: 9.7e-06 tnm: 0.10 Lm: 9.699 (9.699) Lt: 9.697 (9.697) Accm: 0.01 (0.01) Acct: 0.02 (0.02) proj_loss: -0.1401 (-0.1401) time: 0.9259 data: 0.0003 [11-22 16:24:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 417/1669] eta: 1:36:27 tlr: 9.7e-06 tnm: 0.10 Lm: 9.699 (9.699) Lt: 9.698 (9.698) Accm: 0.00 (0.00) Acct: 0.00 (0.00) proj_loss: -0.1439 (-0.1439) time: 0.9259 data: 0.0003 [11-22 16:24:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 417/1669] eta: 1:36:27 tlr: 9.7e-06 tnm: 0.10 Lm: 9.699 (9.699) Lt: 9.698 (9.698) Accm: 0.00 (0.00) Acct: 0.00 (0.00) proj_loss: -0.1553 (-0.1553) time: 0.9259 data: 0.0003 [11-22 16:24:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 417/1669] eta: 1:36:27 tlr: 9.7e-06 tnm: 0.10 Lm: 9.700 (9.700) Lt: 9.698 (9.698) Accm: 0.01 (0.01) Acct: 0.00 (0.00) proj_loss: -0.1430 (-0.1430) time: 0.9259 data: 0.0003 [11-22 16:24:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 417/1669] eta: 1:36:27 tlr: 9.7e-06 tnm: 0.10 Lm: 9.698 (9.698) Lt: 9.697 (9.697) Accm: 0.00 (0.00) Acct: 0.00 (0.00) proj_loss: -0.1451 (-0.1451) time: 0.9259 data: 0.0003 [11-22 16:30:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 834/1669] eta: 0:38:37 tlr: 1.8e-05 tnm: 0.34 Lm: 9.692 (9.675) Lt: 9.691 (9.679) Accm: 0.00 (0.02) Acct: 0.00 (0.02) proj_loss: -0.2904 (-0.2048) time: 0.9239 data: 0.0003 [11-22 16:30:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 834/1669] eta: 0:38:37 tlr: 1.8e-05 tnm: 0.34 Lm: 9.696 (9.675) Lt: 9.693 (9.679) Accm: 0.03 (0.02) Acct: 0.03 (0.02) proj_loss: -0.2738 (-0.2014) time: 0.9239 data: 0.0002 [11-22 16:30:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 834/1669] eta: 0:38:37 tlr: 1.8e-05 tnm: 0.34 Lm: 9.693 (9.674) Lt: 9.692 (9.679) Accm: 0.00 (0.02) Acct: 0.00 (0.01) proj_loss: -0.3099 (-0.2128) time: 0.9239 data: 0.0003 [11-22 16:30:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 834/1669] eta: 0:38:37 tlr: 1.8e-05 tnm: 0.34 Lm: 9.694 (9.674) Lt: 9.689 (9.676) Accm: 0.01 (0.01) Acct: 0.00 (0.01) proj_loss: -0.2806 (-0.2026) time: 0.9239 data: 0.0003 [11-22 16:30:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 834/1669] eta: 0:38:37 tlr: 1.8e-05 tnm: 0.34 Lm: 9.695 (9.676) Lt: 9.693 (9.679) Accm: 0.01 (0.01) Acct: 0.03 (0.02) proj_loss: -0.2965 (-0.2075) time: 0.9239 data: 0.0003 [11-22 16:30:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 834/1669] eta: 0:38:37 tlr: 1.8e-05 tnm: 0.34 Lm: 9.696 (9.676) Lt: 9.693 (9.677) Accm: 0.01 (0.01) Acct: 0.00 (0.00) proj_loss: -0.2882 (-0.2039) time: 0.9239 data: 0.0003 [11-22 16:30:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 834/1669] eta: 0:38:37 tlr: 1.8e-05 tnm: 0.34 Lm: 9.695 (9.676) Lt: 9.691 (9.679) Accm: 0.00 (0.01) Acct: 0.00 (0.00) proj_loss: -0.2876 (-0.2067) time: 0.9239 data: 0.0003 [11-22 16:30:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [ 834/1669] eta: 0:38:37 tlr: 1.8e-05 tnm: 0.34 Lm: 9.696 (9.676) Lt: 9.694 (9.680) Accm: 0.01 (0.01) Acct: 0.00 (0.01) proj_loss: -0.2839 (-0.2037) time: 0.9239 data: 0.0003 [11-22 16:36:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [1251/1669] eta: 0:15:02 tlr: 2.7e-05 tnm: 0.75 Lm: 9.661 (9.642) Lt: 9.667 (9.652) Accm: 0.02 (0.02) Acct: 0.00 (0.01) proj_loss: -0.2997 (-0.2317) time: 0.9262 data: 0.0002 [11-22 16:36:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [1251/1669] eta: 0:15:02 tlr: 2.7e-05 tnm: 0.75 Lm: 9.660 (9.648) Lt: 9.666 (9.658) Accm: 0.03 (0.03) Acct: 0.02 (0.02) proj_loss: -0.3010 (-0.2331) time: 0.9263 data: 0.0002 [11-22 16:36:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [1251/1669] eta: 0:15:02 tlr: 2.7e-05 tnm: 0.75 Lm: 9.660 (9.645) Lt: 9.666 (9.658) Accm: 0.01 (0.02) Acct: 0.02 (0.02) proj_loss: -0.3188 (-0.2437) time: 0.9262 data: 0.0002 [11-22 16:36:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [1251/1669] eta: 0:15:02 tlr: 2.7e-05 tnm: 0.75 Lm: 9.662 (9.648) Lt: 9.664 (9.655) Accm: 0.01 (0.01) Acct: 0.00 (0.00) proj_loss: -0.3070 (-0.2352) time: 0.9263 data: 0.0002 [11-22 16:36:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [1251/1669] eta: 0:15:02 tlr: 2.7e-05 tnm: 0.75 Lm: 9.660 (9.642) Lt: 9.662 (9.649) Accm: 0.01 (0.02) Acct: 0.02 (0.03) proj_loss: -0.3041 (-0.2373) time: 0.9263 data: 0.0002 [11-22 16:36:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [1251/1669] eta: 0:15:02 tlr: 2.7e-05 tnm: 0.75 Lm: 9.660 (9.643) Lt: 9.666 (9.654) Accm: 0.02 (0.03) Acct: 0.02 (0.03) proj_loss: -0.3073 (-0.2353) time: 0.9263 data: 0.0002 [11-22 16:36:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [1251/1669] eta: 0:15:02 tlr: 2.7e-05 tnm: 0.75 Lm: 9.662 (9.645) Lt: 9.667 (9.656) Accm: 0.01 (0.01) Acct: 0.02 (0.02) proj_loss: -0.3070 (-0.2350) time: 0.9262 data: 0.0002 [11-22 16:36:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [1251/1669] eta: 0:15:02 tlr: 2.7e-05 tnm: 0.75 Lm: 9.662 (9.647) Lt: 9.666 (9.656) Accm: 0.01 (0.01) Acct: 0.00 (0.01) proj_loss: -0.3099 (-0.2399) time: 0.9263 data: 0.0003 [11-22 16:43:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [1668/1669] eta: 0:00:01 tlr: 3.5e-05 tnm: 2.25 Lm: 9.629 (9.580) Lt: 9.642 (9.601) Accm: 0.03 (0.04) Acct: 0.00 (0.03) proj_loss: -0.3290 (-0.2577) time: 0.9263 data: 0.0015 [11-22 16:43:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 0/350] Total time: 0:51:28 (1.851 s / it) [11-22 16:43:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [1668/1669] eta: 0:00:01 tlr: 3.5e-05 tnm: 2.25 Lm: 9.625 (9.577) Lt: 9.635 (9.596) Accm: 0.01 (0.02) Acct: 0.03 (0.03) proj_loss: -0.3276 (-0.2572) time: 0.9263 data: 0.0016 [11-22 16:43:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [1668/1669] eta: 0:00:01 tlr: 3.5e-05 tnm: 2.25 Lm: 9.629 (9.577) Lt: 9.642 (9.598) Accm: 0.01 (0.02) Acct: 0.03 (0.02) proj_loss: -0.3176 (-0.2551) time: 0.9263 data: 0.0018 [11-22 16:43:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [1668/1669] eta: 0:00:01 tlr: 3.5e-05 tnm: 2.25 Lm: 9.628 (9.576) Lt: 9.635 (9.595) Accm: 0.01 (0.03) Acct: 0.00 (0.02) proj_loss: -0.3258 (-0.2564) time: 0.9263 data: 0.0018 [11-22 16:43:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [1668/1669] eta: 0:00:01 tlr: 3.5e-05 tnm: 2.25 Lm: 9.624 (9.576) Lt: 9.639 (9.600) Accm: 0.03 (0.03) Acct: 0.03 (0.04) proj_loss: -0.3281 (-0.2529) time: 0.9263 data: 0.0015 [11-22 16:43:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [1668/1669] eta: 0:00:01 tlr: 3.5e-05 tnm: 2.25 Lm: 9.626 (9.571) Lt: 9.640 (9.591) Accm: 0.03 (0.04) Acct: 0.03 (0.06) proj_loss: -0.3128 (-0.2575) time: 0.9263 data: 0.0017 [11-22 16:43:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [1668/1669] eta: 0:00:01 tlr: 3.5e-05 tnm: 2.25 Lm: 9.628 (9.577) Lt: 9.641 (9.601) Accm: 0.04 (0.03) Acct: 0.03 (0.03) proj_loss: -0.3243 (-0.2566) time: 0.9263 data: 0.0019 [11-22 16:43:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 0/350] [1668/1669] eta: 0:00:01 tlr: 3.5e-05 tnm: 2.25 Lm: 9.627 (9.577) Lt: 9.641 (9.598) Accm: 0.03 (0.04) Acct: 0.00 (0.01) proj_loss: -0.3156 (-0.2512) time: 0.9263 data: 0.0018 [11-22 16:43:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 0/350] Total time: 0:51:28 (1.851 s / it) [11-22 16:43:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 0/350] Total time: 0:51:27 (1.850 s / it) [11-22 16:43:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 0/350] Total time: 0:51:28 (1.851 s / it) [11-22 16:43:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 0/350] Total time: 0:51:28 (1.851 s / it) [11-22 16:43:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 0/350] Total time: 0:51:28 (1.851 s / it) [11-22 16:43:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 0/350] Total time: 0:51:28 (1.851 s / it) [11-22 16:43:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 0/350] Total time: 0:51:28 (1.851 s / it) [11-22 16:43:20] (/home/user/VAR/train.py , line 276)=> [ep0] (training ) Lm: 9.577 (9.577), Lt: 9.599 (9.599), Acc m&t: 0.03 0.02, Remain: 6 days, 6:51:31, Finish: 2024-11-28 07:34 [11-22 16:43:20] (/home/user/VAR/train.py , line 276)=> [ep0] (training ) Lm: 9.577 (9.577), Lt: 9.599 (9.599), Acc m&t: 0.03 0.02, Remain: 6 days, 6:51:56, Finish: 2024-11-28 07:35 [11-22 16:43:20] (/home/user/VAR/train.py , line 276)=> [ep0] (training ) Lm: 9.577 (9.577), Lt: 9.599 (9.599), Acc m&t: 0.03 0.02, Remain: 6 days, 6:52:55, Finish: 2024-11-28 07:36 [11-22 16:43:20] (/home/user/VAR/train.py , line 276)=> [ep0] (training ) Lm: 9.577 (9.577), Lt: 9.599 (9.599), Acc m&t: 0.03 0.02, Remain: 6 days, 6:54:01, Finish: 2024-11-28 07:37 [11-22 16:43:20] (/home/user/VAR/train.py , line 276)=> [ep0] (training ) Lm: 9.577 (9.577), Lt: 9.599 (9.599), Acc m&t: 0.03 0.02, Remain: 6 days, 6:51:53, Finish: 2024-11-28 07:35 [11-22 16:43:20] (/home/user/VAR/train.py , line 276)=> [ep0] (training ) Lm: 9.577 (9.577), Lt: 9.599 (9.599), Acc m&t: 0.03 0.02, Remain: 6 days, 6:52:40, Finish: 2024-11-28 07:35 [11-22 16:43:20] (/home/user/VAR/train.py , line 276)=> [ep0] (training ) Lm: 9.577 (9.577), Lt: 9.599 (9.599), Acc m&t: 0.03 0.02, Remain: 6 days, 6:52:22, Finish: 2024-11-28 07:35 [11-22 16:43:20] (/home/user/VAR/train.py , line 276)=> [ep0] (training ) Lm: 9.577 (9.577), Lt: 9.599 (9.599), Acc m&t: 0.03 0.02, Remain: 6 days, 6:52:40, Finish: 2024-11-28 07:36 [11-22 16:43:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 0/1669] eta: 0:24:31 tlr: 3.5e-05 tnm: 1.60 Lm: 9.267 (9.267) Lt: 9.332 (9.332) Accm: 0.12 (0.12) Acct: 0.07 (0.07) proj_loss: -0.3357 (-0.3357) time: 0.8817 data: 0.0003 [11-22 16:43:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 0/1669] eta: 0:24:53 tlr: 3.5e-05 tnm: 1.60 Lm: 9.320 (9.320) Lt: 9.395 (9.395) Accm: 0.03 (0.03) Acct: 0.03 (0.03) proj_loss: -0.3453 (-0.3453) time: 0.8951 data: 0.0003 [11-22 16:43:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 0/1669] eta: 0:24:53 tlr: 3.5e-05 tnm: 1.60 Lm: 9.295 (9.295) Lt: 9.394 (9.394) Accm: 0.06 (0.06) Acct: 0.00 (0.00) proj_loss: -0.3195 (-0.3195) time: 0.8950 data: 0.0003 [11-22 16:43:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 0/1669] eta: 0:24:53 tlr: 3.5e-05 tnm: 1.60 Lm: 9.282 (9.282) Lt: 9.344 (9.344) Accm: 0.07 (0.07) Acct: 0.07 (0.07) proj_loss: -0.3382 (-0.3382) time: 0.8951 data: 0.0005 [11-22 16:43:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 0/1669] eta: 0:24:54 tlr: 3.5e-05 tnm: 1.60 Lm: 9.271 (9.271) Lt: 9.340 (9.340) Accm: 0.09 (0.09) Acct: 0.07 (0.07) proj_loss: -0.3458 (-0.3458) time: 0.8952 data: 0.0004 [11-22 16:43:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 0/1669] eta: 0:24:54 tlr: 3.5e-05 tnm: 1.60 Lm: 9.275 (9.275) Lt: 9.336 (9.336) Accm: 0.06 (0.06) Acct: 0.03 (0.03) proj_loss: -0.3238 (-0.3238) time: 0.8954 data: 0.0003 [11-22 16:43:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 0/1669] eta: 0:24:53 tlr: 3.5e-05 tnm: 1.60 Lm: 9.298 (9.298) Lt: 9.353 (9.353) Accm: 0.10 (0.10) Acct: 0.07 (0.07) proj_loss: -0.3240 (-0.3240) time: 0.8950 data: 0.0004 [11-22 16:43:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 0/1669] eta: 0:24:54 tlr: 3.5e-05 tnm: 1.60 Lm: 9.297 (9.297) Lt: 9.352 (9.352) Accm: 0.03 (0.03) Acct: 0.00 (0.00) proj_loss: -0.3108 (-0.3108) time: 0.8956 data: 0.0005 [11-22 16:49:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 417/1669] eta: 0:19:39 tlr: 4.4e-05 tnm: 1.99 Lm: 8.895 (8.895) Lt: 8.847 (8.847) Accm: 0.22 (0.22) Acct: 0.28 (0.28) proj_loss: -0.3208 (-0.3208) time: 0.9245 data: 0.0003 [11-22 16:49:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 417/1669] eta: 0:19:39 tlr: 4.4e-05 tnm: 1.99 Lm: 8.869 (8.869) Lt: 8.805 (8.805) Accm: 0.25 (0.25) Acct: 0.36 (0.36) proj_loss: -0.3209 (-0.3209) time: 0.9245 data: 0.0003 [11-22 16:49:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 417/1669] eta: 0:19:39 tlr: 4.4e-05 tnm: 1.99 Lm: 8.880 (8.880) Lt: 8.817 (8.817) Accm: 0.25 (0.25) Acct: 0.41 (0.41) proj_loss: -0.3311 (-0.3311) time: 0.9245 data: 0.0002 [11-22 16:49:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 417/1669] eta: 0:19:39 tlr: 4.4e-05 tnm: 1.99 Lm: 8.838 (8.838) Lt: 8.775 (8.775) Accm: 0.20 (0.20) Acct: 0.22 (0.22) proj_loss: -0.3426 (-0.3426) time: 0.9245 data: 0.0003 [11-22 16:49:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 417/1669] eta: 0:19:39 tlr: 4.4e-05 tnm: 1.99 Lm: 8.867 (8.867) Lt: 8.821 (8.821) Accm: 0.25 (0.25) Acct: 0.34 (0.34) proj_loss: -0.3233 (-0.3233) time: 0.9245 data: 0.0003 [11-22 16:49:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 417/1669] eta: 0:19:39 tlr: 4.4e-05 tnm: 1.99 Lm: 8.855 (8.855) Lt: 8.794 (8.794) Accm: 0.27 (0.27) Acct: 0.38 (0.38) proj_loss: -0.3414 (-0.3414) time: 0.9245 data: 0.0003 [11-22 16:49:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 417/1669] eta: 0:19:39 tlr: 4.4e-05 tnm: 1.99 Lm: 8.863 (8.863) Lt: 8.787 (8.787) Accm: 0.24 (0.24) Acct: 0.21 (0.21) proj_loss: -0.3233 (-0.3233) time: 0.9245 data: 0.0003 [11-22 16:49:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 417/1669] eta: 0:19:39 tlr: 4.4e-05 tnm: 1.99 Lm: 8.893 (8.893) Lt: 8.849 (8.849) Accm: 0.25 (0.25) Acct: 0.21 (0.21) proj_loss: -0.3362 (-0.3362) time: 0.9245 data: 0.0003 [11-22 16:56:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 834/1669] eta: 0:12:59 tlr: 5.2e-05 tnm: 1.64 Lm: 8.439 (8.647) Lt: 8.248 (8.514) Accm: 0.41 (0.32) Acct: 0.62 (0.46) proj_loss: -0.3384 (-0.3404) time: 0.9247 data: 0.0003 [11-22 16:56:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 834/1669] eta: 0:12:59 tlr: 5.2e-05 tnm: 1.64 Lm: 8.408 (8.649) Lt: 8.219 (8.511) Accm: 0.28 (0.27) Acct: 0.38 (0.33) proj_loss: -0.3357 (-0.3362) time: 0.9247 data: 0.0003 [11-22 16:56:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 834/1669] eta: 0:12:59 tlr: 5.2e-05 tnm: 1.64 Lm: 8.493 (8.686) Lt: 8.342 (8.564) Accm: 0.41 (0.30) Acct: 0.55 (0.39) proj_loss: -0.3308 (-0.3262) time: 0.9247 data: 0.0003 [11-22 16:56:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 834/1669] eta: 0:12:59 tlr: 5.2e-05 tnm: 1.64 Lm: 8.463 (8.684) Lt: 8.274 (8.568) Accm: 0.44 (0.32) Acct: 0.52 (0.41) proj_loss: -0.3238 (-0.3249) time: 0.9247 data: 0.0003 [11-22 16:56:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 834/1669] eta: 0:12:59 tlr: 5.2e-05 tnm: 1.64 Lm: 8.427 (8.661) Lt: 8.221 (8.524) Accm: 0.38 (0.38) Acct: 0.34 (0.46) proj_loss: -0.3233 (-0.3233) time: 0.9247 data: 0.0002 [11-22 16:56:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 834/1669] eta: 0:12:59 tlr: 5.2e-05 tnm: 1.64 Lm: 8.478 (8.662) Lt: 8.290 (8.545) Accm: 0.44 (0.32) Acct: 0.52 (0.45) proj_loss: -0.3382 (-0.3343) time: 0.9247 data: 0.0003 [11-22 16:56:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 834/1669] eta: 0:12:59 tlr: 5.2e-05 tnm: 1.64 Lm: 8.439 (8.648) Lt: 8.249 (8.524) Accm: 0.45 (0.39) Acct: 0.69 (0.53) proj_loss: -0.3195 (-0.3181) time: 0.9247 data: 0.0003 [11-22 16:56:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [ 834/1669] eta: 0:12:59 tlr: 5.2e-05 tnm: 1.64 Lm: 8.466 (8.692) Lt: 8.302 (8.566) Accm: 0.47 (0.37) Acct: 0.38 (0.48) proj_loss: -0.3285 (-0.3336) time: 0.9248 data: 0.0003 [11-22 17:02:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [1251/1669] eta: 0:06:29 tlr: 6.1e-05 tnm: 1.73 Lm: 8.378 (8.553) Lt: 8.151 (8.389) Accm: 0.54 (0.43) Acct: 0.53 (0.53) proj_loss: -0.3321 (-0.3342) time: 0.9291 data: 0.0003 [11-22 17:02:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [1251/1669] eta: 0:06:29 tlr: 6.1e-05 tnm: 1.73 Lm: 8.381 (8.561) Lt: 8.169 (8.390) Accm: 0.43 (0.38) Acct: 0.59 (0.53) proj_loss: -0.3340 (-0.3304) time: 0.9291 data: 0.0002 [11-22 17:02:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [1251/1669] eta: 0:06:29 tlr: 6.1e-05 tnm: 1.73 Lm: 8.343 (8.530) Lt: 8.109 (8.364) Accm: 0.50 (0.44) Acct: 0.53 (0.53) proj_loss: -0.3236 (-0.3278) time: 0.9291 data: 0.0003 [11-22 17:02:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [1251/1669] eta: 0:06:29 tlr: 6.1e-05 tnm: 1.73 Lm: 8.335 (8.530) Lt: 8.101 (8.360) Accm: 0.43 (0.43) Acct: 0.65 (0.61) proj_loss: -0.3377 (-0.3384) time: 0.9291 data: 0.0003 [11-22 17:02:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [1251/1669] eta: 0:06:29 tlr: 6.1e-05 tnm: 1.73 Lm: 8.325 (8.527) Lt: 8.088 (8.363) Accm: 0.52 (0.44) Acct: 0.72 (0.59) proj_loss: -0.3233 (-0.3212) time: 0.9291 data: 0.0003 [11-22 17:02:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [1251/1669] eta: 0:06:29 tlr: 6.1e-05 tnm: 1.73 Lm: 8.352 (8.548) Lt: 8.146 (8.387) Accm: 0.44 (0.39) Acct: 0.64 (0.57) proj_loss: -0.3366 (-0.3345) time: 0.9291 data: 0.0002 [11-22 17:02:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [1251/1669] eta: 0:06:29 tlr: 6.1e-05 tnm: 1.73 Lm: 8.340 (8.533) Lt: 8.101 (8.365) Accm: 0.35 (0.35) Acct: 0.46 (0.39) proj_loss: -0.3326 (-0.3346) time: 0.9291 data: 0.0002 [11-22 17:02:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [1251/1669] eta: 0:06:29 tlr: 6.1e-05 tnm: 1.73 Lm: 8.388 (8.557) Lt: 8.184 (8.390) Accm: 0.44 (0.38) Acct: 0.60 (0.53) proj_loss: -0.3283 (-0.3280) time: 0.9291 data: 0.0003 [11-22 17:09:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [1668/1669] eta: 0:00:00 tlr: 6.9e-05 tnm: 1.56 Lm: 8.313 (8.479) Lt: 8.093 (8.286) Accm: 0.45 (0.43) Acct: 0.69 (0.57) proj_loss: -0.3328 (-0.3303) time: 0.9270 data: 0.0019 [11-22 17:09:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 1/350] Total time: 0:25:50 (0.929 s / it) [11-22 17:09:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [1668/1669] eta: 0:00:00 tlr: 6.9e-05 tnm: 1.56 Lm: 8.211 (8.449) Lt: 7.928 (8.267) Accm: 0.58 (0.51) Acct: 0.76 (0.67) proj_loss: -0.3272 (-0.3294) time: 0.9270 data: 0.0018 [11-22 17:09:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [1668/1669] eta: 0:00:00 tlr: 6.9e-05 tnm: 1.56 Lm: 8.226 (8.477) Lt: 8.001 (8.287) Accm: 0.44 (0.43) Acct: 0.76 (0.64) proj_loss: -0.3382 (-0.3366) time: 0.9270 data: 0.0015 [11-22 17:09:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [1668/1669] eta: 0:00:00 tlr: 6.9e-05 tnm: 1.56 Lm: 8.291 (8.464) Lt: 7.999 (8.284) Accm: 0.61 (0.48) Acct: 0.69 (0.60) proj_loss: -0.3285 (-0.3327) time: 0.9270 data: 0.0020 [11-22 17:09:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [1668/1669] eta: 0:00:00 tlr: 6.9e-05 tnm: 1.56 Lm: 8.258 (8.459) Lt: 7.997 (8.262) Accm: 0.63 (0.49) Acct: 0.72 (0.62) proj_loss: -0.3240 (-0.3297) time: 0.9270 data: 0.0019 [11-22 17:09:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [1668/1669] eta: 0:00:00 tlr: 6.9e-05 tnm: 1.56 Lm: 8.271 (8.455) Lt: 7.984 (8.255) Accm: 0.42 (0.39) Acct: 0.55 (0.42) proj_loss: -0.3296 (-0.3333) time: 0.9270 data: 0.0016 [11-22 17:09:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [1668/1669] eta: 0:00:00 tlr: 6.9e-05 tnm: 1.56 Lm: 8.269 (8.462) Lt: 7.997 (8.265) Accm: 0.45 (0.45) Acct: 0.62 (0.61) proj_loss: -0.3371 (-0.3355) time: 0.9269 data: 0.0017 [11-22 17:09:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 1/350] [1668/1669] eta: 0:00:00 tlr: 6.9e-05 tnm: 1.56 Lm: 8.231 (8.457) Lt: 7.954 (8.272) Accm: 0.45 (0.47) Acct: 0.69 (0.65) proj_loss: -0.3370 (-0.3376) time: 0.9270 data: 0.0016 [11-22 17:09:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 1/350] Total time: 0:25:50 (0.929 s / it) [11-22 17:09:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 1/350] Total time: 0:25:50 (0.929 s / it) [11-22 17:09:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 1/350] Total time: 0:25:50 (0.929 s / it) [11-22 17:09:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 1/350] Total time: 0:25:50 (0.929 s / it) [11-22 17:09:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 1/350] Total time: 0:25:50 (0.929 s / it) [11-22 17:09:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 1/350] Total time: 0:25:50 (0.929 s / it) [11-22 17:09:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 1/350] Total time: 0:25:50 (0.929 s / it) [11-22 17:09:11] (/home/user/VAR/train.py , line 276)=> [ep1] (training ) Lm: 8.464 (8.464), Lt: 8.274 (8.274), Acc m&t: 0.47 0.62, Remain: 6 days, 6:39:10, Finish: 2024-11-28 07:48 [11-22 17:09:11] (/home/user/VAR/train.py , line 276)=> [ep1] (training ) Lm: 8.464 (8.464), Lt: 8.274 (8.274), Acc m&t: 0.47 0.62, Remain: 6 days, 6:37:38, Finish: 2024-11-28 07:46 [11-22 17:09:11] (/home/user/VAR/train.py , line 276)=> [ep1] (training ) Lm: 8.464 (8.464), Lt: 8.274 (8.274), Acc m&t: 0.47 0.62, Remain: 6 days, 6:38:03, Finish: 2024-11-28 07:47 [11-22 17:09:11] (/home/user/VAR/train.py , line 276)=> [ep1] (training ) Lm: 8.464 (8.464), Lt: 8.274 (8.274), Acc m&t: 0.47 0.62, Remain: 6 days, 6:42:50, Finish: 2024-11-28 07:52 [11-22 17:09:11] (/home/user/VAR/train.py , line 276)=> [ep1] (training ) Lm: 8.464 (8.464), Lt: 8.274 (8.274), Acc m&t: 0.47 0.62, Remain: 6 days, 6:38:04, Finish: 2024-11-28 07:47 [11-22 17:09:11] (/home/user/VAR/train.py , line 276)=> [ep1] (training ) Lm: 8.464 (8.464), Lt: 8.274 (8.274), Acc m&t: 0.47 0.62, Remain: 6 days, 6:38:57, Finish: 2024-11-28 07:48 [11-22 17:09:11] (/home/user/VAR/train.py , line 276)=> [ep1] (training ) Lm: 8.464 (8.464), Lt: 8.274 (8.274), Acc m&t: 0.47 0.62, Remain: 6 days, 6:39:58, Finish: 2024-11-28 07:49 [11-22 17:09:11] (/home/user/VAR/train.py , line 276)=> [ep1] (training ) Lm: 8.464 (8.464), Lt: 8.274 (8.274), Acc m&t: 0.47 0.62, Remain: 6 days, 6:40:55, Finish: 2024-11-28 07:50 [11-22 17:09:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 0/1669] eta: 0:24:53 tlr: 6.9e-05 tnm: 1.74 Lm: 8.105 (8.105) Lt: 7.799 (7.799) Accm: 0.79 (0.79) Acct: 1.07 (1.07) proj_loss: -0.3570 (-0.3570) time: 0.8949 data: 0.0003 [11-22 17:09:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 0/1669] eta: 0:24:53 tlr: 6.9e-05 tnm: 1.74 Lm: 8.075 (8.075) Lt: 7.761 (7.761) Accm: 0.60 (0.60) Acct: 0.90 (0.90) proj_loss: -0.3281 (-0.3281) time: 0.8948 data: 0.0004 [11-22 17:09:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 0/1669] eta: 0:24:53 tlr: 6.9e-05 tnm: 1.74 Lm: 8.115 (8.115) Lt: 7.828 (7.828) Accm: 0.60 (0.60) Acct: 0.79 (0.79) proj_loss: -0.3506 (-0.3506) time: 0.8950 data: 0.0004 [11-22 17:09:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 0/1669] eta: 0:24:53 tlr: 6.9e-05 tnm: 1.74 Lm: 8.189 (8.189) Lt: 7.904 (7.904) Accm: 0.58 (0.58) Acct: 0.86 (0.86) proj_loss: -0.3329 (-0.3329) time: 0.8950 data: 0.0004 [11-22 17:09:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 0/1669] eta: 0:24:52 tlr: 6.9e-05 tnm: 1.74 Lm: 8.063 (8.063) Lt: 7.730 (7.730) Accm: 0.70 (0.70) Acct: 0.86 (0.86) proj_loss: -0.3422 (-0.3422) time: 0.8940 data: 0.0004 [11-22 17:09:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 0/1669] eta: 0:24:53 tlr: 6.9e-05 tnm: 1.74 Lm: 8.056 (8.056) Lt: 7.771 (7.771) Accm: 0.70 (0.70) Acct: 0.83 (0.83) proj_loss: -0.3397 (-0.3397) time: 0.8947 data: 0.0003 [11-22 17:09:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 0/1669] eta: 0:24:54 tlr: 6.9e-05 tnm: 1.74 Lm: 8.205 (8.205) Lt: 7.938 (7.938) Accm: 0.48 (0.48) Acct: 0.69 (0.69) proj_loss: -0.3302 (-0.3302) time: 0.8952 data: 0.0003 [11-22 17:09:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 0/1669] eta: 0:24:54 tlr: 6.9e-05 tnm: 1.74 Lm: 8.183 (8.183) Lt: 7.890 (7.890) Accm: 0.63 (0.63) Acct: 0.90 (0.90) proj_loss: -0.3209 (-0.3209) time: 0.8953 data: 0.0004 [11-22 17:15:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 417/1669] eta: 0:19:17 tlr: 7.8e-05 tnm: 1.50 Lm: 8.130 (8.130) Lt: 7.831 (7.831) Accm: 0.62 (0.62) Acct: 0.93 (0.93) proj_loss: -0.3321 (-0.3321) time: 0.9224 data: 0.0003 [11-22 17:15:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 417/1669] eta: 0:19:17 tlr: 7.8e-05 tnm: 1.50 Lm: 8.095 (8.095) Lt: 7.787 (7.787) Accm: 0.52 (0.52) Acct: 0.79 (0.79) proj_loss: -0.3443 (-0.3443) time: 0.9224 data: 0.0003 [11-22 17:15:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 417/1669] eta: 0:19:17 tlr: 7.8e-05 tnm: 1.50 Lm: 8.053 (8.053) Lt: 7.782 (7.782) Accm: 0.70 (0.70) Acct: 0.83 (0.83) proj_loss: -0.3442 (-0.3442) time: 0.9224 data: 0.0003 [11-22 17:15:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 417/1669] eta: 0:19:17 tlr: 7.8e-05 tnm: 1.50 Lm: 8.081 (8.081) Lt: 7.783 (7.783) Accm: 0.60 (0.60) Acct: 0.79 (0.79) proj_loss: -0.3459 (-0.3459) time: 0.9224 data: 0.0003 [11-22 17:15:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 417/1669] eta: 0:19:17 tlr: 7.8e-05 tnm: 1.50 Lm: 8.058 (8.058) Lt: 7.731 (7.731) Accm: 0.81 (0.81) Acct: 1.19 (1.19) proj_loss: -0.3606 (-0.3606) time: 0.9224 data: 0.0003 [11-22 17:15:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 417/1669] eta: 0:19:17 tlr: 7.8e-05 tnm: 1.50 Lm: 8.137 (8.137) Lt: 7.868 (7.868) Accm: 0.71 (0.71) Acct: 0.95 (0.95) proj_loss: -0.3469 (-0.3469) time: 0.9224 data: 0.0003 [11-22 17:15:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 417/1669] eta: 0:19:17 tlr: 7.8e-05 tnm: 1.50 Lm: 8.064 (8.064) Lt: 7.784 (7.784) Accm: 0.71 (0.71) Acct: 0.86 (0.86) proj_loss: -0.3445 (-0.3445) time: 0.9224 data: 0.0003 [11-22 17:15:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 417/1669] eta: 0:19:17 tlr: 7.8e-05 tnm: 1.50 Lm: 8.167 (8.167) Lt: 7.893 (7.893) Accm: 0.57 (0.57) Acct: 0.79 (0.79) proj_loss: -0.3356 (-0.3356) time: 0.9224 data: 0.0003 [11-22 17:22:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 834/1669] eta: 0:12:52 tlr: 8.6e-05 tnm: 1.34 Lm: 8.129 (8.126) Lt: 7.847 (7.838) Accm: 0.66 (0.61) Acct: 0.90 (0.83) proj_loss: -0.3410 (-0.3448) time: 0.9241 data: 0.0003 [11-22 17:22:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 834/1669] eta: 0:12:52 tlr: 8.6e-05 tnm: 1.34 Lm: 8.056 (8.072) Lt: 7.751 (7.772) Accm: 0.60 (0.66) Acct: 0.79 (0.91) proj_loss: -0.3506 (-0.3487) time: 0.9241 data: 0.0003 [11-22 17:22:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 834/1669] eta: 0:12:52 tlr: 8.6e-05 tnm: 1.34 Lm: 8.086 (8.114) Lt: 7.832 (7.838) Accm: 0.61 (0.68) Acct: 0.86 (0.88) proj_loss: -0.3548 (-0.3495) time: 0.9241 data: 0.0003 [11-22 17:22:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 834/1669] eta: 0:12:52 tlr: 8.6e-05 tnm: 1.34 Lm: 8.105 (8.078) Lt: 7.799 (7.775) Accm: 0.79 (0.75) Acct: 1.07 (1.10) proj_loss: -0.3643 (-0.3641) time: 0.9241 data: 0.0003 [11-22 17:22:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 834/1669] eta: 0:12:52 tlr: 8.6e-05 tnm: 1.34 Lm: 8.075 (8.078) Lt: 7.761 (7.776) Accm: 0.60 (0.61) Acct: 0.90 (0.83) proj_loss: -0.3596 (-0.3494) time: 0.9241 data: 0.0003 [11-22 17:22:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 834/1669] eta: 0:12:52 tlr: 8.6e-05 tnm: 1.34 Lm: 8.066 (8.065) Lt: 7.796 (7.788) Accm: 0.70 (0.69) Acct: 0.83 (0.79) proj_loss: -0.3486 (-0.3459) time: 0.9241 data: 0.0002 [11-22 17:22:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 834/1669] eta: 0:12:52 tlr: 8.6e-05 tnm: 1.34 Lm: 8.044 (8.040) Lt: 7.730 (7.762) Accm: 0.70 (0.72) Acct: 0.86 (0.94) proj_loss: -0.3461 (-0.3474) time: 0.9241 data: 0.0002 [11-22 17:22:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [ 834/1669] eta: 0:12:52 tlr: 8.6e-05 tnm: 1.34 Lm: 8.078 (8.101) Lt: 7.772 (7.803) Accm: 0.61 (0.57) Acct: 0.90 (0.86) proj_loss: -0.3402 (-0.3348) time: 0.9241 data: 0.0003 [11-22 17:28:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [1251/1669] eta: 0:06:29 tlr: 9.5e-05 tnm: 1.25 Lm: 8.084 (8.098) Lt: 7.800 (7.809) Accm: 0.55 (0.54) Acct: 0.81 (0.79) proj_loss: -0.3417 (-0.3409) time: 0.9237 data: 0.0003 [11-22 17:28:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [1251/1669] eta: 0:06:29 tlr: 9.5e-05 tnm: 1.25 Lm: 8.101 (8.112) Lt: 7.812 (7.823) Accm: 0.66 (0.62) Acct: 0.90 (0.85) proj_loss: -0.3520 (-0.3505) time: 0.9237 data: 0.0003 [11-22 17:28:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [1251/1669] eta: 0:06:29 tlr: 9.5e-05 tnm: 1.25 Lm: 8.029 (8.034) Lt: 7.726 (7.745) Accm: 0.74 (0.78) Acct: 1.02 (1.12) proj_loss: -0.3500 (-0.3497) time: 0.9237 data: 0.0002 [11-22 17:28:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [1251/1669] eta: 0:06:29 tlr: 9.5e-05 tnm: 1.25 Lm: 8.060 (8.051) Lt: 7.758 (7.746) Accm: 0.68 (0.70) Acct: 0.90 (0.96) proj_loss: -0.3601 (-0.3540) time: 0.9237 data: 0.0003 [11-22 17:28:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [1251/1669] eta: 0:06:29 tlr: 9.5e-05 tnm: 1.25 Lm: 8.064 (8.064) Lt: 7.745 (7.754) Accm: 0.74 (0.74) Acct: 1.00 (1.01) proj_loss: -0.3606 (-0.3608) time: 0.9237 data: 0.0003 [11-22 17:28:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [1251/1669] eta: 0:06:29 tlr: 9.5e-05 tnm: 1.25 Lm: 8.065 (8.064) Lt: 7.793 (7.789) Accm: 0.68 (0.67) Acct: 0.84 (0.81) proj_loss: -0.3489 (-0.3496) time: 0.9237 data: 0.0002 [11-22 17:28:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [1251/1669] eta: 0:06:29 tlr: 9.5e-05 tnm: 1.25 Lm: 8.076 (8.095) Lt: 7.805 (7.811) Accm: 0.68 (0.70) Acct: 0.91 (0.90) proj_loss: -0.3579 (-0.3541) time: 0.9237 data: 0.0003 [11-22 17:28:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [1251/1669] eta: 0:06:29 tlr: 9.5e-05 tnm: 1.25 Lm: 8.060 (8.070) Lt: 7.751 (7.767) Accm: 0.60 (0.64) Acct: 0.79 (0.87) proj_loss: -0.3525 (-0.3550) time: 0.9237 data: 0.0003 [11-22 17:35:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [1668/1669] eta: 0:00:00 tlr: 0.0001 tnm: 1.12 Lm: 8.062 (8.069) Lt: 7.751 (7.762) Accm: 0.61 (0.64) Acct: 0.79 (0.87) proj_loss: -0.3506 (-0.3541) time: 0.9274 data: 0.0018 [11-22 17:35:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 2/350] Total time: 0:25:51 (0.930 s / it) [11-22 17:35:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [1668/1669] eta: 0:00:00 tlr: 0.0001 tnm: 1.12 Lm: 8.024 (8.052) Lt: 7.690 (7.733) Accm: 0.68 (0.73) Acct: 1.07 (1.02) proj_loss: -0.3643 (-0.3628) time: 0.9274 data: 0.0016 [11-22 17:35:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [1668/1669] eta: 0:00:00 tlr: 0.0001 tnm: 1.12 Lm: 8.078 (8.088) Lt: 7.772 (7.799) Accm: 0.61 (0.58) Acct: 0.90 (0.82) proj_loss: -0.3432 (-0.3471) time: 0.9274 data: 0.0017 [11-22 17:35:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [1668/1669] eta: 0:00:00 tlr: 0.0001 tnm: 1.12 Lm: 8.067 (8.063) Lt: 7.777 (7.780) Accm: 0.74 (0.75) Acct: 0.96 (1.01) proj_loss: -0.3609 (-0.3599) time: 0.9274 data: 0.0018 [11-22 17:35:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [1668/1669] eta: 0:00:00 tlr: 0.0001 tnm: 1.12 Lm: 8.046 (8.041) Lt: 7.756 (7.732) Accm: 0.60 (0.64) Acct: 0.90 (0.90) proj_loss: -0.3606 (-0.3564) time: 0.9274 data: 0.0018 [11-22 17:35:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [1668/1669] eta: 0:00:00 tlr: 0.0001 tnm: 1.12 Lm: 8.015 (8.021) Lt: 7.728 (7.741) Accm: 0.70 (0.73) Acct: 0.86 (1.03) proj_loss: -0.3540 (-0.3532) time: 0.9274 data: 0.0016 [11-22 17:35:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [1668/1669] eta: 0:00:00 tlr: 0.0001 tnm: 1.12 Lm: 8.073 (8.095) Lt: 7.777 (7.805) Accm: 0.67 (0.64) Acct: 0.90 (0.93) proj_loss: -0.3631 (-0.3548) time: 0.9274 data: 0.0016 [11-22 17:35:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 2/350] [1668/1669] eta: 0:00:00 tlr: 0.0001 tnm: 1.12 Lm: 8.064 (8.052) Lt: 7.791 (7.770) Accm: 0.70 (0.71) Acct: 0.86 (0.87) proj_loss: -0.3493 (-0.3527) time: 0.9274 data: 0.0016 [11-22 17:35:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 2/350] Total time: 0:25:51 (0.930 s / it) [11-22 17:35:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 2/350] Total time: 0:25:51 (0.930 s / it) [11-22 17:35:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 2/350] Total time: 0:25:51 (0.930 s / it) [11-22 17:35:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 2/350] Total time: 0:25:51 (0.930 s / it) [11-22 17:35:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 2/350] Total time: 0:25:51 (0.930 s / it) [11-22 17:35:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 2/350] Total time: 0:25:51 (0.930 s / it) [11-22 17:35:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 2/350] Total time: 0:25:51 (0.930 s / it) [11-22 17:35:03] (/home/user/VAR/train.py , line 276)=> [ep2] (training ) Lm: 8.051 (8.051), Lt: 7.756 (7.756), Acc m&t: 0.70 0.96, Remain: 6 days, 6:20:32, Finish: 2024-11-28 07:55 [11-22 17:35:03] (/home/user/VAR/train.py , line 276)=> [ep2] (training ) Lm: 8.051 (8.051), Lt: 7.756 (7.756), Acc m&t: 0.70 0.96, Remain: 6 days, 6:19:59, Finish: 2024-11-28 07:55 [11-22 17:35:03] (/home/user/VAR/train.py , line 276)=> [ep2] (training ) Lm: 8.051 (8.051), Lt: 7.756 (7.756), Acc m&t: 0.70 0.96, Remain: 6 days, 6:18:42, Finish: 2024-11-28 07:53 [11-22 17:35:03] (/home/user/VAR/train.py , line 276)=> [ep2] (training ) Lm: 8.051 (8.051), Lt: 7.756 (7.756), Acc m&t: 0.70 0.96, Remain: 6 days, 6:20:10, Finish: 2024-11-28 07:55 [11-22 17:35:03] (/home/user/VAR/train.py , line 276)=> [ep2] (training ) Lm: 8.051 (8.051), Lt: 7.756 (7.756), Acc m&t: 0.70 0.96, Remain: 6 days, 6:19:24, Finish: 2024-11-28 07:54 [11-22 17:35:03] (/home/user/VAR/train.py , line 276)=> [ep2] (training ) Lm: 8.051 (8.051), Lt: 7.756 (7.756), Acc m&t: 0.70 0.96, Remain: 6 days, 6:21:20, Finish: 2024-11-28 07:56 [11-22 17:35:03] (/home/user/VAR/train.py , line 276)=> [ep2] (training ) Lm: 8.051 (8.051), Lt: 7.756 (7.756), Acc m&t: 0.70 0.96, Remain: 6 days, 6:20:06, Finish: 2024-11-28 07:55 [11-22 17:35:03] (/home/user/VAR/train.py , line 276)=> [ep2] (training ) Lm: 8.051 (8.051), Lt: 7.756 (7.756), Acc m&t: 0.70 0.96, Remain: 6 days, 6:19:09, Finish: 2024-11-28 07:54 [11-22 17:35:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 0/1669] eta: 0:25:28 tlr: 0.0001 tnm: 1.23 Lm: 8.001 (8.001) Lt: 7.712 (7.712) Accm: 0.68 (0.68) Acct: 0.69 (0.69) proj_loss: -0.3836 (-0.3836) time: 0.9157 data: 0.0003 [11-22 17:35:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 0/1669] eta: 0:25:30 tlr: 0.0001 tnm: 1.23 Lm: 7.987 (7.987) Lt: 7.676 (7.676) Accm: 0.68 (0.68) Acct: 0.93 (0.93) proj_loss: -0.3739 (-0.3739) time: 0.9168 data: 0.0003 [11-22 17:35:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 0/1669] eta: 0:25:30 tlr: 0.0001 tnm: 1.23 Lm: 7.969 (7.969) Lt: 7.639 (7.639) Accm: 0.99 (0.99) Acct: 1.38 (1.38) proj_loss: -0.3745 (-0.3745) time: 0.9168 data: 0.0003 [11-22 17:35:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 0/1669] eta: 0:25:28 tlr: 0.0001 tnm: 1.23 Lm: 8.049 (8.049) Lt: 7.796 (7.796) Accm: 0.82 (0.82) Acct: 0.96 (0.96) proj_loss: -0.3798 (-0.3798) time: 0.9160 data: 0.0003 [11-22 17:35:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 0/1669] eta: 0:25:30 tlr: 0.0001 tnm: 1.23 Lm: 7.979 (7.979) Lt: 7.674 (7.674) Accm: 0.77 (0.77) Acct: 1.00 (1.00) proj_loss: -0.3730 (-0.3730) time: 0.9167 data: 0.0004 [11-22 17:35:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 0/1669] eta: 0:25:30 tlr: 0.0001 tnm: 1.23 Lm: 7.984 (7.984) Lt: 7.663 (7.663) Accm: 0.63 (0.63) Acct: 0.83 (0.83) proj_loss: -0.3719 (-0.3719) time: 0.9170 data: 0.0004 [11-22 17:35:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 0/1669] eta: 0:25:30 tlr: 0.0001 tnm: 1.23 Lm: 7.931 (7.931) Lt: 7.650 (7.650) Accm: 0.76 (0.76) Acct: 1.03 (1.03) proj_loss: -0.3813 (-0.3813) time: 0.9172 data: 0.0004 [11-22 17:35:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 0/1669] eta: 0:25:31 tlr: 0.0001 tnm: 1.23 Lm: 7.889 (7.889) Lt: 7.529 (7.529) Accm: 0.93 (0.93) Acct: 1.34 (1.34) proj_loss: -0.3779 (-0.3779) time: 0.9174 data: 0.0003 [11-22 17:41:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 417/1669] eta: 0:19:17 tlr: 0.00011 tnm: 0.91 Lm: 7.935 (7.935) Lt: 7.606 (7.606) Accm: 0.84 (0.84) Acct: 1.17 (1.17) proj_loss: -0.3806 (-0.3806) time: 0.9264 data: 0.0003 [11-22 17:41:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 417/1669] eta: 0:19:17 tlr: 0.00011 tnm: 0.91 Lm: 7.935 (7.935) Lt: 7.610 (7.610) Accm: 0.75 (0.75) Acct: 1.03 (1.03) proj_loss: -0.3751 (-0.3751) time: 0.9264 data: 0.0003 [11-22 17:41:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 417/1669] eta: 0:19:17 tlr: 0.00011 tnm: 0.91 Lm: 7.975 (7.975) Lt: 7.654 (7.654) Accm: 0.86 (0.86) Acct: 1.19 (1.19) proj_loss: -0.3796 (-0.3796) time: 0.9264 data: 0.0003 [11-22 17:41:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 417/1669] eta: 0:19:17 tlr: 0.00011 tnm: 0.91 Lm: 7.992 (7.992) Lt: 7.719 (7.719) Accm: 0.82 (0.82) Acct: 1.10 (1.10) proj_loss: -0.3809 (-0.3809) time: 0.9264 data: 0.0002 [11-22 17:41:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 417/1669] eta: 0:19:17 tlr: 0.00011 tnm: 0.91 Lm: 7.969 (7.969) Lt: 7.670 (7.670) Accm: 0.76 (0.76) Acct: 0.98 (0.98) proj_loss: -0.3788 (-0.3788) time: 0.9264 data: 0.0003 [11-22 17:41:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 417/1669] eta: 0:19:17 tlr: 0.00011 tnm: 0.91 Lm: 8.003 (8.003) Lt: 7.722 (7.722) Accm: 0.66 (0.66) Acct: 0.77 (0.77) proj_loss: -0.3755 (-0.3755) time: 0.9264 data: 0.0003 [11-22 17:41:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 417/1669] eta: 0:19:17 tlr: 0.00011 tnm: 0.91 Lm: 7.966 (7.966) Lt: 7.672 (7.672) Accm: 0.63 (0.63) Acct: 0.79 (0.79) proj_loss: -0.3765 (-0.3765) time: 0.9264 data: 0.0003 [11-22 17:41:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 417/1669] eta: 0:19:17 tlr: 0.00011 tnm: 0.91 Lm: 7.970 (7.970) Lt: 7.683 (7.683) Accm: 0.74 (0.74) Acct: 1.08 (1.08) proj_loss: -0.3812 (-0.3812) time: 0.9265 data: 0.0003 [11-22 17:47:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 834/1669] eta: 0:12:52 tlr: 0.00012 tnm: 0.96 Lm: 7.961 (7.946) Lt: 7.674 (7.652) Accm: 0.76 (0.74) Acct: 1.17 (1.14) proj_loss: -0.3894 (-0.3880) time: 0.9266 data: 0.0003 [11-22 17:47:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 834/1669] eta: 0:12:52 tlr: 0.00012 tnm: 0.96 Lm: 7.984 (7.952) Lt: 7.663 (7.634) Accm: 0.87 (0.79) Acct: 1.07 (1.04) proj_loss: -0.3783 (-0.3765) time: 0.9266 data: 0.0003 [11-22 17:47:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 834/1669] eta: 0:12:52 tlr: 0.00012 tnm: 0.96 Lm: 7.931 (7.941) Lt: 7.650 (7.625) Accm: 0.73 (0.67) Acct: 1.03 (0.87) proj_loss: -0.3813 (-0.3840) time: 0.9266 data: 0.0003 [11-22 17:47:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 834/1669] eta: 0:12:52 tlr: 0.00012 tnm: 0.96 Lm: 7.889 (7.917) Lt: 7.568 (7.593) Accm: 0.93 (0.88) Acct: 1.34 (1.26) proj_loss: -0.3779 (-0.3737) time: 0.9266 data: 0.0003 [11-22 17:47:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 834/1669] eta: 0:12:52 tlr: 0.00012 tnm: 0.96 Lm: 7.934 (7.911) Lt: 7.642 (7.623) Accm: 0.83 (0.86) Acct: 1.17 (1.12) proj_loss: -0.3819 (-0.3849) time: 0.9266 data: 0.0002 [11-22 17:47:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 834/1669] eta: 0:12:52 tlr: 0.00012 tnm: 0.96 Lm: 7.951 (7.920) Lt: 7.664 (7.617) Accm: 0.84 (0.84) Acct: 1.03 (1.11) proj_loss: -0.3838 (-0.3842) time: 0.9266 data: 0.0003 [11-22 17:47:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 834/1669] eta: 0:12:52 tlr: 0.00012 tnm: 0.96 Lm: 8.001 (7.929) Lt: 7.712 (7.636) Accm: 0.68 (0.77) Acct: 0.86 (1.00) proj_loss: -0.3836 (-0.3840) time: 0.9266 data: 0.0002 [11-22 17:47:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [ 834/1669] eta: 0:12:52 tlr: 0.00012 tnm: 0.96 Lm: 7.969 (7.940) Lt: 7.639 (7.621) Accm: 0.89 (0.87) Acct: 1.24 (1.21) proj_loss: -0.3846 (-0.3863) time: 0.9266 data: 0.0003 [11-22 17:54:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.92 Lm: 7.923 (7.925) Lt: 7.641 (7.627) Accm: 0.94 (0.91) Acct: 1.29 (1.24) proj_loss: -0.3921 (-0.3934) time: 0.9763 data: 0.0003 [11-22 17:54:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.92 Lm: 7.935 (7.917) Lt: 7.640 (7.627) Accm: 0.86 (0.87) Acct: 1.21 (1.19) proj_loss: -0.3874 (-0.3915) time: 0.9763 data: 0.0002 [11-22 17:54:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.92 Lm: 7.959 (7.947) Lt: 7.624 (7.622) Accm: 0.82 (0.78) Acct: 1.15 (1.09) proj_loss: -0.3787 (-0.3815) time: 0.9763 data: 0.0002 [11-22 17:54:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.92 Lm: 7.961 (7.932) Lt: 7.640 (7.617) Accm: 0.89 (0.86) Acct: 1.02 (1.08) proj_loss: -0.3825 (-0.3835) time: 0.9763 data: 0.0003 [11-22 17:54:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.92 Lm: 7.898 (7.895) Lt: 7.587 (7.587) Accm: 0.76 (0.79) Acct: 1.07 (1.07) proj_loss: -0.3921 (-0.3881) time: 0.9763 data: 0.0002 [11-22 17:54:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.92 Lm: 7.885 (7.908) Lt: 7.559 (7.582) Accm: 0.92 (0.89) Acct: 1.36 (1.29) proj_loss: -0.3806 (-0.3800) time: 0.9763 data: 0.0003 [11-22 17:54:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.92 Lm: 7.965 (7.952) Lt: 7.679 (7.660) Accm: 0.73 (0.70) Acct: 1.08 (1.04) proj_loss: -0.3954 (-0.3949) time: 0.9763 data: 0.0003 [11-22 17:54:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.92 Lm: 7.951 (7.948) Lt: 7.666 (7.640) Accm: 0.68 (0.66) Acct: 0.98 (0.89) proj_loss: -0.3842 (-0.3848) time: 0.9763 data: 0.0003 [11-22 18:01:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.87 Lm: 7.931 (7.925) Lt: 7.650 (7.618) Accm: 0.73 (0.71) Acct: 1.03 (0.97) proj_loss: -0.3872 (-0.3906) time: 0.9299 data: 0.0019 [11-22 18:01:02] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 3/350] Total time: 0:25:58 (0.934 s / it) [11-22 18:01:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.87 Lm: 7.951 (7.914) Lt: 7.616 (7.600) Accm: 0.89 (0.87) Acct: 1.03 (1.07) proj_loss: -0.3838 (-0.3890) time: 0.9299 data: 0.0018 [11-22 18:01:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.87 Lm: 7.933 (7.914) Lt: 7.585 (7.578) Accm: 0.87 (0.84) Acct: 1.24 (1.23) proj_loss: -0.3792 (-0.3847) time: 0.9299 data: 0.0015 [11-22 18:01:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.87 Lm: 7.917 (7.923) Lt: 7.639 (7.625) Accm: 0.89 (0.87) Acct: 1.24 (1.21) proj_loss: -0.3996 (-0.4010) time: 0.9299 data: 0.0016 [11-22 18:01:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.87 Lm: 7.961 (7.938) Lt: 7.674 (7.640) Accm: 0.76 (0.72) Acct: 1.17 (1.07) proj_loss: -0.4014 (-0.3969) time: 0.9299 data: 0.0020 [11-22 18:01:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.87 Lm: 7.934 (7.914) Lt: 7.637 (7.620) Accm: 0.83 (0.85) Acct: 1.17 (1.16) proj_loss: -0.3930 (-0.3937) time: 0.9299 data: 0.0015 [11-22 18:01:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.87 Lm: 7.881 (7.901) Lt: 7.550 (7.572) Accm: 0.90 (0.86) Acct: 1.34 (1.22) proj_loss: -0.3834 (-0.3927) time: 0.9299 data: 0.0015 [11-22 18:01:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 3/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.87 Lm: 7.835 (7.883) Lt: 7.546 (7.578) Accm: 0.84 (0.80) Acct: 1.14 (1.08) proj_loss: -0.4006 (-0.3948) time: 0.9299 data: 0.0018 [11-22 18:01:02] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 3/350] Total time: 0:25:58 (0.934 s / it) [11-22 18:01:02] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 3/350] Total time: 0:25:58 (0.934 s / it) [11-22 18:01:02] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 3/350] Total time: 0:25:58 (0.934 s / it) [11-22 18:01:02] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 3/350] Total time: 0:25:58 (0.934 s / it) [11-22 18:01:02] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 3/350] Total time: 0:25:58 (0.934 s / it) [11-22 18:01:02] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 3/350] Total time: 0:25:58 (0.934 s / it) [11-22 18:01:02] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 3/350] Total time: 0:25:58 (0.934 s / it) [11-22 18:01:02] (/home/user/VAR/train.py , line 276)=> [ep3] (training ) Lm: 7.915 (7.915), Lt: 7.608 (7.608), Acc m&t: 0.82 1.11, Remain: 6 days, 6:23:55, Finish: 2024-11-28 08:24 [11-22 18:01:02] (/home/user/VAR/train.py , line 276)=> [ep3] (training ) Lm: 7.915 (7.915), Lt: 7.608 (7.608), Acc m&t: 0.82 1.11, Remain: 6 days, 6:22:09, Finish: 2024-11-28 08:23 [11-22 18:01:02] (/home/user/VAR/train.py , line 276)=> [ep3] (training ) Lm: 7.915 (7.915), Lt: 7.608 (7.608), Acc m&t: 0.82 1.11, Remain: 6 days, 6:21:59, Finish: 2024-11-28 08:23 [11-22 18:01:02] (/home/user/VAR/train.py , line 276)=> [ep3] (training ) Lm: 7.915 (7.915), Lt: 7.608 (7.608), Acc m&t: 0.82 1.11, Remain: 6 days, 6:22:12, Finish: 2024-11-28 08:23 [11-22 18:01:02] (/home/user/VAR/train.py , line 276)=> [ep3] (training ) Lm: 7.915 (7.915), Lt: 7.608 (7.608), Acc m&t: 0.82 1.11, Remain: 6 days, 6:21:39, Finish: 2024-11-28 08:22 [11-22 18:01:02] (/home/user/VAR/train.py , line 276)=> [ep3] (training ) Lm: 7.915 (7.915), Lt: 7.608 (7.608), Acc m&t: 0.82 1.11, Remain: 6 days, 6:24:04, Finish: 2024-11-28 08:25 [11-22 18:01:02] (/home/user/VAR/train.py , line 276)=> [ep3] (training ) Lm: 7.915 (7.915), Lt: 7.608 (7.608), Acc m&t: 0.82 1.11, Remain: 6 days, 6:21:13, Finish: 2024-11-28 08:22 [11-22 18:01:02] (/home/user/VAR/train.py , line 276)=> [ep3] (training ) Lm: 7.915 (7.915), Lt: 7.608 (7.608), Acc m&t: 0.82 1.11, Remain: 6 days, 6:21:50, Finish: 2024-11-28 08:22 [11-22 18:01:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 0/1669] eta: 0:25:22 tlr: 0.00014 tnm: 0.86 Lm: 7.866 (7.866) Lt: 7.558 (7.558) Accm: 0.83 (0.83) Acct: 1.00 (1.00) proj_loss: -0.4194 (-0.4194) time: 0.9123 data: 0.0003 [11-22 18:01:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 0/1669] eta: 0:25:23 tlr: 0.00014 tnm: 0.86 Lm: 7.932 (7.932) Lt: 7.616 (7.616) Accm: 0.79 (0.79) Acct: 1.17 (1.17) proj_loss: -0.3950 (-0.3950) time: 0.9129 data: 0.0004 [11-22 18:01:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 0/1669] eta: 0:25:23 tlr: 0.00014 tnm: 0.86 Lm: 7.956 (7.956) Lt: 7.672 (7.672) Accm: 0.80 (0.80) Acct: 0.79 (0.79) proj_loss: -0.4010 (-0.4010) time: 0.9128 data: 0.0004 [11-22 18:01:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 0/1669] eta: 0:25:23 tlr: 0.00014 tnm: 0.86 Lm: 7.731 (7.731) Lt: 7.409 (7.409) Accm: 0.96 (0.96) Acct: 1.38 (1.38) proj_loss: -0.4281 (-0.4281) time: 0.9129 data: 0.0003 [11-22 18:01:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 0/1669] eta: 0:25:23 tlr: 0.00014 tnm: 0.86 Lm: 7.863 (7.863) Lt: 7.560 (7.560) Accm: 0.90 (0.90) Acct: 1.41 (1.41) proj_loss: -0.4308 (-0.4308) time: 0.9129 data: 0.0004 [11-22 18:01:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 0/1669] eta: 0:25:23 tlr: 0.00014 tnm: 0.86 Lm: 7.838 (7.838) Lt: 7.534 (7.534) Accm: 0.95 (0.95) Acct: 1.52 (1.52) proj_loss: -0.4190 (-0.4190) time: 0.9128 data: 0.0004 [11-22 18:01:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 0/1669] eta: 0:25:23 tlr: 0.00014 tnm: 0.86 Lm: 8.017 (8.017) Lt: 7.745 (7.745) Accm: 0.70 (0.70) Acct: 0.90 (0.90) proj_loss: -0.4432 (-0.4432) time: 0.9128 data: 0.0004 [11-22 18:01:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 0/1669] eta: 0:25:24 tlr: 0.00014 tnm: 0.86 Lm: 7.925 (7.925) Lt: 7.630 (7.630) Accm: 0.89 (0.89) Acct: 1.41 (1.41) proj_loss: -0.4334 (-0.4334) time: 0.9132 data: 0.0004 [11-22 18:07:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.96 Lm: 7.899 (7.899) Lt: 7.596 (7.596) Accm: 0.82 (0.82) Acct: 1.15 (1.15) proj_loss: -0.4244 (-0.4244) time: 0.9233 data: 0.0003 [11-22 18:07:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.96 Lm: 7.912 (7.912) Lt: 7.638 (7.638) Accm: 0.75 (0.75) Acct: 0.93 (0.93) proj_loss: -0.4403 (-0.4403) time: 0.9233 data: 0.0003 [11-22 18:07:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.96 Lm: 7.862 (7.862) Lt: 7.553 (7.553) Accm: 0.84 (0.84) Acct: 1.24 (1.24) proj_loss: -0.4307 (-0.4307) time: 0.9233 data: 0.0003 [11-22 18:07:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.96 Lm: 7.880 (7.880) Lt: 7.575 (7.575) Accm: 0.81 (0.81) Acct: 1.00 (1.00) proj_loss: -0.4267 (-0.4267) time: 0.9233 data: 0.0002 [11-22 18:07:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.96 Lm: 7.829 (7.829) Lt: 7.543 (7.543) Accm: 0.90 (0.90) Acct: 1.05 (1.05) proj_loss: -0.4145 (-0.4145) time: 0.9233 data: 0.0003 [11-22 18:07:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.96 Lm: 7.777 (7.777) Lt: 7.466 (7.466) Accm: 0.87 (0.87) Acct: 1.21 (1.21) proj_loss: -0.4190 (-0.4190) time: 0.9233 data: 0.0003 [11-22 18:07:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.96 Lm: 7.787 (7.787) Lt: 7.491 (7.491) Accm: 1.00 (1.00) Acct: 1.48 (1.48) proj_loss: -0.4277 (-0.4277) time: 0.9233 data: 0.0003 [11-22 18:07:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.96 Lm: 7.852 (7.852) Lt: 7.527 (7.527) Accm: 0.95 (0.95) Acct: 1.50 (1.50) proj_loss: -0.4277 (-0.4277) time: 0.9233 data: 0.0003 [11-22 18:13:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.79 Lm: 7.859 (7.854) Lt: 7.534 (7.547) Accm: 0.95 (0.92) Acct: 1.48 (1.39) proj_loss: -0.4323 (-0.4293) time: 0.9266 data: 0.0002 [11-22 18:13:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.79 Lm: 7.848 (7.807) Lt: 7.560 (7.517) Accm: 0.90 (0.95) Acct: 1.41 (1.30) proj_loss: -0.4247 (-0.4227) time: 0.9266 data: 0.0002 [11-22 18:13:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.79 Lm: 7.866 (7.827) Lt: 7.558 (7.525) Accm: 0.83 (0.91) Acct: 1.00 (1.12) proj_loss: -0.4340 (-0.4346) time: 0.9266 data: 0.0003 [11-22 18:13:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.79 Lm: 7.823 (7.828) Lt: 7.522 (7.513) Accm: 0.77 (0.84) Acct: 1.14 (1.18) proj_loss: -0.4098 (-0.4071) time: 0.9266 data: 0.0002 [11-22 18:13:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.79 Lm: 7.733 (7.797) Lt: 7.431 (7.506) Accm: 0.87 (0.89) Acct: 1.17 (1.09) proj_loss: -0.4193 (-0.4161) time: 0.9266 data: 0.0002 [11-22 18:13:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.79 Lm: 7.793 (7.799) Lt: 7.491 (7.467) Accm: 0.89 (0.89) Acct: 1.27 (1.25) proj_loss: -0.4217 (-0.4277) time: 0.9266 data: 0.0003 [11-22 18:13:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.79 Lm: 7.872 (7.881) Lt: 7.561 (7.553) Accm: 0.84 (0.83) Acct: 1.10 (1.14) proj_loss: -0.4155 (-0.4197) time: 0.9266 data: 0.0003 [11-22 18:13:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.79 Lm: 7.852 (7.892) Lt: 7.531 (7.599) Accm: 0.80 (0.80) Acct: 0.96 (1.06) proj_loss: -0.4381 (-0.4395) time: 0.9266 data: 0.0003 [11-22 18:20:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.67 Lm: 7.829 (7.855) Lt: 7.526 (7.532) Accm: 0.85 (0.84) Acct: 1.12 (1.11) proj_loss: -0.4377 (-0.4321) time: 0.9250 data: 0.0003 [11-22 18:20:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.67 Lm: 7.863 (7.860) Lt: 7.560 (7.561) Accm: 0.95 (0.95) Acct: 1.50 (1.44) proj_loss: -0.4339 (-0.4308) time: 0.9250 data: 0.0002 [11-22 18:20:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.67 Lm: 7.870 (7.878) Lt: 7.550 (7.549) Accm: 0.87 (0.85) Acct: 1.21 (1.18) proj_loss: -0.4242 (-0.4230) time: 0.9250 data: 0.0003 [11-22 18:20:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.67 Lm: 7.780 (7.762) Lt: 7.491 (7.467) Accm: 1.00 (1.03) Acct: 1.41 (1.33) proj_loss: -0.4277 (-0.4312) time: 0.9250 data: 0.0002 [11-22 18:20:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.67 Lm: 7.793 (7.790) Lt: 7.491 (7.491) Accm: 0.89 (0.92) Acct: 1.12 (1.15) proj_loss: -0.4323 (-0.4336) time: 0.9250 data: 0.0003 [11-22 18:20:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.67 Lm: 7.739 (7.784) Lt: 7.422 (7.478) Accm: 0.84 (0.85) Acct: 1.14 (1.09) proj_loss: -0.4236 (-0.4212) time: 0.9250 data: 0.0003 [11-22 18:20:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.67 Lm: 7.821 (7.826) Lt: 7.505 (7.507) Accm: 0.87 (0.88) Acct: 1.26 (1.24) proj_loss: -0.4188 (-0.4123) time: 0.9250 data: 0.0002 [11-22 18:20:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.67 Lm: 7.748 (7.775) Lt: 7.433 (7.444) Accm: 0.95 (0.95) Acct: 1.29 (1.28) proj_loss: -0.4367 (-0.4337) time: 0.9250 data: 0.0002 [11-22 18:26:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.67 Lm: 7.722 (7.764) Lt: 7.399 (7.435) Accm: 1.01 (0.99) Acct: 1.31 (1.29) proj_loss: -0.4319 (-0.4333) time: 0.9281 data: 0.0020 [11-22 18:26:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 4/350] Total time: 0:25:43 (0.925 s / it) [11-22 18:26:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.67 Lm: 7.711 (7.736) Lt: 7.422 (7.439) Accm: 0.98 (1.02) Acct: 1.41 (1.32) proj_loss: -0.4308 (-0.4328) time: 0.9281 data: 0.0016 [11-22 18:26:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.67 Lm: 7.807 (7.796) Lt: 7.522 (7.458) Accm: 0.90 (0.91) Acct: 1.27 (1.18) proj_loss: -0.4381 (-0.4340) time: 0.9281 data: 0.0017 [11-22 18:26:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.67 Lm: 7.859 (7.828) Lt: 7.534 (7.523) Accm: 0.96 (0.98) Acct: 1.52 (1.48) proj_loss: -0.4354 (-0.4324) time: 0.9281 data: 0.0016 [11-22 18:26:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.67 Lm: 7.745 (7.788) Lt: 7.431 (7.474) Accm: 0.87 (0.86) Acct: 1.17 (1.18) proj_loss: -0.4279 (-0.4225) time: 0.9281 data: 0.0018 [11-22 18:26:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.67 Lm: 7.820 (7.753) Lt: 7.487 (7.421) Accm: 0.96 (0.92) Acct: 1.38 (1.30) proj_loss: -0.4277 (-0.4167) time: 0.9281 data: 0.0016 [11-22 18:26:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.67 Lm: 7.727 (7.777) Lt: 7.425 (7.470) Accm: 0.95 (0.94) Acct: 1.24 (1.23) proj_loss: -0.4305 (-0.4318) time: 0.9281 data: 0.0019 [11-22 18:26:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 4/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.67 Lm: 7.869 (7.831) Lt: 7.539 (7.491) Accm: 0.89 (0.92) Acct: 1.31 (1.26) proj_loss: -0.4329 (-0.4285) time: 0.9281 data: 0.0018 [11-22 18:26:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 4/350] Total time: 0:25:43 (0.925 s / it) [11-22 18:26:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 4/350] Total time: 0:25:43 (0.925 s / it) [11-22 18:26:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 4/350] Total time: 0:25:43 (0.925 s / it) [11-22 18:26:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 4/350] Total time: 0:25:43 (0.925 s / it) [11-22 18:26:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 4/350] Total time: 0:25:43 (0.925 s / it) [11-22 18:26:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 4/350] Total time: 0:25:43 (0.925 s / it) [11-22 18:26:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 4/350] Total time: 0:25:43 (0.925 s / it) [11-22 18:26:46] (/home/user/VAR/train.py , line 276)=> [ep4] (training ) Lm: 7.774 (7.774), Lt: 7.451 (7.451), Acc m&t: 0.95 1.29, Remain: 6 days, 5:25:46, Finish: 2024-11-28 07:52 [11-22 18:26:46] (/home/user/VAR/train.py , line 276)=> [ep4] (training ) Lm: 7.774 (7.774), Lt: 7.451 (7.451), Acc m&t: 0.95 1.29, Remain: 6 days, 5:26:36, Finish: 2024-11-28 07:53 [11-22 18:26:46] (/home/user/VAR/train.py , line 276)=> [ep4] (training ) Lm: 7.774 (7.774), Lt: 7.451 (7.451), Acc m&t: 0.95 1.29, Remain: 6 days, 5:28:39, Finish: 2024-11-28 07:55 [11-22 18:26:46] (/home/user/VAR/train.py , line 276)=> [ep4] (training ) Lm: 7.774 (7.774), Lt: 7.451 (7.451), Acc m&t: 0.95 1.29, Remain: 6 days, 5:27:30, Finish: 2024-11-28 07:54 [11-22 18:26:46] (/home/user/VAR/train.py , line 276)=> [ep4] (training ) Lm: 7.774 (7.774), Lt: 7.451 (7.451), Acc m&t: 0.95 1.29, Remain: 6 days, 5:25:18, Finish: 2024-11-28 07:52 [11-22 18:26:46] (/home/user/VAR/train.py , line 276)=> [ep4] (training ) Lm: 7.774 (7.774), Lt: 7.451 (7.451), Acc m&t: 0.95 1.29, Remain: 6 days, 5:27:10, Finish: 2024-11-28 07:53 [11-22 18:26:46] (/home/user/VAR/train.py , line 276)=> [ep4] (training ) Lm: 7.774 (7.774), Lt: 7.451 (7.451), Acc m&t: 0.95 1.29, Remain: 6 days, 5:27:21, Finish: 2024-11-28 07:54 [11-22 18:26:46] (/home/user/VAR/train.py , line 276)=> [ep4] (training ) Lm: 7.774 (7.774), Lt: 7.451 (7.451), Acc m&t: 0.95 1.29, Remain: 6 days, 5:24:43, Finish: 2024-11-28 07:51 [11-22 18:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 0/1669] eta: 0:25:35 tlr: 0.00017 tnm: 0.71 Lm: 7.719 (7.719) Lt: 7.411 (7.411) Accm: 0.99 (0.99) Acct: 1.27 (1.27) proj_loss: -0.4482 (-0.4482) time: 0.9199 data: 0.0003 [11-22 18:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 0/1669] eta: 0:25:35 tlr: 0.00017 tnm: 0.71 Lm: 7.497 (7.497) Lt: 7.190 (7.190) Accm: 1.41 (1.41) Acct: 1.86 (1.86) proj_loss: -0.4637 (-0.4637) time: 0.9199 data: 0.0004 [11-22 18:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 0/1669] eta: 0:25:36 tlr: 0.00017 tnm: 0.71 Lm: 7.647 (7.647) Lt: 7.273 (7.273) Accm: 1.03 (1.03) Acct: 1.38 (1.38) proj_loss: -0.4332 (-0.4332) time: 0.9204 data: 0.0004 [11-22 18:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 0/1669] eta: 0:25:34 tlr: 0.00017 tnm: 0.71 Lm: 7.779 (7.779) Lt: 7.472 (7.472) Accm: 0.93 (0.93) Acct: 1.55 (1.55) proj_loss: -0.4266 (-0.4266) time: 0.9193 data: 0.0004 [11-22 18:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 0/1669] eta: 0:25:35 tlr: 0.00017 tnm: 0.71 Lm: 7.621 (7.621) Lt: 7.293 (7.293) Accm: 0.96 (0.96) Acct: 1.17 (1.17) proj_loss: -0.4385 (-0.4385) time: 0.9203 data: 0.0003 [11-22 18:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 0/1669] eta: 0:25:36 tlr: 0.00017 tnm: 0.71 Lm: 7.699 (7.699) Lt: 7.397 (7.397) Accm: 0.92 (0.92) Acct: 1.21 (1.21) proj_loss: -0.4328 (-0.4328) time: 0.9205 data: 0.0004 [11-22 18:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 0/1669] eta: 0:25:36 tlr: 0.00017 tnm: 0.71 Lm: 7.739 (7.739) Lt: 7.395 (7.395) Accm: 0.90 (0.90) Acct: 1.21 (1.21) proj_loss: -0.4233 (-0.4233) time: 0.9207 data: 0.0003 [11-22 18:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 0/1669] eta: 0:25:36 tlr: 0.00017 tnm: 0.71 Lm: 7.600 (7.600) Lt: 7.290 (7.290) Accm: 1.25 (1.25) Acct: 1.65 (1.65) proj_loss: -0.4629 (-0.4629) time: 0.9204 data: 0.0004 [11-22 18:33:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 417/1669] eta: 0:19:21 tlr: 0.00018 tnm: 0.67 Lm: 7.633 (7.633) Lt: 7.285 (7.285) Accm: 1.16 (1.16) Acct: 1.48 (1.48) proj_loss: -0.4561 (-0.4561) time: 0.9633 data: 0.0002 [11-22 18:33:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 417/1669] eta: 0:19:21 tlr: 0.00018 tnm: 0.67 Lm: 7.644 (7.644) Lt: 7.279 (7.279) Accm: 1.06 (1.06) Acct: 1.36 (1.36) proj_loss: -0.4438 (-0.4438) time: 0.9633 data: 0.0002 [11-22 18:33:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 417/1669] eta: 0:19:21 tlr: 0.00018 tnm: 0.67 Lm: 7.698 (7.698) Lt: 7.341 (7.341) Accm: 0.87 (0.87) Acct: 1.15 (1.15) proj_loss: -0.4515 (-0.4515) time: 0.9632 data: 0.0003 [11-22 18:33:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 417/1669] eta: 0:19:21 tlr: 0.00018 tnm: 0.67 Lm: 7.670 (7.670) Lt: 7.301 (7.301) Accm: 1.00 (1.00) Acct: 1.34 (1.34) proj_loss: -0.4286 (-0.4286) time: 0.9633 data: 0.0002 [11-22 18:33:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 417/1669] eta: 0:19:21 tlr: 0.00018 tnm: 0.67 Lm: 7.524 (7.524) Lt: 7.197 (7.197) Accm: 1.29 (1.29) Acct: 1.69 (1.69) proj_loss: -0.4516 (-0.4516) time: 0.9632 data: 0.0003 [11-22 18:33:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 417/1669] eta: 0:19:21 tlr: 0.00018 tnm: 0.67 Lm: 7.683 (7.683) Lt: 7.370 (7.370) Accm: 1.01 (1.01) Acct: 1.43 (1.43) proj_loss: -0.4507 (-0.4507) time: 0.9632 data: 0.0003 [11-22 18:33:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 417/1669] eta: 0:19:21 tlr: 0.00018 tnm: 0.67 Lm: 7.635 (7.635) Lt: 7.290 (7.290) Accm: 1.05 (1.05) Acct: 1.43 (1.43) proj_loss: -0.4375 (-0.4375) time: 0.9632 data: 0.0003 [11-22 18:33:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 417/1669] eta: 0:19:21 tlr: 0.00018 tnm: 0.67 Lm: 7.661 (7.661) Lt: 7.323 (7.323) Accm: 1.17 (1.17) Acct: 1.74 (1.74) proj_loss: -0.4440 (-0.4440) time: 0.9633 data: 0.0003 [11-22 18:39:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.63 Lm: 7.633 (7.652) Lt: 7.214 (7.287) Accm: 1.06 (1.14) Acct: 1.55 (1.65) proj_loss: -0.4266 (-0.4335) time: 0.9232 data: 0.0003 [11-22 18:39:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.63 Lm: 7.677 (7.636) Lt: 7.270 (7.281) Accm: 0.99 (1.03) Acct: 1.27 (1.40) proj_loss: -0.4548 (-0.4585) time: 0.9232 data: 0.0002 [11-22 18:39:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.63 Lm: 7.601 (7.635) Lt: 7.206 (7.248) Accm: 1.09 (1.13) Acct: 1.48 (1.52) proj_loss: -0.4338 (-0.4326) time: 0.9232 data: 0.0002 [11-22 18:39:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.63 Lm: 7.497 (7.498) Lt: 7.190 (7.137) Accm: 1.33 (1.30) Acct: 1.86 (1.74) proj_loss: -0.4475 (-0.4502) time: 0.9232 data: 0.0003 [11-22 18:39:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.63 Lm: 7.600 (7.613) Lt: 7.280 (7.257) Accm: 1.25 (1.20) Acct: 1.65 (1.54) proj_loss: -0.4629 (-0.4627) time: 0.9232 data: 0.0002 [11-22 18:39:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.63 Lm: 7.650 (7.643) Lt: 7.287 (7.279) Accm: 0.96 (0.98) Acct: 1.34 (1.40) proj_loss: -0.4364 (-0.4360) time: 0.9232 data: 0.0003 [11-22 18:39:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.63 Lm: 7.668 (7.632) Lt: 7.342 (7.282) Accm: 1.11 (1.16) Acct: 1.65 (1.68) proj_loss: -0.4474 (-0.4496) time: 0.9232 data: 0.0003 [11-22 18:39:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.63 Lm: 7.647 (7.651) Lt: 7.285 (7.281) Accm: 1.03 (1.04) Acct: 1.38 (1.48) proj_loss: -0.4435 (-0.4437) time: 0.9232 data: 0.0002 [11-22 18:46:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [1251/1669] eta: 0:06:30 tlr: 0.0002 tnm: 0.66 Lm: 7.648 (7.651) Lt: 7.279 (7.254) Accm: 1.06 (1.07) Acct: 1.46 (1.50) proj_loss: -0.4388 (-0.4413) time: 0.9266 data: 0.0002 [11-22 18:46:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [1251/1669] eta: 0:06:30 tlr: 0.0002 tnm: 0.66 Lm: 7.524 (7.512) Lt: 7.187 (7.149) Accm: 1.25 (1.26) Acct: 1.81 (1.75) proj_loss: -0.4556 (-0.4543) time: 0.9266 data: 0.0003 [11-22 18:46:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [1251/1669] eta: 0:06:30 tlr: 0.0002 tnm: 0.66 Lm: 7.583 (7.581) Lt: 7.175 (7.193) Accm: 1.23 (1.19) Acct: 1.65 (1.59) proj_loss: -0.4372 (-0.4402) time: 0.9266 data: 0.0002 [11-22 18:46:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [1251/1669] eta: 0:06:30 tlr: 0.0002 tnm: 0.66 Lm: 7.589 (7.625) Lt: 7.197 (7.260) Accm: 1.12 (1.15) Acct: 1.52 (1.59) proj_loss: -0.4414 (-0.4391) time: 0.9266 data: 0.0002 [11-22 18:46:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [1251/1669] eta: 0:06:30 tlr: 0.0002 tnm: 0.66 Lm: 7.650 (7.645) Lt: 7.274 (7.274) Accm: 1.01 (1.00) Acct: 1.33 (1.38) proj_loss: -0.4375 (-0.4388) time: 0.9266 data: 0.0003 [11-22 18:46:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [1251/1669] eta: 0:06:30 tlr: 0.0002 tnm: 0.66 Lm: 7.586 (7.587) Lt: 7.241 (7.208) Accm: 1.27 (1.24) Acct: 1.65 (1.70) proj_loss: -0.4561 (-0.4543) time: 0.9266 data: 0.0003 [11-22 18:46:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [1251/1669] eta: 0:06:30 tlr: 0.0002 tnm: 0.66 Lm: 7.598 (7.563) Lt: 7.224 (7.202) Accm: 1.28 (1.27) Acct: 1.77 (1.73) proj_loss: -0.4526 (-0.4517) time: 0.9266 data: 0.0003 [11-22 18:46:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [1251/1669] eta: 0:06:30 tlr: 0.0002 tnm: 0.66 Lm: 7.594 (7.583) Lt: 7.216 (7.221) Accm: 1.17 (1.22) Acct: 1.58 (1.70) proj_loss: -0.4562 (-0.4583) time: 0.9266 data: 0.0003 [11-22 18:52:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.70 Lm: 7.579 (7.582) Lt: 7.161 (7.206) Accm: 1.02 (1.18) Acct: 1.41 (1.64) proj_loss: -0.4577 (-0.4607) time: 0.9265 data: 0.0019 [11-22 18:52:43] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 5/350] Total time: 0:25:57 (0.933 s / it) [11-22 18:52:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.70 Lm: 7.647 (7.620) Lt: 7.273 (7.212) Accm: 1.08 (1.12) Acct: 1.55 (1.65) proj_loss: -0.4435 (-0.4432) time: 0.9264 data: 0.0015 [11-22 18:52:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.70 Lm: 7.565 (7.533) Lt: 7.143 (7.129) Accm: 1.37 (1.31) Acct: 1.83 (1.80) proj_loss: -0.4405 (-0.4424) time: 0.9264 data: 0.0016 [11-22 18:52:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.70 Lm: 7.573 (7.543) Lt: 7.202 (7.143) Accm: 1.30 (1.27) Acct: 1.65 (1.73) proj_loss: -0.4629 (-0.4588) time: 0.9264 data: 0.0019 [11-22 18:52:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.70 Lm: 7.545 (7.586) Lt: 7.180 (7.207) Accm: 1.18 (1.21) Acct: 1.55 (1.68) proj_loss: -0.4561 (-0.4444) time: 0.9265 data: 0.0018 [11-22 18:52:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.70 Lm: 7.649 (7.606) Lt: 7.260 (7.230) Accm: 1.06 (1.09) Acct: 1.34 (1.48) proj_loss: -0.4385 (-0.4451) time: 0.9265 data: 0.0017 [11-22 18:52:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.70 Lm: 7.539 (7.518) Lt: 7.185 (7.133) Accm: 1.17 (1.21) Acct: 1.76 (1.67) proj_loss: -0.4475 (-0.4489) time: 0.9265 data: 0.0019 [11-22 18:52:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 5/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.70 Lm: 7.528 (7.543) Lt: 7.106 (7.162) Accm: 1.37 (1.29) Acct: 1.89 (1.87) proj_loss: -0.4474 (-0.4493) time: 0.9265 data: 0.0017 [11-22 18:52:43] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 5/350] Total time: 0:25:57 (0.933 s / it) [11-22 18:52:43] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 5/350] Total time: 0:25:57 (0.933 s / it) [11-22 18:52:43] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 5/350] Total time: 0:25:57 (0.933 s / it) [11-22 18:52:43] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 5/350] Total time: 0:25:57 (0.933 s / it) [11-22 18:52:43] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 5/350] Total time: 0:25:57 (0.933 s / it) [11-22 18:52:43] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 5/350] Total time: 0:25:57 (0.933 s / it) [11-22 18:52:43] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 5/350] Total time: 0:25:57 (0.933 s / it) [11-22 18:52:43] (/home/user/VAR/train.py , line 276)=> [ep5] (training ) Lm: 7.579 (7.579), Lt: 7.185 (7.185), Acc m&t: 1.18 1.67, Remain: 6 days, 4:28:53, Finish: 2024-11-28 07:21 [11-22 18:52:43] (/home/user/VAR/train.py , line 276)=> [ep5] (training ) Lm: 7.579 (7.579), Lt: 7.185 (7.185), Acc m&t: 1.18 1.67, Remain: 6 days, 4:27:33, Finish: 2024-11-28 07:20 [11-22 18:52:43] (/home/user/VAR/train.py , line 276)=> [ep5] (training ) Lm: 7.579 (7.579), Lt: 7.185 (7.185), Acc m&t: 1.18 1.67, Remain: 6 days, 4:28:16, Finish: 2024-11-28 07:20 [11-22 18:52:43] (/home/user/VAR/train.py , line 276)=> [ep5] (training ) Lm: 7.579 (7.579), Lt: 7.185 (7.185), Acc m&t: 1.18 1.67, Remain: 6 days, 4:26:55, Finish: 2024-11-28 07:19 [11-22 18:52:43] (/home/user/VAR/train.py , line 276)=> [ep5] (training ) Lm: 7.579 (7.579), Lt: 7.185 (7.185), Acc m&t: 1.18 1.67, Remain: 6 days, 4:25:59, Finish: 2024-11-28 07:18 [11-22 18:52:43] (/home/user/VAR/train.py , line 276)=> [ep5] (training ) Lm: 7.579 (7.579), Lt: 7.185 (7.185), Acc m&t: 1.18 1.67, Remain: 6 days, 4:25:35, Finish: 2024-11-28 07:18 [11-22 18:52:43] (/home/user/VAR/train.py , line 276)=> [ep5] (training ) Lm: 7.579 (7.579), Lt: 7.185 (7.185), Acc m&t: 1.18 1.67, Remain: 6 days, 4:27:03, Finish: 2024-11-28 07:19 [11-22 18:52:43] (/home/user/VAR/train.py , line 276)=> [ep5] (training ) Lm: 7.579 (7.579), Lt: 7.185 (7.185), Acc m&t: 1.18 1.67, Remain: 6 days, 4:28:15, Finish: 2024-11-28 07:20 [11-22 18:52:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 0/1669] eta: 0:24:36 tlr: 0.00021 tnm: 0.65 Lm: 7.466 (7.466) Lt: 6.999 (6.999) Accm: 1.24 (1.24) Acct: 1.62 (1.62) proj_loss: -0.4431 (-0.4431) time: 0.8849 data: 0.0004 [11-22 18:52:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 0/1669] eta: 0:24:37 tlr: 0.00021 tnm: 0.65 Lm: 7.535 (7.535) Lt: 7.131 (7.131) Accm: 1.38 (1.38) Acct: 1.86 (1.86) proj_loss: -0.4216 (-0.4216) time: 0.8851 data: 0.0004 [11-22 18:52:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 0/1669] eta: 0:24:37 tlr: 0.00021 tnm: 0.65 Lm: 7.504 (7.504) Lt: 7.060 (7.060) Accm: 1.30 (1.30) Acct: 1.89 (1.89) proj_loss: -0.4483 (-0.4483) time: 0.8853 data: 0.0003 [11-22 18:52:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 0/1669] eta: 0:24:37 tlr: 0.00021 tnm: 0.65 Lm: 7.426 (7.426) Lt: 7.004 (7.004) Accm: 1.14 (1.14) Acct: 1.86 (1.86) proj_loss: -0.4591 (-0.4591) time: 0.8854 data: 0.0003 [11-22 18:52:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 0/1669] eta: 0:24:37 tlr: 0.00021 tnm: 0.65 Lm: 7.485 (7.485) Lt: 6.972 (6.972) Accm: 1.38 (1.38) Acct: 2.24 (2.24) proj_loss: -0.4269 (-0.4269) time: 0.8853 data: 0.0004 [11-22 18:52:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 0/1669] eta: 0:24:38 tlr: 0.00021 tnm: 0.65 Lm: 7.415 (7.415) Lt: 6.951 (6.951) Accm: 1.56 (1.56) Acct: 2.20 (2.20) proj_loss: -0.4404 (-0.4404) time: 0.8856 data: 0.0004 [11-22 18:52:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 0/1669] eta: 0:24:38 tlr: 0.00021 tnm: 0.65 Lm: 7.425 (7.425) Lt: 6.929 (6.929) Accm: 1.52 (1.52) Acct: 2.07 (2.07) proj_loss: -0.4525 (-0.4525) time: 0.8856 data: 0.0004 [11-22 18:52:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 0/1669] eta: 0:24:39 tlr: 0.00021 tnm: 0.65 Lm: 7.433 (7.433) Lt: 7.003 (7.003) Accm: 1.33 (1.33) Acct: 1.72 (1.72) proj_loss: -0.4364 (-0.4364) time: 0.8866 data: 0.0003 [11-22 18:59:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 417/1669] eta: 0:19:17 tlr: 0.00021 tnm: 0.65 Lm: 7.312 (7.312) Lt: 6.879 (6.879) Accm: 1.62 (1.62) Acct: 2.00 (2.00) proj_loss: -0.4449 (-0.4449) time: 0.9224 data: 0.0002 [11-22 18:59:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 417/1669] eta: 0:19:17 tlr: 0.00021 tnm: 0.65 Lm: 7.486 (7.486) Lt: 7.073 (7.073) Accm: 1.38 (1.38) Acct: 1.83 (1.83) proj_loss: -0.4474 (-0.4474) time: 0.9224 data: 0.0003 [11-22 18:59:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 417/1669] eta: 0:19:17 tlr: 0.00021 tnm: 0.65 Lm: 7.425 (7.425) Lt: 6.967 (6.967) Accm: 1.43 (1.43) Acct: 2.15 (2.15) proj_loss: -0.4466 (-0.4466) time: 0.9224 data: 0.0002 [11-22 18:59:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 417/1669] eta: 0:19:17 tlr: 0.00021 tnm: 0.65 Lm: 7.427 (7.427) Lt: 6.956 (6.956) Accm: 1.20 (1.20) Acct: 1.69 (1.69) proj_loss: -0.4535 (-0.4535) time: 0.9224 data: 0.0003 [11-22 18:59:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 417/1669] eta: 0:19:17 tlr: 0.00021 tnm: 0.65 Lm: 7.410 (7.410) Lt: 6.955 (6.955) Accm: 1.53 (1.53) Acct: 2.17 (2.17) proj_loss: -0.4494 (-0.4494) time: 0.9224 data: 0.0002 [11-22 18:59:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 417/1669] eta: 0:19:17 tlr: 0.00021 tnm: 0.65 Lm: 7.425 (7.425) Lt: 6.964 (6.964) Accm: 1.21 (1.21) Acct: 1.89 (1.89) proj_loss: -0.4619 (-0.4619) time: 0.9224 data: 0.0002 [11-22 18:59:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 417/1669] eta: 0:19:17 tlr: 0.00021 tnm: 0.65 Lm: 7.405 (7.405) Lt: 6.937 (6.937) Accm: 1.60 (1.60) Acct: 2.17 (2.17) proj_loss: -0.4547 (-0.4547) time: 0.9224 data: 0.0003 [11-22 18:59:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 417/1669] eta: 0:19:17 tlr: 0.00021 tnm: 0.65 Lm: 7.374 (7.374) Lt: 6.878 (6.878) Accm: 1.41 (1.41) Acct: 2.12 (2.12) proj_loss: -0.4422 (-0.4422) time: 0.9224 data: 0.0003 [11-22 19:05:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 834/1669] eta: 0:13:13 tlr: 0.00022 tnm: 0.68 Lm: 7.385 (7.377) Lt: 6.876 (6.877) Accm: 1.38 (1.38) Acct: 2.07 (2.10) proj_loss: -0.4574 (-0.4507) time: 0.9254 data: 0.0003 [11-22 19:05:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 834/1669] eta: 0:13:13 tlr: 0.00022 tnm: 0.68 Lm: 7.403 (7.408) Lt: 6.908 (6.940) Accm: 1.30 (1.44) Acct: 1.89 (2.07) proj_loss: -0.4483 (-0.4435) time: 0.9254 data: 0.0002 [11-22 19:05:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 834/1669] eta: 0:13:13 tlr: 0.00022 tnm: 0.68 Lm: 7.433 (7.368) Lt: 6.985 (6.914) Accm: 1.40 (1.55) Acct: 2.17 (2.05) proj_loss: -0.4525 (-0.4475) time: 0.9254 data: 0.0002 [11-22 19:05:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 834/1669] eta: 0:13:13 tlr: 0.00022 tnm: 0.68 Lm: 7.438 (7.420) Lt: 7.016 (6.980) Accm: 1.38 (1.43) Acct: 1.86 (1.84) proj_loss: -0.4506 (-0.4484) time: 0.9254 data: 0.0003 [11-22 19:05:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 834/1669] eta: 0:13:13 tlr: 0.00022 tnm: 0.68 Lm: 7.426 (7.442) Lt: 7.004 (6.981) Accm: 1.14 (1.18) Acct: 1.86 (1.78) proj_loss: -0.4647 (-0.4639) time: 0.9254 data: 0.0002 [11-22 19:05:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 834/1669] eta: 0:13:13 tlr: 0.00022 tnm: 0.68 Lm: 7.389 (7.402) Lt: 6.914 (6.921) Accm: 1.24 (1.32) Acct: 1.76 (1.94) proj_loss: -0.4607 (-0.4559) time: 0.9254 data: 0.0002 [11-22 19:05:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 834/1669] eta: 0:13:13 tlr: 0.00022 tnm: 0.68 Lm: 7.415 (7.370) Lt: 6.951 (6.906) Accm: 1.56 (1.50) Acct: 2.20 (2.24) proj_loss: -0.4527 (-0.4569) time: 0.9254 data: 0.0002 [11-22 19:05:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [ 834/1669] eta: 0:13:13 tlr: 0.00022 tnm: 0.68 Lm: 7.425 (7.456) Lt: 6.946 (6.989) Accm: 1.52 (1.50) Acct: 2.07 (2.11) proj_loss: -0.4569 (-0.4583) time: 0.9254 data: 0.0003 [11-22 19:12:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [1251/1669] eta: 0:06:33 tlr: 0.00023 tnm: 0.60 Lm: 7.405 (7.414) Lt: 6.937 (6.919) Accm: 1.49 (1.49) Acct: 2.17 (2.18) proj_loss: -0.4547 (-0.4568) time: 0.9221 data: 0.0003 [11-22 19:12:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [1251/1669] eta: 0:06:33 tlr: 0.00023 tnm: 0.60 Lm: 7.425 (7.435) Lt: 6.964 (6.956) Accm: 1.20 (1.20) Acct: 1.89 (1.83) proj_loss: -0.4619 (-0.4608) time: 0.9221 data: 0.0002 [11-22 19:12:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [1251/1669] eta: 0:06:33 tlr: 0.00023 tnm: 0.60 Lm: 7.440 (7.425) Lt: 6.955 (6.955) Accm: 1.27 (1.37) Acct: 1.88 (1.97) proj_loss: -0.4494 (-0.4491) time: 0.9221 data: 0.0003 [11-22 19:12:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [1251/1669] eta: 0:06:33 tlr: 0.00023 tnm: 0.60 Lm: 7.371 (7.354) Lt: 6.872 (6.876) Accm: 1.52 (1.57) Acct: 2.22 (2.16) proj_loss: -0.4530 (-0.4515) time: 0.9221 data: 0.0003 [11-22 19:12:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [1251/1669] eta: 0:06:33 tlr: 0.00023 tnm: 0.60 Lm: 7.362 (7.377) Lt: 6.904 (6.914) Accm: 1.45 (1.48) Acct: 1.86 (1.95) proj_loss: -0.4598 (-0.4536) time: 0.9221 data: 0.0003 [11-22 19:12:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [1251/1669] eta: 0:06:33 tlr: 0.00023 tnm: 0.60 Lm: 7.382 (7.378) Lt: 6.884 (6.881) Accm: 1.35 (1.37) Acct: 2.03 (2.05) proj_loss: -0.4546 (-0.4509) time: 0.9221 data: 0.0003 [11-22 19:12:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [1251/1669] eta: 0:06:33 tlr: 0.00023 tnm: 0.60 Lm: 7.409 (7.409) Lt: 6.913 (6.919) Accm: 1.31 (1.33) Acct: 1.91 (1.97) proj_loss: -0.4519 (-0.4513) time: 0.9221 data: 0.0003 [11-22 19:12:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [1251/1669] eta: 0:06:33 tlr: 0.00023 tnm: 0.60 Lm: 7.337 (7.342) Lt: 6.868 (6.876) Accm: 1.52 (1.49) Acct: 2.17 (2.21) proj_loss: -0.4629 (-0.4610) time: 0.9221 data: 0.0002 [11-22 19:18:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.60 Lm: 7.410 (7.355) Lt: 6.951 (6.892) Accm: 1.49 (1.46) Acct: 2.13 (2.19) proj_loss: -0.4732 (-0.4637) time: 0.9258 data: 0.0019 [11-22 19:18:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 6/350] Total time: 0:26:04 (0.937 s / it) [11-22 19:18:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.60 Lm: 7.403 (7.396) Lt: 6.908 (6.910) Accm: 1.28 (1.35) Acct: 1.89 (1.96) proj_loss: -0.4483 (-0.4486) time: 0.9258 data: 0.0016 [11-22 19:18:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.60 Lm: 7.336 (7.350) Lt: 6.842 (6.869) Accm: 1.40 (1.54) Acct: 2.17 (2.13) proj_loss: -0.4534 (-0.4543) time: 0.9258 data: 0.0018 [11-22 19:18:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.60 Lm: 7.424 (7.380) Lt: 6.924 (6.878) Accm: 1.27 (1.33) Acct: 1.93 (2.07) proj_loss: -0.4647 (-0.4640) time: 0.9258 data: 0.0020 [11-22 19:18:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.60 Lm: 7.290 (7.360) Lt: 6.792 (6.871) Accm: 1.52 (1.51) Acct: 1.86 (2.02) proj_loss: -0.4690 (-0.4567) time: 0.9258 data: 0.0018 [11-22 19:18:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.60 Lm: 7.386 (7.390) Lt: 6.929 (6.910) Accm: 1.52 (1.55) Acct: 2.27 (2.22) proj_loss: -0.4569 (-0.4602) time: 0.9258 data: 0.0017 [11-22 19:18:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.60 Lm: 7.389 (7.403) Lt: 6.912 (6.912) Accm: 1.24 (1.31) Acct: 1.76 (1.90) proj_loss: -0.4607 (-0.4584) time: 0.9258 data: 0.0018 [11-22 19:18:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 6/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.60 Lm: 7.379 (7.365) Lt: 6.890 (6.883) Accm: 1.38 (1.39) Acct: 2.07 (2.06) proj_loss: -0.4574 (-0.4527) time: 0.9258 data: 0.0020 [11-22 19:18:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 6/350] Total time: 0:26:04 (0.937 s / it) [11-22 19:18:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 6/350] Total time: 0:26:04 (0.937 s / it) [11-22 19:18:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 6/350] Total time: 0:26:04 (0.937 s / it) [11-22 19:18:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 6/350] Total time: 0:26:04 (0.937 s / it) [11-22 19:18:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 6/350] Total time: 0:26:04 (0.937 s / it) [11-22 19:18:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 6/350] Total time: 0:26:04 (0.937 s / it) [11-22 19:18:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 6/350] Total time: 0:26:04 (0.937 s / it) [11-22 19:18:47] (/home/user/VAR/train.py , line 276)=> [ep6] (training ) Lm: 7.374 (7.374), Lt: 6.880 (6.880), Acc m&t: 1.46 2.16, Remain: 6 days, 4:25:43, Finish: 2024-11-28 07:44 [11-22 19:18:47] (/home/user/VAR/train.py , line 276)=> [ep6] (training ) Lm: 7.374 (7.374), Lt: 6.880 (6.880), Acc m&t: 1.46 2.16, Remain: 6 days, 4:27:28, Finish: 2024-11-28 07:46 [11-22 19:18:47] (/home/user/VAR/train.py , line 276)=> [ep6] (training ) Lm: 7.374 (7.374), Lt: 6.880 (6.880), Acc m&t: 1.46 2.16, Remain: 6 days, 4:26:30, Finish: 2024-11-28 07:45 [11-22 19:18:47] (/home/user/VAR/train.py , line 276)=> [ep6] (training ) Lm: 7.374 (7.374), Lt: 6.880 (6.880), Acc m&t: 1.46 2.16, Remain: 6 days, 4:27:19, Finish: 2024-11-28 07:46 [11-22 19:18:47] (/home/user/VAR/train.py , line 276)=> [ep6] (training ) Lm: 7.374 (7.374), Lt: 6.880 (6.880), Acc m&t: 1.46 2.16, Remain: 6 days, 4:26:55, Finish: 2024-11-28 07:45 [11-22 19:18:47] (/home/user/VAR/train.py , line 276)=> [ep6] (training ) Lm: 7.374 (7.374), Lt: 6.880 (6.880), Acc m&t: 1.46 2.16, Remain: 6 days, 4:27:03, Finish: 2024-11-28 07:45 [11-22 19:18:47] (/home/user/VAR/train.py , line 276)=> [ep6] (training ) Lm: 7.374 (7.374), Lt: 6.880 (6.880), Acc m&t: 1.46 2.16, Remain: 6 days, 4:27:30, Finish: 2024-11-28 07:46 [11-22 19:18:47] (/home/user/VAR/train.py , line 276)=> [ep6] (training ) Lm: 7.374 (7.374), Lt: 6.880 (6.880), Acc m&t: 1.46 2.16, Remain: 6 days, 4:25:23, Finish: 2024-11-28 07:44 [11-22 19:18:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 0/1669] eta: 0:24:47 tlr: 0.00024 tnm: 0.66 Lm: 7.314 (7.314) Lt: 6.821 (6.821) Accm: 1.79 (1.79) Acct: 2.62 (2.62) proj_loss: -0.4990 (-0.4990) time: 0.8913 data: 0.0004 [11-22 19:18:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 0/1669] eta: 0:25:04 tlr: 0.00024 tnm: 0.66 Lm: 7.382 (7.382) Lt: 6.834 (6.834) Accm: 1.65 (1.65) Acct: 2.48 (2.48) proj_loss: -0.4729 (-0.4729) time: 0.9016 data: 0.0003 [11-22 19:18:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 0/1669] eta: 0:24:51 tlr: 0.00024 tnm: 0.66 Lm: 7.205 (7.205) Lt: 6.676 (6.676) Accm: 1.78 (1.78) Acct: 2.69 (2.69) proj_loss: -0.4657 (-0.4657) time: 0.8935 data: 0.0004 [11-22 19:18:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 0/1669] eta: 0:24:49 tlr: 0.00024 tnm: 0.66 Lm: 7.429 (7.429) Lt: 6.954 (6.954) Accm: 1.22 (1.22) Acct: 1.76 (1.76) proj_loss: -0.4426 (-0.4426) time: 0.8923 data: 0.0004 [11-22 19:18:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 0/1669] eta: 0:24:48 tlr: 0.00024 tnm: 0.66 Lm: 7.196 (7.196) Lt: 6.632 (6.632) Accm: 1.49 (1.49) Acct: 2.20 (2.20) proj_loss: -0.4731 (-0.4731) time: 0.8920 data: 0.0004 [11-22 19:18:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 0/1669] eta: 0:24:49 tlr: 0.00024 tnm: 0.66 Lm: 7.089 (7.089) Lt: 6.511 (6.511) Accm: 2.24 (2.24) Acct: 3.17 (3.17) proj_loss: -0.4594 (-0.4594) time: 0.8923 data: 0.0004 [11-22 19:18:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 0/1669] eta: 0:24:48 tlr: 0.00024 tnm: 0.66 Lm: 7.354 (7.354) Lt: 6.803 (6.803) Accm: 1.52 (1.52) Acct: 2.27 (2.27) proj_loss: -0.4624 (-0.4624) time: 0.8917 data: 0.0004 [11-22 19:18:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 0/1669] eta: 0:24:48 tlr: 0.00024 tnm: 0.66 Lm: 7.277 (7.277) Lt: 6.745 (6.745) Accm: 1.66 (1.66) Acct: 2.48 (2.48) proj_loss: -0.4694 (-0.4694) time: 0.8921 data: 0.0004 [11-22 19:25:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 417/1669] eta: 0:19:18 tlr: 0.00024 tnm: 0.54 Lm: 7.329 (7.329) Lt: 6.827 (6.827) Accm: 1.66 (1.66) Acct: 2.39 (2.39) proj_loss: -0.4710 (-0.4710) time: 0.9228 data: 0.0003 [11-22 19:25:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 417/1669] eta: 0:19:18 tlr: 0.00024 tnm: 0.54 Lm: 7.275 (7.275) Lt: 6.743 (6.743) Accm: 1.52 (1.52) Acct: 2.32 (2.32) proj_loss: -0.4677 (-0.4677) time: 0.9227 data: 0.0003 [11-22 19:25:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 417/1669] eta: 0:19:18 tlr: 0.00024 tnm: 0.54 Lm: 7.370 (7.370) Lt: 6.864 (6.864) Accm: 1.36 (1.36) Acct: 2.10 (2.10) proj_loss: -0.4531 (-0.4531) time: 0.9227 data: 0.0003 [11-22 19:25:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 417/1669] eta: 0:19:18 tlr: 0.00024 tnm: 0.54 Lm: 7.317 (7.317) Lt: 6.741 (6.741) Accm: 1.63 (1.63) Acct: 2.55 (2.55) proj_loss: -0.4824 (-0.4824) time: 0.9227 data: 0.0002 [11-22 19:25:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 417/1669] eta: 0:19:18 tlr: 0.00024 tnm: 0.54 Lm: 7.285 (7.285) Lt: 6.743 (6.743) Accm: 1.78 (1.78) Acct: 2.44 (2.44) proj_loss: -0.4506 (-0.4506) time: 0.9228 data: 0.0002 [11-22 19:25:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 417/1669] eta: 0:19:18 tlr: 0.00024 tnm: 0.54 Lm: 7.239 (7.239) Lt: 6.697 (6.697) Accm: 1.47 (1.47) Acct: 2.13 (2.13) proj_loss: -0.4615 (-0.4615) time: 0.9227 data: 0.0002 [11-22 19:25:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 417/1669] eta: 0:19:18 tlr: 0.00024 tnm: 0.54 Lm: 7.336 (7.336) Lt: 6.768 (6.768) Accm: 1.58 (1.58) Acct: 2.39 (2.39) proj_loss: -0.4555 (-0.4555) time: 0.9227 data: 0.0003 [11-22 19:25:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 417/1669] eta: 0:19:18 tlr: 0.00024 tnm: 0.54 Lm: 7.367 (7.367) Lt: 6.886 (6.886) Accm: 1.62 (1.62) Acct: 2.46 (2.46) proj_loss: -0.4912 (-0.4912) time: 0.9228 data: 0.0003 [11-22 19:31:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 834/1669] eta: 0:12:52 tlr: 0.00024 tnm: 0.60 Lm: 7.314 (7.238) Lt: 6.821 (6.730) Accm: 1.79 (1.83) Acct: 2.62 (2.74) proj_loss: -0.4903 (-0.4909) time: 0.9248 data: 0.0003 [11-22 19:31:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 834/1669] eta: 0:12:52 tlr: 0.00024 tnm: 0.60 Lm: 7.358 (7.309) Lt: 6.881 (6.789) Accm: 1.37 (1.65) Acct: 1.89 (2.26) proj_loss: -0.4594 (-0.4538) time: 0.9248 data: 0.0002 [11-22 19:31:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 834/1669] eta: 0:12:52 tlr: 0.00024 tnm: 0.60 Lm: 7.205 (7.245) Lt: 6.676 (6.695) Accm: 1.78 (1.62) Acct: 2.34 (2.33) proj_loss: -0.4698 (-0.4771) time: 0.9247 data: 0.0003 [11-22 19:31:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 834/1669] eta: 0:12:52 tlr: 0.00024 tnm: 0.60 Lm: 7.310 (7.303) Lt: 6.774 (6.775) Accm: 1.50 (1.63) Acct: 2.44 (2.54) proj_loss: -0.4636 (-0.4624) time: 0.9248 data: 0.0003 [11-22 19:31:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 834/1669] eta: 0:12:52 tlr: 0.00024 tnm: 0.60 Lm: 7.253 (7.281) Lt: 6.665 (6.716) Accm: 1.62 (1.56) Acct: 2.48 (2.39) proj_loss: -0.4729 (-0.4716) time: 0.9248 data: 0.0003 [11-22 19:31:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 834/1669] eta: 0:12:52 tlr: 0.00024 tnm: 0.60 Lm: 7.196 (7.211) Lt: 6.632 (6.668) Accm: 1.49 (1.54) Acct: 2.20 (2.30) proj_loss: -0.4731 (-0.4734) time: 0.9248 data: 0.0002 [11-22 19:31:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 834/1669] eta: 0:12:52 tlr: 0.00024 tnm: 0.60 Lm: 7.291 (7.316) Lt: 6.745 (6.796) Accm: 1.66 (1.60) Acct: 2.34 (2.38) proj_loss: -0.4694 (-0.4694) time: 0.9248 data: 0.0003 [11-22 19:31:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [ 834/1669] eta: 0:12:52 tlr: 0.00024 tnm: 0.60 Lm: 7.341 (7.337) Lt: 6.789 (6.775) Accm: 1.52 (1.54) Acct: 2.27 (2.31) proj_loss: -0.4624 (-0.4681) time: 0.9248 data: 0.0003 [11-22 19:38:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [1251/1669] eta: 0:06:26 tlr: 0.00024 tnm: 0.55 Lm: 7.329 (7.319) Lt: 6.761 (6.758) Accm: 1.58 (1.58) Acct: 2.39 (2.40) proj_loss: -0.4576 (-0.4642) time: 0.9232 data: 0.0003 [11-22 19:38:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [1251/1669] eta: 0:06:26 tlr: 0.00024 tnm: 0.55 Lm: 7.196 (7.222) Lt: 6.643 (6.674) Accm: 1.80 (1.68) Acct: 2.43 (2.38) proj_loss: -0.4677 (-0.4726) time: 0.9232 data: 0.0002 [11-22 19:38:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [1251/1669] eta: 0:06:26 tlr: 0.00024 tnm: 0.55 Lm: 7.321 (7.310) Lt: 6.781 (6.778) Accm: 1.44 (1.57) Acct: 2.20 (2.39) proj_loss: -0.4652 (-0.4635) time: 0.9232 data: 0.0003 [11-22 19:38:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [1251/1669] eta: 0:06:26 tlr: 0.00024 tnm: 0.55 Lm: 7.238 (7.267) Lt: 6.664 (6.703) Accm: 1.63 (1.60) Acct: 2.48 (2.41) proj_loss: -0.4797 (-0.4753) time: 0.9232 data: 0.0003 [11-22 19:38:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [1251/1669] eta: 0:06:26 tlr: 0.00024 tnm: 0.55 Lm: 7.237 (7.228) Lt: 6.696 (6.691) Accm: 1.58 (1.64) Acct: 2.41 (2.52) proj_loss: -0.4677 (-0.4706) time: 0.9232 data: 0.0002 [11-22 19:38:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [1251/1669] eta: 0:06:26 tlr: 0.00024 tnm: 0.55 Lm: 7.294 (7.312) Lt: 6.741 (6.782) Accm: 1.59 (1.58) Acct: 2.41 (2.40) proj_loss: -0.4710 (-0.4735) time: 0.9232 data: 0.0003 [11-22 19:38:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [1251/1669] eta: 0:06:26 tlr: 0.00024 tnm: 0.55 Lm: 7.311 (7.298) Lt: 6.768 (6.756) Accm: 1.53 (1.66) Acct: 2.24 (2.34) proj_loss: -0.4597 (-0.4596) time: 0.9232 data: 0.0002 [11-22 19:38:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [1251/1669] eta: 0:06:26 tlr: 0.00024 tnm: 0.55 Lm: 7.314 (7.257) Lt: 6.782 (6.733) Accm: 1.62 (1.69) Acct: 2.46 (2.60) proj_loss: -0.4869 (-0.4791) time: 0.9232 data: 0.0003 [11-22 19:44:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.59 Lm: 7.314 (7.264) Lt: 6.742 (6.714) Accm: 1.63 (1.68) Acct: 2.62 (2.61) proj_loss: -0.4835 (-0.4729) time: 0.9285 data: 0.0020 [11-22 19:44:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 7/350] Total time: 0:25:59 (0.934 s / it) [11-22 19:44:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.59 Lm: 7.265 (7.265) Lt: 6.655 (6.719) Accm: 1.69 (1.72) Acct: 2.58 (2.44) proj_loss: -0.4594 (-0.4572) time: 0.9285 data: 0.0016 [11-22 19:44:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.59 Lm: 7.318 (7.312) Lt: 6.774 (6.774) Accm: 1.50 (1.55) Acct: 2.27 (2.37) proj_loss: -0.4668 (-0.4662) time: 0.9285 data: 0.0017 [11-22 19:44:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.59 Lm: 7.291 (7.254) Lt: 6.738 (6.708) Accm: 1.66 (1.66) Acct: 2.48 (2.53) proj_loss: -0.4708 (-0.4730) time: 0.9285 data: 0.0017 [11-22 19:44:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.59 Lm: 7.196 (7.221) Lt: 6.632 (6.677) Accm: 1.59 (1.63) Acct: 2.31 (2.48) proj_loss: -0.4717 (-0.4708) time: 0.9285 data: 0.0017 [11-22 19:44:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.59 Lm: 7.223 (7.244) Lt: 6.662 (6.676) Accm: 1.65 (1.61) Acct: 2.48 (2.44) proj_loss: -0.4865 (-0.4789) time: 0.9285 data: 0.0015 [11-22 19:44:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.59 Lm: 7.317 (7.308) Lt: 6.751 (6.757) Accm: 1.62 (1.59) Acct: 2.51 (2.43) proj_loss: -0.4624 (-0.4669) time: 0.9285 data: 0.0015 [11-22 19:44:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 7/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.59 Lm: 7.187 (7.189) Lt: 6.611 (6.628) Accm: 1.82 (1.75) Acct: 2.51 (2.44) proj_loss: -0.4698 (-0.4722) time: 0.9285 data: 0.0020 [11-22 19:44:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 7/350] Total time: 0:25:59 (0.934 s / it) [11-22 19:44:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 7/350] Total time: 0:25:59 (0.934 s / it) [11-22 19:44:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 7/350] Total time: 0:25:59 (0.934 s / it) [11-22 19:44:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 7/350] Total time: 0:25:59 (0.934 s / it) [11-22 19:44:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 7/350] Total time: 0:25:59 (0.934 s / it) [11-22 19:44:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 7/350] Total time: 0:25:59 (0.934 s / it) [11-22 19:44:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 7/350] Total time: 0:25:59 (0.934 s / it) [11-22 19:44:47] (/home/user/VAR/train.py , line 276)=> [ep7] (training ) Lm: 7.252 (7.252), Lt: 6.696 (6.696), Acc m&t: 1.68 2.54, Remain: 6 days, 4:29:18, Finish: 2024-11-28 08:14 [11-22 19:44:47] (/home/user/VAR/train.py , line 276)=> [ep7] (training ) Lm: 7.252 (7.252), Lt: 6.696 (6.696), Acc m&t: 1.68 2.54, Remain: 6 days, 4:25:11, Finish: 2024-11-28 08:09 [11-22 19:44:47] (/home/user/VAR/train.py , line 276)=> [ep7] (training ) Lm: 7.252 (7.252), Lt: 6.696 (6.696), Acc m&t: 1.68 2.54, Remain: 6 days, 4:24:38, Finish: 2024-11-28 08:09 [11-22 19:44:47] (/home/user/VAR/train.py , line 276)=> [ep7] (training ) Lm: 7.252 (7.252), Lt: 6.696 (6.696), Acc m&t: 1.68 2.54, Remain: 6 days, 4:29:49, Finish: 2024-11-28 08:14 [11-22 19:44:47] (/home/user/VAR/train.py , line 276)=> [ep7] (training ) Lm: 7.252 (7.252), Lt: 6.696 (6.696), Acc m&t: 1.68 2.54, Remain: 6 days, 4:28:17, Finish: 2024-11-28 08:13 [11-22 19:44:47] (/home/user/VAR/train.py , line 276)=> [ep7] (training ) Lm: 7.252 (7.252), Lt: 6.696 (6.696), Acc m&t: 1.68 2.54, Remain: 6 days, 4:27:18, Finish: 2024-11-28 08:12 [11-22 19:44:47] (/home/user/VAR/train.py , line 276)=> [ep7] (training ) Lm: 7.252 (7.252), Lt: 6.696 (6.696), Acc m&t: 1.68 2.54, Remain: 6 days, 4:28:08, Finish: 2024-11-28 08:12 [11-22 19:44:47] (/home/user/VAR/train.py , line 276)=> [ep7] (training ) Lm: 7.252 (7.252), Lt: 6.696 (6.696), Acc m&t: 1.68 2.54, Remain: 6 days, 4:24:25, Finish: 2024-11-28 08:09 [11-22 19:44:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 0/1669] eta: 0:24:46 tlr: 0.00024 tnm: 0.53 Lm: 7.206 (7.206) Lt: 6.564 (6.564) Accm: 1.56 (1.56) Acct: 2.44 (2.44) proj_loss: -0.5048 (-0.5048) time: 0.8907 data: 0.0003 [11-22 19:44:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 0/1669] eta: 0:24:46 tlr: 0.00024 tnm: 0.53 Lm: 7.257 (7.257) Lt: 6.649 (6.649) Accm: 1.98 (1.98) Acct: 3.00 (3.00) proj_loss: -0.4624 (-0.4624) time: 0.8904 data: 0.0004 [11-22 19:44:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 0/1669] eta: 0:24:47 tlr: 0.00024 tnm: 0.53 Lm: 7.177 (7.177) Lt: 6.680 (6.680) Accm: 1.78 (1.78) Acct: 2.65 (2.65) proj_loss: -0.5004 (-0.5004) time: 0.8911 data: 0.0004 [11-22 19:44:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 0/1669] eta: 0:24:46 tlr: 0.00024 tnm: 0.53 Lm: 7.157 (7.157) Lt: 6.577 (6.577) Accm: 1.81 (1.81) Acct: 2.86 (2.86) proj_loss: -0.4946 (-0.4946) time: 0.8908 data: 0.0004 [11-22 19:44:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 0/1669] eta: 0:24:46 tlr: 0.00024 tnm: 0.53 Lm: 7.229 (7.229) Lt: 6.717 (6.717) Accm: 1.76 (1.76) Acct: 2.20 (2.20) proj_loss: -0.4510 (-0.4510) time: 0.8907 data: 0.0004 [11-22 19:44:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 0/1669] eta: 0:24:46 tlr: 0.00024 tnm: 0.53 Lm: 7.198 (7.198) Lt: 6.665 (6.665) Accm: 1.86 (1.86) Acct: 2.62 (2.62) proj_loss: -0.4800 (-0.4800) time: 0.8907 data: 0.0004 [11-22 19:44:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 0/1669] eta: 0:24:46 tlr: 0.00024 tnm: 0.53 Lm: 7.246 (7.246) Lt: 6.680 (6.680) Accm: 1.30 (1.30) Acct: 2.27 (2.27) proj_loss: -0.4836 (-0.4836) time: 0.8905 data: 0.0003 [11-22 19:44:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 0/1669] eta: 0:24:46 tlr: 0.00024 tnm: 0.53 Lm: 7.385 (7.385) Lt: 6.880 (6.880) Accm: 1.41 (1.41) Acct: 2.20 (2.20) proj_loss: -0.4379 (-0.4379) time: 0.8907 data: 0.0004 [11-22 19:51:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 417/1669] eta: 0:19:18 tlr: 0.00024 tnm: 0.56 Lm: 7.325 (7.325) Lt: 6.793 (6.793) Accm: 1.52 (1.52) Acct: 2.38 (2.38) proj_loss: -0.4685 (-0.4685) time: 0.9252 data: 0.0003 [11-22 19:51:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 417/1669] eta: 0:19:18 tlr: 0.00024 tnm: 0.56 Lm: 7.135 (7.135) Lt: 6.542 (6.542) Accm: 1.89 (1.89) Acct: 2.84 (2.84) proj_loss: -0.4913 (-0.4913) time: 0.9252 data: 0.0003 [11-22 19:51:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 417/1669] eta: 0:19:18 tlr: 0.00024 tnm: 0.56 Lm: 7.155 (7.155) Lt: 6.544 (6.544) Accm: 1.68 (1.68) Acct: 2.70 (2.70) proj_loss: -0.4791 (-0.4791) time: 0.9252 data: 0.0003 [11-22 19:51:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 417/1669] eta: 0:19:18 tlr: 0.00024 tnm: 0.56 Lm: 7.061 (7.061) Lt: 6.480 (6.480) Accm: 2.03 (2.03) Acct: 2.94 (2.94) proj_loss: -0.4831 (-0.4831) time: 0.9252 data: 0.0003 [11-22 19:51:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 417/1669] eta: 0:19:18 tlr: 0.00024 tnm: 0.56 Lm: 7.124 (7.124) Lt: 6.564 (6.564) Accm: 2.09 (2.09) Acct: 3.06 (3.06) proj_loss: -0.4794 (-0.4794) time: 0.9252 data: 0.0002 [11-22 19:51:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 417/1669] eta: 0:19:18 tlr: 0.00024 tnm: 0.56 Lm: 7.039 (7.039) Lt: 6.475 (6.475) Accm: 2.16 (2.16) Acct: 3.25 (3.25) proj_loss: -0.4844 (-0.4844) time: 0.9252 data: 0.0003 [11-22 19:51:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 417/1669] eta: 0:19:18 tlr: 0.00024 tnm: 0.56 Lm: 7.170 (7.170) Lt: 6.536 (6.536) Accm: 1.86 (1.86) Acct: 2.74 (2.74) proj_loss: -0.4851 (-0.4851) time: 0.9252 data: 0.0002 [11-22 19:51:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 417/1669] eta: 0:19:18 tlr: 0.00024 tnm: 0.56 Lm: 7.241 (7.241) Lt: 6.629 (6.629) Accm: 1.81 (1.81) Acct: 2.93 (2.93) proj_loss: -0.4708 (-0.4708) time: 0.9252 data: 0.0003 [11-22 19:57:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 834/1669] eta: 0:12:52 tlr: 0.00024 tnm: 0.54 Lm: 7.257 (7.255) Lt: 6.649 (6.652) Accm: 1.70 (1.77) Acct: 2.86 (2.71) proj_loss: -0.4792 (-0.4891) time: 0.9250 data: 0.0003 [11-22 19:57:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 834/1669] eta: 0:12:52 tlr: 0.00024 tnm: 0.54 Lm: 7.157 (7.213) Lt: 6.577 (6.629) Accm: 1.81 (1.75) Acct: 2.82 (2.70) proj_loss: -0.4881 (-0.4873) time: 0.9249 data: 0.0003 [11-22 19:57:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 834/1669] eta: 0:12:52 tlr: 0.00024 tnm: 0.54 Lm: 6.975 (7.033) Lt: 6.371 (6.443) Accm: 1.85 (1.97) Acct: 3.00 (2.96) proj_loss: -0.4896 (-0.4853) time: 0.9249 data: 0.0003 [11-22 19:57:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 834/1669] eta: 0:12:52 tlr: 0.00024 tnm: 0.54 Lm: 7.165 (7.159) Lt: 6.526 (6.538) Accm: 1.88 (1.75) Acct: 2.58 (2.66) proj_loss: -0.4836 (-0.4943) time: 0.9249 data: 0.0002 [11-22 19:57:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 834/1669] eta: 0:12:52 tlr: 0.00024 tnm: 0.54 Lm: 7.134 (7.071) Lt: 6.550 (6.500) Accm: 1.78 (2.03) Acct: 2.79 (3.10) proj_loss: -0.4684 (-0.4719) time: 0.9250 data: 0.0002 [11-22 19:57:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 834/1669] eta: 0:12:52 tlr: 0.00024 tnm: 0.54 Lm: 7.049 (7.064) Lt: 6.463 (6.493) Accm: 2.11 (2.10) Acct: 3.34 (3.16) proj_loss: -0.4788 (-0.4774) time: 0.9250 data: 0.0002 [11-22 19:57:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 834/1669] eta: 0:12:52 tlr: 0.00024 tnm: 0.54 Lm: 7.135 (7.157) Lt: 6.564 (6.548) Accm: 1.97 (1.90) Acct: 3.03 (2.86) proj_loss: -0.4654 (-0.4733) time: 0.9250 data: 0.0002 [11-22 19:57:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [ 834/1669] eta: 0:12:52 tlr: 0.00024 tnm: 0.54 Lm: 7.265 (7.174) Lt: 6.707 (6.606) Accm: 1.63 (1.86) Acct: 2.55 (2.80) proj_loss: -0.4795 (-0.4722) time: 0.9250 data: 0.0003 [11-22 20:04:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [1251/1669] eta: 0:06:26 tlr: 0.00024 tnm: 0.58 Lm: 7.190 (7.159) Lt: 6.623 (6.589) Accm: 1.85 (1.91) Acct: 2.82 (2.88) proj_loss: -0.4686 (-0.4686) time: 0.9240 data: 0.0005 [11-22 20:04:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [1251/1669] eta: 0:06:26 tlr: 0.00024 tnm: 0.58 Lm: 7.115 (7.127) Lt: 6.467 (6.492) Accm: 1.94 (1.81) Acct: 2.82 (2.76) proj_loss: -0.4851 (-0.4924) time: 0.9240 data: 0.0003 [11-22 20:04:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [1251/1669] eta: 0:06:26 tlr: 0.00024 tnm: 0.58 Lm: 7.133 (7.147) Lt: 6.565 (6.552) Accm: 1.88 (1.87) Acct: 2.74 (2.75) proj_loss: -0.4851 (-0.4857) time: 0.9240 data: 0.0002 [11-22 20:04:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [1251/1669] eta: 0:06:26 tlr: 0.00024 tnm: 0.58 Lm: 7.156 (7.119) Lt: 6.615 (6.548) Accm: 1.77 (1.90) Acct: 2.72 (2.93) proj_loss: -0.4737 (-0.4737) time: 0.9240 data: 0.0003 [11-22 20:04:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [1251/1669] eta: 0:06:26 tlr: 0.00024 tnm: 0.58 Lm: 7.270 (7.285) Lt: 6.673 (6.692) Accm: 1.67 (1.69) Acct: 2.60 (2.62) proj_loss: -0.4805 (-0.4873) time: 0.9240 data: 0.0003 [11-22 20:04:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [1251/1669] eta: 0:06:26 tlr: 0.00024 tnm: 0.58 Lm: 7.216 (7.229) Lt: 6.629 (6.642) Accm: 1.78 (1.76) Acct: 2.70 (2.67) proj_loss: -0.4872 (-0.4870) time: 0.9240 data: 0.0003 [11-22 20:04:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [1251/1669] eta: 0:06:26 tlr: 0.00024 tnm: 0.58 Lm: 6.963 (7.012) Lt: 6.351 (6.416) Accm: 2.08 (2.07) Acct: 3.13 (3.04) proj_loss: -0.4900 (-0.4866) time: 0.9240 data: 0.0003 [11-22 20:04:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [1251/1669] eta: 0:06:26 tlr: 0.00024 tnm: 0.58 Lm: 6.998 (7.034) Lt: 6.407 (6.440) Accm: 2.21 (2.16) Acct: 3.43 (3.40) proj_loss: -0.4794 (-0.4818) time: 0.9240 data: 0.0002 [11-22 20:10:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.56 Lm: 7.049 (7.084) Lt: 6.463 (6.505) Accm: 2.11 (2.05) Acct: 3.34 (3.22) proj_loss: -0.4800 (-0.4895) time: 0.9285 data: 0.0019 [11-22 20:10:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 8/350] Total time: 0:25:44 (0.925 s / it) [11-22 20:10:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.56 Lm: 7.131 (7.118) Lt: 6.564 (6.524) Accm: 1.97 (1.92) Acct: 3.03 (2.86) proj_loss: -0.4813 (-0.4848) time: 0.9285 data: 0.0017 [11-22 20:10:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.56 Lm: 7.066 (7.115) Lt: 6.487 (6.491) Accm: 1.88 (1.80) Acct: 2.65 (2.74) proj_loss: -0.4865 (-0.4999) time: 0.9285 data: 0.0015 [11-22 20:10:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.56 Lm: 7.134 (7.122) Lt: 6.550 (6.543) Accm: 1.78 (1.91) Acct: 2.79 (2.95) proj_loss: -0.4723 (-0.4734) time: 0.9285 data: 0.0020 [11-22 20:10:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.56 Lm: 6.975 (7.043) Lt: 6.371 (6.452) Accm: 1.85 (2.02) Acct: 3.00 (2.99) proj_loss: -0.4904 (-0.4876) time: 0.9285 data: 0.0017 [11-22 20:10:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.56 Lm: 7.283 (7.293) Lt: 6.697 (6.708) Accm: 1.63 (1.63) Acct: 2.34 (2.52) proj_loss: -0.4792 (-0.4828) time: 0.9285 data: 0.0017 [11-22 20:10:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.56 Lm: 7.157 (7.194) Lt: 6.577 (6.598) Accm: 1.81 (1.84) Acct: 2.82 (2.82) proj_loss: -0.4881 (-0.4875) time: 0.9285 data: 0.0029 [11-22 20:10:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 8/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.56 Lm: 7.172 (7.162) Lt: 6.633 (6.598) Accm: 1.84 (1.89) Acct: 2.72 (2.84) proj_loss: -0.4779 (-0.4704) time: 0.9285 data: 0.0020 [11-22 20:10:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 8/350] Total time: 0:25:44 (0.925 s / it) [11-22 20:10:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 8/350] Total time: 0:25:44 (0.925 s / it) [11-22 20:10:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 8/350] Total time: 0:25:44 (0.925 s / it) [11-22 20:10:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 8/350] Total time: 0:25:44 (0.925 s / it) [11-22 20:10:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 8/350] Total time: 0:25:44 (0.925 s / it) [11-22 20:10:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 8/350] Total time: 0:25:44 (0.926 s / it) [11-22 20:10:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 8/350] Total time: 0:25:44 (0.926 s / it) [11-22 20:10:32] (/home/user/VAR/train.py , line 276)=> [ep8] (training ) Lm: 7.153 (7.153), Lt: 6.560 (6.560), Acc m&t: 1.86 2.83, Remain: 6 days, 4:02:19, Finish: 2024-11-28 08:12 [11-22 20:10:32] (/home/user/VAR/train.py , line 276)=> [ep8] (training ) Lm: 7.153 (7.153), Lt: 6.560 (6.560), Acc m&t: 1.86 2.83, Remain: 6 days, 3:57:43, Finish: 2024-11-28 08:08 [11-22 20:10:32] (/home/user/VAR/train.py , line 276)=> [ep8] (training ) Lm: 7.153 (7.153), Lt: 6.560 (6.560), Acc m&t: 1.86 2.83, Remain: 6 days, 3:58:22, Finish: 2024-11-28 08:08 [11-22 20:10:32] (/home/user/VAR/train.py , line 276)=> [ep8] (training ) Lm: 7.153 (7.153), Lt: 6.560 (6.560), Acc m&t: 1.86 2.83, Remain: 6 days, 3:56:57, Finish: 2024-11-28 08:07 [11-22 20:10:32] (/home/user/VAR/train.py , line 276)=> [ep8] (training ) Lm: 7.153 (7.153), Lt: 6.560 (6.560), Acc m&t: 1.86 2.83, Remain: 6 days, 3:56:34, Finish: 2024-11-28 08:07 [11-22 20:10:32] (/home/user/VAR/train.py , line 276)=> [ep8] (training ) Lm: 7.153 (7.153), Lt: 6.560 (6.560), Acc m&t: 1.86 2.83, Remain: 6 days, 3:56:50, Finish: 2024-11-28 08:07 [11-22 20:10:32] (/home/user/VAR/train.py , line 276)=> [ep8] (training ) Lm: 7.153 (7.153), Lt: 6.560 (6.560), Acc m&t: 1.86 2.83, Remain: 6 days, 3:57:58, Finish: 2024-11-28 08:08 [11-22 20:10:32] (/home/user/VAR/train.py , line 276)=> [ep8] (training ) Lm: 7.153 (7.153), Lt: 6.560 (6.560), Acc m&t: 1.86 2.83, Remain: 6 days, 3:58:31, Finish: 2024-11-28 08:09 [11-22 20:10:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 0/1669] eta: 0:24:23 tlr: 0.00024 tnm: 0.55 Lm: 6.983 (6.983) Lt: 6.336 (6.336) Accm: 2.21 (2.21) Acct: 3.48 (3.48) proj_loss: -0.4651 (-0.4651) time: 0.8769 data: 0.0003 [11-22 20:10:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 0/1669] eta: 0:24:24 tlr: 0.00024 tnm: 0.55 Lm: 7.187 (7.187) Lt: 6.607 (6.607) Accm: 1.88 (1.88) Acct: 2.55 (2.55) proj_loss: -0.4762 (-0.4762) time: 0.8776 data: 0.0003 [11-22 20:10:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 0/1669] eta: 0:24:24 tlr: 0.00024 tnm: 0.55 Lm: 7.181 (7.181) Lt: 6.589 (6.589) Accm: 1.98 (1.98) Acct: 3.20 (3.20) proj_loss: -0.4917 (-0.4917) time: 0.8773 data: 0.0004 [11-22 20:10:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 0/1669] eta: 0:24:23 tlr: 0.00024 tnm: 0.55 Lm: 7.176 (7.176) Lt: 6.588 (6.588) Accm: 1.46 (1.46) Acct: 2.31 (2.31) proj_loss: -0.4785 (-0.4785) time: 0.8769 data: 0.0004 [11-22 20:10:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 0/1669] eta: 0:24:24 tlr: 0.00024 tnm: 0.55 Lm: 7.033 (7.033) Lt: 6.358 (6.358) Accm: 2.13 (2.13) Acct: 3.37 (3.37) proj_loss: -0.4753 (-0.4753) time: 0.8774 data: 0.0004 [11-22 20:10:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 0/1669] eta: 0:24:24 tlr: 0.00024 tnm: 0.55 Lm: 7.164 (7.164) Lt: 6.600 (6.600) Accm: 1.75 (1.75) Acct: 2.89 (2.89) proj_loss: -0.4690 (-0.4690) time: 0.8775 data: 0.0003 [11-22 20:10:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 0/1669] eta: 0:24:25 tlr: 0.00024 tnm: 0.55 Lm: 7.104 (7.104) Lt: 6.499 (6.499) Accm: 1.82 (1.82) Acct: 2.86 (2.86) proj_loss: -0.4907 (-0.4907) time: 0.8781 data: 0.0003 [11-22 20:10:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 0/1669] eta: 0:24:24 tlr: 0.00024 tnm: 0.55 Lm: 7.002 (7.002) Lt: 6.406 (6.406) Accm: 2.04 (2.04) Acct: 2.79 (2.79) proj_loss: -0.4914 (-0.4914) time: 0.8773 data: 0.0003 [11-22 20:17:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 417/1669] eta: 0:20:27 tlr: 0.00024 tnm: 0.47 Lm: 6.931 (6.931) Lt: 6.323 (6.323) Accm: 2.33 (2.33) Acct: 3.55 (3.55) proj_loss: -0.4881 (-0.4881) time: 0.9279 data: 0.0003 [11-22 20:17:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 417/1669] eta: 0:20:27 tlr: 0.00024 tnm: 0.47 Lm: 7.088 (7.088) Lt: 6.436 (6.436) Accm: 2.11 (2.11) Acct: 3.10 (3.10) proj_loss: -0.4851 (-0.4851) time: 0.9280 data: 0.0002 [11-22 20:17:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 417/1669] eta: 0:20:27 tlr: 0.00024 tnm: 0.47 Lm: 7.054 (7.054) Lt: 6.446 (6.446) Accm: 1.94 (1.94) Acct: 2.84 (2.84) proj_loss: -0.4773 (-0.4773) time: 0.9280 data: 0.0002 [11-22 20:17:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 417/1669] eta: 0:20:27 tlr: 0.00024 tnm: 0.47 Lm: 7.160 (7.160) Lt: 6.564 (6.564) Accm: 1.70 (1.70) Acct: 2.51 (2.51) proj_loss: -0.4994 (-0.4994) time: 0.9280 data: 0.0003 [11-22 20:17:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 417/1669] eta: 0:20:27 tlr: 0.00024 tnm: 0.47 Lm: 7.162 (7.162) Lt: 6.535 (6.535) Accm: 1.87 (1.87) Acct: 3.15 (3.15) proj_loss: -0.4889 (-0.4889) time: 0.9280 data: 0.0003 [11-22 20:17:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 417/1669] eta: 0:20:27 tlr: 0.00024 tnm: 0.47 Lm: 7.179 (7.179) Lt: 6.582 (6.582) Accm: 1.76 (1.76) Acct: 2.81 (2.81) proj_loss: -0.4816 (-0.4816) time: 0.9279 data: 0.0003 [11-22 20:17:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 417/1669] eta: 0:20:27 tlr: 0.00024 tnm: 0.47 Lm: 7.057 (7.057) Lt: 6.482 (6.482) Accm: 2.01 (2.01) Acct: 2.81 (2.81) proj_loss: -0.4922 (-0.4922) time: 0.9280 data: 0.0002 [11-22 20:17:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 417/1669] eta: 0:20:27 tlr: 0.00024 tnm: 0.47 Lm: 7.112 (7.112) Lt: 6.501 (6.501) Accm: 2.04 (2.04) Acct: 3.39 (3.39) proj_loss: -0.4695 (-0.4695) time: 0.9280 data: 0.0003 [11-22 20:23:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 834/1669] eta: 0:13:15 tlr: 0.00024 tnm: 0.53 Lm: 7.060 (7.077) Lt: 6.402 (6.448) Accm: 2.20 (2.09) Acct: 3.51 (3.43) proj_loss: -0.4690 (-0.4662) time: 0.9234 data: 0.0003 [11-22 20:23:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 834/1669] eta: 0:13:15 tlr: 0.00024 tnm: 0.53 Lm: 7.127 (7.162) Lt: 6.564 (6.576) Accm: 2.00 (1.84) Acct: 2.82 (2.81) proj_loss: -0.4715 (-0.4782) time: 0.9234 data: 0.0003 [11-22 20:23:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 834/1669] eta: 0:13:15 tlr: 0.00024 tnm: 0.53 Lm: 7.032 (7.049) Lt: 6.365 (6.443) Accm: 2.14 (2.08) Acct: 3.06 (3.10) proj_loss: -0.4762 (-0.4792) time: 0.9234 data: 0.0003 [11-22 20:23:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 834/1669] eta: 0:13:15 tlr: 0.00024 tnm: 0.53 Lm: 7.143 (7.114) Lt: 6.514 (6.490) Accm: 2.08 (2.07) Acct: 3.10 (3.10) proj_loss: -0.4949 (-0.4894) time: 0.9235 data: 0.0002 [11-22 20:23:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 834/1669] eta: 0:13:15 tlr: 0.00024 tnm: 0.53 Lm: 7.104 (7.140) Lt: 6.499 (6.532) Accm: 1.76 (1.72) Acct: 2.86 (2.67) proj_loss: -0.4911 (-0.4966) time: 0.9234 data: 0.0003 [11-22 20:23:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 834/1669] eta: 0:13:15 tlr: 0.00024 tnm: 0.53 Lm: 7.002 (7.030) Lt: 6.406 (6.440) Accm: 2.04 (2.18) Acct: 2.79 (3.23) proj_loss: -0.4848 (-0.4856) time: 0.9234 data: 0.0003 [11-22 20:23:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 834/1669] eta: 0:13:15 tlr: 0.00024 tnm: 0.53 Lm: 7.120 (7.076) Lt: 6.501 (6.464) Accm: 1.78 (1.88) Acct: 2.89 (2.86) proj_loss: -0.4761 (-0.4759) time: 0.9234 data: 0.0002 [11-22 20:23:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [ 834/1669] eta: 0:13:15 tlr: 0.00024 tnm: 0.53 Lm: 7.175 (7.166) Lt: 6.574 (6.548) Accm: 1.76 (1.82) Acct: 3.10 (2.88) proj_loss: -0.4862 (-0.4865) time: 0.9234 data: 0.0003 [11-22 20:30:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [1251/1669] eta: 0:06:34 tlr: 0.00024 tnm: 0.48 Lm: 7.169 (7.166) Lt: 6.567 (6.551) Accm: 1.81 (1.83) Acct: 2.75 (2.76) proj_loss: -0.4889 (-0.4885) time: 0.9274 data: 0.0002 [11-22 20:30:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [1251/1669] eta: 0:06:34 tlr: 0.00024 tnm: 0.48 Lm: 7.110 (7.086) Lt: 6.486 (6.485) Accm: 2.01 (2.02) Acct: 2.96 (3.04) proj_loss: -0.4834 (-0.4820) time: 0.9274 data: 0.0003 [11-22 20:30:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [1251/1669] eta: 0:06:34 tlr: 0.00024 tnm: 0.48 Lm: 7.088 (7.081) Lt: 6.436 (6.447) Accm: 2.08 (2.07) Acct: 3.24 (3.21) proj_loss: -0.4964 (-0.4935) time: 0.9274 data: 0.0002 [11-22 20:30:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [1251/1669] eta: 0:06:34 tlr: 0.00024 tnm: 0.48 Lm: 7.074 (7.064) Lt: 6.452 (6.449) Accm: 1.82 (1.88) Acct: 2.96 (2.90) proj_loss: -0.4773 (-0.4825) time: 0.9274 data: 0.0002 [11-22 20:30:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [1251/1669] eta: 0:06:34 tlr: 0.00024 tnm: 0.48 Lm: 7.057 (7.050) Lt: 6.450 (6.453) Accm: 2.02 (2.13) Acct: 2.81 (3.13) proj_loss: -0.4827 (-0.4814) time: 0.9274 data: 0.0003 [11-22 20:30:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [1251/1669] eta: 0:06:34 tlr: 0.00024 tnm: 0.48 Lm: 7.138 (7.158) Lt: 6.554 (6.568) Accm: 1.79 (1.78) Acct: 2.63 (2.72) proj_loss: -0.4683 (-0.4726) time: 0.9274 data: 0.0003 [11-22 20:30:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [1251/1669] eta: 0:06:34 tlr: 0.00024 tnm: 0.48 Lm: 7.033 (7.050) Lt: 6.372 (6.408) Accm: 2.22 (2.13) Acct: 3.51 (3.45) proj_loss: -0.4695 (-0.4712) time: 0.9274 data: 0.0003 [11-22 20:30:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [1251/1669] eta: 0:06:34 tlr: 0.00024 tnm: 0.48 Lm: 7.102 (7.083) Lt: 6.484 (6.453) Accm: 1.79 (1.89) Acct: 2.93 (2.92) proj_loss: -0.4975 (-0.4985) time: 0.9274 data: 0.0005 [11-22 20:36:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.42 Lm: 7.100 (7.065) Lt: 6.468 (6.438) Accm: 1.82 (1.95) Acct: 3.00 (3.01) proj_loss: -0.4911 (-0.4957) time: 0.9268 data: 0.0016 [11-22 20:36:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 9/350] Total time: 0:26:06 (0.939 s / it) [11-22 20:36:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.42 Lm: 7.123 (7.090) Lt: 6.464 (6.450) Accm: 2.07 (2.00) Acct: 3.10 (3.09) proj_loss: -0.4949 (-0.4930) time: 0.9268 data: 0.0015 [11-22 20:36:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.42 Lm: 7.111 (7.091) Lt: 6.494 (6.501) Accm: 2.00 (2.01) Acct: 2.79 (2.95) proj_loss: -0.4848 (-0.4837) time: 0.9268 data: 0.0015 [11-22 20:36:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.42 Lm: 7.164 (7.101) Lt: 6.560 (6.467) Accm: 1.85 (1.98) Acct: 3.10 (3.02) proj_loss: -0.4917 (-0.4969) time: 0.9268 data: 0.0016 [11-22 20:36:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.42 Lm: 7.032 (7.038) Lt: 6.365 (6.423) Accm: 2.14 (2.19) Acct: 3.06 (3.26) proj_loss: -0.4762 (-0.4805) time: 0.9268 data: 0.0015 [11-22 20:36:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.42 Lm: 7.127 (7.142) Lt: 6.544 (6.530) Accm: 2.00 (1.82) Acct: 2.82 (2.82) proj_loss: -0.4715 (-0.4742) time: 0.9268 data: 0.0017 [11-22 20:36:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.42 Lm: 7.120 (7.080) Lt: 6.501 (6.479) Accm: 1.78 (1.86) Acct: 2.89 (2.86) proj_loss: -0.4761 (-0.4779) time: 0.9268 data: 0.0018 [11-22 20:36:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 9/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.42 Lm: 7.007 (7.033) Lt: 6.342 (6.385) Accm: 2.24 (2.19) Acct: 3.51 (3.51) proj_loss: -0.4700 (-0.4723) time: 0.9268 data: 0.0019 [11-22 20:36:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 9/350] Total time: 0:26:06 (0.939 s / it) [11-22 20:36:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 9/350] Total time: 0:26:06 (0.939 s / it) [11-22 20:36:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 9/350] Total time: 0:26:06 (0.939 s / it) [11-22 20:36:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 9/350] Total time: 0:26:06 (0.939 s / it) [11-22 20:36:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 9/350] Total time: 0:26:06 (0.939 s / it) [11-22 20:36:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 9/350] Total time: 0:26:06 (0.939 s / it) [11-22 20:36:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 9/350] Total time: 0:26:06 (0.939 s / it) [11-22 20:41:20] (me/user/VAR/evaluator.py, line 590)=> downloading InceptionV3 model... [11-22 20:42:41] (home/user/VAR/trainer.py, line 114)=> FID: 10.581002396618317 [11-22 20:42:42] (/home/user/VAR/train.py , line 259)=> [*] [ep9] (val 50000) Lm: 7.0681, Lt: 6.4436, Acc m&t: 2.00 3.10, Val cost: 363.13s [11-22 20:42:42] (/home/user/VAR/train.py , line 264)=> [saving ckpt] ... [saving ckpt](*) finished! @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth [11-22 20:43:49] (/home/user/VAR/train.py , line 276)=> [ep9] (training ) Lm: 7.068 (7.068), Lt: 6.444 (6.444), Acc m&t: 2.00 3.10, Remain: 6 days, 3:01:38, Finish: 2024-11-28 07:38 [11-22 20:43:49] (/home/user/VAR/train.py , line 276)=> [ep9] (training ) Lm: 7.068 (7.068), Lt: 6.444 (6.444), Acc m&t: 2.00 3.10, Remain: 6 days, 3:04:10, Finish: 2024-11-28 07:40 [11-22 20:43:49] (/home/user/VAR/train.py , line 276)=> [ep9] (training ) Lm: 7.068 (7.068), Lt: 6.444 (6.444), Acc m&t: 2.00 3.10, Remain: 6 days, 3:02:57, Finish: 2024-11-28 07:39 [11-22 20:43:49] (/home/user/VAR/train.py , line 276)=> [ep9] (training ) Lm: 7.068 (7.068), Lt: 6.444 (6.444), Acc m&t: 2.00 3.10, Remain: 6 days, 3:04:15, Finish: 2024-11-28 07:40 [11-22 20:43:49] (/home/user/VAR/train.py , line 276)=> [ep9] (training ) Lm: 7.068 (7.068), Lt: 6.444 (6.444), Acc m&t: 2.00 3.10, Remain: 6 days, 3:03:36, Finish: 2024-11-28 07:40 [11-22 20:43:49] (/home/user/VAR/train.py , line 276)=> [ep9] (training ) Lm: 7.068 (7.068), Lt: 6.444 (6.444), Acc m&t: 2.00 3.10, Remain: 6 days, 3:01:03, Finish: 2024-11-28 07:37 [11-22 20:43:49] (/home/user/VAR/train.py , line 276)=> [ep9] (training ) Lm: 7.068 (7.068), Lt: 6.444 (6.444), Acc m&t: 2.00 3.10, Remain: 6 days, 3:05:17, Finish: 2024-11-28 07:41 [11-22 20:43:49] (/home/user/VAR/train.py , line 276)=> [ep9] (training ) Lm: 7.068 (7.068), Lt: 6.444 (6.444), Acc m&t: 2.00 3.10, Remain: 6 days, 3:04:10, Finish: 2024-11-28 07:40 [11-22 20:43:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 0/1669] eta: 0:25:47 tlr: 0.00024 tnm: 0.44 Lm: 6.978 (6.978) Lt: 6.278 (6.278) Accm: 2.14 (2.14) Acct: 3.17 (3.17) proj_loss: -0.4830 (-0.4830) time: 0.9270 data: 0.0003 [11-22 20:43:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 0/1669] eta: 0:25:46 tlr: 0.00024 tnm: 0.44 Lm: 7.060 (7.060) Lt: 6.394 (6.394) Accm: 2.13 (2.13) Acct: 3.58 (3.58) proj_loss: -0.4792 (-0.4792) time: 0.9266 data: 0.0003 [11-22 20:43:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 0/1669] eta: 0:25:45 tlr: 0.00024 tnm: 0.44 Lm: 7.227 (7.227) Lt: 6.628 (6.628) Accm: 1.59 (1.59) Acct: 2.62 (2.62) proj_loss: -0.4992 (-0.4992) time: 0.9261 data: 0.0004 [11-22 20:43:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 0/1669] eta: 0:27:11 tlr: 0.00024 tnm: 0.44 Lm: 7.019 (7.019) Lt: 6.309 (6.309) Accm: 2.11 (2.11) Acct: 3.51 (3.51) proj_loss: -0.4798 (-0.4798) time: 0.9776 data: 0.0004 [11-22 20:43:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 0/1669] eta: 0:25:46 tlr: 0.00024 tnm: 0.44 Lm: 6.846 (6.846) Lt: 6.139 (6.139) Accm: 2.39 (2.39) Acct: 3.51 (3.51) proj_loss: -0.4533 (-0.4533) time: 0.9269 data: 0.0003 [11-22 20:43:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 0/1669] eta: 0:25:45 tlr: 0.00024 tnm: 0.44 Lm: 6.859 (6.859) Lt: 6.213 (6.213) Accm: 2.42 (2.42) Acct: 4.03 (4.03) proj_loss: -0.5207 (-0.5207) time: 0.9261 data: 0.0004 [11-22 20:43:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 0/1669] eta: 0:25:47 tlr: 0.00024 tnm: 0.44 Lm: 7.020 (7.020) Lt: 6.372 (6.372) Accm: 1.72 (1.72) Acct: 2.96 (2.96) proj_loss: -0.4576 (-0.4576) time: 0.9274 data: 0.0004 [11-22 20:43:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 0/1669] eta: 0:25:47 tlr: 0.00024 tnm: 0.44 Lm: 7.016 (7.016) Lt: 6.347 (6.347) Accm: 1.68 (1.68) Acct: 3.10 (3.10) proj_loss: -0.4893 (-0.4893) time: 0.9272 data: 0.0004 [11-22 20:50:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 417/1669] eta: 0:19:21 tlr: 0.00024 tnm: 0.49 Lm: 6.997 (6.997) Lt: 6.332 (6.332) Accm: 1.92 (1.92) Acct: 3.34 (3.34) proj_loss: -0.4871 (-0.4871) time: 0.9254 data: 0.0003 [11-22 20:50:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 417/1669] eta: 0:19:21 tlr: 0.00024 tnm: 0.49 Lm: 7.049 (7.049) Lt: 6.364 (6.364) Accm: 2.08 (2.08) Acct: 3.29 (3.29) proj_loss: -0.4784 (-0.4784) time: 0.9254 data: 0.0002 [11-22 20:50:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 417/1669] eta: 0:19:21 tlr: 0.00024 tnm: 0.49 Lm: 6.945 (6.945) Lt: 6.254 (6.254) Accm: 2.29 (2.29) Acct: 3.70 (3.70) proj_loss: -0.5048 (-0.5048) time: 0.9254 data: 0.0003 [11-22 20:50:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 417/1669] eta: 0:19:21 tlr: 0.00024 tnm: 0.49 Lm: 7.094 (7.094) Lt: 6.475 (6.475) Accm: 1.75 (1.75) Acct: 2.89 (2.89) proj_loss: -0.4653 (-0.4653) time: 0.9254 data: 0.0002 [11-22 20:50:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 417/1669] eta: 0:19:21 tlr: 0.00024 tnm: 0.49 Lm: 7.245 (7.245) Lt: 6.656 (6.656) Accm: 1.65 (1.65) Acct: 2.60 (2.60) proj_loss: -0.4894 (-0.4894) time: 0.9253 data: 0.0003 [11-22 20:50:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 417/1669] eta: 0:19:21 tlr: 0.00024 tnm: 0.49 Lm: 6.942 (6.942) Lt: 6.238 (6.238) Accm: 2.21 (2.21) Acct: 3.50 (3.50) proj_loss: -0.4871 (-0.4871) time: 0.9254 data: 0.0003 [11-22 20:50:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 417/1669] eta: 0:19:21 tlr: 0.00024 tnm: 0.49 Lm: 6.937 (6.937) Lt: 6.225 (6.225) Accm: 2.19 (2.19) Acct: 3.46 (3.46) proj_loss: -0.4672 (-0.4672) time: 0.9254 data: 0.0003 [11-22 20:50:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 417/1669] eta: 0:19:21 tlr: 0.00024 tnm: 0.49 Lm: 7.046 (7.046) Lt: 6.423 (6.423) Accm: 1.97 (1.97) Acct: 3.12 (3.12) proj_loss: -0.4892 (-0.4892) time: 0.9254 data: 0.0003 [11-22 20:56:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.46 Lm: 7.060 (7.076) Lt: 6.453 (6.458) Accm: 1.86 (1.93) Acct: 2.89 (3.04) proj_loss: -0.4954 (-0.4913) time: 0.9267 data: 0.0003 [11-22 20:56:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.46 Lm: 7.227 (7.206) Lt: 6.628 (6.612) Accm: 1.70 (1.71) Acct: 2.62 (2.71) proj_loss: -0.4992 (-0.5026) time: 0.9267 data: 0.0003 [11-22 20:56:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.46 Lm: 7.028 (6.986) Lt: 6.312 (6.296) Accm: 2.01 (2.13) Acct: 3.41 (3.34) proj_loss: -0.4730 (-0.4692) time: 0.9267 data: 0.0003 [11-22 20:56:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.46 Lm: 7.015 (6.969) Lt: 6.294 (6.280) Accm: 2.20 (2.26) Acct: 3.79 (3.73) proj_loss: -0.4915 (-0.5003) time: 0.9268 data: 0.0003 [11-22 20:56:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.46 Lm: 7.080 (7.103) Lt: 6.419 (6.433) Accm: 2.04 (1.96) Acct: 3.06 (3.02) proj_loss: -0.4798 (-0.4838) time: 0.9268 data: 0.0003 [11-22 20:56:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.46 Lm: 6.993 (6.996) Lt: 6.347 (6.346) Accm: 2.14 (2.00) Acct: 3.58 (3.44) proj_loss: -0.4893 (-0.4944) time: 0.9267 data: 0.0003 [11-22 20:56:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.46 Lm: 7.168 (7.159) Lt: 6.579 (6.556) Accm: 1.72 (1.70) Acct: 2.82 (2.80) proj_loss: -0.4730 (-0.4828) time: 0.9267 data: 0.0003 [11-22 20:56:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.46 Lm: 6.978 (6.998) Lt: 6.278 (6.333) Accm: 2.14 (2.07) Acct: 3.17 (3.18) proj_loss: -0.4913 (-0.5027) time: 0.9267 data: 0.0003 [11-22 21:03:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.40 Lm: 6.978 (6.993) Lt: 6.268 (6.315) Accm: 2.18 (2.11) Acct: 3.10 (3.14) proj_loss: -0.4886 (-0.4985) time: 0.9280 data: 0.0003 [11-22 21:03:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.40 Lm: 7.082 (7.099) Lt: 6.387 (6.414) Accm: 1.94 (1.93) Acct: 3.08 (3.04) proj_loss: -0.4794 (-0.4826) time: 0.9280 data: 0.0003 [11-22 21:03:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.40 Lm: 7.005 (7.032) Lt: 6.361 (6.399) Accm: 1.91 (1.91) Acct: 3.34 (3.23) proj_loss: -0.4991 (-0.4983) time: 0.9280 data: 0.0003 [11-22 21:03:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.40 Lm: 7.024 (6.987) Lt: 6.313 (6.311) Accm: 2.18 (2.12) Acct: 3.58 (3.48) proj_loss: -0.5034 (-0.5041) time: 0.9280 data: 0.0003 [11-22 21:03:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.40 Lm: 7.009 (6.987) Lt: 6.347 (6.318) Accm: 2.11 (2.15) Acct: 3.25 (3.22) proj_loss: -0.4771 (-0.4775) time: 0.9280 data: 0.0003 [11-22 21:03:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.40 Lm: 7.046 (7.048) Lt: 6.423 (6.434) Accm: 2.00 (2.12) Acct: 3.24 (3.31) proj_loss: -0.4970 (-0.4931) time: 0.9280 data: 0.0003 [11-22 21:03:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.40 Lm: 7.202 (7.199) Lt: 6.619 (6.611) Accm: 1.75 (1.73) Acct: 2.60 (2.64) proj_loss: -0.5053 (-0.5048) time: 0.9280 data: 0.0003 [11-22 21:03:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.40 Lm: 7.094 (7.104) Lt: 6.475 (6.493) Accm: 1.75 (1.89) Acct: 2.89 (3.04) proj_loss: -0.4798 (-0.4837) time: 0.9280 data: 0.0002 [11-22 21:09:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.38 Lm: 7.020 (7.053) Lt: 6.372 (6.440) Accm: 1.78 (2.05) Acct: 2.96 (3.24) proj_loss: -0.4865 (-0.4881) time: 0.9293 data: 0.0017 [11-22 21:09:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 10/350] Total time: 0:25:48 (0.928 s / it) [11-22 21:09:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.38 Lm: 7.028 (7.003) Lt: 6.383 (6.345) Accm: 2.01 (2.12) Acct: 3.10 (3.15) proj_loss: -0.4812 (-0.4825) time: 0.9294 data: 0.0018 [11-22 21:09:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.38 Lm: 7.016 (7.035) Lt: 6.350 (6.389) Accm: 2.05 (1.94) Acct: 3.37 (3.26) proj_loss: -0.4893 (-0.4961) time: 0.9293 data: 0.0016 [11-22 21:09:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.38 Lm: 7.080 (7.086) Lt: 6.402 (6.411) Accm: 1.98 (1.94) Acct: 3.06 (3.03) proj_loss: -0.4798 (-0.4903) time: 0.9294 data: 0.0016 [11-22 21:09:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.38 Lm: 6.978 (6.994) Lt: 6.278 (6.330) Accm: 2.21 (2.15) Acct: 3.17 (3.28) proj_loss: -0.4913 (-0.5018) time: 0.9293 data: 0.0019 [11-22 21:09:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.38 Lm: 7.037 (7.046) Lt: 6.394 (6.426) Accm: 2.13 (2.17) Acct: 3.58 (3.38) proj_loss: -0.4954 (-0.4901) time: 0.9293 data: 0.0018 [11-22 21:09:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.38 Lm: 7.032 (7.027) Lt: 6.332 (6.364) Accm: 2.16 (2.05) Acct: 3.37 (3.33) proj_loss: -0.4915 (-0.5004) time: 0.9294 data: 0.0021 [11-22 21:09:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 10/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.38 Lm: 7.178 (7.155) Lt: 6.611 (6.555) Accm: 1.79 (1.79) Acct: 2.62 (2.71) proj_loss: -0.4992 (-0.5006) time: 0.9293 data: 0.0019 [11-22 21:09:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 10/350] Total time: 0:25:48 (0.928 s / it) [11-22 21:09:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 10/350] Total time: 0:25:48 (0.928 s / it) [11-22 21:09:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 10/350] Total time: 0:25:48 (0.928 s / it) [11-22 21:09:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 10/350] Total time: 0:25:48 (0.928 s / it) [11-22 21:09:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 10/350] Total time: 0:25:48 (0.928 s / it) [11-22 21:09:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 10/350] Total time: 0:25:48 (0.928 s / it) [11-22 21:09:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 10/350] Total time: 0:25:48 (0.928 s / it) [11-22 21:09:38] (/home/user/VAR/train.py , line 276)=> [ep10] (training ) Lm: 7.023 (7.023), Lt: 6.381 (6.381), Acc m&t: 2.11 3.27, Remain: 6 days, 3:16:59, Finish: 2024-11-28 08:26 [11-22 21:09:38] (/home/user/VAR/train.py , line 276)=> [ep10] (training ) Lm: 7.023 (7.023), Lt: 6.381 (6.381), Acc m&t: 2.11 3.27, Remain: 6 days, 3:16:11, Finish: 2024-11-28 08:25 [11-22 21:09:38] (/home/user/VAR/train.py , line 276)=> [ep10] (training ) Lm: 7.023 (7.023), Lt: 6.381 (6.381), Acc m&t: 2.11 3.27, Remain: 6 days, 3:16:16, Finish: 2024-11-28 08:25 [11-22 21:09:38] (/home/user/VAR/train.py , line 276)=> [ep10] (training ) Lm: 7.023 (7.023), Lt: 6.381 (6.381), Acc m&t: 2.11 3.27, Remain: 6 days, 3:15:46, Finish: 2024-11-28 08:25 [11-22 21:09:38] (/home/user/VAR/train.py , line 276)=> [ep10] (training ) Lm: 7.023 (7.023), Lt: 6.381 (6.381), Acc m&t: 2.11 3.27, Remain: 6 days, 3:17:08, Finish: 2024-11-28 08:26 [11-22 21:09:38] (/home/user/VAR/train.py , line 276)=> [ep10] (training ) Lm: 7.023 (7.023), Lt: 6.381 (6.381), Acc m&t: 2.11 3.27, Remain: 6 days, 3:14:45, Finish: 2024-11-28 08:24 [11-22 21:09:38] (/home/user/VAR/train.py , line 276)=> [ep10] (training ) Lm: 7.023 (7.023), Lt: 6.381 (6.381), Acc m&t: 2.11 3.27, Remain: 6 days, 3:16:18, Finish: 2024-11-28 08:25 [11-22 21:09:38] (/home/user/VAR/train.py , line 276)=> [ep10] (training ) Lm: 7.023 (7.023), Lt: 6.381 (6.381), Acc m&t: 2.11 3.27, Remain: 6 days, 3:18:07, Finish: 2024-11-28 08:27 [11-22 21:09:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 0/1669] eta: 0:24:24 tlr: 0.00024 tnm: 0.40 Lm: 7.153 (7.153) Lt: 6.571 (6.571) Accm: 1.85 (1.85) Acct: 3.10 (3.10) proj_loss: -0.4799 (-0.4799) time: 0.8774 data: 0.0003 [11-22 21:09:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 0/1669] eta: 0:24:25 tlr: 0.00024 tnm: 0.40 Lm: 7.081 (7.081) Lt: 6.478 (6.478) Accm: 1.95 (1.95) Acct: 3.00 (3.00) proj_loss: -0.4974 (-0.4974) time: 0.8778 data: 0.0004 [11-22 21:09:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 0/1669] eta: 0:25:25 tlr: 0.00024 tnm: 0.40 Lm: 6.963 (6.963) Lt: 6.288 (6.288) Accm: 2.35 (2.35) Acct: 3.55 (3.55) proj_loss: -0.4779 (-0.4779) time: 0.9142 data: 0.0003 [11-22 21:09:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 0/1669] eta: 0:24:25 tlr: 0.00024 tnm: 0.40 Lm: 6.995 (6.995) Lt: 6.414 (6.414) Accm: 2.08 (2.08) Acct: 2.96 (2.96) proj_loss: -0.5076 (-0.5076) time: 0.8783 data: 0.0004 [11-22 21:09:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 0/1669] eta: 0:24:26 tlr: 0.00024 tnm: 0.40 Lm: 6.969 (6.969) Lt: 6.358 (6.358) Accm: 2.01 (2.01) Acct: 2.79 (2.79) proj_loss: -0.4782 (-0.4782) time: 0.8785 data: 0.0004 [11-22 21:09:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 0/1669] eta: 0:24:26 tlr: 0.00024 tnm: 0.40 Lm: 6.892 (6.892) Lt: 6.184 (6.184) Accm: 2.46 (2.46) Acct: 3.72 (3.72) proj_loss: -0.4775 (-0.4775) time: 0.8784 data: 0.0004 [11-22 21:09:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 0/1669] eta: 0:24:26 tlr: 0.00024 tnm: 0.40 Lm: 6.968 (6.968) Lt: 6.348 (6.348) Accm: 2.13 (2.13) Acct: 2.89 (2.89) proj_loss: -0.5059 (-0.5059) time: 0.8786 data: 0.0003 [11-22 21:09:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 0/1669] eta: 0:24:25 tlr: 0.00024 tnm: 0.40 Lm: 7.100 (7.100) Lt: 6.462 (6.462) Accm: 1.91 (1.91) Acct: 2.62 (2.62) proj_loss: -0.4986 (-0.4986) time: 0.8782 data: 0.0004 [11-22 21:16:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.44 Lm: 7.066 (7.066) Lt: 6.440 (6.440) Accm: 1.97 (1.97) Acct: 2.86 (2.86) proj_loss: -0.5021 (-0.5021) time: 0.9299 data: 0.0003 [11-22 21:16:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.44 Lm: 7.010 (7.010) Lt: 6.398 (6.398) Accm: 2.06 (2.06) Acct: 3.03 (3.03) proj_loss: -0.4844 (-0.4844) time: 0.9299 data: 0.0003 [11-22 21:16:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.44 Lm: 7.058 (7.058) Lt: 6.435 (6.435) Accm: 2.08 (2.08) Acct: 3.39 (3.39) proj_loss: -0.5004 (-0.5004) time: 0.9299 data: 0.0003 [11-22 21:16:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.44 Lm: 6.979 (6.979) Lt: 6.355 (6.355) Accm: 2.03 (2.03) Acct: 3.20 (3.20) proj_loss: -0.4917 (-0.4917) time: 0.9299 data: 0.0003 [11-22 21:16:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 417/1669] eta: 0:19:21 tlr: 0.00024 tnm: 0.44 Lm: 7.020 (7.020) Lt: 6.363 (6.363) Accm: 2.20 (2.20) Acct: 3.31 (3.31) proj_loss: -0.4738 (-0.4738) time: 0.9299 data: 0.0003 [11-22 21:16:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.44 Lm: 6.955 (6.955) Lt: 6.306 (6.306) Accm: 2.09 (2.09) Acct: 3.08 (3.08) proj_loss: -0.5055 (-0.5055) time: 0.9299 data: 0.0003 [11-22 21:16:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.44 Lm: 6.950 (6.950) Lt: 6.271 (6.271) Accm: 2.29 (2.29) Acct: 3.55 (3.55) proj_loss: -0.4806 (-0.4806) time: 0.9299 data: 0.0003 [11-22 21:16:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.44 Lm: 7.156 (7.156) Lt: 6.554 (6.554) Accm: 1.89 (1.89) Acct: 3.00 (3.00) proj_loss: -0.4772 (-0.4772) time: 0.9299 data: 0.0003 [11-22 21:22:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 834/1669] eta: 0:13:07 tlr: 0.00024 tnm: 0.47 Lm: 7.153 (7.061) Lt: 6.537 (6.426) Accm: 1.94 (2.12) Acct: 3.10 (3.37) proj_loss: -0.4799 (-0.4926) time: 0.9279 data: 0.0003 [11-22 21:22:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 834/1669] eta: 0:13:07 tlr: 0.00024 tnm: 0.47 Lm: 6.963 (6.958) Lt: 6.288 (6.308) Accm: 2.35 (2.41) Acct: 3.55 (3.66) proj_loss: -0.4779 (-0.4873) time: 0.9279 data: 0.0003 [11-22 21:22:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 834/1669] eta: 0:13:07 tlr: 0.00024 tnm: 0.47 Lm: 7.043 (7.021) Lt: 6.358 (6.383) Accm: 2.01 (2.04) Acct: 3.03 (3.03) proj_loss: -0.4799 (-0.4829) time: 0.9279 data: 0.0002 [11-22 21:22:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 834/1669] eta: 0:13:07 tlr: 0.00024 tnm: 0.47 Lm: 6.974 (6.958) Lt: 6.291 (6.278) Accm: 2.46 (2.36) Acct: 3.72 (3.66) proj_loss: -0.4838 (-0.4860) time: 0.9279 data: 0.0003 [11-22 21:22:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 834/1669] eta: 0:13:07 tlr: 0.00024 tnm: 0.47 Lm: 6.941 (6.865) Lt: 6.263 (6.169) Accm: 2.13 (2.37) Acct: 3.27 (3.52) proj_loss: -0.5052 (-0.5008) time: 0.9279 data: 0.0003 [11-22 21:22:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 834/1669] eta: 0:13:07 tlr: 0.00024 tnm: 0.47 Lm: 6.963 (6.953) Lt: 6.295 (6.320) Accm: 2.08 (2.12) Acct: 3.44 (3.28) proj_loss: -0.4759 (-0.4856) time: 0.9279 data: 0.0003 [11-22 21:22:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 834/1669] eta: 0:13:07 tlr: 0.00024 tnm: 0.47 Lm: 7.081 (7.116) Lt: 6.478 (6.479) Accm: 1.95 (1.99) Acct: 3.00 (3.21) proj_loss: -0.5033 (-0.5054) time: 0.9279 data: 0.0003 [11-22 21:22:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [ 834/1669] eta: 0:13:07 tlr: 0.00024 tnm: 0.47 Lm: 7.032 (7.054) Lt: 6.430 (6.436) Accm: 2.04 (2.14) Acct: 3.10 (3.05) proj_loss: -0.4986 (-0.5009) time: 0.9279 data: 0.0003 [11-22 21:29:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [1251/1669] eta: 0:06:31 tlr: 0.00024 tnm: 0.43 Lm: 7.030 (7.044) Lt: 6.423 (6.412) Accm: 2.19 (2.19) Acct: 3.27 (3.16) proj_loss: -0.4985 (-0.4974) time: 0.9244 data: 0.0003 [11-22 21:29:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.43 Lm: 7.006 (6.988) Lt: 6.356 (6.328) Accm: 2.06 (2.08) Acct: 3.15 (3.21) proj_loss: -0.4839 (-0.4841) time: 0.9244 data: 0.0003 [11-22 21:29:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [1251/1669] eta: 0:06:31 tlr: 0.00024 tnm: 0.43 Lm: 7.125 (7.129) Lt: 6.523 (6.501) Accm: 1.88 (1.91) Acct: 2.93 (3.03) proj_loss: -0.5004 (-0.5031) time: 0.9244 data: 0.0002 [11-22 21:29:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [1251/1669] eta: 0:06:31 tlr: 0.00024 tnm: 0.43 Lm: 6.990 (6.986) Lt: 6.325 (6.325) Accm: 2.29 (2.22) Acct: 3.55 (3.44) proj_loss: -0.4867 (-0.4869) time: 0.9244 data: 0.0003 [11-22 21:29:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.43 Lm: 6.910 (6.932) Lt: 6.244 (6.273) Accm: 2.37 (2.41) Acct: 3.68 (3.70) proj_loss: -0.4918 (-0.4919) time: 0.9244 data: 0.0003 [11-22 21:29:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [1251/1669] eta: 0:06:31 tlr: 0.00024 tnm: 0.43 Lm: 6.979 (6.974) Lt: 6.351 (6.342) Accm: 2.19 (2.20) Acct: 3.43 (3.31) proj_loss: -0.4880 (-0.4892) time: 0.9244 data: 0.0002 [11-22 21:29:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [1251/1669] eta: 0:06:31 tlr: 0.00024 tnm: 0.43 Lm: 6.955 (6.911) Lt: 6.306 (6.249) Accm: 2.11 (2.30) Acct: 3.10 (3.37) proj_loss: -0.5003 (-0.4995) time: 0.9244 data: 0.0003 [11-22 21:29:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.43 Lm: 7.012 (6.997) Lt: 6.353 (6.351) Accm: 2.08 (2.15) Acct: 3.37 (3.44) proj_loss: -0.4995 (-0.4993) time: 0.9244 data: 0.0003 [11-22 21:35:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.36 Lm: 6.877 (6.973) Lt: 6.185 (6.318) Accm: 2.23 (2.23) Acct: 3.65 (3.58) proj_loss: -0.4799 (-0.4929) time: 0.9287 data: 0.0017 [11-22 21:35:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 11/350] Total time: 0:26:00 (0.935 s / it) [11-22 21:35:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.36 Lm: 7.169 (7.144) Lt: 6.568 (6.529) Accm: 1.81 (1.86) Acct: 2.86 (2.93) proj_loss: -0.5033 (-0.5037) time: 0.9287 data: 0.0015 [11-22 21:35:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.36 Lm: 6.963 (6.967) Lt: 6.295 (6.322) Accm: 2.29 (2.28) Acct: 3.44 (3.44) proj_loss: -0.4759 (-0.4865) time: 0.9286 data: 0.0018 [11-22 21:35:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.36 Lm: 7.043 (7.003) Lt: 6.358 (6.354) Accm: 2.01 (2.06) Acct: 3.27 (3.23) proj_loss: -0.4878 (-0.4864) time: 0.9286 data: 0.0015 [11-22 21:35:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.36 Lm: 7.032 (7.052) Lt: 6.430 (6.424) Accm: 2.05 (2.16) Acct: 3.10 (3.15) proj_loss: -0.4985 (-0.4965) time: 0.9287 data: 0.0017 [11-22 21:35:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.36 Lm: 6.907 (6.927) Lt: 6.226 (6.264) Accm: 2.39 (2.41) Acct: 3.62 (3.68) proj_loss: -0.5056 (-0.4959) time: 0.9287 data: 0.0017 [11-22 21:35:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.36 Lm: 6.967 (6.922) Lt: 6.287 (6.256) Accm: 2.10 (2.23) Acct: 2.93 (3.26) proj_loss: -0.5010 (-0.4998) time: 0.9286 data: 0.0017 [11-22 21:35:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 11/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.36 Lm: 7.007 (6.999) Lt: 6.359 (6.342) Accm: 2.13 (2.20) Acct: 3.62 (3.48) proj_loss: -0.4850 (-0.4865) time: 0.9287 data: 0.0017 [11-22 21:35:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 11/350] Total time: 0:26:00 (0.935 s / it) [11-22 21:35:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 11/350] Total time: 0:26:00 (0.935 s / it) [11-22 21:35:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 11/350] Total time: 0:26:00 (0.935 s / it) [11-22 21:35:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 11/350] Total time: 0:26:00 (0.935 s / it) [11-22 21:35:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 11/350] Total time: 0:26:00 (0.935 s / it) [11-22 21:35:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 11/350] Total time: 0:26:00 (0.935 s / it) [11-22 21:35:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 11/350] Total time: 0:26:00 (0.935 s / it) [11-22 21:35:39] (/home/user/VAR/train.py , line 276)=> [ep11] (training ) Lm: 6.991 (6.991), Lt: 6.341 (6.341), Acc m&t: 2.20 3.42, Remain: 6 days, 2:24:18, Finish: 2024-11-28 07:59 [11-22 21:35:39] (/home/user/VAR/train.py , line 276)=> [ep11] (training ) Lm: 6.991 (6.991), Lt: 6.341 (6.341), Acc m&t: 2.20 3.42, Remain: 6 days, 2:24:06, Finish: 2024-11-28 07:59 [11-22 21:35:39] (/home/user/VAR/train.py , line 276)=> [ep11] (training ) Lm: 6.991 (6.991), Lt: 6.341 (6.341), Acc m&t: 2.20 3.42, Remain: 6 days, 2:25:54, Finish: 2024-11-28 08:01 [11-22 21:35:39] (/home/user/VAR/train.py , line 276)=> [ep11] (training ) Lm: 6.991 (6.991), Lt: 6.341 (6.341), Acc m&t: 2.20 3.42, Remain: 6 days, 2:25:45, Finish: 2024-11-28 08:01 [11-22 21:35:39] (/home/user/VAR/train.py , line 276)=> [ep11] (training ) Lm: 6.991 (6.991), Lt: 6.341 (6.341), Acc m&t: 2.20 3.42, Remain: 6 days, 2:25:27, Finish: 2024-11-28 08:01 [11-22 21:35:39] (/home/user/VAR/train.py , line 276)=> [ep11] (training ) Lm: 6.991 (6.991), Lt: 6.341 (6.341), Acc m&t: 2.20 3.42, Remain: 6 days, 2:26:56, Finish: 2024-11-28 08:02 [11-22 21:35:39] (/home/user/VAR/train.py , line 276)=> [ep11] (training ) Lm: 6.991 (6.991), Lt: 6.341 (6.341), Acc m&t: 2.20 3.42, Remain: 6 days, 2:23:15, Finish: 2024-11-28 07:58 [11-22 21:35:39] (/home/user/VAR/train.py , line 276)=> [ep11] (training ) Lm: 6.991 (6.991), Lt: 6.341 (6.341), Acc m&t: 2.20 3.42, Remain: 6 days, 2:23:54, Finish: 2024-11-28 07:59 [11-22 21:35:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 0/1669] eta: 0:25:01 tlr: 0.00024 tnm: 0.44 Lm: 6.930 (6.930) Lt: 6.286 (6.286) Accm: 2.61 (2.61) Acct: 4.20 (4.20) proj_loss: -0.4659 (-0.4659) time: 0.8997 data: 0.0004 [11-22 21:35:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 0/1669] eta: 0:24:53 tlr: 0.00024 tnm: 0.44 Lm: 7.125 (7.125) Lt: 6.469 (6.469) Accm: 1.85 (1.85) Acct: 2.93 (2.93) proj_loss: -0.4987 (-0.4987) time: 0.8950 data: 0.0003 [11-22 21:35:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 0/1669] eta: 0:25:03 tlr: 0.00024 tnm: 0.44 Lm: 6.887 (6.887) Lt: 6.217 (6.217) Accm: 2.61 (2.61) Acct: 4.30 (4.30) proj_loss: -0.4819 (-0.4819) time: 0.9009 data: 0.0003 [11-22 21:35:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 0/1669] eta: 0:25:03 tlr: 0.00024 tnm: 0.44 Lm: 6.955 (6.955) Lt: 6.250 (6.250) Accm: 2.14 (2.14) Acct: 3.20 (3.20) proj_loss: -0.4934 (-0.4934) time: 0.9010 data: 0.0003 [11-22 21:35:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 0/1669] eta: 0:25:03 tlr: 0.00024 tnm: 0.44 Lm: 7.247 (7.247) Lt: 6.637 (6.637) Accm: 1.57 (1.57) Acct: 2.41 (2.41) proj_loss: -0.5174 (-0.5174) time: 0.9009 data: 0.0003 [11-22 21:35:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 0/1669] eta: 0:24:54 tlr: 0.00024 tnm: 0.44 Lm: 6.905 (6.905) Lt: 6.212 (6.212) Accm: 2.42 (2.42) Acct: 3.65 (3.65) proj_loss: -0.5358 (-0.5358) time: 0.8954 data: 0.0004 [11-22 21:35:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 0/1669] eta: 0:25:04 tlr: 0.00024 tnm: 0.44 Lm: 7.184 (7.184) Lt: 6.601 (6.601) Accm: 1.69 (1.69) Acct: 2.48 (2.48) proj_loss: -0.5033 (-0.5033) time: 0.9012 data: 0.0004 [11-22 21:35:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 0/1669] eta: 0:24:56 tlr: 0.00024 tnm: 0.44 Lm: 7.070 (7.070) Lt: 6.521 (6.521) Accm: 1.89 (1.89) Acct: 2.75 (2.75) proj_loss: -0.5218 (-0.5218) time: 0.8967 data: 0.0003 [11-22 21:42:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 417/1669] eta: 0:19:21 tlr: 0.00024 tnm: 0.38 Lm: 7.065 (7.065) Lt: 6.485 (6.485) Accm: 1.99 (1.99) Acct: 3.08 (3.08) proj_loss: -0.5107 (-0.5107) time: 0.9274 data: 0.0003 [11-22 21:42:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 417/1669] eta: 0:19:21 tlr: 0.00024 tnm: 0.38 Lm: 6.881 (6.881) Lt: 6.198 (6.198) Accm: 2.48 (2.48) Acct: 3.84 (3.84) proj_loss: -0.5016 (-0.5016) time: 0.9274 data: 0.0002 [11-22 21:42:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 417/1669] eta: 0:19:21 tlr: 0.00024 tnm: 0.38 Lm: 6.985 (6.985) Lt: 6.328 (6.328) Accm: 2.35 (2.35) Acct: 3.74 (3.74) proj_loss: -0.4855 (-0.4855) time: 0.9274 data: 0.0003 [11-22 21:42:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 417/1669] eta: 0:19:21 tlr: 0.00024 tnm: 0.38 Lm: 7.010 (7.010) Lt: 6.348 (6.348) Accm: 2.16 (2.16) Acct: 3.29 (3.29) proj_loss: -0.5215 (-0.5215) time: 0.9274 data: 0.0003 [11-22 21:42:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 417/1669] eta: 0:19:21 tlr: 0.00024 tnm: 0.38 Lm: 7.042 (7.042) Lt: 6.413 (6.413) Accm: 2.01 (2.01) Acct: 2.96 (2.96) proj_loss: -0.5037 (-0.5037) time: 0.9274 data: 0.0003 [11-22 21:42:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 417/1669] eta: 0:19:21 tlr: 0.00024 tnm: 0.38 Lm: 6.966 (6.966) Lt: 6.283 (6.283) Accm: 2.12 (2.12) Acct: 3.22 (3.22) proj_loss: -0.4925 (-0.4925) time: 0.9274 data: 0.0003 [11-22 21:42:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 417/1669] eta: 0:19:21 tlr: 0.00024 tnm: 0.38 Lm: 7.020 (7.020) Lt: 6.395 (6.395) Accm: 2.16 (2.16) Acct: 3.31 (3.31) proj_loss: -0.4994 (-0.4994) time: 0.9274 data: 0.0003 [11-22 21:42:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 417/1669] eta: 0:19:21 tlr: 0.00024 tnm: 0.38 Lm: 7.027 (7.027) Lt: 6.409 (6.409) Accm: 2.24 (2.24) Acct: 3.62 (3.62) proj_loss: -0.4858 (-0.4858) time: 0.9274 data: 0.0002 [11-22 21:48:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.39 Lm: 6.940 (6.998) Lt: 6.286 (6.354) Accm: 1.97 (2.15) Acct: 3.03 (3.40) proj_loss: -0.5058 (-0.4928) time: 0.9292 data: 0.0002 [11-22 21:48:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.39 Lm: 7.116 (7.072) Lt: 6.484 (6.430) Accm: 1.89 (2.00) Acct: 2.93 (3.17) proj_loss: -0.5073 (-0.5137) time: 0.9291 data: 0.0002 [11-22 21:48:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.39 Lm: 6.977 (6.913) Lt: 6.317 (6.237) Accm: 2.07 (2.34) Acct: 3.24 (3.64) proj_loss: -0.4987 (-0.4934) time: 0.9291 data: 0.0002 [11-22 21:48:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.39 Lm: 6.819 (6.953) Lt: 6.152 (6.309) Accm: 2.74 (2.42) Acct: 4.20 (3.75) proj_loss: -0.4871 (-0.4953) time: 0.9291 data: 0.0003 [11-22 21:48:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.39 Lm: 7.060 (7.012) Lt: 6.450 (6.381) Accm: 2.08 (2.26) Acct: 3.41 (3.57) proj_loss: -0.5047 (-0.5087) time: 0.9291 data: 0.0003 [11-22 21:48:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.39 Lm: 7.184 (7.100) Lt: 6.601 (6.479) Accm: 2.24 (2.09) Acct: 3.44 (3.16) proj_loss: -0.5033 (-0.4977) time: 0.9291 data: 0.0003 [11-22 21:48:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.39 Lm: 7.082 (7.023) Lt: 6.439 (6.396) Accm: 2.08 (2.14) Acct: 3.17 (3.46) proj_loss: -0.4891 (-0.4867) time: 0.9292 data: 0.0003 [11-22 21:48:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.39 Lm: 6.976 (6.978) Lt: 6.317 (6.297) Accm: 2.14 (2.15) Acct: 3.24 (3.31) proj_loss: -0.4916 (-0.4872) time: 0.9292 data: 0.0003 [11-22 21:55:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.35 Lm: 6.989 (6.993) Lt: 6.321 (6.306) Accm: 2.12 (2.09) Acct: 3.22 (3.27) proj_loss: -0.4925 (-0.4914) time: 0.9270 data: 0.0003 [11-22 21:55:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.35 Lm: 7.010 (7.022) Lt: 6.348 (6.370) Accm: 2.11 (2.08) Acct: 3.29 (3.31) proj_loss: -0.5070 (-0.5120) time: 0.9270 data: 0.0002 [11-22 21:55:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.35 Lm: 7.072 (7.065) Lt: 6.436 (6.427) Accm: 2.24 (2.12) Acct: 3.50 (3.25) proj_loss: -0.5037 (-0.5007) time: 0.9270 data: 0.0003 [11-22 21:55:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.35 Lm: 7.024 (7.006) Lt: 6.378 (6.363) Accm: 2.16 (2.26) Acct: 3.55 (3.60) proj_loss: -0.5052 (-0.5079) time: 0.9270 data: 0.0003 [11-22 21:55:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.35 Lm: 6.998 (6.996) Lt: 6.328 (6.351) Accm: 2.27 (2.22) Acct: 3.55 (3.57) proj_loss: -0.4891 (-0.4913) time: 0.9270 data: 0.0002 [11-22 21:55:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.35 Lm: 7.032 (7.034) Lt: 6.409 (6.404) Accm: 1.96 (2.10) Acct: 3.00 (3.25) proj_loss: -0.4900 (-0.4882) time: 0.9270 data: 0.0002 [11-22 21:55:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.35 Lm: 6.925 (6.972) Lt: 6.299 (6.343) Accm: 2.33 (2.30) Acct: 3.46 (3.50) proj_loss: -0.5012 (-0.5003) time: 0.9270 data: 0.0003 [11-22 21:55:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.35 Lm: 6.991 (6.936) Lt: 6.393 (6.300) Accm: 2.09 (2.28) Acct: 3.13 (3.49) proj_loss: -0.4958 (-0.4933) time: 0.9270 data: 0.0002 [11-22 22:01:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.38 Lm: 6.977 (6.943) Lt: 6.317 (6.283) Accm: 2.11 (2.27) Acct: 3.24 (3.49) proj_loss: -0.4929 (-0.4924) time: 0.9286 data: 0.0016 [11-22 22:01:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 12/350] Total time: 0:25:48 (0.928 s / it) [11-22 22:01:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.38 Lm: 6.988 (6.978) Lt: 6.307 (6.321) Accm: 2.24 (2.28) Acct: 3.68 (3.67) proj_loss: -0.5047 (-0.5030) time: 0.9286 data: 0.0016 [11-22 22:01:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.38 Lm: 6.924 (6.981) Lt: 6.272 (6.335) Accm: 2.23 (2.22) Acct: 3.58 (3.57) proj_loss: -0.4892 (-0.4978) time: 0.9286 data: 0.0018 [11-22 22:01:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.38 Lm: 6.970 (7.012) Lt: 6.363 (6.368) Accm: 2.32 (2.15) Acct: 3.34 (3.32) proj_loss: -0.5068 (-0.5072) time: 0.9286 data: 0.0016 [11-22 22:01:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.38 Lm: 6.976 (6.985) Lt: 6.317 (6.305) Accm: 2.14 (2.12) Acct: 3.24 (3.28) proj_loss: -0.4934 (-0.4981) time: 0.9286 data: 0.0017 [11-22 22:01:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.38 Lm: 7.077 (7.043) Lt: 6.453 (6.414) Accm: 1.95 (2.04) Acct: 2.96 (3.20) proj_loss: -0.5058 (-0.4950) time: 0.9286 data: 0.0015 [11-22 22:01:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.38 Lm: 6.979 (7.048) Lt: 6.365 (6.415) Accm: 2.24 (2.15) Acct: 3.44 (3.27) proj_loss: -0.5041 (-0.5039) time: 0.9286 data: 0.0016 [11-22 22:01:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 12/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.38 Lm: 6.820 (6.942) Lt: 6.158 (6.306) Accm: 2.33 (2.30) Acct: 3.27 (3.45) proj_loss: -0.4871 (-0.4946) time: 0.9286 data: 0.0020 [11-22 22:01:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 12/350] Total time: 0:25:48 (0.928 s / it) [11-22 22:01:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 12/350] Total time: 0:25:48 (0.928 s / it) [11-22 22:01:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 12/350] Total time: 0:25:48 (0.928 s / it) [11-22 22:01:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 12/350] Total time: 0:25:48 (0.928 s / it) [11-22 22:01:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 12/350] Total time: 0:25:48 (0.928 s / it) [11-22 22:01:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 12/350] Total time: 0:25:48 (0.928 s / it) [11-22 22:01:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 12/350] Total time: 0:25:48 (0.928 s / it) [11-22 22:01:27] (/home/user/VAR/train.py , line 276)=> [ep12] (training ) Lm: 6.966 (6.966), Lt: 6.305 (6.305), Acc m&t: 2.23 3.49, Remain: 6 days, 2:10:08, Finish: 2024-11-28 08:11 [11-22 22:01:27] (/home/user/VAR/train.py , line 276)=> [ep12] (training ) Lm: 6.966 (6.966), Lt: 6.305 (6.305), Acc m&t: 2.23 3.49, Remain: 6 days, 2:09:40, Finish: 2024-11-28 08:11 [11-22 22:01:27] (/home/user/VAR/train.py , line 276)=> [ep12] (training ) Lm: 6.966 (6.966), Lt: 6.305 (6.305), Acc m&t: 2.23 3.49, Remain: 6 days, 2:10:36, Finish: 2024-11-28 08:12 [11-22 22:01:27] (/home/user/VAR/train.py , line 276)=> [ep12] (training ) Lm: 6.966 (6.966), Lt: 6.305 (6.305), Acc m&t: 2.23 3.49, Remain: 6 days, 2:07:50, Finish: 2024-11-28 08:09 [11-22 22:01:27] (/home/user/VAR/train.py , line 276)=> [ep12] (training ) Lm: 6.966 (6.966), Lt: 6.305 (6.305), Acc m&t: 2.23 3.49, Remain: 6 days, 2:09:31, Finish: 2024-11-28 08:10 [11-22 22:01:27] (/home/user/VAR/train.py , line 276)=> [ep12] (training ) Lm: 6.966 (6.966), Lt: 6.305 (6.305), Acc m&t: 2.23 3.49, Remain: 6 days, 2:06:51, Finish: 2024-11-28 08:08 [11-22 22:01:27] (/home/user/VAR/train.py , line 276)=> [ep12] (training ) Lm: 6.966 (6.966), Lt: 6.305 (6.305), Acc m&t: 2.23 3.49, Remain: 6 days, 2:06:50, Finish: 2024-11-28 08:08 [11-22 22:01:27] (/home/user/VAR/train.py , line 276)=> [ep12] (training ) Lm: 6.966 (6.966), Lt: 6.305 (6.305), Acc m&t: 2.23 3.49, Remain: 6 days, 2:09:28, Finish: 2024-11-28 08:10 [11-22 22:01:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 0/1669] eta: 0:25:04 tlr: 0.00024 tnm: 0.39 Lm: 7.097 (7.097) Lt: 6.510 (6.510) Accm: 1.79 (1.79) Acct: 3.00 (3.00) proj_loss: -0.5070 (-0.5070) time: 0.9014 data: 0.0004 [11-22 22:01:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 0/1669] eta: 0:25:04 tlr: 0.00024 tnm: 0.39 Lm: 6.938 (6.938) Lt: 6.221 (6.221) Accm: 2.65 (2.65) Acct: 3.75 (3.75) proj_loss: -0.4776 (-0.4776) time: 0.9013 data: 0.0003 [11-22 22:01:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 0/1669] eta: 0:25:04 tlr: 0.00024 tnm: 0.39 Lm: 6.719 (6.719) Lt: 6.029 (6.029) Accm: 2.81 (2.81) Acct: 4.41 (4.41) proj_loss: -0.5307 (-0.5307) time: 0.9016 data: 0.0004 [11-22 22:01:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 0/1669] eta: 0:25:04 tlr: 0.00024 tnm: 0.39 Lm: 6.951 (6.951) Lt: 6.275 (6.275) Accm: 2.21 (2.21) Acct: 3.37 (3.37) proj_loss: -0.5068 (-0.5068) time: 0.9013 data: 0.0004 [11-22 22:01:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 0/1669] eta: 0:24:56 tlr: 0.00024 tnm: 0.39 Lm: 6.992 (6.992) Lt: 6.301 (6.301) Accm: 2.10 (2.10) Acct: 3.34 (3.34) proj_loss: -0.4601 (-0.4601) time: 0.8965 data: 0.0004 [11-22 22:01:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 0/1669] eta: 0:25:04 tlr: 0.00024 tnm: 0.39 Lm: 6.795 (6.795) Lt: 6.093 (6.093) Accm: 2.94 (2.94) Acct: 4.48 (4.48) proj_loss: -0.5124 (-0.5124) time: 0.9016 data: 0.0003 [11-22 22:01:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 0/1669] eta: 0:25:02 tlr: 0.00024 tnm: 0.39 Lm: 6.993 (6.993) Lt: 6.342 (6.342) Accm: 2.07 (2.07) Acct: 3.34 (3.34) proj_loss: -0.4986 (-0.4986) time: 0.9003 data: 0.0004 [11-22 22:01:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 0/1669] eta: 0:25:04 tlr: 0.00024 tnm: 0.39 Lm: 6.976 (6.976) Lt: 6.384 (6.384) Accm: 1.94 (1.94) Acct: 2.51 (2.51) proj_loss: -0.4751 (-0.4751) time: 0.9017 data: 0.0004 [11-22 22:08:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 417/1669] eta: 0:19:45 tlr: 0.00024 tnm: 0.35 Lm: 6.867 (6.867) Lt: 6.196 (6.196) Accm: 2.44 (2.44) Acct: 3.72 (3.72) proj_loss: -0.4874 (-0.4874) time: 0.9274 data: 0.0003 [11-22 22:08:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 417/1669] eta: 0:19:46 tlr: 0.00024 tnm: 0.35 Lm: 6.841 (6.841) Lt: 6.136 (6.136) Accm: 2.57 (2.57) Acct: 3.93 (3.93) proj_loss: -0.4926 (-0.4926) time: 0.9274 data: 0.0002 [11-22 22:08:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 417/1669] eta: 0:19:45 tlr: 0.00024 tnm: 0.35 Lm: 6.906 (6.906) Lt: 6.206 (6.206) Accm: 2.42 (2.42) Acct: 3.81 (3.81) proj_loss: -0.4886 (-0.4886) time: 0.9273 data: 0.0003 [11-22 22:08:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 417/1669] eta: 0:19:45 tlr: 0.00024 tnm: 0.35 Lm: 6.971 (6.971) Lt: 6.317 (6.317) Accm: 2.24 (2.24) Acct: 3.31 (3.31) proj_loss: -0.4798 (-0.4798) time: 0.9274 data: 0.0003 [11-22 22:08:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 417/1669] eta: 0:19:46 tlr: 0.00024 tnm: 0.35 Lm: 7.095 (7.095) Lt: 6.482 (6.482) Accm: 1.77 (1.77) Acct: 2.91 (2.91) proj_loss: -0.4995 (-0.4995) time: 0.9273 data: 0.0003 [11-22 22:08:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 417/1669] eta: 0:19:45 tlr: 0.00024 tnm: 0.35 Lm: 6.867 (6.867) Lt: 6.154 (6.154) Accm: 2.69 (2.69) Acct: 4.10 (4.10) proj_loss: -0.5128 (-0.5128) time: 0.9273 data: 0.0003 [11-22 22:08:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 417/1669] eta: 0:19:45 tlr: 0.00024 tnm: 0.35 Lm: 6.878 (6.878) Lt: 6.237 (6.237) Accm: 2.35 (2.35) Acct: 3.81 (3.81) proj_loss: -0.5048 (-0.5048) time: 0.9273 data: 0.0003 [11-22 22:08:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 417/1669] eta: 0:19:45 tlr: 0.00024 tnm: 0.35 Lm: 6.965 (6.965) Lt: 6.279 (6.279) Accm: 2.11 (2.11) Acct: 3.15 (3.15) proj_loss: -0.5111 (-0.5111) time: 0.9273 data: 0.0003 [11-22 22:14:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 834/1669] eta: 0:13:02 tlr: 0.00024 tnm: 0.36 Lm: 6.951 (6.890) Lt: 6.275 (6.185) Accm: 2.21 (2.21) Acct: 3.37 (3.32) proj_loss: -0.5068 (-0.5043) time: 0.9270 data: 0.0003 [11-22 22:14:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 834/1669] eta: 0:13:02 tlr: 0.00024 tnm: 0.36 Lm: 7.094 (7.000) Lt: 6.453 (6.353) Accm: 1.79 (2.07) Acct: 3.00 (3.46) proj_loss: -0.5070 (-0.5087) time: 0.9270 data: 0.0003 [11-22 22:14:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 834/1669] eta: 0:13:02 tlr: 0.00024 tnm: 0.36 Lm: 6.745 (6.809) Lt: 6.060 (6.111) Accm: 2.65 (2.68) Acct: 4.10 (4.06) proj_loss: -0.5003 (-0.4951) time: 0.9270 data: 0.0002 [11-22 22:14:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 834/1669] eta: 0:13:02 tlr: 0.00024 tnm: 0.36 Lm: 6.942 (6.918) Lt: 6.253 (6.222) Accm: 2.52 (2.45) Acct: 3.79 (3.80) proj_loss: -0.4870 (-0.4881) time: 0.9269 data: 0.0003 [11-22 22:14:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 834/1669] eta: 0:13:02 tlr: 0.00024 tnm: 0.36 Lm: 6.876 (6.870) Lt: 6.168 (6.158) Accm: 2.46 (2.61) Acct: 3.82 (4.01) proj_loss: -0.5133 (-0.5237) time: 0.9270 data: 0.0003 [11-22 22:14:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 834/1669] eta: 0:13:02 tlr: 0.00024 tnm: 0.36 Lm: 7.037 (6.936) Lt: 6.435 (6.303) Accm: 2.03 (2.24) Acct: 3.20 (3.60) proj_loss: -0.5016 (-0.5037) time: 0.9270 data: 0.0003 [11-22 22:14:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 834/1669] eta: 0:13:02 tlr: 0.00024 tnm: 0.36 Lm: 6.788 (6.841) Lt: 6.088 (6.160) Accm: 2.43 (2.44) Acct: 3.93 (3.79) proj_loss: -0.4997 (-0.4922) time: 0.9270 data: 0.0003 [11-22 22:14:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [ 834/1669] eta: 0:13:02 tlr: 0.00024 tnm: 0.36 Lm: 6.992 (7.014) Lt: 6.333 (6.370) Accm: 2.14 (2.20) Acct: 3.27 (3.26) proj_loss: -0.4996 (-0.5003) time: 0.9270 data: 0.0003 [11-22 22:20:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [1251/1669] eta: 0:06:30 tlr: 0.00024 tnm: 0.37 Lm: 6.971 (6.974) Lt: 6.317 (6.323) Accm: 2.24 (2.24) Acct: 3.31 (3.31) proj_loss: -0.5125 (-0.5066) time: 0.9308 data: 0.0003 [11-22 22:20:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [1251/1669] eta: 0:06:30 tlr: 0.00024 tnm: 0.37 Lm: 6.841 (6.855) Lt: 6.141 (6.171) Accm: 2.57 (2.50) Acct: 3.93 (3.81) proj_loss: -0.4889 (-0.4907) time: 0.9308 data: 0.0002 [11-22 22:20:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [1251/1669] eta: 0:06:30 tlr: 0.00024 tnm: 0.37 Lm: 7.036 (6.961) Lt: 6.401 (6.319) Accm: 2.09 (2.22) Acct: 3.32 (3.56) proj_loss: -0.4945 (-0.4996) time: 0.9308 data: 0.0002 [11-22 22:20:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [1251/1669] eta: 0:06:30 tlr: 0.00024 tnm: 0.37 Lm: 6.818 (6.843) Lt: 6.117 (6.156) Accm: 2.48 (2.46) Acct: 3.89 (3.81) proj_loss: -0.5007 (-0.4947) time: 0.9308 data: 0.0003 [11-22 22:20:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [1251/1669] eta: 0:06:30 tlr: 0.00024 tnm: 0.37 Lm: 6.997 (6.975) Lt: 6.349 (6.326) Accm: 2.23 (2.22) Acct: 3.60 (3.64) proj_loss: -0.5023 (-0.5059) time: 0.9308 data: 0.0002 [11-22 22:20:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [1251/1669] eta: 0:06:30 tlr: 0.00024 tnm: 0.37 Lm: 6.913 (6.910) Lt: 6.193 (6.199) Accm: 2.55 (2.48) Acct: 3.99 (3.90) proj_loss: -0.4928 (-0.4915) time: 0.9308 data: 0.0002 [11-22 22:20:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [1251/1669] eta: 0:06:30 tlr: 0.00024 tnm: 0.37 Lm: 6.965 (6.915) Lt: 6.279 (6.219) Accm: 2.16 (2.19) Acct: 3.43 (3.36) proj_loss: -0.5084 (-0.5057) time: 0.9308 data: 0.0003 [11-22 22:20:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [1251/1669] eta: 0:06:30 tlr: 0.00024 tnm: 0.37 Lm: 6.908 (6.901) Lt: 6.191 (6.190) Accm: 2.45 (2.47) Acct: 3.77 (3.89) proj_loss: -0.5128 (-0.5142) time: 0.9308 data: 0.0003 [11-22 22:27:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.35 Lm: 6.931 (6.907) Lt: 6.214 (6.201) Accm: 2.43 (2.42) Acct: 3.72 (3.77) proj_loss: -0.5133 (-0.5147) time: 0.9272 data: 0.0017 [11-22 22:27:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 13/350] Total time: 0:25:55 (0.932 s / it) [11-22 22:27:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.35 Lm: 7.036 (6.918) Lt: 6.368 (6.253) Accm: 2.16 (2.39) Acct: 3.44 (3.78) proj_loss: -0.5016 (-0.5028) time: 0.9272 data: 0.0016 [11-22 22:27:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.35 Lm: 6.938 (6.880) Lt: 6.221 (6.184) Accm: 2.49 (2.48) Acct: 3.75 (3.80) proj_loss: -0.4951 (-0.4916) time: 0.9272 data: 0.0015 [11-22 22:27:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.35 Lm: 6.992 (6.988) Lt: 6.333 (6.341) Accm: 2.14 (2.19) Acct: 3.27 (3.28) proj_loss: -0.5255 (-0.5111) time: 0.9272 data: 0.0017 [11-22 22:27:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.35 Lm: 7.094 (7.013) Lt: 6.453 (6.369) Accm: 1.84 (2.14) Acct: 3.17 (3.55) proj_loss: -0.5070 (-0.5088) time: 0.9272 data: 0.0022 [11-22 22:27:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.35 Lm: 6.884 (6.878) Lt: 6.132 (6.167) Accm: 2.58 (2.59) Acct: 4.20 (4.05) proj_loss: -0.4986 (-0.5042) time: 0.9272 data: 0.0015 [11-22 22:27:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.35 Lm: 6.848 (6.861) Lt: 6.145 (6.193) Accm: 2.43 (2.40) Acct: 3.86 (3.75) proj_loss: -0.5017 (-0.5038) time: 0.9272 data: 0.0018 [11-22 22:27:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 13/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.35 Lm: 6.951 (6.920) Lt: 6.275 (6.225) Accm: 2.21 (2.21) Acct: 3.48 (3.44) proj_loss: -0.5101 (-0.5079) time: 0.9273 data: 0.0021 [11-22 22:27:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 13/350] Total time: 0:25:55 (0.932 s / it) [11-22 22:27:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 13/350] Total time: 0:25:55 (0.932 s / it) [11-22 22:27:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 13/350] Total time: 0:25:55 (0.932 s / it) [11-22 22:27:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 13/350] Total time: 0:25:55 (0.932 s / it) [11-22 22:27:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 13/350] Total time: 0:25:55 (0.932 s / it) [11-22 22:27:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 13/350] Total time: 0:25:55 (0.932 s / it) [11-22 22:27:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 13/350] Total time: 0:25:55 (0.932 s / it) [11-22 22:27:23] (/home/user/VAR/train.py , line 276)=> [ep13] (training ) Lm: 6.915 (6.915), Lt: 6.241 (6.241), Acc m&t: 2.35 3.65, Remain: 6 days, 1:22:30, Finish: 2024-11-28 07:49 [11-22 22:27:23] (/home/user/VAR/train.py , line 276)=> [ep13] (training ) Lm: 6.915 (6.915), Lt: 6.241 (6.241), Acc m&t: 2.35 3.65, Remain: 6 days, 1:21:17, Finish: 2024-11-28 07:48 [11-22 22:27:23] (/home/user/VAR/train.py , line 276)=> [ep13] (training ) Lm: 6.915 (6.915), Lt: 6.241 (6.241), Acc m&t: 2.35 3.65, Remain: 6 days, 1:18:37, Finish: 2024-11-28 07:46 [11-22 22:27:23] (/home/user/VAR/train.py , line 276)=> [ep13] (training ) Lm: 6.915 (6.915), Lt: 6.241 (6.241), Acc m&t: 2.35 3.65, Remain: 6 days, 1:23:34, Finish: 2024-11-28 07:50 [11-22 22:27:23] (/home/user/VAR/train.py , line 276)=> [ep13] (training ) Lm: 6.915 (6.915), Lt: 6.241 (6.241), Acc m&t: 2.35 3.65, Remain: 6 days, 1:22:35, Finish: 2024-11-28 07:49 [11-22 22:27:23] (/home/user/VAR/train.py , line 276)=> [ep13] (training ) Lm: 6.915 (6.915), Lt: 6.241 (6.241), Acc m&t: 2.35 3.65, Remain: 6 days, 1:21:45, Finish: 2024-11-28 07:49 [11-22 22:27:23] (/home/user/VAR/train.py , line 276)=> [ep13] (training ) Lm: 6.915 (6.915), Lt: 6.241 (6.241), Acc m&t: 2.35 3.65, Remain: 6 days, 1:22:24, Finish: 2024-11-28 07:49 [11-22 22:27:23] (/home/user/VAR/train.py , line 276)=> [ep13] (training ) Lm: 6.915 (6.915), Lt: 6.241 (6.241), Acc m&t: 2.35 3.65, Remain: 6 days, 1:22:27, Finish: 2024-11-28 07:49 [11-22 22:27:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 0/1669] eta: 0:24:34 tlr: 0.00024 tnm: 0.42 Lm: 7.021 (7.021) Lt: 6.358 (6.358) Accm: 1.72 (1.72) Acct: 2.79 (2.79) proj_loss: -0.5191 (-0.5191) time: 0.8834 data: 0.0004 [11-22 22:27:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 0/1669] eta: 0:24:35 tlr: 0.00024 tnm: 0.42 Lm: 6.956 (6.956) Lt: 6.228 (6.228) Accm: 2.19 (2.19) Acct: 3.44 (3.44) proj_loss: -0.5054 (-0.5054) time: 0.8841 data: 0.0003 [11-22 22:27:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 0/1669] eta: 0:24:36 tlr: 0.00024 tnm: 0.42 Lm: 7.150 (7.150) Lt: 6.526 (6.526) Accm: 1.82 (1.82) Acct: 2.96 (2.96) proj_loss: -0.5062 (-0.5062) time: 0.8845 data: 0.0004 [11-22 22:27:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 0/1669] eta: 0:24:34 tlr: 0.00024 tnm: 0.42 Lm: 6.945 (6.945) Lt: 6.283 (6.283) Accm: 2.29 (2.29) Acct: 3.75 (3.75) proj_loss: -0.5135 (-0.5135) time: 0.8833 data: 0.0004 [11-22 22:27:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 0/1669] eta: 0:24:35 tlr: 0.00024 tnm: 0.42 Lm: 6.863 (6.863) Lt: 6.232 (6.232) Accm: 2.35 (2.35) Acct: 3.41 (3.41) proj_loss: -0.5045 (-0.5045) time: 0.8841 data: 0.0004 [11-22 22:27:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 0/1669] eta: 0:24:36 tlr: 0.00024 tnm: 0.42 Lm: 6.834 (6.834) Lt: 6.222 (6.222) Accm: 2.13 (2.13) Acct: 3.13 (3.13) proj_loss: -0.5103 (-0.5103) time: 0.8846 data: 0.0003 [11-22 22:27:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 0/1669] eta: 0:24:35 tlr: 0.00024 tnm: 0.42 Lm: 6.772 (6.772) Lt: 6.038 (6.038) Accm: 2.42 (2.42) Acct: 3.93 (3.93) proj_loss: -0.4487 (-0.4487) time: 0.8840 data: 0.0004 [11-22 22:27:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 0/1669] eta: 0:24:36 tlr: 0.00024 tnm: 0.42 Lm: 6.880 (6.880) Lt: 6.089 (6.089) Accm: 2.53 (2.53) Acct: 3.93 (3.93) proj_loss: -0.4897 (-0.4897) time: 0.8847 data: 0.0004 [11-22 22:33:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 417/1669] eta: 0:19:19 tlr: 0.00024 tnm: 0.39 Lm: 6.953 (6.953) Lt: 6.255 (6.255) Accm: 2.09 (2.09) Acct: 3.22 (3.22) proj_loss: -0.5001 (-0.5001) time: 0.9260 data: 0.0003 [11-22 22:33:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 417/1669] eta: 0:19:19 tlr: 0.00024 tnm: 0.39 Lm: 6.855 (6.855) Lt: 6.206 (6.206) Accm: 2.34 (2.34) Acct: 3.37 (3.37) proj_loss: -0.5020 (-0.5020) time: 0.9260 data: 0.0003 [11-22 22:33:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 417/1669] eta: 0:19:19 tlr: 0.00024 tnm: 0.39 Lm: 6.889 (6.889) Lt: 6.202 (6.202) Accm: 2.27 (2.27) Acct: 3.53 (3.53) proj_loss: -0.4984 (-0.4984) time: 0.9260 data: 0.0003 [11-22 22:33:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 417/1669] eta: 0:19:19 tlr: 0.00024 tnm: 0.39 Lm: 7.044 (7.044) Lt: 6.401 (6.401) Accm: 2.03 (2.03) Acct: 3.32 (3.32) proj_loss: -0.5016 (-0.5016) time: 0.9260 data: 0.0002 [11-22 22:33:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 417/1669] eta: 0:19:19 tlr: 0.00024 tnm: 0.39 Lm: 6.879 (6.879) Lt: 6.193 (6.193) Accm: 2.41 (2.41) Acct: 3.58 (3.58) proj_loss: -0.4989 (-0.4989) time: 0.9260 data: 0.0003 [11-22 22:33:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 417/1669] eta: 0:19:19 tlr: 0.00024 tnm: 0.39 Lm: 6.970 (6.970) Lt: 6.285 (6.285) Accm: 1.96 (1.96) Acct: 3.29 (3.29) proj_loss: -0.5035 (-0.5035) time: 0.9260 data: 0.0003 [11-22 22:33:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 417/1669] eta: 0:19:19 tlr: 0.00024 tnm: 0.39 Lm: 7.021 (7.021) Lt: 6.314 (6.314) Accm: 2.08 (2.08) Acct: 3.32 (3.32) proj_loss: -0.5003 (-0.5003) time: 0.9260 data: 0.0003 [11-22 22:33:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 417/1669] eta: 0:19:19 tlr: 0.00024 tnm: 0.39 Lm: 6.878 (6.878) Lt: 6.209 (6.209) Accm: 2.38 (2.38) Acct: 3.62 (3.62) proj_loss: -0.4771 (-0.4771) time: 0.9261 data: 0.0003 [11-22 22:40:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 834/1669] eta: 0:13:17 tlr: 0.00024 tnm: 0.36 Lm: 6.984 (6.949) Lt: 6.379 (6.301) Accm: 2.35 (2.23) Acct: 3.31 (3.42) proj_loss: -0.5055 (-0.4936) time: 0.9302 data: 0.0003 [11-22 22:40:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 834/1669] eta: 0:13:17 tlr: 0.00024 tnm: 0.36 Lm: 6.938 (6.937) Lt: 6.276 (6.282) Accm: 2.24 (2.21) Acct: 3.68 (3.51) proj_loss: -0.5062 (-0.5044) time: 0.9302 data: 0.0002 [11-22 22:40:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 834/1669] eta: 0:13:17 tlr: 0.00024 tnm: 0.36 Lm: 6.880 (6.927) Lt: 6.181 (6.230) Accm: 2.53 (2.24) Acct: 3.93 (3.46) proj_loss: -0.5106 (-0.5044) time: 0.9302 data: 0.0003 [11-22 22:40:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 834/1669] eta: 0:13:17 tlr: 0.00024 tnm: 0.36 Lm: 6.919 (6.900) Lt: 6.213 (6.215) Accm: 2.20 (2.26) Acct: 3.79 (3.66) proj_loss: -0.5191 (-0.5101) time: 0.9302 data: 0.0003 [11-22 22:40:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 834/1669] eta: 0:13:17 tlr: 0.00024 tnm: 0.36 Lm: 6.890 (6.883) Lt: 6.222 (6.203) Accm: 2.45 (2.42) Acct: 3.75 (3.73) proj_loss: -0.5045 (-0.5041) time: 0.9302 data: 0.0003 [11-22 22:40:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 834/1669] eta: 0:13:17 tlr: 0.00024 tnm: 0.36 Lm: 6.832 (6.859) Lt: 6.120 (6.155) Accm: 2.29 (2.53) Acct: 3.75 (3.85) proj_loss: -0.4942 (-0.4970) time: 0.9302 data: 0.0003 [11-22 22:40:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 834/1669] eta: 0:13:17 tlr: 0.00024 tnm: 0.36 Lm: 6.956 (6.966) Lt: 6.228 (6.263) Accm: 2.19 (2.14) Acct: 3.44 (3.39) proj_loss: -0.4953 (-0.4979) time: 0.9302 data: 0.0003 [11-22 22:40:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [ 834/1669] eta: 0:13:17 tlr: 0.00024 tnm: 0.36 Lm: 6.834 (6.776) Lt: 6.190 (6.097) Accm: 2.55 (2.76) Acct: 3.62 (4.09) proj_loss: -0.4938 (-0.4993) time: 0.9302 data: 0.0003 [11-22 22:47:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [1251/1669] eta: 0:06:35 tlr: 0.00024 tnm: 0.30 Lm: 6.855 (6.817) Lt: 6.206 (6.160) Accm: 2.34 (2.59) Acct: 3.37 (3.85) proj_loss: -0.5020 (-0.5093) time: 0.9277 data: 0.0003 [11-22 22:47:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [1251/1669] eta: 0:06:35 tlr: 0.00024 tnm: 0.30 Lm: 7.002 (6.970) Lt: 6.386 (6.335) Accm: 2.32 (2.26) Acct: 3.72 (3.57) proj_loss: -0.5082 (-0.5110) time: 0.9277 data: 0.0002 [11-22 22:47:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [1251/1669] eta: 0:06:35 tlr: 0.00024 tnm: 0.30 Lm: 6.878 (6.900) Lt: 6.152 (6.203) Accm: 2.43 (2.27) Acct: 3.93 (3.59) proj_loss: -0.5077 (-0.5045) time: 0.9277 data: 0.0003 [11-22 22:47:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [1251/1669] eta: 0:06:35 tlr: 0.00024 tnm: 0.30 Lm: 6.995 (6.983) Lt: 6.290 (6.285) Accm: 2.08 (2.08) Acct: 3.34 (3.35) proj_loss: -0.5003 (-0.5067) time: 0.9277 data: 0.0003 [11-22 22:47:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [1251/1669] eta: 0:06:35 tlr: 0.00024 tnm: 0.30 Lm: 6.950 (6.941) Lt: 6.325 (6.294) Accm: 2.20 (2.19) Acct: 3.43 (3.45) proj_loss: -0.5052 (-0.4964) time: 0.9277 data: 0.0003 [11-22 22:47:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [1251/1669] eta: 0:06:35 tlr: 0.00024 tnm: 0.30 Lm: 6.848 (6.860) Lt: 6.117 (6.145) Accm: 2.32 (2.48) Acct: 3.82 (3.86) proj_loss: -0.4974 (-0.4979) time: 0.9277 data: 0.0002 [11-22 22:47:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [1251/1669] eta: 0:06:35 tlr: 0.00024 tnm: 0.30 Lm: 6.849 (6.870) Lt: 6.171 (6.194) Accm: 2.47 (2.38) Acct: 3.86 (3.73) proj_loss: -0.5127 (-0.5091) time: 0.9277 data: 0.0003 [11-22 22:47:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [1251/1669] eta: 0:06:35 tlr: 0.00024 tnm: 0.30 Lm: 6.892 (6.905) Lt: 6.227 (6.238) Accm: 2.40 (2.39) Acct: 3.62 (3.67) proj_loss: -0.5053 (-0.5046) time: 0.9277 data: 0.0003 [11-22 22:53:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.32 Lm: 6.894 (6.936) Lt: 6.232 (6.278) Accm: 2.35 (2.35) Acct: 3.48 (3.62) proj_loss: -0.5061 (-0.5069) time: 0.9307 data: 0.0018 [11-22 22:53:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 14/350] Total time: 0:26:11 (0.942 s / it) [11-22 22:53:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.32 Lm: 6.938 (6.944) Lt: 6.276 (6.303) Accm: 2.29 (2.27) Acct: 3.75 (3.66) proj_loss: -0.5102 (-0.5109) time: 0.9307 data: 0.0020 [11-22 22:53:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.32 Lm: 6.956 (6.957) Lt: 6.228 (6.267) Accm: 2.17 (2.10) Acct: 3.44 (3.40) proj_loss: -0.5054 (-0.5136) time: 0.9307 data: 0.0016 [11-22 22:53:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.32 Lm: 6.834 (6.787) Lt: 6.190 (6.129) Accm: 2.55 (2.72) Acct: 3.62 (4.09) proj_loss: -0.5103 (-0.5097) time: 0.9307 data: 0.0016 [11-22 22:53:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.32 Lm: 6.917 (6.926) Lt: 6.272 (6.263) Accm: 2.32 (2.21) Acct: 3.55 (3.50) proj_loss: -0.5055 (-0.5011) time: 0.9307 data: 0.0019 [11-22 22:53:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.32 Lm: 6.834 (6.863) Lt: 6.129 (6.170) Accm: 2.36 (2.37) Acct: 3.93 (3.82) proj_loss: -0.5062 (-0.5029) time: 0.9307 data: 0.0016 [11-22 22:53:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.32 Lm: 6.864 (6.863) Lt: 6.120 (6.153) Accm: 2.35 (2.46) Acct: 3.75 (3.72) proj_loss: -0.4942 (-0.4935) time: 0.9307 data: 0.0018 [11-22 22:53:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 14/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.32 Lm: 6.875 (6.879) Lt: 6.124 (6.181) Accm: 2.39 (2.29) Acct: 3.93 (3.63) proj_loss: -0.5049 (-0.5042) time: 0.9307 data: 0.0021 [11-22 22:53:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 14/350] Total time: 0:26:11 (0.942 s / it) [11-22 22:53:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 14/350] Total time: 0:26:11 (0.942 s / it) [11-22 22:53:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 14/350] Total time: 0:26:11 (0.942 s / it) [11-22 22:53:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 14/350] Total time: 0:26:11 (0.942 s / it) [11-22 22:53:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 14/350] Total time: 0:26:11 (0.942 s / it) [11-22 22:53:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 14/350] Total time: 0:26:11 (0.942 s / it) [11-22 22:53:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 14/350] Total time: 0:26:11 (0.942 s / it) [11-22 22:53:35] (/home/user/VAR/train.py , line 276)=> [ep14] (training ) Lm: 6.906 (6.906), Lt: 6.226 (6.226), Acc m&t: 2.35 3.68, Remain: 6 days, 1:33:54, Finish: 2024-11-28 08:27 [11-22 22:53:35] (/home/user/VAR/train.py , line 276)=> [ep14] (training ) Lm: 6.906 (6.906), Lt: 6.226 (6.226), Acc m&t: 2.35 3.68, Remain: 6 days, 1:33:03, Finish: 2024-11-28 08:26 [11-22 22:53:35] (/home/user/VAR/train.py , line 276)=> [ep14] (training ) Lm: 6.906 (6.906), Lt: 6.226 (6.226), Acc m&t: 2.35 3.68, Remain: 6 days, 1:33:54, Finish: 2024-11-28 08:27 [11-22 22:53:35] (/home/user/VAR/train.py , line 276)=> [ep14] (training ) Lm: 6.906 (6.906), Lt: 6.226 (6.226), Acc m&t: 2.35 3.68, Remain: 6 days, 1:33:45, Finish: 2024-11-28 08:27 [11-22 22:53:35] (/home/user/VAR/train.py , line 276)=> [ep14] (training ) Lm: 6.906 (6.906), Lt: 6.226 (6.226), Acc m&t: 2.35 3.68, Remain: 6 days, 1:34:30, Finish: 2024-11-28 08:28 [11-22 22:53:35] (/home/user/VAR/train.py , line 276)=> [ep14] (training ) Lm: 6.906 (6.906), Lt: 6.226 (6.226), Acc m&t: 2.35 3.68, Remain: 6 days, 1:34:47, Finish: 2024-11-28 08:28 [11-22 22:53:35] (/home/user/VAR/train.py , line 276)=> [ep14] (training ) Lm: 6.906 (6.906), Lt: 6.226 (6.226), Acc m&t: 2.35 3.68, Remain: 6 days, 1:35:28, Finish: 2024-11-28 08:29 [11-22 22:53:35] (/home/user/VAR/train.py , line 276)=> [ep14] (training ) Lm: 6.906 (6.906), Lt: 6.226 (6.226), Acc m&t: 2.35 3.68, Remain: 6 days, 1:32:21, Finish: 2024-11-28 08:25 [11-22 22:53:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 0/1669] eta: 0:24:55 tlr: 0.00024 tnm: 0.32 Lm: 7.060 (7.060) Lt: 6.404 (6.404) Accm: 1.70 (1.70) Acct: 2.72 (2.72) proj_loss: -0.5273 (-0.5273) time: 0.8958 data: 0.0003 [11-22 22:53:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 0/1669] eta: 0:24:55 tlr: 0.00024 tnm: 0.32 Lm: 6.773 (6.773) Lt: 6.056 (6.056) Accm: 2.65 (2.65) Acct: 4.34 (4.34) proj_loss: -0.5308 (-0.5308) time: 0.8963 data: 0.0003 [11-22 22:53:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 0/1669] eta: 0:24:55 tlr: 0.00024 tnm: 0.32 Lm: 7.014 (7.014) Lt: 6.341 (6.341) Accm: 2.14 (2.14) Acct: 3.65 (3.65) proj_loss: -0.5276 (-0.5276) time: 0.8961 data: 0.0004 [11-22 22:53:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 0/1669] eta: 0:24:56 tlr: 0.00024 tnm: 0.32 Lm: 6.806 (6.806) Lt: 6.119 (6.119) Accm: 2.07 (2.07) Acct: 2.79 (2.79) proj_loss: -0.5229 (-0.5229) time: 0.8964 data: 0.0003 [11-22 22:53:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 0/1669] eta: 0:24:55 tlr: 0.00024 tnm: 0.32 Lm: 6.548 (6.548) Lt: 5.806 (5.806) Accm: 3.06 (3.06) Acct: 4.79 (4.79) proj_loss: -0.5026 (-0.5026) time: 0.8960 data: 0.0003 [11-22 22:53:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 0/1669] eta: 0:24:54 tlr: 0.00024 tnm: 0.32 Lm: 6.868 (6.868) Lt: 6.202 (6.202) Accm: 2.64 (2.64) Acct: 4.17 (4.17) proj_loss: -0.5267 (-0.5267) time: 0.8956 data: 0.0004 [11-22 22:53:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 0/1669] eta: 0:24:56 tlr: 0.00024 tnm: 0.32 Lm: 6.836 (6.836) Lt: 6.115 (6.115) Accm: 2.59 (2.59) Acct: 3.96 (3.96) proj_loss: -0.4999 (-0.4999) time: 0.8965 data: 0.0004 [11-22 22:53:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 0/1669] eta: 0:24:57 tlr: 0.00024 tnm: 0.32 Lm: 6.790 (6.790) Lt: 6.101 (6.101) Accm: 2.26 (2.26) Acct: 3.65 (3.65) proj_loss: -0.5150 (-0.5150) time: 0.8972 data: 0.0004 [11-22 23:00:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.35 Lm: 6.754 (6.754) Lt: 6.062 (6.062) Accm: 2.48 (2.48) Acct: 4.08 (4.08) proj_loss: -0.5112 (-0.5112) time: 0.9280 data: 0.0002 [11-22 23:00:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.35 Lm: 6.961 (6.961) Lt: 6.262 (6.262) Accm: 2.16 (2.16) Acct: 3.44 (3.44) proj_loss: -0.5224 (-0.5224) time: 0.9280 data: 0.0003 [11-22 23:00:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.35 Lm: 6.875 (6.875) Lt: 6.214 (6.214) Accm: 2.16 (2.16) Acct: 3.22 (3.22) proj_loss: -0.5208 (-0.5208) time: 0.9280 data: 0.0003 [11-22 23:00:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.35 Lm: 6.941 (6.941) Lt: 6.265 (6.265) Accm: 2.32 (2.32) Acct: 3.81 (3.81) proj_loss: -0.5031 (-0.5031) time: 0.9280 data: 0.0003 [11-22 23:00:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.35 Lm: 6.840 (6.840) Lt: 6.132 (6.132) Accm: 2.59 (2.59) Acct: 4.20 (4.20) proj_loss: -0.5123 (-0.5123) time: 0.9280 data: 0.0003 [11-22 23:00:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.35 Lm: 6.768 (6.768) Lt: 6.077 (6.077) Accm: 2.62 (2.62) Acct: 3.96 (3.96) proj_loss: -0.4947 (-0.4947) time: 0.9280 data: 0.0003 [11-22 23:00:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.35 Lm: 6.909 (6.909) Lt: 6.223 (6.223) Accm: 2.40 (2.40) Acct: 3.86 (3.86) proj_loss: -0.4951 (-0.4951) time: 0.9280 data: 0.0003 [11-22 23:00:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.35 Lm: 6.820 (6.820) Lt: 6.125 (6.125) Accm: 2.72 (2.72) Acct: 4.18 (4.18) proj_loss: -0.5002 (-0.5002) time: 0.9280 data: 0.0003 [11-22 23:06:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.33 Lm: 6.819 (6.820) Lt: 6.112 (6.121) Accm: 2.64 (2.62) Acct: 4.17 (4.16) proj_loss: -0.5164 (-0.5056) time: 0.9257 data: 0.0003 [11-22 23:06:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.33 Lm: 6.887 (6.879) Lt: 6.222 (6.217) Accm: 2.24 (2.32) Acct: 3.65 (3.47) proj_loss: -0.5186 (-0.5094) time: 0.9257 data: 0.0003 [11-22 23:06:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.33 Lm: 6.907 (6.893) Lt: 6.208 (6.215) Accm: 2.53 (2.36) Acct: 4.06 (3.86) proj_loss: -0.4938 (-0.5045) time: 0.9257 data: 0.0003 [11-22 23:06:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.33 Lm: 6.989 (6.850) Lt: 6.327 (6.161) Accm: 2.51 (2.58) Acct: 3.58 (3.83) proj_loss: -0.5026 (-0.5011) time: 0.9257 data: 0.0003 [11-22 23:06:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.33 Lm: 6.757 (6.755) Lt: 6.101 (6.091) Accm: 2.71 (2.56) Acct: 4.13 (4.10) proj_loss: -0.5150 (-0.5202) time: 0.9257 data: 0.0002 [11-22 23:06:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.33 Lm: 6.836 (6.808) Lt: 6.115 (6.123) Accm: 2.59 (2.68) Acct: 3.96 (4.17) proj_loss: -0.4999 (-0.5026) time: 0.9257 data: 0.0002 [11-22 23:06:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.33 Lm: 6.941 (6.954) Lt: 6.269 (6.264) Accm: 2.51 (2.27) Acct: 4.03 (3.64) proj_loss: -0.5176 (-0.5125) time: 0.9257 data: 0.0003 [11-22 23:06:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.33 Lm: 6.885 (6.922) Lt: 6.194 (6.241) Accm: 2.14 (2.26) Acct: 3.65 (3.58) proj_loss: -0.5276 (-0.5159) time: 0.9257 data: 0.0003 [11-22 23:12:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.35 Lm: 6.906 (6.923) Lt: 6.227 (6.246) Accm: 2.14 (2.23) Acct: 3.39 (3.46) proj_loss: -0.5256 (-0.5179) time: 0.9269 data: 0.0003 [11-22 23:12:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.35 Lm: 6.975 (6.968) Lt: 6.300 (6.281) Accm: 2.42 (2.29) Acct: 3.82 (3.63) proj_loss: -0.5051 (-0.5066) time: 0.9270 data: 0.0003 [11-22 23:12:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.35 Lm: 6.891 (6.888) Lt: 6.189 (6.203) Accm: 2.45 (2.36) Acct: 3.99 (3.87) proj_loss: -0.4914 (-0.4991) time: 0.9269 data: 0.0003 [11-22 23:12:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.35 Lm: 6.856 (6.865) Lt: 6.170 (6.185) Accm: 2.35 (2.36) Acct: 3.81 (3.67) proj_loss: -0.5129 (-0.5088) time: 0.9269 data: 0.0002 [11-22 23:12:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.35 Lm: 6.843 (6.863) Lt: 6.157 (6.172) Accm: 2.53 (2.46) Acct: 4.13 (3.85) proj_loss: -0.5215 (-0.5122) time: 0.9269 data: 0.0003 [11-22 23:12:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.35 Lm: 6.774 (6.786) Lt: 6.125 (6.116) Accm: 2.48 (2.44) Acct: 3.89 (3.82) proj_loss: -0.5267 (-0.5264) time: 0.9270 data: 0.0002 [11-22 23:12:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.35 Lm: 6.909 (6.859) Lt: 6.222 (6.175) Accm: 2.40 (2.56) Acct: 3.86 (3.94) proj_loss: -0.5033 (-0.5036) time: 0.9270 data: 0.0003 [11-22 23:12:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.35 Lm: 7.001 (6.897) Lt: 6.338 (6.222) Accm: 2.34 (2.35) Acct: 3.36 (3.61) proj_loss: -0.5082 (-0.5063) time: 0.9269 data: 0.0003 [11-22 23:19:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.36 Lm: 6.989 (6.904) Lt: 6.327 (6.216) Accm: 2.51 (2.39) Acct: 3.58 (3.71) proj_loss: -0.5026 (-0.5040) time: 0.9265 data: 0.0019 [11-22 23:19:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 15/350] Total time: 0:25:47 (0.927 s / it) [11-22 23:19:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.36 Lm: 6.790 (6.819) Lt: 6.149 (6.130) Accm: 2.26 (2.40) Acct: 3.72 (3.80) proj_loss: -0.5150 (-0.5218) time: 0.9264 data: 0.0016 [11-22 23:19:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.36 Lm: 6.996 (6.973) Lt: 6.331 (6.309) Accm: 2.33 (2.26) Acct: 3.62 (3.55) proj_loss: -0.4987 (-0.5050) time: 0.9265 data: 0.0017 [11-22 23:19:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.36 Lm: 6.819 (6.845) Lt: 6.112 (6.143) Accm: 2.64 (2.50) Acct: 4.17 (3.95) proj_loss: -0.5164 (-0.5072) time: 0.9265 data: 0.0018 [11-22 23:19:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.36 Lm: 6.981 (6.885) Lt: 6.330 (6.224) Accm: 2.21 (2.42) Acct: 3.75 (3.71) proj_loss: -0.5053 (-0.5040) time: 0.9265 data: 0.0016 [11-22 23:19:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.36 Lm: 6.882 (6.869) Lt: 6.222 (6.198) Accm: 2.24 (2.33) Acct: 3.65 (3.61) proj_loss: -0.5186 (-0.5115) time: 0.9265 data: 0.0016 [11-22 23:19:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.36 Lm: 6.874 (6.869) Lt: 6.170 (6.191) Accm: 2.37 (2.37) Acct: 3.93 (3.84) proj_loss: -0.4932 (-0.4979) time: 0.9265 data: 0.0017 [11-22 23:19:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 15/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.36 Lm: 6.908 (6.920) Lt: 6.222 (6.241) Accm: 2.14 (2.19) Acct: 3.13 (3.38) proj_loss: -0.5236 (-0.5171) time: 0.9265 data: 0.0018 [11-22 23:19:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 15/350] Total time: 0:25:47 (0.927 s / it) [11-22 23:19:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 15/350] Total time: 0:25:47 (0.927 s / it) [11-22 23:19:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 15/350] Total time: 0:25:47 (0.927 s / it) [11-22 23:19:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 15/350] Total time: 0:25:47 (0.927 s / it) [11-22 23:19:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 15/350] Total time: 0:25:47 (0.927 s / it) [11-22 23:19:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 15/350] Total time: 0:25:47 (0.927 s / it) [11-22 23:19:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 15/350] Total time: 0:25:47 (0.927 s / it) [11-22 23:19:22] (/home/user/VAR/train.py , line 276)=> [ep15] (training ) Lm: 6.874 (6.874), Lt: 6.181 (6.181), Acc m&t: 2.43 3.83, Remain: 6 days, 0:25:30, Finish: 2024-11-28 07:44 [11-22 23:19:22] (/home/user/VAR/train.py , line 276)=> [ep15] (training ) Lm: 6.874 (6.874), Lt: 6.181 (6.181), Acc m&t: 2.43 3.83, Remain: 6 days, 0:22:21, Finish: 2024-11-28 07:41 [11-22 23:19:22] (/home/user/VAR/train.py , line 276)=> [ep15] (training ) Lm: 6.874 (6.874), Lt: 6.181 (6.181), Acc m&t: 2.43 3.83, Remain: 6 days, 0:22:20, Finish: 2024-11-28 07:41 [11-22 23:19:22] (/home/user/VAR/train.py , line 276)=> [ep15] (training ) Lm: 6.874 (6.874), Lt: 6.181 (6.181), Acc m&t: 2.43 3.83, Remain: 6 days, 0:25:43, Finish: 2024-11-28 07:45 [11-22 23:19:22] (/home/user/VAR/train.py , line 276)=> [ep15] (training ) Lm: 6.874 (6.874), Lt: 6.181 (6.181), Acc m&t: 2.43 3.83, Remain: 6 days, 0:23:25, Finish: 2024-11-28 07:42 [11-22 23:19:22] (/home/user/VAR/train.py , line 276)=> [ep15] (training ) Lm: 6.874 (6.874), Lt: 6.181 (6.181), Acc m&t: 2.43 3.83, Remain: 6 days, 0:24:31, Finish: 2024-11-28 07:43 [11-22 23:19:22] (/home/user/VAR/train.py , line 276)=> [ep15] (training ) Lm: 6.874 (6.874), Lt: 6.181 (6.181), Acc m&t: 2.43 3.83, Remain: 6 days, 0:24:12, Finish: 2024-11-28 07:43 [11-22 23:19:22] (/home/user/VAR/train.py , line 276)=> [ep15] (training ) Lm: 6.874 (6.874), Lt: 6.181 (6.181), Acc m&t: 2.43 3.83, Remain: 6 days, 0:21:11, Finish: 2024-11-28 07:40 [11-22 23:19:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 0/1669] eta: 0:24:58 tlr: 0.00024 tnm: 0.31 Lm: 6.610 (6.610) Lt: 5.931 (5.931) Accm: 3.28 (3.28) Acct: 4.89 (4.89) proj_loss: -0.5012 (-0.5012) time: 0.8980 data: 0.0004 [11-22 23:19:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 0/1669] eta: 0:24:58 tlr: 0.00024 tnm: 0.31 Lm: 6.914 (6.914) Lt: 6.225 (6.225) Accm: 2.33 (2.33) Acct: 3.72 (3.72) proj_loss: -0.5107 (-0.5107) time: 0.8980 data: 0.0004 [11-22 23:19:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 0/1669] eta: 0:24:59 tlr: 0.00024 tnm: 0.31 Lm: 6.807 (6.807) Lt: 6.061 (6.061) Accm: 2.62 (2.62) Acct: 4.34 (4.34) proj_loss: -0.5205 (-0.5205) time: 0.8982 data: 0.0004 [11-22 23:19:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 0/1669] eta: 0:24:58 tlr: 0.00024 tnm: 0.31 Lm: 6.553 (6.553) Lt: 5.789 (5.789) Accm: 3.22 (3.22) Acct: 5.13 (5.13) proj_loss: -0.4909 (-0.4909) time: 0.8981 data: 0.0004 [11-22 23:19:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 0/1669] eta: 0:24:59 tlr: 0.00024 tnm: 0.31 Lm: 6.970 (6.970) Lt: 6.305 (6.305) Accm: 1.94 (1.94) Acct: 2.93 (2.93) proj_loss: -0.4796 (-0.4796) time: 0.8984 data: 0.0004 [11-22 23:19:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 0/1669] eta: 0:24:59 tlr: 0.00024 tnm: 0.31 Lm: 7.031 (7.031) Lt: 6.327 (6.327) Accm: 2.30 (2.30) Acct: 3.65 (3.65) proj_loss: -0.4983 (-0.4983) time: 0.8984 data: 0.0004 [11-22 23:19:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 0/1669] eta: 0:24:59 tlr: 0.00024 tnm: 0.31 Lm: 7.041 (7.041) Lt: 6.376 (6.376) Accm: 2.14 (2.14) Acct: 3.86 (3.86) proj_loss: -0.5092 (-0.5092) time: 0.8986 data: 0.0004 [11-22 23:19:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 0/1669] eta: 0:24:59 tlr: 0.00024 tnm: 0.31 Lm: 6.636 (6.636) Lt: 5.917 (5.917) Accm: 2.99 (2.99) Acct: 4.48 (4.48) proj_loss: -0.4864 (-0.4864) time: 0.8986 data: 0.0004 [11-22 23:26:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 417/1669] eta: 0:20:01 tlr: 0.00024 tnm: 0.29 Lm: 6.725 (6.725) Lt: 6.046 (6.046) Accm: 2.84 (2.84) Acct: 4.39 (4.39) proj_loss: -0.4984 (-0.4984) time: 0.9278 data: 0.0003 [11-22 23:26:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 417/1669] eta: 0:20:01 tlr: 0.00024 tnm: 0.29 Lm: 6.933 (6.933) Lt: 6.233 (6.233) Accm: 2.24 (2.24) Acct: 3.63 (3.63) proj_loss: -0.5024 (-0.5024) time: 0.9278 data: 0.0002 [11-22 23:26:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 417/1669] eta: 0:20:01 tlr: 0.00024 tnm: 0.29 Lm: 6.819 (6.819) Lt: 6.109 (6.109) Accm: 2.56 (2.56) Acct: 4.20 (4.20) proj_loss: -0.5098 (-0.5098) time: 0.9278 data: 0.0002 [11-22 23:26:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 417/1669] eta: 0:20:01 tlr: 0.00024 tnm: 0.29 Lm: 6.896 (6.896) Lt: 6.201 (6.201) Accm: 2.17 (2.17) Acct: 3.29 (3.29) proj_loss: -0.5133 (-0.5133) time: 0.9278 data: 0.0003 [11-22 23:26:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 417/1669] eta: 0:20:01 tlr: 0.00024 tnm: 0.29 Lm: 6.913 (6.913) Lt: 6.236 (6.236) Accm: 2.42 (2.42) Acct: 4.05 (4.05) proj_loss: -0.5116 (-0.5116) time: 0.9278 data: 0.0003 [11-22 23:26:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 417/1669] eta: 0:20:01 tlr: 0.00024 tnm: 0.29 Lm: 6.976 (6.976) Lt: 6.261 (6.261) Accm: 2.26 (2.26) Acct: 3.53 (3.53) proj_loss: -0.5147 (-0.5147) time: 0.9278 data: 0.0002 [11-22 23:26:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 417/1669] eta: 0:20:01 tlr: 0.00024 tnm: 0.29 Lm: 6.760 (6.760) Lt: 6.077 (6.077) Accm: 2.84 (2.84) Acct: 4.41 (4.41) proj_loss: -0.4936 (-0.4936) time: 0.9279 data: 0.0002 [11-22 23:26:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 417/1669] eta: 0:20:01 tlr: 0.00024 tnm: 0.29 Lm: 6.602 (6.602) Lt: 5.829 (5.829) Accm: 3.08 (3.08) Acct: 4.96 (4.96) proj_loss: -0.5031 (-0.5031) time: 0.9279 data: 0.0002 [11-22 23:32:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 834/1669] eta: 0:13:07 tlr: 0.00024 tnm: 0.30 Lm: 6.652 (6.648) Lt: 5.869 (5.898) Accm: 2.94 (2.92) Acct: 4.79 (4.65) proj_loss: -0.5146 (-0.5069) time: 0.9263 data: 0.0002 [11-22 23:32:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 834/1669] eta: 0:13:07 tlr: 0.00024 tnm: 0.30 Lm: 6.807 (6.815) Lt: 6.061 (6.083) Accm: 2.62 (2.68) Acct: 4.34 (4.36) proj_loss: -0.4992 (-0.4995) time: 0.9262 data: 0.0002 [11-22 23:32:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 834/1669] eta: 0:13:07 tlr: 0.00024 tnm: 0.30 Lm: 6.954 (6.969) Lt: 6.243 (6.255) Accm: 2.21 (2.23) Acct: 3.48 (3.51) proj_loss: -0.5124 (-0.5139) time: 0.9262 data: 0.0002 [11-22 23:32:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 834/1669] eta: 0:13:07 tlr: 0.00024 tnm: 0.30 Lm: 6.970 (6.928) Lt: 6.269 (6.223) Accm: 2.40 (2.30) Acct: 3.65 (3.57) proj_loss: -0.5032 (-0.5099) time: 0.9262 data: 0.0002 [11-22 23:32:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 834/1669] eta: 0:13:07 tlr: 0.00024 tnm: 0.30 Lm: 6.914 (6.888) Lt: 6.225 (6.201) Accm: 2.33 (2.31) Acct: 3.55 (3.58) proj_loss: -0.5045 (-0.5031) time: 0.9262 data: 0.0003 [11-22 23:32:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 834/1669] eta: 0:13:07 tlr: 0.00024 tnm: 0.30 Lm: 6.775 (6.742) Lt: 6.050 (6.047) Accm: 2.81 (2.83) Acct: 4.48 (4.50) proj_loss: -0.4882 (-0.4950) time: 0.9262 data: 0.0003 [11-22 23:32:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 834/1669] eta: 0:13:07 tlr: 0.00024 tnm: 0.30 Lm: 6.911 (6.844) Lt: 6.224 (6.158) Accm: 2.40 (2.52) Acct: 3.93 (3.89) proj_loss: -0.4988 (-0.4953) time: 0.9262 data: 0.0003 [11-22 23:32:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [ 834/1669] eta: 0:13:07 tlr: 0.00024 tnm: 0.30 Lm: 6.939 (6.922) Lt: 6.251 (6.241) Accm: 2.16 (2.33) Acct: 3.86 (3.78) proj_loss: -0.5092 (-0.5064) time: 0.9264 data: 0.0003 [11-22 23:38:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.33 Lm: 6.876 (6.894) Lt: 6.173 (6.193) Accm: 2.43 (2.48) Acct: 4.05 (4.05) proj_loss: -0.5116 (-0.5094) time: 0.9266 data: 0.0003 [11-22 23:38:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.33 Lm: 6.891 (6.851) Lt: 6.177 (6.151) Accm: 2.53 (2.55) Acct: 4.10 (3.99) proj_loss: -0.5000 (-0.4969) time: 0.9266 data: 0.0003 [11-22 23:38:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.33 Lm: 6.937 (6.953) Lt: 6.254 (6.257) Accm: 2.26 (2.29) Acct: 3.56 (3.55) proj_loss: -0.5133 (-0.5140) time: 0.9266 data: 0.0003 [11-22 23:38:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.33 Lm: 6.695 (6.717) Lt: 5.953 (5.992) Accm: 2.77 (2.79) Acct: 4.41 (4.36) proj_loss: -0.5149 (-0.5096) time: 0.9266 data: 0.0003 [11-22 23:38:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.33 Lm: 6.794 (6.773) Lt: 6.093 (6.069) Accm: 2.75 (2.76) Acct: 4.39 (4.35) proj_loss: -0.4873 (-0.4886) time: 0.9266 data: 0.0003 [11-22 23:38:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.33 Lm: 6.896 (6.846) Lt: 6.182 (6.138) Accm: 2.48 (2.46) Acct: 3.89 (3.87) proj_loss: -0.5057 (-0.5095) time: 0.9266 data: 0.0003 [11-22 23:38:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.33 Lm: 6.819 (6.839) Lt: 6.109 (6.124) Accm: 2.56 (2.63) Acct: 4.27 (4.32) proj_loss: -0.5088 (-0.5042) time: 0.9266 data: 0.0002 [11-22 23:38:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.33 Lm: 6.856 (6.859) Lt: 6.181 (6.154) Accm: 2.40 (2.48) Acct: 3.63 (3.90) proj_loss: -0.5068 (-0.5046) time: 0.9266 data: 0.0003 [11-22 23:45:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.31 Lm: 6.798 (6.838) Lt: 6.137 (6.125) Accm: 2.46 (2.56) Acct: 3.72 (3.95) proj_loss: -0.5045 (-0.5020) time: 0.9278 data: 0.0020 [11-22 23:45:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 16/350] Total time: 0:26:00 (0.935 s / it) [11-22 23:45:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.31 Lm: 6.807 (6.811) Lt: 6.061 (6.096) Accm: 2.62 (2.73) Acct: 4.34 (4.47) proj_loss: -0.5145 (-0.5063) time: 0.9278 data: 0.0016 [11-22 23:45:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.31 Lm: 6.823 (6.837) Lt: 6.096 (6.128) Accm: 2.56 (2.50) Acct: 4.13 (3.94) proj_loss: -0.5082 (-0.5093) time: 0.9278 data: 0.0016 [11-22 23:45:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.31 Lm: 6.921 (6.912) Lt: 6.243 (6.225) Accm: 2.30 (2.34) Acct: 3.65 (3.60) proj_loss: -0.5142 (-0.5227) time: 0.9278 data: 0.0018 [11-22 23:45:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.31 Lm: 6.871 (6.852) Lt: 6.138 (6.149) Accm: 2.51 (2.54) Acct: 3.93 (3.97) proj_loss: -0.5012 (-0.5034) time: 0.9279 data: 0.0018 [11-22 23:45:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.31 Lm: 6.739 (6.734) Lt: 6.037 (6.023) Accm: 2.59 (2.70) Acct: 4.03 (4.20) proj_loss: -0.5153 (-0.5147) time: 0.9279 data: 0.0015 [11-22 23:45:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.31 Lm: 6.939 (6.909) Lt: 6.196 (6.193) Accm: 2.16 (2.40) Acct: 3.86 (3.91) proj_loss: -0.5092 (-0.5060) time: 0.9279 data: 0.0018 [11-22 23:45:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 16/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.31 Lm: 6.814 (6.792) Lt: 6.136 (6.089) Accm: 2.70 (2.72) Acct: 4.30 (4.32) proj_loss: -0.4882 (-0.4990) time: 0.9278 data: 0.0017 [11-22 23:45:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 16/350] Total time: 0:26:00 (0.935 s / it) [11-22 23:45:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 16/350] Total time: 0:26:00 (0.935 s / it) [11-22 23:45:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 16/350] Total time: 0:26:00 (0.935 s / it) [11-22 23:45:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 16/350] Total time: 0:26:00 (0.935 s / it) [11-22 23:45:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 16/350] Total time: 0:26:00 (0.935 s / it) [11-22 23:45:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 16/350] Total time: 0:26:00 (0.935 s / it) [11-22 23:45:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 16/350] Total time: 0:26:00 (0.935 s / it) [11-22 23:45:23] (/home/user/VAR/train.py , line 276)=> [ep16] (training ) Lm: 6.863 (6.863), Lt: 6.173 (6.173), Acc m&t: 2.46 3.87, Remain: 6 days, 0:35:05, Finish: 2024-11-28 08:20 [11-22 23:45:23] (/home/user/VAR/train.py , line 276)=> [ep16] (training ) Lm: 6.863 (6.863), Lt: 6.173 (6.173), Acc m&t: 2.46 3.87, Remain: 6 days, 0:33:17, Finish: 2024-11-28 08:18 [11-22 23:45:23] (/home/user/VAR/train.py , line 276)=> [ep16] (training ) Lm: 6.863 (6.863), Lt: 6.173 (6.173), Acc m&t: 2.46 3.87, Remain: 6 days, 0:31:46, Finish: 2024-11-28 08:17 [11-22 23:45:23] (/home/user/VAR/train.py , line 276)=> [ep16] (training ) Lm: 6.863 (6.863), Lt: 6.173 (6.173), Acc m&t: 2.46 3.87, Remain: 6 days, 0:30:51, Finish: 2024-11-28 08:16 [11-22 23:45:23] (/home/user/VAR/train.py , line 276)=> [ep16] (training ) Lm: 6.863 (6.863), Lt: 6.173 (6.173), Acc m&t: 2.46 3.87, Remain: 6 days, 0:29:50, Finish: 2024-11-28 08:15 [11-22 23:45:23] (/home/user/VAR/train.py , line 276)=> [ep16] (training ) Lm: 6.863 (6.863), Lt: 6.173 (6.173), Acc m&t: 2.46 3.87, Remain: 6 days, 0:31:37, Finish: 2024-11-28 08:17 [11-22 23:45:23] (/home/user/VAR/train.py , line 276)=> [ep16] (training ) Lm: 6.863 (6.863), Lt: 6.173 (6.173), Acc m&t: 2.46 3.87, Remain: 6 days, 0:28:52, Finish: 2024-11-28 08:14 [11-22 23:45:23] (/home/user/VAR/train.py , line 276)=> [ep16] (training ) Lm: 6.863 (6.863), Lt: 6.173 (6.173), Acc m&t: 2.46 3.87, Remain: 6 days, 0:30:25, Finish: 2024-11-28 08:15 [11-22 23:45:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 0/1669] eta: 0:24:39 tlr: 0.00024 tnm: 0.30 Lm: 6.790 (6.790) Lt: 6.034 (6.034) Accm: 2.86 (2.86) Acct: 4.58 (4.58) proj_loss: -0.5107 (-0.5107) time: 0.8863 data: 0.0004 [11-22 23:45:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 0/1669] eta: 0:24:40 tlr: 0.00024 tnm: 0.30 Lm: 6.722 (6.722) Lt: 6.055 (6.055) Accm: 2.61 (2.61) Acct: 3.86 (3.86) proj_loss: -0.5474 (-0.5474) time: 0.8868 data: 0.0003 [11-22 23:45:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 0/1669] eta: 0:24:39 tlr: 0.00024 tnm: 0.30 Lm: 6.888 (6.888) Lt: 6.255 (6.255) Accm: 2.16 (2.16) Acct: 3.20 (3.20) proj_loss: -0.5200 (-0.5200) time: 0.8865 data: 0.0004 [11-22 23:45:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 0/1669] eta: 0:24:40 tlr: 0.00024 tnm: 0.30 Lm: 6.671 (6.671) Lt: 5.878 (5.878) Accm: 3.16 (3.16) Acct: 4.96 (4.96) proj_loss: -0.5092 (-0.5092) time: 0.8868 data: 0.0004 [11-22 23:45:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 0/1669] eta: 0:24:40 tlr: 0.00024 tnm: 0.30 Lm: 6.622 (6.622) Lt: 5.924 (5.924) Accm: 3.09 (3.09) Acct: 4.61 (4.61) proj_loss: -0.5075 (-0.5075) time: 0.8869 data: 0.0004 [11-22 23:45:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 0/1669] eta: 0:24:39 tlr: 0.00024 tnm: 0.30 Lm: 6.959 (6.959) Lt: 6.263 (6.263) Accm: 1.94 (1.94) Acct: 3.10 (3.10) proj_loss: -0.4968 (-0.4968) time: 0.8862 data: 0.0004 [11-22 23:45:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 0/1669] eta: 0:24:40 tlr: 0.00024 tnm: 0.30 Lm: 7.123 (7.123) Lt: 6.431 (6.431) Accm: 2.00 (2.00) Acct: 3.06 (3.06) proj_loss: -0.5123 (-0.5123) time: 0.8871 data: 0.0003 [11-22 23:45:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 0/1669] eta: 0:24:40 tlr: 0.00024 tnm: 0.30 Lm: 6.734 (6.734) Lt: 6.029 (6.029) Accm: 3.00 (3.00) Acct: 4.61 (4.61) proj_loss: -0.4850 (-0.4850) time: 0.8871 data: 0.0004 [11-22 23:51:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.29 Lm: 6.791 (6.791) Lt: 6.084 (6.084) Accm: 2.70 (2.70) Acct: 4.15 (4.15) proj_loss: -0.5062 (-0.5062) time: 0.9277 data: 0.0003 [11-22 23:51:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.29 Lm: 6.714 (6.714) Lt: 5.929 (5.929) Accm: 2.94 (2.94) Acct: 4.87 (4.87) proj_loss: -0.5209 (-0.5209) time: 0.9277 data: 0.0003 [11-22 23:51:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.29 Lm: 6.844 (6.844) Lt: 6.206 (6.206) Accm: 2.51 (2.51) Acct: 3.70 (3.70) proj_loss: -0.5128 (-0.5128) time: 0.9277 data: 0.0003 [11-22 23:51:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.29 Lm: 6.685 (6.685) Lt: 5.975 (5.975) Accm: 2.91 (2.91) Acct: 4.42 (4.42) proj_loss: -0.4971 (-0.4971) time: 0.9277 data: 0.0003 [11-22 23:51:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.29 Lm: 6.901 (6.901) Lt: 6.163 (6.163) Accm: 2.22 (2.22) Acct: 3.55 (3.55) proj_loss: -0.5111 (-0.5111) time: 0.9277 data: 0.0003 [11-22 23:51:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.29 Lm: 6.961 (6.961) Lt: 6.249 (6.249) Accm: 2.16 (2.16) Acct: 3.41 (3.41) proj_loss: -0.5084 (-0.5084) time: 0.9277 data: 0.0002 [11-22 23:51:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.29 Lm: 6.780 (6.780) Lt: 6.036 (6.036) Accm: 2.79 (2.79) Acct: 4.44 (4.44) proj_loss: -0.5231 (-0.5231) time: 0.9277 data: 0.0003 [11-22 23:51:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.29 Lm: 6.725 (6.725) Lt: 6.071 (6.071) Accm: 2.72 (2.72) Acct: 4.08 (4.08) proj_loss: -0.5350 (-0.5350) time: 0.9277 data: 0.0003 [11-22 23:58:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 834/1669] eta: 0:12:56 tlr: 0.00024 tnm: 0.31 Lm: 6.727 (6.731) Lt: 6.055 (6.054) Accm: 2.64 (2.70) Acct: 4.17 (4.11) proj_loss: -0.5356 (-0.5352) time: 0.9920 data: 0.0003 [11-22 23:58:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 834/1669] eta: 0:12:56 tlr: 0.00024 tnm: 0.31 Lm: 6.892 (6.898) Lt: 6.198 (6.175) Accm: 2.17 (2.20) Acct: 3.58 (3.56) proj_loss: -0.5253 (-0.5218) time: 0.9920 data: 0.0003 [11-22 23:58:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 834/1669] eta: 0:12:56 tlr: 0.00024 tnm: 0.31 Lm: 6.790 (6.783) Lt: 6.034 (6.040) Accm: 2.86 (2.73) Acct: 4.58 (4.53) proj_loss: -0.5249 (-0.5223) time: 0.9920 data: 0.0003 [11-22 23:58:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 834/1669] eta: 0:12:56 tlr: 0.00024 tnm: 0.31 Lm: 6.848 (6.812) Lt: 6.140 (6.108) Accm: 2.40 (2.59) Acct: 3.93 (4.07) proj_loss: -0.5274 (-0.5154) time: 0.9920 data: 0.0002 [11-22 23:58:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 834/1669] eta: 0:12:56 tlr: 0.00024 tnm: 0.31 Lm: 6.803 (6.908) Lt: 6.130 (6.209) Accm: 2.33 (2.34) Acct: 3.75 (3.70) proj_loss: -0.5045 (-0.5056) time: 0.9920 data: 0.0002 [11-22 23:58:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 834/1669] eta: 0:12:56 tlr: 0.00024 tnm: 0.31 Lm: 6.749 (6.727) Lt: 6.026 (6.054) Accm: 2.74 (2.85) Acct: 4.24 (4.18) proj_loss: -0.5075 (-0.5016) time: 0.9921 data: 0.0003 [11-22 23:58:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 834/1669] eta: 0:12:56 tlr: 0.00024 tnm: 0.31 Lm: 6.849 (6.846) Lt: 6.158 (6.172) Accm: 2.51 (2.51) Acct: 4.17 (3.86) proj_loss: -0.5055 (-0.5071) time: 0.9921 data: 0.0003 [11-22 23:58:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [ 834/1669] eta: 0:12:56 tlr: 0.00024 tnm: 0.31 Lm: 6.779 (6.779) Lt: 6.142 (6.071) Accm: 2.67 (2.75) Acct: 4.10 (4.33) proj_loss: -0.5289 (-0.5250) time: 0.9921 data: 0.0003 [11-23 00:05:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [1251/1669] eta: 0:06:37 tlr: 0.00024 tnm: 0.30 Lm: 6.771 (6.775) Lt: 6.088 (6.062) Accm: 2.68 (2.74) Acct: 4.10 (4.27) proj_loss: -0.5238 (-0.5234) time: 0.9278 data: 0.0002 [11-23 00:05:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [1251/1669] eta: 0:06:37 tlr: 0.00024 tnm: 0.30 Lm: 6.867 (6.865) Lt: 6.149 (6.156) Accm: 2.34 (2.28) Acct: 3.56 (3.56) proj_loss: -0.5228 (-0.5214) time: 0.9278 data: 0.0003 [11-23 00:05:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [1251/1669] eta: 0:06:37 tlr: 0.00024 tnm: 0.30 Lm: 6.843 (6.811) Lt: 6.138 (6.091) Accm: 2.71 (2.69) Acct: 4.29 (4.40) proj_loss: -0.5178 (-0.5182) time: 0.9278 data: 0.0002 [11-23 00:05:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [1251/1669] eta: 0:06:37 tlr: 0.00024 tnm: 0.30 Lm: 6.851 (6.827) Lt: 6.147 (6.120) Accm: 2.39 (2.52) Acct: 3.81 (3.94) proj_loss: -0.5234 (-0.5164) time: 0.9278 data: 0.0003 [11-23 00:05:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [1251/1669] eta: 0:06:37 tlr: 0.00024 tnm: 0.30 Lm: 6.823 (6.892) Lt: 6.153 (6.201) Accm: 2.31 (2.33) Acct: 3.63 (3.65) proj_loss: -0.5084 (-0.5155) time: 0.9278 data: 0.0002 [11-23 00:05:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [1251/1669] eta: 0:06:37 tlr: 0.00024 tnm: 0.30 Lm: 6.824 (6.827) Lt: 6.131 (6.139) Accm: 2.60 (2.55) Acct: 4.18 (4.08) proj_loss: -0.5007 (-0.4972) time: 0.9278 data: 0.0003 [11-23 00:05:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [1251/1669] eta: 0:06:37 tlr: 0.00024 tnm: 0.30 Lm: 6.736 (6.750) Lt: 6.068 (6.061) Accm: 2.70 (2.71) Acct: 4.22 (4.15) proj_loss: -0.5291 (-0.5269) time: 0.9278 data: 0.0003 [11-23 00:05:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [1251/1669] eta: 0:06:37 tlr: 0.00024 tnm: 0.30 Lm: 6.773 (6.745) Lt: 6.102 (6.085) Accm: 2.72 (2.75) Acct: 4.05 (4.10) proj_loss: -0.5090 (-0.5165) time: 0.9278 data: 0.0003 [11-23 00:11:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.30 Lm: 6.797 (6.774) Lt: 6.179 (6.104) Accm: 2.71 (2.71) Acct: 3.89 (4.06) proj_loss: -0.5106 (-0.5171) time: 0.9315 data: 0.0017 [11-23 00:11:42] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 17/350] Total time: 0:26:18 (0.946 s / it) [11-23 00:11:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.30 Lm: 6.792 (6.808) Lt: 6.110 (6.094) Accm: 2.68 (2.69) Acct: 4.10 (4.34) proj_loss: -0.5167 (-0.5179) time: 0.9315 data: 0.0020 [11-23 00:11:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.30 Lm: 6.849 (6.840) Lt: 6.158 (6.155) Accm: 2.51 (2.47) Acct: 4.17 (3.86) proj_loss: -0.5055 (-0.4998) time: 0.9315 data: 0.0021 [11-23 00:11:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.30 Lm: 6.892 (6.884) Lt: 6.198 (6.181) Accm: 2.51 (2.35) Acct: 3.58 (3.71) proj_loss: -0.5202 (-0.5200) time: 0.9315 data: 0.0016 [11-23 00:11:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.30 Lm: 6.779 (6.787) Lt: 6.140 (6.078) Accm: 2.70 (2.79) Acct: 4.10 (4.39) proj_loss: -0.5269 (-0.5241) time: 0.9314 data: 0.0019 [11-23 00:11:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.30 Lm: 6.848 (6.821) Lt: 6.140 (6.103) Accm: 2.40 (2.53) Acct: 3.93 (4.03) proj_loss: -0.5194 (-0.5137) time: 0.9315 data: 0.0020 [11-23 00:11:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.30 Lm: 6.843 (6.919) Lt: 6.177 (6.249) Accm: 2.29 (2.28) Acct: 3.65 (3.65) proj_loss: -0.5123 (-0.5191) time: 0.9315 data: 0.0021 [11-23 00:11:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 17/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.30 Lm: 6.744 (6.780) Lt: 6.082 (6.094) Accm: 2.64 (2.70) Acct: 4.17 (4.15) proj_loss: -0.5226 (-0.5236) time: 0.9315 data: 0.0020 [11-23 00:11:42] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 17/350] Total time: 0:26:18 (0.946 s / it) [11-23 00:11:42] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 17/350] Total time: 0:26:18 (0.946 s / it) [11-23 00:11:42] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 17/350] Total time: 0:26:18 (0.946 s / it) [11-23 00:11:42] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 17/350] Total time: 0:26:18 (0.946 s / it) [11-23 00:11:42] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 17/350] Total time: 0:26:18 (0.946 s / it) [11-23 00:11:42] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 17/350] Total time: 0:26:18 (0.946 s / it) [11-23 00:11:42] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 17/350] Total time: 0:26:18 (0.946 s / it) [11-23 00:11:42] (/home/user/VAR/train.py , line 276)=> [ep17] (training ) Lm: 6.831 (6.831), Lt: 6.127 (6.127), Acc m&t: 2.55 4.01, Remain: 6 days, 0:30:54, Finish: 2024-11-28 08:42 [11-23 00:11:42] (/home/user/VAR/train.py , line 276)=> [ep17] (training ) Lm: 6.831 (6.831), Lt: 6.127 (6.127), Acc m&t: 2.55 4.01, Remain: 6 days, 0:31:15, Finish: 2024-11-28 08:42 [11-23 00:11:42] (/home/user/VAR/train.py , line 276)=> [ep17] (training ) Lm: 6.831 (6.831), Lt: 6.127 (6.127), Acc m&t: 2.55 4.01, Remain: 6 days, 0:30:57, Finish: 2024-11-28 08:42 [11-23 00:11:42] (/home/user/VAR/train.py , line 276)=> [ep17] (training ) Lm: 6.831 (6.831), Lt: 6.127 (6.127), Acc m&t: 2.55 4.01, Remain: 6 days, 0:24:32, Finish: 2024-11-28 08:36 [11-23 00:11:42] (/home/user/VAR/train.py , line 276)=> [ep17] (training ) Lm: 6.831 (6.831), Lt: 6.127 (6.127), Acc m&t: 2.55 4.01, Remain: 6 days, 0:30:17, Finish: 2024-11-28 08:41 [11-23 00:11:42] (/home/user/VAR/train.py , line 276)=> [ep17] (training ) Lm: 6.831 (6.831), Lt: 6.127 (6.127), Acc m&t: 2.55 4.01, Remain: 6 days, 0:28:39, Finish: 2024-11-28 08:40 [11-23 00:11:42] (/home/user/VAR/train.py , line 276)=> [ep17] (training ) Lm: 6.831 (6.831), Lt: 6.127 (6.127), Acc m&t: 2.55 4.01, Remain: 6 days, 0:28:50, Finish: 2024-11-28 08:40 [11-23 00:11:42] (/home/user/VAR/train.py , line 276)=> [ep17] (training ) Lm: 6.831 (6.831), Lt: 6.127 (6.127), Acc m&t: 2.55 4.01, Remain: 6 days, 0:31:34, Finish: 2024-11-28 08:43 [11-23 00:11:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 0/1669] eta: 0:25:09 tlr: 0.00024 tnm: 0.30 Lm: 6.823 (6.823) Lt: 6.161 (6.161) Accm: 2.74 (2.74) Acct: 4.34 (4.34) proj_loss: -0.5269 (-0.5269) time: 0.9043 data: 0.0004 [11-23 00:11:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 0/1669] eta: 0:25:10 tlr: 0.00024 tnm: 0.30 Lm: 6.660 (6.660) Lt: 5.990 (5.990) Accm: 3.13 (3.13) Acct: 4.72 (4.72) proj_loss: -0.5144 (-0.5144) time: 0.9050 data: 0.0004 [11-23 00:11:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 0/1669] eta: 0:25:10 tlr: 0.00024 tnm: 0.30 Lm: 6.770 (6.770) Lt: 6.086 (6.086) Accm: 2.90 (2.90) Acct: 4.65 (4.65) proj_loss: -0.5235 (-0.5235) time: 0.9051 data: 0.0004 [11-23 00:11:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 0/1669] eta: 0:25:10 tlr: 0.00024 tnm: 0.30 Lm: 6.927 (6.927) Lt: 6.211 (6.211) Accm: 2.20 (2.20) Acct: 3.99 (3.99) proj_loss: -0.5062 (-0.5062) time: 0.9051 data: 0.0004 [11-23 00:11:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 0/1669] eta: 0:25:10 tlr: 0.00024 tnm: 0.30 Lm: 6.851 (6.851) Lt: 6.123 (6.123) Accm: 2.37 (2.37) Acct: 3.93 (3.93) proj_loss: -0.5137 (-0.5137) time: 0.9053 data: 0.0004 [11-23 00:11:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 0/1669] eta: 0:25:10 tlr: 0.00024 tnm: 0.30 Lm: 6.798 (6.798) Lt: 6.075 (6.075) Accm: 2.56 (2.56) Acct: 4.10 (4.10) proj_loss: -0.4954 (-0.4954) time: 0.9052 data: 0.0004 [11-23 00:11:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 0/1669] eta: 0:25:11 tlr: 0.00024 tnm: 0.30 Lm: 6.729 (6.729) Lt: 5.981 (5.981) Accm: 3.10 (3.10) Acct: 4.65 (4.65) proj_loss: -0.5055 (-0.5055) time: 0.9054 data: 0.0004 [11-23 00:11:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 0/1669] eta: 0:25:11 tlr: 0.00024 tnm: 0.30 Lm: 6.700 (6.700) Lt: 5.985 (5.985) Accm: 2.80 (2.80) Acct: 4.27 (4.27) proj_loss: -0.5287 (-0.5287) time: 0.9055 data: 0.0004 [11-23 00:18:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.28 Lm: 6.796 (6.796) Lt: 6.056 (6.056) Accm: 2.61 (2.61) Acct: 3.98 (3.98) proj_loss: -0.5087 (-0.5087) time: 0.9263 data: 0.0002 [11-23 00:18:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.28 Lm: 6.695 (6.695) Lt: 5.960 (5.960) Accm: 2.99 (2.99) Acct: 4.63 (4.63) proj_loss: -0.5027 (-0.5027) time: 0.9263 data: 0.0002 [11-23 00:18:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.28 Lm: 6.823 (6.823) Lt: 6.106 (6.106) Accm: 2.46 (2.46) Acct: 4.25 (4.25) proj_loss: -0.5140 (-0.5140) time: 0.9263 data: 0.0003 [11-23 00:18:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.28 Lm: 6.851 (6.851) Lt: 6.139 (6.139) Accm: 2.54 (2.54) Acct: 4.15 (4.15) proj_loss: -0.5243 (-0.5243) time: 0.9263 data: 0.0003 [11-23 00:18:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.28 Lm: 6.756 (6.756) Lt: 6.025 (6.025) Accm: 2.71 (2.71) Acct: 4.17 (4.17) proj_loss: -0.5036 (-0.5036) time: 0.9263 data: 0.0003 [11-23 00:18:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.28 Lm: 6.764 (6.764) Lt: 6.099 (6.099) Accm: 2.80 (2.80) Acct: 4.37 (4.37) proj_loss: -0.5036 (-0.5036) time: 0.9263 data: 0.0003 [11-23 00:18:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.28 Lm: 6.874 (6.874) Lt: 6.187 (6.187) Accm: 2.56 (2.56) Acct: 4.15 (4.15) proj_loss: -0.5127 (-0.5127) time: 0.9263 data: 0.0003 [11-23 00:18:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.28 Lm: 6.802 (6.802) Lt: 6.062 (6.062) Accm: 2.78 (2.78) Acct: 4.60 (4.60) proj_loss: -0.5177 (-0.5177) time: 0.9263 data: 0.0003 [11-23 00:24:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.30 Lm: 6.780 (6.775) Lt: 6.029 (6.051) Accm: 2.81 (2.87) Acct: 4.61 (4.60) proj_loss: -0.5254 (-0.5203) time: 0.9278 data: 0.0003 [11-23 00:24:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.30 Lm: 6.729 (6.818) Lt: 5.981 (6.096) Accm: 2.88 (2.74) Acct: 4.61 (4.34) proj_loss: -0.5050 (-0.5035) time: 0.9278 data: 0.0002 [11-23 00:24:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.30 Lm: 6.773 (6.788) Lt: 6.070 (6.061) Accm: 2.80 (2.68) Acct: 4.27 (4.07) proj_loss: -0.5090 (-0.5088) time: 0.9278 data: 0.0002 [11-23 00:24:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.30 Lm: 6.933 (6.894) Lt: 6.288 (6.224) Accm: 2.21 (2.40) Acct: 3.65 (3.78) proj_loss: -0.5196 (-0.5150) time: 0.9278 data: 0.0003 [11-23 00:24:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.30 Lm: 6.740 (6.751) Lt: 6.005 (6.018) Accm: 2.56 (2.65) Acct: 4.10 (4.02) proj_loss: -0.5013 (-0.5028) time: 0.9278 data: 0.0003 [11-23 00:24:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.30 Lm: 6.868 (6.848) Lt: 6.209 (6.191) Accm: 2.46 (2.59) Acct: 4.03 (4.07) proj_loss: -0.5144 (-0.5240) time: 0.9278 data: 0.0003 [11-23 00:24:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.30 Lm: 6.718 (6.787) Lt: 6.001 (6.040) Accm: 2.70 (2.54) Acct: 4.51 (4.41) proj_loss: -0.5218 (-0.5168) time: 0.9278 data: 0.0003 [11-23 00:24:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.30 Lm: 6.851 (6.788) Lt: 6.123 (6.083) Accm: 2.71 (2.67) Acct: 4.34 (4.21) proj_loss: -0.5137 (-0.5201) time: 0.9278 data: 0.0003 [11-23 00:31:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.28 Lm: 6.798 (6.777) Lt: 6.051 (6.057) Accm: 2.77 (2.71) Acct: 4.36 (4.33) proj_loss: -0.5128 (-0.5170) time: 0.9284 data: 0.0003 [11-23 00:31:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.28 Lm: 6.832 (6.828) Lt: 6.099 (6.097) Accm: 2.61 (2.53) Acct: 3.98 (3.86) proj_loss: -0.5000 (-0.5043) time: 0.9284 data: 0.0003 [11-23 00:31:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.28 Lm: 6.778 (6.820) Lt: 6.063 (6.109) Accm: 2.71 (2.69) Acct: 4.18 (4.17) proj_loss: -0.5053 (-0.5092) time: 0.9284 data: 0.0002 [11-23 00:31:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.28 Lm: 6.797 (6.817) Lt: 6.116 (6.149) Accm: 2.62 (2.63) Acct: 4.20 (4.15) proj_loss: -0.5158 (-0.5223) time: 0.9284 data: 0.0003 [11-23 00:31:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.28 Lm: 6.802 (6.821) Lt: 6.095 (6.106) Accm: 2.78 (2.74) Acct: 4.48 (4.36) proj_loss: -0.5262 (-0.5235) time: 0.9284 data: 0.0002 [11-23 00:31:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.28 Lm: 6.852 (6.849) Lt: 6.187 (6.170) Accm: 2.48 (2.48) Acct: 3.94 (3.89) proj_loss: -0.5111 (-0.5119) time: 0.9284 data: 0.0003 [11-23 00:31:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.28 Lm: 6.823 (6.823) Lt: 6.106 (6.092) Accm: 2.49 (2.48) Acct: 4.25 (4.21) proj_loss: -0.5140 (-0.5127) time: 0.9284 data: 0.0003 [11-23 00:31:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.28 Lm: 6.745 (6.751) Lt: 6.040 (6.032) Accm: 2.60 (2.64) Acct: 3.98 (3.98) proj_loss: -0.5066 (-0.5120) time: 0.9284 data: 0.0003 [11-23 00:37:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.751 (6.754) Lt: 6.005 (6.024) Accm: 2.64 (2.69) Acct: 4.10 (4.13) proj_loss: -0.5119 (-0.5154) time: 0.9310 data: 0.0018 [11-23 00:37:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 18/350] Total time: 0:25:46 (0.927 s / it) [11-23 00:37:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.773 (6.805) Lt: 6.070 (6.085) Accm: 2.74 (2.57) Acct: 4.06 (3.90) proj_loss: -0.5039 (-0.5043) time: 0.9310 data: 0.0015 [11-23 00:37:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.826 (6.845) Lt: 6.145 (6.126) Accm: 2.53 (2.56) Acct: 3.75 (4.00) proj_loss: -0.5050 (-0.5043) time: 0.9310 data: 0.0017 [11-23 00:37:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.780 (6.786) Lt: 6.029 (6.069) Accm: 2.81 (2.79) Acct: 4.61 (4.45) proj_loss: -0.5269 (-0.5248) time: 0.9310 data: 0.0019 [11-23 00:37:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.718 (6.792) Lt: 6.008 (6.076) Accm: 2.70 (2.60) Acct: 4.37 (4.24) proj_loss: -0.5218 (-0.5148) time: 0.9310 data: 0.0018 [11-23 00:37:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.862 (6.826) Lt: 6.176 (6.155) Accm: 2.46 (2.57) Acct: 4.03 (4.03) proj_loss: -0.5173 (-0.5251) time: 0.9310 data: 0.0020 [11-23 00:37:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.851 (6.823) Lt: 6.123 (6.113) Accm: 2.71 (2.59) Acct: 4.34 (4.15) proj_loss: -0.5137 (-0.5205) time: 0.9310 data: 0.0020 [11-23 00:37:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 18/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.845 (6.848) Lt: 6.128 (6.162) Accm: 2.56 (2.50) Acct: 4.13 (3.94) proj_loss: -0.5196 (-0.5173) time: 0.9310 data: 0.0014 [11-23 00:37:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 18/350] Total time: 0:25:46 (0.927 s / it) [11-23 00:37:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 18/350] Total time: 0:25:46 (0.927 s / it) [11-23 00:37:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 18/350] Total time: 0:25:46 (0.927 s / it) [11-23 00:37:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 18/350] Total time: 0:25:46 (0.927 s / it) [11-23 00:37:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 18/350] Total time: 0:25:46 (0.927 s / it) [11-23 00:37:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 18/350] Total time: 0:25:46 (0.927 s / it) [11-23 00:37:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 18/350] Total time: 0:25:46 (0.927 s / it) [11-23 00:37:29] (/home/user/VAR/train.py , line 276)=> [ep18] (training ) Lm: 6.820 (6.820), Lt: 6.115 (6.115), Acc m&t: 2.58 4.05, Remain: 5 days, 23:49:51, Finish: 2024-11-28 08:27 [11-23 00:37:29] (/home/user/VAR/train.py , line 276)=> [ep18] (training ) Lm: 6.820 (6.820), Lt: 6.115 (6.115), Acc m&t: 2.58 4.05, Remain: 5 days, 23:48:44, Finish: 2024-11-28 08:26 [11-23 00:37:29] (/home/user/VAR/train.py , line 276)=> [ep18] (training ) Lm: 6.820 (6.820), Lt: 6.115 (6.115), Acc m&t: 2.58 4.05, Remain: 5 days, 23:48:08, Finish: 2024-11-28 08:25 [11-23 00:37:29] (/home/user/VAR/train.py , line 276)=> [ep18] (training ) Lm: 6.820 (6.820), Lt: 6.115 (6.115), Acc m&t: 2.58 4.05, Remain: 5 days, 23:47:26, Finish: 2024-11-28 08:24 [11-23 00:37:29] (/home/user/VAR/train.py , line 276)=> [ep18] (training ) Lm: 6.820 (6.820), Lt: 6.115 (6.115), Acc m&t: 2.58 4.05, Remain: 5 days, 23:45:04, Finish: 2024-11-28 08:22 [11-23 00:37:29] (/home/user/VAR/train.py , line 276)=> [ep18] (training ) Lm: 6.820 (6.820), Lt: 6.115 (6.115), Acc m&t: 2.58 4.05, Remain: 5 days, 23:47:27, Finish: 2024-11-28 08:24 [11-23 00:37:29] (/home/user/VAR/train.py , line 276)=> [ep18] (training ) Lm: 6.820 (6.820), Lt: 6.115 (6.115), Acc m&t: 2.58 4.05, Remain: 5 days, 23:45:35, Finish: 2024-11-28 08:23 [11-23 00:37:29] (/home/user/VAR/train.py , line 276)=> [ep18] (training ) Lm: 6.820 (6.820), Lt: 6.115 (6.115), Acc m&t: 2.58 4.05, Remain: 5 days, 23:51:41, Finish: 2024-11-28 08:29 [11-23 00:37:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 0/1669] eta: 0:24:59 tlr: 0.00024 tnm: 0.29 Lm: 6.927 (6.927) Lt: 6.245 (6.245) Accm: 2.21 (2.21) Acct: 3.65 (3.65) proj_loss: -0.5442 (-0.5442) time: 0.8983 data: 0.0004 [11-23 00:37:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 0/1669] eta: 0:24:59 tlr: 0.00024 tnm: 0.29 Lm: 6.822 (6.822) Lt: 6.174 (6.174) Accm: 2.88 (2.88) Acct: 4.10 (4.10) proj_loss: -0.5186 (-0.5186) time: 0.8986 data: 0.0004 [11-23 00:37:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 0/1669] eta: 0:24:59 tlr: 0.00024 tnm: 0.29 Lm: 6.722 (6.722) Lt: 5.990 (5.990) Accm: 2.93 (2.93) Acct: 4.68 (4.68) proj_loss: -0.5559 (-0.5559) time: 0.8984 data: 0.0004 [11-23 00:37:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 0/1669] eta: 0:24:59 tlr: 0.00024 tnm: 0.29 Lm: 6.847 (6.847) Lt: 6.101 (6.101) Accm: 2.62 (2.62) Acct: 4.03 (4.03) proj_loss: -0.4863 (-0.4863) time: 0.8985 data: 0.0003 [11-23 00:37:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 0/1669] eta: 0:24:59 tlr: 0.00024 tnm: 0.29 Lm: 6.909 (6.909) Lt: 6.211 (6.211) Accm: 2.45 (2.45) Acct: 4.10 (4.10) proj_loss: -0.5271 (-0.5271) time: 0.8985 data: 0.0005 [11-23 00:37:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 0/1669] eta: 0:24:59 tlr: 0.00024 tnm: 0.29 Lm: 6.857 (6.857) Lt: 6.216 (6.216) Accm: 2.52 (2.52) Acct: 3.86 (3.86) proj_loss: -0.5195 (-0.5195) time: 0.8987 data: 0.0004 [11-23 00:37:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 0/1669] eta: 0:24:59 tlr: 0.00024 tnm: 0.29 Lm: 6.755 (6.755) Lt: 6.145 (6.145) Accm: 2.61 (2.61) Acct: 3.93 (3.93) proj_loss: -0.5516 (-0.5516) time: 0.8986 data: 0.0004 [11-23 00:37:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 0/1669] eta: 0:25:05 tlr: 0.00024 tnm: 0.29 Lm: 6.631 (6.631) Lt: 5.918 (5.918) Accm: 3.09 (3.09) Acct: 4.86 (4.86) proj_loss: -0.4964 (-0.4964) time: 0.9018 data: 0.0004 [11-23 00:43:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.30 Lm: 6.686 (6.686) Lt: 5.987 (5.987) Accm: 3.12 (3.12) Acct: 4.87 (4.87) proj_loss: -0.5135 (-0.5135) time: 0.9265 data: 0.0003 [11-23 00:43:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.30 Lm: 6.807 (6.807) Lt: 6.091 (6.091) Accm: 2.72 (2.72) Acct: 4.49 (4.49) proj_loss: -0.5464 (-0.5464) time: 0.9265 data: 0.0002 [11-23 00:43:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.30 Lm: 6.963 (6.963) Lt: 6.276 (6.276) Accm: 2.33 (2.33) Acct: 3.81 (3.81) proj_loss: -0.5276 (-0.5276) time: 0.9265 data: 0.0003 [11-23 00:43:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.30 Lm: 6.848 (6.848) Lt: 6.182 (6.182) Accm: 2.40 (2.40) Acct: 3.89 (3.89) proj_loss: -0.5058 (-0.5058) time: 0.9265 data: 0.0003 [11-23 00:43:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.30 Lm: 6.792 (6.792) Lt: 6.134 (6.134) Accm: 2.70 (2.70) Acct: 4.03 (4.03) proj_loss: -0.5160 (-0.5160) time: 0.9265 data: 0.0003 [11-23 00:43:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.30 Lm: 6.802 (6.802) Lt: 6.044 (6.044) Accm: 2.75 (2.75) Acct: 4.39 (4.39) proj_loss: -0.5017 (-0.5017) time: 0.9265 data: 0.0003 [11-23 00:43:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.30 Lm: 6.860 (6.860) Lt: 6.199 (6.199) Accm: 2.60 (2.60) Acct: 4.22 (4.22) proj_loss: -0.5318 (-0.5318) time: 0.9265 data: 0.0003 [11-23 00:43:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.30 Lm: 6.766 (6.766) Lt: 6.112 (6.112) Accm: 2.72 (2.72) Acct: 4.12 (4.12) proj_loss: -0.5441 (-0.5441) time: 0.9265 data: 0.0003 [11-23 00:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 834/1669] eta: 0:13:14 tlr: 0.00024 tnm: 0.29 Lm: 6.755 (6.672) Lt: 6.079 (5.991) Accm: 2.83 (3.00) Acct: 4.30 (4.64) proj_loss: -0.5366 (-0.5347) time: 0.9254 data: 0.0003 [11-23 00:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 834/1669] eta: 0:13:14 tlr: 0.00024 tnm: 0.29 Lm: 6.892 (6.858) Lt: 6.191 (6.154) Accm: 2.51 (2.58) Acct: 4.30 (4.18) proj_loss: -0.5530 (-0.5486) time: 0.9254 data: 0.0002 [11-23 00:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 834/1669] eta: 0:13:14 tlr: 0.00024 tnm: 0.29 Lm: 6.764 (6.789) Lt: 6.091 (6.060) Accm: 2.84 (2.78) Acct: 4.44 (4.41) proj_loss: -0.4981 (-0.5005) time: 0.9254 data: 0.0003 [11-23 00:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 834/1669] eta: 0:13:14 tlr: 0.00024 tnm: 0.29 Lm: 6.705 (6.692) Lt: 6.043 (6.006) Accm: 3.09 (2.90) Acct: 4.86 (4.41) proj_loss: -0.5307 (-0.5318) time: 0.9254 data: 0.0002 [11-23 00:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 834/1669] eta: 0:13:14 tlr: 0.00024 tnm: 0.29 Lm: 6.857 (6.885) Lt: 6.216 (6.222) Accm: 2.30 (2.37) Acct: 3.86 (3.76) proj_loss: -0.5195 (-0.5127) time: 0.9254 data: 0.0003 [11-23 00:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 834/1669] eta: 0:13:14 tlr: 0.00024 tnm: 0.29 Lm: 6.909 (6.880) Lt: 6.196 (6.198) Accm: 2.45 (2.51) Acct: 4.10 (4.05) proj_loss: -0.5271 (-0.5268) time: 0.9254 data: 0.0002 [11-23 00:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 834/1669] eta: 0:13:14 tlr: 0.00024 tnm: 0.29 Lm: 6.809 (6.798) Lt: 6.093 (6.103) Accm: 2.51 (2.62) Acct: 4.10 (4.11) proj_loss: -0.5134 (-0.5099) time: 0.9254 data: 0.0003 [11-23 00:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [ 834/1669] eta: 0:13:14 tlr: 0.00024 tnm: 0.29 Lm: 6.927 (6.922) Lt: 6.245 (6.227) Accm: 2.43 (2.36) Acct: 3.96 (3.86) proj_loss: -0.5110 (-0.5147) time: 0.9254 data: 0.0003 [11-23 00:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [1251/1669] eta: 0:06:34 tlr: 0.00024 tnm: 0.29 Lm: 6.932 (6.926) Lt: 6.274 (6.246) Accm: 2.32 (2.30) Acct: 3.81 (3.75) proj_loss: -0.5225 (-0.5195) time: 0.9264 data: 0.0003 [11-23 00:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [1251/1669] eta: 0:06:34 tlr: 0.00024 tnm: 0.29 Lm: 6.719 (6.702) Lt: 6.018 (6.003) Accm: 2.88 (2.84) Acct: 4.55 (4.36) proj_loss: -0.5274 (-0.5299) time: 0.9264 data: 0.0003 [11-23 00:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [1251/1669] eta: 0:06:34 tlr: 0.00024 tnm: 0.29 Lm: 6.760 (6.716) Lt: 6.039 (5.991) Accm: 2.86 (2.98) Acct: 4.60 (4.68) proj_loss: -0.5076 (-0.5108) time: 0.9264 data: 0.0003 [11-23 00:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [1251/1669] eta: 0:06:34 tlr: 0.00024 tnm: 0.29 Lm: 6.886 (6.893) Lt: 6.204 (6.215) Accm: 2.41 (2.44) Acct: 3.89 (3.85) proj_loss: -0.5058 (-0.5060) time: 0.9264 data: 0.0003 [11-23 00:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [1251/1669] eta: 0:06:34 tlr: 0.00024 tnm: 0.29 Lm: 6.766 (6.713) Lt: 6.073 (6.010) Accm: 2.72 (2.86) Acct: 4.13 (4.47) proj_loss: -0.5262 (-0.5278) time: 0.9264 data: 0.0003 [11-23 00:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [1251/1669] eta: 0:06:34 tlr: 0.00024 tnm: 0.29 Lm: 6.860 (6.848) Lt: 6.191 (6.146) Accm: 2.43 (2.48) Acct: 4.17 (4.10) proj_loss: -0.5220 (-0.5225) time: 0.9264 data: 0.0002 [11-23 00:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [1251/1669] eta: 0:06:34 tlr: 0.00024 tnm: 0.29 Lm: 6.881 (6.861) Lt: 6.195 (6.165) Accm: 2.51 (2.56) Acct: 4.08 (4.10) proj_loss: -0.5449 (-0.5329) time: 0.9264 data: 0.0002 [11-23 00:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [1251/1669] eta: 0:06:34 tlr: 0.00024 tnm: 0.29 Lm: 6.806 (6.799) Lt: 6.097 (6.103) Accm: 2.48 (2.58) Acct: 4.03 (4.00) proj_loss: -0.5055 (-0.5039) time: 0.9264 data: 0.0003 [11-23 01:03:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.809 (6.850) Lt: 6.101 (6.164) Accm: 2.46 (2.46) Acct: 3.96 (3.80) proj_loss: -0.5134 (-0.5070) time: 0.9299 data: 0.0017 [11-23 01:03:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 19/350] Total time: 0:26:08 (0.940 s / it) [11-23 01:03:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.927 (6.887) Lt: 6.245 (6.201) Accm: 2.43 (2.41) Acct: 3.96 (3.91) proj_loss: -0.5341 (-0.5230) time: 0.9299 data: 0.0017 [11-23 01:03:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.732 (6.719) Lt: 6.043 (6.016) Accm: 2.75 (2.83) Acct: 4.24 (4.29) proj_loss: -0.5307 (-0.5301) time: 0.9299 data: 0.0019 [11-23 01:03:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.764 (6.745) Lt: 6.091 (6.018) Accm: 2.84 (2.92) Acct: 4.44 (4.63) proj_loss: -0.4981 (-0.5082) time: 0.9299 data: 0.0018 [11-23 01:03:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.811 (6.816) Lt: 6.186 (6.116) Accm: 2.45 (2.56) Acct: 4.10 (4.10) proj_loss: -0.5271 (-0.5259) time: 0.9299 data: 0.0015 [11-23 01:03:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.776 (6.726) Lt: 6.068 (6.008) Accm: 2.61 (2.79) Acct: 4.03 (4.38) proj_loss: -0.5158 (-0.5212) time: 0.9299 data: 0.0017 [11-23 01:03:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.857 (6.838) Lt: 6.192 (6.145) Accm: 2.52 (2.59) Acct: 3.93 (4.08) proj_loss: -0.5195 (-0.5109) time: 0.9299 data: 0.0018 [11-23 01:03:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 19/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.870 (6.808) Lt: 6.191 (6.096) Accm: 2.51 (2.63) Acct: 4.30 (4.28) proj_loss: -0.5369 (-0.5268) time: 0.9299 data: 0.0016 [11-23 01:03:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 19/350] Total time: 0:26:08 (0.940 s / it) [11-23 01:03:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 19/350] Total time: 0:26:08 (0.940 s / it) [11-23 01:03:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 19/350] Total time: 0:26:08 (0.940 s / it) [11-23 01:03:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 19/350] Total time: 0:26:08 (0.940 s / it) [11-23 01:03:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 19/350] Total time: 0:26:08 (0.940 s / it) [11-23 01:03:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 19/350] Total time: 0:26:08 (0.940 s / it) [11-23 01:03:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 19/350] Total time: 0:26:08 (0.940 s / it) [11-23 01:05:46] (home/user/VAR/trainer.py, line 114)=> FID: 5.846519008719042 [11-23 01:05:47] (/home/user/VAR/train.py , line 259)=> [*] [ep19] (val 50000) Lm: 6.7972, Lt: 6.0872, Acc m&t: 2.62 4.15, Val cost: 129.27s [11-23 01:05:47] (/home/user/VAR/train.py , line 264)=> [saving ckpt] ... [saving ckpt](*) finished! @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth [11-23 01:06:49] (/home/user/VAR/train.py , line 276)=> [ep19] (training ) Lm: 6.797 (6.797), Lt: 6.087 (6.087), Acc m&t: 2.62 4.15, Remain: 5 days, 23:18:38, Finish: 2024-11-28 08:22 [11-23 01:06:49] (/home/user/VAR/train.py , line 276)=> [ep19] (training ) Lm: 6.797 (6.797), Lt: 6.087 (6.087), Acc m&t: 2.62 4.15, Remain: 5 days, 23:21:10, Finish: 2024-11-28 08:24 [11-23 01:06:49] (/home/user/VAR/train.py , line 276)=> [ep19] (training ) Lm: 6.797 (6.797), Lt: 6.087 (6.087), Acc m&t: 2.62 4.15, Remain: 5 days, 23:23:53, Finish: 2024-11-28 08:27 [11-23 01:06:49] (/home/user/VAR/train.py , line 276)=> [ep19] (training ) Lm: 6.797 (6.797), Lt: 6.087 (6.087), Acc m&t: 2.62 4.15, Remain: 5 days, 23:19:52, Finish: 2024-11-28 08:23 [11-23 01:06:49] (/home/user/VAR/train.py , line 276)=> [ep19] (training ) Lm: 6.797 (6.797), Lt: 6.087 (6.087), Acc m&t: 2.62 4.15, Remain: 5 days, 23:25:32, Finish: 2024-11-28 08:29 [11-23 01:06:49] (/home/user/VAR/train.py , line 276)=> [ep19] (training ) Lm: 6.797 (6.797), Lt: 6.087 (6.087), Acc m&t: 2.62 4.15, Remain: 5 days, 23:20:17, Finish: 2024-11-28 08:23 [11-23 01:06:49] (/home/user/VAR/train.py , line 276)=> [ep19] (training ) Lm: 6.797 (6.797), Lt: 6.087 (6.087), Acc m&t: 2.62 4.15, Remain: 5 days, 23:26:09, Finish: 2024-11-28 08:29 [11-23 01:06:49] (/home/user/VAR/train.py , line 276)=> [ep19] (training ) Lm: 6.797 (6.797), Lt: 6.087 (6.087), Acc m&t: 2.62 4.15, Remain: 5 days, 23:25:15, Finish: 2024-11-28 08:28 [11-23 01:06:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 0/1669] eta: 0:25:05 tlr: 0.00024 tnm: 0.27 Lm: 6.720 (6.720) Lt: 6.006 (6.006) Accm: 2.88 (2.88) Acct: 4.27 (4.27) proj_loss: -0.5102 (-0.5102) time: 0.9021 data: 0.0004 [11-23 01:06:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 0/1669] eta: 0:25:17 tlr: 0.00024 tnm: 0.27 Lm: 6.948 (6.948) Lt: 6.189 (6.189) Accm: 2.21 (2.21) Acct: 3.31 (3.31) proj_loss: -0.5330 (-0.5330) time: 0.9090 data: 0.0003 [11-23 01:06:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 0/1669] eta: 0:25:03 tlr: 0.00024 tnm: 0.27 Lm: 6.681 (6.681) Lt: 5.969 (5.969) Accm: 3.00 (3.00) Acct: 4.89 (4.89) proj_loss: -0.5379 (-0.5379) time: 0.9006 data: 0.0004 [11-23 01:06:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 0/1669] eta: 0:25:29 tlr: 0.00024 tnm: 0.27 Lm: 6.728 (6.728) Lt: 6.111 (6.111) Accm: 2.81 (2.81) Acct: 4.58 (4.58) proj_loss: -0.5394 (-0.5394) time: 0.9165 data: 0.0004 [11-23 01:06:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 0/1669] eta: 0:25:03 tlr: 0.00024 tnm: 0.27 Lm: 6.657 (6.657) Lt: 5.885 (5.885) Accm: 2.55 (2.55) Acct: 4.03 (4.03) proj_loss: -0.5275 (-0.5275) time: 0.9006 data: 0.0004 [11-23 01:06:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 0/1669] eta: 0:25:01 tlr: 0.00024 tnm: 0.27 Lm: 6.707 (6.707) Lt: 5.955 (5.955) Accm: 2.78 (2.78) Acct: 4.65 (4.65) proj_loss: -0.4979 (-0.4979) time: 0.8998 data: 0.0004 [11-23 01:06:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 0/1669] eta: 0:25:03 tlr: 0.00024 tnm: 0.27 Lm: 6.883 (6.883) Lt: 6.174 (6.174) Accm: 2.51 (2.51) Acct: 4.03 (4.03) proj_loss: -0.5235 (-0.5235) time: 0.9008 data: 0.0003 [11-23 01:06:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 0/1669] eta: 0:25:03 tlr: 0.00024 tnm: 0.27 Lm: 6.920 (6.920) Lt: 6.299 (6.299) Accm: 2.51 (2.51) Acct: 3.62 (3.62) proj_loss: -0.5301 (-0.5301) time: 0.9008 data: 0.0003 [11-23 01:13:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.28 Lm: 6.738 (6.738) Lt: 6.081 (6.081) Accm: 3.06 (3.06) Acct: 4.68 (4.68) proj_loss: -0.5434 (-0.5434) time: 0.9248 data: 0.0002 [11-23 01:13:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.28 Lm: 6.703 (6.703) Lt: 6.020 (6.020) Accm: 2.96 (2.96) Acct: 4.70 (4.70) proj_loss: -0.5312 (-0.5312) time: 0.9248 data: 0.0002 [11-23 01:13:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.28 Lm: 6.880 (6.880) Lt: 6.137 (6.137) Accm: 2.41 (2.41) Acct: 3.72 (3.72) proj_loss: -0.5271 (-0.5271) time: 0.9248 data: 0.0003 [11-23 01:13:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.28 Lm: 6.848 (6.848) Lt: 6.125 (6.125) Accm: 2.53 (2.53) Acct: 3.99 (3.99) proj_loss: -0.5180 (-0.5180) time: 0.9248 data: 0.0003 [11-23 01:13:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.28 Lm: 6.828 (6.828) Lt: 6.090 (6.090) Accm: 2.73 (2.73) Acct: 4.42 (4.42) proj_loss: -0.5203 (-0.5203) time: 0.9248 data: 0.0003 [11-23 01:13:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.28 Lm: 6.797 (6.797) Lt: 6.079 (6.079) Accm: 2.57 (2.57) Acct: 4.17 (4.17) proj_loss: -0.5045 (-0.5045) time: 0.9248 data: 0.0003 [11-23 01:13:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.28 Lm: 6.770 (6.770) Lt: 6.033 (6.033) Accm: 2.48 (2.48) Acct: 4.13 (4.13) proj_loss: -0.5206 (-0.5206) time: 0.9248 data: 0.0003 [11-23 01:13:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.28 Lm: 6.808 (6.808) Lt: 6.115 (6.115) Accm: 2.59 (2.59) Acct: 3.98 (3.98) proj_loss: -0.5089 (-0.5089) time: 0.9248 data: 0.0003 [11-23 01:19:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.32 Lm: 6.779 (6.798) Lt: 6.007 (6.079) Accm: 2.64 (2.61) Acct: 4.06 (4.01) proj_loss: -0.5102 (-0.5152) time: 0.9285 data: 0.0004 [11-23 01:19:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.32 Lm: 6.905 (6.793) Lt: 6.299 (6.154) Accm: 2.53 (2.88) Acct: 3.99 (4.45) proj_loss: -0.5301 (-0.5380) time: 0.9284 data: 0.0002 [11-23 01:19:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.32 Lm: 6.837 (6.831) Lt: 6.140 (6.107) Accm: 2.67 (2.71) Acct: 4.06 (4.30) proj_loss: -0.5196 (-0.5201) time: 0.9284 data: 0.0003 [11-23 01:19:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.32 Lm: 6.657 (6.731) Lt: 5.885 (5.958) Accm: 2.55 (2.68) Acct: 4.24 (4.45) proj_loss: -0.5275 (-0.5308) time: 0.9285 data: 0.0003 [11-23 01:19:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.32 Lm: 6.728 (6.748) Lt: 6.102 (6.047) Accm: 2.81 (2.86) Acct: 4.58 (4.45) proj_loss: -0.5343 (-0.5323) time: 0.9285 data: 0.0003 [11-23 01:19:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.32 Lm: 6.812 (6.831) Lt: 6.098 (6.116) Accm: 2.56 (2.62) Acct: 4.03 (4.06) proj_loss: -0.5235 (-0.5207) time: 0.9285 data: 0.0003 [11-23 01:19:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.32 Lm: 6.817 (6.859) Lt: 6.121 (6.132) Accm: 2.43 (2.42) Acct: 4.06 (3.83) proj_loss: -0.5211 (-0.5250) time: 0.9285 data: 0.0003 [11-23 01:19:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.32 Lm: 6.853 (6.816) Lt: 6.165 (6.108) Accm: 2.52 (2.55) Acct: 4.13 (4.16) proj_loss: -0.5111 (-0.5119) time: 0.9285 data: 0.0003 [11-23 01:26:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.29 Lm: 6.870 (6.834) Lt: 6.149 (6.114) Accm: 2.53 (2.55) Acct: 4.12 (4.14) proj_loss: -0.5176 (-0.5149) time: 0.9294 data: 0.0003 [11-23 01:26:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.29 Lm: 6.814 (6.822) Lt: 6.103 (6.092) Accm: 2.52 (2.61) Acct: 4.10 (4.15) proj_loss: -0.5271 (-0.5317) time: 0.9294 data: 0.0002 [11-23 01:26:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.29 Lm: 6.910 (6.824) Lt: 6.285 (6.183) Accm: 2.52 (2.78) Acct: 4.15 (4.42) proj_loss: -0.5434 (-0.5493) time: 0.9294 data: 0.0003 [11-23 01:26:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.29 Lm: 6.764 (6.786) Lt: 6.047 (6.081) Accm: 2.76 (2.68) Acct: 4.17 (4.08) proj_loss: -0.5189 (-0.5227) time: 0.9294 data: 0.0003 [11-23 01:26:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.29 Lm: 6.848 (6.851) Lt: 6.136 (6.131) Accm: 2.57 (2.61) Acct: 4.12 (4.15) proj_loss: -0.5195 (-0.5194) time: 0.9294 data: 0.0003 [11-23 01:26:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.29 Lm: 6.782 (6.784) Lt: 6.107 (6.078) Accm: 2.74 (2.77) Acct: 4.27 (4.29) proj_loss: -0.5326 (-0.5319) time: 0.9294 data: 0.0003 [11-23 01:26:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.29 Lm: 6.898 (6.863) Lt: 6.176 (6.151) Accm: 2.56 (2.55) Acct: 4.01 (4.06) proj_loss: -0.5277 (-0.5240) time: 0.9294 data: 0.0003 [11-23 01:26:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.29 Lm: 6.716 (6.742) Lt: 5.964 (5.979) Accm: 2.48 (2.60) Acct: 4.13 (4.25) proj_loss: -0.5206 (-0.5242) time: 0.9294 data: 0.0003 [11-23 01:32:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.30 Lm: 6.728 (6.739) Lt: 6.019 (5.987) Accm: 2.55 (2.61) Acct: 4.03 (4.19) proj_loss: -0.5275 (-0.5258) time: 0.9287 data: 0.0017 [11-23 01:32:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 20/350] Total time: 0:25:47 (0.927 s / it) [11-23 01:32:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.30 Lm: 6.905 (6.815) Lt: 6.270 (6.145) Accm: 2.53 (2.76) Acct: 4.30 (4.44) proj_loss: -0.5301 (-0.5434) time: 0.9287 data: 0.0015 [11-23 01:32:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.30 Lm: 6.837 (6.832) Lt: 6.140 (6.119) Accm: 2.67 (2.59) Acct: 4.06 (4.24) proj_loss: -0.5359 (-0.5277) time: 0.9287 data: 0.0017 [11-23 01:32:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.30 Lm: 6.812 (6.808) Lt: 6.098 (6.084) Accm: 2.58 (2.62) Acct: 4.20 (4.19) proj_loss: -0.5171 (-0.5190) time: 0.9287 data: 0.0016 [11-23 01:32:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.30 Lm: 6.817 (6.833) Lt: 6.121 (6.101) Accm: 2.58 (2.60) Acct: 4.13 (4.22) proj_loss: -0.5211 (-0.5293) time: 0.9287 data: 0.0018 [11-23 01:32:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.30 Lm: 6.748 (6.744) Lt: 6.007 (6.033) Accm: 2.88 (2.73) Acct: 4.27 (4.21) proj_loss: -0.5129 (-0.5207) time: 0.9287 data: 0.0016 [11-23 01:32:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.30 Lm: 6.853 (6.809) Lt: 6.134 (6.084) Accm: 2.53 (2.62) Acct: 4.13 (4.24) proj_loss: -0.5240 (-0.5173) time: 0.9287 data: 0.0023 [11-23 01:32:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 20/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.30 Lm: 6.728 (6.757) Lt: 6.102 (6.032) Accm: 2.75 (2.77) Acct: 4.58 (4.36) proj_loss: -0.5343 (-0.5325) time: 0.9287 data: 0.0016 [11-23 01:32:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 20/350] Total time: 0:25:47 (0.927 s / it) [11-23 01:32:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 20/350] Total time: 0:25:47 (0.927 s / it) [11-23 01:32:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 20/350] Total time: 0:25:47 (0.927 s / it) [11-23 01:32:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 20/350] Total time: 0:25:47 (0.927 s / it) [11-23 01:32:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 20/350] Total time: 0:25:47 (0.927 s / it) [11-23 01:32:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 20/350] Total time: 0:25:47 (0.927 s / it) [11-23 01:32:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 20/350] Total time: 0:25:47 (0.927 s / it) [11-23 01:32:37] (/home/user/VAR/train.py , line 276)=> [ep20] (training ) Lm: 6.797 (6.797), Lt: 6.082 (6.082), Acc m&t: 2.63 4.15, Remain: 5 days, 22:35:12, Finish: 2024-11-28 08:07 [11-23 01:32:37] (/home/user/VAR/train.py , line 276)=> [ep20] (training ) Lm: 6.797 (6.797), Lt: 6.082 (6.082), Acc m&t: 2.63 4.15, Remain: 5 days, 22:34:46, Finish: 2024-11-28 08:07 [11-23 01:32:37] (/home/user/VAR/train.py , line 276)=> [ep20] (training ) Lm: 6.797 (6.797), Lt: 6.082 (6.082), Acc m&t: 2.63 4.15, Remain: 5 days, 22:36:07, Finish: 2024-11-28 08:08 [11-23 01:32:37] (/home/user/VAR/train.py , line 276)=> [ep20] (training ) Lm: 6.797 (6.797), Lt: 6.082 (6.082), Acc m&t: 2.63 4.15, Remain: 5 days, 22:34:45, Finish: 2024-11-28 08:07 [11-23 01:32:37] (/home/user/VAR/train.py , line 276)=> [ep20] (training ) Lm: 6.797 (6.797), Lt: 6.082 (6.082), Acc m&t: 2.63 4.15, Remain: 5 days, 22:35:53, Finish: 2024-11-28 08:08 [11-23 01:32:37] (/home/user/VAR/train.py , line 276)=> [ep20] (training ) Lm: 6.797 (6.797), Lt: 6.082 (6.082), Acc m&t: 2.63 4.15, Remain: 5 days, 22:34:28, Finish: 2024-11-28 08:07 [11-23 01:32:37] (/home/user/VAR/train.py , line 276)=> [ep20] (training ) Lm: 6.797 (6.797), Lt: 6.082 (6.082), Acc m&t: 2.63 4.15, Remain: 5 days, 22:37:00, Finish: 2024-11-28 08:09 [11-23 01:32:37] (/home/user/VAR/train.py , line 276)=> [ep20] (training ) Lm: 6.797 (6.797), Lt: 6.082 (6.082), Acc m&t: 2.63 4.15, Remain: 5 days, 22:36:14, Finish: 2024-11-28 08:08 [11-23 01:32:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 0/1669] eta: 0:26:02 tlr: 0.00024 tnm: 0.29 Lm: 6.873 (6.873) Lt: 6.230 (6.230) Accm: 2.52 (2.52) Acct: 3.48 (3.48) proj_loss: -0.5283 (-0.5283) time: 0.9363 data: 0.0003 [11-23 01:32:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 0/1669] eta: 0:25:13 tlr: 0.00024 tnm: 0.29 Lm: 6.833 (6.833) Lt: 6.164 (6.164) Accm: 2.49 (2.49) Acct: 4.17 (4.17) proj_loss: -0.5183 (-0.5183) time: 0.9069 data: 0.0004 [11-23 01:32:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 0/1669] eta: 0:25:12 tlr: 0.00024 tnm: 0.29 Lm: 6.975 (6.975) Lt: 6.332 (6.332) Accm: 2.21 (2.21) Acct: 3.31 (3.31) proj_loss: -0.5141 (-0.5141) time: 0.9060 data: 0.0003 [11-23 01:32:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 0/1669] eta: 0:25:13 tlr: 0.00024 tnm: 0.29 Lm: 6.844 (6.844) Lt: 6.129 (6.129) Accm: 2.29 (2.29) Acct: 3.55 (3.55) proj_loss: -0.5418 (-0.5418) time: 0.9066 data: 0.0003 [11-23 01:32:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 0/1669] eta: 0:25:10 tlr: 0.00024 tnm: 0.29 Lm: 6.922 (6.922) Lt: 6.192 (6.192) Accm: 2.26 (2.26) Acct: 3.51 (3.51) proj_loss: -0.5282 (-0.5282) time: 0.9051 data: 0.0003 [11-23 01:32:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 0/1669] eta: 0:25:13 tlr: 0.00024 tnm: 0.29 Lm: 6.937 (6.937) Lt: 6.182 (6.182) Accm: 2.13 (2.13) Acct: 3.58 (3.58) proj_loss: -0.5273 (-0.5273) time: 0.9069 data: 0.0003 [11-23 01:32:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 0/1669] eta: 0:25:13 tlr: 0.00024 tnm: 0.29 Lm: 6.787 (6.787) Lt: 6.057 (6.057) Accm: 2.67 (2.67) Acct: 4.51 (4.51) proj_loss: -0.5194 (-0.5194) time: 0.9068 data: 0.0004 [11-23 01:32:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 0/1669] eta: 0:25:13 tlr: 0.00024 tnm: 0.29 Lm: 6.826 (6.826) Lt: 6.160 (6.160) Accm: 2.70 (2.70) Acct: 3.99 (3.99) proj_loss: -0.5373 (-0.5373) time: 0.9070 data: 0.0004 [11-23 01:39:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 417/1669] eta: 0:19:19 tlr: 0.00024 tnm: 0.28 Lm: 6.895 (6.895) Lt: 6.192 (6.192) Accm: 2.40 (2.40) Acct: 3.65 (3.65) proj_loss: -0.5274 (-0.5274) time: 0.9266 data: 0.0003 [11-23 01:39:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 417/1669] eta: 0:19:19 tlr: 0.00024 tnm: 0.28 Lm: 6.840 (6.840) Lt: 6.142 (6.142) Accm: 2.45 (2.45) Acct: 3.53 (3.53) proj_loss: -0.5282 (-0.5282) time: 0.9266 data: 0.0002 [11-23 01:39:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 417/1669] eta: 0:19:19 tlr: 0.00024 tnm: 0.28 Lm: 6.890 (6.890) Lt: 6.163 (6.163) Accm: 2.40 (2.40) Acct: 3.89 (3.89) proj_loss: -0.5244 (-0.5244) time: 0.9266 data: 0.0003 [11-23 01:39:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 417/1669] eta: 0:19:19 tlr: 0.00024 tnm: 0.28 Lm: 6.951 (6.951) Lt: 6.292 (6.292) Accm: 2.24 (2.24) Acct: 3.41 (3.41) proj_loss: -0.5173 (-0.5173) time: 0.9266 data: 0.0002 [11-23 01:39:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 417/1669] eta: 0:19:19 tlr: 0.00024 tnm: 0.28 Lm: 6.801 (6.801) Lt: 6.143 (6.143) Accm: 2.39 (2.39) Acct: 3.82 (3.82) proj_loss: -0.5314 (-0.5314) time: 0.9266 data: 0.0003 [11-23 01:39:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 417/1669] eta: 0:19:19 tlr: 0.00024 tnm: 0.28 Lm: 6.807 (6.807) Lt: 6.131 (6.131) Accm: 2.49 (2.49) Acct: 3.86 (3.86) proj_loss: -0.5362 (-0.5362) time: 0.9266 data: 0.0003 [11-23 01:39:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 417/1669] eta: 0:19:19 tlr: 0.00024 tnm: 0.28 Lm: 6.734 (6.734) Lt: 5.988 (5.988) Accm: 2.80 (2.80) Acct: 4.41 (4.41) proj_loss: -0.5399 (-0.5399) time: 0.9266 data: 0.0003 [11-23 01:39:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 417/1669] eta: 0:19:19 tlr: 0.00024 tnm: 0.28 Lm: 6.882 (6.882) Lt: 6.186 (6.186) Accm: 2.37 (2.37) Acct: 3.96 (3.96) proj_loss: -0.5108 (-0.5108) time: 0.9266 data: 0.0003 [11-23 01:45:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 834/1669] eta: 0:12:58 tlr: 0.00024 tnm: 0.25 Lm: 6.787 (6.834) Lt: 6.057 (6.119) Accm: 2.45 (2.40) Acct: 3.51 (3.81) proj_loss: -0.5194 (-0.5271) time: 0.9286 data: 0.0003 [11-23 01:45:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 834/1669] eta: 0:12:58 tlr: 0.00024 tnm: 0.25 Lm: 6.806 (6.828) Lt: 6.123 (6.136) Accm: 2.52 (2.51) Acct: 3.58 (3.70) proj_loss: -0.5280 (-0.5179) time: 0.9286 data: 0.0002 [11-23 01:45:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 834/1669] eta: 0:12:58 tlr: 0.00024 tnm: 0.25 Lm: 6.826 (6.852) Lt: 6.160 (6.139) Accm: 2.46 (2.42) Acct: 3.82 (3.71) proj_loss: -0.5175 (-0.5198) time: 0.9286 data: 0.0003 [11-23 01:45:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 834/1669] eta: 0:12:58 tlr: 0.00024 tnm: 0.25 Lm: 6.926 (6.910) Lt: 6.252 (6.228) Accm: 2.26 (2.40) Acct: 3.51 (3.67) proj_loss: -0.5205 (-0.5251) time: 0.9286 data: 0.0003 [11-23 01:45:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 834/1669] eta: 0:12:58 tlr: 0.00024 tnm: 0.25 Lm: 6.844 (6.856) Lt: 6.145 (6.122) Accm: 2.43 (2.41) Acct: 3.82 (3.87) proj_loss: -0.5216 (-0.5220) time: 0.9286 data: 0.0003 [11-23 01:45:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 834/1669] eta: 0:12:58 tlr: 0.00024 tnm: 0.25 Lm: 6.922 (6.858) Lt: 6.192 (6.175) Accm: 2.26 (2.34) Acct: 3.51 (3.60) proj_loss: -0.5282 (-0.5275) time: 0.9286 data: 0.0003 [11-23 01:45:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 834/1669] eta: 0:12:58 tlr: 0.00024 tnm: 0.25 Lm: 6.844 (6.811) Lt: 6.129 (6.090) Accm: 2.29 (2.49) Acct: 3.55 (3.99) proj_loss: -0.5380 (-0.5286) time: 0.9286 data: 0.0003 [11-23 01:45:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [ 834/1669] eta: 0:12:58 tlr: 0.00024 tnm: 0.25 Lm: 6.770 (6.785) Lt: 6.121 (6.113) Accm: 2.45 (2.41) Acct: 3.89 (3.85) proj_loss: -0.5336 (-0.5321) time: 0.9287 data: 0.0003 [11-23 01:52:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [1251/1669] eta: 0:06:29 tlr: 0.00024 tnm: 0.29 Lm: 6.801 (6.812) Lt: 6.143 (6.135) Accm: 2.47 (2.46) Acct: 4.03 (3.96) proj_loss: -0.5260 (-0.5247) time: 0.9274 data: 0.0003 [11-23 01:52:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [1251/1669] eta: 0:06:29 tlr: 0.00024 tnm: 0.29 Lm: 6.796 (6.812) Lt: 6.097 (6.082) Accm: 2.50 (2.45) Acct: 3.82 (3.74) proj_loss: -0.5140 (-0.5174) time: 0.9274 data: 0.0002 [11-23 01:52:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [1251/1669] eta: 0:06:29 tlr: 0.00024 tnm: 0.29 Lm: 6.816 (6.811) Lt: 6.092 (6.088) Accm: 2.55 (2.58) Acct: 4.01 (4.19) proj_loss: -0.5194 (-0.5158) time: 0.9274 data: 0.0003 [11-23 01:52:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [1251/1669] eta: 0:06:29 tlr: 0.00024 tnm: 0.29 Lm: 6.815 (6.827) Lt: 6.137 (6.140) Accm: 2.46 (2.48) Acct: 3.53 (3.62) proj_loss: -0.5246 (-0.5187) time: 0.9274 data: 0.0003 [11-23 01:52:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [1251/1669] eta: 0:06:29 tlr: 0.00024 tnm: 0.29 Lm: 6.809 (6.817) Lt: 6.131 (6.106) Accm: 2.49 (2.48) Acct: 3.86 (3.93) proj_loss: -0.5191 (-0.5225) time: 0.9274 data: 0.0003 [11-23 01:52:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [1251/1669] eta: 0:06:29 tlr: 0.00024 tnm: 0.29 Lm: 6.828 (6.843) Lt: 6.105 (6.127) Accm: 2.38 (2.38) Acct: 3.46 (3.68) proj_loss: -0.5161 (-0.5236) time: 0.9274 data: 0.0003 [11-23 01:52:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [1251/1669] eta: 0:06:29 tlr: 0.00024 tnm: 0.29 Lm: 6.878 (6.862) Lt: 6.176 (6.186) Accm: 2.49 (2.52) Acct: 3.86 (3.93) proj_loss: -0.5258 (-0.5266) time: 0.9274 data: 0.0003 [11-23 01:52:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [1251/1669] eta: 0:06:29 tlr: 0.00024 tnm: 0.29 Lm: 6.803 (6.799) Lt: 6.120 (6.095) Accm: 2.37 (2.48) Acct: 3.63 (3.93) proj_loss: -0.5399 (-0.5319) time: 0.9274 data: 0.0003 [11-23 01:58:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.797 (6.798) Lt: 6.110 (6.094) Accm: 2.46 (2.50) Acct: 3.72 (3.95) proj_loss: -0.5380 (-0.5313) time: 0.9285 data: 0.0019 [11-23 01:58:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 21/350] Total time: 0:25:58 (0.934 s / it) [11-23 01:58:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.765 (6.799) Lt: 6.052 (6.076) Accm: 2.53 (2.48) Acct: 3.82 (3.77) proj_loss: -0.5175 (-0.5190) time: 0.9285 data: 0.0015 [11-23 01:58:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.870 (6.852) Lt: 6.147 (6.131) Accm: 2.45 (2.44) Acct: 3.51 (3.85) proj_loss: -0.5194 (-0.5259) time: 0.9285 data: 0.0017 [11-23 01:58:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.788 (6.752) Lt: 6.040 (6.025) Accm: 2.67 (2.72) Acct: 4.20 (4.41) proj_loss: -0.5216 (-0.5214) time: 0.9285 data: 0.0017 [11-23 01:58:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.830 (6.850) Lt: 6.100 (6.162) Accm: 2.72 (2.59) Acct: 4.20 (4.04) proj_loss: -0.5277 (-0.5268) time: 0.9285 data: 0.0017 [11-23 01:58:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.823 (6.844) Lt: 6.151 (6.157) Accm: 2.45 (2.47) Acct: 3.58 (3.75) proj_loss: -0.5212 (-0.5180) time: 0.9285 data: 0.0018 [11-23 01:58:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.833 (6.842) Lt: 6.164 (6.163) Accm: 2.45 (2.40) Acct: 3.89 (3.79) proj_loss: -0.5183 (-0.5231) time: 0.9285 data: 0.0018 [11-23 01:58:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 21/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.786 (6.811) Lt: 6.082 (6.101) Accm: 2.62 (2.51) Acct: 3.75 (3.89) proj_loss: -0.5195 (-0.5219) time: 0.9285 data: 0.0018 [11-23 01:58:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 21/350] Total time: 0:25:58 (0.934 s / it) [11-23 01:58:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 21/350] Total time: 0:25:58 (0.934 s / it) [11-23 01:58:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 21/350] Total time: 0:25:58 (0.934 s / it) [11-23 01:58:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 21/350] Total time: 0:25:58 (0.934 s / it) [11-23 01:58:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 21/350] Total time: 0:25:58 (0.934 s / it) [11-23 01:58:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 21/350] Total time: 0:25:58 (0.934 s / it) [11-23 01:58:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 21/350] Total time: 0:25:58 (0.934 s / it) [11-23 01:58:36] (/home/user/VAR/train.py , line 276)=> [ep21] (training ) Lm: 6.782 (6.782), Lt: 6.067 (6.067), Acc m&t: 2.66 4.20, Remain: 5 days, 22:27:56, Finish: 2024-11-28 08:26 [11-23 01:58:36] (/home/user/VAR/train.py , line 276)=> [ep21] (training ) Lm: 6.782 (6.782), Lt: 6.067 (6.067), Acc m&t: 2.66 4.20, Remain: 5 days, 22:27:22, Finish: 2024-11-28 08:25 [11-23 01:58:36] (/home/user/VAR/train.py , line 276)=> [ep21] (training ) Lm: 6.782 (6.782), Lt: 6.067 (6.067), Acc m&t: 2.66 4.20, Remain: 5 days, 22:27:29, Finish: 2024-11-28 08:26 [11-23 01:58:36] (/home/user/VAR/train.py , line 276)=> [ep21] (training ) Lm: 6.782 (6.782), Lt: 6.067 (6.067), Acc m&t: 2.66 4.20, Remain: 5 days, 22:25:11, Finish: 2024-11-28 08:23 [11-23 01:58:36] (/home/user/VAR/train.py , line 276)=> [ep21] (training ) Lm: 6.782 (6.782), Lt: 6.067 (6.067), Acc m&t: 2.66 4.20, Remain: 5 days, 22:28:55, Finish: 2024-11-28 08:27 [11-23 01:58:36] (/home/user/VAR/train.py , line 276)=> [ep21] (training ) Lm: 6.782 (6.782), Lt: 6.067 (6.067), Acc m&t: 2.66 4.20, Remain: 5 days, 22:27:32, Finish: 2024-11-28 08:26 [11-23 01:58:36] (/home/user/VAR/train.py , line 276)=> [ep21] (training ) Lm: 6.782 (6.782), Lt: 6.067 (6.067), Acc m&t: 2.66 4.20, Remain: 5 days, 22:24:08, Finish: 2024-11-28 08:22 [11-23 01:58:36] (/home/user/VAR/train.py , line 276)=> [ep21] (training ) Lm: 6.782 (6.782), Lt: 6.067 (6.067), Acc m&t: 2.66 4.20, Remain: 5 days, 22:27:09, Finish: 2024-11-28 08:25 [11-23 01:58:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 0/1669] eta: 0:24:43 tlr: 0.00024 tnm: 0.27 Lm: 6.664 (6.664) Lt: 5.994 (5.994) Accm: 2.97 (2.97) Acct: 4.79 (4.79) proj_loss: -0.5429 (-0.5429) time: 0.8891 data: 0.0003 [11-23 01:58:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 0/1669] eta: 0:24:42 tlr: 0.00024 tnm: 0.27 Lm: 6.793 (6.793) Lt: 6.092 (6.092) Accm: 2.21 (2.21) Acct: 3.62 (3.62) proj_loss: -0.5333 (-0.5333) time: 0.8881 data: 0.0003 [11-23 01:58:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 0/1669] eta: 0:24:43 tlr: 0.00024 tnm: 0.27 Lm: 6.811 (6.811) Lt: 6.116 (6.116) Accm: 2.40 (2.40) Acct: 3.96 (3.96) proj_loss: -0.5436 (-0.5436) time: 0.8891 data: 0.0003 [11-23 01:58:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 0/1669] eta: 0:24:44 tlr: 0.00024 tnm: 0.27 Lm: 6.783 (6.783) Lt: 6.074 (6.074) Accm: 2.75 (2.75) Acct: 4.24 (4.24) proj_loss: -0.5329 (-0.5329) time: 0.8895 data: 0.0004 [11-23 01:58:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 0/1669] eta: 0:24:44 tlr: 0.00024 tnm: 0.27 Lm: 6.660 (6.660) Lt: 6.003 (6.003) Accm: 3.26 (3.26) Acct: 5.30 (5.30) proj_loss: -0.5380 (-0.5380) time: 0.8893 data: 0.0004 [11-23 01:58:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 0/1669] eta: 0:24:42 tlr: 0.00024 tnm: 0.27 Lm: 6.821 (6.821) Lt: 6.072 (6.072) Accm: 2.67 (2.67) Acct: 4.06 (4.06) proj_loss: -0.5573 (-0.5573) time: 0.8883 data: 0.0004 [11-23 01:58:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 0/1669] eta: 0:24:45 tlr: 0.00024 tnm: 0.27 Lm: 6.608 (6.608) Lt: 5.884 (5.884) Accm: 3.37 (3.37) Acct: 5.23 (5.23) proj_loss: -0.5476 (-0.5476) time: 0.8898 data: 0.0004 [11-23 01:58:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 0/1669] eta: 0:24:41 tlr: 0.00024 tnm: 0.27 Lm: 6.907 (6.907) Lt: 6.187 (6.187) Accm: 2.10 (2.10) Acct: 3.37 (3.37) proj_loss: -0.5216 (-0.5216) time: 0.8875 data: 0.0003 [11-23 02:05:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.26 Lm: 6.898 (6.898) Lt: 6.202 (6.202) Accm: 2.24 (2.24) Acct: 3.68 (3.68) proj_loss: -0.5295 (-0.5295) time: 0.9281 data: 0.0003 [11-23 02:05:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.26 Lm: 6.729 (6.729) Lt: 6.043 (6.043) Accm: 2.80 (2.80) Acct: 4.42 (4.42) proj_loss: -0.5463 (-0.5463) time: 0.9281 data: 0.0002 [11-23 02:05:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.26 Lm: 6.823 (6.823) Lt: 6.100 (6.100) Accm: 2.61 (2.61) Acct: 3.99 (3.99) proj_loss: -0.5474 (-0.5474) time: 0.9281 data: 0.0003 [11-23 02:05:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.26 Lm: 6.891 (6.891) Lt: 6.199 (6.199) Accm: 2.53 (2.53) Acct: 3.91 (3.91) proj_loss: -0.5426 (-0.5426) time: 0.9281 data: 0.0003 [11-23 02:05:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.26 Lm: 6.766 (6.766) Lt: 6.049 (6.049) Accm: 2.64 (2.64) Acct: 4.20 (4.20) proj_loss: -0.5264 (-0.5264) time: 0.9281 data: 0.0003 [11-23 02:05:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.26 Lm: 6.787 (6.787) Lt: 6.069 (6.069) Accm: 2.47 (2.47) Acct: 3.94 (3.94) proj_loss: -0.5264 (-0.5264) time: 0.9281 data: 0.0002 [11-23 02:05:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.26 Lm: 6.634 (6.634) Lt: 5.913 (5.913) Accm: 3.15 (3.15) Acct: 5.13 (5.13) proj_loss: -0.5478 (-0.5478) time: 0.9281 data: 0.0003 [11-23 02:05:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 417/1669] eta: 0:19:20 tlr: 0.00024 tnm: 0.26 Lm: 6.593 (6.593) Lt: 5.814 (5.814) Accm: 3.59 (3.59) Acct: 5.63 (5.63) proj_loss: -0.5420 (-0.5420) time: 0.9281 data: 0.0003 [11-23 02:11:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.30 Lm: 6.608 (6.683) Lt: 5.884 (5.952) Accm: 3.37 (3.04) Acct: 5.23 (4.69) proj_loss: -0.5364 (-0.5397) time: 0.9275 data: 0.0003 [11-23 02:11:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.30 Lm: 6.793 (6.776) Lt: 6.091 (6.086) Accm: 2.62 (2.71) Acct: 4.06 (4.24) proj_loss: -0.5467 (-0.5464) time: 0.9275 data: 0.0002 [11-23 02:11:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.30 Lm: 6.763 (6.723) Lt: 6.023 (5.996) Accm: 2.53 (2.74) Acct: 3.96 (4.42) proj_loss: -0.5092 (-0.5204) time: 0.9275 data: 0.0002 [11-23 02:11:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.30 Lm: 6.783 (6.805) Lt: 6.126 (6.109) Accm: 2.49 (2.57) Acct: 3.96 (3.98) proj_loss: -0.5392 (-0.5447) time: 0.9275 data: 0.0003 [11-23 02:11:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.30 Lm: 6.660 (6.696) Lt: 6.003 (6.005) Accm: 3.04 (2.89) Acct: 4.96 (4.60) proj_loss: -0.5436 (-0.5464) time: 0.9275 data: 0.0003 [11-23 02:11:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.30 Lm: 6.740 (6.744) Lt: 6.051 (6.049) Accm: 3.03 (2.77) Acct: 4.68 (4.36) proj_loss: -0.5287 (-0.5271) time: 0.9275 data: 0.0003 [11-23 02:11:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.30 Lm: 6.831 (6.871) Lt: 6.072 (6.156) Accm: 2.39 (2.48) Acct: 3.86 (3.89) proj_loss: -0.5280 (-0.5348) time: 0.9275 data: 0.0003 [11-23 02:11:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [ 834/1669] eta: 0:12:54 tlr: 0.00024 tnm: 0.30 Lm: 6.889 (6.889) Lt: 6.212 (6.205) Accm: 2.29 (2.25) Acct: 3.55 (3.64) proj_loss: -0.5374 (-0.5355) time: 0.9275 data: 0.0003 [11-23 02:17:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.27 Lm: 6.880 (6.855) Lt: 6.199 (6.172) Accm: 2.33 (2.40) Acct: 3.77 (3.81) proj_loss: -0.5322 (-0.5334) time: 0.9289 data: 0.0003 [11-23 02:17:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.27 Lm: 6.789 (6.779) Lt: 6.071 (6.078) Accm: 2.78 (2.77) Acct: 4.42 (4.40) proj_loss: -0.5448 (-0.5366) time: 0.9289 data: 0.0003 [11-23 02:17:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.27 Lm: 6.744 (6.723) Lt: 6.011 (5.997) Accm: 2.56 (2.70) Acct: 3.96 (4.30) proj_loss: -0.5206 (-0.5233) time: 0.9289 data: 0.0002 [11-23 02:17:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.27 Lm: 6.727 (6.736) Lt: 6.028 (6.032) Accm: 3.02 (2.83) Acct: 4.60 (4.40) proj_loss: -0.5282 (-0.5273) time: 0.9289 data: 0.0002 [11-23 02:17:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.27 Lm: 6.798 (6.807) Lt: 6.126 (6.114) Accm: 2.50 (2.55) Acct: 3.86 (3.92) proj_loss: -0.5499 (-0.5486) time: 0.9289 data: 0.0002 [11-23 02:17:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.27 Lm: 6.826 (6.808) Lt: 6.070 (6.080) Accm: 2.53 (2.60) Acct: 3.96 (4.11) proj_loss: -0.5235 (-0.5301) time: 0.9289 data: 0.0003 [11-23 02:17:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.27 Lm: 6.683 (6.699) Lt: 6.030 (6.018) Accm: 2.95 (2.88) Acct: 4.77 (4.60) proj_loss: -0.5489 (-0.5484) time: 0.9289 data: 0.0003 [11-23 02:17:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [1251/1669] eta: 0:06:27 tlr: 0.00024 tnm: 0.27 Lm: 6.669 (6.695) Lt: 5.966 (5.975) Accm: 2.94 (2.91) Acct: 4.51 (4.47) proj_loss: -0.5357 (-0.5363) time: 0.9289 data: 0.0003 [11-23 02:24:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.731 (6.737) Lt: 6.047 (6.027) Accm: 2.52 (2.77) Acct: 3.79 (4.27) proj_loss: -0.5364 (-0.5396) time: 0.9291 data: 0.0021 [11-23 02:24:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 22/350] Total time: 0:25:47 (0.927 s / it) [11-23 02:24:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.783 (6.769) Lt: 6.126 (6.077) Accm: 2.51 (2.65) Acct: 3.96 (4.04) proj_loss: -0.5392 (-0.5401) time: 0.9291 data: 0.0015 [11-23 02:24:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.785 (6.771) Lt: 6.076 (6.077) Accm: 2.62 (2.72) Acct: 4.06 (4.27) proj_loss: -0.5429 (-0.5347) time: 0.9291 data: 0.0015 [11-23 02:24:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.821 (6.797) Lt: 6.069 (6.075) Accm: 2.67 (2.70) Acct: 4.06 (4.24) proj_loss: -0.5222 (-0.5286) time: 0.9291 data: 0.0016 [11-23 02:24:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.763 (6.736) Lt: 6.020 (6.001) Accm: 2.58 (2.72) Acct: 3.96 (4.37) proj_loss: -0.5092 (-0.5156) time: 0.9291 data: 0.0016 [11-23 02:24:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.714 (6.727) Lt: 6.020 (6.030) Accm: 3.02 (2.84) Acct: 4.68 (4.48) proj_loss: -0.5277 (-0.5200) time: 0.9291 data: 0.0016 [11-23 02:24:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.705 (6.757) Lt: 6.058 (6.090) Accm: 2.86 (2.76) Acct: 4.58 (4.37) proj_loss: -0.5454 (-0.5478) time: 0.9291 data: 0.0018 [11-23 02:24:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 22/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.872 (6.834) Lt: 6.187 (6.149) Accm: 2.37 (2.42) Acct: 3.99 (3.86) proj_loss: -0.5374 (-0.5369) time: 0.9291 data: 0.0017 [11-23 02:24:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 22/350] Total time: 0:25:47 (0.927 s / it) [11-23 02:24:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 22/350] Total time: 0:25:47 (0.927 s / it) [11-23 02:24:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 22/350] Total time: 0:25:47 (0.927 s / it) [11-23 02:24:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 22/350] Total time: 0:25:47 (0.927 s / it) [11-23 02:24:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 22/350] Total time: 0:25:47 (0.927 s / it) [11-23 02:24:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 22/350] Total time: 0:25:47 (0.927 s / it) [11-23 02:24:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 22/350] Total time: 0:25:47 (0.927 s / it) [11-23 02:24:24] (/home/user/VAR/train.py , line 276)=> [ep22] (training ) Lm: 6.778 (6.778), Lt: 6.060 (6.060), Acc m&t: 2.66 4.20, Remain: 5 days, 22:12:45, Finish: 2024-11-28 08:37 [11-23 02:24:24] (/home/user/VAR/train.py , line 276)=> [ep22] (training ) Lm: 6.778 (6.778), Lt: 6.060 (6.060), Acc m&t: 2.66 4.20, Remain: 5 days, 22:13:24, Finish: 2024-11-28 08:37 [11-23 02:24:24] (/home/user/VAR/train.py , line 276)=> [ep22] (training ) Lm: 6.778 (6.778), Lt: 6.060 (6.060), Acc m&t: 2.66 4.20, Remain: 5 days, 22:12:56, Finish: 2024-11-28 08:37 [11-23 02:24:24] (/home/user/VAR/train.py , line 276)=> [ep22] (training ) Lm: 6.778 (6.778), Lt: 6.060 (6.060), Acc m&t: 2.66 4.20, Remain: 5 days, 22:12:27, Finish: 2024-11-28 08:36 [11-23 02:24:24] (/home/user/VAR/train.py , line 276)=> [ep22] (training ) Lm: 6.778 (6.778), Lt: 6.060 (6.060), Acc m&t: 2.66 4.20, Remain: 5 days, 22:13:54, Finish: 2024-11-28 08:38 [11-23 02:24:24] (/home/user/VAR/train.py , line 276)=> [ep22] (training ) Lm: 6.778 (6.778), Lt: 6.060 (6.060), Acc m&t: 2.66 4.20, Remain: 5 days, 22:12:40, Finish: 2024-11-28 08:37 [11-23 02:24:24] (/home/user/VAR/train.py , line 276)=> [ep22] (training ) Lm: 6.778 (6.778), Lt: 6.060 (6.060), Acc m&t: 2.66 4.20, Remain: 5 days, 22:12:54, Finish: 2024-11-28 08:37 [11-23 02:24:24] (/home/user/VAR/train.py , line 276)=> [ep22] (training ) Lm: 6.778 (6.778), Lt: 6.060 (6.060), Acc m&t: 2.66 4.20, Remain: 5 days, 22:11:22, Finish: 2024-11-28 08:35 [11-23 02:24:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 0/1669] eta: 0:25:28 tlr: 0.00024 tnm: 0.26 Lm: 6.852 (6.852) Lt: 6.140 (6.140) Accm: 2.46 (2.46) Acct: 3.96 (3.96) proj_loss: -0.5372 (-0.5372) time: 0.9160 data: 0.0003 [11-23 02:24:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 0/1669] eta: 0:25:28 tlr: 0.00024 tnm: 0.26 Lm: 6.846 (6.846) Lt: 6.175 (6.175) Accm: 2.49 (2.49) Acct: 4.24 (4.24) proj_loss: -0.5575 (-0.5575) time: 0.9160 data: 0.0003 [11-23 02:24:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 0/1669] eta: 0:25:28 tlr: 0.00024 tnm: 0.26 Lm: 6.498 (6.498) Lt: 5.682 (5.682) Accm: 3.66 (3.66) Acct: 6.37 (6.37) proj_loss: -0.5076 (-0.5076) time: 0.9160 data: 0.0004 [11-23 02:24:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 0/1669] eta: 0:25:29 tlr: 0.00024 tnm: 0.26 Lm: 6.826 (6.826) Lt: 6.149 (6.149) Accm: 2.53 (2.53) Acct: 3.82 (3.82) proj_loss: -0.5373 (-0.5373) time: 0.9163 data: 0.0004 [11-23 02:24:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 0/1669] eta: 0:25:29 tlr: 0.00024 tnm: 0.26 Lm: 6.711 (6.711) Lt: 5.998 (5.998) Accm: 2.75 (2.75) Acct: 4.34 (4.34) proj_loss: -0.5296 (-0.5296) time: 0.9162 data: 0.0004 [11-23 02:24:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 0/1669] eta: 0:25:29 tlr: 0.00024 tnm: 0.26 Lm: 6.850 (6.850) Lt: 6.181 (6.181) Accm: 2.45 (2.45) Acct: 3.65 (3.65) proj_loss: -0.5206 (-0.5206) time: 0.9163 data: 0.0004 [11-23 02:24:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 0/1669] eta: 0:25:29 tlr: 0.00024 tnm: 0.26 Lm: 6.718 (6.718) Lt: 5.961 (5.961) Accm: 2.71 (2.71) Acct: 4.30 (4.30) proj_loss: -0.5260 (-0.5260) time: 0.9163 data: 0.0004 [11-23 02:24:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 0/1669] eta: 0:25:30 tlr: 0.00024 tnm: 0.26 Lm: 6.705 (6.705) Lt: 5.989 (5.989) Accm: 2.81 (2.81) Acct: 4.27 (4.27) proj_loss: -0.5687 (-0.5687) time: 0.9168 data: 0.0004 [11-23 02:31:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 417/1669] eta: 0:19:52 tlr: 0.00024 tnm: 0.29 Lm: 6.704 (6.704) Lt: 5.987 (5.987) Accm: 3.20 (3.20) Acct: 4.87 (4.87) proj_loss: -0.5492 (-0.5492) time: 0.9256 data: 0.0003 [11-23 02:31:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 417/1669] eta: 0:19:52 tlr: 0.00024 tnm: 0.29 Lm: 6.762 (6.762) Lt: 6.062 (6.062) Accm: 2.70 (2.70) Acct: 4.18 (4.18) proj_loss: -0.5299 (-0.5299) time: 0.9256 data: 0.0003 [11-23 02:31:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 417/1669] eta: 0:19:52 tlr: 0.00024 tnm: 0.29 Lm: 6.646 (6.646) Lt: 5.929 (5.929) Accm: 3.31 (3.31) Acct: 5.18 (5.18) proj_loss: -0.5246 (-0.5246) time: 0.9256 data: 0.0002 [11-23 02:31:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 417/1669] eta: 0:19:53 tlr: 0.00024 tnm: 0.29 Lm: 6.802 (6.802) Lt: 6.140 (6.140) Accm: 2.49 (2.49) Acct: 3.93 (3.93) proj_loss: -0.5614 (-0.5614) time: 0.9256 data: 0.0002 [11-23 02:31:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 417/1669] eta: 0:19:52 tlr: 0.00024 tnm: 0.29 Lm: 6.801 (6.801) Lt: 6.127 (6.127) Accm: 2.59 (2.59) Acct: 3.99 (3.99) proj_loss: -0.5208 (-0.5208) time: 0.9256 data: 0.0003 [11-23 02:31:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 417/1669] eta: 0:19:52 tlr: 0.00024 tnm: 0.29 Lm: 6.793 (6.793) Lt: 6.074 (6.074) Accm: 2.54 (2.54) Acct: 3.89 (3.89) proj_loss: -0.5340 (-0.5340) time: 0.9256 data: 0.0002 [11-23 02:31:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 417/1669] eta: 0:19:53 tlr: 0.00024 tnm: 0.29 Lm: 6.879 (6.879) Lt: 6.210 (6.210) Accm: 2.34 (2.34) Acct: 3.62 (3.62) proj_loss: -0.5442 (-0.5442) time: 0.9256 data: 0.0002 [11-23 02:31:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 417/1669] eta: 0:19:52 tlr: 0.00024 tnm: 0.29 Lm: 6.538 (6.538) Lt: 5.761 (5.761) Accm: 2.99 (2.99) Acct: 4.82 (4.82) proj_loss: -0.5194 (-0.5194) time: 0.9256 data: 0.0003 [11-23 02:37:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 834/1669] eta: 0:13:05 tlr: 0.00024 tnm: 0.29 Lm: 6.718 (6.608) Lt: 5.921 (5.814) Accm: 2.71 (2.81) Acct: 4.30 (4.57) proj_loss: -0.5209 (-0.5199) time: 0.9252 data: 0.0003 [11-23 02:37:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 834/1669] eta: 0:13:05 tlr: 0.00024 tnm: 0.29 Lm: 6.852 (6.833) Lt: 6.140 (6.133) Accm: 2.46 (2.40) Acct: 3.96 (3.79) proj_loss: -0.5372 (-0.5355) time: 0.9252 data: 0.0003 [11-23 02:37:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 834/1669] eta: 0:13:05 tlr: 0.00024 tnm: 0.29 Lm: 6.795 (6.699) Lt: 6.062 (5.973) Accm: 2.97 (3.10) Acct: 4.20 (4.86) proj_loss: -0.5248 (-0.5247) time: 0.9252 data: 0.0002 [11-23 02:37:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 834/1669] eta: 0:13:05 tlr: 0.00024 tnm: 0.29 Lm: 6.758 (6.778) Lt: 6.105 (6.095) Accm: 2.49 (2.56) Acct: 4.13 (3.99) proj_loss: -0.5575 (-0.5491) time: 0.9252 data: 0.0002 [11-23 02:37:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 834/1669] eta: 0:13:05 tlr: 0.00024 tnm: 0.29 Lm: 6.705 (6.705) Lt: 5.989 (5.997) Accm: 2.81 (2.94) Acct: 4.27 (4.51) proj_loss: -0.5537 (-0.5507) time: 0.9252 data: 0.0003 [11-23 02:37:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 834/1669] eta: 0:13:05 tlr: 0.00024 tnm: 0.29 Lm: 6.754 (6.780) Lt: 6.149 (6.112) Accm: 2.61 (2.56) Acct: 3.62 (3.80) proj_loss: -0.5384 (-0.5395) time: 0.9252 data: 0.0003 [11-23 02:37:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 834/1669] eta: 0:13:05 tlr: 0.00024 tnm: 0.29 Lm: 6.850 (6.834) Lt: 6.181 (6.190) Accm: 2.45 (2.50) Acct: 3.65 (3.78) proj_loss: -0.5209 (-0.5411) time: 0.9252 data: 0.0003 [11-23 02:37:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [ 834/1669] eta: 0:13:05 tlr: 0.00024 tnm: 0.29 Lm: 6.698 (6.694) Lt: 5.976 (5.997) Accm: 2.86 (2.94) Acct: 4.55 (4.57) proj_loss: -0.5373 (-0.5337) time: 0.9253 data: 0.0003 [11-23 02:43:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [1251/1669] eta: 0:06:31 tlr: 0.00024 tnm: 0.27 Lm: 6.640 (6.666) Lt: 5.921 (5.940) Accm: 2.94 (2.96) Acct: 4.68 (4.63) proj_loss: -0.5309 (-0.5314) time: 0.9281 data: 0.0003 [11-23 02:43:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [1251/1669] eta: 0:06:31 tlr: 0.00024 tnm: 0.27 Lm: 6.744 (6.766) Lt: 6.073 (6.081) Accm: 2.59 (2.63) Acct: 4.13 (4.03) proj_loss: -0.5410 (-0.5345) time: 0.9281 data: 0.0003 [11-23 02:43:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [1251/1669] eta: 0:06:31 tlr: 0.00024 tnm: 0.27 Lm: 6.835 (6.829) Lt: 6.105 (6.117) Accm: 2.49 (2.44) Acct: 4.05 (3.94) proj_loss: -0.5372 (-0.5359) time: 0.9281 data: 0.0002 [11-23 02:43:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [1251/1669] eta: 0:06:31 tlr: 0.00024 tnm: 0.27 Lm: 6.704 (6.645) Lt: 5.987 (5.926) Accm: 3.17 (3.09) Acct: 4.72 (4.67) proj_loss: -0.5417 (-0.5447) time: 0.9281 data: 0.0003 [11-23 02:43:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [1251/1669] eta: 0:06:31 tlr: 0.00024 tnm: 0.27 Lm: 6.823 (6.825) Lt: 6.143 (6.169) Accm: 2.46 (2.49) Acct: 3.67 (3.75) proj_loss: -0.5304 (-0.5408) time: 0.9281 data: 0.0003 [11-23 02:43:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [1251/1669] eta: 0:06:31 tlr: 0.00024 tnm: 0.27 Lm: 6.732 (6.753) Lt: 6.074 (6.073) Accm: 2.68 (2.64) Acct: 3.98 (3.98) proj_loss: -0.5436 (-0.5418) time: 0.9281 data: 0.0003 [11-23 02:43:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [1251/1669] eta: 0:06:31 tlr: 0.00024 tnm: 0.27 Lm: 6.788 (6.719) Lt: 6.066 (5.997) Accm: 2.82 (2.93) Acct: 4.10 (4.59) proj_loss: -0.5162 (-0.5197) time: 0.9281 data: 0.0003 [11-23 02:43:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [1251/1669] eta: 0:06:31 tlr: 0.00024 tnm: 0.27 Lm: 6.713 (6.633) Lt: 5.941 (5.863) Accm: 2.84 (2.85) Acct: 4.32 (4.51) proj_loss: -0.5169 (-0.5127) time: 0.9281 data: 0.0003 [11-23 02:50:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.708 (6.609) Lt: 5.921 (5.836) Accm: 2.97 (2.95) Acct: 4.34 (4.77) proj_loss: -0.5209 (-0.5157) time: 0.9309 data: 0.0015 [11-23 02:50:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 23/350] Total time: 0:25:59 (0.934 s / it) [11-23 02:50:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.850 (6.833) Lt: 6.171 (6.169) Accm: 2.45 (2.47) Acct: 3.65 (3.72) proj_loss: -0.5399 (-0.5454) time: 0.9309 data: 0.0016 [11-23 02:50:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.836 (6.831) Lt: 6.081 (6.110) Accm: 2.52 (2.50) Acct: 4.13 (4.04) proj_loss: -0.5372 (-0.5310) time: 0.9309 data: 0.0018 [11-23 02:50:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.711 (6.736) Lt: 5.998 (6.047) Accm: 2.75 (2.72) Acct: 4.34 (4.13) proj_loss: -0.5384 (-0.5393) time: 0.9309 data: 0.0018 [11-23 02:50:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.702 (6.645) Lt: 5.985 (5.928) Accm: 3.16 (3.10) Acct: 5.17 (4.77) proj_loss: -0.5497 (-0.5457) time: 0.9309 data: 0.0016 [11-23 02:50:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.698 (6.715) Lt: 5.976 (5.983) Accm: 2.86 (2.85) Acct: 4.55 (4.46) proj_loss: -0.5245 (-0.5221) time: 0.9309 data: 0.0020 [11-23 02:50:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.758 (6.815) Lt: 6.105 (6.141) Accm: 2.49 (2.53) Acct: 4.13 (3.87) proj_loss: -0.5245 (-0.5302) time: 0.9309 data: 0.0017 [11-23 02:50:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 23/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.27 Lm: 6.795 (6.761) Lt: 6.070 (6.055) Accm: 2.67 (2.81) Acct: 3.99 (4.41) proj_loss: -0.5248 (-0.5289) time: 0.9309 data: 0.0018 [11-23 02:50:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 23/350] Total time: 0:25:59 (0.934 s / it) [11-23 02:50:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 23/350] Total time: 0:25:59 (0.934 s / it) [11-23 02:50:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 23/350] Total time: 0:25:59 (0.934 s / it) [11-23 02:50:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 23/350] Total time: 0:25:59 (0.934 s / it) [11-23 02:50:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 23/350] Total time: 0:25:59 (0.934 s / it) [11-23 02:50:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 23/350] Total time: 0:25:59 (0.934 s / it) [11-23 02:50:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 23/350] Total time: 0:25:59 (0.934 s / it) [11-23 02:50:23] (/home/user/VAR/train.py , line 276)=> [ep23] (training ) Lm: 6.753 (6.753), Lt: 6.032 (6.032), Acc m&t: 2.73 4.30, Remain: 5 days, 21:36:42, Finish: 2024-11-28 08:27 [11-23 02:50:23] (/home/user/VAR/train.py , line 276)=> [ep23] (training ) Lm: 6.753 (6.753), Lt: 6.032 (6.032), Acc m&t: 2.73 4.30, Remain: 5 days, 21:37:59, Finish: 2024-11-28 08:28 [11-23 02:50:23] (/home/user/VAR/train.py , line 276)=> [ep23] (training ) Lm: 6.753 (6.753), Lt: 6.032 (6.032), Acc m&t: 2.73 4.30, Remain: 5 days, 21:35:24, Finish: 2024-11-28 08:25 [11-23 02:50:23] (/home/user/VAR/train.py , line 276)=> [ep23] (training ) Lm: 6.753 (6.753), Lt: 6.032 (6.032), Acc m&t: 2.73 4.30, Remain: 5 days, 21:38:16, Finish: 2024-11-28 08:28 [11-23 02:50:23] (/home/user/VAR/train.py , line 276)=> [ep23] (training ) Lm: 6.753 (6.753), Lt: 6.032 (6.032), Acc m&t: 2.73 4.30, Remain: 5 days, 21:39:08, Finish: 2024-11-28 08:29 [11-23 02:50:23] (/home/user/VAR/train.py , line 276)=> [ep23] (training ) Lm: 6.753 (6.753), Lt: 6.032 (6.032), Acc m&t: 2.73 4.30, Remain: 5 days, 21:38:31, Finish: 2024-11-28 08:28 [11-23 02:50:23] (/home/user/VAR/train.py , line 276)=> [ep23] (training ) Lm: 6.753 (6.753), Lt: 6.032 (6.032), Acc m&t: 2.73 4.30, Remain: 5 days, 21:40:10, Finish: 2024-11-28 08:30 [11-23 02:50:23] (/home/user/VAR/train.py , line 276)=> [ep23] (training ) Lm: 6.753 (6.753), Lt: 6.032 (6.032), Acc m&t: 2.73 4.30, Remain: 5 days, 21:34:53, Finish: 2024-11-28 08:25 [11-23 02:50:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 0/1669] eta: 0:25:43 tlr: 0.00024 tnm: 0.29 Lm: 6.830 (6.830) Lt: 6.184 (6.184) Accm: 2.75 (2.75) Acct: 4.65 (4.65) proj_loss: -0.5455 (-0.5455) time: 0.9246 data: 0.0003 [11-23 02:50:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 0/1669] eta: 0:25:42 tlr: 0.00024 tnm: 0.29 Lm: 6.588 (6.588) Lt: 5.821 (5.821) Accm: 2.94 (2.94) Acct: 4.68 (4.68) proj_loss: -0.5484 (-0.5484) time: 0.9244 data: 0.0004 [11-23 02:50:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 0/1669] eta: 0:25:42 tlr: 0.00024 tnm: 0.29 Lm: 6.688 (6.688) Lt: 5.934 (5.934) Accm: 2.72 (2.72) Acct: 4.55 (4.55) proj_loss: -0.5020 (-0.5020) time: 0.9241 data: 0.0004 [11-23 02:50:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 0/1669] eta: 0:25:42 tlr: 0.00024 tnm: 0.29 Lm: 6.795 (6.795) Lt: 6.124 (6.124) Accm: 2.68 (2.68) Acct: 4.17 (4.17) proj_loss: -0.5204 (-0.5204) time: 0.9244 data: 0.0004 [11-23 02:50:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 0/1669] eta: 0:25:47 tlr: 0.00024 tnm: 0.29 Lm: 6.798 (6.798) Lt: 6.096 (6.096) Accm: 2.80 (2.80) Acct: 4.72 (4.72) proj_loss: -0.5615 (-0.5615) time: 0.9273 data: 0.0004 [11-23 02:50:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 0/1669] eta: 0:25:43 tlr: 0.00024 tnm: 0.29 Lm: 6.780 (6.780) Lt: 6.104 (6.104) Accm: 2.62 (2.62) Acct: 3.79 (3.79) proj_loss: -0.5717 (-0.5717) time: 0.9250 data: 0.0004 [11-23 02:50:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 0/1669] eta: 0:25:43 tlr: 0.00024 tnm: 0.29 Lm: 6.594 (6.594) Lt: 5.811 (5.811) Accm: 3.18 (3.18) Acct: 4.79 (4.79) proj_loss: -0.5174 (-0.5174) time: 0.9250 data: 0.0004 [11-23 02:50:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 0/1669] eta: 0:25:43 tlr: 0.00024 tnm: 0.29 Lm: 6.760 (6.760) Lt: 6.082 (6.082) Accm: 2.29 (2.29) Acct: 3.68 (3.68) proj_loss: -0.5495 (-0.5495) time: 0.9247 data: 0.0004 [11-23 02:56:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 417/1669] eta: 0:19:22 tlr: 0.00024 tnm: 0.28 Lm: 6.714 (6.714) Lt: 6.034 (6.034) Accm: 2.51 (2.51) Acct: 3.89 (3.89) proj_loss: -0.5621 (-0.5621) time: 0.9297 data: 0.0003 [11-23 02:56:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 417/1669] eta: 0:19:22 tlr: 0.00024 tnm: 0.28 Lm: 6.855 (6.855) Lt: 6.160 (6.160) Accm: 2.69 (2.69) Acct: 4.49 (4.49) proj_loss: -0.5499 (-0.5499) time: 0.9297 data: 0.0003 [11-23 02:56:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 417/1669] eta: 0:19:22 tlr: 0.00024 tnm: 0.28 Lm: 6.784 (6.784) Lt: 6.082 (6.082) Accm: 2.80 (2.80) Acct: 4.49 (4.49) proj_loss: -0.5350 (-0.5350) time: 0.9297 data: 0.0002 [11-23 02:56:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 417/1669] eta: 0:19:22 tlr: 0.00024 tnm: 0.28 Lm: 6.656 (6.656) Lt: 5.941 (5.941) Accm: 2.99 (2.99) Acct: 4.82 (4.82) proj_loss: -0.5281 (-0.5281) time: 0.9297 data: 0.0003 [11-23 02:56:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 417/1669] eta: 0:19:22 tlr: 0.00024 tnm: 0.28 Lm: 6.677 (6.677) Lt: 5.982 (5.982) Accm: 2.84 (2.84) Acct: 4.36 (4.36) proj_loss: -0.5457 (-0.5457) time: 0.9297 data: 0.0003 [11-23 02:56:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 417/1669] eta: 0:19:22 tlr: 0.00024 tnm: 0.28 Lm: 6.622 (6.622) Lt: 5.856 (5.856) Accm: 2.81 (2.81) Acct: 4.20 (4.20) proj_loss: -0.5282 (-0.5282) time: 0.9297 data: 0.0003 [11-23 02:56:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 417/1669] eta: 0:19:22 tlr: 0.00024 tnm: 0.28 Lm: 6.683 (6.683) Lt: 5.981 (5.981) Accm: 2.97 (2.97) Acct: 4.46 (4.46) proj_loss: -0.5528 (-0.5528) time: 0.9297 data: 0.0003 [11-23 02:56:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 417/1669] eta: 0:19:22 tlr: 0.00024 tnm: 0.28 Lm: 6.608 (6.608) Lt: 5.851 (5.851) Accm: 3.04 (3.04) Acct: 4.77 (4.77) proj_loss: -0.5180 (-0.5180) time: 0.9297 data: 0.0003 [11-23 03:03:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 834/1669] eta: 0:13:04 tlr: 0.00024 tnm: 0.26 Lm: 6.622 (6.649) Lt: 5.891 (5.904) Accm: 2.96 (3.02) Acct: 4.75 (4.68) proj_loss: -0.5187 (-0.5244) time: 0.9289 data: 0.0003 [11-23 03:03:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 834/1669] eta: 0:13:04 tlr: 0.00024 tnm: 0.26 Lm: 6.737 (6.705) Lt: 5.981 (5.968) Accm: 2.84 (3.00) Acct: 4.65 (4.86) proj_loss: -0.5455 (-0.5397) time: 0.9289 data: 0.0003 [11-23 03:03:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 834/1669] eta: 0:13:04 tlr: 0.00024 tnm: 0.26 Lm: 6.640 (6.628) Lt: 5.892 (5.873) Accm: 2.94 (2.95) Acct: 4.68 (4.38) proj_loss: -0.5262 (-0.5276) time: 0.9289 data: 0.0003 [11-23 03:03:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 834/1669] eta: 0:13:04 tlr: 0.00024 tnm: 0.26 Lm: 6.813 (6.841) Lt: 6.096 (6.113) Accm: 2.67 (2.68) Acct: 4.51 (4.50) proj_loss: -0.5383 (-0.5358) time: 0.9289 data: 0.0003 [11-23 03:03:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 834/1669] eta: 0:13:04 tlr: 0.00024 tnm: 0.26 Lm: 6.737 (6.697) Lt: 6.048 (6.004) Accm: 2.84 (2.84) Acct: 4.34 (4.35) proj_loss: -0.5624 (-0.5513) time: 0.9289 data: 0.0003 [11-23 03:03:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 834/1669] eta: 0:13:04 tlr: 0.00024 tnm: 0.26 Lm: 6.667 (6.647) Lt: 5.986 (5.943) Accm: 2.72 (2.75) Acct: 4.10 (4.47) proj_loss: -0.5495 (-0.5537) time: 0.9289 data: 0.0003 [11-23 03:03:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 834/1669] eta: 0:13:04 tlr: 0.00024 tnm: 0.26 Lm: 6.688 (6.766) Lt: 5.948 (6.070) Accm: 2.72 (2.78) Acct: 4.55 (4.44) proj_loss: -0.5302 (-0.5288) time: 0.9289 data: 0.0003 [11-23 03:03:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [ 834/1669] eta: 0:13:04 tlr: 0.00024 tnm: 0.26 Lm: 6.780 (6.740) Lt: 6.058 (6.007) Accm: 2.62 (2.80) Acct: 3.79 (4.22) proj_loss: -0.5340 (-0.5452) time: 0.9289 data: 0.0003 [11-23 03:09:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [1251/1669] eta: 0:06:31 tlr: 0.00024 tnm: 0.27 Lm: 6.816 (6.795) Lt: 6.081 (6.079) Accm: 2.54 (2.68) Acct: 3.77 (4.08) proj_loss: -0.5481 (-0.5494) time: 0.9282 data: 0.0002 [11-23 03:09:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [1251/1669] eta: 0:06:31 tlr: 0.00024 tnm: 0.27 Lm: 6.643 (6.633) Lt: 5.889 (5.876) Accm: 2.99 (2.97) Acct: 4.63 (4.43) proj_loss: -0.5268 (-0.5275) time: 0.9282 data: 0.0002 [11-23 03:09:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [1251/1669] eta: 0:06:31 tlr: 0.00024 tnm: 0.27 Lm: 6.766 (6.731) Lt: 6.055 (6.018) Accm: 2.76 (2.79) Acct: 4.25 (4.28) proj_loss: -0.5499 (-0.5478) time: 0.9282 data: 0.0003 [11-23 03:09:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [1251/1669] eta: 0:06:31 tlr: 0.00024 tnm: 0.27 Lm: 6.709 (6.673) Lt: 6.013 (5.967) Accm: 2.53 (2.64) Acct: 3.89 (4.27) proj_loss: -0.5439 (-0.5498) time: 0.9282 data: 0.0003 [11-23 03:09:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [1251/1669] eta: 0:06:31 tlr: 0.00024 tnm: 0.27 Lm: 6.813 (6.809) Lt: 6.099 (6.115) Accm: 2.57 (2.69) Acct: 4.12 (4.22) proj_loss: -0.5240 (-0.5261) time: 0.9282 data: 0.0003 [11-23 03:09:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [1251/1669] eta: 0:06:31 tlr: 0.00024 tnm: 0.27 Lm: 6.828 (6.842) Lt: 6.102 (6.112) Accm: 2.62 (2.60) Acct: 4.39 (4.32) proj_loss: -0.5244 (-0.5295) time: 0.9282 data: 0.0003 [11-23 03:09:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [1251/1669] eta: 0:06:31 tlr: 0.00024 tnm: 0.27 Lm: 6.784 (6.780) Lt: 6.082 (6.039) Accm: 2.80 (2.78) Acct: 4.49 (4.60) proj_loss: -0.5350 (-0.5313) time: 0.9283 data: 0.0002 [11-23 03:09:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [1251/1669] eta: 0:06:31 tlr: 0.00024 tnm: 0.27 Lm: 6.677 (6.702) Lt: 5.950 (5.972) Accm: 2.94 (2.90) Acct: 4.63 (4.50) proj_loss: -0.5279 (-0.5289) time: 0.9282 data: 0.0003 [11-23 03:16:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.677 (6.697) Lt: 5.933 (5.965) Accm: 2.96 (2.96) Acct: 4.75 (4.68) proj_loss: -0.5187 (-0.5213) time: 0.9304 data: 0.0018 [11-23 03:16:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 24/350] Total time: 0:26:12 (0.942 s / it) [11-23 03:16:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.646 (6.639) Lt: 5.892 (5.901) Accm: 3.00 (2.98) Acct: 4.68 (4.49) proj_loss: -0.5262 (-0.5258) time: 0.9304 data: 0.0019 [11-23 03:16:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.843 (6.844) Lt: 6.108 (6.112) Accm: 2.67 (2.62) Acct: 4.27 (4.30) proj_loss: -0.5290 (-0.5294) time: 0.9304 data: 0.0016 [11-23 03:16:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.794 (6.743) Lt: 6.062 (6.045) Accm: 2.68 (2.70) Acct: 4.17 (4.10) proj_loss: -0.5375 (-0.5455) time: 0.9304 data: 0.0018 [11-23 03:16:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.688 (6.775) Lt: 5.948 (6.068) Accm: 2.72 (2.76) Acct: 4.55 (4.35) proj_loss: -0.5179 (-0.5226) time: 0.9304 data: 0.0019 [11-23 03:16:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.780 (6.779) Lt: 6.058 (6.046) Accm: 2.62 (2.82) Acct: 3.79 (4.34) proj_loss: -0.5340 (-0.5424) time: 0.9304 data: 0.0019 [11-23 03:16:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.707 (6.680) Lt: 6.024 (5.979) Accm: 2.72 (2.68) Acct: 4.10 (4.30) proj_loss: -0.5462 (-0.5491) time: 0.9304 data: 0.0017 [11-23 03:16:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 24/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.737 (6.749) Lt: 5.981 (5.989) Accm: 2.84 (2.88) Acct: 4.65 (4.79) proj_loss: -0.5244 (-0.5253) time: 0.9304 data: 0.0016 [11-23 03:16:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 24/350] Total time: 0:26:12 (0.942 s / it) [11-23 03:16:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 24/350] Total time: 0:26:12 (0.942 s / it) [11-23 03:16:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 24/350] Total time: 0:26:12 (0.942 s / it) [11-23 03:16:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 24/350] Total time: 0:26:12 (0.942 s / it) [11-23 03:16:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 24/350] Total time: 0:26:12 (0.942 s / it) [11-23 03:16:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 24/350] Total time: 0:26:12 (0.942 s / it) [11-23 03:16:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 24/350] Total time: 0:26:12 (0.942 s / it) [11-23 03:16:35] (/home/user/VAR/train.py , line 276)=> [ep24] (training ) Lm: 6.749 (6.749), Lt: 6.030 (6.030), Acc m&t: 2.74 4.32, Remain: 5 days, 21:07:30, Finish: 2024-11-28 08:24 [11-23 03:16:35] (/home/user/VAR/train.py , line 276)=> [ep24] (training ) Lm: 6.749 (6.749), Lt: 6.030 (6.030), Acc m&t: 2.74 4.32, Remain: 5 days, 21:09:46, Finish: 2024-11-28 08:26 [11-23 03:16:35] (/home/user/VAR/train.py , line 276)=> [ep24] (training ) Lm: 6.749 (6.749), Lt: 6.030 (6.030), Acc m&t: 2.74 4.32, Remain: 5 days, 21:08:04, Finish: 2024-11-28 08:24 [11-23 03:16:35] (/home/user/VAR/train.py , line 276)=> [ep24] (training ) Lm: 6.749 (6.749), Lt: 6.030 (6.030), Acc m&t: 2.74 4.32, Remain: 5 days, 21:11:34, Finish: 2024-11-28 08:28 [11-23 03:16:35] (/home/user/VAR/train.py , line 276)=> [ep24] (training ) Lm: 6.749 (6.749), Lt: 6.030 (6.030), Acc m&t: 2.74 4.32, Remain: 5 days, 21:11:05, Finish: 2024-11-28 08:27 [11-23 03:16:35] (/home/user/VAR/train.py , line 276)=> [ep24] (training ) Lm: 6.749 (6.749), Lt: 6.030 (6.030), Acc m&t: 2.74 4.32, Remain: 5 days, 21:11:04, Finish: 2024-11-28 08:27 [11-23 03:16:35] (/home/user/VAR/train.py , line 276)=> [ep24] (training ) Lm: 6.749 (6.749), Lt: 6.030 (6.030), Acc m&t: 2.74 4.32, Remain: 5 days, 21:09:35, Finish: 2024-11-28 08:26 [11-23 03:16:35] (/home/user/VAR/train.py , line 276)=> [ep24] (training ) Lm: 6.749 (6.749), Lt: 6.030 (6.030), Acc m&t: 2.74 4.32, Remain: 5 days, 21:08:10, Finish: 2024-11-28 08:24 [11-23 03:16:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 0/1669] eta: 0:25:24 tlr: 0.00024 tnm: 0.24 Lm: 6.436 (6.436) Lt: 5.688 (5.688) Accm: 3.85 (3.85) Acct: 6.06 (6.06) proj_loss: -0.5758 (-0.5758) time: 0.9134 data: 0.0003 [11-23 03:16:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 0/1669] eta: 0:25:23 tlr: 0.00024 tnm: 0.24 Lm: 6.571 (6.571) Lt: 5.776 (5.776) Accm: 3.03 (3.03) Acct: 5.03 (5.03) proj_loss: -0.5260 (-0.5260) time: 0.9129 data: 0.0003 [11-23 03:16:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 0/1669] eta: 0:25:24 tlr: 0.00024 tnm: 0.24 Lm: 6.650 (6.650) Lt: 5.942 (5.942) Accm: 3.28 (3.28) Acct: 5.27 (5.27) proj_loss: -0.5227 (-0.5227) time: 0.9134 data: 0.0004 [11-23 03:16:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 0/1669] eta: 0:25:25 tlr: 0.00024 tnm: 0.24 Lm: 6.850 (6.850) Lt: 6.130 (6.130) Accm: 2.32 (2.32) Acct: 3.34 (3.34) proj_loss: -0.5108 (-0.5108) time: 0.9139 data: 0.0004 [11-23 03:16:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 0/1669] eta: 0:25:25 tlr: 0.00024 tnm: 0.24 Lm: 6.662 (6.662) Lt: 5.878 (5.878) Accm: 2.67 (2.67) Acct: 4.41 (4.41) proj_loss: -0.5319 (-0.5319) time: 0.9140 data: 0.0003 [11-23 03:16:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 0/1669] eta: 0:25:25 tlr: 0.00024 tnm: 0.24 Lm: 6.826 (6.826) Lt: 6.192 (6.192) Accm: 2.59 (2.59) Acct: 3.79 (3.79) proj_loss: -0.5410 (-0.5410) time: 0.9139 data: 0.0004 [11-23 03:16:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 0/1669] eta: 0:25:24 tlr: 0.00024 tnm: 0.24 Lm: 6.771 (6.771) Lt: 6.048 (6.048) Accm: 2.62 (2.62) Acct: 4.17 (4.17) proj_loss: -0.5090 (-0.5090) time: 0.9137 data: 0.0004 [11-23 03:16:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 0/1669] eta: 0:25:25 tlr: 0.00024 tnm: 0.24 Lm: 6.837 (6.837) Lt: 6.103 (6.103) Accm: 2.56 (2.56) Acct: 4.20 (4.20) proj_loss: -0.5285 (-0.5285) time: 0.9141 data: 0.0004 [11-23 03:23:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 417/1669] eta: 0:19:22 tlr: 0.00024 tnm: 0.26 Lm: 6.752 (6.752) Lt: 5.990 (5.990) Accm: 2.88 (2.88) Acct: 4.72 (4.72) proj_loss: -0.5125 (-0.5125) time: 0.9277 data: 0.0003 [11-23 03:23:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 417/1669] eta: 0:19:22 tlr: 0.00024 tnm: 0.26 Lm: 6.719 (6.719) Lt: 5.994 (5.994) Accm: 2.60 (2.60) Acct: 4.20 (4.20) proj_loss: -0.5305 (-0.5305) time: 0.9277 data: 0.0003 [11-23 03:23:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 417/1669] eta: 0:19:22 tlr: 0.00024 tnm: 0.26 Lm: 6.872 (6.872) Lt: 6.172 (6.172) Accm: 2.33 (2.33) Acct: 3.43 (3.43) proj_loss: -0.5195 (-0.5195) time: 0.9277 data: 0.0003 [11-23 03:23:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 417/1669] eta: 0:19:22 tlr: 0.00024 tnm: 0.26 Lm: 6.666 (6.666) Lt: 5.935 (5.935) Accm: 3.15 (3.15) Acct: 4.99 (4.99) proj_loss: -0.5595 (-0.5595) time: 0.9277 data: 0.0003 [11-23 03:23:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 417/1669] eta: 0:19:22 tlr: 0.00024 tnm: 0.26 Lm: 6.662 (6.662) Lt: 5.912 (5.912) Accm: 2.78 (2.78) Acct: 4.44 (4.44) proj_loss: -0.5410 (-0.5410) time: 0.9277 data: 0.0003 [11-23 03:23:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 417/1669] eta: 0:19:22 tlr: 0.00024 tnm: 0.26 Lm: 6.744 (6.744) Lt: 6.005 (6.005) Accm: 2.90 (2.90) Acct: 4.79 (4.79) proj_loss: -0.5325 (-0.5325) time: 0.9277 data: 0.0003 [11-23 03:23:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 417/1669] eta: 0:19:22 tlr: 0.00024 tnm: 0.26 Lm: 6.859 (6.859) Lt: 6.152 (6.152) Accm: 2.37 (2.37) Acct: 3.68 (3.68) proj_loss: -0.5255 (-0.5255) time: 0.9277 data: 0.0003 [11-23 03:23:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 417/1669] eta: 0:19:22 tlr: 0.00024 tnm: 0.26 Lm: 6.857 (6.857) Lt: 6.177 (6.177) Accm: 2.57 (2.57) Acct: 3.91 (3.91) proj_loss: -0.5304 (-0.5304) time: 0.9277 data: 0.0003 [11-23 03:29:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 834/1669] eta: 0:12:55 tlr: 0.00024 tnm: 0.26 Lm: 6.838 (6.851) Lt: 6.162 (6.151) Accm: 2.59 (2.62) Acct: 4.03 (4.13) proj_loss: -0.5273 (-0.5294) time: 0.9270 data: 0.0003 [11-23 03:29:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 834/1669] eta: 0:12:55 tlr: 0.00024 tnm: 0.26 Lm: 6.680 (6.723) Lt: 5.942 (5.952) Accm: 2.74 (2.85) Acct: 4.30 (4.57) proj_loss: -0.5422 (-0.5406) time: 0.9270 data: 0.0003 [11-23 03:29:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 834/1669] eta: 0:12:55 tlr: 0.00024 tnm: 0.26 Lm: 6.837 (6.793) Lt: 6.103 (6.057) Accm: 2.62 (2.80) Acct: 4.37 (4.60) proj_loss: -0.5285 (-0.5190) time: 0.9270 data: 0.0003 [11-23 03:29:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 834/1669] eta: 0:12:55 tlr: 0.00024 tnm: 0.26 Lm: 6.895 (6.755) Lt: 6.182 (6.031) Accm: 2.45 (2.91) Acct: 3.99 (4.66) proj_loss: -0.5432 (-0.5473) time: 0.9270 data: 0.0003 [11-23 03:29:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 834/1669] eta: 0:12:55 tlr: 0.00024 tnm: 0.26 Lm: 6.850 (6.853) Lt: 6.130 (6.129) Accm: 2.35 (2.48) Acct: 3.51 (3.82) proj_loss: -0.5282 (-0.5362) time: 0.9270 data: 0.0003 [11-23 03:29:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 834/1669] eta: 0:12:55 tlr: 0.00024 tnm: 0.26 Lm: 6.662 (6.624) Lt: 5.878 (5.885) Accm: 2.90 (2.97) Acct: 4.48 (4.72) proj_loss: -0.5502 (-0.5475) time: 0.9270 data: 0.0003 [11-23 03:29:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 834/1669] eta: 0:12:55 tlr: 0.00024 tnm: 0.26 Lm: 6.571 (6.663) Lt: 5.776 (5.919) Accm: 3.03 (2.75) Acct: 4.92 (4.44) proj_loss: -0.5349 (-0.5333) time: 0.9270 data: 0.0002 [11-23 03:29:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [ 834/1669] eta: 0:12:55 tlr: 0.00024 tnm: 0.26 Lm: 6.771 (6.748) Lt: 6.048 (6.018) Accm: 2.62 (2.76) Acct: 4.17 (4.22) proj_loss: -0.5420 (-0.5385) time: 0.9270 data: 0.0003 [11-23 03:35:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [1251/1669] eta: 0:06:28 tlr: 0.00024 tnm: 0.23 Lm: 6.720 (6.728) Lt: 5.980 (5.991) Accm: 2.88 (2.86) Acct: 4.58 (4.42) proj_loss: -0.5533 (-0.5490) time: 0.9298 data: 0.0003 [11-23 03:35:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [1251/1669] eta: 0:06:28 tlr: 0.00024 tnm: 0.23 Lm: 6.642 (6.676) Lt: 5.892 (5.941) Accm: 2.80 (2.71) Acct: 4.49 (4.35) proj_loss: -0.5352 (-0.5338) time: 0.9298 data: 0.0003 [11-23 03:35:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [1251/1669] eta: 0:06:28 tlr: 0.00024 tnm: 0.23 Lm: 6.712 (6.699) Lt: 5.978 (5.967) Accm: 2.89 (3.02) Acct: 4.53 (4.76) proj_loss: -0.5461 (-0.5477) time: 0.9298 data: 0.0002 [11-23 03:35:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [1251/1669] eta: 0:06:28 tlr: 0.00024 tnm: 0.23 Lm: 6.833 (6.818) Lt: 6.087 (6.103) Accm: 2.56 (2.58) Acct: 4.06 (4.05) proj_loss: -0.5329 (-0.5366) time: 0.9298 data: 0.0003 [11-23 03:35:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [1251/1669] eta: 0:06:28 tlr: 0.00024 tnm: 0.23 Lm: 6.727 (6.735) Lt: 6.005 (5.997) Accm: 2.63 (2.76) Acct: 4.22 (4.30) proj_loss: -0.5433 (-0.5416) time: 0.9298 data: 0.0003 [11-23 03:35:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [1251/1669] eta: 0:06:28 tlr: 0.00024 tnm: 0.23 Lm: 6.840 (6.806) Lt: 6.102 (6.068) Accm: 2.59 (2.65) Acct: 4.29 (4.32) proj_loss: -0.5302 (-0.5320) time: 0.9298 data: 0.0003 [11-23 03:35:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [1251/1669] eta: 0:06:28 tlr: 0.00024 tnm: 0.23 Lm: 6.832 (6.773) Lt: 6.131 (6.049) Accm: 2.65 (2.77) Acct: 4.30 (4.44) proj_loss: -0.5236 (-0.5270) time: 0.9298 data: 0.0003 [11-23 03:35:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [1251/1669] eta: 0:06:28 tlr: 0.00024 tnm: 0.23 Lm: 6.623 (6.614) Lt: 5.854 (5.863) Accm: 2.94 (2.98) Acct: 4.58 (4.71) proj_loss: -0.5428 (-0.5444) time: 0.9298 data: 0.0003 [11-23 03:42:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.25 Lm: 6.585 (6.569) Lt: 5.830 (5.808) Accm: 2.99 (3.14) Acct: 4.68 (5.05) proj_loss: -0.5443 (-0.5444) time: 0.9292 data: 0.0016 [11-23 03:42:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 25/350] Total time: 0:25:50 (0.929 s / it) [11-23 03:42:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.25 Lm: 6.714 (6.689) Lt: 6.008 (5.958) Accm: 2.68 (2.70) Acct: 4.06 (4.21) proj_loss: -0.5356 (-0.5408) time: 0.9292 data: 0.0017 [11-23 03:42:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.25 Lm: 6.838 (6.794) Lt: 6.147 (6.069) Accm: 2.59 (2.66) Acct: 4.03 (4.31) proj_loss: -0.5273 (-0.5280) time: 0.9291 data: 0.0017 [11-23 03:42:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.25 Lm: 6.816 (6.781) Lt: 6.043 (6.062) Accm: 2.77 (2.67) Acct: 4.51 (4.15) proj_loss: -0.5376 (-0.5379) time: 0.9292 data: 0.0015 [11-23 03:42:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.25 Lm: 6.837 (6.791) Lt: 6.101 (6.059) Accm: 2.62 (2.70) Acct: 4.37 (4.35) proj_loss: -0.5285 (-0.5268) time: 0.9292 data: 0.0017 [11-23 03:42:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.25 Lm: 6.680 (6.713) Lt: 5.942 (5.967) Accm: 2.74 (2.76) Acct: 4.30 (4.39) proj_loss: -0.5422 (-0.5372) time: 0.9292 data: 0.0017 [11-23 03:42:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.25 Lm: 6.718 (6.703) Lt: 5.933 (5.960) Accm: 2.52 (2.92) Acct: 3.99 (4.59) proj_loss: -0.5470 (-0.5475) time: 0.9292 data: 0.0016 [11-23 03:42:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 25/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.25 Lm: 6.771 (6.774) Lt: 6.048 (6.051) Accm: 2.62 (2.76) Acct: 4.17 (4.29) proj_loss: -0.5420 (-0.5453) time: 0.9292 data: 0.0018 [11-23 03:42:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 25/350] Total time: 0:25:50 (0.929 s / it) [11-23 03:42:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 25/350] Total time: 0:25:50 (0.929 s / it) [11-23 03:42:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 25/350] Total time: 0:25:50 (0.929 s / it) [11-23 03:42:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 25/350] Total time: 0:25:50 (0.929 s / it) [11-23 03:42:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 25/350] Total time: 0:25:50 (0.929 s / it) [11-23 03:42:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 25/350] Total time: 0:25:50 (0.929 s / it) [11-23 03:42:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 25/350] Total time: 0:25:50 (0.929 s / it) [11-23 03:42:26] (/home/user/VAR/train.py , line 276)=> [ep25] (training ) Lm: 6.743 (6.743), Lt: 6.017 (6.017), Acc m&t: 2.74 4.33, Remain: 5 days, 20:35:34, Finish: 2024-11-28 08:18 [11-23 03:42:26] (/home/user/VAR/train.py , line 276)=> [ep25] (training ) Lm: 6.743 (6.743), Lt: 6.017 (6.017), Acc m&t: 2.74 4.33, Remain: 5 days, 20:39:23, Finish: 2024-11-28 08:21 [11-23 03:42:26] (/home/user/VAR/train.py , line 276)=> [ep25] (training ) Lm: 6.743 (6.743), Lt: 6.017 (6.017), Acc m&t: 2.74 4.33, Remain: 5 days, 20:39:17, Finish: 2024-11-28 08:21 [11-23 03:42:26] (/home/user/VAR/train.py , line 276)=> [ep25] (training ) Lm: 6.743 (6.743), Lt: 6.017 (6.017), Acc m&t: 2.74 4.33, Remain: 5 days, 20:35:29, Finish: 2024-11-28 08:17 [11-23 03:42:26] (/home/user/VAR/train.py , line 276)=> [ep25] (training ) Lm: 6.743 (6.743), Lt: 6.017 (6.017), Acc m&t: 2.74 4.33, Remain: 5 days, 20:36:17, Finish: 2024-11-28 08:18 [11-23 03:42:26] (/home/user/VAR/train.py , line 276)=> [ep25] (training ) Lm: 6.743 (6.743), Lt: 6.017 (6.017), Acc m&t: 2.74 4.33, Remain: 5 days, 20:39:12, Finish: 2024-11-28 08:21 [11-23 03:42:26] (/home/user/VAR/train.py , line 276)=> [ep25] (training ) Lm: 6.743 (6.743), Lt: 6.017 (6.017), Acc m&t: 2.74 4.33, Remain: 5 days, 20:37:18, Finish: 2024-11-28 08:19 [11-23 03:42:26] (/home/user/VAR/train.py , line 276)=> [ep25] (training ) Lm: 6.743 (6.743), Lt: 6.017 (6.017), Acc m&t: 2.74 4.33, Remain: 5 days, 20:38:43, Finish: 2024-11-28 08:21 [11-23 03:42:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 0/1669] eta: 0:48:43 tlr: 0.00024 tnm: 0.24 Lm: 6.842 (6.842) Lt: 6.096 (6.096) Accm: 2.43 (2.43) Acct: 4.24 (4.24) proj_loss: -0.5291 (-0.5291) time: 1.7519 data: 0.0004 [11-23 03:42:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 0/1669] eta: 0:44:38 tlr: 0.00024 tnm: 0.24 Lm: 6.645 (6.645) Lt: 5.941 (5.941) Accm: 3.06 (3.06) Acct: 5.17 (5.17) proj_loss: -0.5559 (-0.5559) time: 1.6050 data: 0.0004 [11-23 03:42:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 0/1669] eta: 0:25:04 tlr: 0.00024 tnm: 0.24 Lm: 6.524 (6.524) Lt: 5.795 (5.795) Accm: 3.25 (3.25) Acct: 4.96 (4.96) proj_loss: -0.5451 (-0.5451) time: 0.9016 data: 0.0004 [11-23 03:42:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 0/1669] eta: 0:48:45 tlr: 0.00024 tnm: 0.24 Lm: 6.872 (6.872) Lt: 6.157 (6.157) Accm: 2.37 (2.37) Acct: 3.96 (3.96) proj_loss: -0.5728 (-0.5728) time: 1.7529 data: 0.0004 [11-23 03:42:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 0/1669] eta: 0:25:03 tlr: 0.00024 tnm: 0.24 Lm: 6.695 (6.695) Lt: 5.886 (5.886) Accm: 2.67 (2.67) Acct: 4.34 (4.34) proj_loss: -0.5279 (-0.5279) time: 0.9010 data: 0.0005 [11-23 03:42:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 0/1669] eta: 0:44:40 tlr: 0.00024 tnm: 0.24 Lm: 6.734 (6.734) Lt: 6.070 (6.070) Accm: 2.64 (2.64) Acct: 3.86 (3.86) proj_loss: -0.5517 (-0.5517) time: 1.6062 data: 0.0004 [11-23 03:42:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 0/1669] eta: 0:48:45 tlr: 0.00024 tnm: 0.24 Lm: 6.758 (6.758) Lt: 6.047 (6.047) Accm: 2.67 (2.67) Acct: 4.17 (4.17) proj_loss: -0.5180 (-0.5180) time: 1.7526 data: 0.0004 [11-23 03:42:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 0/1669] eta: 0:44:40 tlr: 0.00024 tnm: 0.24 Lm: 6.595 (6.595) Lt: 5.834 (5.834) Accm: 3.61 (3.61) Acct: 6.06 (6.06) proj_loss: -0.5450 (-0.5450) time: 1.6063 data: 0.0004 [11-23 03:49:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 417/1669] eta: 0:20:04 tlr: 0.00024 tnm: 0.23 Lm: 6.703 (6.703) Lt: 5.973 (5.973) Accm: 3.10 (3.10) Acct: 5.13 (5.13) proj_loss: -0.5545 (-0.5545) time: 1.2958 data: 0.0003 [11-23 03:49:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 417/1669] eta: 0:20:02 tlr: 0.00024 tnm: 0.23 Lm: 6.621 (6.621) Lt: 5.899 (5.899) Accm: 3.05 (3.05) Acct: 4.73 (4.73) proj_loss: -0.5408 (-0.5408) time: 1.2958 data: 0.0003 [11-23 03:49:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 417/1669] eta: 0:20:04 tlr: 0.00024 tnm: 0.23 Lm: 6.823 (6.823) Lt: 6.153 (6.153) Accm: 2.61 (2.61) Acct: 3.77 (3.77) proj_loss: -0.5648 (-0.5648) time: 1.2958 data: 0.0003 [11-23 03:49:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 417/1669] eta: 0:20:04 tlr: 0.00024 tnm: 0.23 Lm: 6.678 (6.678) Lt: 5.949 (5.949) Accm: 2.88 (2.88) Acct: 4.48 (4.48) proj_loss: -0.5218 (-0.5218) time: 1.2958 data: 0.0003 [11-23 03:49:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 417/1669] eta: 0:20:04 tlr: 0.00024 tnm: 0.23 Lm: 6.704 (6.704) Lt: 6.005 (6.005) Accm: 2.83 (2.83) Acct: 4.53 (4.53) proj_loss: -0.5641 (-0.5641) time: 1.2959 data: 0.0003 [11-23 03:49:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 417/1669] eta: 0:20:04 tlr: 0.00024 tnm: 0.23 Lm: 6.917 (6.917) Lt: 6.161 (6.161) Accm: 2.38 (2.38) Acct: 4.01 (4.01) proj_loss: -0.5415 (-0.5415) time: 1.2958 data: 0.0002 [11-23 03:49:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 417/1669] eta: 0:20:04 tlr: 0.00024 tnm: 0.23 Lm: 6.876 (6.876) Lt: 6.095 (6.095) Accm: 2.44 (2.44) Acct: 4.20 (4.20) proj_loss: -0.5299 (-0.5299) time: 1.2959 data: 0.0003 [11-23 03:49:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 417/1669] eta: 0:20:02 tlr: 0.00024 tnm: 0.23 Lm: 6.727 (6.727) Lt: 5.953 (5.953) Accm: 2.68 (2.68) Acct: 4.34 (4.34) proj_loss: -0.5287 (-0.5287) time: 1.2959 data: 0.0003 [11-23 03:55:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 834/1669] eta: 0:13:14 tlr: 0.00024 tnm: 0.28 Lm: 6.758 (6.757) Lt: 6.021 (5.992) Accm: 2.67 (2.66) Acct: 4.34 (4.38) proj_loss: -0.5294 (-0.5295) time: 0.9310 data: 0.0003 [11-23 03:55:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 834/1669] eta: 0:13:15 tlr: 0.00024 tnm: 0.28 Lm: 6.790 (6.732) Lt: 6.020 (5.989) Accm: 2.90 (3.03) Acct: 4.72 (4.99) proj_loss: -0.5450 (-0.5359) time: 0.9310 data: 0.0003 [11-23 03:55:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 834/1669] eta: 0:13:15 tlr: 0.00024 tnm: 0.28 Lm: 6.842 (6.845) Lt: 6.096 (6.071) Accm: 2.43 (2.58) Acct: 4.24 (4.29) proj_loss: -0.5291 (-0.5365) time: 0.9310 data: 0.0002 [11-23 03:55:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 834/1669] eta: 0:13:15 tlr: 0.00024 tnm: 0.28 Lm: 6.764 (6.766) Lt: 6.070 (6.065) Accm: 2.61 (2.66) Acct: 3.89 (4.22) proj_loss: -0.5651 (-0.5645) time: 0.9310 data: 0.0002 [11-23 03:55:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 834/1669] eta: 0:13:15 tlr: 0.00024 tnm: 0.28 Lm: 6.598 (6.620) Lt: 5.850 (5.858) Accm: 3.10 (3.05) Acct: 4.79 (4.75) proj_loss: -0.5243 (-0.5226) time: 0.9310 data: 0.0003 [11-23 03:55:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 834/1669] eta: 0:13:15 tlr: 0.00024 tnm: 0.28 Lm: 6.872 (6.795) Lt: 6.033 (6.032) Accm: 2.51 (2.82) Acct: 4.44 (4.65) proj_loss: -0.5332 (-0.5310) time: 0.9309 data: 0.0003 [11-23 03:55:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 834/1669] eta: 0:13:14 tlr: 0.00024 tnm: 0.28 Lm: 6.718 (6.713) Lt: 6.003 (6.011) Accm: 2.86 (2.85) Acct: 4.51 (4.44) proj_loss: -0.5365 (-0.5319) time: 0.9310 data: 0.0002 [11-23 03:55:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [ 834/1669] eta: 0:13:15 tlr: 0.00024 tnm: 0.28 Lm: 6.906 (6.851) Lt: 6.136 (6.147) Accm: 2.58 (2.50) Acct: 3.79 (3.78) proj_loss: -0.5517 (-0.5597) time: 0.9310 data: 0.0003 [11-23 04:02:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [1251/1669] eta: 0:06:34 tlr: 0.00024 tnm: 0.25 Lm: 6.910 (6.871) Lt: 6.186 (6.178) Accm: 2.51 (2.48) Acct: 3.74 (3.75) proj_loss: -0.5584 (-0.5610) time: 0.9292 data: 0.0003 [11-23 04:02:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [1251/1669] eta: 0:06:34 tlr: 0.00024 tnm: 0.25 Lm: 6.801 (6.759) Lt: 6.047 (6.010) Accm: 2.76 (2.93) Acct: 4.46 (4.69) proj_loss: -0.5545 (-0.5435) time: 0.9292 data: 0.0002 [11-23 04:02:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [1251/1669] eta: 0:06:35 tlr: 0.00024 tnm: 0.25 Lm: 6.772 (6.798) Lt: 5.997 (6.027) Accm: 2.67 (2.67) Acct: 4.25 (4.29) proj_loss: -0.5327 (-0.5365) time: 0.9292 data: 0.0002 [11-23 04:02:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [1251/1669] eta: 0:06:34 tlr: 0.00024 tnm: 0.25 Lm: 6.696 (6.703) Lt: 5.973 (5.994) Accm: 2.78 (2.81) Acct: 4.67 (4.54) proj_loss: -0.5301 (-0.5299) time: 0.9292 data: 0.0003 [11-23 04:02:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [1251/1669] eta: 0:06:35 tlr: 0.00024 tnm: 0.25 Lm: 6.752 (6.734) Lt: 5.969 (5.983) Accm: 2.88 (2.93) Acct: 4.79 (4.77) proj_loss: -0.5115 (-0.5207) time: 0.9292 data: 0.0003 [11-23 04:02:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [1251/1669] eta: 0:06:34 tlr: 0.00024 tnm: 0.25 Lm: 6.732 (6.744) Lt: 5.994 (5.986) Accm: 2.68 (2.70) Acct: 4.34 (4.31) proj_loss: -0.5287 (-0.5279) time: 0.9292 data: 0.0003 [11-23 04:02:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [1251/1669] eta: 0:06:35 tlr: 0.00024 tnm: 0.25 Lm: 6.643 (6.637) Lt: 5.882 (5.872) Accm: 3.07 (3.04) Acct: 4.86 (4.80) proj_loss: -0.5211 (-0.5187) time: 0.9292 data: 0.0003 [11-23 04:02:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [1251/1669] eta: 0:06:34 tlr: 0.00024 tnm: 0.25 Lm: 6.704 (6.716) Lt: 6.005 (5.995) Accm: 2.83 (2.87) Acct: 4.53 (4.51) proj_loss: -0.5605 (-0.5536) time: 0.9292 data: 0.0002 [11-23 04:08:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.24 Lm: 6.726 (6.718) Lt: 5.997 (5.996) Accm: 2.61 (2.79) Acct: 4.10 (4.43) proj_loss: -0.5638 (-0.5556) time: 0.9321 data: 0.0017 [11-23 04:08:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 26/350] Total time: 0:26:10 (0.941 s / it) [11-23 04:08:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.24 Lm: 6.706 (6.695) Lt: 5.967 (5.938) Accm: 2.70 (2.86) Acct: 4.34 (4.57) proj_loss: -0.5294 (-0.5338) time: 0.9321 data: 0.0018 [11-23 04:08:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.24 Lm: 6.712 (6.729) Lt: 5.923 (5.971) Accm: 3.10 (2.96) Acct: 5.10 (4.83) proj_loss: -0.5332 (-0.5250) time: 0.9321 data: 0.0017 [11-23 04:08:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.24 Lm: 6.674 (6.697) Lt: 6.003 (6.003) Accm: 2.71 (2.78) Acct: 4.51 (4.42) proj_loss: -0.5365 (-0.5335) time: 0.9321 data: 0.0017 [11-23 04:08:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.24 Lm: 6.906 (6.857) Lt: 6.136 (6.146) Accm: 2.43 (2.45) Acct: 3.79 (3.78) proj_loss: -0.5517 (-0.5546) time: 0.9321 data: 0.0016 [11-23 04:08:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.24 Lm: 6.702 (6.769) Lt: 5.904 (6.003) Accm: 2.91 (2.75) Acct: 4.27 (4.46) proj_loss: -0.5364 (-0.5377) time: 0.9321 data: 0.0017 [11-23 04:08:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.24 Lm: 6.790 (6.701) Lt: 6.020 (5.958) Accm: 2.90 (3.06) Acct: 4.72 (4.87) proj_loss: -0.5450 (-0.5435) time: 0.9321 data: 0.0018 [11-23 04:08:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 26/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.24 Lm: 6.687 (6.692) Lt: 5.913 (5.949) Accm: 3.03 (2.90) Acct: 4.79 (4.50) proj_loss: -0.5243 (-0.5204) time: 0.9321 data: 0.0016 [11-23 04:08:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 26/350] Total time: 0:26:10 (0.941 s / it) [11-23 04:08:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 26/350] Total time: 0:26:11 (0.941 s / it) [11-23 04:08:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 26/350] Total time: 0:26:10 (0.941 s / it) [11-23 04:08:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 26/350] Total time: 0:26:10 (0.941 s / it) [11-23 04:08:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 26/350] Total time: 0:26:11 (0.941 s / it) [11-23 04:08:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 26/350] Total time: 0:26:10 (0.941 s / it) [11-23 04:08:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 26/350] Total time: 0:26:11 (0.941 s / it) [11-23 04:08:39] (/home/user/VAR/train.py , line 276)=> [ep26] (training ) Lm: 6.739 (6.739), Lt: 6.012 (6.012), Acc m&t: 2.75 4.34, Remain: 5 days, 20:38:34, Finish: 2024-11-28 08:47 [11-23 04:08:39] (/home/user/VAR/train.py , line 276)=> [ep26] (training ) Lm: 6.739 (6.739), Lt: 6.012 (6.012), Acc m&t: 2.75 4.34, Remain: 5 days, 20:36:01, Finish: 2024-11-28 08:44 [11-23 04:08:39] (/home/user/VAR/train.py , line 276)=> [ep26] (training ) Lm: 6.739 (6.739), Lt: 6.012 (6.012), Acc m&t: 2.75 4.34, Remain: 5 days, 20:39:48, Finish: 2024-11-28 08:48 [11-23 04:08:39] (/home/user/VAR/train.py , line 276)=> [ep26] (training ) Lm: 6.739 (6.739), Lt: 6.012 (6.012), Acc m&t: 2.75 4.34, Remain: 5 days, 20:42:09, Finish: 2024-11-28 08:50 [11-23 04:08:39] (/home/user/VAR/train.py , line 276)=> [ep26] (training ) Lm: 6.739 (6.739), Lt: 6.012 (6.012), Acc m&t: 2.75 4.34, Remain: 5 days, 20:42:22, Finish: 2024-11-28 08:51 [11-23 04:08:39] (/home/user/VAR/train.py , line 276)=> [ep26] (training ) Lm: 6.739 (6.739), Lt: 6.012 (6.012), Acc m&t: 2.75 4.34, Remain: 5 days, 20:41:04, Finish: 2024-11-28 08:49 [11-23 04:08:39] (/home/user/VAR/train.py , line 276)=> [ep26] (training ) Lm: 6.739 (6.739), Lt: 6.012 (6.012), Acc m&t: 2.75 4.34, Remain: 5 days, 20:41:17, Finish: 2024-11-28 08:49 [11-23 04:08:39] (/home/user/VAR/train.py , line 276)=> [ep26] (training ) Lm: 6.739 (6.739), Lt: 6.012 (6.012), Acc m&t: 2.75 4.34, Remain: 5 days, 20:41:02, Finish: 2024-11-28 08:49 [11-23 04:08:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 0/1669] eta: 0:25:26 tlr: 0.00024 tnm: 0.26 Lm: 6.750 (6.750) Lt: 5.989 (5.989) Accm: 2.71 (2.71) Acct: 4.30 (4.30) proj_loss: -0.5565 (-0.5565) time: 0.9145 data: 0.0003 [11-23 04:08:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 0/1669] eta: 0:25:26 tlr: 0.00024 tnm: 0.26 Lm: 6.576 (6.576) Lt: 5.872 (5.872) Accm: 2.99 (2.99) Acct: 4.30 (4.30) proj_loss: -0.5422 (-0.5422) time: 0.9147 data: 0.0004 [11-23 04:08:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 0/1669] eta: 0:25:27 tlr: 0.00024 tnm: 0.26 Lm: 6.597 (6.597) Lt: 5.857 (5.857) Accm: 3.19 (3.19) Acct: 5.06 (5.06) proj_loss: -0.5151 (-0.5151) time: 0.9152 data: 0.0004 [11-23 04:08:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 0/1669] eta: 0:25:25 tlr: 0.00024 tnm: 0.26 Lm: 6.442 (6.442) Lt: 5.685 (5.685) Accm: 3.64 (3.64) Acct: 5.23 (5.23) proj_loss: -0.5387 (-0.5387) time: 0.9140 data: 0.0004 [11-23 04:08:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 0/1669] eta: 0:25:28 tlr: 0.00024 tnm: 0.26 Lm: 6.809 (6.809) Lt: 6.100 (6.100) Accm: 2.70 (2.70) Acct: 4.17 (4.17) proj_loss: -0.5223 (-0.5223) time: 0.9157 data: 0.0004 [11-23 04:08:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 0/1669] eta: 0:25:27 tlr: 0.00024 tnm: 0.26 Lm: 6.749 (6.749) Lt: 6.017 (6.017) Accm: 2.53 (2.53) Acct: 4.13 (4.13) proj_loss: -0.5608 (-0.5608) time: 0.9152 data: 0.0003 [11-23 04:08:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 0/1669] eta: 0:25:25 tlr: 0.00024 tnm: 0.26 Lm: 6.850 (6.850) Lt: 6.183 (6.183) Accm: 2.45 (2.45) Acct: 3.79 (3.79) proj_loss: -0.5356 (-0.5356) time: 0.9143 data: 0.0005 [11-23 04:08:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 0/1669] eta: 0:25:26 tlr: 0.00024 tnm: 0.26 Lm: 6.605 (6.605) Lt: 5.879 (5.879) Accm: 3.12 (3.12) Acct: 4.65 (4.65) proj_loss: -0.5226 (-0.5226) time: 0.9148 data: 0.0004 [11-23 04:15:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.27 Lm: 6.734 (6.734) Lt: 6.019 (6.019) Accm: 2.73 (2.73) Acct: 4.05 (4.05) proj_loss: -0.5459 (-0.5459) time: 0.9296 data: 0.0003 [11-23 04:15:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.27 Lm: 6.684 (6.684) Lt: 5.928 (5.928) Accm: 2.88 (2.88) Acct: 4.56 (4.56) proj_loss: -0.5504 (-0.5504) time: 0.9296 data: 0.0003 [11-23 04:15:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.27 Lm: 6.602 (6.602) Lt: 5.850 (5.850) Accm: 3.10 (3.10) Acct: 4.92 (4.92) proj_loss: -0.5210 (-0.5210) time: 0.9296 data: 0.0003 [11-23 04:15:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.27 Lm: 6.566 (6.566) Lt: 5.849 (5.849) Accm: 3.07 (3.07) Acct: 4.60 (4.60) proj_loss: -0.5418 (-0.5418) time: 0.9296 data: 0.0002 [11-23 04:15:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.27 Lm: 6.766 (6.766) Lt: 6.005 (6.005) Accm: 2.70 (2.70) Acct: 4.20 (4.20) proj_loss: -0.5217 (-0.5217) time: 0.9296 data: 0.0003 [11-23 04:15:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.27 Lm: 6.543 (6.543) Lt: 5.792 (5.792) Accm: 3.34 (3.34) Acct: 5.15 (5.15) proj_loss: -0.5543 (-0.5543) time: 0.9296 data: 0.0003 [11-23 04:15:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.27 Lm: 6.659 (6.659) Lt: 5.942 (5.942) Accm: 3.07 (3.07) Acct: 4.79 (4.79) proj_loss: -0.5297 (-0.5297) time: 0.9296 data: 0.0003 [11-23 04:15:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.27 Lm: 6.720 (6.720) Lt: 5.995 (5.995) Accm: 2.62 (2.62) Acct: 4.29 (4.29) proj_loss: -0.5564 (-0.5564) time: 0.9296 data: 0.0003 [11-23 04:21:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 834/1669] eta: 0:12:55 tlr: 0.00024 tnm: 0.26 Lm: 6.691 (6.692) Lt: 5.993 (5.994) Accm: 2.70 (2.72) Acct: 4.34 (4.30) proj_loss: -0.5608 (-0.5602) time: 0.9293 data: 0.0003 [11-23 04:21:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 834/1669] eta: 0:12:55 tlr: 0.00024 tnm: 0.26 Lm: 6.645 (6.618) Lt: 5.900 (5.890) Accm: 3.04 (3.03) Acct: 5.06 (4.71) proj_loss: -0.5387 (-0.5415) time: 0.9293 data: 0.0003 [11-23 04:21:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 834/1669] eta: 0:12:55 tlr: 0.00024 tnm: 0.26 Lm: 6.607 (6.700) Lt: 5.857 (5.970) Accm: 3.02 (2.89) Acct: 4.79 (4.66) proj_loss: -0.5218 (-0.5213) time: 0.9293 data: 0.0002 [11-23 04:21:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 834/1669] eta: 0:12:55 tlr: 0.00024 tnm: 0.26 Lm: 6.748 (6.689) Lt: 5.990 (5.958) Accm: 2.72 (2.96) Acct: 4.41 (4.66) proj_loss: -0.5356 (-0.5341) time: 0.9293 data: 0.0002 [11-23 04:21:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 834/1669] eta: 0:12:55 tlr: 0.00024 tnm: 0.26 Lm: 6.723 (6.749) Lt: 6.005 (6.005) Accm: 2.70 (2.74) Acct: 4.24 (4.36) proj_loss: -0.5223 (-0.5337) time: 0.9293 data: 0.0003 [11-23 04:21:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 834/1669] eta: 0:12:55 tlr: 0.00024 tnm: 0.26 Lm: 6.576 (6.626) Lt: 5.872 (5.920) Accm: 2.99 (2.92) Acct: 4.30 (4.44) proj_loss: -0.5422 (-0.5444) time: 0.9293 data: 0.0003 [11-23 04:21:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 834/1669] eta: 0:12:55 tlr: 0.00024 tnm: 0.26 Lm: 6.618 (6.625) Lt: 5.868 (5.865) Accm: 3.04 (3.14) Acct: 4.82 (4.90) proj_loss: -0.5565 (-0.5535) time: 0.9293 data: 0.0003 [11-23 04:21:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [ 834/1669] eta: 0:12:55 tlr: 0.00024 tnm: 0.26 Lm: 6.751 (6.740) Lt: 6.051 (6.030) Accm: 2.49 (2.65) Acct: 3.68 (3.93) proj_loss: -0.5630 (-0.5516) time: 0.9293 data: 0.0003 [11-23 04:28:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.24 Lm: 6.754 (6.744) Lt: 6.025 (6.022) Accm: 2.49 (2.61) Acct: 3.84 (3.94) proj_loss: -0.5612 (-0.5536) time: 0.9294 data: 0.0003 [11-23 04:28:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.24 Lm: 6.661 (6.695) Lt: 5.967 (5.980) Accm: 2.80 (2.74) Acct: 4.22 (4.29) proj_loss: -0.5418 (-0.5402) time: 0.9294 data: 0.0003 [11-23 04:28:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.24 Lm: 6.617 (6.623) Lt: 5.867 (5.866) Accm: 3.21 (3.20) Acct: 4.92 (4.93) proj_loss: -0.5504 (-0.5509) time: 0.9294 data: 0.0003 [11-23 04:28:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.24 Lm: 6.799 (6.754) Lt: 6.087 (6.029) Accm: 2.59 (2.75) Acct: 4.10 (4.31) proj_loss: -0.5354 (-0.5344) time: 0.9294 data: 0.0003 [11-23 04:28:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.24 Lm: 6.613 (6.680) Lt: 5.890 (5.958) Accm: 2.99 (2.91) Acct: 4.86 (4.73) proj_loss: -0.5244 (-0.5287) time: 0.9294 data: 0.0002 [11-23 04:28:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.24 Lm: 6.707 (6.665) Lt: 5.992 (5.940) Accm: 2.75 (2.88) Acct: 4.44 (4.42) proj_loss: -0.5493 (-0.5461) time: 0.9294 data: 0.0003 [11-23 04:28:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.24 Lm: 6.687 (6.689) Lt: 5.983 (5.979) Accm: 2.71 (2.72) Acct: 4.34 (4.31) proj_loss: -0.5564 (-0.5574) time: 0.9294 data: 0.0003 [11-23 04:28:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.24 Lm: 6.718 (6.716) Lt: 5.957 (5.981) Accm: 2.77 (2.87) Acct: 4.46 (4.55) proj_loss: -0.5380 (-0.5387) time: 0.9294 data: 0.0003 [11-23 04:34:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.713 (6.703) Lt: 5.909 (5.958) Accm: 2.84 (2.88) Acct: 4.68 (4.60) proj_loss: -0.5441 (-0.5398) time: 0.9818 data: 0.0018 [11-23 04:34:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 27/350] Total time: 0:26:05 (0.938 s / it) [11-23 04:34:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.618 (6.696) Lt: 5.923 (5.967) Accm: 2.97 (2.86) Acct: 4.79 (4.61) proj_loss: -0.5269 (-0.5291) time: 0.9818 data: 0.0016 [11-23 04:34:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.741 (6.680) Lt: 5.968 (5.946) Accm: 2.67 (2.84) Acct: 4.44 (4.42) proj_loss: -0.5387 (-0.5416) time: 0.9818 data: 0.0019 [11-23 04:34:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.748 (6.728) Lt: 5.990 (6.010) Accm: 2.67 (2.74) Acct: 4.20 (4.29) proj_loss: -0.5356 (-0.5393) time: 0.9818 data: 0.0016 [11-23 04:34:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.576 (6.652) Lt: 5.872 (5.920) Accm: 2.99 (2.85) Acct: 4.30 (4.52) proj_loss: -0.5415 (-0.5336) time: 0.9818 data: 0.0016 [11-23 04:34:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.683 (6.671) Lt: 5.973 (5.952) Accm: 2.72 (2.79) Acct: 4.34 (4.44) proj_loss: -0.5521 (-0.5434) time: 0.9818 data: 0.0015 [11-23 04:34:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.617 (6.607) Lt: 5.867 (5.855) Accm: 3.26 (3.21) Acct: 5.03 (5.06) proj_loss: -0.5455 (-0.5498) time: 0.9818 data: 0.0018 [11-23 04:34:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 27/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.757 (6.775) Lt: 6.051 (6.064) Accm: 2.49 (2.60) Acct: 3.99 (4.00) proj_loss: -0.5594 (-0.5463) time: 0.9818 data: 0.0022 [11-23 04:34:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 27/350] Total time: 0:26:05 (0.938 s / it) [11-23 04:34:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 27/350] Total time: 0:26:05 (0.938 s / it) [11-23 04:34:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 27/350] Total time: 0:26:05 (0.938 s / it) [11-23 04:34:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 27/350] Total time: 0:26:05 (0.938 s / it) [11-23 04:34:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 27/350] Total time: 0:26:05 (0.938 s / it) [11-23 04:34:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 27/350] Total time: 0:26:05 (0.938 s / it) [11-23 04:34:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 27/350] Total time: 0:26:05 (0.938 s / it) [11-23 04:34:44] (/home/user/VAR/train.py , line 276)=> [ep27] (training ) Lm: 6.725 (6.725), Lt: 5.995 (5.995), Acc m&t: 2.79 4.42, Remain: 5 days, 20:12:32, Finish: 2024-11-28 08:47 [11-23 04:34:44] (/home/user/VAR/train.py , line 276)=> [ep27] (training ) Lm: 6.725 (6.725), Lt: 5.995 (5.995), Acc m&t: 2.79 4.42, Remain: 5 days, 20:00:59, Finish: 2024-11-28 08:35 [11-23 04:34:44] (/home/user/VAR/train.py , line 276)=> [ep27] (training ) Lm: 6.725 (6.725), Lt: 5.995 (5.995), Acc m&t: 2.79 4.42, Remain: 5 days, 20:04:41, Finish: 2024-11-28 08:39 [11-23 04:34:44] (/home/user/VAR/train.py , line 276)=> [ep27] (training ) Lm: 6.725 (6.725), Lt: 5.995 (5.995), Acc m&t: 2.79 4.42, Remain: 5 days, 20:03:54, Finish: 2024-11-28 08:38 [11-23 04:34:44] (/home/user/VAR/train.py , line 276)=> [ep27] (training ) Lm: 6.725 (6.725), Lt: 5.995 (5.995), Acc m&t: 2.79 4.42, Remain: 5 days, 19:59:41, Finish: 2024-11-28 08:34 [11-23 04:34:44] (/home/user/VAR/train.py , line 276)=> [ep27] (training ) Lm: 6.725 (6.725), Lt: 5.995 (5.995), Acc m&t: 2.79 4.42, Remain: 5 days, 20:00:03, Finish: 2024-11-28 08:34 [11-23 04:34:44] (/home/user/VAR/train.py , line 276)=> [ep27] (training ) Lm: 6.725 (6.725), Lt: 5.995 (5.995), Acc m&t: 2.79 4.42, Remain: 5 days, 20:01:47, Finish: 2024-11-28 08:36 [11-23 04:34:44] (/home/user/VAR/train.py , line 276)=> [ep27] (training ) Lm: 6.725 (6.725), Lt: 5.995 (5.995), Acc m&t: 2.79 4.42, Remain: 5 days, 20:04:54, Finish: 2024-11-28 08:39 [11-23 04:34:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 0/1669] eta: 0:25:07 tlr: 0.00024 tnm: 0.26 Lm: 6.753 (6.753) Lt: 5.912 (5.912) Accm: 2.80 (2.80) Acct: 4.55 (4.55) proj_loss: -0.5062 (-0.5062) time: 0.9030 data: 0.0004 [11-23 04:34:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 0/1669] eta: 0:25:07 tlr: 0.00024 tnm: 0.26 Lm: 6.551 (6.551) Lt: 5.801 (5.801) Accm: 3.32 (3.32) Acct: 5.03 (5.03) proj_loss: -0.5598 (-0.5598) time: 0.9032 data: 0.0004 [11-23 04:34:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 0/1669] eta: 0:25:07 tlr: 0.00024 tnm: 0.26 Lm: 6.774 (6.774) Lt: 6.075 (6.075) Accm: 2.93 (2.93) Acct: 4.79 (4.79) proj_loss: -0.5071 (-0.5071) time: 0.9034 data: 0.0004 [11-23 04:34:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 0/1669] eta: 0:25:02 tlr: 0.00024 tnm: 0.26 Lm: 6.771 (6.771) Lt: 6.003 (6.003) Accm: 2.52 (2.52) Acct: 3.89 (3.89) proj_loss: -0.4839 (-0.4839) time: 0.9002 data: 0.0004 [11-23 04:34:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 0/1669] eta: 0:25:07 tlr: 0.00024 tnm: 0.26 Lm: 6.813 (6.813) Lt: 6.032 (6.032) Accm: 2.86 (2.86) Acct: 4.48 (4.48) proj_loss: -0.5510 (-0.5510) time: 0.9035 data: 0.0004 [11-23 04:34:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 0/1669] eta: 0:25:08 tlr: 0.00024 tnm: 0.26 Lm: 6.991 (6.991) Lt: 6.282 (6.282) Accm: 2.10 (2.10) Acct: 3.55 (3.55) proj_loss: -0.5448 (-0.5448) time: 0.9040 data: 0.0003 [11-23 04:34:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 0/1669] eta: 0:25:07 tlr: 0.00024 tnm: 0.26 Lm: 6.800 (6.800) Lt: 6.018 (6.018) Accm: 2.56 (2.56) Acct: 4.58 (4.58) proj_loss: -0.5772 (-0.5772) time: 0.9031 data: 0.0004 [11-23 04:34:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 0/1669] eta: 0:25:09 tlr: 0.00024 tnm: 0.26 Lm: 6.796 (6.796) Lt: 6.072 (6.072) Accm: 2.48 (2.48) Acct: 4.24 (4.24) proj_loss: -0.5389 (-0.5389) time: 0.9043 data: 0.0004 [11-23 04:41:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 417/1669] eta: 0:20:02 tlr: 0.00024 tnm: 0.24 Lm: 6.800 (6.800) Lt: 6.099 (6.099) Accm: 2.62 (2.62) Acct: 4.32 (4.32) proj_loss: -0.5319 (-0.5319) time: 0.9286 data: 0.0003 [11-23 04:41:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 417/1669] eta: 0:20:02 tlr: 0.00024 tnm: 0.24 Lm: 6.708 (6.708) Lt: 5.945 (5.945) Accm: 2.70 (2.70) Acct: 4.37 (4.37) proj_loss: -0.5177 (-0.5177) time: 0.9286 data: 0.0003 [11-23 04:41:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 417/1669] eta: 0:20:02 tlr: 0.00024 tnm: 0.24 Lm: 6.795 (6.795) Lt: 6.018 (6.018) Accm: 2.62 (2.62) Acct: 4.63 (4.63) proj_loss: -0.5563 (-0.5563) time: 0.9286 data: 0.0003 [11-23 04:41:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 417/1669] eta: 0:20:02 tlr: 0.00024 tnm: 0.24 Lm: 6.903 (6.903) Lt: 6.181 (6.181) Accm: 2.30 (2.30) Acct: 3.75 (3.75) proj_loss: -0.5488 (-0.5488) time: 0.9286 data: 0.0003 [11-23 04:41:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 417/1669] eta: 0:20:02 tlr: 0.00024 tnm: 0.24 Lm: 6.662 (6.662) Lt: 5.918 (5.918) Accm: 3.02 (3.02) Acct: 4.48 (4.48) proj_loss: -0.5434 (-0.5434) time: 0.9286 data: 0.0003 [11-23 04:41:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 417/1669] eta: 0:20:02 tlr: 0.00024 tnm: 0.24 Lm: 6.769 (6.769) Lt: 6.054 (6.054) Accm: 2.80 (2.80) Acct: 4.48 (4.48) proj_loss: -0.5236 (-0.5236) time: 0.9286 data: 0.0003 [11-23 04:41:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 417/1669] eta: 0:20:02 tlr: 0.00024 tnm: 0.24 Lm: 6.834 (6.834) Lt: 6.068 (6.068) Accm: 2.40 (2.40) Acct: 3.91 (3.91) proj_loss: -0.4950 (-0.4950) time: 0.9286 data: 0.0003 [11-23 04:41:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 417/1669] eta: 0:20:02 tlr: 0.00024 tnm: 0.24 Lm: 6.704 (6.704) Lt: 5.934 (5.934) Accm: 3.26 (3.26) Acct: 5.18 (5.18) proj_loss: -0.5321 (-0.5321) time: 0.9286 data: 0.0003 [11-23 04:47:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 834/1669] eta: 0:13:08 tlr: 0.00024 tnm: 0.24 Lm: 6.765 (6.724) Lt: 6.032 (5.969) Accm: 2.86 (2.96) Acct: 4.48 (4.74) proj_loss: -0.5442 (-0.5361) time: 0.9279 data: 0.0003 [11-23 04:47:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 834/1669] eta: 0:13:08 tlr: 0.00024 tnm: 0.24 Lm: 6.791 (6.763) Lt: 6.018 (5.999) Accm: 2.68 (2.68) Acct: 4.58 (4.50) proj_loss: -0.5429 (-0.5519) time: 0.9279 data: 0.0003 [11-23 04:47:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 834/1669] eta: 0:13:08 tlr: 0.00024 tnm: 0.24 Lm: 6.558 (6.627) Lt: 5.801 (5.868) Accm: 3.13 (3.06) Acct: 4.86 (4.60) proj_loss: -0.5270 (-0.5330) time: 0.9279 data: 0.0003 [11-23 04:47:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 834/1669] eta: 0:13:08 tlr: 0.00024 tnm: 0.24 Lm: 6.954 (6.920) Lt: 6.282 (6.221) Accm: 2.20 (2.27) Acct: 3.55 (3.68) proj_loss: -0.5448 (-0.5433) time: 0.9279 data: 0.0003 [11-23 04:47:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 834/1669] eta: 0:13:08 tlr: 0.00024 tnm: 0.24 Lm: 6.796 (6.758) Lt: 6.072 (6.066) Accm: 2.77 (2.70) Acct: 4.41 (4.49) proj_loss: -0.5249 (-0.5280) time: 0.9279 data: 0.0004 [11-23 04:47:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 834/1669] eta: 0:13:08 tlr: 0.00024 tnm: 0.24 Lm: 6.664 (6.651) Lt: 5.912 (5.896) Accm: 2.80 (3.04) Acct: 4.55 (4.82) proj_loss: -0.5292 (-0.5350) time: 0.9279 data: 0.0002 [11-23 04:47:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 834/1669] eta: 0:13:08 tlr: 0.00024 tnm: 0.24 Lm: 6.771 (6.768) Lt: 6.003 (6.005) Accm: 2.52 (2.65) Acct: 3.93 (4.22) proj_loss: -0.5060 (-0.5121) time: 0.9279 data: 0.0003 [11-23 04:47:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [ 834/1669] eta: 0:13:08 tlr: 0.00024 tnm: 0.24 Lm: 6.764 (6.765) Lt: 6.044 (6.051) Accm: 2.77 (2.79) Acct: 4.27 (4.41) proj_loss: -0.5385 (-0.5285) time: 0.9279 data: 0.0003 [11-23 04:54:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.25 Lm: 6.760 (6.753) Lt: 6.038 (6.022) Accm: 2.72 (2.74) Acct: 4.49 (4.49) proj_loss: -0.5392 (-0.5344) time: 0.9305 data: 0.0003 [11-23 04:54:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.25 Lm: 6.667 (6.656) Lt: 5.911 (5.900) Accm: 2.99 (3.07) Acct: 4.80 (4.88) proj_loss: -0.5472 (-0.5425) time: 0.9305 data: 0.0002 [11-23 04:54:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.25 Lm: 6.789 (6.769) Lt: 6.035 (6.018) Accm: 2.60 (2.77) Acct: 4.17 (4.43) proj_loss: -0.5444 (-0.5382) time: 0.9305 data: 0.0003 [11-23 04:54:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.25 Lm: 6.665 (6.720) Lt: 5.918 (5.970) Accm: 2.93 (2.86) Acct: 4.39 (4.35) proj_loss: -0.5362 (-0.5361) time: 0.9305 data: 0.0003 [11-23 04:54:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.25 Lm: 6.884 (6.861) Lt: 6.181 (6.144) Accm: 2.35 (2.46) Acct: 3.75 (4.02) proj_loss: -0.5437 (-0.5431) time: 0.9305 data: 0.0003 [11-23 04:54:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.25 Lm: 6.808 (6.787) Lt: 6.068 (6.046) Accm: 2.53 (2.62) Acct: 3.91 (4.11) proj_loss: -0.4950 (-0.5046) time: 0.9305 data: 0.0003 [11-23 04:54:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.25 Lm: 6.768 (6.758) Lt: 6.018 (6.006) Accm: 2.73 (2.70) Acct: 4.56 (4.51) proj_loss: -0.5496 (-0.5530) time: 0.9305 data: 0.0002 [11-23 04:54:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.25 Lm: 6.746 (6.742) Lt: 6.035 (6.039) Accm: 2.80 (2.76) Acct: 4.49 (4.51) proj_loss: -0.5294 (-0.5295) time: 0.9305 data: 0.0003 [11-23 05:00:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.695 (6.674) Lt: 5.999 (5.961) Accm: 2.84 (2.81) Acct: 4.58 (4.58) proj_loss: -0.5340 (-0.5307) time: 0.9294 data: 0.0016 [11-23 05:00:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 28/350] Total time: 0:26:03 (0.937 s / it) [11-23 05:00:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.676 (6.711) Lt: 5.943 (5.964) Accm: 2.99 (2.88) Acct: 4.86 (4.50) proj_loss: -0.5405 (-0.5370) time: 0.9294 data: 0.0018 [11-23 05:00:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.791 (6.766) Lt: 6.019 (6.017) Accm: 2.68 (2.63) Acct: 4.55 (4.39) proj_loss: -0.5563 (-0.5538) time: 0.9294 data: 0.0016 [11-23 05:00:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.664 (6.654) Lt: 5.912 (5.910) Accm: 3.16 (3.09) Acct: 4.99 (4.90) proj_loss: -0.5292 (-0.5366) time: 0.9294 data: 0.0015 [11-23 05:00:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.845 (6.802) Lt: 6.134 (6.073) Accm: 2.52 (2.59) Acct: 3.89 (4.02) proj_loss: -0.5060 (-0.5196) time: 0.9294 data: 0.0018 [11-23 05:00:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.756 (6.744) Lt: 6.033 (6.020) Accm: 2.77 (2.78) Acct: 4.27 (4.41) proj_loss: -0.5385 (-0.5322) time: 0.9294 data: 0.0018 [11-23 05:00:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.813 (6.794) Lt: 6.038 (6.071) Accm: 2.61 (2.74) Acct: 3.99 (4.35) proj_loss: -0.5442 (-0.5373) time: 0.9294 data: 0.0016 [11-23 05:00:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 28/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.26 Lm: 6.814 (6.789) Lt: 6.081 (6.053) Accm: 2.51 (2.58) Acct: 3.96 (4.23) proj_loss: -0.5448 (-0.5436) time: 0.9294 data: 0.0017 [11-23 05:00:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 28/350] Total time: 0:26:03 (0.937 s / it) [11-23 05:00:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 28/350] Total time: 0:26:03 (0.937 s / it) [11-23 05:00:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 28/350] Total time: 0:26:03 (0.937 s / it) [11-23 05:00:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 28/350] Total time: 0:26:03 (0.937 s / it) [11-23 05:00:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 28/350] Total time: 0:26:03 (0.937 s / it) [11-23 05:00:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 28/350] Total time: 0:26:03 (0.937 s / it) [11-23 05:00:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 28/350] Total time: 0:26:03 (0.937 s / it) [11-23 05:00:48] (/home/user/VAR/train.py , line 276)=> [ep28] (training ) Lm: 6.715 (6.715), Lt: 5.982 (5.982), Acc m&t: 2.82 4.46, Remain: 5 days, 19:07:06, Finish: 2024-11-28 08:07 [11-23 05:00:48] (/home/user/VAR/train.py , line 276)=> [ep28] (training ) Lm: 6.715 (6.715), Lt: 5.982 (5.982), Acc m&t: 2.82 4.46, Remain: 5 days, 19:09:07, Finish: 2024-11-28 08:09 [11-23 05:00:48] (/home/user/VAR/train.py , line 276)=> [ep28] (training ) Lm: 6.715 (6.715), Lt: 5.982 (5.982), Acc m&t: 2.82 4.46, Remain: 5 days, 19:11:21, Finish: 2024-11-28 08:12 [11-23 05:00:48] (/home/user/VAR/train.py , line 276)=> [ep28] (training ) Lm: 6.715 (6.715), Lt: 5.982 (5.982), Acc m&t: 2.82 4.46, Remain: 5 days, 19:09:56, Finish: 2024-11-28 08:10 [11-23 05:00:48] (/home/user/VAR/train.py , line 276)=> [ep28] (training ) Lm: 6.715 (6.715), Lt: 5.982 (5.982), Acc m&t: 2.82 4.46, Remain: 5 days, 19:11:01, Finish: 2024-11-28 08:11 [11-23 05:00:48] (/home/user/VAR/train.py , line 276)=> [ep28] (training ) Lm: 6.715 (6.715), Lt: 5.982 (5.982), Acc m&t: 2.82 4.46, Remain: 5 days, 19:08:17, Finish: 2024-11-28 08:09 [11-23 05:00:48] (/home/user/VAR/train.py , line 276)=> [ep28] (training ) Lm: 6.715 (6.715), Lt: 5.982 (5.982), Acc m&t: 2.82 4.46, Remain: 5 days, 19:07:09, Finish: 2024-11-28 08:07 [11-23 05:00:48] (/home/user/VAR/train.py , line 276)=> [ep28] (training ) Lm: 6.715 (6.715), Lt: 5.982 (5.982), Acc m&t: 2.82 4.46, Remain: 5 days, 19:07:26, Finish: 2024-11-28 08:08 [11-23 05:00:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 0/1669] eta: 0:26:11 tlr: 0.00024 tnm: 0.23 Lm: 6.788 (6.788) Lt: 6.042 (6.042) Accm: 2.59 (2.59) Acct: 4.30 (4.30) proj_loss: -0.5506 (-0.5506) time: 0.9414 data: 0.0004 [11-23 05:00:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 0/1669] eta: 0:24:09 tlr: 0.00024 tnm: 0.23 Lm: 6.410 (6.410) Lt: 5.684 (5.684) Accm: 3.61 (3.61) Acct: 5.48 (5.48) proj_loss: -0.5576 (-0.5576) time: 0.8686 data: 0.0003 [11-23 05:00:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 0/1669] eta: 0:26:15 tlr: 0.00024 tnm: 0.23 Lm: 6.495 (6.495) Lt: 5.751 (5.751) Accm: 3.37 (3.37) Acct: 4.99 (4.99) proj_loss: -0.5401 (-0.5401) time: 0.9439 data: 0.0004 [11-23 05:00:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 0/1669] eta: 0:26:11 tlr: 0.00024 tnm: 0.23 Lm: 6.363 (6.363) Lt: 5.503 (5.503) Accm: 3.79 (3.79) Acct: 6.47 (6.47) proj_loss: -0.5238 (-0.5238) time: 0.9413 data: 0.0004 [11-23 05:00:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 0/1669] eta: 0:26:11 tlr: 0.00024 tnm: 0.23 Lm: 6.747 (6.747) Lt: 6.041 (6.041) Accm: 2.64 (2.64) Acct: 3.79 (3.79) proj_loss: -0.5517 (-0.5517) time: 0.9417 data: 0.0003 [11-23 05:00:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 0/1669] eta: 0:26:11 tlr: 0.00024 tnm: 0.23 Lm: 6.703 (6.703) Lt: 6.000 (6.000) Accm: 3.19 (3.19) Acct: 5.13 (5.13) proj_loss: -0.5160 (-0.5160) time: 0.9419 data: 0.0004 [11-23 05:00:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 0/1669] eta: 0:28:42 tlr: 0.00024 tnm: 0.23 Lm: 6.911 (6.911) Lt: 6.184 (6.184) Accm: 2.29 (2.29) Acct: 4.10 (4.10) proj_loss: -0.5578 (-0.5578) time: 1.0321 data: 0.0003 [11-23 05:00:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 0/1669] eta: 0:26:12 tlr: 0.00024 tnm: 0.23 Lm: 6.863 (6.863) Lt: 6.135 (6.135) Accm: 2.48 (2.48) Acct: 3.68 (3.68) proj_loss: -0.5176 (-0.5176) time: 0.9421 data: 0.0004 [11-23 05:07:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.25 Lm: 6.678 (6.678) Lt: 5.934 (5.934) Accm: 3.13 (3.13) Acct: 4.73 (4.73) proj_loss: -0.5275 (-0.5275) time: 0.9303 data: 0.0003 [11-23 05:07:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.25 Lm: 6.738 (6.738) Lt: 5.985 (5.985) Accm: 2.80 (2.80) Acct: 4.39 (4.39) proj_loss: -0.5204 (-0.5204) time: 0.9303 data: 0.0002 [11-23 05:07:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.25 Lm: 6.591 (6.591) Lt: 5.878 (5.878) Accm: 3.12 (3.12) Acct: 4.92 (4.92) proj_loss: -0.5821 (-0.5821) time: 0.9303 data: 0.0002 [11-23 05:07:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.25 Lm: 6.519 (6.519) Lt: 5.755 (5.755) Accm: 3.48 (3.48) Acct: 5.48 (5.48) proj_loss: -0.5388 (-0.5388) time: 0.9303 data: 0.0003 [11-23 05:07:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.25 Lm: 6.491 (6.491) Lt: 5.687 (5.687) Accm: 3.35 (3.35) Acct: 5.49 (5.49) proj_loss: -0.5398 (-0.5398) time: 0.9303 data: 0.0003 [11-23 05:07:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.25 Lm: 6.772 (6.772) Lt: 6.087 (6.087) Accm: 2.96 (2.96) Acct: 4.72 (4.72) proj_loss: -0.5267 (-0.5267) time: 0.9303 data: 0.0003 [11-23 05:07:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.25 Lm: 6.846 (6.846) Lt: 6.130 (6.130) Accm: 2.51 (2.51) Acct: 4.29 (4.29) proj_loss: -0.5482 (-0.5482) time: 0.9303 data: 0.0003 [11-23 05:07:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.25 Lm: 6.738 (6.738) Lt: 6.003 (6.003) Accm: 2.74 (2.74) Acct: 3.91 (3.91) proj_loss: -0.5317 (-0.5317) time: 0.9303 data: 0.0003 [11-23 05:14:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 834/1669] eta: 0:13:17 tlr: 0.00024 tnm: 0.24 Lm: 6.728 (6.688) Lt: 5.966 (5.953) Accm: 2.84 (2.80) Acct: 4.03 (4.09) proj_loss: -0.5481 (-0.5372) time: 0.9274 data: 0.0003 [11-23 05:14:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 834/1669] eta: 0:13:17 tlr: 0.00024 tnm: 0.24 Lm: 6.688 (6.713) Lt: 5.950 (5.973) Accm: 3.02 (2.91) Acct: 4.48 (4.58) proj_loss: -0.5506 (-0.5316) time: 0.9274 data: 0.0003 [11-23 05:14:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 834/1669] eta: 0:13:17 tlr: 0.00024 tnm: 0.24 Lm: 6.595 (6.526) Lt: 5.773 (5.716) Accm: 3.23 (3.31) Acct: 5.17 (5.38) proj_loss: -0.5275 (-0.5357) time: 0.9274 data: 0.0003 [11-23 05:14:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 834/1669] eta: 0:13:17 tlr: 0.00024 tnm: 0.24 Lm: 6.542 (6.542) Lt: 5.760 (5.780) Accm: 3.37 (3.24) Acct: 4.99 (5.11) proj_loss: -0.5375 (-0.5375) time: 0.9274 data: 0.0003 [11-23 05:14:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 834/1669] eta: 0:13:17 tlr: 0.00024 tnm: 0.24 Lm: 6.530 (6.571) Lt: 5.747 (5.834) Accm: 3.18 (3.14) Acct: 4.99 (4.95) proj_loss: -0.5576 (-0.5713) time: 0.9274 data: 0.0002 [11-23 05:14:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 834/1669] eta: 0:13:17 tlr: 0.00024 tnm: 0.24 Lm: 6.720 (6.754) Lt: 6.006 (6.060) Accm: 2.77 (2.90) Acct: 4.68 (4.71) proj_loss: -0.5374 (-0.5325) time: 0.9275 data: 0.0003 [11-23 05:14:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 834/1669] eta: 0:13:18 tlr: 0.00024 tnm: 0.24 Lm: 6.781 (6.781) Lt: 6.075 (6.055) Accm: 2.68 (2.56) Acct: 4.44 (4.34) proj_loss: -0.5386 (-0.5431) time: 0.9274 data: 0.0003 [11-23 05:14:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [ 834/1669] eta: 0:13:17 tlr: 0.00024 tnm: 0.24 Lm: 6.815 (6.723) Lt: 6.077 (5.982) Accm: 2.58 (2.95) Acct: 4.10 (4.52) proj_loss: -0.5260 (-0.5270) time: 0.9275 data: 0.0003 [11-23 05:20:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [1251/1669] eta: 0:06:35 tlr: 0.00024 tnm: 0.24 Lm: 6.721 (6.699) Lt: 5.970 (5.952) Accm: 2.94 (3.03) Acct: 4.67 (4.70) proj_loss: -0.5316 (-0.5344) time: 0.9310 data: 0.0003 [11-23 05:20:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [1251/1669] eta: 0:06:35 tlr: 0.00024 tnm: 0.24 Lm: 6.607 (6.600) Lt: 5.822 (5.836) Accm: 3.07 (3.06) Acct: 4.84 (4.94) proj_loss: -0.5303 (-0.5351) time: 0.9310 data: 0.0003 [11-23 05:20:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [1251/1669] eta: 0:06:35 tlr: 0.00024 tnm: 0.24 Lm: 6.565 (6.601) Lt: 5.795 (5.853) Accm: 3.07 (3.03) Acct: 4.68 (4.74) proj_loss: -0.5388 (-0.5475) time: 0.9310 data: 0.0002 [11-23 05:20:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [1251/1669] eta: 0:06:35 tlr: 0.00024 tnm: 0.24 Lm: 6.602 (6.597) Lt: 5.859 (5.868) Accm: 2.97 (3.04) Acct: 4.68 (4.69) proj_loss: -0.5548 (-0.5665) time: 0.9310 data: 0.0002 [11-23 05:20:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [1251/1669] eta: 0:06:35 tlr: 0.00024 tnm: 0.24 Lm: 6.725 (6.725) Lt: 5.996 (5.993) Accm: 2.97 (2.91) Acct: 4.67 (4.65) proj_loss: -0.5495 (-0.5358) time: 0.9310 data: 0.0003 [11-23 05:20:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [1251/1669] eta: 0:06:35 tlr: 0.00024 tnm: 0.24 Lm: 6.658 (6.637) Lt: 5.909 (5.901) Accm: 2.88 (2.99) Acct: 4.24 (4.59) proj_loss: -0.5499 (-0.5526) time: 0.9310 data: 0.0003 [11-23 05:20:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [1251/1669] eta: 0:06:35 tlr: 0.00024 tnm: 0.24 Lm: 6.745 (6.758) Lt: 6.004 (6.046) Accm: 2.86 (2.91) Acct: 4.79 (4.75) proj_loss: -0.5273 (-0.5286) time: 0.9310 data: 0.0003 [11-23 05:20:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [1251/1669] eta: 0:06:35 tlr: 0.00024 tnm: 0.24 Lm: 6.716 (6.725) Lt: 5.991 (5.990) Accm: 2.70 (2.82) Acct: 4.46 (4.69) proj_loss: -0.5358 (-0.5397) time: 0.9310 data: 0.0003 [11-23 05:27:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.23 Lm: 6.651 (6.699) Lt: 5.906 (5.959) Accm: 2.72 (2.85) Acct: 4.48 (4.77) proj_loss: -0.5386 (-0.5405) time: 0.9327 data: 0.0018 [11-23 05:27:01] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 29/350] Total time: 0:26:12 (0.942 s / it) [11-23 05:27:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.23 Lm: 6.588 (6.607) Lt: 5.830 (5.858) Accm: 3.07 (3.04) Acct: 4.96 (4.79) proj_loss: -0.5401 (-0.5492) time: 0.9328 data: 0.0016 [11-23 05:27:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.23 Lm: 6.671 (6.612) Lt: 5.863 (5.867) Accm: 3.13 (3.06) Acct: 4.89 (4.73) proj_loss: -0.5520 (-0.5618) time: 0.9327 data: 0.0016 [11-23 05:27:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.23 Lm: 6.803 (6.720) Lt: 6.077 (6.000) Accm: 2.68 (2.96) Acct: 4.24 (4.61) proj_loss: -0.5373 (-0.5448) time: 0.9327 data: 0.0016 [11-23 05:27:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.23 Lm: 6.728 (6.673) Lt: 5.966 (5.955) Accm: 2.84 (2.90) Acct: 4.24 (4.52) proj_loss: -0.5517 (-0.5557) time: 0.9327 data: 0.0016 [11-23 05:27:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.23 Lm: 6.612 (6.602) Lt: 5.804 (5.829) Accm: 3.18 (3.09) Acct: 5.17 (5.07) proj_loss: -0.5331 (-0.5388) time: 0.9328 data: 0.0020 [11-23 05:27:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.23 Lm: 6.688 (6.718) Lt: 5.987 (5.992) Accm: 2.93 (2.89) Acct: 4.51 (4.62) proj_loss: -0.5502 (-0.5387) time: 0.9328 data: 0.0017 [11-23 05:27:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 29/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.23 Lm: 6.755 (6.758) Lt: 6.003 (6.026) Accm: 2.77 (2.86) Acct: 4.68 (4.68) proj_loss: -0.5263 (-0.5282) time: 0.9328 data: 0.0018 [11-23 05:27:01] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 29/350] Total time: 0:26:12 (0.942 s / it) [11-23 05:27:01] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 29/350] Total time: 0:26:12 (0.942 s / it) [11-23 05:27:01] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 29/350] Total time: 0:26:12 (0.942 s / it) [11-23 05:27:01] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 29/350] Total time: 0:26:12 (0.942 s / it) [11-23 05:27:01] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 29/350] Total time: 0:26:12 (0.942 s / it) [11-23 05:27:01] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 29/350] Total time: 0:26:12 (0.942 s / it) [11-23 05:27:01] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 29/350] Total time: 0:26:12 (0.942 s / it) [11-23 05:29:10] (home/user/VAR/trainer.py, line 114)=> FID: 4.8816310334439095 [11-23 05:29:11] (/home/user/VAR/train.py , line 259)=> [*] [ep29] (val 50000) Lm: 6.7107, Lt: 5.9801, Acc m&t: 2.85 4.50, Val cost: 129.43s [11-23 05:29:11] (/home/user/VAR/train.py , line 264)=> [saving ckpt] ... [saving ckpt](*) finished! @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth [11-23 05:30:32] (/home/user/VAR/train.py , line 276)=> [ep29] (training ) Lm: 6.711 (6.711), Lt: 5.980 (5.980), Acc m&t: 2.85 4.50, Remain: 5 days, 19:22:12, Finish: 2024-11-28 08:49 [11-23 05:30:32] (/home/user/VAR/train.py , line 276)=> [ep29] (training ) Lm: 6.711 (6.711), Lt: 5.980 (5.980), Acc m&t: 2.85 4.50, Remain: 5 days, 19:17:45, Finish: 2024-11-28 08:44 [11-23 05:30:32] (/home/user/VAR/train.py , line 276)=> [ep29] (training ) Lm: 6.711 (6.711), Lt: 5.980 (5.980), Acc m&t: 2.85 4.50, Remain: 5 days, 19:20:12, Finish: 2024-11-28 08:47 [11-23 05:30:32] (/home/user/VAR/train.py , line 276)=> [ep29] (training ) Lm: 6.711 (6.711), Lt: 5.980 (5.980), Acc m&t: 2.85 4.50, Remain: 5 days, 19:18:04, Finish: 2024-11-28 08:45 [11-23 05:30:32] (/home/user/VAR/train.py , line 276)=> [ep29] (training ) Lm: 6.711 (6.711), Lt: 5.980 (5.980), Acc m&t: 2.85 4.50, Remain: 5 days, 19:17:32, Finish: 2024-11-28 08:44 [11-23 05:30:32] (/home/user/VAR/train.py , line 276)=> [ep29] (training ) Lm: 6.711 (6.711), Lt: 5.980 (5.980), Acc m&t: 2.85 4.50, Remain: 5 days, 19:21:36, Finish: 2024-11-28 08:48 [11-23 05:30:32] (/home/user/VAR/train.py , line 276)=> [ep29] (training ) Lm: 6.711 (6.711), Lt: 5.980 (5.980), Acc m&t: 2.85 4.50, Remain: 5 days, 19:18:52, Finish: 2024-11-28 08:45 [11-23 05:30:32] (/home/user/VAR/train.py , line 276)=> [ep29] (training ) Lm: 6.711 (6.711), Lt: 5.980 (5.980), Acc m&t: 2.85 4.50, Remain: 5 days, 19:20:33, Finish: 2024-11-28 08:47 [11-23 05:30:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 0/1669] eta: 0:25:46 tlr: 0.00024 tnm: 0.22 Lm: 6.561 (6.561) Lt: 5.839 (5.839) Accm: 3.54 (3.54) Acct: 5.48 (5.48) proj_loss: -0.5588 (-0.5588) time: 0.9269 data: 0.0004 [11-23 05:30:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 0/1669] eta: 0:25:38 tlr: 0.00024 tnm: 0.22 Lm: 6.707 (6.707) Lt: 5.932 (5.932) Accm: 2.70 (2.70) Acct: 4.48 (4.48) proj_loss: -0.5447 (-0.5447) time: 0.9218 data: 0.0004 [11-23 05:30:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 0/1669] eta: 0:25:48 tlr: 0.00024 tnm: 0.22 Lm: 6.531 (6.531) Lt: 5.755 (5.755) Accm: 3.10 (3.10) Acct: 4.86 (4.86) proj_loss: -0.5533 (-0.5533) time: 0.9275 data: 0.0004 [11-23 05:30:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 0/1669] eta: 0:25:48 tlr: 0.00024 tnm: 0.22 Lm: 6.766 (6.766) Lt: 6.046 (6.046) Accm: 2.40 (2.40) Acct: 4.13 (4.13) proj_loss: -0.5332 (-0.5332) time: 0.9276 data: 0.0004 [11-23 05:30:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 0/1669] eta: 0:25:48 tlr: 0.00024 tnm: 0.22 Lm: 6.572 (6.572) Lt: 5.830 (5.830) Accm: 3.55 (3.55) Acct: 5.99 (5.99) proj_loss: -0.5822 (-0.5822) time: 0.9279 data: 0.0004 [11-23 05:30:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 0/1669] eta: 0:25:48 tlr: 0.00024 tnm: 0.22 Lm: 6.609 (6.609) Lt: 5.886 (5.886) Accm: 3.03 (3.03) Acct: 4.72 (4.72) proj_loss: -0.5402 (-0.5402) time: 0.9276 data: 0.0004 [11-23 05:30:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 0/1669] eta: 0:25:48 tlr: 0.00024 tnm: 0.22 Lm: 6.752 (6.752) Lt: 6.068 (6.068) Accm: 2.48 (2.48) Acct: 4.03 (4.03) proj_loss: -0.5151 (-0.5151) time: 0.9278 data: 0.0004 [11-23 05:30:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 0/1669] eta: 0:25:48 tlr: 0.00024 tnm: 0.22 Lm: 6.649 (6.649) Lt: 5.885 (5.885) Accm: 3.10 (3.10) Acct: 4.58 (4.58) proj_loss: -0.5240 (-0.5240) time: 0.9280 data: 0.0005 [11-23 05:37:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.24 Lm: 6.625 (6.625) Lt: 5.851 (5.851) Accm: 3.18 (3.18) Acct: 4.89 (4.89) proj_loss: -0.5307 (-0.5307) time: 0.9291 data: 0.0003 [11-23 05:37:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.24 Lm: 6.685 (6.685) Lt: 5.938 (5.938) Accm: 2.82 (2.82) Acct: 4.65 (4.65) proj_loss: -0.5580 (-0.5580) time: 0.9290 data: 0.0003 [11-23 05:37:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.24 Lm: 6.694 (6.694) Lt: 5.951 (5.951) Accm: 2.83 (2.83) Acct: 4.73 (4.73) proj_loss: -0.5221 (-0.5221) time: 0.9290 data: 0.0003 [11-23 05:37:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.24 Lm: 6.652 (6.652) Lt: 5.914 (5.914) Accm: 3.00 (3.00) Acct: 4.94 (4.94) proj_loss: -0.5636 (-0.5636) time: 0.9291 data: 0.0003 [11-23 05:37:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.24 Lm: 6.682 (6.682) Lt: 5.954 (5.954) Accm: 3.05 (3.05) Acct: 4.82 (4.82) proj_loss: -0.5467 (-0.5467) time: 0.9290 data: 0.0003 [11-23 05:37:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.24 Lm: 6.555 (6.555) Lt: 5.836 (5.836) Accm: 3.04 (3.04) Acct: 4.72 (4.72) proj_loss: -0.5318 (-0.5318) time: 0.9290 data: 0.0003 [11-23 05:37:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.24 Lm: 6.503 (6.503) Lt: 5.724 (5.724) Accm: 3.22 (3.22) Acct: 4.89 (4.89) proj_loss: -0.5511 (-0.5511) time: 0.9291 data: 0.0003 [11-23 05:37:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 417/1669] eta: 0:19:23 tlr: 0.00024 tnm: 0.24 Lm: 6.818 (6.818) Lt: 6.139 (6.139) Accm: 2.27 (2.27) Acct: 3.75 (3.75) proj_loss: -0.5362 (-0.5362) time: 0.9291 data: 0.0003 [11-23 05:43:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 834/1669] eta: 0:12:56 tlr: 0.00024 tnm: 0.25 Lm: 6.663 (6.620) Lt: 5.932 (5.871) Accm: 2.94 (3.06) Acct: 4.82 (4.87) proj_loss: -0.5511 (-0.5557) time: 0.9288 data: 0.0002 [11-23 05:43:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 834/1669] eta: 0:12:56 tlr: 0.00024 tnm: 0.25 Lm: 6.766 (6.758) Lt: 6.046 (6.018) Accm: 2.40 (2.64) Acct: 4.13 (4.37) proj_loss: -0.5332 (-0.5316) time: 0.9288 data: 0.0003 [11-23 05:43:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 834/1669] eta: 0:12:56 tlr: 0.00024 tnm: 0.25 Lm: 6.713 (6.692) Lt: 6.068 (5.994) Accm: 2.84 (2.98) Acct: 4.55 (4.73) proj_loss: -0.5588 (-0.5518) time: 0.9288 data: 0.0003 [11-23 05:43:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 834/1669] eta: 0:12:56 tlr: 0.00024 tnm: 0.25 Lm: 6.670 (6.658) Lt: 5.905 (5.911) Accm: 2.67 (2.89) Acct: 4.24 (4.71) proj_loss: -0.5450 (-0.5533) time: 0.9288 data: 0.0003 [11-23 05:43:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 834/1669] eta: 0:12:56 tlr: 0.00024 tnm: 0.25 Lm: 6.752 (6.724) Lt: 6.068 (6.012) Accm: 2.48 (2.54) Acct: 4.03 (4.13) proj_loss: -0.5268 (-0.5330) time: 0.9288 data: 0.0003 [11-23 05:43:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 834/1669] eta: 0:12:56 tlr: 0.00024 tnm: 0.25 Lm: 6.601 (6.613) Lt: 5.885 (5.867) Accm: 3.25 (3.22) Acct: 5.20 (5.07) proj_loss: -0.5373 (-0.5435) time: 0.9288 data: 0.0003 [11-23 05:43:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 834/1669] eta: 0:12:56 tlr: 0.00024 tnm: 0.25 Lm: 6.476 (6.425) Lt: 5.694 (5.638) Accm: 3.34 (3.56) Acct: 4.92 (5.45) proj_loss: -0.5533 (-0.5587) time: 0.9288 data: 0.0003 [11-23 05:43:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [ 834/1669] eta: 0:12:56 tlr: 0.00024 tnm: 0.25 Lm: 6.609 (6.593) Lt: 5.886 (5.873) Accm: 3.06 (3.17) Acct: 4.72 (5.03) proj_loss: -0.5386 (-0.5341) time: 0.9288 data: 0.0003 [11-23 05:50:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.23 Lm: 6.640 (6.643) Lt: 5.917 (5.918) Accm: 3.04 (2.98) Acct: 4.72 (4.70) proj_loss: -0.5353 (-0.5336) time: 1.1374 data: 0.0003 [11-23 05:50:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.23 Lm: 6.503 (6.481) Lt: 5.724 (5.700) Accm: 3.28 (3.48) Acct: 5.10 (5.41) proj_loss: -0.5637 (-0.5632) time: 1.1374 data: 0.0003 [11-23 05:50:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.23 Lm: 6.579 (6.589) Lt: 5.859 (5.850) Accm: 3.25 (3.19) Acct: 5.01 (4.95) proj_loss: -0.5487 (-0.5533) time: 1.1374 data: 0.0003 [11-23 05:50:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.23 Lm: 6.707 (6.730) Lt: 5.951 (5.973) Accm: 2.78 (2.76) Acct: 4.60 (4.55) proj_loss: -0.5286 (-0.5297) time: 1.1374 data: 0.0003 [11-23 05:50:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.23 Lm: 6.625 (6.642) Lt: 5.891 (5.890) Accm: 3.18 (3.00) Acct: 4.89 (4.80) proj_loss: -0.5430 (-0.5447) time: 1.1373 data: 0.0003 [11-23 05:50:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.23 Lm: 6.701 (6.686) Lt: 5.951 (5.947) Accm: 2.75 (2.88) Acct: 4.60 (4.77) proj_loss: -0.5416 (-0.5495) time: 1.1374 data: 0.0003 [11-23 05:50:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.23 Lm: 6.637 (6.651) Lt: 5.954 (5.913) Accm: 2.97 (3.01) Acct: 4.86 (4.84) proj_loss: -0.5604 (-0.5561) time: 1.1374 data: 0.0003 [11-23 05:50:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [1251/1669] eta: 0:06:32 tlr: 0.00024 tnm: 0.23 Lm: 6.690 (6.700) Lt: 5.975 (5.979) Accm: 2.74 (2.66) Acct: 4.46 (4.43) proj_loss: -0.5337 (-0.5349) time: 1.1374 data: 0.0003 [11-23 05:56:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.25 Lm: 6.649 (6.690) Lt: 5.882 (5.950) Accm: 3.00 (2.74) Acct: 4.79 (4.50) proj_loss: -0.5405 (-0.5365) time: 0.9327 data: 0.0020 [11-23 05:56:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 30/350] Total time: 0:26:07 (0.939 s / it) [11-23 05:56:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.25 Lm: 6.561 (6.618) Lt: 5.839 (5.874) Accm: 3.10 (3.08) Acct: 5.17 (4.96) proj_loss: -0.5588 (-0.5498) time: 0.9327 data: 0.0016 [11-23 05:56:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.25 Lm: 6.724 (6.694) Lt: 5.998 (5.961) Accm: 2.72 (2.85) Acct: 4.34 (4.68) proj_loss: -0.5381 (-0.5461) time: 0.9327 data: 0.0016 [11-23 05:56:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.25 Lm: 6.663 (6.613) Lt: 5.932 (5.883) Accm: 2.94 (3.04) Acct: 4.82 (4.74) proj_loss: -0.5511 (-0.5540) time: 0.9327 data: 0.0018 [11-23 05:56:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.25 Lm: 6.669 (6.718) Lt: 5.970 (5.973) Accm: 2.53 (2.72) Acct: 4.13 (4.39) proj_loss: -0.5332 (-0.5356) time: 0.9327 data: 0.0016 [11-23 05:56:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.25 Lm: 6.649 (6.712) Lt: 5.897 (5.968) Accm: 3.10 (2.82) Acct: 4.58 (4.55) proj_loss: -0.5486 (-0.5466) time: 0.9327 data: 0.0017 [11-23 05:56:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.25 Lm: 6.531 (6.504) Lt: 5.755 (5.722) Accm: 3.22 (3.43) Acct: 5.27 (5.44) proj_loss: -0.5533 (-0.5597) time: 0.9327 data: 0.0015 [11-23 05:56:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 30/350] [1668/1669] eta: 0:00:00 tlr: 0.00024 tnm: 0.25 Lm: 6.671 (6.665) Lt: 5.948 (5.933) Accm: 3.03 (2.93) Acct: 4.72 (4.63) proj_loss: -0.5386 (-0.5366) time: 0.9328 data: 0.0021 [11-23 05:56:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 30/350] Total time: 0:26:07 (0.939 s / it) [11-23 05:56:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 30/350] Total time: 0:26:07 (0.939 s / it) [11-23 05:56:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 30/350] Total time: 0:26:07 (0.939 s / it) [11-23 05:56:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 30/350] Total time: 0:26:07 (0.939 s / it) [11-23 05:56:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 30/350] Total time: 0:26:07 (0.939 s / it) [11-23 05:56:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 30/350] Total time: 0:26:07 (0.939 s / it) [11-23 05:56:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 30/350] Total time: 0:26:07 (0.939 s / it) [11-23 05:56:40] (/home/user/VAR/train.py , line 276)=> [ep30] (training ) Lm: 6.711 (6.711), Lt: 5.979 (5.979), Acc m&t: 2.85 4.50, Remain: 5 days, 19:03:18, Finish: 2024-11-28 08:59 [11-23 05:56:40] (/home/user/VAR/train.py , line 276)=> [ep30] (training ) Lm: 6.711 (6.711), Lt: 5.979 (5.979), Acc m&t: 2.85 4.50, Remain: 5 days, 19:02:51, Finish: 2024-11-28 08:59 [11-23 05:56:40] (/home/user/VAR/train.py , line 276)=> [ep30] (training ) Lm: 6.711 (6.711), Lt: 5.979 (5.979), Acc m&t: 2.85 4.50, Remain: 5 days, 19:02:33, Finish: 2024-11-28 08:59 [11-23 05:56:40] (/home/user/VAR/train.py , line 276)=> [ep30] (training ) Lm: 6.711 (6.711), Lt: 5.979 (5.979), Acc m&t: 2.85 4.50, Remain: 5 days, 19:02:41, Finish: 2024-11-28 08:59 [11-23 05:56:40] (/home/user/VAR/train.py , line 276)=> [ep30] (training ) Lm: 6.711 (6.711), Lt: 5.979 (5.979), Acc m&t: 2.85 4.50, Remain: 5 days, 19:02:15, Finish: 2024-11-28 08:58 [11-23 05:56:40] (/home/user/VAR/train.py , line 276)=> [ep30] (training ) Lm: 6.711 (6.711), Lt: 5.979 (5.979), Acc m&t: 2.85 4.50, Remain: 5 days, 19:02:40, Finish: 2024-11-28 08:59 [11-23 05:56:40] (/home/user/VAR/train.py , line 276)=> [ep30] (training ) Lm: 6.711 (6.711), Lt: 5.979 (5.979), Acc m&t: 2.85 4.50, Remain: 5 days, 19:00:05, Finish: 2024-11-28 08:56 [11-23 05:56:40] (/home/user/VAR/train.py , line 276)=> [ep30] (training ) Lm: 6.711 (6.711), Lt: 5.979 (5.979), Acc m&t: 2.85 4.50, Remain: 5 days, 19:01:44, Finish: 2024-11-28 08:58 [11-23 05:56:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 0/1669] eta: 0:25:43 tlr: 0.00024 tnm: 0.25 Lm: 6.618 (6.618) Lt: 5.810 (5.810) Accm: 3.39 (3.39) Acct: 5.75 (5.75) proj_loss: -0.5480 (-0.5480) time: 0.9247 data: 0.0004 [11-23 05:56:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 0/1669] eta: 0:24:21 tlr: 0.00024 tnm: 0.25 Lm: 6.804 (6.804) Lt: 6.032 (6.032) Accm: 2.64 (2.64) Acct: 4.41 (4.41) proj_loss: -0.5433 (-0.5433) time: 0.8756 data: 0.0004 [11-23 05:56:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 0/1669] eta: 0:24:20 tlr: 0.00024 tnm: 0.25 Lm: 6.861 (6.861) Lt: 6.253 (6.253) Accm: 2.27 (2.27) Acct: 3.37 (3.37) proj_loss: -0.5737 (-0.5737) time: 0.8750 data: 0.0004 [11-23 05:56:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 0/1669] eta: 0:24:22 tlr: 0.00024 tnm: 0.25 Lm: 6.894 (6.894) Lt: 6.210 (6.210) Accm: 2.59 (2.59) Acct: 3.72 (3.72) proj_loss: -0.5410 (-0.5410) time: 0.8762 data: 0.0004 [11-23 05:56:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 0/1669] eta: 0:24:21 tlr: 0.00024 tnm: 0.25 Lm: 6.600 (6.600) Lt: 5.806 (5.806) Accm: 2.91 (2.91) Acct: 5.10 (5.10) proj_loss: -0.5503 (-0.5503) time: 0.8755 data: 0.0004 [11-23 05:56:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 0/1669] eta: 0:24:21 tlr: 0.00024 tnm: 0.25 Lm: 6.626 (6.626) Lt: 5.878 (5.878) Accm: 3.04 (3.04) Acct: 5.13 (5.13) proj_loss: -0.5757 (-0.5757) time: 0.8757 data: 0.0004 [11-23 05:56:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 0/1669] eta: 0:24:24 tlr: 0.00024 tnm: 0.25 Lm: 6.617 (6.617) Lt: 5.917 (5.917) Accm: 2.93 (2.93) Acct: 4.51 (4.51) proj_loss: -0.5659 (-0.5659) time: 0.8772 data: 0.0003 [11-23 05:56:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 0/1669] eta: 0:24:21 tlr: 0.00024 tnm: 0.25 Lm: 6.497 (6.497) Lt: 5.733 (5.733) Accm: 3.10 (3.10) Acct: 4.82 (4.82) proj_loss: -0.5819 (-0.5819) time: 0.8757 data: 0.0004 [11-23 06:03:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 417/1669] eta: 0:20:09 tlr: 0.00023 tnm: 0.24 Lm: 6.521 (6.521) Lt: 5.762 (5.762) Accm: 3.14 (3.14) Acct: 4.99 (4.99) proj_loss: -0.5560 (-0.5560) time: 0.9284 data: 0.0003 [11-23 06:03:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 417/1669] eta: 0:20:09 tlr: 0.00023 tnm: 0.24 Lm: 6.682 (6.682) Lt: 5.886 (5.886) Accm: 3.32 (3.32) Acct: 5.48 (5.48) proj_loss: -0.5374 (-0.5374) time: 0.9284 data: 0.0002 [11-23 06:03:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 417/1669] eta: 0:20:09 tlr: 0.00023 tnm: 0.24 Lm: 6.731 (6.731) Lt: 6.067 (6.067) Accm: 2.67 (2.67) Acct: 4.24 (4.24) proj_loss: -0.5646 (-0.5646) time: 0.9284 data: 0.0003 [11-23 06:03:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 417/1669] eta: 0:20:09 tlr: 0.00023 tnm: 0.24 Lm: 6.623 (6.623) Lt: 5.880 (5.880) Accm: 3.29 (3.29) Acct: 5.30 (5.30) proj_loss: -0.5504 (-0.5504) time: 0.9284 data: 0.0003 [11-23 06:03:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 417/1669] eta: 0:20:09 tlr: 0.00023 tnm: 0.24 Lm: 6.781 (6.781) Lt: 6.054 (6.054) Accm: 3.02 (3.02) Acct: 4.51 (4.51) proj_loss: -0.5441 (-0.5441) time: 0.9284 data: 0.0003 [11-23 06:03:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 417/1669] eta: 0:20:09 tlr: 0.00023 tnm: 0.24 Lm: 6.634 (6.634) Lt: 5.931 (5.931) Accm: 3.07 (3.07) Acct: 4.80 (4.80) proj_loss: -0.5541 (-0.5541) time: 0.9283 data: 0.0003 [11-23 06:03:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 417/1669] eta: 0:20:09 tlr: 0.00023 tnm: 0.24 Lm: 6.608 (6.608) Lt: 5.820 (5.820) Accm: 2.93 (2.93) Acct: 4.96 (4.96) proj_loss: -0.5469 (-0.5469) time: 0.9284 data: 0.0003 [11-23 06:03:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 417/1669] eta: 0:20:09 tlr: 0.00023 tnm: 0.24 Lm: 6.723 (6.723) Lt: 5.984 (5.984) Accm: 2.83 (2.83) Acct: 4.73 (4.73) proj_loss: -0.5545 (-0.5545) time: 0.9284 data: 0.0005 [11-23 06:09:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 834/1669] eta: 0:13:11 tlr: 0.00023 tnm: 0.23 Lm: 6.631 (6.692) Lt: 5.878 (5.930) Accm: 3.04 (2.98) Acct: 5.13 (4.95) proj_loss: -0.5334 (-0.5381) time: 0.9300 data: 0.0003 [11-23 06:09:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 834/1669] eta: 0:13:11 tlr: 0.00023 tnm: 0.23 Lm: 6.705 (6.755) Lt: 5.963 (6.024) Accm: 2.81 (2.95) Acct: 3.89 (4.30) proj_loss: -0.5473 (-0.5460) time: 0.9300 data: 0.0003 [11-23 06:09:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 834/1669] eta: 0:13:11 tlr: 0.00023 tnm: 0.23 Lm: 6.745 (6.761) Lt: 5.963 (5.985) Accm: 3.25 (2.98) Acct: 5.20 (4.94) proj_loss: -0.5357 (-0.5368) time: 0.9300 data: 0.0002 [11-23 06:09:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 834/1669] eta: 0:13:11 tlr: 0.00023 tnm: 0.23 Lm: 6.716 (6.726) Lt: 6.002 (6.045) Accm: 2.61 (2.65) Acct: 4.06 (4.18) proj_loss: -0.5591 (-0.5627) time: 0.9300 data: 0.0003 [11-23 06:09:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 834/1669] eta: 0:13:11 tlr: 0.00023 tnm: 0.23 Lm: 6.694 (6.647) Lt: 5.991 (5.917) Accm: 3.02 (3.20) Acct: 4.65 (5.08) proj_loss: -0.5433 (-0.5418) time: 0.9300 data: 0.0003 [11-23 06:09:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 834/1669] eta: 0:13:11 tlr: 0.00023 tnm: 0.23 Lm: 6.616 (6.619) Lt: 5.835 (5.840) Accm: 2.94 (2.95) Acct: 4.82 (4.81) proj_loss: -0.5434 (-0.5388) time: 0.9300 data: 0.0003 [11-23 06:09:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 834/1669] eta: 0:13:11 tlr: 0.00023 tnm: 0.23 Lm: 6.545 (6.564) Lt: 5.790 (5.796) Accm: 3.18 (3.15) Acct: 4.82 (4.90) proj_loss: -0.5300 (-0.5444) time: 0.9300 data: 0.0003 [11-23 06:09:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [ 834/1669] eta: 0:13:11 tlr: 0.00023 tnm: 0.23 Lm: 6.651 (6.698) Lt: 5.946 (6.003) Accm: 2.93 (2.94) Acct: 4.51 (4.67) proj_loss: -0.5659 (-0.5611) time: 0.9300 data: 0.0003 [11-23 06:16:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [1251/1669] eta: 0:06:33 tlr: 0.00023 tnm: 0.23 Lm: 6.660 (6.691) Lt: 5.957 (5.994) Accm: 2.95 (2.95) Acct: 4.72 (4.73) proj_loss: -0.5593 (-0.5590) time: 0.9297 data: 0.0003 [11-23 06:16:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [1251/1669] eta: 0:06:33 tlr: 0.00023 tnm: 0.23 Lm: 6.749 (6.699) Lt: 6.011 (5.972) Accm: 2.83 (3.02) Acct: 4.53 (4.82) proj_loss: -0.5475 (-0.5443) time: 0.9296 data: 0.0003 [11-23 06:16:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [1251/1669] eta: 0:06:33 tlr: 0.00023 tnm: 0.23 Lm: 6.682 (6.695) Lt: 5.886 (5.933) Accm: 3.32 (3.09) Acct: 5.13 (4.97) proj_loss: -0.5419 (-0.5467) time: 0.9296 data: 0.0003 [11-23 06:16:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [1251/1669] eta: 0:06:33 tlr: 0.00023 tnm: 0.23 Lm: 6.652 (6.687) Lt: 5.880 (5.918) Accm: 3.15 (3.05) Acct: 5.08 (4.97) proj_loss: -0.5471 (-0.5438) time: 0.9296 data: 0.0003 [11-23 06:16:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [1251/1669] eta: 0:06:33 tlr: 0.00023 tnm: 0.23 Lm: 6.745 (6.763) Lt: 6.006 (6.030) Accm: 2.75 (2.88) Acct: 3.93 (4.22) proj_loss: -0.5441 (-0.5401) time: 0.9296 data: 0.0003 [11-23 06:16:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [1251/1669] eta: 0:06:33 tlr: 0.00023 tnm: 0.23 Lm: 6.629 (6.651) Lt: 5.857 (5.885) Accm: 2.93 (2.82) Acct: 4.67 (4.57) proj_loss: -0.5469 (-0.5442) time: 0.9296 data: 0.0003 [11-23 06:16:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [1251/1669] eta: 0:06:33 tlr: 0.00023 tnm: 0.23 Lm: 6.737 (6.734) Lt: 6.037 (6.052) Accm: 2.78 (2.72) Acct: 4.36 (4.30) proj_loss: -0.5598 (-0.5622) time: 0.9296 data: 0.0003 [11-23 06:16:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [1251/1669] eta: 0:06:33 tlr: 0.00023 tnm: 0.23 Lm: 6.597 (6.663) Lt: 5.828 (5.912) Accm: 3.14 (2.94) Acct: 4.77 (4.65) proj_loss: -0.5358 (-0.5437) time: 0.9296 data: 0.0003 [11-23 06:22:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.24 Lm: 6.649 (6.673) Lt: 5.865 (5.925) Accm: 3.10 (2.91) Acct: 4.72 (4.57) proj_loss: -0.5416 (-0.5510) time: 0.9328 data: 0.0019 [11-23 06:22:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 31/350] Total time: 0:26:06 (0.938 s / it) [11-23 06:22:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.24 Lm: 6.804 (6.728) Lt: 6.032 (6.015) Accm: 2.64 (2.91) Acct: 4.41 (4.64) proj_loss: -0.5433 (-0.5438) time: 0.9328 data: 0.0018 [11-23 06:22:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.24 Lm: 6.651 (6.639) Lt: 5.946 (5.932) Accm: 2.97 (3.03) Acct: 4.92 (4.78) proj_loss: -0.5659 (-0.5608) time: 0.9328 data: 0.0020 [11-23 06:22:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.24 Lm: 6.716 (6.730) Lt: 6.002 (6.038) Accm: 2.75 (2.73) Acct: 4.55 (4.35) proj_loss: -0.5605 (-0.5625) time: 0.9328 data: 0.0026 [11-23 06:22:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.24 Lm: 6.705 (6.743) Lt: 5.963 (6.000) Accm: 2.81 (2.87) Acct: 3.96 (4.24) proj_loss: -0.5473 (-0.5447) time: 0.9328 data: 0.0020 [11-23 06:22:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.24 Lm: 6.631 (6.671) Lt: 5.878 (5.902) Accm: 3.25 (3.14) Acct: 5.13 (5.10) proj_loss: -0.5334 (-0.5384) time: 0.9328 data: 0.0022 [11-23 06:22:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.24 Lm: 6.616 (6.637) Lt: 5.835 (5.866) Accm: 2.94 (2.89) Acct: 4.82 (4.72) proj_loss: -0.5434 (-0.5433) time: 0.9328 data: 0.0018 [11-23 06:22:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 31/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.24 Lm: 6.698 (6.695) Lt: 5.875 (5.922) Accm: 3.25 (3.02) Acct: 5.06 (4.86) proj_loss: -0.5480 (-0.5486) time: 0.9328 data: 0.0016 [11-23 06:22:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 31/350] Total time: 0:26:06 (0.938 s / it) [11-23 06:22:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 31/350] Total time: 0:26:06 (0.938 s / it) [11-23 06:22:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 31/350] Total time: 0:26:06 (0.938 s / it) [11-23 06:22:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 31/350] Total time: 0:26:06 (0.938 s / it) [11-23 06:22:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 31/350] Total time: 0:26:06 (0.938 s / it) [11-23 06:22:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 31/350] Total time: 0:26:06 (0.938 s / it) [11-23 06:22:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 31/350] Total time: 0:26:06 (0.939 s / it) [11-23 06:22:46] (/home/user/VAR/train.py , line 276)=> [ep31] (training ) Lm: 6.688 (6.688), Lt: 5.950 (5.950), Acc m&t: 2.88 4.58, Remain: 5 days, 18:21:32, Finish: 2024-11-28 08:44 [11-23 06:22:46] (/home/user/VAR/train.py , line 276)=> [ep31] (training ) Lm: 6.688 (6.688), Lt: 5.950 (5.950), Acc m&t: 2.88 4.58, Remain: 5 days, 18:20:54, Finish: 2024-11-28 08:43 [11-23 06:22:46] (/home/user/VAR/train.py , line 276)=> [ep31] (training ) Lm: 6.688 (6.688), Lt: 5.950 (5.950), Acc m&t: 2.88 4.58, Remain: 5 days, 18:23:14, Finish: 2024-11-28 08:46 [11-23 06:22:46] (/home/user/VAR/train.py , line 276)=> [ep31] (training ) Lm: 6.688 (6.688), Lt: 5.950 (5.950), Acc m&t: 2.88 4.58, Remain: 5 days, 18:18:53, Finish: 2024-11-28 08:41 [11-23 06:22:46] (/home/user/VAR/train.py , line 276)=> [ep31] (training ) Lm: 6.688 (6.688), Lt: 5.950 (5.950), Acc m&t: 2.88 4.58, Remain: 5 days, 18:19:15, Finish: 2024-11-28 08:42 [11-23 06:22:46] (/home/user/VAR/train.py , line 276)=> [ep31] (training ) Lm: 6.688 (6.688), Lt: 5.950 (5.950), Acc m&t: 2.88 4.58, Remain: 5 days, 18:18:37, Finish: 2024-11-28 08:41 [11-23 06:22:46] (/home/user/VAR/train.py , line 276)=> [ep31] (training ) Lm: 6.688 (6.688), Lt: 5.950 (5.950), Acc m&t: 2.88 4.58, Remain: 5 days, 18:17:50, Finish: 2024-11-28 08:40 [11-23 06:22:46] (/home/user/VAR/train.py , line 276)=> [ep31] (training ) Lm: 6.688 (6.688), Lt: 5.950 (5.950), Acc m&t: 2.88 4.58, Remain: 5 days, 18:21:16, Finish: 2024-11-28 08:44 [11-23 06:22:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 0/1669] eta: 0:25:31 tlr: 0.00023 tnm: 0.24 Lm: 6.668 (6.668) Lt: 5.874 (5.874) Accm: 3.13 (3.13) Acct: 4.99 (4.99) proj_loss: -0.5504 (-0.5504) time: 0.9177 data: 0.0004 [11-23 06:22:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 0/1669] eta: 0:25:32 tlr: 0.00023 tnm: 0.24 Lm: 6.580 (6.580) Lt: 5.881 (5.881) Accm: 2.86 (2.86) Acct: 4.55 (4.55) proj_loss: -0.5752 (-0.5752) time: 0.9181 data: 0.0004 [11-23 06:22:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 0/1669] eta: 0:25:40 tlr: 0.00023 tnm: 0.24 Lm: 6.929 (6.929) Lt: 6.246 (6.246) Accm: 2.16 (2.16) Acct: 3.55 (3.55) proj_loss: -0.5356 (-0.5356) time: 0.9229 data: 0.0003 [11-23 06:22:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 0/1669] eta: 0:25:41 tlr: 0.00023 tnm: 0.24 Lm: 6.567 (6.567) Lt: 5.879 (5.879) Accm: 3.55 (3.55) Acct: 5.41 (5.41) proj_loss: -0.5565 (-0.5565) time: 0.9235 data: 0.0004 [11-23 06:22:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 0/1669] eta: 0:25:33 tlr: 0.00023 tnm: 0.24 Lm: 6.423 (6.423) Lt: 5.676 (5.676) Accm: 3.64 (3.64) Acct: 5.65 (5.65) proj_loss: -0.5345 (-0.5345) time: 0.9187 data: 0.0004 [11-23 06:22:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 0/1669] eta: 0:25:33 tlr: 0.00023 tnm: 0.24 Lm: 6.704 (6.704) Lt: 5.943 (5.943) Accm: 2.55 (2.55) Acct: 3.82 (3.82) proj_loss: -0.5593 (-0.5593) time: 0.9191 data: 0.0004 [11-23 06:22:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 0/1669] eta: 0:25:31 tlr: 0.00023 tnm: 0.24 Lm: 6.538 (6.538) Lt: 5.782 (5.782) Accm: 3.47 (3.47) Acct: 5.34 (5.34) proj_loss: -0.5456 (-0.5456) time: 0.9179 data: 0.0004 [11-23 06:22:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 0/1669] eta: 0:25:33 tlr: 0.00023 tnm: 0.24 Lm: 6.783 (6.783) Lt: 6.054 (6.054) Accm: 2.74 (2.74) Acct: 4.20 (4.20) proj_loss: -0.5353 (-0.5353) time: 0.9190 data: 0.0004 [11-23 06:29:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 417/1669] eta: 0:19:23 tlr: 0.00023 tnm: 0.24 Lm: 6.680 (6.680) Lt: 5.952 (5.952) Accm: 2.98 (2.98) Acct: 4.53 (4.53) proj_loss: -0.5483 (-0.5483) time: 0.9294 data: 0.0003 [11-23 06:29:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 417/1669] eta: 0:19:23 tlr: 0.00023 tnm: 0.24 Lm: 6.863 (6.863) Lt: 6.133 (6.133) Accm: 2.64 (2.64) Acct: 4.13 (4.13) proj_loss: -0.5448 (-0.5448) time: 0.9294 data: 0.0003 [11-23 06:29:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 417/1669] eta: 0:19:23 tlr: 0.00023 tnm: 0.24 Lm: 6.555 (6.555) Lt: 5.812 (5.812) Accm: 2.91 (2.91) Acct: 4.44 (4.44) proj_loss: -0.5664 (-0.5664) time: 0.9294 data: 0.0003 [11-23 06:29:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 417/1669] eta: 0:19:23 tlr: 0.00023 tnm: 0.24 Lm: 6.850 (6.850) Lt: 6.149 (6.149) Accm: 2.51 (2.51) Acct: 3.81 (3.81) proj_loss: -0.5442 (-0.5442) time: 0.9294 data: 0.0003 [11-23 06:29:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 417/1669] eta: 0:19:23 tlr: 0.00023 tnm: 0.24 Lm: 6.569 (6.569) Lt: 5.869 (5.869) Accm: 3.13 (3.13) Acct: 4.98 (4.98) proj_loss: -0.5486 (-0.5486) time: 0.9294 data: 0.0003 [11-23 06:29:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 417/1669] eta: 0:19:23 tlr: 0.00023 tnm: 0.24 Lm: 6.668 (6.668) Lt: 5.976 (5.976) Accm: 2.98 (2.98) Acct: 4.61 (4.61) proj_loss: -0.5393 (-0.5393) time: 0.9294 data: 0.0003 [11-23 06:29:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 417/1669] eta: 0:19:23 tlr: 0.00023 tnm: 0.24 Lm: 6.627 (6.627) Lt: 5.864 (5.864) Accm: 3.21 (3.21) Acct: 4.86 (4.86) proj_loss: -0.5515 (-0.5515) time: 0.9294 data: 0.0003 [11-23 06:29:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 417/1669] eta: 0:19:23 tlr: 0.00023 tnm: 0.24 Lm: 6.684 (6.684) Lt: 5.985 (5.985) Accm: 2.94 (2.94) Acct: 4.53 (4.53) proj_loss: -0.5418 (-0.5418) time: 0.9294 data: 0.0002 [11-23 06:36:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 834/1669] eta: 0:13:15 tlr: 0.00023 tnm: 0.24 Lm: 6.610 (6.659) Lt: 5.894 (5.955) Accm: 2.86 (2.91) Acct: 5.03 (4.69) proj_loss: -0.5481 (-0.5457) time: 1.3025 data: 0.0003 [11-23 06:36:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 834/1669] eta: 0:13:15 tlr: 0.00023 tnm: 0.24 Lm: 6.656 (6.672) Lt: 6.007 (5.971) Accm: 3.03 (3.00) Acct: 4.65 (4.57) proj_loss: -0.5614 (-0.5533) time: 1.3025 data: 0.0003 [11-23 06:36:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 834/1669] eta: 0:13:15 tlr: 0.00023 tnm: 0.24 Lm: 6.716 (6.693) Lt: 5.945 (5.936) Accm: 2.96 (3.02) Acct: 4.41 (4.71) proj_loss: -0.5456 (-0.5470) time: 1.3025 data: 0.0003 [11-23 06:36:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 834/1669] eta: 0:13:15 tlr: 0.00023 tnm: 0.24 Lm: 6.606 (6.581) Lt: 5.809 (5.849) Accm: 2.84 (3.03) Acct: 4.65 (4.87) proj_loss: -0.5345 (-0.5370) time: 1.3025 data: 0.0003 [11-23 06:36:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 834/1669] eta: 0:13:15 tlr: 0.00023 tnm: 0.24 Lm: 6.770 (6.717) Lt: 6.048 (6.000) Accm: 2.81 (2.92) Acct: 4.58 (4.60) proj_loss: -0.5291 (-0.5359) time: 1.3025 data: 0.0003 [11-23 06:36:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 834/1669] eta: 0:13:15 tlr: 0.00023 tnm: 0.24 Lm: 6.580 (6.602) Lt: 5.881 (5.873) Accm: 2.86 (2.88) Acct: 4.34 (4.37) proj_loss: -0.5576 (-0.5589) time: 1.3025 data: 0.0003 [11-23 06:36:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 834/1669] eta: 0:13:15 tlr: 0.00023 tnm: 0.24 Lm: 6.668 (6.747) Lt: 5.874 (5.974) Accm: 3.13 (2.99) Acct: 4.99 (4.86) proj_loss: -0.5391 (-0.5415) time: 1.3025 data: 0.0003 [11-23 06:36:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [ 834/1669] eta: 0:13:15 tlr: 0.00023 tnm: 0.24 Lm: 6.704 (6.788) Lt: 5.943 (6.049) Accm: 2.55 (2.59) Acct: 3.82 (4.06) proj_loss: -0.5308 (-0.5397) time: 1.3025 data: 0.0003 [11-23 06:42:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [1251/1669] eta: 0:06:38 tlr: 0.00023 tnm: 0.23 Lm: 6.661 (6.637) Lt: 5.935 (5.921) Accm: 2.72 (2.88) Acct: 4.48 (4.60) proj_loss: -0.5369 (-0.5376) time: 0.9312 data: 0.0003 [11-23 06:42:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [1251/1669] eta: 0:06:38 tlr: 0.00023 tnm: 0.23 Lm: 6.592 (6.678) Lt: 5.765 (5.890) Accm: 3.28 (3.10) Acct: 5.32 (5.05) proj_loss: -0.5448 (-0.5453) time: 0.9312 data: 0.0003 [11-23 06:42:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [1251/1669] eta: 0:06:38 tlr: 0.00023 tnm: 0.23 Lm: 6.682 (6.687) Lt: 5.999 (5.987) Accm: 2.82 (2.90) Acct: 4.42 (4.52) proj_loss: -0.5428 (-0.5500) time: 0.9312 data: 0.0003 [11-23 06:42:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [1251/1669] eta: 0:06:38 tlr: 0.00023 tnm: 0.23 Lm: 6.559 (6.586) Lt: 5.812 (5.833) Accm: 2.91 (3.00) Acct: 4.44 (4.71) proj_loss: -0.5507 (-0.5506) time: 0.9312 data: 0.0003 [11-23 06:42:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [1251/1669] eta: 0:06:38 tlr: 0.00023 tnm: 0.23 Lm: 6.771 (6.732) Lt: 6.013 (5.986) Accm: 2.79 (2.89) Acct: 4.39 (4.44) proj_loss: -0.5418 (-0.5445) time: 0.9312 data: 0.0003 [11-23 06:42:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [1251/1669] eta: 0:06:38 tlr: 0.00023 tnm: 0.23 Lm: 6.704 (6.694) Lt: 6.038 (6.012) Accm: 2.68 (2.81) Acct: 4.51 (4.52) proj_loss: -0.5508 (-0.5546) time: 0.9312 data: 0.0002 [11-23 06:42:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [1251/1669] eta: 0:06:38 tlr: 0.00023 tnm: 0.23 Lm: 6.719 (6.709) Lt: 6.031 (6.000) Accm: 2.90 (2.94) Acct: 4.42 (4.47) proj_loss: -0.5623 (-0.5576) time: 0.9312 data: 0.0003 [11-23 06:42:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [1251/1669] eta: 0:06:38 tlr: 0.00023 tnm: 0.23 Lm: 6.703 (6.766) Lt: 5.973 (6.037) Accm: 2.65 (2.72) Acct: 4.13 (4.16) proj_loss: -0.5400 (-0.5421) time: 0.9313 data: 0.0003 [11-23 06:49:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.704 (6.786) Lt: 6.002 (6.062) Accm: 2.55 (2.63) Acct: 3.86 (4.10) proj_loss: -0.5493 (-0.5444) time: 0.9320 data: 0.0019 [11-23 06:49:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 32/350] Total time: 0:26:20 (0.947 s / it) [11-23 06:49:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.649 (6.685) Lt: 5.894 (5.987) Accm: 2.72 (2.79) Acct: 4.10 (4.44) proj_loss: -0.5481 (-0.5506) time: 0.9320 data: 0.0015 [11-23 06:49:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.668 (6.719) Lt: 5.874 (5.947) Accm: 3.13 (2.95) Acct: 4.99 (4.80) proj_loss: -0.5391 (-0.5419) time: 0.9320 data: 0.0019 [11-23 06:49:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.539 (6.569) Lt: 5.742 (5.811) Accm: 2.97 (3.13) Acct: 4.55 (4.94) proj_loss: -0.5442 (-0.5493) time: 0.9320 data: 0.0018 [11-23 06:49:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.783 (6.742) Lt: 6.054 (6.027) Accm: 2.77 (2.86) Acct: 4.30 (4.44) proj_loss: -0.5631 (-0.5613) time: 0.9320 data: 0.0019 [11-23 06:49:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.770 (6.717) Lt: 6.048 (6.016) Accm: 2.81 (2.77) Acct: 4.27 (4.26) proj_loss: -0.5565 (-0.5523) time: 0.9320 data: 0.0018 [11-23 06:49:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.606 (6.629) Lt: 5.946 (5.926) Accm: 2.84 (2.95) Acct: 4.65 (4.61) proj_loss: -0.5393 (-0.5440) time: 0.9320 data: 0.0019 [11-23 06:49:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 32/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.825 (6.756) Lt: 6.082 (6.024) Accm: 2.62 (2.75) Acct: 4.37 (4.24) proj_loss: -0.5456 (-0.5496) time: 0.9320 data: 0.0018 [11-23 06:49:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 32/350] Total time: 0:26:20 (0.947 s / it) [11-23 06:49:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 32/350] Total time: 0:26:20 (0.947 s / it) [11-23 06:49:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 32/350] Total time: 0:26:20 (0.947 s / it) [11-23 06:49:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 32/350] Total time: 0:26:20 (0.947 s / it) [11-23 06:49:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 32/350] Total time: 0:26:20 (0.947 s / it) [11-23 06:49:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 32/350] Total time: 0:26:20 (0.947 s / it) [11-23 06:49:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 32/350] Total time: 0:26:20 (0.947 s / it) [11-23 06:49:07] (/home/user/VAR/train.py , line 276)=> [ep32] (training ) Lm: 6.688 (6.697), Lt: 5.950 (5.963), Acc m&t: 2.88 4.58, Remain: 5 days, 18:05:31, Finish: 2024-11-28 08:54 [11-23 06:49:07] (/home/user/VAR/train.py , line 276)=> [ep32] (training ) Lm: 6.688 (6.697), Lt: 5.950 (5.963), Acc m&t: 2.88 4.58, Remain: 5 days, 18:02:58, Finish: 2024-11-28 08:52 [11-23 06:49:07] (/home/user/VAR/train.py , line 276)=> [ep32] (training ) Lm: 6.688 (6.697), Lt: 5.950 (5.963), Acc m&t: 2.88 4.58, Remain: 5 days, 18:03:58, Finish: 2024-11-28 08:53 [11-23 06:49:07] (/home/user/VAR/train.py , line 276)=> [ep32] (training ) Lm: 6.688 (6.697), Lt: 5.950 (5.963), Acc m&t: 2.88 4.58, Remain: 5 days, 18:03:14, Finish: 2024-11-28 08:52 [11-23 06:49:07] (/home/user/VAR/train.py , line 276)=> [ep32] (training ) Lm: 6.688 (6.697), Lt: 5.950 (5.963), Acc m&t: 2.88 4.58, Remain: 5 days, 18:03:21, Finish: 2024-11-28 08:52 [11-23 06:49:07] (/home/user/VAR/train.py , line 276)=> [ep32] (training ) Lm: 6.688 (6.697), Lt: 5.950 (5.963), Acc m&t: 2.88 4.58, Remain: 5 days, 18:03:19, Finish: 2024-11-28 08:52 [11-23 06:49:07] (/home/user/VAR/train.py , line 276)=> [ep32] (training ) Lm: 6.688 (6.697), Lt: 5.950 (5.963), Acc m&t: 2.88 4.58, Remain: 5 days, 18:05:54, Finish: 2024-11-28 08:55 [11-23 06:49:07] (/home/user/VAR/train.py , line 276)=> [ep32] (training ) Lm: 6.688 (6.697), Lt: 5.950 (5.963), Acc m&t: 2.88 4.58, Remain: 5 days, 18:02:47, Finish: 2024-11-28 08:51 [11-23 06:49:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 0/1669] eta: 0:24:47 tlr: 0.00023 tnm: 0.23 Lm: 6.810 (6.810) Lt: 6.098 (6.098) Accm: 2.42 (2.42) Acct: 3.51 (3.51) proj_loss: -0.5653 (-0.5653) time: 0.8910 data: 0.0004 [11-23 06:49:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 0/1669] eta: 0:24:47 tlr: 0.00023 tnm: 0.23 Lm: 6.547 (6.547) Lt: 5.711 (5.711) Accm: 3.21 (3.21) Acct: 5.34 (5.34) proj_loss: -0.5240 (-0.5240) time: 0.8911 data: 0.0003 [11-23 06:49:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 0/1669] eta: 0:24:47 tlr: 0.00023 tnm: 0.23 Lm: 6.449 (6.449) Lt: 5.613 (5.613) Accm: 3.63 (3.63) Acct: 5.96 (5.96) proj_loss: -0.5601 (-0.5601) time: 0.8911 data: 0.0004 [11-23 06:49:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 0/1669] eta: 0:24:40 tlr: 0.00023 tnm: 0.23 Lm: 6.668 (6.668) Lt: 5.923 (5.923) Accm: 2.91 (2.91) Acct: 4.65 (4.65) proj_loss: -0.5616 (-0.5616) time: 0.8868 data: 0.0004 [11-23 06:49:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 0/1669] eta: 0:24:47 tlr: 0.00023 tnm: 0.23 Lm: 6.806 (6.806) Lt: 6.052 (6.052) Accm: 2.37 (2.37) Acct: 3.96 (3.96) proj_loss: -0.5317 (-0.5317) time: 0.8915 data: 0.0004 [11-23 06:49:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 0/1669] eta: 0:24:47 tlr: 0.00023 tnm: 0.23 Lm: 6.837 (6.837) Lt: 6.175 (6.175) Accm: 2.33 (2.33) Acct: 3.89 (3.89) proj_loss: -0.5471 (-0.5471) time: 0.8915 data: 0.0004 [11-23 06:49:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 0/1669] eta: 0:24:46 tlr: 0.00023 tnm: 0.23 Lm: 6.570 (6.570) Lt: 5.846 (5.846) Accm: 3.18 (3.18) Acct: 4.61 (4.61) proj_loss: -0.5321 (-0.5321) time: 0.8905 data: 0.0004 [11-23 06:49:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 0/1669] eta: 0:24:42 tlr: 0.00023 tnm: 0.23 Lm: 6.556 (6.556) Lt: 5.808 (5.808) Accm: 3.66 (3.66) Acct: 6.37 (6.37) proj_loss: -0.5686 (-0.5686) time: 0.8880 data: 0.0004 [11-23 06:55:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 417/1669] eta: 0:19:22 tlr: 0.00023 tnm: 0.22 Lm: 6.592 (6.592) Lt: 5.825 (5.825) Accm: 3.17 (3.17) Acct: 5.23 (5.23) proj_loss: -0.5531 (-0.5531) time: 0.9283 data: 0.0003 [11-23 06:55:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 417/1669] eta: 0:19:23 tlr: 0.00023 tnm: 0.22 Lm: 6.690 (6.690) Lt: 5.921 (5.921) Accm: 2.76 (2.76) Acct: 4.65 (4.65) proj_loss: -0.5459 (-0.5459) time: 0.9283 data: 0.0003 [11-23 06:55:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 417/1669] eta: 0:19:23 tlr: 0.00023 tnm: 0.22 Lm: 6.633 (6.633) Lt: 5.843 (5.843) Accm: 3.10 (3.10) Acct: 5.03 (5.03) proj_loss: -0.5512 (-0.5512) time: 0.9283 data: 0.0003 [11-23 06:55:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 417/1669] eta: 0:19:23 tlr: 0.00023 tnm: 0.22 Lm: 6.594 (6.594) Lt: 5.869 (5.869) Accm: 3.27 (3.27) Acct: 5.23 (5.23) proj_loss: -0.5428 (-0.5428) time: 0.9283 data: 0.0002 [11-23 06:55:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 417/1669] eta: 0:19:23 tlr: 0.00023 tnm: 0.22 Lm: 6.578 (6.578) Lt: 5.829 (5.829) Accm: 3.15 (3.15) Acct: 5.15 (5.15) proj_loss: -0.5485 (-0.5485) time: 0.9283 data: 0.0003 [11-23 06:55:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 417/1669] eta: 0:19:23 tlr: 0.00023 tnm: 0.22 Lm: 6.797 (6.797) Lt: 6.082 (6.082) Accm: 2.60 (2.60) Acct: 4.08 (4.08) proj_loss: -0.5374 (-0.5374) time: 0.9283 data: 0.0003 [11-23 06:55:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 417/1669] eta: 0:19:23 tlr: 0.00023 tnm: 0.22 Lm: 6.724 (6.724) Lt: 6.014 (6.014) Accm: 2.57 (2.57) Acct: 3.74 (3.74) proj_loss: -0.5511 (-0.5511) time: 0.9283 data: 0.0003 [11-23 06:55:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 417/1669] eta: 0:19:23 tlr: 0.00023 tnm: 0.22 Lm: 6.758 (6.758) Lt: 6.031 (6.031) Accm: 2.73 (2.73) Acct: 4.42 (4.42) proj_loss: -0.5600 (-0.5600) time: 0.9283 data: 0.0003 [11-23 07:02:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.24 Lm: 6.668 (6.695) Lt: 5.923 (5.992) Accm: 2.67 (2.71) Acct: 4.20 (4.18) proj_loss: -0.5616 (-0.5632) time: 0.9309 data: 0.0003 [11-23 07:02:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.24 Lm: 6.734 (6.705) Lt: 5.995 (5.946) Accm: 2.74 (2.75) Acct: 3.96 (4.29) proj_loss: -0.5550 (-0.5490) time: 0.9309 data: 0.0003 [11-23 07:02:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.24 Lm: 6.705 (6.657) Lt: 6.030 (5.906) Accm: 2.99 (3.06) Acct: 4.34 (4.80) proj_loss: -0.5601 (-0.5596) time: 0.9309 data: 0.0002 [11-23 07:02:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.24 Lm: 6.556 (6.574) Lt: 5.808 (5.793) Accm: 3.10 (3.15) Acct: 5.03 (5.17) proj_loss: -0.5478 (-0.5513) time: 0.9309 data: 0.0003 [11-23 07:02:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.24 Lm: 6.758 (6.759) Lt: 6.007 (6.057) Accm: 2.87 (2.74) Acct: 4.27 (4.41) proj_loss: -0.5471 (-0.5468) time: 0.9309 data: 0.0003 [11-23 07:02:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.24 Lm: 6.777 (6.742) Lt: 6.098 (6.060) Accm: 2.72 (2.63) Acct: 3.93 (3.80) proj_loss: -0.5562 (-0.5528) time: 0.9309 data: 0.0003 [11-23 07:02:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.24 Lm: 6.609 (6.607) Lt: 5.947 (5.877) Accm: 3.09 (3.10) Acct: 4.96 (4.94) proj_loss: -0.5731 (-0.5568) time: 0.9309 data: 0.0003 [11-23 07:02:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.24 Lm: 6.617 (6.615) Lt: 5.888 (5.875) Accm: 3.23 (3.26) Acct: 5.41 (5.29) proj_loss: -0.5534 (-0.5492) time: 0.9309 data: 0.0003 [11-23 07:08:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.25 Lm: 6.625 (6.620) Lt: 5.890 (5.888) Accm: 3.21 (3.19) Acct: 5.01 (4.97) proj_loss: -0.5561 (-0.5516) time: 0.9284 data: 0.0003 [11-23 07:08:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.25 Lm: 6.582 (6.594) Lt: 5.865 (5.853) Accm: 3.15 (3.14) Acct: 5.08 (5.00) proj_loss: -0.5649 (-0.5568) time: 0.9284 data: 0.0003 [11-23 07:08:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.25 Lm: 6.718 (6.721) Lt: 6.033 (6.037) Accm: 2.74 (2.68) Acct: 3.94 (3.88) proj_loss: -0.5581 (-0.5546) time: 0.9284 data: 0.0003 [11-23 07:08:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.25 Lm: 6.547 (6.544) Lt: 5.769 (5.749) Accm: 3.31 (3.24) Acct: 5.15 (5.19) proj_loss: -0.5427 (-0.5463) time: 0.9284 data: 0.0003 [11-23 07:08:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.25 Lm: 6.705 (6.669) Lt: 5.992 (5.918) Accm: 3.10 (3.10) Acct: 4.94 (4.98) proj_loss: -0.5512 (-0.5520) time: 0.9284 data: 0.0002 [11-23 07:08:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.25 Lm: 6.694 (6.701) Lt: 5.941 (5.984) Accm: 2.62 (2.68) Acct: 4.29 (4.23) proj_loss: -0.5655 (-0.5648) time: 0.9284 data: 0.0003 [11-23 07:08:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.25 Lm: 6.673 (6.681) Lt: 5.932 (5.927) Accm: 2.94 (2.86) Acct: 4.39 (4.42) proj_loss: -0.5576 (-0.5557) time: 0.9284 data: 0.0003 [11-23 07:08:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.25 Lm: 6.729 (6.744) Lt: 5.998 (6.036) Accm: 2.82 (2.75) Acct: 4.49 (4.49) proj_loss: -0.5563 (-0.5516) time: 0.9284 data: 0.0003 [11-23 07:15:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.701 (6.725) Lt: 5.988 (6.013) Accm: 2.87 (2.79) Acct: 4.48 (4.48) proj_loss: -0.5491 (-0.5511) time: 0.9322 data: 0.0023 [11-23 07:15:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 33/350] Total time: 0:26:06 (0.938 s / it) [11-23 07:15:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.705 (6.678) Lt: 6.004 (5.935) Accm: 2.99 (3.03) Acct: 4.34 (4.84) proj_loss: -0.5601 (-0.5563) time: 0.9322 data: 0.0021 [11-23 07:15:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.683 (6.682) Lt: 5.927 (5.927) Accm: 2.74 (2.82) Acct: 4.27 (4.39) proj_loss: -0.5550 (-0.5548) time: 0.9322 data: 0.0018 [11-23 07:15:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.624 (6.621) Lt: 5.888 (5.885) Accm: 3.18 (3.18) Acct: 4.86 (4.94) proj_loss: -0.5588 (-0.5562) time: 0.9322 data: 0.0016 [11-23 07:15:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.556 (6.596) Lt: 5.808 (5.809) Accm: 3.10 (3.07) Acct: 5.03 (5.01) proj_loss: -0.5376 (-0.5443) time: 0.9322 data: 0.0016 [11-23 07:15:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.668 (6.673) Lt: 5.923 (5.951) Accm: 2.67 (2.80) Acct: 4.37 (4.46) proj_loss: -0.5694 (-0.5692) time: 0.9321 data: 0.0017 [11-23 07:15:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.609 (6.627) Lt: 5.947 (5.886) Accm: 3.09 (2.97) Acct: 4.96 (4.75) proj_loss: -0.5567 (-0.5539) time: 0.9322 data: 0.0018 [11-23 07:15:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 33/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.658 (6.685) Lt: 5.969 (6.001) Accm: 2.75 (2.83) Acct: 3.96 (4.10) proj_loss: -0.5601 (-0.5567) time: 0.9322 data: 0.0015 [11-23 07:15:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 33/350] Total time: 0:26:06 (0.938 s / it) [11-23 07:15:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 33/350] Total time: 0:26:06 (0.938 s / it) [11-23 07:15:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 33/350] Total time: 0:26:06 (0.938 s / it) [11-23 07:15:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 33/350] Total time: 0:26:06 (0.938 s / it) [11-23 07:15:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 33/350] Total time: 0:26:06 (0.938 s / it) [11-23 07:15:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 33/350] Total time: 0:26:06 (0.938 s / it) [11-23 07:15:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 33/350] Total time: 0:26:06 (0.938 s / it) [11-23 07:15:13] (/home/user/VAR/train.py , line 276)=> [ep33] (training ) Lm: 6.680 (6.680), Lt: 5.947 (5.947), Acc m&t: 2.88 4.58, Remain: 5 days, 17:36:18, Finish: 2024-11-28 08:51 [11-23 07:15:13] (/home/user/VAR/train.py , line 276)=> [ep33] (training ) Lm: 6.680 (6.680), Lt: 5.947 (5.947), Acc m&t: 2.88 4.58, Remain: 5 days, 17:34:21, Finish: 2024-11-28 08:49 [11-23 07:15:13] (/home/user/VAR/train.py , line 276)=> [ep33] (training ) Lm: 6.680 (6.680), Lt: 5.947 (5.947), Acc m&t: 2.88 4.58, Remain: 5 days, 17:33:27, Finish: 2024-11-28 08:48 [11-23 07:15:13] (/home/user/VAR/train.py , line 276)=> [ep33] (training ) Lm: 6.680 (6.680), Lt: 5.947 (5.947), Acc m&t: 2.88 4.58, Remain: 5 days, 17:38:02, Finish: 2024-11-28 08:53 [11-23 07:15:13] (/home/user/VAR/train.py , line 276)=> [ep33] (training ) Lm: 6.680 (6.680), Lt: 5.947 (5.947), Acc m&t: 2.88 4.58, Remain: 5 days, 17:35:06, Finish: 2024-11-28 08:50 [11-23 07:15:13] (/home/user/VAR/train.py , line 276)=> [ep33] (training ) Lm: 6.680 (6.680), Lt: 5.947 (5.947), Acc m&t: 2.88 4.58, Remain: 5 days, 17:35:52, Finish: 2024-11-28 08:51 [11-23 07:15:13] (/home/user/VAR/train.py , line 276)=> [ep33] (training ) Lm: 6.680 (6.680), Lt: 5.947 (5.947), Acc m&t: 2.88 4.58, Remain: 5 days, 17:34:11, Finish: 2024-11-28 08:49 [11-23 07:15:13] (/home/user/VAR/train.py , line 276)=> [ep33] (training ) Lm: 6.680 (6.680), Lt: 5.947 (5.947), Acc m&t: 2.88 4.58, Remain: 5 days, 17:32:40, Finish: 2024-11-28 08:47 [11-23 07:15:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 0/1669] eta: 0:25:06 tlr: 0.00023 tnm: 0.25 Lm: 6.665 (6.665) Lt: 5.843 (5.843) Accm: 3.28 (3.28) Acct: 5.41 (5.41) proj_loss: -0.5568 (-0.5568) time: 0.9026 data: 0.0004 [11-23 07:15:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 0/1669] eta: 0:25:06 tlr: 0.00023 tnm: 0.25 Lm: 6.655 (6.655) Lt: 5.940 (5.940) Accm: 2.91 (2.91) Acct: 4.72 (4.72) proj_loss: -0.5810 (-0.5810) time: 0.9027 data: 0.0004 [11-23 07:15:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 0/1669] eta: 0:25:06 tlr: 0.00023 tnm: 0.25 Lm: 6.867 (6.867) Lt: 6.165 (6.165) Accm: 2.45 (2.45) Acct: 3.72 (3.72) proj_loss: -0.5388 (-0.5388) time: 0.9026 data: 0.0004 [11-23 07:15:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 0/1669] eta: 0:25:01 tlr: 0.00023 tnm: 0.25 Lm: 6.788 (6.788) Lt: 6.122 (6.122) Accm: 2.26 (2.26) Acct: 3.72 (3.72) proj_loss: -0.5507 (-0.5507) time: 0.8997 data: 0.0003 [11-23 07:15:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 0/1669] eta: 0:25:06 tlr: 0.00023 tnm: 0.25 Lm: 6.767 (6.767) Lt: 6.002 (6.002) Accm: 2.88 (2.88) Acct: 4.44 (4.44) proj_loss: -0.5908 (-0.5908) time: 0.9025 data: 0.0004 [11-23 07:15:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 0/1669] eta: 0:25:05 tlr: 0.00023 tnm: 0.25 Lm: 6.742 (6.742) Lt: 6.077 (6.077) Accm: 2.48 (2.48) Acct: 3.68 (3.68) proj_loss: -0.5546 (-0.5546) time: 0.9023 data: 0.0004 [11-23 07:15:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 0/1669] eta: 0:25:06 tlr: 0.00023 tnm: 0.25 Lm: 6.657 (6.657) Lt: 5.861 (5.861) Accm: 2.94 (2.94) Acct: 5.03 (5.03) proj_loss: -0.5416 (-0.5416) time: 0.9026 data: 0.0004 [11-23 07:15:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 0/1669] eta: 0:25:07 tlr: 0.00023 tnm: 0.25 Lm: 6.493 (6.493) Lt: 5.708 (5.708) Accm: 3.60 (3.60) Acct: 5.99 (5.99) proj_loss: -0.5686 (-0.5686) time: 0.9031 data: 0.0004 [11-23 07:21:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 417/1669] eta: 0:19:34 tlr: 0.00023 tnm: 0.23 Lm: 6.647 (6.647) Lt: 5.900 (5.900) Accm: 3.04 (3.04) Acct: 4.84 (4.84) proj_loss: -0.5519 (-0.5519) time: 0.9892 data: 0.0003 [11-23 07:21:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 417/1669] eta: 0:19:34 tlr: 0.00023 tnm: 0.23 Lm: 6.760 (6.760) Lt: 6.024 (6.024) Accm: 2.83 (2.83) Acct: 4.48 (4.48) proj_loss: -0.5439 (-0.5439) time: 0.9892 data: 0.0003 [11-23 07:21:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 417/1669] eta: 0:19:34 tlr: 0.00023 tnm: 0.23 Lm: 6.824 (6.824) Lt: 6.119 (6.119) Accm: 2.29 (2.29) Acct: 3.72 (3.72) proj_loss: -0.5634 (-0.5634) time: 0.9892 data: 0.0003 [11-23 07:21:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 417/1669] eta: 0:19:34 tlr: 0.00023 tnm: 0.23 Lm: 6.732 (6.732) Lt: 5.975 (5.975) Accm: 3.01 (3.01) Acct: 4.75 (4.75) proj_loss: -0.5712 (-0.5712) time: 0.9892 data: 0.0003 [11-23 07:21:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 417/1669] eta: 0:19:34 tlr: 0.00023 tnm: 0.23 Lm: 6.633 (6.633) Lt: 5.926 (5.926) Accm: 3.03 (3.03) Acct: 4.61 (4.61) proj_loss: -0.5599 (-0.5599) time: 0.9892 data: 0.0003 [11-23 07:21:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 417/1669] eta: 0:19:34 tlr: 0.00023 tnm: 0.23 Lm: 6.703 (6.703) Lt: 5.892 (5.892) Accm: 3.11 (3.11) Acct: 4.96 (4.96) proj_loss: -0.5619 (-0.5619) time: 0.9892 data: 0.0003 [11-23 07:21:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 417/1669] eta: 0:19:34 tlr: 0.00023 tnm: 0.23 Lm: 6.572 (6.572) Lt: 5.789 (5.789) Accm: 3.32 (3.32) Acct: 5.41 (5.41) proj_loss: -0.5319 (-0.5319) time: 0.9892 data: 0.0003 [11-23 07:21:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 417/1669] eta: 0:19:34 tlr: 0.00023 tnm: 0.23 Lm: 6.732 (6.732) Lt: 6.047 (6.047) Accm: 2.48 (2.48) Acct: 3.77 (3.77) proj_loss: -0.5476 (-0.5476) time: 0.9892 data: 0.0003 [11-23 07:28:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 834/1669] eta: 0:13:19 tlr: 0.00023 tnm: 0.23 Lm: 6.742 (6.810) Lt: 6.077 (6.140) Accm: 2.48 (2.44) Acct: 3.68 (3.72) proj_loss: -0.5546 (-0.5571) time: 0.9280 data: 0.0002 [11-23 07:28:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 834/1669] eta: 0:13:19 tlr: 0.00023 tnm: 0.23 Lm: 6.655 (6.693) Lt: 5.940 (5.977) Accm: 2.91 (2.87) Acct: 4.51 (4.43) proj_loss: -0.5387 (-0.5473) time: 0.9280 data: 0.0003 [11-23 07:28:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 834/1669] eta: 0:13:19 tlr: 0.00023 tnm: 0.23 Lm: 6.741 (6.764) Lt: 5.941 (5.992) Accm: 2.94 (2.83) Acct: 4.51 (4.42) proj_loss: -0.5631 (-0.5623) time: 0.9280 data: 0.0003 [11-23 07:28:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 834/1669] eta: 0:13:19 tlr: 0.00023 tnm: 0.23 Lm: 6.652 (6.655) Lt: 5.884 (5.904) Accm: 3.21 (3.17) Acct: 5.23 (5.04) proj_loss: -0.5489 (-0.5584) time: 0.9280 data: 0.0003 [11-23 07:28:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 834/1669] eta: 0:13:19 tlr: 0.00023 tnm: 0.23 Lm: 6.698 (6.718) Lt: 6.002 (5.986) Accm: 2.88 (2.89) Acct: 4.44 (4.55) proj_loss: -0.5817 (-0.5747) time: 0.9280 data: 0.0003 [11-23 07:28:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 834/1669] eta: 0:13:19 tlr: 0.00023 tnm: 0.23 Lm: 6.683 (6.659) Lt: 5.972 (5.924) Accm: 2.81 (2.97) Acct: 4.03 (4.57) proj_loss: -0.5637 (-0.5558) time: 0.9280 data: 0.0003 [11-23 07:28:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 834/1669] eta: 0:13:19 tlr: 0.00023 tnm: 0.23 Lm: 6.657 (6.639) Lt: 5.861 (5.882) Accm: 2.94 (3.02) Acct: 5.03 (4.95) proj_loss: -0.5223 (-0.5269) time: 0.9280 data: 0.0003 [11-23 07:28:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [ 834/1669] eta: 0:13:19 tlr: 0.00023 tnm: 0.23 Lm: 6.788 (6.722) Lt: 6.116 (5.996) Accm: 2.33 (2.70) Acct: 3.72 (4.27) proj_loss: -0.5507 (-0.5587) time: 0.9280 data: 0.0003 [11-23 07:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [1251/1669] eta: 0:06:36 tlr: 0.00023 tnm: 0.23 Lm: 6.654 (6.669) Lt: 5.933 (5.931) Accm: 2.75 (2.81) Acct: 4.34 (4.44) proj_loss: -0.5500 (-0.5535) time: 0.9282 data: 0.0003 [11-23 07:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [1251/1669] eta: 0:06:36 tlr: 0.00023 tnm: 0.23 Lm: 6.716 (6.677) Lt: 5.964 (5.936) Accm: 2.78 (2.92) Acct: 4.53 (4.67) proj_loss: -0.5319 (-0.5380) time: 0.9281 data: 0.0003 [11-23 07:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [1251/1669] eta: 0:06:36 tlr: 0.00023 tnm: 0.23 Lm: 6.727 (6.751) Lt: 5.939 (5.979) Accm: 3.10 (2.94) Acct: 4.96 (4.73) proj_loss: -0.5650 (-0.5647) time: 0.9281 data: 0.0003 [11-23 07:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [1251/1669] eta: 0:06:36 tlr: 0.00023 tnm: 0.23 Lm: 6.685 (6.699) Lt: 5.944 (5.970) Accm: 2.98 (2.91) Acct: 4.61 (4.61) proj_loss: -0.5446 (-0.5481) time: 0.9281 data: 0.0003 [11-23 07:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [1251/1669] eta: 0:06:36 tlr: 0.00023 tnm: 0.23 Lm: 6.693 (6.662) Lt: 5.975 (5.961) Accm: 3.00 (2.95) Acct: 4.72 (4.66) proj_loss: -0.5698 (-0.5705) time: 0.9282 data: 0.0003 [11-23 07:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [1251/1669] eta: 0:06:36 tlr: 0.00023 tnm: 0.23 Lm: 6.732 (6.756) Lt: 6.047 (6.069) Accm: 2.48 (2.58) Acct: 3.77 (4.09) proj_loss: -0.5476 (-0.5467) time: 0.9282 data: 0.0003 [11-23 07:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [1251/1669] eta: 0:06:36 tlr: 0.00023 tnm: 0.23 Lm: 6.597 (6.627) Lt: 5.801 (5.858) Accm: 3.21 (3.18) Acct: 5.30 (5.12) proj_loss: -0.5439 (-0.5468) time: 0.9281 data: 0.0003 [11-23 07:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [1251/1669] eta: 0:06:36 tlr: 0.00023 tnm: 0.23 Lm: 6.671 (6.659) Lt: 5.933 (5.916) Accm: 2.99 (3.02) Acct: 4.56 (4.70) proj_loss: -0.5600 (-0.5559) time: 0.9281 data: 0.0003 [11-23 07:41:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.24 Lm: 6.659 (6.639) Lt: 5.894 (5.889) Accm: 3.06 (3.03) Acct: 5.10 (4.79) proj_loss: -0.5637 (-0.5584) time: 0.9317 data: 0.0019 [11-23 07:41:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 34/350] Total time: 0:26:14 (0.943 s / it) [11-23 07:41:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.24 Lm: 6.742 (6.787) Lt: 6.077 (6.105) Accm: 2.48 (2.53) Acct: 3.72 (4.02) proj_loss: -0.5546 (-0.5487) time: 0.9317 data: 0.0017 [11-23 07:41:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.24 Lm: 6.713 (6.737) Lt: 5.937 (5.965) Accm: 3.15 (2.98) Acct: 5.27 (4.84) proj_loss: -0.5631 (-0.5636) time: 0.9317 data: 0.0016 [11-23 07:41:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.24 Lm: 6.715 (6.715) Lt: 5.949 (5.985) Accm: 2.91 (2.84) Acct: 4.51 (4.52) proj_loss: -0.5387 (-0.5440) time: 0.9317 data: 0.0019 [11-23 07:41:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.24 Lm: 6.788 (6.742) Lt: 6.116 (6.023) Accm: 2.33 (2.67) Acct: 3.72 (4.25) proj_loss: -0.5507 (-0.5598) time: 0.9317 data: 0.0018 [11-23 07:41:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.24 Lm: 6.657 (6.651) Lt: 5.861 (5.903) Accm: 2.94 (2.96) Acct: 4.89 (4.72) proj_loss: -0.5416 (-0.5401) time: 0.9317 data: 0.0020 [11-23 07:41:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.24 Lm: 6.652 (6.638) Lt: 5.884 (5.869) Accm: 3.21 (3.16) Acct: 5.23 (5.05) proj_loss: -0.5449 (-0.5464) time: 0.9317 data: 0.0019 [11-23 07:41:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 34/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.24 Lm: 6.688 (6.641) Lt: 5.948 (5.924) Accm: 3.12 (3.09) Acct: 4.99 (4.93) proj_loss: -0.5578 (-0.5639) time: 0.9317 data: 0.0019 [11-23 07:41:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 34/350] Total time: 0:26:14 (0.943 s / it) [11-23 07:41:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 34/350] Total time: 0:26:14 (0.943 s / it) [11-23 07:41:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 34/350] Total time: 0:26:14 (0.943 s / it) [11-23 07:41:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 34/350] Total time: 0:26:14 (0.943 s / it) [11-23 07:41:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 34/350] Total time: 0:26:14 (0.943 s / it) [11-23 07:41:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 34/350] Total time: 0:26:14 (0.943 s / it) [11-23 07:41:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 34/350] Total time: 0:26:14 (0.943 s / it) [11-23 07:41:28] (/home/user/VAR/train.py , line 276)=> [ep34] (training ) Lm: 6.678 (6.678), Lt: 5.941 (5.941), Acc m&t: 2.92 4.61, Remain: 5 days, 16:39:13, Finish: 2024-11-28 08:20 [11-23 07:41:28] (/home/user/VAR/train.py , line 276)=> [ep34] (training ) Lm: 6.678 (6.678), Lt: 5.941 (5.941), Acc m&t: 2.92 4.61, Remain: 5 days, 16:40:08, Finish: 2024-11-28 08:21 [11-23 07:41:28] (/home/user/VAR/train.py , line 276)=> [ep34] (training ) Lm: 6.678 (6.678), Lt: 5.941 (5.941), Acc m&t: 2.92 4.61, Remain: 5 days, 16:41:27, Finish: 2024-11-28 08:22 [11-23 07:41:28] (/home/user/VAR/train.py , line 276)=> [ep34] (training ) Lm: 6.678 (6.678), Lt: 5.941 (5.941), Acc m&t: 2.92 4.61, Remain: 5 days, 16:40:12, Finish: 2024-11-28 08:21 [11-23 07:41:28] (/home/user/VAR/train.py , line 276)=> [ep34] (training ) Lm: 6.678 (6.678), Lt: 5.941 (5.941), Acc m&t: 2.92 4.61, Remain: 5 days, 16:39:22, Finish: 2024-11-28 08:20 [11-23 07:41:28] (/home/user/VAR/train.py , line 276)=> [ep34] (training ) Lm: 6.678 (6.678), Lt: 5.941 (5.941), Acc m&t: 2.92 4.61, Remain: 5 days, 16:40:44, Finish: 2024-11-28 08:22 [11-23 07:41:28] (/home/user/VAR/train.py , line 276)=> [ep34] (training ) Lm: 6.678 (6.678), Lt: 5.941 (5.941), Acc m&t: 2.92 4.61, Remain: 5 days, 16:38:55, Finish: 2024-11-28 08:20 [11-23 07:41:28] (/home/user/VAR/train.py , line 276)=> [ep34] (training ) Lm: 6.678 (6.678), Lt: 5.941 (5.941), Acc m&t: 2.92 4.61, Remain: 5 days, 16:40:07, Finish: 2024-11-28 08:21 [11-23 07:41:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 0/1669] eta: 0:24:34 tlr: 0.00023 tnm: 0.23 Lm: 6.689 (6.689) Lt: 5.975 (5.975) Accm: 2.84 (2.84) Acct: 4.55 (4.55) proj_loss: -0.5785 (-0.5785) time: 0.8834 data: 0.0004 [11-23 07:41:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 0/1669] eta: 0:24:43 tlr: 0.00023 tnm: 0.23 Lm: 6.683 (6.683) Lt: 5.920 (5.920) Accm: 2.86 (2.86) Acct: 5.10 (5.10) proj_loss: -0.5403 (-0.5403) time: 0.8890 data: 0.0004 [11-23 07:41:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 0/1669] eta: 0:24:44 tlr: 0.00023 tnm: 0.23 Lm: 6.669 (6.669) Lt: 5.953 (5.953) Accm: 2.86 (2.86) Acct: 4.75 (4.75) proj_loss: -0.5705 (-0.5705) time: 0.8894 data: 0.0004 [11-23 07:41:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 0/1669] eta: 0:24:44 tlr: 0.00023 tnm: 0.23 Lm: 6.623 (6.623) Lt: 5.959 (5.959) Accm: 2.64 (2.64) Acct: 4.17 (4.17) proj_loss: -0.5550 (-0.5550) time: 0.8896 data: 0.0005 [11-23 07:41:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 0/1669] eta: 0:24:44 tlr: 0.00023 tnm: 0.23 Lm: 6.667 (6.667) Lt: 5.924 (5.924) Accm: 2.77 (2.77) Acct: 4.20 (4.20) proj_loss: -0.5711 (-0.5711) time: 0.8897 data: 0.0004 [11-23 07:41:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 0/1669] eta: 0:24:45 tlr: 0.00023 tnm: 0.23 Lm: 6.746 (6.746) Lt: 6.013 (6.013) Accm: 2.65 (2.65) Acct: 4.06 (4.06) proj_loss: -0.5386 (-0.5386) time: 0.8899 data: 0.0004 [11-23 07:41:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 0/1669] eta: 0:24:45 tlr: 0.00023 tnm: 0.23 Lm: 6.799 (6.799) Lt: 6.018 (6.018) Accm: 2.64 (2.64) Acct: 4.06 (4.06) proj_loss: -0.5590 (-0.5590) time: 0.8898 data: 0.0004 [11-23 07:41:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 0/1669] eta: 0:24:46 tlr: 0.00023 tnm: 0.23 Lm: 6.598 (6.598) Lt: 5.824 (5.824) Accm: 3.09 (3.09) Acct: 4.61 (4.61) proj_loss: -0.5374 (-0.5374) time: 0.8908 data: 0.0005 [11-23 07:47:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.680 (6.680) Lt: 5.918 (5.918) Accm: 2.83 (2.83) Acct: 4.39 (4.39) proj_loss: -0.5500 (-0.5500) time: 0.9313 data: 0.0003 [11-23 07:47:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.719 (6.719) Lt: 5.972 (5.972) Accm: 2.82 (2.82) Acct: 4.70 (4.70) proj_loss: -0.5571 (-0.5571) time: 0.9313 data: 0.0003 [11-23 07:47:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.789 (6.789) Lt: 6.109 (6.109) Accm: 2.64 (2.64) Acct: 4.22 (4.22) proj_loss: -0.5470 (-0.5470) time: 0.9313 data: 0.0003 [11-23 07:47:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.637 (6.637) Lt: 5.869 (5.869) Accm: 2.80 (2.80) Acct: 4.60 (4.60) proj_loss: -0.5556 (-0.5556) time: 0.9313 data: 0.0003 [11-23 07:47:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.739 (6.739) Lt: 5.990 (5.990) Accm: 2.75 (2.75) Acct: 4.20 (4.20) proj_loss: -0.5574 (-0.5574) time: 0.9313 data: 0.0003 [11-23 07:47:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.631 (6.631) Lt: 5.906 (5.906) Accm: 2.99 (2.99) Acct: 4.60 (4.60) proj_loss: -0.5554 (-0.5554) time: 0.9313 data: 0.0003 [11-23 07:47:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.669 (6.669) Lt: 5.917 (5.917) Accm: 2.94 (2.94) Acct: 4.65 (4.65) proj_loss: -0.5704 (-0.5704) time: 0.9313 data: 0.0003 [11-23 07:47:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.724 (6.724) Lt: 5.990 (5.990) Accm: 2.70 (2.70) Acct: 4.58 (4.58) proj_loss: -0.5521 (-0.5521) time: 0.9313 data: 0.0003 [11-23 07:54:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 834/1669] eta: 0:12:58 tlr: 0.00023 tnm: 0.22 Lm: 6.683 (6.703) Lt: 5.920 (5.944) Accm: 2.86 (2.90) Acct: 5.10 (4.84) proj_loss: -0.5504 (-0.5515) time: 0.9307 data: 0.0003 [11-23 07:54:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 834/1669] eta: 0:12:58 tlr: 0.00023 tnm: 0.22 Lm: 6.669 (6.571) Lt: 5.953 (5.813) Accm: 2.86 (3.40) Acct: 4.75 (5.61) proj_loss: -0.5625 (-0.5589) time: 0.9307 data: 0.0003 [11-23 07:54:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 834/1669] eta: 0:12:58 tlr: 0.00023 tnm: 0.22 Lm: 6.762 (6.714) Lt: 6.011 (5.953) Accm: 2.58 (2.75) Acct: 4.17 (4.32) proj_loss: -0.5374 (-0.5378) time: 0.9307 data: 0.0003 [11-23 07:54:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 834/1669] eta: 0:12:58 tlr: 0.00023 tnm: 0.22 Lm: 6.689 (6.656) Lt: 5.975 (5.916) Accm: 2.77 (2.77) Acct: 4.55 (4.45) proj_loss: -0.5539 (-0.5550) time: 0.9307 data: 0.0003 [11-23 07:54:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 834/1669] eta: 0:12:58 tlr: 0.00023 tnm: 0.22 Lm: 6.623 (6.731) Lt: 5.959 (6.047) Accm: 2.65 (2.68) Acct: 4.17 (4.17) proj_loss: -0.5418 (-0.5452) time: 0.9307 data: 0.0003 [11-23 07:54:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 834/1669] eta: 0:12:58 tlr: 0.00023 tnm: 0.22 Lm: 6.559 (6.607) Lt: 5.801 (5.871) Accm: 3.32 (3.17) Acct: 5.13 (4.95) proj_loss: -0.5568 (-0.5559) time: 0.9307 data: 0.0003 [11-23 07:54:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 834/1669] eta: 0:12:58 tlr: 0.00023 tnm: 0.22 Lm: 6.667 (6.579) Lt: 5.910 (5.811) Accm: 3.10 (3.21) Acct: 5.10 (5.14) proj_loss: -0.5711 (-0.5746) time: 0.9307 data: 0.0003 [11-23 07:54:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [ 834/1669] eta: 0:12:58 tlr: 0.00023 tnm: 0.22 Lm: 6.724 (6.734) Lt: 5.992 (5.991) Accm: 2.77 (2.76) Acct: 4.34 (4.34) proj_loss: -0.5590 (-0.5594) time: 0.9307 data: 0.0003 [11-23 08:01:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [1251/1669] eta: 0:06:39 tlr: 0.00023 tnm: 0.23 Lm: 6.718 (6.729) Lt: 6.005 (5.998) Accm: 2.82 (2.82) Acct: 4.42 (4.38) proj_loss: -0.5574 (-0.5552) time: 0.9301 data: 0.0003 [11-23 08:01:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [1251/1669] eta: 0:06:39 tlr: 0.00023 tnm: 0.23 Lm: 6.724 (6.728) Lt: 5.990 (5.985) Accm: 2.78 (2.85) Acct: 4.77 (4.74) proj_loss: -0.5454 (-0.5423) time: 0.9301 data: 0.0002 [11-23 08:01:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [1251/1669] eta: 0:06:39 tlr: 0.00023 tnm: 0.23 Lm: 6.719 (6.634) Lt: 5.972 (5.884) Accm: 2.82 (3.21) Acct: 4.70 (5.21) proj_loss: -0.5530 (-0.5525) time: 0.9301 data: 0.0003 [11-23 08:01:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [1251/1669] eta: 0:06:39 tlr: 0.00023 tnm: 0.23 Lm: 6.555 (6.593) Lt: 5.800 (5.853) Accm: 3.43 (3.29) Acct: 5.04 (4.95) proj_loss: -0.5576 (-0.5565) time: 0.9301 data: 0.0003 [11-23 08:01:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [1251/1669] eta: 0:06:39 tlr: 0.00023 tnm: 0.23 Lm: 6.692 (6.667) Lt: 5.950 (5.918) Accm: 2.80 (2.81) Acct: 4.55 (4.48) proj_loss: -0.5597 (-0.5576) time: 0.9301 data: 0.0003 [11-23 08:01:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [1251/1669] eta: 0:06:39 tlr: 0.00023 tnm: 0.23 Lm: 6.727 (6.709) Lt: 5.986 (5.955) Accm: 2.58 (2.70) Acct: 4.29 (4.34) proj_loss: -0.5496 (-0.5438) time: 0.9301 data: 0.0003 [11-23 08:01:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [1251/1669] eta: 0:06:39 tlr: 0.00023 tnm: 0.23 Lm: 6.721 (6.753) Lt: 6.028 (6.059) Accm: 2.68 (2.69) Acct: 4.22 (4.23) proj_loss: -0.5438 (-0.5454) time: 0.9301 data: 0.0003 [11-23 08:01:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [1251/1669] eta: 0:06:39 tlr: 0.00023 tnm: 0.23 Lm: 6.669 (6.609) Lt: 5.885 (5.823) Accm: 3.12 (3.19) Acct: 5.13 (5.15) proj_loss: -0.5704 (-0.5561) time: 0.9301 data: 0.0003 [11-23 08:07:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.671 (6.633) Lt: 5.910 (5.849) Accm: 3.13 (3.24) Acct: 5.17 (5.28) proj_loss: -0.5698 (-0.5532) time: 0.9331 data: 0.0023 [11-23 08:07:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 35/350] Total time: 0:26:26 (0.950 s / it) [11-23 08:07:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.669 (6.624) Lt: 5.953 (5.856) Accm: 2.86 (3.26) Acct: 4.75 (5.33) proj_loss: -0.5436 (-0.5506) time: 0.9331 data: 0.0019 [11-23 08:07:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.728 (6.728) Lt: 6.043 (5.996) Accm: 2.70 (2.80) Acct: 4.44 (4.61) proj_loss: -0.5504 (-0.5535) time: 0.9331 data: 0.0015 [11-23 08:07:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.692 (6.679) Lt: 5.960 (5.910) Accm: 2.58 (2.83) Acct: 4.41 (4.52) proj_loss: -0.5428 (-0.5436) time: 0.9331 data: 0.0020 [11-23 08:07:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.623 (6.717) Lt: 5.959 (6.005) Accm: 2.71 (2.86) Acct: 4.27 (4.50) proj_loss: -0.5458 (-0.5471) time: 0.9331 data: 0.0018 [11-23 08:07:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.695 (6.686) Lt: 5.975 (5.954) Accm: 2.77 (2.76) Acct: 4.55 (4.37) proj_loss: -0.5655 (-0.5594) time: 0.9331 data: 0.0018 [11-23 08:07:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.712 (6.722) Lt: 5.992 (5.977) Accm: 2.87 (2.83) Acct: 4.51 (4.46) proj_loss: -0.5558 (-0.5513) time: 0.9331 data: 0.0018 [11-23 08:07:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 35/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.559 (6.595) Lt: 5.801 (5.843) Accm: 3.32 (3.28) Acct: 5.13 (5.04) proj_loss: -0.5584 (-0.5606) time: 0.9332 data: 0.0018 [11-23 08:07:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 35/350] Total time: 0:26:26 (0.950 s / it) [11-23 08:07:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 35/350] Total time: 0:26:26 (0.950 s / it) [11-23 08:07:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 35/350] Total time: 0:26:26 (0.950 s / it) [11-23 08:07:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 35/350] Total time: 0:26:26 (0.950 s / it) [11-23 08:07:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 35/350] Total time: 0:26:26 (0.950 s / it) [11-23 08:07:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 35/350] Total time: 0:26:26 (0.950 s / it) [11-23 08:07:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 35/350] Total time: 0:26:26 (0.950 s / it) [11-23 08:07:54] (/home/user/VAR/train.py , line 276)=> [ep35] (training ) Lm: 6.678 (6.678), Lt: 5.936 (5.936), Acc m&t: 2.94 4.66, Remain: 5 days, 16:54:07, Finish: 2024-11-28 09:02 [11-23 08:07:54] (/home/user/VAR/train.py , line 276)=> [ep35] (training ) Lm: 6.678 (6.678), Lt: 5.936 (5.936), Acc m&t: 2.94 4.66, Remain: 5 days, 16:53:25, Finish: 2024-11-28 09:01 [11-23 08:07:54] (/home/user/VAR/train.py , line 276)=> [ep35] (training ) Lm: 6.678 (6.678), Lt: 5.936 (5.936), Acc m&t: 2.94 4.66, Remain: 5 days, 16:53:33, Finish: 2024-11-28 09:01 [11-23 08:07:54] (/home/user/VAR/train.py , line 276)=> [ep35] (training ) Lm: 6.678 (6.678), Lt: 5.936 (5.936), Acc m&t: 2.94 4.66, Remain: 5 days, 16:54:07, Finish: 2024-11-28 09:02 [11-23 08:07:54] (/home/user/VAR/train.py , line 276)=> [ep35] (training ) Lm: 6.678 (6.678), Lt: 5.936 (5.936), Acc m&t: 2.94 4.66, Remain: 5 days, 16:53:42, Finish: 2024-11-28 09:01 [11-23 08:07:54] (/home/user/VAR/train.py , line 276)=> [ep35] (training ) Lm: 6.678 (6.678), Lt: 5.936 (5.936), Acc m&t: 2.94 4.66, Remain: 5 days, 16:53:17, Finish: 2024-11-28 09:01 [11-23 08:07:54] (/home/user/VAR/train.py , line 276)=> [ep35] (training ) Lm: 6.678 (6.678), Lt: 5.936 (5.936), Acc m&t: 2.94 4.66, Remain: 5 days, 16:52:52, Finish: 2024-11-28 09:00 [11-23 08:07:54] (/home/user/VAR/train.py , line 276)=> [ep35] (training ) Lm: 6.678 (6.678), Lt: 5.936 (5.936), Acc m&t: 2.94 4.66, Remain: 5 days, 16:54:16, Finish: 2024-11-28 09:02 [11-23 08:07:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 0/1669] eta: 0:24:41 tlr: 0.00023 tnm: 0.23 Lm: 6.475 (6.475) Lt: 5.702 (5.702) Accm: 3.15 (3.15) Acct: 5.03 (5.03) proj_loss: -0.5852 (-0.5852) time: 0.8879 data: 0.0003 [11-23 08:07:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 0/1669] eta: 0:24:35 tlr: 0.00023 tnm: 0.23 Lm: 6.832 (6.832) Lt: 6.108 (6.108) Accm: 2.64 (2.64) Acct: 4.17 (4.17) proj_loss: -0.5558 (-0.5558) time: 0.8840 data: 0.0004 [11-23 08:07:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 0/1669] eta: 0:24:42 tlr: 0.00023 tnm: 0.23 Lm: 6.556 (6.556) Lt: 5.800 (5.800) Accm: 3.15 (3.15) Acct: 4.75 (4.75) proj_loss: -0.5799 (-0.5799) time: 0.8882 data: 0.0004 [11-23 08:07:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 0/1669] eta: 0:24:41 tlr: 0.00023 tnm: 0.23 Lm: 6.401 (6.401) Lt: 5.570 (5.570) Accm: 4.14 (4.14) Acct: 6.68 (6.68) proj_loss: -0.5105 (-0.5105) time: 0.8879 data: 0.0004 [11-23 08:07:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 0/1669] eta: 0:24:42 tlr: 0.00023 tnm: 0.23 Lm: 6.871 (6.871) Lt: 6.085 (6.085) Accm: 2.42 (2.42) Acct: 3.82 (3.82) proj_loss: -0.5088 (-0.5088) time: 0.8880 data: 0.0004 [11-23 08:07:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 0/1669] eta: 0:24:42 tlr: 0.00023 tnm: 0.23 Lm: 6.628 (6.628) Lt: 5.864 (5.864) Accm: 3.19 (3.19) Acct: 5.03 (5.03) proj_loss: -0.5734 (-0.5734) time: 0.8884 data: 0.0004 [11-23 08:07:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 0/1669] eta: 0:24:33 tlr: 0.00023 tnm: 0.23 Lm: 6.723 (6.723) Lt: 6.012 (6.012) Accm: 2.64 (2.64) Acct: 4.41 (4.41) proj_loss: -0.5493 (-0.5493) time: 0.8831 data: 0.0003 [11-23 08:07:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 0/1669] eta: 0:24:41 tlr: 0.00023 tnm: 0.23 Lm: 6.757 (6.757) Lt: 6.103 (6.103) Accm: 2.35 (2.35) Acct: 3.41 (3.41) proj_loss: -0.5578 (-0.5578) time: 0.8876 data: 0.0004 [11-23 08:14:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.640 (6.640) Lt: 5.934 (5.934) Accm: 2.88 (2.88) Acct: 4.18 (4.18) proj_loss: -0.5509 (-0.5509) time: 0.9295 data: 0.0003 [11-23 08:14:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.582 (6.582) Lt: 5.830 (5.830) Accm: 2.94 (2.94) Acct: 4.60 (4.60) proj_loss: -0.5560 (-0.5560) time: 0.9295 data: 0.0003 [11-23 08:14:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.445 (6.445) Lt: 5.660 (5.660) Accm: 3.76 (3.76) Acct: 6.08 (6.08) proj_loss: -0.5345 (-0.5345) time: 0.9295 data: 0.0003 [11-23 08:14:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.715 (6.715) Lt: 5.967 (5.967) Accm: 3.12 (3.12) Acct: 4.87 (4.87) proj_loss: -0.5660 (-0.5660) time: 0.9295 data: 0.0003 [11-23 08:14:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.669 (6.669) Lt: 5.896 (5.896) Accm: 2.94 (2.94) Acct: 4.94 (4.94) proj_loss: -0.5432 (-0.5432) time: 0.9295 data: 0.0003 [11-23 08:14:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.677 (6.677) Lt: 5.953 (5.953) Accm: 2.79 (2.79) Acct: 4.51 (4.51) proj_loss: -0.5667 (-0.5667) time: 0.9295 data: 0.0003 [11-23 08:14:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.637 (6.637) Lt: 5.886 (5.886) Accm: 3.13 (3.13) Acct: 4.75 (4.75) proj_loss: -0.5571 (-0.5571) time: 0.9295 data: 0.0003 [11-23 08:14:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.493 (6.493) Lt: 5.702 (5.702) Accm: 3.29 (3.29) Acct: 5.17 (5.17) proj_loss: -0.5748 (-0.5748) time: 0.9295 data: 0.0002 [11-23 08:20:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.21 Lm: 6.475 (6.477) Lt: 5.701 (5.688) Accm: 3.42 (3.43) Acct: 5.30 (5.28) proj_loss: -0.5644 (-0.5648) time: 0.9281 data: 0.0002 [11-23 08:20:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.21 Lm: 6.489 (6.562) Lt: 5.750 (5.788) Accm: 3.38 (3.36) Acct: 5.48 (5.28) proj_loss: -0.5586 (-0.5458) time: 0.9281 data: 0.0003 [11-23 08:20:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.21 Lm: 6.676 (6.672) Lt: 5.925 (5.906) Accm: 2.94 (2.94) Acct: 4.86 (4.91) proj_loss: -0.5410 (-0.5425) time: 0.9281 data: 0.0003 [11-23 08:20:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.21 Lm: 6.608 (6.607) Lt: 5.859 (5.856) Accm: 2.99 (2.95) Acct: 4.75 (4.68) proj_loss: -0.5713 (-0.5611) time: 0.9281 data: 0.0003 [11-23 08:20:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.21 Lm: 6.646 (6.679) Lt: 5.909 (5.958) Accm: 3.07 (3.05) Acct: 4.75 (4.75) proj_loss: -0.5734 (-0.5742) time: 0.9281 data: 0.0003 [11-23 08:20:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.21 Lm: 6.632 (6.651) Lt: 5.894 (5.930) Accm: 2.94 (2.87) Acct: 4.61 (4.58) proj_loss: -0.5678 (-0.5671) time: 0.9281 data: 0.0003 [11-23 08:20:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.21 Lm: 6.757 (6.738) Lt: 6.103 (6.033) Accm: 2.35 (2.68) Acct: 3.89 (4.09) proj_loss: -0.5440 (-0.5465) time: 0.9281 data: 0.0003 [11-23 08:20:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.21 Lm: 6.599 (6.644) Lt: 5.825 (5.883) Accm: 3.29 (3.18) Acct: 5.58 (5.17) proj_loss: -0.5558 (-0.5554) time: 0.9281 data: 0.0003 [11-23 08:27:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.22 Lm: 6.658 (6.663) Lt: 5.883 (5.897) Accm: 3.10 (3.11) Acct: 5.30 (5.13) proj_loss: -0.5579 (-0.5565) time: 0.9264 data: 0.0003 [11-23 08:27:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.22 Lm: 6.572 (6.587) Lt: 5.816 (5.822) Accm: 3.20 (3.23) Acct: 5.46 (5.26) proj_loss: -0.5593 (-0.5528) time: 0.9264 data: 0.0003 [11-23 08:27:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.22 Lm: 6.493 (6.513) Lt: 5.702 (5.722) Accm: 3.44 (3.43) Acct: 5.25 (5.26) proj_loss: -0.5546 (-0.5580) time: 0.9264 data: 0.0002 [11-23 08:27:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.22 Lm: 6.637 (6.653) Lt: 5.886 (5.929) Accm: 3.13 (3.12) Acct: 4.89 (4.96) proj_loss: -0.5793 (-0.5770) time: 0.9264 data: 0.0003 [11-23 08:27:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.22 Lm: 6.640 (6.682) Lt: 5.934 (5.960) Accm: 2.66 (2.75) Acct: 4.42 (4.30) proj_loss: -0.5509 (-0.5512) time: 0.9264 data: 0.0003 [11-23 08:27:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.22 Lm: 6.632 (6.667) Lt: 5.885 (5.938) Accm: 2.86 (2.84) Acct: 4.60 (4.58) proj_loss: -0.5691 (-0.5626) time: 0.9264 data: 0.0003 [11-23 08:27:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.22 Lm: 6.677 (6.673) Lt: 5.929 (5.938) Accm: 2.85 (2.84) Acct: 4.67 (4.64) proj_loss: -0.5642 (-0.5654) time: 0.9264 data: 0.0003 [11-23 08:27:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.22 Lm: 6.478 (6.538) Lt: 5.725 (5.766) Accm: 3.61 (3.48) Acct: 5.73 (5.46) proj_loss: -0.5635 (-0.5520) time: 0.9264 data: 0.0003 [11-23 08:33:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.22 Lm: 6.489 (6.565) Lt: 5.750 (5.799) Accm: 3.38 (3.44) Acct: 5.48 (5.40) proj_loss: -0.5684 (-0.5579) time: 1.0608 data: 0.0016 [11-23 08:33:56] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 36/350] Total time: 0:26:02 (0.936 s / it) [11-23 08:33:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.22 Lm: 6.510 (6.548) Lt: 5.702 (5.787) Accm: 3.42 (3.32) Acct: 5.20 (5.08) proj_loss: -0.5644 (-0.5607) time: 1.0608 data: 0.0015 [11-23 08:33:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.22 Lm: 6.655 (6.692) Lt: 5.910 (5.968) Accm: 2.72 (2.74) Acct: 4.44 (4.43) proj_loss: -0.5669 (-0.5581) time: 1.0608 data: 0.0020 [11-23 08:33:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.22 Lm: 6.632 (6.636) Lt: 5.894 (5.886) Accm: 2.94 (2.96) Acct: 4.72 (4.85) proj_loss: -0.5606 (-0.5621) time: 1.0607 data: 0.0018 [11-23 08:33:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.22 Lm: 6.646 (6.654) Lt: 5.909 (5.931) Accm: 3.07 (3.04) Acct: 4.75 (4.79) proj_loss: -0.5734 (-0.5708) time: 1.0607 data: 0.0015 [11-23 08:33:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.22 Lm: 6.729 (6.691) Lt: 6.032 (5.974) Accm: 2.48 (2.70) Acct: 3.89 (4.21) proj_loss: -0.5501 (-0.5510) time: 1.0608 data: 0.0016 [11-23 08:33:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.22 Lm: 6.599 (6.644) Lt: 5.849 (5.887) Accm: 3.29 (3.15) Acct: 5.27 (5.16) proj_loss: -0.5558 (-0.5529) time: 1.0608 data: 0.0017 [11-23 08:33:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 36/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.22 Lm: 6.516 (6.573) Lt: 5.739 (5.805) Accm: 3.45 (3.28) Acct: 5.37 (5.28) proj_loss: -0.5715 (-0.5566) time: 1.0608 data: 0.0017 [11-23 08:33:56] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 36/350] Total time: 0:26:02 (0.936 s / it) [11-23 08:33:56] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 36/350] Total time: 0:26:02 (0.936 s / it) [11-23 08:33:56] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 36/350] Total time: 0:26:02 (0.936 s / it) [11-23 08:33:56] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 36/350] Total time: 0:26:02 (0.936 s / it) [11-23 08:33:56] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 36/350] Total time: 0:26:02 (0.936 s / it) [11-23 08:33:56] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 36/350] Total time: 0:26:02 (0.936 s / it) [11-23 08:33:56] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 36/350] Total time: 0:26:02 (0.936 s / it) [11-23 08:33:56] (/home/user/VAR/train.py , line 276)=> [ep36] (training ) Lm: 6.658 (6.658), Lt: 5.916 (5.916), Acc m&t: 2.97 4.69, Remain: 5 days, 15:45:03, Finish: 2024-11-28 08:18 [11-23 08:33:56] (/home/user/VAR/train.py , line 276)=> [ep36] (training ) Lm: 6.658 (6.658), Lt: 5.916 (5.916), Acc m&t: 2.97 4.69, Remain: 5 days, 15:48:46, Finish: 2024-11-28 08:22 [11-23 08:33:56] (/home/user/VAR/train.py , line 276)=> [ep36] (training ) Lm: 6.658 (6.658), Lt: 5.916 (5.916), Acc m&t: 2.97 4.69, Remain: 5 days, 15:47:17, Finish: 2024-11-28 08:21 [11-23 08:33:56] (/home/user/VAR/train.py , line 276)=> [ep36] (training ) Lm: 6.658 (6.658), Lt: 5.916 (5.916), Acc m&t: 2.97 4.69, Remain: 5 days, 15:48:48, Finish: 2024-11-28 08:22 [11-23 08:33:56] (/home/user/VAR/train.py , line 276)=> [ep36] (training ) Lm: 6.658 (6.658), Lt: 5.916 (5.916), Acc m&t: 2.97 4.69, Remain: 5 days, 15:44:49, Finish: 2024-11-28 08:18 [11-23 08:33:56] (/home/user/VAR/train.py , line 276)=> [ep36] (training ) Lm: 6.658 (6.658), Lt: 5.916 (5.916), Acc m&t: 2.97 4.69, Remain: 5 days, 15:45:38, Finish: 2024-11-28 08:19 [11-23 08:33:56] (/home/user/VAR/train.py , line 276)=> [ep36] (training ) Lm: 6.658 (6.658), Lt: 5.916 (5.916), Acc m&t: 2.97 4.69, Remain: 5 days, 15:49:26, Finish: 2024-11-28 08:23 [11-23 08:33:56] (/home/user/VAR/train.py , line 276)=> [ep36] (training ) Lm: 6.658 (6.658), Lt: 5.916 (5.916), Acc m&t: 2.97 4.69, Remain: 5 days, 15:49:59, Finish: 2024-11-28 08:23 [11-23 08:33:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 0/1669] eta: 0:25:06 tlr: 0.00023 tnm: 0.22 Lm: 6.503 (6.503) Lt: 5.690 (5.690) Accm: 3.58 (3.58) Acct: 5.54 (5.54) proj_loss: -0.5629 (-0.5629) time: 0.9026 data: 0.0004 [11-23 08:33:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 0/1669] eta: 0:25:09 tlr: 0.00023 tnm: 0.22 Lm: 6.917 (6.917) Lt: 6.326 (6.326) Accm: 2.13 (2.13) Acct: 3.27 (3.27) proj_loss: -0.5655 (-0.5655) time: 0.9042 data: 0.0004 [11-23 08:33:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 0/1669] eta: 0:25:30 tlr: 0.00023 tnm: 0.22 Lm: 6.395 (6.395) Lt: 5.565 (5.565) Accm: 3.74 (3.74) Acct: 5.75 (5.75) proj_loss: -0.5534 (-0.5534) time: 0.9172 data: 0.0004 [11-23 08:33:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 0/1669] eta: 0:25:59 tlr: 0.00023 tnm: 0.22 Lm: 6.619 (6.619) Lt: 5.815 (5.815) Accm: 2.78 (2.78) Acct: 4.58 (4.58) proj_loss: -0.5364 (-0.5364) time: 0.9346 data: 0.0003 [11-23 08:33:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 0/1669] eta: 0:25:09 tlr: 0.00023 tnm: 0.22 Lm: 6.922 (6.922) Lt: 6.165 (6.165) Accm: 2.23 (2.23) Acct: 3.75 (3.75) proj_loss: -0.5119 (-0.5119) time: 0.9042 data: 0.0005 [11-23 08:33:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 0/1669] eta: 0:25:28 tlr: 0.00023 tnm: 0.22 Lm: 6.673 (6.673) Lt: 5.956 (5.956) Accm: 2.64 (2.64) Acct: 4.24 (4.24) proj_loss: -0.5871 (-0.5871) time: 0.9157 data: 0.0004 [11-23 08:33:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 0/1669] eta: 0:25:28 tlr: 0.00023 tnm: 0.22 Lm: 6.755 (6.755) Lt: 6.023 (6.023) Accm: 2.36 (2.36) Acct: 3.93 (3.93) proj_loss: -0.5796 (-0.5796) time: 0.9157 data: 0.0004 [11-23 08:33:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 0/1669] eta: 0:25:11 tlr: 0.00023 tnm: 0.22 Lm: 6.604 (6.604) Lt: 5.872 (5.872) Accm: 3.13 (3.13) Acct: 5.10 (5.10) proj_loss: -0.6020 (-0.6020) time: 0.9054 data: 0.0004 [11-23 08:40:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 417/1669] eta: 0:19:42 tlr: 0.00023 tnm: 0.22 Lm: 6.665 (6.665) Lt: 5.975 (5.975) Accm: 2.94 (2.94) Acct: 4.65 (4.65) proj_loss: -0.6028 (-0.6028) time: 0.9309 data: 0.0003 [11-23 08:40:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 417/1669] eta: 0:19:42 tlr: 0.00023 tnm: 0.22 Lm: 6.426 (6.426) Lt: 5.619 (5.619) Accm: 3.62 (3.62) Acct: 5.75 (5.75) proj_loss: -0.5466 (-0.5466) time: 0.9309 data: 0.0003 [11-23 08:40:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 417/1669] eta: 0:19:42 tlr: 0.00023 tnm: 0.22 Lm: 6.756 (6.756) Lt: 5.993 (5.993) Accm: 2.71 (2.71) Acct: 4.39 (4.39) proj_loss: -0.5306 (-0.5306) time: 0.9309 data: 0.0003 [11-23 08:40:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 417/1669] eta: 0:19:42 tlr: 0.00023 tnm: 0.22 Lm: 6.628 (6.628) Lt: 5.889 (5.889) Accm: 2.91 (2.91) Acct: 4.70 (4.70) proj_loss: -0.5348 (-0.5348) time: 0.9309 data: 0.0003 [11-23 08:40:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 417/1669] eta: 0:19:42 tlr: 0.00023 tnm: 0.22 Lm: 6.758 (6.758) Lt: 6.065 (6.065) Accm: 2.67 (2.67) Acct: 4.36 (4.36) proj_loss: -0.5329 (-0.5329) time: 0.9309 data: 0.0003 [11-23 08:40:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 417/1669] eta: 0:19:42 tlr: 0.00023 tnm: 0.22 Lm: 6.688 (6.688) Lt: 5.914 (5.914) Accm: 2.86 (2.86) Acct: 4.46 (4.46) proj_loss: -0.5542 (-0.5542) time: 0.9309 data: 0.0003 [11-23 08:40:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 417/1669] eta: 0:19:42 tlr: 0.00023 tnm: 0.22 Lm: 6.572 (6.572) Lt: 5.859 (5.859) Accm: 2.86 (2.86) Acct: 4.46 (4.46) proj_loss: -0.5627 (-0.5627) time: 0.9309 data: 0.0003 [11-23 08:40:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 417/1669] eta: 0:19:42 tlr: 0.00023 tnm: 0.22 Lm: 6.641 (6.641) Lt: 5.891 (5.891) Accm: 2.80 (2.80) Acct: 4.39 (4.39) proj_loss: -0.5603 (-0.5603) time: 0.9309 data: 0.0003 [11-23 08:47:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 834/1669] eta: 0:13:24 tlr: 0.00023 tnm: 0.23 Lm: 6.622 (6.635) Lt: 5.870 (5.884) Accm: 2.96 (2.91) Acct: 4.55 (4.47) proj_loss: -0.5521 (-0.5576) time: 0.9299 data: 0.0003 [11-23 08:47:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 834/1669] eta: 0:13:24 tlr: 0.00023 tnm: 0.23 Lm: 6.456 (6.551) Lt: 5.674 (5.796) Accm: 3.50 (3.22) Acct: 5.75 (4.98) proj_loss: -0.5419 (-0.5450) time: 0.9299 data: 0.0003 [11-23 08:47:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 834/1669] eta: 0:13:24 tlr: 0.00023 tnm: 0.23 Lm: 6.604 (6.622) Lt: 5.872 (5.889) Accm: 3.13 (3.08) Acct: 5.10 (4.86) proj_loss: -0.6020 (-0.5839) time: 0.9299 data: 0.0003 [11-23 08:47:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 834/1669] eta: 0:13:24 tlr: 0.00023 tnm: 0.23 Lm: 6.590 (6.670) Lt: 5.821 (5.904) Accm: 3.19 (2.90) Acct: 5.03 (4.68) proj_loss: -0.5492 (-0.5407) time: 0.9299 data: 0.0003 [11-23 08:47:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 834/1669] eta: 0:13:24 tlr: 0.00023 tnm: 0.23 Lm: 6.636 (6.671) Lt: 5.889 (5.906) Accm: 2.97 (2.90) Acct: 4.79 (4.57) proj_loss: -0.5629 (-0.5589) time: 0.9299 data: 0.0003 [11-23 08:47:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 834/1669] eta: 0:13:24 tlr: 0.00023 tnm: 0.23 Lm: 6.755 (6.645) Lt: 6.023 (5.938) Accm: 2.58 (2.77) Acct: 4.06 (4.33) proj_loss: -0.5676 (-0.5643) time: 0.9298 data: 0.0003 [11-23 08:47:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 834/1669] eta: 0:13:24 tlr: 0.00023 tnm: 0.23 Lm: 6.836 (6.784) Lt: 6.159 (6.096) Accm: 2.55 (2.63) Acct: 3.41 (4.04) proj_loss: -0.5624 (-0.5427) time: 0.9299 data: 0.0003 [11-23 08:47:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [ 834/1669] eta: 0:13:24 tlr: 0.00023 tnm: 0.23 Lm: 6.619 (6.546) Lt: 5.815 (5.825) Accm: 3.04 (3.20) Acct: 4.82 (5.15) proj_loss: -0.5364 (-0.5455) time: 0.9299 data: 0.0003 [11-23 08:53:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [1251/1669] eta: 0:06:38 tlr: 0.00023 tnm: 0.21 Lm: 6.593 (6.551) Lt: 5.830 (5.830) Accm: 3.14 (3.21) Acct: 4.96 (5.14) proj_loss: -0.5390 (-0.5446) time: 0.9309 data: 0.0003 [11-23 08:53:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [1251/1669] eta: 0:06:38 tlr: 0.00023 tnm: 0.21 Lm: 6.735 (6.747) Lt: 6.008 (6.036) Accm: 2.88 (2.79) Acct: 4.29 (4.32) proj_loss: -0.5524 (-0.5426) time: 0.9309 data: 0.0002 [11-23 08:53:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [1251/1669] eta: 0:06:38 tlr: 0.00023 tnm: 0.21 Lm: 6.620 (6.631) Lt: 5.903 (5.897) Accm: 3.02 (2.95) Acct: 4.58 (4.50) proj_loss: -0.5566 (-0.5585) time: 0.9308 data: 0.0003 [11-23 08:53:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [1251/1669] eta: 0:06:38 tlr: 0.00023 tnm: 0.21 Lm: 6.761 (6.676) Lt: 6.053 (5.975) Accm: 2.63 (2.75) Acct: 4.34 (4.40) proj_loss: -0.5680 (-0.5653) time: 0.9309 data: 0.0003 [11-23 08:53:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [1251/1669] eta: 0:06:38 tlr: 0.00023 tnm: 0.21 Lm: 6.570 (6.629) Lt: 5.797 (5.855) Accm: 3.12 (2.99) Acct: 4.82 (4.64) proj_loss: -0.5557 (-0.5563) time: 0.9309 data: 0.0003 [11-23 08:53:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [1251/1669] eta: 0:06:38 tlr: 0.00023 tnm: 0.21 Lm: 6.666 (6.687) Lt: 5.918 (5.932) Accm: 3.01 (2.88) Acct: 4.58 (4.55) proj_loss: -0.5551 (-0.5480) time: 0.9309 data: 0.0003 [11-23 08:53:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [1251/1669] eta: 0:06:38 tlr: 0.00023 tnm: 0.21 Lm: 6.533 (6.565) Lt: 5.794 (5.825) Accm: 3.11 (3.10) Acct: 4.82 (4.71) proj_loss: -0.5477 (-0.5537) time: 0.9309 data: 0.0003 [11-23 08:53:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [1251/1669] eta: 0:06:38 tlr: 0.00023 tnm: 0.21 Lm: 6.658 (6.644) Lt: 5.927 (5.912) Accm: 3.09 (3.07) Acct: 4.89 (4.81) proj_loss: -0.5836 (-0.5792) time: 0.9309 data: 0.0003 [11-23 09:00:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.604 (6.611) Lt: 5.872 (5.869) Accm: 3.04 (3.06) Acct: 4.82 (4.81) proj_loss: -0.5879 (-0.5809) time: 0.9322 data: 0.0018 [11-23 09:00:17] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 37/350] Total time: 0:26:20 (0.947 s / it) [11-23 09:00:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.610 (6.627) Lt: 5.915 (5.890) Accm: 2.72 (2.95) Acct: 3.89 (4.52) proj_loss: -0.5534 (-0.5567) time: 0.9322 data: 0.0016 [11-23 09:00:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.741 (6.704) Lt: 6.016 (5.951) Accm: 3.09 (2.93) Acct: 4.68 (4.57) proj_loss: -0.5492 (-0.5428) time: 0.9322 data: 0.0016 [11-23 09:00:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.726 (6.743) Lt: 5.984 (6.026) Accm: 2.59 (2.75) Acct: 4.37 (4.33) proj_loss: -0.5624 (-0.5489) time: 0.9322 data: 0.0015 [11-23 09:00:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.622 (6.648) Lt: 5.935 (5.925) Accm: 2.96 (2.94) Acct: 4.55 (4.50) proj_loss: -0.5586 (-0.5585) time: 0.9322 data: 0.0018 [11-23 09:00:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.568 (6.547) Lt: 5.845 (5.834) Accm: 3.23 (3.21) Acct: 4.82 (5.01) proj_loss: -0.5416 (-0.5444) time: 0.9323 data: 0.0016 [11-23 09:00:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.755 (6.691) Lt: 6.079 (5.995) Accm: 2.68 (2.73) Acct: 4.17 (4.35) proj_loss: -0.5683 (-0.5666) time: 0.9323 data: 0.0016 [11-23 09:00:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 37/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.23 Lm: 6.636 (6.650) Lt: 5.889 (5.884) Accm: 2.97 (2.95) Acct: 4.79 (4.61) proj_loss: -0.5586 (-0.5567) time: 0.9323 data: 0.0021 [11-23 09:00:17] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 37/350] Total time: 0:26:20 (0.947 s / it) [11-23 09:00:17] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 37/350] Total time: 0:26:20 (0.947 s / it) [11-23 09:00:17] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 37/350] Total time: 0:26:20 (0.947 s / it) [11-23 09:00:17] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 37/350] Total time: 0:26:20 (0.947 s / it) [11-23 09:00:17] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 37/350] Total time: 0:26:20 (0.947 s / it) [11-23 09:00:17] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 37/350] Total time: 0:26:20 (0.947 s / it) [11-23 09:00:17] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 37/350] Total time: 0:26:20 (0.947 s / it) [11-23 09:00:17] (/home/user/VAR/train.py , line 276)=> [ep37] (training ) Lm: 6.653 (6.653), Lt: 5.916 (5.916), Acc m&t: 2.97 4.69, Remain: 5 days, 15:49:20, Finish: 2024-11-28 08:49 [11-23 09:00:17] (/home/user/VAR/train.py , line 276)=> [ep37] (training ) Lm: 6.653 (6.653), Lt: 5.916 (5.916), Acc m&t: 2.97 4.69, Remain: 5 days, 15:47:53, Finish: 2024-11-28 08:48 [11-23 09:00:17] (/home/user/VAR/train.py , line 276)=> [ep37] (training ) Lm: 6.653 (6.653), Lt: 5.916 (5.916), Acc m&t: 2.97 4.69, Remain: 5 days, 15:46:52, Finish: 2024-11-28 08:47 [11-23 09:00:17] (/home/user/VAR/train.py , line 276)=> [ep37] (training ) Lm: 6.653 (6.653), Lt: 5.916 (5.916), Acc m&t: 2.97 4.69, Remain: 5 days, 15:46:16, Finish: 2024-11-28 08:46 [11-23 09:00:17] (/home/user/VAR/train.py , line 276)=> [ep37] (training ) Lm: 6.653 (6.653), Lt: 5.916 (5.916), Acc m&t: 2.97 4.69, Remain: 5 days, 15:47:50, Finish: 2024-11-28 08:48 [11-23 09:00:17] (/home/user/VAR/train.py , line 276)=> [ep37] (training ) Lm: 6.653 (6.653), Lt: 5.916 (5.916), Acc m&t: 2.97 4.69, Remain: 5 days, 15:46:26, Finish: 2024-11-28 08:46 [11-23 09:00:17] (/home/user/VAR/train.py , line 276)=> [ep37] (training ) Lm: 6.653 (6.653), Lt: 5.916 (5.916), Acc m&t: 2.97 4.69, Remain: 5 days, 15:44:35, Finish: 2024-11-28 08:44 [11-23 09:00:17] (/home/user/VAR/train.py , line 276)=> [ep37] (training ) Lm: 6.653 (6.653), Lt: 5.916 (5.916), Acc m&t: 2.97 4.69, Remain: 5 days, 15:43:43, Finish: 2024-11-28 08:44 [11-23 09:00:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 0/1669] eta: 0:25:33 tlr: 0.00023 tnm: 0.24 Lm: 6.507 (6.507) Lt: 5.739 (5.739) Accm: 3.54 (3.54) Acct: 6.06 (6.06) proj_loss: -0.5462 (-0.5462) time: 0.9189 data: 0.0004 [11-23 09:00:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 0/1669] eta: 0:25:34 tlr: 0.00023 tnm: 0.24 Lm: 6.776 (6.776) Lt: 6.081 (6.081) Accm: 2.78 (2.78) Acct: 4.30 (4.30) proj_loss: -0.5754 (-0.5754) time: 0.9194 data: 0.0003 [11-23 09:00:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 0/1669] eta: 0:25:34 tlr: 0.00023 tnm: 0.24 Lm: 6.609 (6.609) Lt: 5.892 (5.892) Accm: 3.32 (3.32) Acct: 4.99 (4.99) proj_loss: -0.5590 (-0.5590) time: 0.9194 data: 0.0003 [11-23 09:00:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 0/1669] eta: 0:25:34 tlr: 0.00023 tnm: 0.24 Lm: 6.573 (6.573) Lt: 5.793 (5.793) Accm: 3.10 (3.10) Acct: 4.92 (4.92) proj_loss: -0.5466 (-0.5466) time: 0.9194 data: 0.0004 [11-23 09:00:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 0/1669] eta: 0:25:33 tlr: 0.00023 tnm: 0.24 Lm: 6.824 (6.824) Lt: 6.136 (6.136) Accm: 2.59 (2.59) Acct: 3.93 (3.93) proj_loss: -0.5754 (-0.5754) time: 0.9188 data: 0.0004 [11-23 09:00:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 0/1669] eta: 0:25:34 tlr: 0.00023 tnm: 0.24 Lm: 6.569 (6.569) Lt: 5.868 (5.868) Accm: 3.21 (3.21) Acct: 4.99 (4.99) proj_loss: -0.5576 (-0.5576) time: 0.9195 data: 0.0004 [11-23 09:00:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 0/1669] eta: 0:25:34 tlr: 0.00023 tnm: 0.24 Lm: 6.610 (6.610) Lt: 5.743 (5.743) Accm: 3.10 (3.10) Acct: 5.17 (5.17) proj_loss: -0.5520 (-0.5520) time: 0.9196 data: 0.0004 [11-23 09:00:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 0/1669] eta: 0:25:35 tlr: 0.00023 tnm: 0.24 Lm: 6.425 (6.425) Lt: 5.624 (5.624) Accm: 3.53 (3.53) Acct: 5.61 (5.61) proj_loss: -0.5295 (-0.5295) time: 0.9199 data: 0.0004 [11-23 09:06:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.570 (6.570) Lt: 5.789 (5.789) Accm: 3.32 (3.32) Acct: 5.35 (5.35) proj_loss: -0.5476 (-0.5476) time: 0.9298 data: 0.0003 [11-23 09:06:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.625 (6.625) Lt: 5.919 (5.919) Accm: 3.15 (3.15) Acct: 5.15 (5.15) proj_loss: -0.5530 (-0.5530) time: 0.9298 data: 0.0002 [11-23 09:06:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.632 (6.632) Lt: 5.866 (5.866) Accm: 3.25 (3.25) Acct: 5.04 (5.04) proj_loss: -0.5671 (-0.5671) time: 0.9298 data: 0.0003 [11-23 09:06:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.614 (6.614) Lt: 5.907 (5.907) Accm: 3.09 (3.09) Acct: 4.92 (4.92) proj_loss: -0.5688 (-0.5688) time: 0.9298 data: 0.0003 [11-23 09:06:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.711 (6.711) Lt: 5.994 (5.994) Accm: 2.87 (2.87) Acct: 4.49 (4.49) proj_loss: -0.5701 (-0.5701) time: 0.9298 data: 0.0003 [11-23 09:06:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.545 (6.545) Lt: 5.725 (5.725) Accm: 3.39 (3.39) Acct: 5.56 (5.56) proj_loss: -0.5564 (-0.5564) time: 0.9298 data: 0.0003 [11-23 09:06:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.726 (6.726) Lt: 6.003 (6.003) Accm: 2.91 (2.91) Acct: 4.49 (4.49) proj_loss: -0.5613 (-0.5613) time: 0.9298 data: 0.0003 [11-23 09:06:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.643 (6.643) Lt: 5.872 (5.872) Accm: 2.96 (2.96) Acct: 4.55 (4.55) proj_loss: -0.5410 (-0.5410) time: 0.9298 data: 0.0003 [11-23 09:13:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.22 Lm: 6.713 (6.676) Lt: 5.950 (5.936) Accm: 2.81 (2.81) Acct: 4.17 (4.36) proj_loss: -0.5466 (-0.5578) time: 0.9308 data: 0.0003 [11-23 09:13:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.22 Lm: 6.569 (6.611) Lt: 5.811 (5.848) Accm: 3.22 (3.24) Acct: 5.27 (5.12) proj_loss: -0.5588 (-0.5578) time: 0.9308 data: 0.0002 [11-23 09:13:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.22 Lm: 6.549 (6.563) Lt: 5.822 (5.800) Accm: 3.29 (3.31) Acct: 5.10 (5.26) proj_loss: -0.5547 (-0.5499) time: 0.9308 data: 0.0003 [11-23 09:13:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.22 Lm: 6.610 (6.575) Lt: 5.743 (5.764) Accm: 3.10 (3.28) Acct: 5.17 (5.35) proj_loss: -0.5536 (-0.5554) time: 0.9308 data: 0.0002 [11-23 09:13:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.22 Lm: 6.610 (6.620) Lt: 5.889 (5.909) Accm: 2.99 (3.10) Acct: 4.99 (5.10) proj_loss: -0.5599 (-0.5623) time: 0.9308 data: 0.0003 [11-23 09:13:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.22 Lm: 6.638 (6.697) Lt: 6.003 (6.003) Accm: 2.52 (2.78) Acct: 3.99 (4.25) proj_loss: -0.5637 (-0.5653) time: 0.9308 data: 0.0003 [11-23 09:13:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.22 Lm: 6.650 (6.626) Lt: 5.925 (5.913) Accm: 2.97 (3.01) Acct: 4.86 (4.73) proj_loss: -0.5735 (-0.5704) time: 0.9308 data: 0.0003 [11-23 09:13:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.22 Lm: 6.673 (6.698) Lt: 5.927 (5.972) Accm: 2.94 (2.89) Acct: 4.92 (4.64) proj_loss: -0.5665 (-0.5689) time: 0.9308 data: 0.0003 [11-23 09:20:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [1251/1669] eta: 0:06:36 tlr: 0.00023 tnm: 0.21 Lm: 6.721 (6.716) Lt: 5.964 (5.979) Accm: 2.79 (2.83) Acct: 4.53 (4.51) proj_loss: -0.5656 (-0.5594) time: 1.2308 data: 0.0003 [11-23 09:20:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [1251/1669] eta: 0:06:36 tlr: 0.00023 tnm: 0.21 Lm: 6.673 (6.682) Lt: 5.946 (5.930) Accm: 3.00 (3.10) Acct: 4.82 (4.93) proj_loss: -0.5574 (-0.5573) time: 1.2308 data: 0.0002 [11-23 09:20:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [1251/1669] eta: 0:06:36 tlr: 0.00023 tnm: 0.21 Lm: 6.677 (6.677) Lt: 5.994 (5.963) Accm: 2.88 (2.96) Acct: 4.61 (4.83) proj_loss: -0.5572 (-0.5604) time: 1.2308 data: 0.0002 [11-23 09:20:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [1251/1669] eta: 0:06:36 tlr: 0.00023 tnm: 0.21 Lm: 6.589 (6.579) Lt: 5.865 (5.827) Accm: 3.21 (3.18) Acct: 5.08 (5.07) proj_loss: -0.5602 (-0.5594) time: 1.2308 data: 0.0003 [11-23 09:20:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [1251/1669] eta: 0:06:36 tlr: 0.00023 tnm: 0.21 Lm: 6.654 (6.636) Lt: 5.904 (5.906) Accm: 2.91 (2.96) Acct: 4.77 (4.72) proj_loss: -0.5655 (-0.5639) time: 1.2308 data: 0.0003 [11-23 09:20:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [1251/1669] eta: 0:06:36 tlr: 0.00023 tnm: 0.21 Lm: 6.623 (6.598) Lt: 5.792 (5.808) Accm: 3.08 (3.19) Acct: 5.04 (5.23) proj_loss: -0.5572 (-0.5574) time: 1.2308 data: 0.0003 [11-23 09:20:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [1251/1669] eta: 0:06:36 tlr: 0.00023 tnm: 0.21 Lm: 6.740 (6.747) Lt: 6.059 (6.079) Accm: 2.51 (2.69) Acct: 3.89 (4.13) proj_loss: -0.5684 (-0.5694) time: 1.2308 data: 0.0003 [11-23 09:20:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [1251/1669] eta: 0:06:36 tlr: 0.00023 tnm: 0.21 Lm: 6.671 (6.664) Lt: 5.887 (5.908) Accm: 2.94 (2.88) Acct: 4.55 (4.55) proj_loss: -0.5541 (-0.5588) time: 1.2308 data: 0.0003 [11-23 09:26:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.25 Lm: 6.629 (6.646) Lt: 5.866 (5.900) Accm: 2.90 (2.88) Acct: 4.65 (4.57) proj_loss: -0.5617 (-0.5634) time: 0.9326 data: 0.0018 [11-23 09:26:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 38/350] Total time: 0:26:28 (0.952 s / it) [11-23 09:26:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.25 Lm: 6.743 (6.692) Lt: 5.980 (5.966) Accm: 2.77 (2.91) Acct: 4.55 (4.77) proj_loss: -0.5546 (-0.5559) time: 0.9326 data: 0.0018 [11-23 09:26:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.25 Lm: 6.650 (6.629) Lt: 5.884 (5.895) Accm: 2.97 (3.03) Acct: 4.86 (4.85) proj_loss: -0.5576 (-0.5578) time: 0.9326 data: 0.0015 [11-23 09:26:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.25 Lm: 6.769 (6.752) Lt: 6.000 (6.041) Accm: 2.64 (2.77) Acct: 4.13 (4.39) proj_loss: -0.5665 (-0.5639) time: 0.9326 data: 0.0016 [11-23 09:26:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.25 Lm: 6.569 (6.639) Lt: 5.811 (5.873) Accm: 3.22 (3.14) Acct: 5.27 (5.00) proj_loss: -0.5561 (-0.5562) time: 0.9326 data: 0.0020 [11-23 09:26:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.25 Lm: 6.636 (6.613) Lt: 5.840 (5.834) Accm: 3.06 (3.14) Acct: 4.92 (5.09) proj_loss: -0.5607 (-0.5592) time: 0.9326 data: 0.0021 [11-23 09:26:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.25 Lm: 6.629 (6.604) Lt: 5.909 (5.860) Accm: 3.12 (3.14) Acct: 5.06 (5.00) proj_loss: -0.5636 (-0.5603) time: 0.9326 data: 0.0020 [11-23 09:26:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 38/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.25 Lm: 6.638 (6.680) Lt: 6.003 (5.984) Accm: 2.52 (2.96) Acct: 3.99 (4.51) proj_loss: -0.5637 (-0.5672) time: 0.9326 data: 0.0018 [11-23 09:26:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 38/350] Total time: 0:26:28 (0.952 s / it) [11-23 09:26:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 38/350] Total time: 0:26:28 (0.952 s / it) [11-23 09:26:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 38/350] Total time: 0:26:28 (0.952 s / it) [11-23 09:26:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 38/350] Total time: 0:26:28 (0.952 s / it) [11-23 09:26:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 38/350] Total time: 0:26:28 (0.952 s / it) [11-23 09:26:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 38/350] Total time: 0:26:28 (0.952 s / it) [11-23 09:26:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 38/350] Total time: 0:26:28 (0.952 s / it) [11-23 09:26:46] (/home/user/VAR/train.py , line 276)=> [ep38] (training ) Lm: 6.653 (6.654), Lt: 5.913 (5.913), Acc m&t: 2.97 4.69, Remain: 5 days, 15:15:20, Finish: 2024-11-28 08:42 [11-23 09:26:46] (/home/user/VAR/train.py , line 276)=> [ep38] (training ) Lm: 6.653 (6.654), Lt: 5.913 (5.913), Acc m&t: 2.97 4.69, Remain: 5 days, 15:13:27, Finish: 2024-11-28 08:40 [11-23 09:26:46] (/home/user/VAR/train.py , line 276)=> [ep38] (training ) Lm: 6.653 (6.654), Lt: 5.913 (5.913), Acc m&t: 2.97 4.69, Remain: 5 days, 15:14:09, Finish: 2024-11-28 08:40 [11-23 09:26:46] (/home/user/VAR/train.py , line 276)=> [ep38] (training ) Lm: 6.653 (6.654), Lt: 5.913 (5.913), Acc m&t: 2.97 4.69, Remain: 5 days, 15:15:00, Finish: 2024-11-28 08:41 [11-23 09:26:46] (/home/user/VAR/train.py , line 276)=> [ep38] (training ) Lm: 6.653 (6.654), Lt: 5.913 (5.913), Acc m&t: 2.97 4.69, Remain: 5 days, 15:16:44, Finish: 2024-11-28 08:43 [11-23 09:26:46] (/home/user/VAR/train.py , line 276)=> [ep38] (training ) Lm: 6.653 (6.654), Lt: 5.913 (5.913), Acc m&t: 2.97 4.69, Remain: 5 days, 15:13:57, Finish: 2024-11-28 08:40 [11-23 09:26:46] (/home/user/VAR/train.py , line 276)=> [ep38] (training ) Lm: 6.653 (6.654), Lt: 5.913 (5.913), Acc m&t: 2.97 4.69, Remain: 5 days, 15:15:09, Finish: 2024-11-28 08:41 [11-23 09:26:46] (/home/user/VAR/train.py , line 276)=> [ep38] (training ) Lm: 6.653 (6.654), Lt: 5.913 (5.913), Acc m&t: 2.97 4.69, Remain: 5 days, 15:13:33, Finish: 2024-11-28 08:40 [11-23 09:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 0/1669] eta: 0:25:12 tlr: 0.00023 tnm: 0.21 Lm: 6.821 (6.821) Lt: 6.169 (6.169) Accm: 2.78 (2.78) Acct: 4.41 (4.41) proj_loss: -0.5503 (-0.5503) time: 0.9062 data: 0.0004 [11-23 09:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 0/1669] eta: 0:25:12 tlr: 0.00023 tnm: 0.21 Lm: 6.453 (6.453) Lt: 5.675 (5.675) Accm: 3.69 (3.69) Acct: 5.99 (5.99) proj_loss: -0.5525 (-0.5525) time: 0.9065 data: 0.0004 [11-23 09:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 0/1669] eta: 0:25:13 tlr: 0.00023 tnm: 0.21 Lm: 6.659 (6.659) Lt: 6.005 (6.005) Accm: 2.74 (2.74) Acct: 4.20 (4.20) proj_loss: -0.5646 (-0.5646) time: 0.9066 data: 0.0003 [11-23 09:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 0/1669] eta: 0:25:13 tlr: 0.00023 tnm: 0.21 Lm: 6.819 (6.819) Lt: 6.117 (6.117) Accm: 2.64 (2.64) Acct: 4.17 (4.17) proj_loss: -0.5603 (-0.5603) time: 0.9069 data: 0.0004 [11-23 09:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 0/1669] eta: 0:25:13 tlr: 0.00023 tnm: 0.21 Lm: 6.657 (6.657) Lt: 5.893 (5.893) Accm: 2.77 (2.77) Acct: 4.75 (4.75) proj_loss: -0.5798 (-0.5798) time: 0.9065 data: 0.0004 [11-23 09:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 0/1669] eta: 0:25:11 tlr: 0.00023 tnm: 0.21 Lm: 6.690 (6.690) Lt: 5.880 (5.880) Accm: 2.77 (2.77) Acct: 4.48 (4.48) proj_loss: -0.5672 (-0.5672) time: 0.9055 data: 0.0004 [11-23 09:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 0/1669] eta: 0:25:14 tlr: 0.00023 tnm: 0.21 Lm: 6.786 (6.786) Lt: 6.043 (6.043) Accm: 2.67 (2.67) Acct: 4.41 (4.41) proj_loss: -0.5497 (-0.5497) time: 0.9073 data: 0.0003 [11-23 09:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 0/1669] eta: 0:25:13 tlr: 0.00023 tnm: 0.21 Lm: 6.333 (6.333) Lt: 5.573 (5.573) Accm: 4.04 (4.04) Acct: 5.92 (5.92) proj_loss: -0.5815 (-0.5815) time: 0.9070 data: 0.0004 [11-23 09:33:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.561 (6.561) Lt: 5.840 (5.840) Accm: 3.42 (3.42) Acct: 5.15 (5.15) proj_loss: -0.5588 (-0.5588) time: 0.9306 data: 0.0003 [11-23 09:33:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.463 (6.463) Lt: 5.685 (5.685) Accm: 3.42 (3.42) Acct: 5.51 (5.51) proj_loss: -0.5651 (-0.5651) time: 0.9306 data: 0.0003 [11-23 09:33:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.787 (6.787) Lt: 6.062 (6.062) Accm: 2.92 (2.92) Acct: 4.91 (4.91) proj_loss: -0.5716 (-0.5716) time: 0.9306 data: 0.0003 [11-23 09:33:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.602 (6.602) Lt: 5.855 (5.855) Accm: 2.94 (2.94) Acct: 4.80 (4.80) proj_loss: -0.5722 (-0.5722) time: 0.9306 data: 0.0003 [11-23 09:33:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.789 (6.789) Lt: 6.043 (6.043) Accm: 2.80 (2.80) Acct: 4.65 (4.65) proj_loss: -0.5598 (-0.5598) time: 0.9306 data: 0.0003 [11-23 09:33:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.596 (6.596) Lt: 5.798 (5.798) Accm: 3.06 (3.06) Acct: 4.84 (4.84) proj_loss: -0.5620 (-0.5620) time: 0.9306 data: 0.0003 [11-23 09:33:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.558 (6.558) Lt: 5.858 (5.858) Accm: 3.29 (3.29) Acct: 5.15 (5.15) proj_loss: -0.5741 (-0.5741) time: 0.9306 data: 0.0003 [11-23 09:33:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 417/1669] eta: 0:19:24 tlr: 0.00023 tnm: 0.22 Lm: 6.688 (6.688) Lt: 5.911 (5.911) Accm: 2.86 (2.86) Acct: 4.68 (4.68) proj_loss: -0.5559 (-0.5559) time: 0.9306 data: 0.0003 [11-23 09:39:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.23 Lm: 6.786 (6.727) Lt: 6.043 (5.964) Accm: 2.86 (2.86) Acct: 4.72 (4.69) proj_loss: -0.5620 (-0.5588) time: 0.9311 data: 0.0003 [11-23 09:39:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.23 Lm: 6.657 (6.640) Lt: 5.893 (5.879) Accm: 2.77 (2.85) Acct: 4.75 (4.64) proj_loss: -0.5695 (-0.5713) time: 0.9311 data: 0.0003 [11-23 09:39:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.23 Lm: 6.760 (6.696) Lt: 5.969 (5.955) Accm: 2.97 (3.12) Acct: 5.13 (4.92) proj_loss: -0.5603 (-0.5679) time: 0.9311 data: 0.0003 [11-23 09:39:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.23 Lm: 6.754 (6.638) Lt: 5.956 (5.899) Accm: 3.06 (3.22) Acct: 5.41 (5.29) proj_loss: -0.5503 (-0.5642) time: 0.9311 data: 0.0003 [11-23 09:39:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.23 Lm: 6.502 (6.542) Lt: 5.716 (5.715) Accm: 3.35 (3.34) Acct: 5.20 (5.37) proj_loss: -0.5569 (-0.5563) time: 0.9311 data: 0.0003 [11-23 09:39:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.23 Lm: 6.474 (6.536) Lt: 5.695 (5.769) Accm: 3.15 (3.15) Acct: 5.03 (5.10) proj_loss: -0.5525 (-0.5517) time: 0.9311 data: 0.0002 [11-23 09:39:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.23 Lm: 6.585 (6.567) Lt: 5.819 (5.845) Accm: 3.69 (3.42) Acct: 5.99 (5.43) proj_loss: -0.5646 (-0.5667) time: 0.9311 data: 0.0003 [11-23 09:39:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.23 Lm: 6.560 (6.560) Lt: 5.875 (5.852) Accm: 3.03 (3.29) Acct: 4.92 (5.07) proj_loss: -0.5399 (-0.5525) time: 0.9311 data: 0.0003 [11-23 09:46:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.22 Lm: 6.666 (6.613) Lt: 5.955 (5.897) Accm: 2.91 (3.13) Acct: 4.65 (4.87) proj_loss: -0.5607 (-0.5602) time: 0.9307 data: 0.0003 [11-23 09:46:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.22 Lm: 6.734 (6.699) Lt: 5.961 (5.954) Accm: 2.91 (3.05) Acct: 4.77 (4.80) proj_loss: -0.5649 (-0.5683) time: 0.9307 data: 0.0003 [11-23 09:46:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.22 Lm: 6.577 (6.577) Lt: 5.816 (5.821) Accm: 2.96 (3.06) Acct: 4.65 (4.83) proj_loss: -0.5646 (-0.5580) time: 0.9307 data: 0.0003 [11-23 09:46:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.22 Lm: 6.789 (6.744) Lt: 6.056 (6.017) Accm: 2.76 (2.74) Acct: 4.56 (4.41) proj_loss: -0.5559 (-0.5547) time: 0.9307 data: 0.0003 [11-23 09:46:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.22 Lm: 6.762 (6.671) Lt: 6.025 (5.947) Accm: 2.92 (3.00) Acct: 4.91 (4.85) proj_loss: -0.5547 (-0.5629) time: 0.9307 data: 0.0003 [11-23 09:46:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.22 Lm: 6.686 (6.687) Lt: 5.910 (5.930) Accm: 2.72 (2.70) Acct: 4.53 (4.43) proj_loss: -0.5694 (-0.5708) time: 0.9307 data: 0.0003 [11-23 09:46:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.22 Lm: 6.554 (6.556) Lt: 5.772 (5.815) Accm: 3.44 (3.37) Acct: 5.53 (5.34) proj_loss: -0.5632 (-0.5655) time: 0.9307 data: 0.0003 [11-23 09:46:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [1251/1669] eta: 0:06:28 tlr: 0.00023 tnm: 0.22 Lm: 6.596 (6.640) Lt: 5.798 (5.848) Accm: 3.06 (3.07) Acct: 4.84 (4.98) proj_loss: -0.5509 (-0.5529) time: 0.9307 data: 0.0003 [11-23 09:52:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.690 (6.662) Lt: 5.880 (5.874) Accm: 3.10 (3.08) Acct: 4.65 (4.91) proj_loss: -0.5569 (-0.5568) time: 0.9310 data: 0.0016 [11-23 09:52:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 39/350] Total time: 0:25:52 (0.930 s / it) [11-23 09:52:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.525 (6.567) Lt: 5.751 (5.807) Accm: 3.15 (3.09) Acct: 4.65 (4.79) proj_loss: -0.5525 (-0.5545) time: 0.9310 data: 0.0020 [11-23 09:52:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.709 (6.663) Lt: 5.952 (5.906) Accm: 2.97 (3.11) Acct: 5.13 (4.94) proj_loss: -0.5603 (-0.5652) time: 0.9310 data: 0.0018 [11-23 09:52:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.585 (6.567) Lt: 5.819 (5.831) Accm: 3.19 (3.30) Acct: 5.06 (5.21) proj_loss: -0.5617 (-0.5604) time: 0.9310 data: 0.0016 [11-23 09:52:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.584 (6.608) Lt: 5.875 (5.863) Accm: 3.03 (3.15) Acct: 4.92 (4.94) proj_loss: -0.5515 (-0.5585) time: 0.9310 data: 0.0017 [11-23 09:52:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.793 (6.759) Lt: 6.066 (6.027) Accm: 2.67 (2.65) Acct: 4.41 (4.24) proj_loss: -0.5620 (-0.5602) time: 0.9310 data: 0.0022 [11-23 09:52:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.771 (6.723) Lt: 6.093 (6.022) Accm: 2.78 (2.81) Acct: 4.41 (4.51) proj_loss: -0.5503 (-0.5601) time: 0.9310 data: 0.0017 [11-23 09:52:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 39/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.715 (6.718) Lt: 5.927 (5.964) Accm: 2.67 (2.61) Acct: 4.30 (4.26) proj_loss: -0.5692 (-0.5683) time: 0.9310 data: 0.0016 [11-23 09:52:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 39/350] Total time: 0:25:52 (0.930 s / it) [11-23 09:52:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 39/350] Total time: 0:25:52 (0.930 s / it) [11-23 09:52:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 39/350] Total time: 0:25:52 (0.930 s / it) [11-23 09:52:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 39/350] Total time: 0:25:52 (0.930 s / it) [11-23 09:52:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 39/350] Total time: 0:25:52 (0.930 s / it) [11-23 09:52:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 39/350] Total time: 0:25:52 (0.930 s / it) [11-23 09:52:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 39/350] Total time: 0:25:52 (0.930 s / it) [11-23 09:54:47] (home/user/VAR/trainer.py, line 114)=> FID: 4.270040892360214 [11-23 09:54:48] (/home/user/VAR/train.py , line 259)=> [*] [ep39] (val 50000) Lm: 6.6504, Lt: 5.9049, Acc m&t: 2.98 4.72, Val cost: 129.06s [11-23 09:54:48] (/home/user/VAR/train.py , line 264)=> [saving ckpt] ... [saving ckpt](*) finished! @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth [11-23 09:56:02] (/home/user/VAR/train.py , line 276)=> [ep39] (training ) Lm: 6.650 (6.650), Lt: 5.905 (5.905), Acc m&t: 2.98 4.72, Remain: 5 days, 14:38:13, Finish: 2024-11-28 08:30 [11-23 09:56:02] (/home/user/VAR/train.py , line 276)=> [ep39] (training ) Lm: 6.650 (6.650), Lt: 5.905 (5.905), Acc m&t: 2.98 4.72, Remain: 5 days, 14:37:12, Finish: 2024-11-28 08:29 [11-23 09:56:02] (/home/user/VAR/train.py , line 276)=> [ep39] (training ) Lm: 6.650 (6.650), Lt: 5.905 (5.905), Acc m&t: 2.98 4.72, Remain: 5 days, 14:37:49, Finish: 2024-11-28 08:30 [11-23 09:56:02] (/home/user/VAR/train.py , line 276)=> [ep39] (training ) Lm: 6.650 (6.650), Lt: 5.905 (5.905), Acc m&t: 2.98 4.72, Remain: 5 days, 14:36:56, Finish: 2024-11-28 08:29 [11-23 09:56:02] (/home/user/VAR/train.py , line 276)=> [ep39] (training ) Lm: 6.650 (6.650), Lt: 5.905 (5.905), Acc m&t: 2.98 4.72, Remain: 5 days, 14:38:35, Finish: 2024-11-28 08:31 [11-23 09:56:02] (/home/user/VAR/train.py , line 276)=> [ep39] (training ) Lm: 6.650 (6.650), Lt: 5.905 (5.905), Acc m&t: 2.98 4.72, Remain: 5 days, 14:39:00, Finish: 2024-11-28 08:31 [11-23 09:56:02] (/home/user/VAR/train.py , line 276)=> [ep39] (training ) Lm: 6.650 (6.650), Lt: 5.905 (5.905), Acc m&t: 2.98 4.72, Remain: 5 days, 14:37:13, Finish: 2024-11-28 08:29 [11-23 09:56:02] (/home/user/VAR/train.py , line 276)=> [ep39] (training ) Lm: 6.650 (6.650), Lt: 5.905 (5.905), Acc m&t: 2.98 4.72, Remain: 5 days, 14:38:03, Finish: 2024-11-28 08:30 [11-23 09:56:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 0/1669] eta: 0:25:02 tlr: 0.00023 tnm: 0.24 Lm: 6.688 (6.688) Lt: 5.955 (5.955) Accm: 2.88 (2.88) Acct: 4.27 (4.27) proj_loss: -0.5792 (-0.5792) time: 0.9002 data: 0.0004 [11-23 09:56:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 0/1669] eta: 0:25:03 tlr: 0.00023 tnm: 0.24 Lm: 6.679 (6.679) Lt: 5.909 (5.909) Accm: 2.88 (2.88) Acct: 4.51 (4.51) proj_loss: -0.5230 (-0.5230) time: 0.9010 data: 0.0004 [11-23 09:56:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 0/1669] eta: 0:25:03 tlr: 0.00023 tnm: 0.24 Lm: 6.763 (6.763) Lt: 5.963 (5.963) Accm: 2.62 (2.62) Acct: 4.27 (4.27) proj_loss: -0.5548 (-0.5548) time: 0.9006 data: 0.0004 [11-23 09:56:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 0/1669] eta: 0:25:01 tlr: 0.00023 tnm: 0.24 Lm: 6.765 (6.765) Lt: 6.001 (6.001) Accm: 2.84 (2.84) Acct: 4.89 (4.89) proj_loss: -0.5455 (-0.5455) time: 0.8996 data: 0.0004 [11-23 09:56:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 0/1669] eta: 0:25:03 tlr: 0.00023 tnm: 0.24 Lm: 6.881 (6.881) Lt: 6.213 (6.213) Accm: 2.48 (2.48) Acct: 3.65 (3.65) proj_loss: -0.5584 (-0.5584) time: 0.9009 data: 0.0004 [11-23 09:56:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 0/1669] eta: 0:25:04 tlr: 0.00023 tnm: 0.24 Lm: 6.651 (6.651) Lt: 5.886 (5.886) Accm: 2.90 (2.90) Acct: 4.99 (4.99) proj_loss: -0.5477 (-0.5477) time: 0.9013 data: 0.0003 [11-23 09:56:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 0/1669] eta: 0:25:03 tlr: 0.00023 tnm: 0.24 Lm: 6.568 (6.568) Lt: 5.835 (5.835) Accm: 3.25 (3.25) Acct: 5.20 (5.20) proj_loss: -0.5732 (-0.5732) time: 0.9007 data: 0.0004 [11-23 09:56:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 0/1669] eta: 0:25:03 tlr: 0.00023 tnm: 0.24 Lm: 6.653 (6.653) Lt: 5.915 (5.915) Accm: 3.03 (3.03) Acct: 4.92 (4.92) proj_loss: -0.5392 (-0.5392) time: 0.9010 data: 0.0004 [11-23 10:02:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 417/1669] eta: 0:20:17 tlr: 0.00023 tnm: 0.21 Lm: 6.694 (6.694) Lt: 5.948 (5.948) Accm: 2.89 (2.89) Acct: 4.58 (4.58) proj_loss: -0.5478 (-0.5478) time: 0.9307 data: 0.0003 [11-23 10:02:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 417/1669] eta: 0:20:17 tlr: 0.00023 tnm: 0.21 Lm: 6.740 (6.740) Lt: 5.974 (5.974) Accm: 2.66 (2.66) Acct: 4.51 (4.51) proj_loss: -0.5724 (-0.5724) time: 0.9307 data: 0.0003 [11-23 10:02:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 417/1669] eta: 0:20:17 tlr: 0.00023 tnm: 0.21 Lm: 6.626 (6.626) Lt: 5.850 (5.850) Accm: 3.00 (3.00) Acct: 4.84 (4.84) proj_loss: -0.5361 (-0.5361) time: 0.9307 data: 0.0003 [11-23 10:02:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 417/1669] eta: 0:20:17 tlr: 0.00023 tnm: 0.21 Lm: 6.726 (6.726) Lt: 6.012 (6.012) Accm: 2.72 (2.72) Acct: 4.22 (4.22) proj_loss: -0.5686 (-0.5686) time: 0.9307 data: 0.0003 [11-23 10:02:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 417/1669] eta: 0:20:17 tlr: 0.00023 tnm: 0.21 Lm: 6.653 (6.653) Lt: 5.916 (5.916) Accm: 3.16 (3.16) Acct: 5.06 (5.06) proj_loss: -0.5669 (-0.5669) time: 0.9307 data: 0.0003 [11-23 10:02:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 417/1669] eta: 0:20:17 tlr: 0.00023 tnm: 0.21 Lm: 6.627 (6.627) Lt: 5.877 (5.877) Accm: 2.98 (2.98) Acct: 4.53 (4.53) proj_loss: -0.5735 (-0.5735) time: 0.9307 data: 0.0003 [11-23 10:02:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 417/1669] eta: 0:20:17 tlr: 0.00023 tnm: 0.21 Lm: 6.616 (6.616) Lt: 5.858 (5.858) Accm: 3.04 (3.04) Acct: 4.96 (4.96) proj_loss: -0.5532 (-0.5532) time: 0.9307 data: 0.0003 [11-23 10:02:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 417/1669] eta: 0:20:17 tlr: 0.00023 tnm: 0.21 Lm: 6.769 (6.769) Lt: 6.002 (6.002) Accm: 2.67 (2.67) Acct: 4.48 (4.48) proj_loss: -0.5545 (-0.5545) time: 0.9307 data: 0.0003 [11-23 10:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 834/1669] eta: 0:13:23 tlr: 0.00023 tnm: 0.22 Lm: 6.765 (6.739) Lt: 6.004 (6.003) Accm: 2.84 (2.74) Acct: 4.30 (4.42) proj_loss: -0.5600 (-0.5563) time: 1.0974 data: 0.0003 [11-23 10:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 834/1669] eta: 0:13:23 tlr: 0.00023 tnm: 0.22 Lm: 6.679 (6.679) Lt: 5.909 (5.920) Accm: 2.88 (2.93) Acct: 4.51 (4.61) proj_loss: -0.5493 (-0.5564) time: 1.0974 data: 0.0003 [11-23 10:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 834/1669] eta: 0:13:23 tlr: 0.00023 tnm: 0.22 Lm: 6.728 (6.678) Lt: 5.927 (5.920) Accm: 3.07 (3.09) Acct: 4.92 (4.91) proj_loss: -0.5607 (-0.5582) time: 1.0974 data: 0.0003 [11-23 10:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 834/1669] eta: 0:13:23 tlr: 0.00023 tnm: 0.22 Lm: 6.653 (6.638) Lt: 5.915 (5.900) Accm: 3.03 (3.16) Acct: 4.92 (4.96) proj_loss: -0.5564 (-0.5561) time: 1.0974 data: 0.0003 [11-23 10:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 834/1669] eta: 0:13:23 tlr: 0.00023 tnm: 0.22 Lm: 6.716 (6.670) Lt: 5.963 (5.904) Accm: 2.70 (2.85) Acct: 4.75 (4.66) proj_loss: -0.5548 (-0.5611) time: 1.0974 data: 0.0003 [11-23 10:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 834/1669] eta: 0:13:23 tlr: 0.00023 tnm: 0.22 Lm: 6.624 (6.619) Lt: 5.836 (5.851) Accm: 3.18 (3.08) Acct: 4.99 (5.08) proj_loss: -0.5588 (-0.5580) time: 1.0974 data: 0.0003 [11-23 10:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 834/1669] eta: 0:13:23 tlr: 0.00023 tnm: 0.22 Lm: 6.688 (6.677) Lt: 5.955 (5.904) Accm: 2.88 (2.87) Acct: 4.55 (4.53) proj_loss: -0.5677 (-0.5658) time: 1.0974 data: 0.0003 [11-23 10:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [ 834/1669] eta: 0:13:23 tlr: 0.00023 tnm: 0.22 Lm: 6.571 (6.589) Lt: 5.811 (5.833) Accm: 2.96 (3.13) Acct: 4.79 (4.82) proj_loss: -0.5764 (-0.5712) time: 1.0974 data: 0.0003 [11-23 10:16:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [1251/1669] eta: 0:06:42 tlr: 0.00023 tnm: 0.22 Lm: 6.611 (6.604) Lt: 5.874 (5.859) Accm: 2.86 (3.04) Acct: 4.65 (4.74) proj_loss: -0.5674 (-0.5680) time: 0.9308 data: 0.0003 [11-23 10:16:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [1251/1669] eta: 0:06:42 tlr: 0.00023 tnm: 0.22 Lm: 6.640 (6.660) Lt: 5.850 (5.879) Accm: 2.88 (2.92) Acct: 4.56 (4.61) proj_loss: -0.5635 (-0.5617) time: 0.9308 data: 0.0003 [11-23 10:16:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [1251/1669] eta: 0:06:42 tlr: 0.00023 tnm: 0.22 Lm: 6.696 (6.671) Lt: 5.950 (5.912) Accm: 2.88 (2.91) Acct: 4.80 (4.71) proj_loss: -0.5722 (-0.5683) time: 0.9307 data: 0.0003 [11-23 10:16:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [1251/1669] eta: 0:06:42 tlr: 0.00023 tnm: 0.22 Lm: 6.617 (6.624) Lt: 5.879 (5.886) Accm: 3.16 (3.19) Acct: 5.10 (5.04) proj_loss: -0.5645 (-0.5625) time: 0.9307 data: 0.0003 [11-23 10:16:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [1251/1669] eta: 0:06:42 tlr: 0.00023 tnm: 0.22 Lm: 6.627 (6.640) Lt: 5.877 (5.836) Accm: 2.98 (3.01) Acct: 4.67 (4.91) proj_loss: -0.5697 (-0.5673) time: 0.9308 data: 0.0003 [11-23 10:16:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [1251/1669] eta: 0:06:42 tlr: 0.00023 tnm: 0.22 Lm: 6.761 (6.744) Lt: 6.004 (6.005) Accm: 2.78 (2.74) Acct: 4.37 (4.42) proj_loss: -0.5618 (-0.5655) time: 0.9307 data: 0.0003 [11-23 10:16:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [1251/1669] eta: 0:06:42 tlr: 0.00023 tnm: 0.22 Lm: 6.648 (6.637) Lt: 5.881 (5.866) Accm: 3.16 (3.21) Acct: 5.06 (5.15) proj_loss: -0.5669 (-0.5679) time: 0.9307 data: 0.0003 [11-23 10:16:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [1251/1669] eta: 0:06:42 tlr: 0.00023 tnm: 0.22 Lm: 6.637 (6.637) Lt: 5.861 (5.897) Accm: 3.04 (3.00) Acct: 4.96 (4.83) proj_loss: -0.5631 (-0.5611) time: 0.9308 data: 0.0003 [11-23 10:22:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.651 (6.697) Lt: 5.886 (5.963) Accm: 2.90 (2.84) Acct: 4.92 (4.57) proj_loss: -0.5588 (-0.5598) time: 0.9317 data: 0.0019 [11-23 10:22:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 40/350] Total time: 0:26:34 (0.956 s / it) [11-23 10:22:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.651 (6.653) Lt: 5.937 (5.920) Accm: 2.77 (2.97) Acct: 4.51 (4.70) proj_loss: -0.5723 (-0.5689) time: 0.9317 data: 0.0019 [11-23 10:22:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.757 (6.702) Lt: 6.004 (5.960) Accm: 2.75 (2.74) Acct: 4.30 (4.36) proj_loss: -0.5635 (-0.5691) time: 0.9317 data: 0.0018 [11-23 10:22:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.676 (6.646) Lt: 5.938 (5.903) Accm: 3.02 (2.93) Acct: 4.86 (4.77) proj_loss: -0.5548 (-0.5635) time: 0.9317 data: 0.0017 [11-23 10:22:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.594 (6.631) Lt: 5.824 (5.834) Accm: 3.07 (3.02) Acct: 4.79 (4.98) proj_loss: -0.5716 (-0.5695) time: 0.9317 data: 0.0018 [11-23 10:22:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.679 (6.699) Lt: 5.909 (5.928) Accm: 2.88 (2.82) Acct: 4.51 (4.48) proj_loss: -0.5653 (-0.5624) time: 0.9317 data: 0.0021 [11-23 10:22:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.581 (6.591) Lt: 5.844 (5.854) Accm: 3.29 (3.28) Acct: 5.10 (5.05) proj_loss: -0.5580 (-0.5616) time: 0.9317 data: 0.0018 [11-23 10:22:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 40/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.570 (6.623) Lt: 5.835 (5.845) Accm: 3.25 (3.22) Acct: 5.20 (5.17) proj_loss: -0.5715 (-0.5686) time: 0.9317 data: 0.0021 [11-23 10:22:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 40/350] Total time: 0:26:34 (0.956 s / it) [11-23 10:22:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 40/350] Total time: 0:26:34 (0.956 s / it) [11-23 10:22:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 40/350] Total time: 0:26:34 (0.956 s / it) [11-23 10:22:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 40/350] Total time: 0:26:34 (0.956 s / it) [11-23 10:22:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 40/350] Total time: 0:26:34 (0.956 s / it) [11-23 10:22:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 40/350] Total time: 0:26:34 (0.956 s / it) [11-23 10:22:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 40/350] Total time: 0:26:34 (0.956 s / it) [11-23 10:22:37] (/home/user/VAR/train.py , line 276)=> [ep40] (training ) Lm: 6.650 (6.662), Lt: 5.905 (5.916), Acc m&t: 2.98 4.72, Remain: 5 days, 14:33:08, Finish: 2024-11-28 08:55 [11-23 10:22:37] (/home/user/VAR/train.py , line 276)=> [ep40] (training ) Lm: 6.650 (6.662), Lt: 5.905 (5.916), Acc m&t: 2.98 4.72, Remain: 5 days, 14:33:58, Finish: 2024-11-28 08:56 [11-23 10:22:37] (/home/user/VAR/train.py , line 276)=> [ep40] (training ) Lm: 6.650 (6.662), Lt: 5.905 (5.916), Acc m&t: 2.98 4.72, Remain: 5 days, 14:32:56, Finish: 2024-11-28 08:55 [11-23 10:22:37] (/home/user/VAR/train.py , line 276)=> [ep40] (training ) Lm: 6.650 (6.662), Lt: 5.905 (5.916), Acc m&t: 2.98 4.72, Remain: 5 days, 14:33:57, Finish: 2024-11-28 08:56 [11-23 10:22:37] (/home/user/VAR/train.py , line 276)=> [ep40] (training ) Lm: 6.650 (6.662), Lt: 5.905 (5.916), Acc m&t: 2.98 4.72, Remain: 5 days, 14:31:59, Finish: 2024-11-28 08:54 [11-23 10:22:37] (/home/user/VAR/train.py , line 276)=> [ep40] (training ) Lm: 6.650 (6.662), Lt: 5.905 (5.916), Acc m&t: 2.98 4.72, Remain: 5 days, 14:33:03, Finish: 2024-11-28 08:55 [11-23 10:22:37] (/home/user/VAR/train.py , line 276)=> [ep40] (training ) Lm: 6.650 (6.662), Lt: 5.905 (5.916), Acc m&t: 2.98 4.72, Remain: 5 days, 14:32:42, Finish: 2024-11-28 08:55 [11-23 10:22:37] (/home/user/VAR/train.py , line 276)=> [ep40] (training ) Lm: 6.650 (6.662), Lt: 5.905 (5.916), Acc m&t: 2.98 4.72, Remain: 5 days, 14:32:17, Finish: 2024-11-28 08:54 [11-23 10:22:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 0/1669] eta: 0:24:44 tlr: 0.00023 tnm: 0.22 Lm: 6.722 (6.722) Lt: 5.982 (5.982) Accm: 2.87 (2.87) Acct: 4.41 (4.41) proj_loss: -0.5392 (-0.5392) time: 0.8892 data: 0.0004 [11-23 10:22:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 0/1669] eta: 0:24:45 tlr: 0.00023 tnm: 0.22 Lm: 6.754 (6.754) Lt: 6.044 (6.044) Accm: 2.55 (2.55) Acct: 4.17 (4.17) proj_loss: -0.5828 (-0.5828) time: 0.8900 data: 0.0004 [11-23 10:22:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 0/1669] eta: 0:24:44 tlr: 0.00023 tnm: 0.22 Lm: 6.615 (6.615) Lt: 5.836 (5.836) Accm: 3.32 (3.32) Acct: 5.30 (5.30) proj_loss: -0.5421 (-0.5421) time: 0.8896 data: 0.0004 [11-23 10:22:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 0/1669] eta: 0:24:44 tlr: 0.00023 tnm: 0.22 Lm: 6.638 (6.638) Lt: 5.860 (5.860) Accm: 3.41 (3.41) Acct: 5.54 (5.54) proj_loss: -0.5765 (-0.5765) time: 0.8893 data: 0.0004 [11-23 10:22:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 0/1669] eta: 0:24:43 tlr: 0.00023 tnm: 0.22 Lm: 6.731 (6.731) Lt: 5.949 (5.949) Accm: 3.04 (3.04) Acct: 4.89 (4.89) proj_loss: -0.5629 (-0.5629) time: 0.8891 data: 0.0003 [11-23 10:22:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 0/1669] eta: 0:24:44 tlr: 0.00023 tnm: 0.22 Lm: 6.640 (6.640) Lt: 5.820 (5.820) Accm: 3.16 (3.16) Acct: 5.27 (5.27) proj_loss: -0.5292 (-0.5292) time: 0.8897 data: 0.0004 [11-23 10:22:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 0/1669] eta: 0:24:56 tlr: 0.00023 tnm: 0.22 Lm: 6.635 (6.635) Lt: 5.907 (5.907) Accm: 3.06 (3.06) Acct: 4.99 (4.99) proj_loss: -0.5473 (-0.5473) time: 0.8969 data: 0.0004 [11-23 10:22:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 0/1669] eta: 0:24:38 tlr: 0.00023 tnm: 0.22 Lm: 6.499 (6.499) Lt: 5.679 (5.679) Accm: 3.37 (3.37) Acct: 5.27 (5.27) proj_loss: -0.5585 (-0.5585) time: 0.8856 data: 0.0004 [11-23 10:29:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 417/1669] eta: 0:19:25 tlr: 0.00023 tnm: 0.21 Lm: 6.579 (6.579) Lt: 5.802 (5.802) Accm: 3.09 (3.09) Acct: 4.82 (4.82) proj_loss: -0.5549 (-0.5549) time: 0.9319 data: 0.0003 [11-23 10:29:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 417/1669] eta: 0:19:25 tlr: 0.00023 tnm: 0.21 Lm: 6.655 (6.655) Lt: 5.866 (5.866) Accm: 2.95 (2.95) Acct: 4.75 (4.75) proj_loss: -0.5356 (-0.5356) time: 0.9318 data: 0.0003 [11-23 10:29:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 417/1669] eta: 0:19:25 tlr: 0.00023 tnm: 0.21 Lm: 6.685 (6.685) Lt: 6.002 (6.002) Accm: 2.74 (2.74) Acct: 4.20 (4.20) proj_loss: -0.5818 (-0.5818) time: 0.9319 data: 0.0002 [11-23 10:29:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 417/1669] eta: 0:19:25 tlr: 0.00023 tnm: 0.21 Lm: 6.408 (6.408) Lt: 5.674 (5.674) Accm: 3.83 (3.83) Acct: 5.84 (5.84) proj_loss: -0.5813 (-0.5813) time: 0.9318 data: 0.0003 [11-23 10:29:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 417/1669] eta: 0:19:25 tlr: 0.00023 tnm: 0.21 Lm: 6.604 (6.604) Lt: 5.857 (5.857) Accm: 3.15 (3.15) Acct: 5.10 (5.10) proj_loss: -0.5440 (-0.5440) time: 0.9319 data: 0.0003 [11-23 10:29:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 417/1669] eta: 0:19:25 tlr: 0.00023 tnm: 0.21 Lm: 6.802 (6.802) Lt: 6.089 (6.089) Accm: 2.59 (2.59) Acct: 4.08 (4.08) proj_loss: -0.5395 (-0.5395) time: 0.9319 data: 0.0003 [11-23 10:29:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 417/1669] eta: 0:19:25 tlr: 0.00023 tnm: 0.21 Lm: 6.576 (6.576) Lt: 5.765 (5.765) Accm: 3.53 (3.53) Acct: 5.85 (5.85) proj_loss: -0.5622 (-0.5622) time: 0.9318 data: 0.0003 [11-23 10:29:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 417/1669] eta: 0:19:25 tlr: 0.00023 tnm: 0.21 Lm: 6.574 (6.574) Lt: 5.762 (5.762) Accm: 3.42 (3.42) Acct: 5.49 (5.49) proj_loss: -0.5348 (-0.5348) time: 0.9319 data: 0.0003 [11-23 10:35:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.21 Lm: 6.615 (6.622) Lt: 5.836 (5.856) Accm: 3.32 (3.11) Acct: 5.30 (5.08) proj_loss: -0.5421 (-0.5557) time: 0.9279 data: 0.0005 [11-23 10:35:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.21 Lm: 6.615 (6.644) Lt: 5.959 (5.929) Accm: 2.77 (2.75) Acct: 4.24 (4.32) proj_loss: -0.5808 (-0.5744) time: 0.9279 data: 0.0002 [11-23 10:35:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.21 Lm: 6.514 (6.544) Lt: 5.718 (5.749) Accm: 3.41 (3.45) Acct: 5.54 (5.53) proj_loss: -0.5576 (-0.5607) time: 0.9279 data: 0.0003 [11-23 10:35:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.21 Lm: 6.635 (6.630) Lt: 5.907 (5.902) Accm: 3.06 (2.84) Acct: 4.99 (4.49) proj_loss: -0.5473 (-0.5547) time: 0.9279 data: 0.0003 [11-23 10:35:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.21 Lm: 6.658 (6.664) Lt: 5.924 (5.907) Accm: 2.81 (2.84) Acct: 4.37 (4.44) proj_loss: -0.5585 (-0.5617) time: 0.9279 data: 0.0003 [11-23 10:35:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.21 Lm: 6.670 (6.737) Lt: 5.912 (5.979) Accm: 2.74 (2.84) Acct: 4.24 (4.49) proj_loss: -0.5419 (-0.5396) time: 0.9279 data: 0.0003 [11-23 10:35:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.21 Lm: 6.722 (6.719) Lt: 5.982 (5.977) Accm: 2.87 (2.86) Acct: 4.41 (4.64) proj_loss: -0.5398 (-0.5475) time: 0.9279 data: 0.0003 [11-23 10:35:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [ 834/1669] eta: 0:12:56 tlr: 0.00023 tnm: 0.21 Lm: 6.643 (6.486) Lt: 5.900 (5.749) Accm: 3.10 (3.59) Acct: 5.06 (5.58) proj_loss: -0.5629 (-0.5717) time: 0.9279 data: 0.0003 [11-23 10:42:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [1251/1669] eta: 0:06:29 tlr: 0.00023 tnm: 0.19 Lm: 6.683 (6.545) Lt: 5.925 (5.810) Accm: 3.07 (3.41) Acct: 4.98 (5.34) proj_loss: -0.5668 (-0.5715) time: 0.9303 data: 0.0003 [11-23 10:42:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [1251/1669] eta: 0:06:29 tlr: 0.00023 tnm: 0.19 Lm: 6.722 (6.746) Lt: 5.987 (6.000) Accm: 2.75 (2.82) Acct: 4.15 (4.38) proj_loss: -0.5448 (-0.5522) time: 0.9303 data: 0.0003 [11-23 10:42:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [1251/1669] eta: 0:06:29 tlr: 0.00023 tnm: 0.19 Lm: 6.651 (6.638) Lt: 5.863 (5.865) Accm: 3.24 (3.13) Acct: 5.35 (5.17) proj_loss: -0.5514 (-0.5570) time: 0.9303 data: 0.0003 [11-23 10:42:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [1251/1669] eta: 0:06:29 tlr: 0.00023 tnm: 0.19 Lm: 6.640 (6.679) Lt: 5.907 (5.941) Accm: 3.02 (2.94) Acct: 4.72 (4.73) proj_loss: -0.5517 (-0.5519) time: 0.9303 data: 0.0003 [11-23 10:42:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [1251/1669] eta: 0:06:29 tlr: 0.00023 tnm: 0.19 Lm: 6.746 (6.716) Lt: 6.021 (5.981) Accm: 2.66 (2.75) Acct: 4.03 (4.18) proj_loss: -0.5549 (-0.5581) time: 0.9303 data: 0.0003 [11-23 10:42:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [1251/1669] eta: 0:06:29 tlr: 0.00023 tnm: 0.19 Lm: 6.496 (6.517) Lt: 5.740 (5.752) Accm: 3.47 (3.47) Acct: 5.48 (5.50) proj_loss: -0.5671 (-0.5654) time: 0.9303 data: 0.0003 [11-23 10:42:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [1251/1669] eta: 0:06:29 tlr: 0.00023 tnm: 0.19 Lm: 6.589 (6.601) Lt: 5.872 (5.857) Accm: 2.85 (2.92) Acct: 4.39 (4.63) proj_loss: -0.5702 (-0.5693) time: 0.9303 data: 0.0003 [11-23 10:42:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [1251/1669] eta: 0:06:29 tlr: 0.00023 tnm: 0.19 Lm: 6.652 (6.640) Lt: 5.948 (5.928) Accm: 3.02 (2.88) Acct: 4.84 (4.54) proj_loss: -0.5494 (-0.5539) time: 0.9303 data: 0.0003 [11-23 10:49:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.670 (6.663) Lt: 5.990 (5.951) Accm: 2.99 (2.77) Acct: 4.68 (4.36) proj_loss: -0.5473 (-0.5497) time: 0.9333 data: 0.0020 [11-23 10:49:08] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 41/350] Total time: 0:26:30 (0.953 s / it) [11-23 10:49:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.615 (6.612) Lt: 5.815 (5.849) Accm: 2.84 (2.91) Acct: 4.55 (4.62) proj_loss: -0.5597 (-0.5671) time: 0.9333 data: 0.0021 [11-23 10:49:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.643 (6.530) Lt: 5.900 (5.797) Accm: 3.10 (3.39) Acct: 5.06 (5.31) proj_loss: -0.5679 (-0.5708) time: 0.9333 data: 0.0017 [11-23 10:49:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.773 (6.755) Lt: 6.063 (6.023) Accm: 2.74 (2.80) Acct: 4.24 (4.35) proj_loss: -0.5477 (-0.5573) time: 0.9333 data: 0.0016 [11-23 10:49:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.558 (6.640) Lt: 5.833 (5.894) Accm: 3.18 (3.04) Acct: 5.03 (4.86) proj_loss: -0.5577 (-0.5530) time: 0.9333 data: 0.0017 [11-23 10:49:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.658 (6.628) Lt: 5.924 (5.874) Accm: 2.81 (3.00) Acct: 4.37 (4.59) proj_loss: -0.5513 (-0.5557) time: 0.9332 data: 0.0018 [11-23 10:49:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.514 (6.531) Lt: 5.761 (5.757) Accm: 3.41 (3.42) Acct: 5.41 (5.43) proj_loss: -0.5576 (-0.5595) time: 0.9333 data: 0.0017 [11-23 10:49:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 41/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.615 (6.623) Lt: 5.836 (5.858) Accm: 3.21 (3.14) Acct: 5.30 (5.19) proj_loss: -0.5606 (-0.5604) time: 0.9333 data: 0.0019 [11-23 10:49:08] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 41/350] Total time: 0:26:30 (0.953 s / it) [11-23 10:49:08] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 41/350] Total time: 0:26:30 (0.953 s / it) [11-23 10:49:08] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 41/350] Total time: 0:26:30 (0.953 s / it) [11-23 10:49:08] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 41/350] Total time: 0:26:30 (0.953 s / it) [11-23 10:49:08] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 41/350] Total time: 0:26:30 (0.953 s / it) [11-23 10:49:08] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 41/350] Total time: 0:26:30 (0.953 s / it) [11-23 10:49:08] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 41/350] Total time: 0:26:30 (0.953 s / it) [11-23 10:49:08] (/home/user/VAR/train.py , line 276)=> [ep41] (training ) Lm: 6.649 (6.649), Lt: 5.902 (5.902), Acc m&t: 2.98 4.73, Remain: 5 days, 14:22:53, Finish: 2024-11-28 09:12 [11-23 10:49:08] (/home/user/VAR/train.py , line 276)=> [ep41] (training ) Lm: 6.649 (6.649), Lt: 5.902 (5.902), Acc m&t: 2.98 4.73, Remain: 5 days, 14:21:58, Finish: 2024-11-28 09:11 [11-23 10:49:08] (/home/user/VAR/train.py , line 276)=> [ep41] (training ) Lm: 6.649 (6.649), Lt: 5.902 (5.902), Acc m&t: 2.98 4.73, Remain: 5 days, 14:23:02, Finish: 2024-11-28 09:12 [11-23 10:49:08] (/home/user/VAR/train.py , line 276)=> [ep41] (training ) Lm: 6.649 (6.649), Lt: 5.902 (5.902), Acc m&t: 2.98 4.73, Remain: 5 days, 14:20:27, Finish: 2024-11-28 09:09 [11-23 10:49:08] (/home/user/VAR/train.py , line 276)=> [ep41] (training ) Lm: 6.649 (6.649), Lt: 5.902 (5.902), Acc m&t: 2.98 4.73, Remain: 5 days, 14:20:02, Finish: 2024-11-28 09:09 [11-23 10:49:08] (/home/user/VAR/train.py , line 276)=> [ep41] (training ) Lm: 6.649 (6.649), Lt: 5.902 (5.902), Acc m&t: 2.98 4.73, Remain: 5 days, 14:19:24, Finish: 2024-11-28 09:08 [11-23 10:49:08] (/home/user/VAR/train.py , line 276)=> [ep41] (training ) Lm: 6.649 (6.649), Lt: 5.902 (5.902), Acc m&t: 2.98 4.73, Remain: 5 days, 14:18:59, Finish: 2024-11-28 09:08 [11-23 10:49:08] (/home/user/VAR/train.py , line 276)=> [ep41] (training ) Lm: 6.649 (6.649), Lt: 5.902 (5.902), Acc m&t: 2.98 4.73, Remain: 5 days, 14:24:34, Finish: 2024-11-28 09:13 [11-23 10:49:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 0/1669] eta: 0:25:25 tlr: 0.00023 tnm: 0.21 Lm: 6.771 (6.771) Lt: 6.066 (6.066) Accm: 2.91 (2.91) Acct: 4.37 (4.37) proj_loss: -0.5811 (-0.5811) time: 0.9138 data: 0.0004 [11-23 10:49:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 0/1669] eta: 0:25:24 tlr: 0.00023 tnm: 0.21 Lm: 6.776 (6.776) Lt: 5.981 (5.981) Accm: 2.53 (2.53) Acct: 4.65 (4.65) proj_loss: -0.5283 (-0.5283) time: 0.9137 data: 0.0004 [11-23 10:49:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 0/1669] eta: 0:25:24 tlr: 0.00023 tnm: 0.21 Lm: 6.323 (6.323) Lt: 5.523 (5.523) Accm: 4.09 (4.09) Acct: 6.20 (6.20) proj_loss: -0.5373 (-0.5373) time: 0.9133 data: 0.0003 [11-23 10:49:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 0/1669] eta: 0:25:25 tlr: 0.00023 tnm: 0.21 Lm: 6.761 (6.761) Lt: 6.018 (6.018) Accm: 2.91 (2.91) Acct: 4.79 (4.79) proj_loss: -0.5600 (-0.5600) time: 0.9141 data: 0.0004 [11-23 10:49:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 0/1669] eta: 0:25:23 tlr: 0.00023 tnm: 0.21 Lm: 6.602 (6.602) Lt: 5.900 (5.900) Accm: 3.19 (3.19) Acct: 4.92 (4.92) proj_loss: -0.5850 (-0.5850) time: 0.9131 data: 0.0004 [11-23 10:49:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 0/1669] eta: 0:25:24 tlr: 0.00023 tnm: 0.21 Lm: 6.515 (6.515) Lt: 5.699 (5.699) Accm: 3.26 (3.26) Acct: 5.44 (5.44) proj_loss: -0.5484 (-0.5484) time: 0.9133 data: 0.0004 [11-23 10:49:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 0/1669] eta: 0:25:42 tlr: 0.00023 tnm: 0.21 Lm: 6.390 (6.390) Lt: 5.733 (5.733) Accm: 3.61 (3.61) Acct: 5.27 (5.27) proj_loss: -0.5596 (-0.5596) time: 0.9243 data: 0.0004 [11-23 10:49:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 0/1669] eta: 0:25:24 tlr: 0.00023 tnm: 0.21 Lm: 6.689 (6.689) Lt: 6.022 (6.022) Accm: 2.65 (2.65) Acct: 3.99 (3.99) proj_loss: -0.5809 (-0.5809) time: 0.9135 data: 0.0004 [11-23 10:55:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 417/1669] eta: 0:19:29 tlr: 0.00023 tnm: 0.23 Lm: 6.646 (6.646) Lt: 5.906 (5.906) Accm: 3.02 (3.02) Acct: 4.75 (4.75) proj_loss: -0.5674 (-0.5674) time: 0.9319 data: 0.0003 [11-23 10:55:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 417/1669] eta: 0:19:29 tlr: 0.00023 tnm: 0.23 Lm: 6.746 (6.746) Lt: 5.951 (5.951) Accm: 2.65 (2.65) Acct: 4.61 (4.61) proj_loss: -0.5448 (-0.5448) time: 0.9319 data: 0.0003 [11-23 10:55:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 417/1669] eta: 0:19:29 tlr: 0.00023 tnm: 0.23 Lm: 6.796 (6.796) Lt: 6.061 (6.061) Accm: 2.75 (2.75) Acct: 4.36 (4.36) proj_loss: -0.5734 (-0.5734) time: 0.9319 data: 0.0003 [11-23 10:55:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 417/1669] eta: 0:19:29 tlr: 0.00023 tnm: 0.23 Lm: 6.694 (6.694) Lt: 5.953 (5.953) Accm: 3.04 (3.04) Acct: 4.79 (4.79) proj_loss: -0.5499 (-0.5499) time: 0.9319 data: 0.0003 [11-23 10:55:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 417/1669] eta: 0:19:29 tlr: 0.00023 tnm: 0.23 Lm: 6.569 (6.569) Lt: 5.788 (5.788) Accm: 3.30 (3.30) Acct: 5.13 (5.13) proj_loss: -0.5505 (-0.5505) time: 0.9319 data: 0.0003 [11-23 10:55:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 417/1669] eta: 0:19:29 tlr: 0.00023 tnm: 0.23 Lm: 6.580 (6.580) Lt: 5.868 (5.868) Accm: 3.13 (3.13) Acct: 4.80 (4.80) proj_loss: -0.5623 (-0.5623) time: 0.9319 data: 0.0002 [11-23 10:55:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 417/1669] eta: 0:19:29 tlr: 0.00023 tnm: 0.23 Lm: 6.551 (6.551) Lt: 5.855 (5.855) Accm: 3.26 (3.26) Acct: 5.18 (5.18) proj_loss: -0.5551 (-0.5551) time: 0.9319 data: 0.0003 [11-23 10:55:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 417/1669] eta: 0:19:29 tlr: 0.00023 tnm: 0.23 Lm: 6.680 (6.680) Lt: 5.956 (5.956) Accm: 3.10 (3.10) Acct: 4.86 (4.86) proj_loss: -0.5510 (-0.5510) time: 0.9319 data: 0.0003 [11-23 11:02:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 834/1669] eta: 0:12:58 tlr: 0.00023 tnm: 0.23 Lm: 6.515 (6.607) Lt: 5.727 (5.880) Accm: 3.26 (3.24) Acct: 5.44 (5.20) proj_loss: -0.5537 (-0.5535) time: 0.9312 data: 0.0003 [11-23 11:02:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 834/1669] eta: 0:12:58 tlr: 0.00023 tnm: 0.23 Lm: 6.558 (6.553) Lt: 5.835 (5.830) Accm: 3.19 (3.20) Acct: 4.92 (4.87) proj_loss: -0.5613 (-0.5620) time: 0.9311 data: 0.0002 [11-23 11:02:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 834/1669] eta: 0:12:58 tlr: 0.00023 tnm: 0.23 Lm: 6.724 (6.704) Lt: 5.947 (5.951) Accm: 2.93 (3.01) Acct: 4.79 (4.75) proj_loss: -0.5511 (-0.5503) time: 0.9311 data: 0.0003 [11-23 11:02:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 834/1669] eta: 0:12:58 tlr: 0.00023 tnm: 0.23 Lm: 6.774 (6.755) Lt: 5.981 (5.979) Accm: 2.53 (2.61) Acct: 4.58 (4.41) proj_loss: -0.5410 (-0.5436) time: 0.9312 data: 0.0003 [11-23 11:02:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 834/1669] eta: 0:12:58 tlr: 0.00023 tnm: 0.23 Lm: 6.601 (6.580) Lt: 5.828 (5.802) Accm: 3.10 (3.23) Acct: 5.20 (5.15) proj_loss: -0.5517 (-0.5509) time: 0.9311 data: 0.0003 [11-23 11:02:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 834/1669] eta: 0:12:58 tlr: 0.00023 tnm: 0.23 Lm: 6.639 (6.581) Lt: 5.833 (5.848) Accm: 3.09 (3.20) Acct: 5.10 (5.04) proj_loss: -0.5505 (-0.5450) time: 0.9311 data: 0.0003 [11-23 11:02:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 834/1669] eta: 0:12:58 tlr: 0.00023 tnm: 0.23 Lm: 6.771 (6.783) Lt: 6.055 (6.041) Accm: 2.59 (2.70) Acct: 4.34 (4.22) proj_loss: -0.5657 (-0.5670) time: 0.9312 data: 0.0003 [11-23 11:02:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [ 834/1669] eta: 0:12:58 tlr: 0.00023 tnm: 0.23 Lm: 6.689 (6.710) Lt: 6.022 (5.958) Accm: 2.91 (2.99) Acct: 4.68 (4.73) proj_loss: -0.5805 (-0.5718) time: 0.9312 data: 0.0003 [11-23 11:08:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [1251/1669] eta: 0:06:29 tlr: 0.00023 tnm: 0.21 Lm: 6.646 (6.673) Lt: 5.906 (5.911) Accm: 3.10 (3.06) Acct: 5.10 (4.92) proj_loss: -0.5775 (-0.5724) time: 0.9296 data: 0.0003 [11-23 11:08:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [1251/1669] eta: 0:06:29 tlr: 0.00023 tnm: 0.21 Lm: 6.580 (6.590) Lt: 5.868 (5.862) Accm: 3.13 (3.11) Acct: 4.86 (4.85) proj_loss: -0.5504 (-0.5521) time: 0.9296 data: 0.0003 [11-23 11:08:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [1251/1669] eta: 0:06:29 tlr: 0.00023 tnm: 0.21 Lm: 6.745 (6.684) Lt: 5.951 (5.929) Accm: 2.65 (2.80) Acct: 4.61 (4.63) proj_loss: -0.5512 (-0.5536) time: 0.9296 data: 0.0002 [11-23 11:08:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [1251/1669] eta: 0:06:29 tlr: 0.00023 tnm: 0.21 Lm: 6.594 (6.581) Lt: 5.843 (5.816) Accm: 2.99 (3.15) Acct: 4.86 (4.99) proj_loss: -0.5577 (-0.5542) time: 0.9296 data: 0.0003 [11-23 11:08:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [1251/1669] eta: 0:06:29 tlr: 0.00023 tnm: 0.21 Lm: 6.676 (6.661) Lt: 5.918 (5.890) Accm: 3.05 (3.11) Acct: 4.79 (4.98) proj_loss: -0.5555 (-0.5571) time: 0.9296 data: 0.0003 [11-23 11:08:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [1251/1669] eta: 0:06:29 tlr: 0.00023 tnm: 0.21 Lm: 6.764 (6.775) Lt: 6.029 (6.012) Accm: 2.75 (2.76) Acct: 4.36 (4.41) proj_loss: -0.5622 (-0.5649) time: 0.9296 data: 0.0003 [11-23 11:08:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [1251/1669] eta: 0:06:29 tlr: 0.00023 tnm: 0.21 Lm: 6.676 (6.632) Lt: 5.905 (5.898) Accm: 2.99 (3.01) Acct: 4.92 (4.72) proj_loss: -0.5463 (-0.5443) time: 0.9296 data: 0.0003 [11-23 11:08:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [1251/1669] eta: 0:06:29 tlr: 0.00023 tnm: 0.21 Lm: 6.629 (6.641) Lt: 5.903 (5.929) Accm: 3.10 (3.15) Acct: 5.03 (5.05) proj_loss: -0.5561 (-0.5602) time: 0.9296 data: 0.0003 [11-23 11:15:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.610 (6.635) Lt: 5.912 (5.926) Accm: 2.94 (3.11) Acct: 4.61 (4.94) proj_loss: -0.5585 (-0.5716) time: 0.9318 data: 0.0019 [11-23 11:15:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 42/350] Total time: 0:25:54 (0.932 s / it) [11-23 11:15:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.716 (6.652) Lt: 5.922 (5.898) Accm: 2.77 (2.88) Acct: 4.65 (4.74) proj_loss: -0.5614 (-0.5572) time: 0.9318 data: 0.0019 [11-23 11:15:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.558 (6.582) Lt: 5.900 (5.873) Accm: 3.07 (3.10) Acct: 4.79 (4.75) proj_loss: -0.5613 (-0.5600) time: 0.9318 data: 0.0016 [11-23 11:15:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.771 (6.791) Lt: 6.055 (6.036) Accm: 2.59 (2.70) Acct: 4.34 (4.28) proj_loss: -0.5629 (-0.5645) time: 0.9318 data: 0.0021 [11-23 11:15:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.627 (6.653) Lt: 5.888 (5.882) Accm: 3.18 (3.18) Acct: 4.79 (5.05) proj_loss: -0.5600 (-0.5591) time: 0.9318 data: 0.0016 [11-23 11:15:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.639 (6.607) Lt: 5.833 (5.870) Accm: 3.09 (3.04) Acct: 4.96 (4.77) proj_loss: -0.5505 (-0.5499) time: 0.9318 data: 0.0016 [11-23 11:15:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.623 (6.663) Lt: 5.850 (5.899) Accm: 3.09 (3.07) Acct: 4.79 (4.90) proj_loss: -0.5805 (-0.5744) time: 0.9318 data: 0.0017 [11-23 11:15:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 42/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.601 (6.612) Lt: 5.858 (5.837) Accm: 2.90 (3.10) Acct: 4.86 (4.97) proj_loss: -0.5636 (-0.5593) time: 0.9318 data: 0.0018 [11-23 11:15:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 42/350] Total time: 0:25:54 (0.932 s / it) [11-23 11:15:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 42/350] Total time: 0:25:54 (0.932 s / it) [11-23 11:15:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 42/350] Total time: 0:25:54 (0.932 s / it) [11-23 11:15:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 42/350] Total time: 0:25:54 (0.932 s / it) [11-23 11:15:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 42/350] Total time: 0:25:54 (0.932 s / it) [11-23 11:15:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 42/350] Total time: 0:25:54 (0.932 s / it) [11-23 11:15:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 42/350] Total time: 0:25:54 (0.932 s / it) [11-23 11:15:03] (/home/user/VAR/train.py , line 276)=> [ep42] (training ) Lm: 6.649 (6.649), Lt: 5.902 (5.906), Acc m&t: 2.99 4.73, Remain: 5 days, 13:36:49, Finish: 2024-11-28 08:51 [11-23 11:15:03] (/home/user/VAR/train.py , line 276)=> [ep42] (training ) Lm: 6.649 (6.649), Lt: 5.902 (5.906), Acc m&t: 2.99 4.73, Remain: 5 days, 13:36:04, Finish: 2024-11-28 08:51 [11-23 11:15:03] (/home/user/VAR/train.py , line 276)=> [ep42] (training ) Lm: 6.649 (6.649), Lt: 5.902 (5.906), Acc m&t: 2.99 4.73, Remain: 5 days, 13:34:00, Finish: 2024-11-28 08:49 [11-23 11:15:03] (/home/user/VAR/train.py , line 276)=> [ep42] (training ) Lm: 6.649 (6.649), Lt: 5.902 (5.906), Acc m&t: 2.99 4.73, Remain: 5 days, 13:39:07, Finish: 2024-11-28 08:54 [11-23 11:15:03] (/home/user/VAR/train.py , line 276)=> [ep42] (training ) Lm: 6.649 (6.649), Lt: 5.902 (5.906), Acc m&t: 2.99 4.73, Remain: 5 days, 13:38:17, Finish: 2024-11-28 08:53 [11-23 11:15:03] (/home/user/VAR/train.py , line 276)=> [ep42] (training ) Lm: 6.649 (6.649), Lt: 5.902 (5.906), Acc m&t: 2.99 4.73, Remain: 5 days, 13:36:30, Finish: 2024-11-28 08:51 [11-23 11:15:03] (/home/user/VAR/train.py , line 276)=> [ep42] (training ) Lm: 6.649 (6.649), Lt: 5.902 (5.906), Acc m&t: 2.99 4.73, Remain: 5 days, 13:35:22, Finish: 2024-11-28 08:50 [11-23 11:15:03] (/home/user/VAR/train.py , line 276)=> [ep42] (training ) Lm: 6.649 (6.649), Lt: 5.902 (5.906), Acc m&t: 2.99 4.73, Remain: 5 days, 13:37:09, Finish: 2024-11-28 08:52 [11-23 11:15:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 0/1669] eta: 0:24:45 tlr: 0.00023 tnm: 0.20 Lm: 6.513 (6.513) Lt: 5.696 (5.696) Accm: 3.50 (3.50) Acct: 5.79 (5.79) proj_loss: -0.5672 (-0.5672) time: 0.8899 data: 0.0003 [11-23 11:15:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 0/1669] eta: 0:24:45 tlr: 0.00023 tnm: 0.20 Lm: 6.713 (6.713) Lt: 6.033 (6.033) Accm: 3.29 (3.29) Acct: 4.89 (4.89) proj_loss: -0.6033 (-0.6033) time: 0.8901 data: 0.0003 [11-23 11:15:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 0/1669] eta: 0:24:45 tlr: 0.00023 tnm: 0.20 Lm: 6.829 (6.829) Lt: 6.128 (6.128) Accm: 2.61 (2.61) Acct: 3.96 (3.96) proj_loss: -0.5547 (-0.5547) time: 0.8902 data: 0.0004 [11-23 11:15:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 0/1669] eta: 0:24:45 tlr: 0.00023 tnm: 0.20 Lm: 6.995 (6.995) Lt: 6.315 (6.315) Accm: 2.24 (2.24) Acct: 3.51 (3.51) proj_loss: -0.6019 (-0.6019) time: 0.8903 data: 0.0004 [11-23 11:15:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 0/1669] eta: 0:24:42 tlr: 0.00023 tnm: 0.20 Lm: 6.694 (6.694) Lt: 5.899 (5.899) Accm: 2.99 (2.99) Acct: 4.65 (4.65) proj_loss: -0.5620 (-0.5620) time: 0.8883 data: 0.0003 [11-23 11:15:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 0/1669] eta: 0:24:46 tlr: 0.00023 tnm: 0.20 Lm: 6.742 (6.742) Lt: 6.093 (6.093) Accm: 2.99 (2.99) Acct: 4.41 (4.41) proj_loss: -0.5495 (-0.5495) time: 0.8905 data: 0.0004 [11-23 11:15:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 0/1669] eta: 0:24:46 tlr: 0.00023 tnm: 0.20 Lm: 6.607 (6.607) Lt: 5.780 (5.780) Accm: 3.23 (3.23) Acct: 5.92 (5.92) proj_loss: -0.5723 (-0.5723) time: 0.8908 data: 0.0004 [11-23 11:15:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 0/1669] eta: 0:24:52 tlr: 0.00023 tnm: 0.20 Lm: 6.501 (6.501) Lt: 5.706 (5.706) Accm: 3.57 (3.57) Acct: 6.03 (6.03) proj_loss: -0.5744 (-0.5744) time: 0.8944 data: 0.0004 [11-23 11:21:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 417/1669] eta: 0:20:05 tlr: 0.00023 tnm: 0.23 Lm: 6.653 (6.653) Lt: 5.846 (5.846) Accm: 3.16 (3.16) Acct: 5.06 (5.06) proj_loss: -0.5666 (-0.5666) time: 1.0034 data: 0.0003 [11-23 11:21:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 417/1669] eta: 0:20:05 tlr: 0.00023 tnm: 0.23 Lm: 6.691 (6.691) Lt: 5.978 (5.978) Accm: 2.64 (2.64) Acct: 4.05 (4.05) proj_loss: -0.5614 (-0.5614) time: 1.0034 data: 0.0003 [11-23 11:21:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 417/1669] eta: 0:20:05 tlr: 0.00023 tnm: 0.23 Lm: 6.841 (6.841) Lt: 6.122 (6.122) Accm: 2.72 (2.72) Acct: 4.22 (4.22) proj_loss: -0.5829 (-0.5829) time: 1.0034 data: 0.0002 [11-23 11:21:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 417/1669] eta: 0:20:05 tlr: 0.00023 tnm: 0.23 Lm: 6.549 (6.549) Lt: 5.755 (5.755) Accm: 3.26 (3.26) Acct: 5.35 (5.35) proj_loss: -0.5688 (-0.5688) time: 1.0034 data: 0.0003 [11-23 11:21:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 417/1669] eta: 0:20:05 tlr: 0.00023 tnm: 0.23 Lm: 6.667 (6.667) Lt: 5.895 (5.895) Accm: 3.07 (3.07) Acct: 4.72 (4.72) proj_loss: -0.5649 (-0.5649) time: 1.0034 data: 0.0003 [11-23 11:21:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 417/1669] eta: 0:20:05 tlr: 0.00023 tnm: 0.23 Lm: 6.688 (6.688) Lt: 5.977 (5.977) Accm: 2.92 (2.92) Acct: 4.48 (4.48) proj_loss: -0.5829 (-0.5829) time: 1.0034 data: 0.0003 [11-23 11:21:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 417/1669] eta: 0:20:05 tlr: 0.00023 tnm: 0.23 Lm: 6.745 (6.745) Lt: 5.971 (5.971) Accm: 2.91 (2.91) Acct: 4.63 (4.63) proj_loss: -0.5900 (-0.5900) time: 1.0034 data: 0.0003 [11-23 11:21:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 417/1669] eta: 0:20:05 tlr: 0.00023 tnm: 0.23 Lm: 6.684 (6.684) Lt: 5.923 (5.923) Accm: 2.88 (2.88) Acct: 4.84 (4.84) proj_loss: -0.5597 (-0.5597) time: 1.0034 data: 0.0003 [11-23 11:28:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 834/1669] eta: 0:13:18 tlr: 0.00023 tnm: 0.21 Lm: 6.607 (6.657) Lt: 5.840 (5.895) Accm: 3.23 (3.17) Acct: 5.92 (5.25) proj_loss: -0.5675 (-0.5623) time: 0.9321 data: 0.0003 [11-23 11:28:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 834/1669] eta: 0:13:18 tlr: 0.00023 tnm: 0.21 Lm: 6.685 (6.689) Lt: 5.829 (5.923) Accm: 2.68 (2.69) Acct: 4.13 (4.09) proj_loss: -0.5547 (-0.5492) time: 0.9321 data: 0.0002 [11-23 11:28:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 834/1669] eta: 0:13:18 tlr: 0.00023 tnm: 0.21 Lm: 6.639 (6.710) Lt: 5.928 (5.957) Accm: 2.70 (2.84) Acct: 4.17 (4.48) proj_loss: -0.5781 (-0.5820) time: 0.9321 data: 0.0003 [11-23 11:28:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 834/1669] eta: 0:13:18 tlr: 0.00023 tnm: 0.21 Lm: 6.585 (6.572) Lt: 5.815 (5.790) Accm: 3.02 (3.10) Acct: 4.92 (5.14) proj_loss: -0.5672 (-0.5669) time: 0.9321 data: 0.0003 [11-23 11:28:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 834/1669] eta: 0:13:18 tlr: 0.00023 tnm: 0.21 Lm: 6.694 (6.695) Lt: 5.899 (5.945) Accm: 2.99 (3.01) Acct: 4.65 (4.67) proj_loss: -0.5620 (-0.5617) time: 0.9321 data: 0.0003 [11-23 11:28:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 834/1669] eta: 0:13:18 tlr: 0.00023 tnm: 0.21 Lm: 6.713 (6.773) Lt: 6.033 (6.032) Accm: 2.94 (2.79) Acct: 4.72 (4.38) proj_loss: -0.5685 (-0.5781) time: 0.9321 data: 0.0003 [11-23 11:28:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 834/1669] eta: 0:13:18 tlr: 0.00023 tnm: 0.21 Lm: 6.634 (6.637) Lt: 5.861 (5.909) Accm: 2.99 (3.13) Acct: 4.55 (4.81) proj_loss: -0.5590 (-0.5749) time: 0.9321 data: 0.0003 [11-23 11:28:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [ 834/1669] eta: 0:13:18 tlr: 0.00023 tnm: 0.21 Lm: 6.580 (6.629) Lt: 5.817 (5.837) Accm: 3.35 (3.22) Acct: 5.30 (5.14) proj_loss: -0.5744 (-0.5753) time: 0.9321 data: 0.0003 [11-23 11:35:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [1251/1669] eta: 0:06:43 tlr: 0.00023 tnm: 0.21 Lm: 6.548 (6.600) Lt: 5.808 (5.827) Accm: 3.46 (3.34) Acct: 5.42 (5.24) proj_loss: -0.5771 (-0.5764) time: 0.9310 data: 0.0003 [11-23 11:35:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [1251/1669] eta: 0:06:43 tlr: 0.00023 tnm: 0.21 Lm: 6.619 (6.644) Lt: 5.821 (5.877) Accm: 2.72 (2.82) Acct: 4.15 (4.40) proj_loss: -0.5454 (-0.5460) time: 0.9310 data: 0.0003 [11-23 11:35:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [1251/1669] eta: 0:06:43 tlr: 0.00023 tnm: 0.21 Lm: 6.602 (6.606) Lt: 5.838 (5.836) Accm: 2.90 (3.00) Acct: 4.82 (4.96) proj_loss: -0.5688 (-0.5708) time: 0.9310 data: 0.0003 [11-23 11:35:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [1251/1669] eta: 0:06:43 tlr: 0.00023 tnm: 0.21 Lm: 6.656 (6.648) Lt: 5.897 (5.915) Accm: 2.92 (3.00) Acct: 4.48 (4.68) proj_loss: -0.5733 (-0.5781) time: 0.9310 data: 0.0003 [11-23 11:35:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [1251/1669] eta: 0:06:43 tlr: 0.00023 tnm: 0.21 Lm: 6.727 (6.736) Lt: 5.975 (5.973) Accm: 2.79 (2.85) Acct: 4.60 (4.61) proj_loss: -0.5721 (-0.5716) time: 0.9310 data: 0.0003 [11-23 11:35:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [1251/1669] eta: 0:06:43 tlr: 0.00023 tnm: 0.21 Lm: 6.682 (6.742) Lt: 5.959 (5.995) Accm: 2.88 (2.80) Acct: 4.63 (4.42) proj_loss: -0.5775 (-0.5802) time: 0.9310 data: 0.0003 [11-23 11:35:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [1251/1669] eta: 0:06:43 tlr: 0.00023 tnm: 0.21 Lm: 6.612 (6.647) Lt: 5.846 (5.884) Accm: 3.19 (3.16) Acct: 5.61 (5.26) proj_loss: -0.5699 (-0.5653) time: 0.9310 data: 0.0003 [11-23 11:35:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [1251/1669] eta: 0:06:43 tlr: 0.00023 tnm: 0.21 Lm: 6.667 (6.655) Lt: 5.895 (5.911) Accm: 3.07 (3.13) Acct: 4.72 (4.84) proj_loss: -0.5592 (-0.5604) time: 0.9310 data: 0.0003 [11-23 11:41:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.691 (6.662) Lt: 5.899 (5.922) Accm: 3.13 (3.13) Acct: 4.65 (4.79) proj_loss: -0.5620 (-0.5719) time: 0.9313 data: 0.0018 [11-23 11:41:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 43/350] Total time: 0:26:37 (0.957 s / it) [11-23 11:41:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.655 (6.646) Lt: 5.829 (5.894) Accm: 2.71 (2.79) Acct: 4.17 (4.41) proj_loss: -0.5547 (-0.5551) time: 0.9313 data: 0.0016 [11-23 11:41:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.585 (6.583) Lt: 5.815 (5.809) Accm: 3.02 (3.05) Acct: 4.92 (5.04) proj_loss: -0.5703 (-0.5727) time: 0.9313 data: 0.0020 [11-23 11:41:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.574 (6.595) Lt: 5.798 (5.811) Accm: 3.35 (3.33) Acct: 5.54 (5.33) proj_loss: -0.5794 (-0.5770) time: 0.9313 data: 0.0017 [11-23 11:41:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.639 (6.693) Lt: 5.928 (5.935) Accm: 2.88 (2.94) Acct: 5.03 (4.70) proj_loss: -0.5660 (-0.5694) time: 0.9313 data: 0.0017 [11-23 11:41:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.617 (6.681) Lt: 5.852 (5.943) Accm: 3.15 (2.98) Acct: 5.30 (4.88) proj_loss: -0.5675 (-0.5654) time: 0.9313 data: 0.0019 [11-23 11:41:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.650 (6.708) Lt: 5.885 (5.958) Accm: 2.94 (2.88) Acct: 4.72 (4.56) proj_loss: -0.5685 (-0.5769) time: 0.9313 data: 0.0020 [11-23 11:41:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 43/350] [1668/1669] eta: 0:00:00 tlr: 0.00023 tnm: 0.21 Lm: 6.679 (6.666) Lt: 5.932 (5.944) Accm: 2.93 (2.98) Acct: 4.55 (4.69) proj_loss: -0.5809 (-0.5787) time: 0.9313 data: 0.0017 [11-23 11:41:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 43/350] Total time: 0:26:37 (0.957 s / it) [11-23 11:41:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 43/350] Total time: 0:26:37 (0.957 s / it) [11-23 11:41:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 43/350] Total time: 0:26:37 (0.957 s / it) [11-23 11:41:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 43/350] Total time: 0:26:37 (0.957 s / it) [11-23 11:41:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 43/350] Total time: 0:26:37 (0.957 s / it) [11-23 11:41:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 43/350] Total time: 0:26:37 (0.957 s / it) [11-23 11:41:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 43/350] Total time: 0:26:37 (0.957 s / it) [11-23 11:41:40] (/home/user/VAR/train.py , line 276)=> [ep43] (training ) Lm: 6.641 (6.641), Lt: 5.901 (5.901), Acc m&t: 3.01 4.73, Remain: 5 days, 13:14:16, Finish: 2024-11-28 08:55 [11-23 11:41:40] (/home/user/VAR/train.py , line 276)=> [ep43] (training ) Lm: 6.641 (6.641), Lt: 5.901 (5.901), Acc m&t: 3.01 4.73, Remain: 5 days, 13:15:01, Finish: 2024-11-28 08:56 [11-23 11:41:40] (/home/user/VAR/train.py , line 276)=> [ep43] (training ) Lm: 6.641 (6.641), Lt: 5.901 (5.901), Acc m&t: 3.01 4.73, Remain: 5 days, 13:17:30, Finish: 2024-11-28 08:59 [11-23 11:41:40] (/home/user/VAR/train.py , line 276)=> [ep43] (training ) Lm: 6.641 (6.641), Lt: 5.901 (5.901), Acc m&t: 3.01 4.73, Remain: 5 days, 13:16:49, Finish: 2024-11-28 08:58 [11-23 11:41:40] (/home/user/VAR/train.py , line 276)=> [ep43] (training ) Lm: 6.641 (6.641), Lt: 5.901 (5.901), Acc m&t: 3.01 4.73, Remain: 5 days, 13:15:37, Finish: 2024-11-28 08:57 [11-23 11:41:40] (/home/user/VAR/train.py , line 276)=> [ep43] (training ) Lm: 6.641 (6.641), Lt: 5.901 (5.901), Acc m&t: 3.01 4.73, Remain: 5 days, 13:16:48, Finish: 2024-11-28 08:58 [11-23 11:41:40] (/home/user/VAR/train.py , line 276)=> [ep43] (training ) Lm: 6.641 (6.641), Lt: 5.901 (5.901), Acc m&t: 3.01 4.73, Remain: 5 days, 13:16:09, Finish: 2024-11-28 08:57 [11-23 11:41:40] (/home/user/VAR/train.py , line 276)=> [ep43] (training ) Lm: 6.641 (6.641), Lt: 5.901 (5.901), Acc m&t: 3.01 4.73, Remain: 5 days, 13:16:33, Finish: 2024-11-28 08:58 [11-23 11:41:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 0/1669] eta: 0:25:12 tlr: 0.00023 tnm: 0.22 Lm: 6.560 (6.560) Lt: 5.835 (5.835) Accm: 3.41 (3.41) Acct: 5.17 (5.17) proj_loss: -0.5824 (-0.5824) time: 0.9064 data: 0.0003 [11-23 11:41:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 0/1669] eta: 0:25:13 tlr: 0.00023 tnm: 0.22 Lm: 6.604 (6.604) Lt: 5.856 (5.856) Accm: 2.84 (2.84) Acct: 4.20 (4.20) proj_loss: -0.5901 (-0.5901) time: 0.9066 data: 0.0003 [11-23 11:41:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 0/1669] eta: 0:25:16 tlr: 0.00023 tnm: 0.22 Lm: 6.489 (6.489) Lt: 5.709 (5.709) Accm: 4.01 (4.01) Acct: 6.51 (6.51) proj_loss: -0.5705 (-0.5705) time: 0.9086 data: 0.0004 [11-23 11:41:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 0/1669] eta: 0:25:13 tlr: 0.00023 tnm: 0.22 Lm: 6.371 (6.371) Lt: 5.565 (5.565) Accm: 3.83 (3.83) Acct: 6.06 (6.06) proj_loss: -0.5780 (-0.5780) time: 0.9067 data: 0.0004 [11-23 11:41:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 0/1669] eta: 0:25:13 tlr: 0.00023 tnm: 0.22 Lm: 6.728 (6.728) Lt: 5.945 (5.945) Accm: 2.74 (2.74) Acct: 4.17 (4.17) proj_loss: -0.5787 (-0.5787) time: 0.9067 data: 0.0004 [11-23 11:41:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 0/1669] eta: 0:25:13 tlr: 0.00023 tnm: 0.22 Lm: 6.202 (6.202) Lt: 5.429 (5.429) Accm: 4.91 (4.91) Acct: 7.82 (7.82) proj_loss: -0.5731 (-0.5731) time: 0.9069 data: 0.0003 [11-23 11:41:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 0/1669] eta: 0:25:13 tlr: 0.00023 tnm: 0.22 Lm: 6.579 (6.579) Lt: 5.832 (5.832) Accm: 3.04 (3.04) Acct: 5.03 (5.03) proj_loss: -0.5573 (-0.5573) time: 0.9069 data: 0.0004 [11-23 11:41:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 0/1669] eta: 0:25:21 tlr: 0.00023 tnm: 0.22 Lm: 6.584 (6.584) Lt: 5.832 (5.832) Accm: 3.39 (3.39) Acct: 5.34 (5.34) proj_loss: -0.5478 (-0.5478) time: 0.9117 data: 0.0004 [11-23 11:48:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 417/1669] eta: 0:19:25 tlr: 0.00023 tnm: 0.21 Lm: 6.528 (6.528) Lt: 5.762 (5.762) Accm: 3.50 (3.50) Acct: 5.68 (5.68) proj_loss: -0.5751 (-0.5751) time: 0.9292 data: 0.0003 [11-23 11:48:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 417/1669] eta: 0:19:25 tlr: 0.00023 tnm: 0.21 Lm: 6.363 (6.363) Lt: 5.519 (5.519) Accm: 3.77 (3.77) Acct: 6.18 (6.18) proj_loss: -0.5788 (-0.5788) time: 0.9292 data: 0.0003 [11-23 11:48:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 417/1669] eta: 0:19:25 tlr: 0.00023 tnm: 0.21 Lm: 6.428 (6.428) Lt: 5.675 (5.675) Accm: 3.86 (3.86) Acct: 6.22 (6.22) proj_loss: -0.5665 (-0.5665) time: 0.9292 data: 0.0003 [11-23 11:48:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 417/1669] eta: 0:19:25 tlr: 0.00023 tnm: 0.21 Lm: 6.550 (6.550) Lt: 5.815 (5.815) Accm: 3.05 (3.05) Acct: 5.06 (5.06) proj_loss: -0.5592 (-0.5592) time: 0.9292 data: 0.0003 [11-23 11:48:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 417/1669] eta: 0:19:25 tlr: 0.00023 tnm: 0.21 Lm: 6.637 (6.637) Lt: 5.848 (5.848) Accm: 2.91 (2.91) Acct: 4.55 (4.55) proj_loss: -0.5724 (-0.5724) time: 0.9292 data: 0.0003 [11-23 11:48:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 417/1669] eta: 0:19:25 tlr: 0.00023 tnm: 0.21 Lm: 6.560 (6.560) Lt: 5.792 (5.792) Accm: 3.21 (3.21) Acct: 5.01 (5.01) proj_loss: -0.5821 (-0.5821) time: 0.9292 data: 0.0003 [11-23 11:48:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 417/1669] eta: 0:19:25 tlr: 0.00023 tnm: 0.21 Lm: 6.527 (6.527) Lt: 5.810 (5.810) Accm: 3.26 (3.26) Acct: 4.79 (4.79) proj_loss: -0.5724 (-0.5724) time: 0.9292 data: 0.0003 [11-23 11:48:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 417/1669] eta: 0:19:25 tlr: 0.00023 tnm: 0.21 Lm: 6.518 (6.518) Lt: 5.754 (5.754) Accm: 3.83 (3.83) Acct: 6.22 (6.22) proj_loss: -0.5777 (-0.5777) time: 0.9292 data: 0.0003 [11-23 11:54:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 834/1669] eta: 0:12:57 tlr: 0.00023 tnm: 0.22 Lm: 6.548 (6.538) Lt: 5.787 (5.765) Accm: 3.66 (3.72) Acct: 5.92 (6.07) proj_loss: -0.5705 (-0.5708) time: 0.9290 data: 0.0003 [11-23 11:54:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 834/1669] eta: 0:12:57 tlr: 0.00023 tnm: 0.22 Lm: 6.560 (6.646) Lt: 5.835 (5.948) Accm: 3.12 (2.94) Acct: 4.41 (4.41) proj_loss: -0.5824 (-0.5835) time: 0.9290 data: 0.0003 [11-23 11:54:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 834/1669] eta: 0:12:57 tlr: 0.00023 tnm: 0.22 Lm: 6.371 (6.458) Lt: 5.565 (5.670) Accm: 3.70 (3.49) Acct: 6.06 (5.50) proj_loss: -0.5796 (-0.5799) time: 0.9290 data: 0.0003 [11-23 11:54:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 834/1669] eta: 0:12:57 tlr: 0.00023 tnm: 0.22 Lm: 6.579 (6.655) Lt: 5.832 (5.912) Accm: 3.04 (2.85) Acct: 5.03 (4.81) proj_loss: -0.5611 (-0.5649) time: 0.9290 data: 0.0003 [11-23 11:54:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 834/1669] eta: 0:12:57 tlr: 0.00023 tnm: 0.22 Lm: 6.725 (6.667) Lt: 5.945 (5.904) Accm: 2.90 (2.91) Acct: 4.44 (4.51) proj_loss: -0.5696 (-0.5715) time: 0.9290 data: 0.0002 [11-23 11:54:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 834/1669] eta: 0:12:57 tlr: 0.00023 tnm: 0.22 Lm: 6.473 (6.509) Lt: 5.691 (5.719) Accm: 3.53 (3.51) Acct: 5.65 (5.67) proj_loss: -0.5500 (-0.5667) time: 0.9290 data: 0.0003 [11-23 11:54:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 834/1669] eta: 0:12:57 tlr: 0.00023 tnm: 0.22 Lm: 6.604 (6.632) Lt: 5.856 (5.870) Accm: 2.84 (3.07) Acct: 4.65 (4.89) proj_loss: -0.5740 (-0.5699) time: 0.9290 data: 0.0003 [11-23 11:54:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [ 834/1669] eta: 0:12:57 tlr: 0.00023 tnm: 0.22 Lm: 6.500 (6.452) Lt: 5.781 (5.710) Accm: 3.47 (3.73) Acct: 5.61 (6.01) proj_loss: -0.5731 (-0.5707) time: 0.9290 data: 0.0003 [11-23 12:01:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.23 Lm: 6.480 (6.454) Lt: 5.741 (5.708) Accm: 3.42 (3.64) Acct: 5.66 (5.94) proj_loss: -0.5761 (-0.5753) time: 0.9293 data: 0.0003 [11-23 12:01:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.23 Lm: 6.527 (6.590) Lt: 5.810 (5.896) Accm: 3.25 (3.05) Acct: 4.79 (4.67) proj_loss: -0.5805 (-0.5823) time: 0.9293 data: 0.0003 [11-23 12:01:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.23 Lm: 6.528 (6.560) Lt: 5.762 (5.807) Accm: 3.46 (3.34) Acct: 5.49 (5.26) proj_loss: -0.5564 (-0.5657) time: 0.9293 data: 0.0003 [11-23 12:01:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.23 Lm: 6.659 (6.648) Lt: 5.887 (5.885) Accm: 2.99 (3.01) Acct: 4.68 (4.73) proj_loss: -0.5725 (-0.5724) time: 0.9293 data: 0.0003 [11-23 12:01:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.23 Lm: 6.488 (6.495) Lt: 5.684 (5.703) Accm: 3.36 (3.37) Acct: 5.29 (5.25) proj_loss: -0.5808 (-0.5860) time: 0.9293 data: 0.0003 [11-23 12:01:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.23 Lm: 6.562 (6.577) Lt: 5.793 (5.800) Accm: 3.58 (3.52) Acct: 5.85 (5.69) proj_loss: -0.5737 (-0.5723) time: 0.9293 data: 0.0003 [11-23 12:01:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.23 Lm: 6.689 (6.687) Lt: 5.941 (5.936) Accm: 2.83 (2.96) Acct: 4.42 (4.71) proj_loss: -0.5742 (-0.5710) time: 0.9293 data: 0.0003 [11-23 12:01:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.23 Lm: 6.626 (6.660) Lt: 5.885 (5.919) Accm: 3.05 (2.96) Acct: 5.03 (4.86) proj_loss: -0.5687 (-0.5715) time: 0.9293 data: 0.0003 [11-23 12:07:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.24 Lm: 6.583 (6.644) Lt: 5.865 (5.908) Accm: 3.06 (3.01) Acct: 5.03 (4.88) proj_loss: -0.5611 (-0.5662) time: 1.2077 data: 0.0017 [11-23 12:07:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 44/350] Total time: 0:26:17 (0.945 s / it) [11-23 12:07:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.24 Lm: 6.584 (6.587) Lt: 5.832 (5.852) Accm: 3.39 (3.26) Acct: 5.34 (5.03) proj_loss: -0.5627 (-0.5714) time: 1.2077 data: 0.0017 [11-23 12:07:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.24 Lm: 6.560 (6.635) Lt: 5.835 (5.945) Accm: 3.12 (2.92) Acct: 4.41 (4.53) proj_loss: -0.5787 (-0.5799) time: 1.2077 data: 0.0017 [11-23 12:07:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.24 Lm: 6.594 (6.627) Lt: 5.829 (5.866) Accm: 3.09 (3.05) Acct: 4.92 (4.82) proj_loss: -0.5753 (-0.5735) time: 1.2077 data: 0.0017 [11-23 12:07:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.24 Lm: 6.576 (6.600) Lt: 5.798 (5.845) Accm: 3.51 (3.37) Acct: 5.79 (5.48) proj_loss: -0.5769 (-0.5750) time: 1.2077 data: 0.0020 [11-23 12:07:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.24 Lm: 6.500 (6.483) Lt: 5.781 (5.738) Accm: 3.38 (3.56) Acct: 5.61 (5.81) proj_loss: -0.5731 (-0.5735) time: 1.2077 data: 0.0016 [11-23 12:07:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.24 Lm: 6.652 (6.680) Lt: 5.971 (5.943) Accm: 2.81 (2.89) Acct: 4.20 (4.55) proj_loss: -0.5745 (-0.5737) time: 1.2077 data: 0.0018 [11-23 12:07:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 44/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.24 Lm: 6.606 (6.521) Lt: 5.803 (5.731) Accm: 3.02 (3.24) Acct: 4.51 (4.97) proj_loss: -0.5796 (-0.5814) time: 1.2077 data: 0.0021 [11-23 12:07:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 44/350] Total time: 0:26:17 (0.945 s / it) [11-23 12:07:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 44/350] Total time: 0:26:17 (0.945 s / it) [11-23 12:07:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 44/350] Total time: 0:26:17 (0.945 s / it) [11-23 12:07:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 44/350] Total time: 0:26:17 (0.945 s / it) [11-23 12:07:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 44/350] Total time: 0:26:17 (0.945 s / it) [11-23 12:07:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 44/350] Total time: 0:26:17 (0.945 s / it) [11-23 12:07:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 44/350] Total time: 0:26:17 (0.945 s / it) [11-23 12:07:58] (/home/user/VAR/train.py , line 276)=> [ep44] (training ) Lm: 6.627 (6.627), Lt: 5.883 (5.883), Acc m&t: 3.04 4.80, Remain: 5 days, 13:25:45, Finish: 2024-11-28 09:33 [11-23 12:07:58] (/home/user/VAR/train.py , line 276)=> [ep44] (training ) Lm: 6.627 (6.627), Lt: 5.883 (5.883), Acc m&t: 3.04 4.80, Remain: 5 days, 13:24:13, Finish: 2024-11-28 09:32 [11-23 12:07:58] (/home/user/VAR/train.py , line 276)=> [ep44] (training ) Lm: 6.627 (6.627), Lt: 5.883 (5.883), Acc m&t: 3.04 4.80, Remain: 5 days, 13:24:44, Finish: 2024-11-28 09:32 [11-23 12:07:58] (/home/user/VAR/train.py , line 276)=> [ep44] (training ) Lm: 6.627 (6.627), Lt: 5.883 (5.883), Acc m&t: 3.04 4.80, Remain: 5 days, 13:24:14, Finish: 2024-11-28 09:32 [11-23 12:07:58] (/home/user/VAR/train.py , line 276)=> [ep44] (training ) Lm: 6.627 (6.627), Lt: 5.883 (5.883), Acc m&t: 3.04 4.80, Remain: 5 days, 13:24:57, Finish: 2024-11-28 09:32 [11-23 12:07:58] (/home/user/VAR/train.py , line 276)=> [ep44] (training ) Lm: 6.627 (6.627), Lt: 5.883 (5.883), Acc m&t: 3.04 4.80, Remain: 5 days, 13:25:21, Finish: 2024-11-28 09:33 [11-23 12:07:58] (/home/user/VAR/train.py , line 276)=> [ep44] (training ) Lm: 6.627 (6.627), Lt: 5.883 (5.883), Acc m&t: 3.04 4.80, Remain: 5 days, 13:25:24, Finish: 2024-11-28 09:33 [11-23 12:07:58] (/home/user/VAR/train.py , line 276)=> [ep44] (training ) Lm: 6.627 (6.627), Lt: 5.883 (5.883), Acc m&t: 3.04 4.80, Remain: 5 days, 13:25:07, Finish: 2024-11-28 09:33 [11-23 12:08:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 0/1669] eta: 1:23:29 tlr: 0.00022 tnm: 0.21 Lm: 6.601 (6.601) Lt: 5.878 (5.878) Accm: 3.19 (3.19) Acct: 5.27 (5.27) proj_loss: -0.5602 (-0.5602) time: 3.0016 data: 0.0003 [11-23 12:08:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 0/1669] eta: 1:23:31 tlr: 0.00022 tnm: 0.21 Lm: 6.565 (6.565) Lt: 5.812 (5.812) Accm: 3.13 (3.13) Acct: 5.06 (5.06) proj_loss: -0.5773 (-0.5773) time: 3.0029 data: 0.0004 [11-23 12:08:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 0/1669] eta: 1:23:31 tlr: 0.00022 tnm: 0.21 Lm: 6.538 (6.538) Lt: 5.809 (5.809) Accm: 3.37 (3.37) Acct: 5.10 (5.10) proj_loss: -0.5723 (-0.5723) time: 3.0029 data: 0.0004 [11-23 12:08:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 0/1669] eta: 1:23:26 tlr: 0.00022 tnm: 0.21 Lm: 6.727 (6.727) Lt: 6.047 (6.047) Accm: 3.07 (3.07) Acct: 4.65 (4.65) proj_loss: -0.5650 (-0.5650) time: 2.9997 data: 0.0003 [11-23 12:08:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 0/1669] eta: 1:23:31 tlr: 0.00022 tnm: 0.21 Lm: 6.245 (6.245) Lt: 5.485 (5.485) Accm: 4.49 (4.49) Acct: 6.61 (6.61) proj_loss: -0.5750 (-0.5750) time: 3.0030 data: 0.0004 [11-23 12:08:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 0/1669] eta: 1:23:32 tlr: 0.00022 tnm: 0.21 Lm: 6.659 (6.659) Lt: 5.877 (5.877) Accm: 3.12 (3.12) Acct: 5.34 (5.34) proj_loss: -0.5844 (-0.5844) time: 3.0031 data: 0.0004 [11-23 12:08:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 0/1669] eta: 1:23:28 tlr: 0.00022 tnm: 0.21 Lm: 6.726 (6.726) Lt: 6.005 (6.005) Accm: 3.00 (3.00) Acct: 4.82 (4.82) proj_loss: -0.5706 (-0.5706) time: 3.0010 data: 0.0004 [11-23 12:08:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 0/1669] eta: 1:23:32 tlr: 0.00022 tnm: 0.21 Lm: 6.458 (6.458) Lt: 5.822 (5.822) Accm: 3.25 (3.25) Acct: 5.10 (5.10) proj_loss: -0.5578 (-0.5578) time: 3.0034 data: 0.0004 [11-23 12:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 417/1669] eta: 0:20:07 tlr: 0.00022 tnm: 0.21 Lm: 6.473 (6.473) Lt: 5.794 (5.794) Accm: 3.41 (3.41) Acct: 5.54 (5.54) proj_loss: -0.5572 (-0.5572) time: 0.9318 data: 0.0003 [11-23 12:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 417/1669] eta: 0:20:07 tlr: 0.00022 tnm: 0.21 Lm: 6.479 (6.479) Lt: 5.766 (5.766) Accm: 3.47 (3.47) Acct: 5.39 (5.39) proj_loss: -0.5798 (-0.5798) time: 0.9318 data: 0.0003 [11-23 12:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 417/1669] eta: 0:20:07 tlr: 0.00022 tnm: 0.21 Lm: 6.707 (6.707) Lt: 5.922 (5.922) Accm: 2.92 (2.92) Acct: 5.03 (5.03) proj_loss: -0.5853 (-0.5853) time: 0.9318 data: 0.0003 [11-23 12:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 417/1669] eta: 0:20:07 tlr: 0.00022 tnm: 0.21 Lm: 6.718 (6.718) Lt: 6.039 (6.039) Accm: 2.94 (2.94) Acct: 4.48 (4.48) proj_loss: -0.5927 (-0.5927) time: 0.9318 data: 0.0003 [11-23 12:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 417/1669] eta: 0:20:07 tlr: 0.00022 tnm: 0.21 Lm: 6.322 (6.322) Lt: 5.582 (5.582) Accm: 4.21 (4.21) Acct: 6.42 (6.42) proj_loss: -0.5680 (-0.5680) time: 0.9318 data: 0.0003 [11-23 12:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 417/1669] eta: 0:20:07 tlr: 0.00022 tnm: 0.21 Lm: 6.633 (6.633) Lt: 5.851 (5.851) Accm: 3.20 (3.20) Acct: 4.87 (4.87) proj_loss: -0.5542 (-0.5542) time: 0.9318 data: 0.0003 [11-23 12:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 417/1669] eta: 0:20:07 tlr: 0.00022 tnm: 0.21 Lm: 6.687 (6.687) Lt: 5.956 (5.956) Accm: 2.95 (2.95) Acct: 4.67 (4.67) proj_loss: -0.5569 (-0.5569) time: 0.9318 data: 0.0003 [11-23 12:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 417/1669] eta: 0:20:07 tlr: 0.00022 tnm: 0.21 Lm: 6.627 (6.627) Lt: 5.950 (5.950) Accm: 3.12 (3.12) Acct: 4.60 (4.60) proj_loss: -0.5761 (-0.5761) time: 0.9319 data: 0.0003 [11-23 12:21:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 834/1669] eta: 0:13:11 tlr: 0.00022 tnm: 0.22 Lm: 6.538 (6.560) Lt: 5.809 (5.837) Accm: 3.37 (3.25) Acct: 5.10 (4.95) proj_loss: -0.5723 (-0.5683) time: 0.9291 data: 0.0003 [11-23 12:21:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 834/1669] eta: 0:13:11 tlr: 0.00022 tnm: 0.22 Lm: 6.601 (6.649) Lt: 5.879 (5.930) Accm: 3.10 (3.00) Acct: 5.10 (4.81) proj_loss: -0.5602 (-0.5728) time: 0.9291 data: 0.0003 [11-23 12:21:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 834/1669] eta: 0:13:11 tlr: 0.00022 tnm: 0.22 Lm: 6.756 (6.740) Lt: 5.967 (5.995) Accm: 2.75 (2.87) Acct: 4.72 (4.86) proj_loss: -0.5853 (-0.5853) time: 0.9291 data: 0.0003 [11-23 12:21:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 834/1669] eta: 0:13:11 tlr: 0.00022 tnm: 0.22 Lm: 6.565 (6.561) Lt: 5.812 (5.837) Accm: 3.13 (3.28) Acct: 5.06 (5.12) proj_loss: -0.5773 (-0.5604) time: 0.9291 data: 0.0003 [11-23 12:21:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 834/1669] eta: 0:13:11 tlr: 0.00022 tnm: 0.22 Lm: 6.726 (6.774) Lt: 6.072 (6.082) Accm: 2.87 (2.68) Acct: 4.13 (4.27) proj_loss: -0.5706 (-0.5828) time: 0.9291 data: 0.0003 [11-23 12:21:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 834/1669] eta: 0:13:11 tlr: 0.00022 tnm: 0.22 Lm: 6.400 (6.398) Lt: 5.680 (5.657) Accm: 3.93 (3.89) Acct: 6.23 (5.95) proj_loss: -0.5750 (-0.5799) time: 0.9291 data: 0.0007 [11-23 12:21:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 834/1669] eta: 0:13:11 tlr: 0.00022 tnm: 0.22 Lm: 6.487 (6.503) Lt: 5.795 (5.795) Accm: 3.37 (3.39) Acct: 5.44 (5.51) proj_loss: -0.5565 (-0.5553) time: 0.9291 data: 0.0003 [11-23 12:21:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [ 834/1669] eta: 0:13:11 tlr: 0.00022 tnm: 0.22 Lm: 6.727 (6.668) Lt: 6.016 (5.906) Accm: 3.07 (3.05) Acct: 4.65 (4.67) proj_loss: -0.5630 (-0.5571) time: 0.9290 data: 0.0003 [11-23 12:27:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.21 Lm: 6.535 (6.547) Lt: 5.797 (5.824) Accm: 3.31 (3.33) Acct: 5.11 (5.13) proj_loss: -0.5798 (-0.5663) time: 0.9312 data: 0.0003 [11-23 12:27:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.21 Lm: 6.718 (6.689) Lt: 6.039 (5.947) Accm: 2.94 (2.87) Acct: 4.48 (4.66) proj_loss: -0.5782 (-0.5836) time: 0.9313 data: 0.0003 [11-23 12:27:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.21 Lm: 6.475 (6.453) Lt: 5.744 (5.704) Accm: 3.60 (3.72) Acct: 5.61 (5.66) proj_loss: -0.5680 (-0.5745) time: 0.9312 data: 0.0003 [11-23 12:27:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.21 Lm: 6.580 (6.576) Lt: 5.804 (5.827) Accm: 3.16 (3.18) Acct: 5.06 (4.97) proj_loss: -0.5761 (-0.5770) time: 0.9313 data: 0.0003 [11-23 12:27:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.21 Lm: 6.687 (6.690) Lt: 5.956 (5.997) Accm: 2.91 (2.90) Acct: 4.61 (4.64) proj_loss: -0.5792 (-0.5792) time: 0.9313 data: 0.0003 [11-23 12:27:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.21 Lm: 6.526 (6.606) Lt: 5.809 (5.887) Accm: 3.31 (3.19) Acct: 5.27 (5.15) proj_loss: -0.5572 (-0.5571) time: 0.9313 data: 0.0003 [11-23 12:27:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.21 Lm: 6.781 (6.763) Lt: 6.035 (6.022) Accm: 2.74 (2.72) Acct: 4.61 (4.55) proj_loss: -0.5849 (-0.5771) time: 0.9313 data: 0.0003 [11-23 12:27:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.21 Lm: 6.633 (6.629) Lt: 5.921 (5.886) Accm: 3.20 (3.17) Acct: 4.87 (4.83) proj_loss: -0.5640 (-0.5629) time: 0.9313 data: 0.0003 [11-23 12:34:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.23 Lm: 6.546 (6.613) Lt: 5.826 (5.872) Accm: 3.09 (3.15) Acct: 4.65 (4.79) proj_loss: -0.5650 (-0.5648) time: 0.9331 data: 0.0016 [11-23 12:34:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 45/350] Total time: 0:26:08 (0.940 s / it) [11-23 12:34:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.23 Lm: 6.482 (6.459) Lt: 5.680 (5.699) Accm: 3.93 (3.78) Acct: 6.23 (5.78) proj_loss: -0.5750 (-0.5759) time: 0.9331 data: 0.0015 [11-23 12:34:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.23 Lm: 6.646 (6.681) Lt: 5.901 (5.977) Accm: 3.10 (2.97) Acct: 4.65 (4.64) proj_loss: -0.5696 (-0.5773) time: 0.9331 data: 0.0020 [11-23 12:34:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.23 Lm: 6.756 (6.711) Lt: 5.967 (5.972) Accm: 2.75 (2.79) Acct: 4.72 (4.61) proj_loss: -0.5853 (-0.5790) time: 0.9331 data: 0.0016 [11-23 12:34:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.23 Lm: 6.565 (6.569) Lt: 5.812 (5.833) Accm: 3.13 (3.25) Acct: 5.06 (5.04) proj_loss: -0.5773 (-0.5677) time: 0.9331 data: 0.0016 [11-23 12:34:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.23 Lm: 6.565 (6.629) Lt: 5.822 (5.910) Accm: 3.25 (3.10) Acct: 5.10 (5.02) proj_loss: -0.5578 (-0.5577) time: 0.9331 data: 0.0016 [11-23 12:34:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.23 Lm: 6.538 (6.536) Lt: 5.799 (5.792) Accm: 3.37 (3.25) Acct: 5.10 (5.11) proj_loss: -0.5723 (-0.5734) time: 0.9331 data: 0.0021 [11-23 12:34:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 45/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.23 Lm: 6.711 (6.675) Lt: 6.005 (5.925) Accm: 3.00 (2.92) Acct: 4.82 (4.75) proj_loss: -0.5859 (-0.5863) time: 0.9331 data: 0.0021 [11-23 12:34:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 45/350] Total time: 0:26:08 (0.940 s / it) [11-23 12:34:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 45/350] Total time: 0:26:08 (0.940 s / it) [11-23 12:34:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 45/350] Total time: 0:26:08 (0.940 s / it) [11-23 12:34:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 45/350] Total time: 0:26:08 (0.940 s / it) [11-23 12:34:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 45/350] Total time: 0:26:08 (0.940 s / it) [11-23 12:34:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 45/350] Total time: 0:26:08 (0.940 s / it) [11-23 12:34:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 45/350] Total time: 0:26:08 (0.940 s / it) [11-23 12:34:06] (/home/user/VAR/train.py , line 276)=> [ep45] (training ) Lm: 6.627 (6.632), Lt: 5.883 (5.895), Acc m&t: 3.04 4.80, Remain: 5 days, 12:21:53, Finish: 2024-11-28 08:56 [11-23 12:34:06] (/home/user/VAR/train.py , line 276)=> [ep45] (training ) Lm: 6.627 (6.632), Lt: 5.883 (5.895), Acc m&t: 3.04 4.80, Remain: 5 days, 12:20:18, Finish: 2024-11-28 08:54 [11-23 12:34:06] (/home/user/VAR/train.py , line 276)=> [ep45] (training ) Lm: 6.627 (6.632), Lt: 5.883 (5.895), Acc m&t: 3.04 4.80, Remain: 5 days, 12:20:14, Finish: 2024-11-28 08:54 [11-23 12:34:06] (/home/user/VAR/train.py , line 276)=> [ep45] (training ) Lm: 6.627 (6.632), Lt: 5.883 (5.895), Acc m&t: 3.04 4.80, Remain: 5 days, 12:19:06, Finish: 2024-11-28 08:53 [11-23 12:34:06] (/home/user/VAR/train.py , line 276)=> [ep45] (training ) Lm: 6.627 (6.632), Lt: 5.883 (5.895), Acc m&t: 3.04 4.80, Remain: 5 days, 12:21:10, Finish: 2024-11-28 08:55 [11-23 12:34:06] (/home/user/VAR/train.py , line 276)=> [ep45] (training ) Lm: 6.627 (6.632), Lt: 5.883 (5.895), Acc m&t: 3.04 4.80, Remain: 5 days, 12:20:55, Finish: 2024-11-28 08:55 [11-23 12:34:06] (/home/user/VAR/train.py , line 276)=> [ep45] (training ) Lm: 6.627 (6.632), Lt: 5.883 (5.895), Acc m&t: 3.04 4.80, Remain: 5 days, 12:21:08, Finish: 2024-11-28 08:55 [11-23 12:34:06] (/home/user/VAR/train.py , line 276)=> [ep45] (training ) Lm: 6.627 (6.632), Lt: 5.883 (5.895), Acc m&t: 3.04 4.80, Remain: 5 days, 12:21:32, Finish: 2024-11-28 08:55 [11-23 12:34:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 0/1669] eta: 0:25:45 tlr: 0.00022 tnm: 0.21 Lm: 6.651 (6.651) Lt: 5.876 (5.876) Accm: 2.97 (2.97) Acct: 5.13 (5.13) proj_loss: -0.5632 (-0.5632) time: 0.9263 data: 0.0005 [11-23 12:34:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 0/1669] eta: 0:25:46 tlr: 0.00022 tnm: 0.21 Lm: 6.610 (6.610) Lt: 5.771 (5.771) Accm: 3.39 (3.39) Acct: 5.54 (5.54) proj_loss: -0.5666 (-0.5666) time: 0.9269 data: 0.0004 [11-23 12:34:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 0/1669] eta: 0:25:47 tlr: 0.00022 tnm: 0.21 Lm: 6.506 (6.506) Lt: 5.806 (5.806) Accm: 3.37 (3.37) Acct: 5.20 (5.20) proj_loss: -0.5802 (-0.5802) time: 0.9271 data: 0.0004 [11-23 12:34:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 0/1669] eta: 0:25:47 tlr: 0.00022 tnm: 0.21 Lm: 6.576 (6.576) Lt: 5.803 (5.803) Accm: 3.13 (3.13) Acct: 5.10 (5.10) proj_loss: -0.5566 (-0.5566) time: 0.9271 data: 0.0004 [11-23 12:34:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 0/1669] eta: 0:25:47 tlr: 0.00022 tnm: 0.21 Lm: 6.500 (6.500) Lt: 5.663 (5.663) Accm: 3.31 (3.31) Acct: 5.44 (5.44) proj_loss: -0.5455 (-0.5455) time: 0.9273 data: 0.0003 [11-23 12:34:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 0/1669] eta: 0:25:47 tlr: 0.00022 tnm: 0.21 Lm: 6.650 (6.650) Lt: 5.884 (5.884) Accm: 2.86 (2.86) Acct: 4.68 (4.68) proj_loss: -0.5945 (-0.5945) time: 0.9274 data: 0.0004 [11-23 12:34:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 0/1669] eta: 0:25:47 tlr: 0.00022 tnm: 0.21 Lm: 6.698 (6.698) Lt: 6.012 (6.012) Accm: 2.83 (2.83) Acct: 4.72 (4.72) proj_loss: -0.5705 (-0.5705) time: 0.9274 data: 0.0004 [11-23 12:34:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 0/1669] eta: 0:25:47 tlr: 0.00022 tnm: 0.21 Lm: 6.839 (6.839) Lt: 6.154 (6.154) Accm: 2.37 (2.37) Acct: 3.82 (3.82) proj_loss: -0.5326 (-0.5326) time: 0.9275 data: 0.0004 [11-23 12:40:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.22 Lm: 6.894 (6.894) Lt: 6.198 (6.198) Accm: 2.29 (2.29) Acct: 3.53 (3.53) proj_loss: -0.5616 (-0.5616) time: 0.9321 data: 0.0003 [11-23 12:40:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.22 Lm: 6.663 (6.663) Lt: 5.936 (5.936) Accm: 2.79 (2.79) Acct: 4.36 (4.36) proj_loss: -0.5853 (-0.5853) time: 0.9321 data: 0.0003 [11-23 12:40:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.22 Lm: 6.524 (6.524) Lt: 5.709 (5.709) Accm: 3.49 (3.49) Acct: 5.65 (5.65) proj_loss: -0.5604 (-0.5604) time: 0.9321 data: 0.0002 [11-23 12:40:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.22 Lm: 6.682 (6.682) Lt: 5.933 (5.933) Accm: 2.75 (2.75) Acct: 4.60 (4.60) proj_loss: -0.5927 (-0.5927) time: 0.9321 data: 0.0002 [11-23 12:40:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.22 Lm: 6.617 (6.617) Lt: 5.899 (5.899) Accm: 3.10 (3.10) Acct: 4.89 (4.89) proj_loss: -0.5534 (-0.5534) time: 0.9321 data: 0.0003 [11-23 12:40:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.22 Lm: 6.738 (6.738) Lt: 6.028 (6.028) Accm: 2.73 (2.73) Acct: 4.46 (4.46) proj_loss: -0.5642 (-0.5642) time: 0.9321 data: 0.0003 [11-23 12:40:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.22 Lm: 6.759 (6.759) Lt: 6.027 (6.027) Accm: 2.73 (2.73) Acct: 4.51 (4.51) proj_loss: -0.5677 (-0.5677) time: 0.9321 data: 0.0003 [11-23 12:40:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.22 Lm: 6.435 (6.435) Lt: 5.662 (5.662) Accm: 3.66 (3.66) Acct: 5.75 (5.75) proj_loss: -0.5768 (-0.5768) time: 0.9321 data: 0.0003 [11-23 12:47:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 834/1669] eta: 0:13:15 tlr: 0.00022 tnm: 0.22 Lm: 6.500 (6.476) Lt: 5.663 (5.727) Accm: 3.31 (3.53) Acct: 5.44 (5.54) proj_loss: -0.5847 (-0.5795) time: 0.9306 data: 0.0003 [11-23 12:47:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 834/1669] eta: 0:13:15 tlr: 0.00022 tnm: 0.22 Lm: 6.650 (6.659) Lt: 5.911 (5.927) Accm: 2.96 (2.85) Acct: 4.79 (4.50) proj_loss: -0.5802 (-0.5718) time: 0.9306 data: 0.0003 [11-23 12:47:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 834/1669] eta: 0:13:15 tlr: 0.00022 tnm: 0.22 Lm: 6.601 (6.550) Lt: 5.771 (5.761) Accm: 3.39 (3.41) Acct: 5.54 (5.58) proj_loss: -0.5666 (-0.5698) time: 0.9306 data: 0.0003 [11-23 12:47:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 834/1669] eta: 0:13:15 tlr: 0.00022 tnm: 0.22 Lm: 6.650 (6.574) Lt: 5.884 (5.794) Accm: 2.86 (3.20) Acct: 4.68 (5.41) proj_loss: -0.5910 (-0.5869) time: 0.9306 data: 0.0002 [11-23 12:47:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 834/1669] eta: 0:13:15 tlr: 0.00022 tnm: 0.22 Lm: 6.651 (6.656) Lt: 5.876 (5.948) Accm: 2.97 (2.92) Acct: 4.61 (4.51) proj_loss: -0.5652 (-0.5770) time: 0.9306 data: 0.0003 [11-23 12:47:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 834/1669] eta: 0:13:15 tlr: 0.00022 tnm: 0.22 Lm: 6.698 (6.701) Lt: 6.012 (5.989) Accm: 2.83 (2.86) Acct: 4.72 (4.68) proj_loss: -0.5649 (-0.5660) time: 0.9306 data: 0.0003 [11-23 12:47:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 834/1669] eta: 0:13:15 tlr: 0.00022 tnm: 0.22 Lm: 6.839 (6.842) Lt: 6.154 (6.138) Accm: 2.37 (2.46) Acct: 3.82 (3.93) proj_loss: -0.5326 (-0.5491) time: 0.9306 data: 0.0003 [11-23 12:47:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [ 834/1669] eta: 0:13:15 tlr: 0.00022 tnm: 0.22 Lm: 6.576 (6.582) Lt: 5.803 (5.863) Accm: 3.07 (3.09) Acct: 4.99 (4.92) proj_loss: -0.5566 (-0.5655) time: 0.9306 data: 0.0003 [11-23 12:54:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [1251/1669] eta: 0:06:39 tlr: 0.00022 tnm: 0.22 Lm: 6.544 (6.538) Lt: 5.797 (5.795) Accm: 3.10 (3.31) Acct: 5.04 (5.34) proj_loss: -0.5595 (-0.5647) time: 1.1731 data: 0.0003 [11-23 12:54:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [1251/1669] eta: 0:06:39 tlr: 0.00022 tnm: 0.22 Lm: 6.788 (6.731) Lt: 6.086 (6.013) Accm: 2.59 (2.90) Acct: 4.27 (4.55) proj_loss: -0.5569 (-0.5572) time: 1.1731 data: 0.0003 [11-23 12:54:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [1251/1669] eta: 0:06:39 tlr: 0.00022 tnm: 0.22 Lm: 6.571 (6.591) Lt: 5.833 (5.851) Accm: 3.14 (3.09) Acct: 4.87 (4.86) proj_loss: -0.5642 (-0.5717) time: 1.1731 data: 0.0003 [11-23 12:54:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [1251/1669] eta: 0:06:39 tlr: 0.00022 tnm: 0.22 Lm: 6.619 (6.641) Lt: 5.884 (5.910) Accm: 3.00 (2.90) Acct: 4.82 (4.59) proj_loss: -0.5817 (-0.5747) time: 1.1731 data: 0.0003 [11-23 12:54:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [1251/1669] eta: 0:06:39 tlr: 0.00022 tnm: 0.22 Lm: 6.529 (6.523) Lt: 5.759 (5.778) Accm: 3.29 (3.40) Acct: 5.34 (5.47) proj_loss: -0.5762 (-0.5765) time: 1.1731 data: 0.0003 [11-23 12:54:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [1251/1669] eta: 0:06:39 tlr: 0.00022 tnm: 0.22 Lm: 6.660 (6.681) Lt: 5.997 (5.987) Accm: 2.96 (3.00) Acct: 4.87 (4.86) proj_loss: -0.5677 (-0.5696) time: 1.1731 data: 0.0003 [11-23 12:54:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [1251/1669] eta: 0:06:39 tlr: 0.00022 tnm: 0.22 Lm: 6.607 (6.572) Lt: 5.798 (5.773) Accm: 3.04 (3.21) Acct: 5.04 (5.41) proj_loss: -0.5831 (-0.5777) time: 1.1731 data: 0.0003 [11-23 12:54:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [1251/1669] eta: 0:06:39 tlr: 0.00022 tnm: 0.22 Lm: 6.556 (6.540) Lt: 5.754 (5.755) Accm: 3.37 (3.40) Acct: 5.49 (5.52) proj_loss: -0.5604 (-0.5640) time: 1.1731 data: 0.0003 [11-23 13:00:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.20 Lm: 6.511 (6.531) Lt: 5.771 (5.772) Accm: 3.35 (3.25) Acct: 5.44 (5.28) proj_loss: -0.5666 (-0.5764) time: 0.9329 data: 0.0015 [11-23 13:00:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 46/350] Total time: 0:26:38 (0.958 s / it) [11-23 13:00:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.20 Lm: 6.651 (6.649) Lt: 5.876 (5.907) Accm: 2.97 (2.97) Acct: 4.61 (4.66) proj_loss: -0.5632 (-0.5660) time: 0.9329 data: 0.0018 [11-23 13:00:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.20 Lm: 6.500 (6.517) Lt: 5.805 (5.784) Accm: 3.31 (3.46) Acct: 5.23 (5.41) proj_loss: -0.5690 (-0.5750) time: 0.9329 data: 0.0017 [11-23 13:00:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.20 Lm: 6.576 (6.552) Lt: 5.803 (5.812) Accm: 3.07 (3.26) Acct: 4.99 (5.17) proj_loss: -0.5625 (-0.5647) time: 0.9329 data: 0.0018 [11-23 13:00:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.20 Lm: 6.839 (6.763) Lt: 6.142 (6.039) Accm: 2.45 (2.81) Acct: 3.82 (4.35) proj_loss: -0.5740 (-0.5605) time: 0.9329 data: 0.0020 [11-23 13:00:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.20 Lm: 6.650 (6.606) Lt: 5.884 (5.814) Accm: 2.86 (3.13) Acct: 4.68 (5.24) proj_loss: -0.5752 (-0.5760) time: 0.9329 data: 0.0021 [11-23 13:00:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.20 Lm: 6.650 (6.658) Lt: 5.911 (5.935) Accm: 2.96 (2.83) Acct: 4.79 (4.48) proj_loss: -0.5833 (-0.5768) time: 0.9329 data: 0.0019 [11-23 13:00:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 46/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.20 Lm: 6.622 (6.649) Lt: 5.981 (5.949) Accm: 3.10 (3.14) Acct: 5.03 (4.98) proj_loss: -0.5705 (-0.5726) time: 0.9329 data: 0.0019 [11-23 13:00:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 46/350] Total time: 0:26:38 (0.958 s / it) [11-23 13:00:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 46/350] Total time: 0:26:38 (0.958 s / it) [11-23 13:00:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 46/350] Total time: 0:26:38 (0.958 s / it) [11-23 13:00:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 46/350] Total time: 0:26:38 (0.958 s / it) [11-23 13:00:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 46/350] Total time: 0:26:38 (0.958 s / it) [11-23 13:00:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 46/350] Total time: 0:26:38 (0.958 s / it) [11-23 13:00:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 46/350] Total time: 0:26:38 (0.958 s / it) [11-23 13:00:45] (/home/user/VAR/train.py , line 276)=> [ep46] (training ) Lm: 6.611 (6.611), Lt: 5.859 (5.859), Acc m&t: 3.10 4.91, Remain: 5 days, 12:00:08, Finish: 2024-11-28 09:00 [11-23 13:00:45] (/home/user/VAR/train.py , line 276)=> [ep46] (training ) Lm: 6.611 (6.611), Lt: 5.859 (5.859), Acc m&t: 3.10 4.91, Remain: 5 days, 12:02:30, Finish: 2024-11-28 09:03 [11-23 13:00:45] (/home/user/VAR/train.py , line 276)=> [ep46] (training ) Lm: 6.611 (6.611), Lt: 5.859 (5.859), Acc m&t: 3.10 4.91, Remain: 5 days, 12:04:14, Finish: 2024-11-28 09:04 [11-23 13:00:45] (/home/user/VAR/train.py , line 276)=> [ep46] (training ) Lm: 6.611 (6.611), Lt: 5.859 (5.859), Acc m&t: 3.10 4.91, Remain: 5 days, 11:59:11, Finish: 2024-11-28 08:59 [11-23 13:00:45] (/home/user/VAR/train.py , line 276)=> [ep46] (training ) Lm: 6.611 (6.611), Lt: 5.859 (5.859), Acc m&t: 3.10 4.91, Remain: 5 days, 12:01:06, Finish: 2024-11-28 09:01 [11-23 13:00:45] (/home/user/VAR/train.py , line 276)=> [ep46] (training ) Lm: 6.611 (6.611), Lt: 5.859 (5.859), Acc m&t: 3.10 4.91, Remain: 5 days, 11:59:14, Finish: 2024-11-28 08:59 [11-23 13:00:45] (/home/user/VAR/train.py , line 276)=> [ep46] (training ) Lm: 6.611 (6.611), Lt: 5.859 (5.859), Acc m&t: 3.10 4.91, Remain: 5 days, 12:01:31, Finish: 2024-11-28 09:02 [11-23 13:00:45] (/home/user/VAR/train.py , line 276)=> [ep46] (training ) Lm: 6.611 (6.611), Lt: 5.859 (5.859), Acc m&t: 3.10 4.91, Remain: 5 days, 12:01:58, Finish: 2024-11-28 09:02 [11-23 13:00:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 0/1669] eta: 0:25:38 tlr: 0.00022 tnm: 0.21 Lm: 6.646 (6.646) Lt: 5.933 (5.933) Accm: 2.77 (2.77) Acct: 4.44 (4.44) proj_loss: -0.5741 (-0.5741) time: 0.9220 data: 0.0004 [11-23 13:00:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 0/1669] eta: 0:25:40 tlr: 0.00022 tnm: 0.21 Lm: 6.486 (6.486) Lt: 5.669 (5.669) Accm: 3.66 (3.66) Acct: 5.75 (5.75) proj_loss: -0.5816 (-0.5816) time: 0.9228 data: 0.0004 [11-23 13:00:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 0/1669] eta: 0:25:40 tlr: 0.00022 tnm: 0.21 Lm: 6.620 (6.620) Lt: 5.788 (5.788) Accm: 3.13 (3.13) Acct: 5.30 (5.30) proj_loss: -0.5573 (-0.5573) time: 0.9229 data: 0.0004 [11-23 13:00:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 0/1669] eta: 0:25:39 tlr: 0.00022 tnm: 0.21 Lm: 6.430 (6.430) Lt: 5.643 (5.643) Accm: 3.42 (3.42) Acct: 5.23 (5.23) proj_loss: -0.5491 (-0.5491) time: 0.9226 data: 0.0004 [11-23 13:00:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 0/1669] eta: 0:25:40 tlr: 0.00022 tnm: 0.21 Lm: 6.826 (6.826) Lt: 6.059 (6.059) Accm: 2.53 (2.53) Acct: 4.06 (4.06) proj_loss: -0.5492 (-0.5492) time: 0.9228 data: 0.0004 [11-23 13:00:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 0/1669] eta: 0:25:40 tlr: 0.00022 tnm: 0.21 Lm: 6.713 (6.713) Lt: 5.983 (5.983) Accm: 2.99 (2.99) Acct: 4.58 (4.58) proj_loss: -0.5487 (-0.5487) time: 0.9229 data: 0.0004 [11-23 13:00:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 0/1669] eta: 0:25:40 tlr: 0.00022 tnm: 0.21 Lm: 6.728 (6.728) Lt: 5.904 (5.904) Accm: 2.87 (2.87) Acct: 4.44 (4.44) proj_loss: -0.5187 (-0.5187) time: 0.9232 data: 0.0004 [11-23 13:00:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 0/1669] eta: 0:25:41 tlr: 0.00022 tnm: 0.21 Lm: 6.535 (6.535) Lt: 5.779 (5.779) Accm: 3.41 (3.41) Acct: 5.44 (5.44) proj_loss: -0.5758 (-0.5758) time: 0.9234 data: 0.0004 [11-23 13:07:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.20 Lm: 6.602 (6.602) Lt: 5.810 (5.810) Accm: 3.02 (3.02) Acct: 4.79 (4.79) proj_loss: -0.5735 (-0.5735) time: 0.9311 data: 0.0003 [11-23 13:07:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.20 Lm: 6.686 (6.686) Lt: 5.945 (5.945) Accm: 3.07 (3.07) Acct: 4.80 (4.80) proj_loss: -0.5604 (-0.5604) time: 0.9311 data: 0.0003 [11-23 13:07:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.20 Lm: 6.721 (6.721) Lt: 5.964 (5.964) Accm: 2.90 (2.90) Acct: 4.68 (4.68) proj_loss: -0.5618 (-0.5618) time: 0.9311 data: 0.0003 [11-23 13:07:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.20 Lm: 6.733 (6.733) Lt: 5.928 (5.928) Accm: 2.80 (2.80) Acct: 4.56 (4.56) proj_loss: -0.5300 (-0.5300) time: 0.9311 data: 0.0003 [11-23 13:07:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.20 Lm: 6.563 (6.563) Lt: 5.782 (5.782) Accm: 3.31 (3.31) Acct: 5.15 (5.15) proj_loss: -0.5794 (-0.5794) time: 0.9311 data: 0.0003 [11-23 13:07:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.20 Lm: 6.537 (6.537) Lt: 5.788 (5.788) Accm: 3.15 (3.15) Acct: 4.98 (4.98) proj_loss: -0.5748 (-0.5748) time: 0.9311 data: 0.0003 [11-23 13:07:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.20 Lm: 6.648 (6.648) Lt: 5.861 (5.861) Accm: 2.94 (2.94) Acct: 4.63 (4.63) proj_loss: -0.5509 (-0.5509) time: 0.9311 data: 0.0003 [11-23 13:07:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.20 Lm: 6.563 (6.563) Lt: 5.839 (5.839) Accm: 3.09 (3.09) Acct: 4.75 (4.75) proj_loss: -0.5618 (-0.5618) time: 0.9311 data: 0.0003 [11-23 13:13:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.21 Lm: 6.713 (6.710) Lt: 5.983 (5.963) Accm: 2.99 (2.94) Acct: 4.58 (4.66) proj_loss: -0.5600 (-0.5603) time: 0.9303 data: 0.0003 [11-23 13:13:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.21 Lm: 6.798 (6.747) Lt: 6.111 (6.013) Accm: 2.71 (2.84) Acct: 4.37 (4.58) proj_loss: -0.5663 (-0.5680) time: 0.9303 data: 0.0003 [11-23 13:13:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.21 Lm: 6.550 (6.542) Lt: 5.710 (5.762) Accm: 3.38 (3.23) Acct: 5.27 (5.07) proj_loss: -0.5741 (-0.5675) time: 0.9303 data: 0.0003 [11-23 13:13:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.21 Lm: 6.486 (6.535) Lt: 5.699 (5.754) Accm: 3.66 (3.43) Acct: 5.75 (5.43) proj_loss: -0.5772 (-0.5781) time: 0.9303 data: 0.0003 [11-23 13:13:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.21 Lm: 6.607 (6.604) Lt: 5.841 (5.821) Accm: 3.41 (3.18) Acct: 5.34 (4.97) proj_loss: -0.5758 (-0.5746) time: 0.9303 data: 0.0003 [11-23 13:13:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.21 Lm: 6.728 (6.723) Lt: 5.952 (5.966) Accm: 2.74 (2.76) Acct: 4.44 (4.50) proj_loss: -0.5412 (-0.5466) time: 0.9303 data: 0.0003 [11-23 13:13:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.21 Lm: 6.608 (6.635) Lt: 5.820 (5.847) Accm: 3.23 (3.04) Acct: 5.06 (4.78) proj_loss: -0.5527 (-0.5634) time: 0.9303 data: 0.0003 [11-23 13:13:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.21 Lm: 6.446 (6.524) Lt: 5.711 (5.797) Accm: 3.42 (3.25) Acct: 5.23 (5.00) proj_loss: -0.5491 (-0.5576) time: 0.9303 data: 0.0003 [11-23 13:20:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.21 Lm: 6.571 (6.583) Lt: 5.841 (5.840) Accm: 3.30 (3.23) Acct: 5.32 (5.11) proj_loss: -0.5542 (-0.5580) time: 0.9322 data: 0.0003 [11-23 13:20:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.21 Lm: 6.586 (6.561) Lt: 5.812 (5.800) Accm: 3.07 (3.08) Acct: 4.86 (4.79) proj_loss: -0.5748 (-0.5703) time: 0.9322 data: 0.0003 [11-23 13:20:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.21 Lm: 6.638 (6.621) Lt: 5.842 (5.854) Accm: 3.19 (3.13) Acct: 5.10 (4.94) proj_loss: -0.5763 (-0.5768) time: 0.9322 data: 0.0003 [11-23 13:20:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.21 Lm: 6.647 (6.648) Lt: 5.860 (5.861) Accm: 3.15 (3.04) Acct: 5.01 (4.82) proj_loss: -0.5569 (-0.5628) time: 0.9322 data: 0.0003 [11-23 13:20:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.21 Lm: 6.733 (6.747) Lt: 5.997 (6.006) Accm: 2.70 (2.71) Acct: 4.41 (4.36) proj_loss: -0.5605 (-0.5578) time: 0.9322 data: 0.0003 [11-23 13:20:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.21 Lm: 6.489 (6.524) Lt: 5.720 (5.751) Accm: 3.47 (3.39) Acct: 5.27 (5.27) proj_loss: -0.5764 (-0.5774) time: 0.9322 data: 0.0003 [11-23 13:20:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.21 Lm: 6.709 (6.693) Lt: 5.962 (5.963) Accm: 2.92 (2.98) Acct: 4.84 (4.81) proj_loss: -0.5733 (-0.5715) time: 0.9322 data: 0.0003 [11-23 13:20:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.21 Lm: 6.686 (6.678) Lt: 5.948 (5.950) Accm: 3.07 (3.04) Acct: 4.68 (4.69) proj_loss: -0.5661 (-0.5686) time: 0.9322 data: 0.0003 [11-23 13:26:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.713 (6.720) Lt: 5.983 (5.993) Accm: 2.99 (2.86) Acct: 4.58 (4.46) proj_loss: -0.5622 (-0.5674) time: 0.9326 data: 0.0017 [11-23 13:26:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 47/350] Total time: 0:25:56 (0.932 s / it) [11-23 13:26:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.608 (6.621) Lt: 5.820 (5.852) Accm: 3.13 (3.06) Acct: 4.96 (4.80) proj_loss: -0.5612 (-0.5721) time: 0.9326 data: 0.0019 [11-23 13:26:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.668 (6.653) Lt: 5.843 (5.877) Accm: 2.97 (3.00) Acct: 4.86 (4.70) proj_loss: -0.5767 (-0.5780) time: 0.9326 data: 0.0015 [11-23 13:26:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.728 (6.723) Lt: 5.952 (5.975) Accm: 2.74 (2.77) Acct: 4.44 (4.45) proj_loss: -0.5701 (-0.5603) time: 0.9326 data: 0.0021 [11-23 13:26:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.639 (6.682) Lt: 5.904 (5.951) Accm: 2.86 (2.96) Acct: 4.41 (4.73) proj_loss: -0.5803 (-0.5736) time: 0.9326 data: 0.0016 [11-23 13:26:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.621 (6.604) Lt: 5.914 (5.855) Accm: 2.83 (3.03) Acct: 4.44 (4.70) proj_loss: -0.5741 (-0.5696) time: 0.9326 data: 0.0020 [11-23 13:26:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.486 (6.512) Lt: 5.727 (5.746) Accm: 3.35 (3.38) Acct: 5.03 (5.22) proj_loss: -0.5772 (-0.5791) time: 0.9326 data: 0.0017 [11-23 13:26:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 47/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.638 (6.594) Lt: 5.841 (5.840) Accm: 3.19 (3.22) Acct: 5.41 (5.17) proj_loss: -0.5563 (-0.5577) time: 0.9326 data: 0.0016 [11-23 13:26:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 47/350] Total time: 0:25:56 (0.932 s / it) [11-23 13:26:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 47/350] Total time: 0:25:56 (0.932 s / it) [11-23 13:26:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 47/350] Total time: 0:25:56 (0.932 s / it) [11-23 13:26:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 47/350] Total time: 0:25:56 (0.932 s / it) [11-23 13:26:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 47/350] Total time: 0:25:56 (0.932 s / it) [11-23 13:26:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 47/350] Total time: 0:25:56 (0.932 s / it) [11-23 13:26:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 47/350] Total time: 0:25:56 (0.932 s / it) [11-23 13:26:41] (/home/user/VAR/train.py , line 276)=> [ep47] (training ) Lm: 6.611 (6.627), Lt: 5.859 (5.884), Acc m&t: 3.10 4.91, Remain: 5 days, 11:39:24, Finish: 2024-11-28 09:06 [11-23 13:26:41] (/home/user/VAR/train.py , line 276)=> [ep47] (training ) Lm: 6.611 (6.627), Lt: 5.859 (5.884), Acc m&t: 3.10 4.91, Remain: 5 days, 11:38:25, Finish: 2024-11-28 09:05 [11-23 13:26:41] (/home/user/VAR/train.py , line 276)=> [ep47] (training ) Lm: 6.611 (6.627), Lt: 5.859 (5.884), Acc m&t: 3.10 4.91, Remain: 5 days, 11:38:24, Finish: 2024-11-28 09:05 [11-23 13:26:41] (/home/user/VAR/train.py , line 276)=> [ep47] (training ) Lm: 6.611 (6.627), Lt: 5.859 (5.884), Acc m&t: 3.10 4.91, Remain: 5 days, 11:36:39, Finish: 2024-11-28 09:03 [11-23 13:26:41] (/home/user/VAR/train.py , line 276)=> [ep47] (training ) Lm: 6.611 (6.627), Lt: 5.859 (5.884), Acc m&t: 3.10 4.91, Remain: 5 days, 11:36:46, Finish: 2024-11-28 09:03 [11-23 13:26:41] (/home/user/VAR/train.py , line 276)=> [ep47] (training ) Lm: 6.611 (6.627), Lt: 5.859 (5.884), Acc m&t: 3.10 4.91, Remain: 5 days, 11:36:16, Finish: 2024-11-28 09:02 [11-23 13:26:41] (/home/user/VAR/train.py , line 276)=> [ep47] (training ) Lm: 6.611 (6.627), Lt: 5.859 (5.884), Acc m&t: 3.10 4.91, Remain: 5 days, 11:36:59, Finish: 2024-11-28 09:03 [11-23 13:26:41] (/home/user/VAR/train.py , line 276)=> [ep47] (training ) Lm: 6.611 (6.627), Lt: 5.859 (5.884), Acc m&t: 3.10 4.91, Remain: 5 days, 11:39:02, Finish: 2024-11-28 09:05 [11-23 13:26:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 0/1669] eta: 0:25:10 tlr: 0.00022 tnm: 0.22 Lm: 6.661 (6.661) Lt: 5.924 (5.924) Accm: 3.06 (3.06) Acct: 4.99 (4.99) proj_loss: -0.5830 (-0.5830) time: 0.9049 data: 0.0004 [11-23 13:26:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 0/1669] eta: 0:25:10 tlr: 0.00022 tnm: 0.22 Lm: 6.627 (6.627) Lt: 5.892 (5.892) Accm: 3.12 (3.12) Acct: 5.17 (5.17) proj_loss: -0.5739 (-0.5739) time: 0.9050 data: 0.0004 [11-23 13:26:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 0/1669] eta: 0:26:12 tlr: 0.00022 tnm: 0.22 Lm: 6.548 (6.548) Lt: 5.764 (5.764) Accm: 3.53 (3.53) Acct: 5.30 (5.30) proj_loss: -0.5743 (-0.5743) time: 0.9419 data: 0.0004 [11-23 13:26:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 0/1669] eta: 0:25:14 tlr: 0.00022 tnm: 0.22 Lm: 6.622 (6.622) Lt: 5.929 (5.929) Accm: 3.03 (3.03) Acct: 5.37 (5.37) proj_loss: -0.5995 (-0.5995) time: 0.9077 data: 0.0004 [11-23 13:26:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 0/1669] eta: 0:24:17 tlr: 0.00022 tnm: 0.22 Lm: 6.526 (6.526) Lt: 5.746 (5.746) Accm: 2.94 (2.94) Acct: 4.89 (4.89) proj_loss: -0.5814 (-0.5814) time: 0.8731 data: 0.0004 [11-23 13:26:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 0/1669] eta: 0:25:14 tlr: 0.00022 tnm: 0.22 Lm: 6.447 (6.447) Lt: 5.609 (5.609) Accm: 3.44 (3.44) Acct: 5.51 (5.51) proj_loss: -0.5855 (-0.5855) time: 0.9073 data: 0.0003 [11-23 13:26:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 0/1669] eta: 0:26:09 tlr: 0.00022 tnm: 0.22 Lm: 6.486 (6.486) Lt: 5.789 (5.789) Accm: 3.69 (3.69) Acct: 5.37 (5.37) proj_loss: -0.5941 (-0.5941) time: 0.9405 data: 0.0004 [11-23 13:26:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 0/1669] eta: 0:24:15 tlr: 0.00022 tnm: 0.22 Lm: 6.409 (6.409) Lt: 5.638 (5.638) Accm: 3.60 (3.60) Acct: 5.85 (5.85) proj_loss: -0.5741 (-0.5741) time: 0.8719 data: 0.0003 [11-23 13:33:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 417/1669] eta: 0:21:08 tlr: 0.00022 tnm: 0.20 Lm: 6.682 (6.682) Lt: 5.947 (5.947) Accm: 2.84 (2.84) Acct: 4.46 (4.46) proj_loss: -0.5729 (-0.5729) time: 0.9338 data: 0.0003 [11-23 13:33:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 417/1669] eta: 0:21:08 tlr: 0.00022 tnm: 0.20 Lm: 6.566 (6.566) Lt: 5.761 (5.761) Accm: 3.37 (3.37) Acct: 5.48 (5.48) proj_loss: -0.5711 (-0.5711) time: 0.9338 data: 0.0003 [11-23 13:33:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 417/1669] eta: 0:21:08 tlr: 0.00022 tnm: 0.20 Lm: 6.610 (6.610) Lt: 5.866 (5.866) Accm: 2.97 (2.97) Acct: 4.86 (4.86) proj_loss: -0.5770 (-0.5770) time: 0.9338 data: 0.0003 [11-23 13:33:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 417/1669] eta: 0:21:08 tlr: 0.00022 tnm: 0.20 Lm: 6.589 (6.589) Lt: 5.802 (5.802) Accm: 3.22 (3.22) Acct: 4.89 (4.89) proj_loss: -0.5620 (-0.5620) time: 0.9338 data: 0.0003 [11-23 13:33:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 417/1669] eta: 0:21:08 tlr: 0.00022 tnm: 0.20 Lm: 6.718 (6.718) Lt: 6.018 (6.018) Accm: 2.74 (2.74) Acct: 4.80 (4.80) proj_loss: -0.5904 (-0.5904) time: 0.9338 data: 0.0003 [11-23 13:33:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 417/1669] eta: 0:21:08 tlr: 0.00022 tnm: 0.20 Lm: 6.490 (6.490) Lt: 5.741 (5.741) Accm: 3.50 (3.50) Acct: 5.34 (5.34) proj_loss: -0.5870 (-0.5870) time: 0.9338 data: 0.0003 [11-23 13:33:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 417/1669] eta: 0:21:08 tlr: 0.00022 tnm: 0.20 Lm: 6.420 (6.420) Lt: 5.637 (5.637) Accm: 3.43 (3.43) Acct: 5.37 (5.37) proj_loss: -0.5858 (-0.5858) time: 0.9338 data: 0.0003 [11-23 13:33:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 417/1669] eta: 0:21:08 tlr: 0.00022 tnm: 0.20 Lm: 6.576 (6.576) Lt: 5.815 (5.815) Accm: 3.35 (3.35) Acct: 5.41 (5.41) proj_loss: -0.5615 (-0.5615) time: 0.9338 data: 0.0003 [11-23 13:40:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 834/1669] eta: 0:13:33 tlr: 0.00022 tnm: 0.21 Lm: 6.627 (6.694) Lt: 5.892 (5.952) Accm: 3.12 (2.94) Acct: 5.17 (4.79) proj_loss: -0.5739 (-0.5738) time: 0.9331 data: 0.0003 [11-23 13:40:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 834/1669] eta: 0:13:33 tlr: 0.00022 tnm: 0.21 Lm: 6.447 (6.523) Lt: 5.665 (5.755) Accm: 3.42 (3.18) Acct: 5.23 (5.00) proj_loss: -0.5855 (-0.5843) time: 0.9331 data: 0.0003 [11-23 13:40:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 834/1669] eta: 0:13:33 tlr: 0.00022 tnm: 0.21 Lm: 6.494 (6.492) Lt: 5.715 (5.733) Accm: 3.31 (3.40) Acct: 5.30 (5.26) proj_loss: -0.5799 (-0.5740) time: 0.9331 data: 0.0003 [11-23 13:40:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 834/1669] eta: 0:13:33 tlr: 0.00022 tnm: 0.21 Lm: 6.526 (6.524) Lt: 5.746 (5.760) Accm: 3.00 (3.31) Acct: 4.89 (5.35) proj_loss: -0.5725 (-0.5676) time: 0.9331 data: 0.0003 [11-23 13:40:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 834/1669] eta: 0:13:33 tlr: 0.00022 tnm: 0.21 Lm: 6.548 (6.536) Lt: 5.764 (5.735) Accm: 3.53 (3.46) Acct: 5.30 (5.33) proj_loss: -0.5497 (-0.5486) time: 0.9331 data: 0.0003 [11-23 13:40:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 834/1669] eta: 0:13:33 tlr: 0.00022 tnm: 0.21 Lm: 6.622 (6.666) Lt: 5.929 (5.942) Accm: 3.03 (2.94) Acct: 5.03 (4.88) proj_loss: -0.5813 (-0.5772) time: 0.9331 data: 0.0003 [11-23 13:40:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 834/1669] eta: 0:13:33 tlr: 0.00022 tnm: 0.21 Lm: 6.661 (6.601) Lt: 5.879 (5.800) Accm: 3.06 (3.04) Acct: 4.99 (4.87) proj_loss: -0.5809 (-0.5744) time: 0.9331 data: 0.0003 [11-23 13:40:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [ 834/1669] eta: 0:13:33 tlr: 0.00022 tnm: 0.21 Lm: 6.721 (6.695) Lt: 6.019 (5.971) Accm: 2.75 (2.81) Acct: 4.34 (4.42) proj_loss: -0.5716 (-0.5704) time: 0.9331 data: 0.0003 [11-23 13:46:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [1251/1669] eta: 0:06:41 tlr: 0.00022 tnm: 0.21 Lm: 6.598 (6.640) Lt: 5.829 (5.885) Accm: 3.09 (2.96) Acct: 4.87 (4.67) proj_loss: -0.5729 (-0.5721) time: 0.9323 data: 0.0003 [11-23 13:46:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [1251/1669] eta: 0:06:41 tlr: 0.00022 tnm: 0.21 Lm: 6.592 (6.557) Lt: 5.850 (5.809) Accm: 2.97 (3.18) Acct: 4.86 (5.04) proj_loss: -0.5640 (-0.5646) time: 0.9323 data: 0.0003 [11-23 13:46:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [1251/1669] eta: 0:06:41 tlr: 0.00022 tnm: 0.21 Lm: 6.647 (6.668) Lt: 5.961 (5.954) Accm: 2.85 (2.87) Acct: 4.63 (4.62) proj_loss: -0.5871 (-0.5811) time: 0.9323 data: 0.0003 [11-23 13:46:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [1251/1669] eta: 0:06:41 tlr: 0.00022 tnm: 0.21 Lm: 6.493 (6.492) Lt: 5.752 (5.747) Accm: 3.30 (3.37) Acct: 5.25 (5.24) proj_loss: -0.5727 (-0.5719) time: 0.9323 data: 0.0003 [11-23 13:46:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [1251/1669] eta: 0:06:41 tlr: 0.00022 tnm: 0.21 Lm: 6.560 (6.545) Lt: 5.762 (5.741) Accm: 3.47 (3.45) Acct: 5.46 (5.40) proj_loss: -0.5458 (-0.5470) time: 0.9323 data: 0.0003 [11-23 13:46:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [1251/1669] eta: 0:06:41 tlr: 0.00022 tnm: 0.21 Lm: 6.666 (6.638) Lt: 5.902 (5.839) Accm: 3.06 (3.04) Acct: 5.08 (4.94) proj_loss: -0.5819 (-0.5815) time: 0.9323 data: 0.0003 [11-23 13:46:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [1251/1669] eta: 0:06:41 tlr: 0.00022 tnm: 0.21 Lm: 6.700 (6.714) Lt: 5.938 (5.960) Accm: 2.90 (2.88) Acct: 4.73 (4.67) proj_loss: -0.5631 (-0.5684) time: 0.9323 data: 0.0003 [11-23 13:46:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [1251/1669] eta: 0:06:41 tlr: 0.00022 tnm: 0.21 Lm: 6.586 (6.574) Lt: 5.807 (5.804) Accm: 3.23 (3.14) Acct: 4.99 (4.94) proj_loss: -0.5834 (-0.5761) time: 0.9323 data: 0.0003 [11-23 13:53:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.634 (6.586) Lt: 5.888 (5.821) Accm: 3.39 (3.19) Acct: 5.23 (5.07) proj_loss: -0.5814 (-0.5721) time: 0.9356 data: 0.0022 [11-23 13:53:12] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 48/350] Total time: 0:26:30 (0.953 s / it) [11-23 13:53:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.627 (6.674) Lt: 5.892 (5.915) Accm: 3.12 (3.05) Acct: 5.17 (4.93) proj_loss: -0.5739 (-0.5727) time: 0.9356 data: 0.0017 [11-23 13:53:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.661 (6.635) Lt: 5.888 (5.849) Accm: 3.06 (3.07) Acct: 5.13 (4.98) proj_loss: -0.5830 (-0.5850) time: 0.9356 data: 0.0016 [11-23 13:53:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.548 (6.536) Lt: 5.759 (5.731) Accm: 3.42 (3.44) Acct: 5.61 (5.47) proj_loss: -0.5497 (-0.5544) time: 0.9356 data: 0.0018 [11-23 13:53:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.622 (6.640) Lt: 5.929 (5.912) Accm: 3.03 (2.93) Acct: 5.03 (4.70) proj_loss: -0.5930 (-0.5883) time: 0.9356 data: 0.0016 [11-23 13:53:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.634 (6.572) Lt: 5.924 (5.832) Accm: 2.99 (3.14) Acct: 4.89 (5.01) proj_loss: -0.5725 (-0.5729) time: 0.9355 data: 0.0017 [11-23 13:53:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.492 (6.474) Lt: 5.715 (5.732) Accm: 3.31 (3.46) Acct: 5.30 (5.38) proj_loss: -0.5664 (-0.5708) time: 0.9355 data: 0.0021 [11-23 13:53:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 48/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.498 (6.612) Lt: 5.736 (5.855) Accm: 3.42 (3.11) Acct: 5.27 (4.79) proj_loss: -0.5716 (-0.5685) time: 0.9356 data: 0.0017 [11-23 13:53:12] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 48/350] Total time: 0:26:30 (0.953 s / it) [11-23 13:53:12] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 48/350] Total time: 0:26:30 (0.953 s / it) [11-23 13:53:12] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 48/350] Total time: 0:26:30 (0.953 s / it) [11-23 13:53:12] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 48/350] Total time: 0:26:30 (0.953 s / it) [11-23 13:53:12] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 48/350] Total time: 0:26:30 (0.953 s / it) [11-23 13:53:12] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 48/350] Total time: 0:26:30 (0.953 s / it) [11-23 13:53:12] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 48/350] Total time: 0:26:30 (0.953 s / it) [11-23 13:53:12] (/home/user/VAR/train.py , line 276)=> [ep48] (training ) Lm: 6.611 (6.619), Lt: 5.859 (5.867), Acc m&t: 3.10 4.91, Remain: 5 days, 11:34:05, Finish: 2024-11-28 09:27 [11-23 13:53:12] (/home/user/VAR/train.py , line 276)=> [ep48] (training ) Lm: 6.611 (6.619), Lt: 5.859 (5.867), Acc m&t: 3.10 4.91, Remain: 5 days, 11:32:40, Finish: 2024-11-28 09:25 [11-23 13:53:12] (/home/user/VAR/train.py , line 276)=> [ep48] (training ) Lm: 6.611 (6.619), Lt: 5.859 (5.867), Acc m&t: 3.10 4.91, Remain: 5 days, 11:32:46, Finish: 2024-11-28 09:25 [11-23 13:53:12] (/home/user/VAR/train.py , line 276)=> [ep48] (training ) Lm: 6.611 (6.619), Lt: 5.859 (5.867), Acc m&t: 3.10 4.91, Remain: 5 days, 11:33:25, Finish: 2024-11-28 09:26 [11-23 13:53:12] (/home/user/VAR/train.py , line 276)=> [ep48] (training ) Lm: 6.611 (6.619), Lt: 5.859 (5.867), Acc m&t: 3.10 4.91, Remain: 5 days, 11:34:01, Finish: 2024-11-28 09:27 [11-23 13:53:12] (/home/user/VAR/train.py , line 276)=> [ep48] (training ) Lm: 6.611 (6.619), Lt: 5.859 (5.867), Acc m&t: 3.10 4.91, Remain: 5 days, 11:33:28, Finish: 2024-11-28 09:26 [11-23 13:53:12] (/home/user/VAR/train.py , line 276)=> [ep48] (training ) Lm: 6.611 (6.619), Lt: 5.859 (5.867), Acc m&t: 3.10 4.91, Remain: 5 days, 11:34:29, Finish: 2024-11-28 09:27 [11-23 13:53:12] (/home/user/VAR/train.py , line 276)=> [ep48] (training ) Lm: 6.611 (6.619), Lt: 5.859 (5.867), Acc m&t: 3.10 4.91, Remain: 5 days, 11:31:55, Finish: 2024-11-28 09:25 [11-23 13:53:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 0/1669] eta: 0:24:50 tlr: 0.00022 tnm: 0.22 Lm: 6.611 (6.611) Lt: 5.833 (5.833) Accm: 3.29 (3.29) Acct: 5.30 (5.30) proj_loss: -0.5751 (-0.5751) time: 0.8929 data: 0.0004 [11-23 13:53:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 0/1669] eta: 0:24:50 tlr: 0.00022 tnm: 0.22 Lm: 6.696 (6.696) Lt: 6.014 (6.014) Accm: 2.96 (2.96) Acct: 4.34 (4.34) proj_loss: -0.6041 (-0.6041) time: 0.8929 data: 0.0003 [11-23 13:53:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 0/1669] eta: 0:24:49 tlr: 0.00022 tnm: 0.22 Lm: 6.426 (6.426) Lt: 5.711 (5.711) Accm: 3.82 (3.82) Acct: 5.85 (5.85) proj_loss: -0.5952 (-0.5952) time: 0.8926 data: 0.0004 [11-23 13:53:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 0/1669] eta: 0:24:50 tlr: 0.00022 tnm: 0.22 Lm: 6.651 (6.651) Lt: 5.869 (5.869) Accm: 2.80 (2.80) Acct: 4.79 (4.79) proj_loss: -0.5481 (-0.5481) time: 0.8928 data: 0.0003 [11-23 13:53:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 0/1669] eta: 0:24:51 tlr: 0.00022 tnm: 0.22 Lm: 6.580 (6.580) Lt: 5.839 (5.839) Accm: 3.26 (3.26) Acct: 4.92 (4.92) proj_loss: -0.5432 (-0.5432) time: 0.8934 data: 0.0004 [11-23 13:53:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 0/1669] eta: 0:24:50 tlr: 0.00022 tnm: 0.22 Lm: 6.445 (6.445) Lt: 5.665 (5.665) Accm: 3.77 (3.77) Acct: 5.92 (5.92) proj_loss: -0.5686 (-0.5686) time: 0.8931 data: 0.0004 [11-23 13:53:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 0/1669] eta: 0:24:51 tlr: 0.00022 tnm: 0.22 Lm: 6.713 (6.713) Lt: 6.001 (6.001) Accm: 2.65 (2.65) Acct: 4.34 (4.34) proj_loss: -0.5544 (-0.5544) time: 0.8936 data: 0.0004 [11-23 13:53:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 0/1669] eta: 0:24:51 tlr: 0.00022 tnm: 0.22 Lm: 6.667 (6.667) Lt: 5.920 (5.920) Accm: 2.86 (2.86) Acct: 4.82 (4.82) proj_loss: -0.5676 (-0.5676) time: 0.8936 data: 0.0003 [11-23 13:59:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.21 Lm: 6.571 (6.571) Lt: 5.838 (5.838) Accm: 3.01 (3.01) Acct: 4.91 (4.91) proj_loss: -0.5780 (-0.5780) time: 0.9308 data: 0.0003 [11-23 13:59:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.21 Lm: 6.577 (6.577) Lt: 5.849 (5.849) Accm: 3.18 (3.18) Acct: 5.11 (5.11) proj_loss: -0.5824 (-0.5824) time: 0.9308 data: 0.0003 [11-23 13:59:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.21 Lm: 6.700 (6.700) Lt: 6.003 (6.003) Accm: 3.04 (3.04) Acct: 4.56 (4.56) proj_loss: -0.5864 (-0.5864) time: 0.9308 data: 0.0003 [11-23 13:59:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.21 Lm: 6.570 (6.570) Lt: 5.799 (5.799) Accm: 3.19 (3.19) Acct: 5.11 (5.11) proj_loss: -0.5651 (-0.5651) time: 0.9308 data: 0.0003 [11-23 13:59:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.21 Lm: 6.521 (6.521) Lt: 5.829 (5.829) Accm: 3.46 (3.46) Acct: 5.39 (5.39) proj_loss: -0.5674 (-0.5674) time: 0.9308 data: 0.0003 [11-23 13:59:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.21 Lm: 6.529 (6.529) Lt: 5.738 (5.738) Accm: 3.31 (3.31) Acct: 5.42 (5.42) proj_loss: -0.5785 (-0.5785) time: 0.9308 data: 0.0003 [11-23 13:59:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.21 Lm: 6.562 (6.562) Lt: 5.747 (5.747) Accm: 3.13 (3.13) Acct: 5.22 (5.22) proj_loss: -0.5635 (-0.5635) time: 0.9308 data: 0.0003 [11-23 13:59:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.21 Lm: 6.612 (6.612) Lt: 5.853 (5.853) Accm: 3.21 (3.21) Acct: 5.15 (5.15) proj_loss: -0.5642 (-0.5642) time: 0.9308 data: 0.0003 [11-23 14:06:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 834/1669] eta: 0:13:07 tlr: 0.00022 tnm: 0.22 Lm: 6.527 (6.584) Lt: 5.787 (5.831) Accm: 3.06 (3.16) Acct: 4.75 (5.02) proj_loss: -0.5686 (-0.5657) time: 0.9291 data: 0.0003 [11-23 14:06:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 834/1669] eta: 0:13:07 tlr: 0.00022 tnm: 0.22 Lm: 6.727 (6.630) Lt: 5.986 (5.919) Accm: 3.19 (3.19) Acct: 4.96 (5.06) proj_loss: -0.5952 (-0.5866) time: 0.9291 data: 0.0003 [11-23 14:06:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 834/1669] eta: 0:13:07 tlr: 0.00022 tnm: 0.22 Lm: 6.696 (6.619) Lt: 5.992 (5.899) Accm: 3.12 (3.21) Acct: 4.79 (4.81) proj_loss: -0.5687 (-0.5745) time: 0.9291 data: 0.0003 [11-23 14:06:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 834/1669] eta: 0:13:07 tlr: 0.00022 tnm: 0.22 Lm: 6.580 (6.643) Lt: 5.839 (5.869) Accm: 3.12 (2.99) Acct: 4.92 (4.90) proj_loss: -0.5571 (-0.5624) time: 0.9291 data: 0.0003 [11-23 14:06:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 834/1669] eta: 0:13:07 tlr: 0.00022 tnm: 0.22 Lm: 6.556 (6.560) Lt: 5.716 (5.737) Accm: 3.37 (3.21) Acct: 5.41 (5.28) proj_loss: -0.5786 (-0.5686) time: 0.9291 data: 0.0003 [11-23 14:06:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 834/1669] eta: 0:13:07 tlr: 0.00022 tnm: 0.22 Lm: 6.713 (6.604) Lt: 6.000 (5.886) Accm: 2.65 (3.18) Acct: 4.34 (5.00) proj_loss: -0.5687 (-0.5678) time: 0.9291 data: 0.0003 [11-23 14:06:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 834/1669] eta: 0:13:07 tlr: 0.00022 tnm: 0.22 Lm: 6.667 (6.611) Lt: 5.920 (5.891) Accm: 2.86 (2.95) Acct: 4.82 (4.80) proj_loss: -0.5846 (-0.5802) time: 0.9291 data: 0.0003 [11-23 14:06:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [ 834/1669] eta: 0:13:07 tlr: 0.00022 tnm: 0.22 Lm: 6.611 (6.570) Lt: 5.833 (5.795) Accm: 3.29 (3.09) Acct: 5.30 (4.97) proj_loss: -0.5751 (-0.5706) time: 0.9292 data: 0.0003 [11-23 14:12:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [1251/1669] eta: 0:06:36 tlr: 0.00022 tnm: 0.21 Lm: 6.631 (6.595) Lt: 5.871 (5.836) Accm: 2.97 (2.98) Acct: 4.73 (4.77) proj_loss: -0.5649 (-0.5619) time: 1.0008 data: 0.0003 [11-23 14:12:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [1251/1669] eta: 0:06:36 tlr: 0.00022 tnm: 0.21 Lm: 6.590 (6.601) Lt: 5.852 (5.852) Accm: 2.85 (3.00) Acct: 4.56 (4.80) proj_loss: -0.5687 (-0.5719) time: 1.0008 data: 0.0003 [11-23 14:12:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [1251/1669] eta: 0:06:36 tlr: 0.00022 tnm: 0.21 Lm: 6.643 (6.596) Lt: 5.907 (5.868) Accm: 2.94 (3.19) Acct: 4.68 (5.01) proj_loss: -0.5664 (-0.5669) time: 1.0008 data: 0.0003 [11-23 14:12:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [1251/1669] eta: 0:06:36 tlr: 0.00022 tnm: 0.21 Lm: 6.604 (6.639) Lt: 5.832 (5.858) Accm: 3.10 (3.01) Acct: 4.86 (4.87) proj_loss: -0.5721 (-0.5751) time: 1.0008 data: 0.0003 [11-23 14:12:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [1251/1669] eta: 0:06:36 tlr: 0.00022 tnm: 0.21 Lm: 6.602 (6.582) Lt: 5.777 (5.762) Accm: 3.08 (3.05) Acct: 5.10 (5.13) proj_loss: -0.5704 (-0.5670) time: 1.0008 data: 0.0003 [11-23 14:12:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [1251/1669] eta: 0:06:36 tlr: 0.00022 tnm: 0.21 Lm: 6.661 (6.621) Lt: 5.960 (5.906) Accm: 3.04 (3.12) Acct: 4.72 (4.77) proj_loss: -0.5735 (-0.5754) time: 1.0008 data: 0.0003 [11-23 14:12:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [1251/1669] eta: 0:06:36 tlr: 0.00022 tnm: 0.21 Lm: 6.624 (6.603) Lt: 5.859 (5.872) Accm: 3.21 (3.20) Acct: 5.08 (5.10) proj_loss: -0.5823 (-0.5790) time: 1.0008 data: 0.0003 [11-23 14:12:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [1251/1669] eta: 0:06:36 tlr: 0.00022 tnm: 0.21 Lm: 6.633 (6.608) Lt: 5.918 (5.897) Accm: 3.01 (3.06) Acct: 4.91 (4.97) proj_loss: -0.5761 (-0.5761) time: 1.0008 data: 0.0003 [11-23 14:19:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.22 Lm: 6.640 (6.614) Lt: 5.915 (5.891) Accm: 3.16 (3.09) Acct: 4.82 (4.94) proj_loss: -0.5758 (-0.5761) time: 0.9326 data: 0.0015 [11-23 14:19:51] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 49/350] Total time: 0:26:38 (0.958 s / it) [11-23 14:19:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.22 Lm: 6.527 (6.581) Lt: 5.787 (5.820) Accm: 3.06 (3.05) Acct: 4.75 (4.88) proj_loss: -0.5686 (-0.5707) time: 0.9326 data: 0.0016 [11-23 14:19:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.22 Lm: 6.652 (6.608) Lt: 5.907 (5.850) Accm: 2.86 (2.95) Acct: 4.72 (4.76) proj_loss: -0.5547 (-0.5602) time: 0.9326 data: 0.0018 [11-23 14:19:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.22 Lm: 6.577 (6.581) Lt: 5.721 (5.754) Accm: 3.31 (3.10) Acct: 5.41 (5.23) proj_loss: -0.5631 (-0.5662) time: 0.9326 data: 0.0019 [11-23 14:19:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.22 Lm: 6.713 (6.634) Lt: 6.000 (5.929) Accm: 2.70 (3.09) Acct: 4.34 (4.81) proj_loss: -0.5687 (-0.5698) time: 0.9326 data: 0.0018 [11-23 14:19:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.22 Lm: 6.528 (6.588) Lt: 5.731 (5.838) Accm: 3.23 (3.32) Acct: 5.20 (5.40) proj_loss: -0.5695 (-0.5706) time: 0.9326 data: 0.0019 [11-23 14:19:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.22 Lm: 6.580 (6.577) Lt: 5.825 (5.784) Accm: 3.12 (3.25) Acct: 4.92 (5.28) proj_loss: -0.5871 (-0.5814) time: 0.9326 data: 0.0020 [11-23 14:19:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 49/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.22 Lm: 6.627 (6.613) Lt: 5.929 (5.894) Accm: 3.12 (3.18) Acct: 4.79 (4.91) proj_loss: -0.5687 (-0.5734) time: 0.9326 data: 0.0016 [11-23 14:19:51] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 49/350] Total time: 0:26:38 (0.958 s / it) [11-23 14:19:51] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 49/350] Total time: 0:26:38 (0.958 s / it) [11-23 14:19:51] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 49/350] Total time: 0:26:38 (0.958 s / it) [11-23 14:19:51] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 49/350] Total time: 0:26:38 (0.958 s / it) [11-23 14:19:51] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 49/350] Total time: 0:26:38 (0.958 s / it) [11-23 14:19:51] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 49/350] Total time: 0:26:38 (0.958 s / it) [11-23 14:19:51] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 49/350] Total time: 0:26:38 (0.958 s / it) [11-23 14:21:59] (home/user/VAR/trainer.py, line 114)=> FID: 4.127485460700541 [11-23 14:22:00] (/home/user/VAR/train.py , line 259)=> [*] [ep49] (val 50000) Lm: 6.6075, Lt: 5.8584, Acc m&t: 3.12 4.96, Val cost: 128.69s [11-23 14:22:00] (/home/user/VAR/train.py , line 264)=> [saving ckpt] ... [saving ckpt](*) finished! @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth [11-23 14:23:16] (/home/user/VAR/train.py , line 276)=> [ep49] (training ) Lm: 6.608 (6.608), Lt: 5.858 (5.858), Acc m&t: 3.12 4.96, Remain: 5 days, 10:22:26, Finish: 2024-11-28 08:42 [11-23 14:23:16] (/home/user/VAR/train.py , line 276)=> [ep49] (training ) Lm: 6.608 (6.608), Lt: 5.858 (5.858), Acc m&t: 3.12 4.96, Remain: 5 days, 10:23:10, Finish: 2024-11-28 08:43 [11-23 14:23:16] (/home/user/VAR/train.py , line 276)=> [ep49] (training ) Lm: 6.608 (6.608), Lt: 5.858 (5.858), Acc m&t: 3.12 4.96, Remain: 5 days, 10:23:27, Finish: 2024-11-28 08:43 [11-23 14:23:16] (/home/user/VAR/train.py , line 276)=> [ep49] (training ) Lm: 6.608 (6.608), Lt: 5.858 (5.858), Acc m&t: 3.12 4.96, Remain: 5 days, 10:23:59, Finish: 2024-11-28 08:43 [11-23 14:23:16] (/home/user/VAR/train.py , line 276)=> [ep49] (training ) Lm: 6.608 (6.608), Lt: 5.858 (5.858), Acc m&t: 3.12 4.96, Remain: 5 days, 10:25:20, Finish: 2024-11-28 08:45 [11-23 14:23:16] (/home/user/VAR/train.py , line 276)=> [ep49] (training ) Lm: 6.608 (6.608), Lt: 5.858 (5.858), Acc m&t: 3.12 4.96, Remain: 5 days, 10:25:38, Finish: 2024-11-28 08:45 [11-23 14:23:16] (/home/user/VAR/train.py , line 276)=> [ep49] (training ) Lm: 6.608 (6.608), Lt: 5.858 (5.858), Acc m&t: 3.12 4.96, Remain: 5 days, 10:24:49, Finish: 2024-11-28 08:44 [11-23 14:23:16] (/home/user/VAR/train.py , line 276)=> [ep49] (training ) Lm: 6.608 (6.608), Lt: 5.858 (5.858), Acc m&t: 3.12 4.96, Remain: 5 days, 10:25:17, Finish: 2024-11-28 08:45 [11-23 14:23:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 0/1669] eta: 0:24:53 tlr: 0.00022 tnm: 0.22 Lm: 6.391 (6.391) Lt: 5.607 (5.607) Accm: 3.96 (3.96) Acct: 6.27 (6.27) proj_loss: -0.5778 (-0.5778) time: 0.8948 data: 0.0004 [11-23 14:23:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 0/1669] eta: 0:24:55 tlr: 0.00022 tnm: 0.22 Lm: 6.734 (6.734) Lt: 5.972 (5.972) Accm: 2.68 (2.68) Acct: 4.44 (4.44) proj_loss: -0.5900 (-0.5900) time: 0.8958 data: 0.0003 [11-23 14:23:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 0/1669] eta: 0:25:27 tlr: 0.00022 tnm: 0.22 Lm: 6.427 (6.427) Lt: 5.628 (5.628) Accm: 3.44 (3.44) Acct: 5.89 (5.89) proj_loss: -0.5546 (-0.5546) time: 0.9150 data: 0.0004 [11-23 14:23:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 0/1669] eta: 0:24:55 tlr: 0.00022 tnm: 0.22 Lm: 6.485 (6.485) Lt: 5.687 (5.687) Accm: 3.63 (3.63) Acct: 5.41 (5.41) proj_loss: -0.5810 (-0.5810) time: 0.8960 data: 0.0004 [11-23 14:23:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 0/1669] eta: 0:24:55 tlr: 0.00022 tnm: 0.22 Lm: 6.589 (6.589) Lt: 5.832 (5.832) Accm: 3.32 (3.32) Acct: 5.20 (5.20) proj_loss: -0.5675 (-0.5675) time: 0.8958 data: 0.0003 [11-23 14:23:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 0/1669] eta: 0:24:56 tlr: 0.00022 tnm: 0.22 Lm: 6.585 (6.585) Lt: 5.956 (5.956) Accm: 3.06 (3.06) Acct: 4.13 (4.13) proj_loss: -0.5798 (-0.5798) time: 0.8966 data: 0.0004 [11-23 14:23:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 0/1669] eta: 0:24:56 tlr: 0.00022 tnm: 0.22 Lm: 6.828 (6.828) Lt: 6.159 (6.159) Accm: 2.67 (2.67) Acct: 4.30 (4.30) proj_loss: -0.6156 (-0.6156) time: 0.8966 data: 0.0004 [11-23 14:23:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 0/1669] eta: 0:24:56 tlr: 0.00022 tnm: 0.22 Lm: 6.612 (6.612) Lt: 5.861 (5.861) Accm: 3.16 (3.16) Acct: 4.86 (4.86) proj_loss: -0.5746 (-0.5746) time: 0.8966 data: 0.0004 [11-23 14:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.22 Lm: 6.544 (6.544) Lt: 5.731 (5.731) Accm: 3.42 (3.42) Acct: 5.32 (5.32) proj_loss: -0.5780 (-0.5780) time: 0.9317 data: 0.0003 [11-23 14:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.22 Lm: 6.450 (6.450) Lt: 5.657 (5.657) Accm: 3.69 (3.69) Acct: 5.89 (5.89) proj_loss: -0.5637 (-0.5637) time: 0.9317 data: 0.0003 [11-23 14:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.22 Lm: 6.609 (6.609) Lt: 5.931 (5.931) Accm: 3.04 (3.04) Acct: 4.56 (4.56) proj_loss: -0.5697 (-0.5697) time: 0.9317 data: 0.0003 [11-23 14:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.22 Lm: 6.725 (6.725) Lt: 6.037 (6.037) Accm: 2.61 (2.61) Acct: 4.18 (4.18) proj_loss: -0.5937 (-0.5937) time: 0.9317 data: 0.0003 [11-23 14:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.22 Lm: 6.596 (6.596) Lt: 5.838 (5.838) Accm: 3.19 (3.19) Acct: 5.04 (5.04) proj_loss: -0.5529 (-0.5529) time: 0.9317 data: 0.0003 [11-23 14:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.22 Lm: 6.501 (6.501) Lt: 5.737 (5.737) Accm: 3.36 (3.36) Acct: 5.13 (5.13) proj_loss: -0.5723 (-0.5723) time: 0.9317 data: 0.0003 [11-23 14:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.22 Lm: 6.638 (6.638) Lt: 5.861 (5.861) Accm: 2.84 (2.84) Acct: 4.63 (4.63) proj_loss: -0.5854 (-0.5854) time: 0.9317 data: 0.0003 [11-23 14:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.22 Lm: 6.675 (6.675) Lt: 5.956 (5.956) Accm: 2.83 (2.83) Acct: 4.72 (4.72) proj_loss: -0.5642 (-0.5642) time: 0.9317 data: 0.0003 [11-23 14:36:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.20 Lm: 6.587 (6.645) Lt: 5.859 (5.923) Accm: 3.19 (2.95) Acct: 5.03 (4.82) proj_loss: -0.5737 (-0.5736) time: 0.9309 data: 0.0003 [11-23 14:36:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.20 Lm: 6.626 (6.634) Lt: 5.865 (5.863) Accm: 3.00 (2.97) Acct: 4.82 (4.78) proj_loss: -0.5808 (-0.5781) time: 0.9309 data: 0.0003 [11-23 14:36:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.20 Lm: 6.517 (6.540) Lt: 5.786 (5.806) Accm: 3.09 (3.23) Acct: 4.86 (4.91) proj_loss: -0.5636 (-0.5689) time: 0.9309 data: 0.0003 [11-23 14:36:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.20 Lm: 6.714 (6.721) Lt: 5.915 (5.994) Accm: 2.67 (2.70) Acct: 4.30 (4.25) proj_loss: -0.5717 (-0.5816) time: 0.9309 data: 0.0003 [11-23 14:36:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.20 Lm: 6.585 (6.591) Lt: 5.906 (5.916) Accm: 3.02 (2.98) Acct: 4.27 (4.47) proj_loss: -0.5798 (-0.5835) time: 0.9309 data: 0.0003 [11-23 14:36:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.20 Lm: 6.612 (6.593) Lt: 5.861 (5.788) Accm: 3.16 (3.21) Acct: 4.86 (5.13) proj_loss: -0.5779 (-0.5780) time: 0.9309 data: 0.0003 [11-23 14:36:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.20 Lm: 6.509 (6.556) Lt: 5.707 (5.754) Accm: 3.41 (3.37) Acct: 5.51 (5.37) proj_loss: -0.5778 (-0.5692) time: 0.9309 data: 0.0003 [11-23 14:36:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.20 Lm: 6.589 (6.569) Lt: 5.832 (5.809) Accm: 3.32 (3.27) Acct: 5.20 (5.10) proj_loss: -0.5675 (-0.5579) time: 0.9309 data: 0.0003 [11-23 14:42:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.21 Lm: 6.558 (6.558) Lt: 5.790 (5.786) Accm: 3.20 (3.22) Acct: 5.18 (5.11) proj_loss: -0.5677 (-0.5652) time: 0.9284 data: 0.0003 [11-23 14:42:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.21 Lm: 6.680 (6.677) Lt: 5.934 (5.945) Accm: 2.89 (2.86) Acct: 4.56 (4.64) proj_loss: -0.5642 (-0.5676) time: 0.9284 data: 0.0003 [11-23 14:42:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.21 Lm: 6.585 (6.537) Lt: 5.808 (5.779) Accm: 3.12 (3.28) Acct: 4.94 (5.22) proj_loss: -0.5854 (-0.5816) time: 0.9284 data: 0.0003 [11-23 14:42:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.21 Lm: 6.609 (6.704) Lt: 5.931 (6.033) Accm: 2.94 (2.76) Acct: 4.20 (4.22) proj_loss: -0.5697 (-0.5720) time: 0.9284 data: 0.0003 [11-23 14:42:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.21 Lm: 6.732 (6.728) Lt: 5.925 (5.979) Accm: 2.61 (2.66) Acct: 4.18 (4.20) proj_loss: -0.5771 (-0.5818) time: 0.9284 data: 0.0003 [11-23 14:42:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.21 Lm: 6.568 (6.562) Lt: 5.842 (5.829) Accm: 3.04 (3.07) Acct: 4.67 (4.72) proj_loss: -0.5723 (-0.5774) time: 0.9284 data: 0.0003 [11-23 14:42:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.21 Lm: 6.607 (6.593) Lt: 5.827 (5.840) Accm: 3.07 (3.19) Acct: 4.92 (5.01) proj_loss: -0.5790 (-0.5731) time: 0.9284 data: 0.0003 [11-23 14:42:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [1251/1669] eta: 0:06:29 tlr: 0.00022 tnm: 0.21 Lm: 6.652 (6.624) Lt: 5.881 (5.831) Accm: 2.97 (3.06) Acct: 4.80 (4.89) proj_loss: -0.5797 (-0.5818) time: 0.9284 data: 0.0003 [11-23 14:49:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.612 (6.618) Lt: 5.861 (5.825) Accm: 3.16 (3.14) Acct: 4.86 (4.94) proj_loss: -0.5804 (-0.5815) time: 0.9333 data: 0.0019 [11-23 14:49:10] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 50/350] Total time: 0:25:54 (0.931 s / it) [11-23 14:49:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.544 (6.539) Lt: 5.750 (5.766) Accm: 3.23 (3.31) Acct: 5.06 (5.25) proj_loss: -0.5808 (-0.5767) time: 0.9333 data: 0.0016 [11-23 14:49:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.527 (6.524) Lt: 5.749 (5.761) Accm: 3.32 (3.26) Acct: 5.17 (5.10) proj_loss: -0.5679 (-0.5677) time: 0.9333 data: 0.0018 [11-23 14:49:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.672 (6.676) Lt: 5.889 (5.934) Accm: 2.81 (2.85) Acct: 4.55 (4.62) proj_loss: -0.5590 (-0.5659) time: 0.9333 data: 0.0018 [11-23 14:49:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.620 (6.593) Lt: 5.897 (5.882) Accm: 2.99 (3.03) Acct: 4.48 (4.67) proj_loss: -0.5796 (-0.5778) time: 0.9333 data: 0.0015 [11-23 14:49:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.685 (6.612) Lt: 5.947 (5.883) Accm: 2.80 (3.11) Acct: 4.34 (4.79) proj_loss: -0.5801 (-0.5815) time: 0.9333 data: 0.0016 [11-23 14:49:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.634 (6.730) Lt: 5.956 (6.054) Accm: 2.87 (2.70) Acct: 4.13 (4.17) proj_loss: -0.5724 (-0.5721) time: 0.9333 data: 0.0017 [11-23 14:49:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 50/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.714 (6.662) Lt: 5.915 (5.894) Accm: 2.67 (2.91) Acct: 4.30 (4.61) proj_loss: -0.5717 (-0.5746) time: 0.9333 data: 0.0018 [11-23 14:49:10] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 50/350] Total time: 0:25:54 (0.931 s / it) [11-23 14:49:10] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 50/350] Total time: 0:25:54 (0.931 s / it) [11-23 14:49:10] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 50/350] Total time: 0:25:54 (0.931 s / it) [11-23 14:49:10] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 50/350] Total time: 0:25:54 (0.931 s / it) [11-23 14:49:10] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 50/350] Total time: 0:25:54 (0.931 s / it) [11-23 14:49:10] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 50/350] Total time: 0:25:54 (0.931 s / it) [11-23 14:49:10] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 50/350] Total time: 0:25:54 (0.931 s / it) [11-23 14:49:10] (/home/user/VAR/train.py , line 276)=> [ep50] (training ) Lm: 6.607 (6.607), Lt: 5.855 (5.855), Acc m&t: 3.12 4.96, Remain: 5 days, 10:21:09, Finish: 2024-11-28 09:10 [11-23 14:49:10] (/home/user/VAR/train.py , line 276)=> [ep50] (training ) Lm: 6.607 (6.607), Lt: 5.855 (5.855), Acc m&t: 3.12 4.96, Remain: 5 days, 10:19:49, Finish: 2024-11-28 09:08 [11-23 14:49:10] (/home/user/VAR/train.py , line 276)=> [ep50] (training ) Lm: 6.607 (6.607), Lt: 5.855 (5.855), Acc m&t: 3.12 4.96, Remain: 5 days, 10:19:59, Finish: 2024-11-28 09:09 [11-23 14:49:10] (/home/user/VAR/train.py , line 276)=> [ep50] (training ) Lm: 6.607 (6.607), Lt: 5.855 (5.855), Acc m&t: 3.12 4.96, Remain: 5 days, 10:20:01, Finish: 2024-11-28 09:09 [11-23 14:49:10] (/home/user/VAR/train.py , line 276)=> [ep50] (training ) Lm: 6.607 (6.607), Lt: 5.855 (5.855), Acc m&t: 3.12 4.96, Remain: 5 days, 10:20:28, Finish: 2024-11-28 09:09 [11-23 14:49:10] (/home/user/VAR/train.py , line 276)=> [ep50] (training ) Lm: 6.607 (6.607), Lt: 5.855 (5.855), Acc m&t: 3.12 4.96, Remain: 5 days, 10:20:31, Finish: 2024-11-28 09:09 [11-23 14:49:10] (/home/user/VAR/train.py , line 276)=> [ep50] (training ) Lm: 6.607 (6.607), Lt: 5.855 (5.855), Acc m&t: 3.12 4.96, Remain: 5 days, 10:20:15, Finish: 2024-11-28 09:09 [11-23 14:49:10] (/home/user/VAR/train.py , line 276)=> [ep50] (training ) Lm: 6.607 (6.607), Lt: 5.855 (5.855), Acc m&t: 3.12 4.96, Remain: 5 days, 10:19:37, Finish: 2024-11-28 09:08 [11-23 14:49:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 0/1669] eta: 0:25:02 tlr: 0.00022 tnm: 0.21 Lm: 6.674 (6.674) Lt: 5.906 (5.906) Accm: 2.84 (2.84) Acct: 4.24 (4.24) proj_loss: -0.5565 (-0.5565) time: 0.9000 data: 0.0003 [11-23 14:49:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 0/1669] eta: 0:24:24 tlr: 0.00022 tnm: 0.21 Lm: 6.646 (6.646) Lt: 5.853 (5.853) Accm: 2.78 (2.78) Acct: 4.58 (4.58) proj_loss: -0.5802 (-0.5802) time: 0.8777 data: 0.0003 [11-23 14:49:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 0/1669] eta: 0:24:20 tlr: 0.00022 tnm: 0.21 Lm: 6.680 (6.680) Lt: 5.908 (5.908) Accm: 2.64 (2.64) Acct: 4.48 (4.48) proj_loss: -0.5353 (-0.5353) time: 0.8753 data: 0.0003 [11-23 14:49:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 0/1669] eta: 0:24:21 tlr: 0.00022 tnm: 0.21 Lm: 6.270 (6.270) Lt: 5.446 (5.446) Accm: 4.31 (4.31) Acct: 7.13 (7.13) proj_loss: -0.5724 (-0.5724) time: 0.8758 data: 0.0004 [11-23 14:49:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 0/1669] eta: 0:24:24 tlr: 0.00022 tnm: 0.21 Lm: 6.430 (6.430) Lt: 5.624 (5.624) Accm: 3.44 (3.44) Acct: 5.54 (5.54) proj_loss: -0.5784 (-0.5784) time: 0.8774 data: 0.0003 [11-23 14:49:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 0/1669] eta: 0:24:25 tlr: 0.00022 tnm: 0.21 Lm: 6.634 (6.634) Lt: 5.941 (5.941) Accm: 2.84 (2.84) Acct: 4.51 (4.51) proj_loss: -0.6079 (-0.6079) time: 0.8780 data: 0.0003 [11-23 14:49:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 0/1669] eta: 0:24:25 tlr: 0.00022 tnm: 0.21 Lm: 6.760 (6.760) Lt: 6.009 (6.009) Accm: 2.78 (2.78) Acct: 4.51 (4.51) proj_loss: -0.5815 (-0.5815) time: 0.8783 data: 0.0004 [11-23 14:49:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 0/1669] eta: 0:24:29 tlr: 0.00022 tnm: 0.21 Lm: 6.748 (6.748) Lt: 6.052 (6.052) Accm: 2.81 (2.81) Acct: 4.44 (4.44) proj_loss: -0.5723 (-0.5723) time: 0.8807 data: 0.0005 [11-23 14:56:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 417/1669] eta: 0:20:55 tlr: 0.00022 tnm: 0.21 Lm: 6.683 (6.683) Lt: 5.967 (5.967) Accm: 3.03 (3.03) Acct: 4.72 (4.72) proj_loss: -0.5737 (-0.5737) time: 1.1461 data: 0.0003 [11-23 14:56:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 417/1669] eta: 0:20:55 tlr: 0.00022 tnm: 0.21 Lm: 6.624 (6.624) Lt: 5.777 (5.777) Accm: 2.99 (2.99) Acct: 4.67 (4.67) proj_loss: -0.5540 (-0.5540) time: 1.1461 data: 0.0003 [11-23 14:56:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 417/1669] eta: 0:20:55 tlr: 0.00022 tnm: 0.21 Lm: 6.724 (6.724) Lt: 6.013 (6.013) Accm: 2.84 (2.84) Acct: 4.46 (4.46) proj_loss: -0.5718 (-0.5718) time: 1.1461 data: 0.0003 [11-23 14:56:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 417/1669] eta: 0:20:55 tlr: 0.00022 tnm: 0.21 Lm: 6.623 (6.623) Lt: 5.912 (5.912) Accm: 3.03 (3.03) Acct: 4.80 (4.80) proj_loss: -0.6013 (-0.6013) time: 1.1461 data: 0.0003 [11-23 14:56:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 417/1669] eta: 0:20:55 tlr: 0.00022 tnm: 0.21 Lm: 6.454 (6.454) Lt: 5.642 (5.642) Accm: 3.69 (3.69) Acct: 5.94 (5.94) proj_loss: -0.5687 (-0.5687) time: 1.1461 data: 0.0003 [11-23 14:56:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 417/1669] eta: 0:20:55 tlr: 0.00022 tnm: 0.21 Lm: 6.613 (6.613) Lt: 5.850 (5.850) Accm: 3.19 (3.19) Acct: 4.89 (4.89) proj_loss: -0.5761 (-0.5761) time: 1.1461 data: 0.0003 [11-23 14:56:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 417/1669] eta: 0:20:55 tlr: 0.00022 tnm: 0.21 Lm: 6.595 (6.595) Lt: 5.811 (5.811) Accm: 2.93 (2.93) Acct: 4.70 (4.70) proj_loss: -0.5826 (-0.5826) time: 1.1461 data: 0.0003 [11-23 14:56:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 417/1669] eta: 0:20:55 tlr: 0.00022 tnm: 0.21 Lm: 6.727 (6.727) Lt: 5.978 (5.978) Accm: 2.75 (2.75) Acct: 4.41 (4.41) proj_loss: -0.5550 (-0.5550) time: 1.1461 data: 0.0003 [11-23 15:02:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 834/1669] eta: 0:13:41 tlr: 0.00022 tnm: 0.21 Lm: 6.680 (6.677) Lt: 5.908 (5.918) Accm: 2.87 (2.89) Acct: 4.48 (4.64) proj_loss: -0.5646 (-0.5582) time: 0.9324 data: 0.0003 [11-23 15:02:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 834/1669] eta: 0:13:41 tlr: 0.00022 tnm: 0.21 Lm: 6.612 (6.617) Lt: 5.926 (5.917) Accm: 3.15 (3.07) Acct: 4.96 (4.86) proj_loss: -0.6054 (-0.6026) time: 0.9324 data: 0.0003 [11-23 15:02:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 834/1669] eta: 0:13:41 tlr: 0.00022 tnm: 0.21 Lm: 6.635 (6.628) Lt: 5.882 (5.812) Accm: 3.12 (3.03) Acct: 5.03 (4.79) proj_loss: -0.5565 (-0.5569) time: 0.9324 data: 0.0003 [11-23 15:02:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 834/1669] eta: 0:13:41 tlr: 0.00022 tnm: 0.21 Lm: 6.625 (6.511) Lt: 5.818 (5.700) Accm: 3.07 (3.46) Acct: 5.17 (5.68) proj_loss: -0.5724 (-0.5798) time: 0.9324 data: 0.0003 [11-23 15:02:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 834/1669] eta: 0:13:41 tlr: 0.00022 tnm: 0.21 Lm: 6.646 (6.661) Lt: 5.853 (5.897) Accm: 2.78 (2.79) Acct: 4.58 (4.52) proj_loss: -0.5802 (-0.5774) time: 0.9324 data: 0.0003 [11-23 15:02:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 834/1669] eta: 0:13:41 tlr: 0.00022 tnm: 0.21 Lm: 6.688 (6.640) Lt: 6.009 (5.869) Accm: 2.90 (2.94) Acct: 4.51 (4.52) proj_loss: -0.5660 (-0.5699) time: 0.9324 data: 0.0003 [11-23 15:02:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 834/1669] eta: 0:13:41 tlr: 0.00022 tnm: 0.21 Lm: 6.430 (6.546) Lt: 5.647 (5.782) Accm: 3.44 (3.32) Acct: 5.48 (5.08) proj_loss: -0.5737 (-0.5690) time: 0.9324 data: 0.0003 [11-23 15:02:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [ 834/1669] eta: 0:13:41 tlr: 0.00022 tnm: 0.21 Lm: 6.618 (6.636) Lt: 5.882 (5.877) Accm: 3.25 (3.17) Acct: 4.99 (5.21) proj_loss: -0.5723 (-0.5650) time: 0.9324 data: 0.0003 [11-23 15:09:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [1251/1669] eta: 0:06:43 tlr: 0.00022 tnm: 0.20 Lm: 6.616 (6.630) Lt: 5.868 (5.871) Accm: 3.08 (3.11) Acct: 4.72 (4.99) proj_loss: -0.5677 (-0.5646) time: 0.9326 data: 0.0003 [11-23 15:09:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [1251/1669] eta: 0:06:43 tlr: 0.00022 tnm: 0.20 Lm: 6.632 (6.650) Lt: 5.904 (5.912) Accm: 2.87 (2.83) Acct: 4.49 (4.49) proj_loss: -0.5826 (-0.5810) time: 0.9326 data: 0.0003 [11-23 15:09:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [1251/1669] eta: 0:06:43 tlr: 0.00022 tnm: 0.20 Lm: 6.628 (6.603) Lt: 5.853 (5.841) Accm: 3.02 (3.12) Acct: 4.79 (4.98) proj_loss: -0.5696 (-0.5649) time: 0.9326 data: 0.0003 [11-23 15:09:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [1251/1669] eta: 0:06:43 tlr: 0.00022 tnm: 0.20 Lm: 6.623 (6.642) Lt: 5.934 (5.942) Accm: 2.99 (2.99) Acct: 4.73 (4.57) proj_loss: -0.6000 (-0.5936) time: 0.9326 data: 0.0003 [11-23 15:09:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [1251/1669] eta: 0:06:43 tlr: 0.00022 tnm: 0.20 Lm: 6.617 (6.621) Lt: 5.879 (5.828) Accm: 3.13 (3.08) Acct: 4.94 (4.80) proj_loss: -0.5596 (-0.5685) time: 0.9326 data: 0.0003 [11-23 15:09:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [1251/1669] eta: 0:06:43 tlr: 0.00022 tnm: 0.20 Lm: 6.544 (6.574) Lt: 5.812 (5.831) Accm: 3.19 (3.21) Acct: 5.23 (5.06) proj_loss: -0.5761 (-0.5747) time: 0.9326 data: 0.0003 [11-23 15:09:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [1251/1669] eta: 0:06:43 tlr: 0.00022 tnm: 0.20 Lm: 6.629 (6.541) Lt: 5.827 (5.758) Accm: 3.04 (3.30) Acct: 4.96 (5.39) proj_loss: -0.5873 (-0.5861) time: 0.9326 data: 0.0003 [11-23 15:09:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [1251/1669] eta: 0:06:43 tlr: 0.00022 tnm: 0.20 Lm: 6.724 (6.675) Lt: 6.013 (5.910) Accm: 2.84 (2.89) Acct: 4.53 (4.53) proj_loss: -0.5737 (-0.5746) time: 0.9326 data: 0.0003 [11-23 15:15:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.688 (6.669) Lt: 6.009 (5.918) Accm: 2.78 (2.84) Acct: 4.51 (4.39) proj_loss: -0.5815 (-0.5809) time: 0.9320 data: 0.0016 [11-23 15:15:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 51/350] Total time: 0:26:37 (0.957 s / it) [11-23 15:15:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.573 (6.574) Lt: 5.785 (5.822) Accm: 3.44 (3.28) Acct: 5.48 (5.19) proj_loss: -0.5784 (-0.5807) time: 0.9320 data: 0.0017 [11-23 15:15:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.635 (6.629) Lt: 5.882 (5.842) Accm: 3.12 (3.06) Acct: 4.86 (4.74) proj_loss: -0.5627 (-0.5737) time: 0.9320 data: 0.0018 [11-23 15:15:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.671 (6.617) Lt: 5.908 (5.873) Accm: 3.04 (3.11) Acct: 4.48 (4.86) proj_loss: -0.5746 (-0.5693) time: 0.9320 data: 0.0016 [11-23 15:15:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.646 (6.664) Lt: 5.956 (5.923) Accm: 2.96 (2.86) Acct: 4.58 (4.59) proj_loss: -0.5802 (-0.5806) time: 0.9320 data: 0.0017 [11-23 15:15:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.621 (6.638) Lt: 5.926 (5.925) Accm: 3.15 (3.04) Acct: 4.86 (4.63) proj_loss: -0.5946 (-0.5924) time: 0.9320 data: 0.0018 [11-23 15:15:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.614 (6.612) Lt: 5.854 (5.844) Accm: 3.25 (3.18) Acct: 4.99 (5.08) proj_loss: -0.5723 (-0.5682) time: 0.9320 data: 0.0015 [11-23 15:15:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 51/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.632 (6.569) Lt: 5.837 (5.779) Accm: 3.00 (3.22) Acct: 4.79 (5.27) proj_loss: -0.5834 (-0.5856) time: 0.9320 data: 0.0021 [11-23 15:15:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 51/350] Total time: 0:26:37 (0.957 s / it) [11-23 15:15:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 51/350] Total time: 0:26:37 (0.957 s / it) [11-23 15:15:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 51/350] Total time: 0:26:37 (0.957 s / it) [11-23 15:15:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 51/350] Total time: 0:26:37 (0.957 s / it) [11-23 15:15:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 51/350] Total time: 0:26:37 (0.957 s / it) [11-23 15:15:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 51/350] Total time: 0:26:37 (0.957 s / it) [11-23 15:15:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 51/350] Total time: 0:26:37 (0.957 s / it) [11-23 15:15:48] (/home/user/VAR/train.py , line 276)=> [ep51] (training ) Lm: 6.607 (6.610), Lt: 5.855 (5.858), Acc m&t: 3.12 4.96, Remain: 5 days, 9:39:03, Finish: 2024-11-28 08:54 [11-23 15:15:48] (/home/user/VAR/train.py , line 276)=> [ep51] (training ) Lm: 6.607 (6.610), Lt: 5.855 (5.858), Acc m&t: 3.12 4.96, Remain: 5 days, 9:41:03, Finish: 2024-11-28 08:56 [11-23 15:15:48] (/home/user/VAR/train.py , line 276)=> [ep51] (training ) Lm: 6.607 (6.610), Lt: 5.855 (5.858), Acc m&t: 3.12 4.96, Remain: 5 days, 9:39:13, Finish: 2024-11-28 08:55 [11-23 15:15:48] (/home/user/VAR/train.py , line 276)=> [ep51] (training ) Lm: 6.607 (6.610), Lt: 5.855 (5.858), Acc m&t: 3.12 4.96, Remain: 5 days, 9:40:36, Finish: 2024-11-28 08:56 [11-23 15:15:48] (/home/user/VAR/train.py , line 276)=> [ep51] (training ) Lm: 6.607 (6.610), Lt: 5.855 (5.858), Acc m&t: 3.12 4.96, Remain: 5 days, 9:38:49, Finish: 2024-11-28 08:54 [11-23 15:15:48] (/home/user/VAR/train.py , line 276)=> [ep51] (training ) Lm: 6.607 (6.610), Lt: 5.855 (5.858), Acc m&t: 3.12 4.96, Remain: 5 days, 9:39:25, Finish: 2024-11-28 08:55 [11-23 15:15:48] (/home/user/VAR/train.py , line 276)=> [ep51] (training ) Lm: 6.607 (6.610), Lt: 5.855 (5.858), Acc m&t: 3.12 4.96, Remain: 5 days, 9:38:34, Finish: 2024-11-28 08:54 [11-23 15:15:48] (/home/user/VAR/train.py , line 276)=> [ep51] (training ) Lm: 6.607 (6.610), Lt: 5.855 (5.858), Acc m&t: 3.12 4.96, Remain: 5 days, 9:40:46, Finish: 2024-11-28 08:56 [11-23 15:15:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 0/1669] eta: 0:24:45 tlr: 0.00022 tnm: 0.21 Lm: 6.675 (6.675) Lt: 6.022 (6.022) Accm: 2.90 (2.90) Acct: 4.06 (4.06) proj_loss: -0.5800 (-0.5800) time: 0.8899 data: 0.0004 [11-23 15:15:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 0/1669] eta: 0:24:44 tlr: 0.00022 tnm: 0.21 Lm: 6.455 (6.455) Lt: 5.581 (5.581) Accm: 3.47 (3.47) Acct: 5.68 (5.68) proj_loss: -0.5627 (-0.5627) time: 0.8896 data: 0.0004 [11-23 15:15:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 0/1669] eta: 0:24:45 tlr: 0.00022 tnm: 0.21 Lm: 6.628 (6.628) Lt: 5.910 (5.910) Accm: 2.78 (2.78) Acct: 4.79 (4.79) proj_loss: -0.5970 (-0.5970) time: 0.8898 data: 0.0004 [11-23 15:15:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 0/1669] eta: 0:24:45 tlr: 0.00022 tnm: 0.21 Lm: 6.544 (6.544) Lt: 5.857 (5.857) Accm: 3.25 (3.25) Acct: 5.44 (5.44) proj_loss: -0.5633 (-0.5633) time: 0.8900 data: 0.0004 [11-23 15:15:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 0/1669] eta: 0:24:45 tlr: 0.00022 tnm: 0.21 Lm: 6.567 (6.567) Lt: 5.707 (5.707) Accm: 3.23 (3.23) Acct: 4.96 (4.96) proj_loss: -0.5865 (-0.5865) time: 0.8901 data: 0.0004 [11-23 15:15:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 0/1669] eta: 0:24:39 tlr: 0.00022 tnm: 0.21 Lm: 6.803 (6.803) Lt: 6.152 (6.152) Accm: 2.29 (2.29) Acct: 3.37 (3.37) proj_loss: -0.5432 (-0.5432) time: 0.8862 data: 0.0003 [11-23 15:15:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 0/1669] eta: 0:24:45 tlr: 0.00022 tnm: 0.21 Lm: 6.646 (6.646) Lt: 5.886 (5.886) Accm: 3.25 (3.25) Acct: 5.30 (5.30) proj_loss: -0.5578 (-0.5578) time: 0.8901 data: 0.0004 [11-23 15:15:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 0/1669] eta: 0:24:46 tlr: 0.00022 tnm: 0.21 Lm: 6.815 (6.815) Lt: 6.040 (6.040) Accm: 2.40 (2.40) Acct: 3.62 (3.62) proj_loss: -0.5628 (-0.5628) time: 0.8904 data: 0.0004 [11-23 15:22:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.23 Lm: 6.682 (6.682) Lt: 5.858 (5.858) Accm: 2.81 (2.81) Acct: 4.49 (4.49) proj_loss: -0.5571 (-0.5571) time: 0.9329 data: 0.0003 [11-23 15:22:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.23 Lm: 6.530 (6.530) Lt: 5.793 (5.793) Accm: 3.10 (3.10) Acct: 5.25 (5.25) proj_loss: -0.5863 (-0.5863) time: 0.9329 data: 0.0003 [11-23 15:22:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.23 Lm: 6.480 (6.480) Lt: 5.692 (5.692) Accm: 3.25 (3.25) Acct: 5.10 (5.10) proj_loss: -0.5547 (-0.5547) time: 0.9329 data: 0.0003 [11-23 15:22:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.23 Lm: 6.661 (6.661) Lt: 5.941 (5.941) Accm: 2.96 (2.96) Acct: 4.37 (4.37) proj_loss: -0.5496 (-0.5496) time: 0.9329 data: 0.0003 [11-23 15:22:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.23 Lm: 6.752 (6.752) Lt: 6.049 (6.049) Accm: 2.51 (2.51) Acct: 3.79 (3.79) proj_loss: -0.5528 (-0.5528) time: 0.9329 data: 0.0003 [11-23 15:22:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.23 Lm: 6.559 (6.559) Lt: 5.836 (5.836) Accm: 3.15 (3.15) Acct: 5.20 (5.20) proj_loss: -0.5709 (-0.5709) time: 0.9329 data: 0.0003 [11-23 15:22:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.23 Lm: 6.638 (6.638) Lt: 5.852 (5.852) Accm: 3.04 (3.04) Acct: 4.79 (4.79) proj_loss: -0.5880 (-0.5880) time: 0.9329 data: 0.0003 [11-23 15:22:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.23 Lm: 6.654 (6.654) Lt: 5.880 (5.880) Accm: 3.18 (3.18) Acct: 5.15 (5.15) proj_loss: -0.5606 (-0.5606) time: 0.9329 data: 0.0003 [11-23 15:28:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.21 Lm: 6.646 (6.623) Lt: 5.873 (5.824) Accm: 3.25 (3.21) Acct: 5.27 (5.19) proj_loss: -0.5578 (-0.5567) time: 0.9289 data: 0.0003 [11-23 15:28:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.21 Lm: 6.573 (6.577) Lt: 5.857 (5.843) Accm: 3.06 (3.11) Acct: 4.96 (4.95) proj_loss: -0.5633 (-0.5672) time: 0.9289 data: 0.0003 [11-23 15:28:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.21 Lm: 6.675 (6.700) Lt: 6.022 (5.984) Accm: 2.90 (2.88) Acct: 4.20 (4.32) proj_loss: -0.5486 (-0.5493) time: 0.9289 data: 0.0003 [11-23 15:28:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.21 Lm: 6.455 (6.425) Lt: 5.581 (5.627) Accm: 3.47 (3.55) Acct: 5.68 (5.54) proj_loss: -0.5627 (-0.5580) time: 0.9289 data: 0.0003 [11-23 15:28:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.21 Lm: 6.628 (6.621) Lt: 5.910 (5.884) Accm: 2.78 (2.78) Acct: 4.79 (4.68) proj_loss: -0.5755 (-0.5724) time: 0.9289 data: 0.0003 [11-23 15:28:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.21 Lm: 6.709 (6.663) Lt: 5.898 (5.867) Accm: 2.86 (2.94) Acct: 4.72 (4.76) proj_loss: -0.5865 (-0.5799) time: 0.9289 data: 0.0003 [11-23 15:28:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.21 Lm: 6.741 (6.702) Lt: 5.996 (5.904) Accm: 2.86 (2.83) Acct: 4.27 (4.42) proj_loss: -0.5628 (-0.5709) time: 0.9289 data: 0.0003 [11-23 15:28:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.21 Lm: 6.702 (6.669) Lt: 5.946 (5.961) Accm: 2.74 (2.87) Acct: 4.20 (4.53) proj_loss: -0.5625 (-0.5582) time: 0.9289 data: 0.0003 [11-23 15:35:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [1251/1669] eta: 0:06:35 tlr: 0.00022 tnm: 0.20 Lm: 6.640 (6.647) Lt: 5.895 (5.932) Accm: 3.02 (2.98) Acct: 4.44 (4.57) proj_loss: -0.5657 (-0.5623) time: 0.9306 data: 0.0003 [11-23 15:35:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [1251/1669] eta: 0:06:35 tlr: 0.00022 tnm: 0.20 Lm: 6.659 (6.638) Lt: 5.906 (5.888) Accm: 2.86 (2.82) Acct: 4.56 (4.60) proj_loss: -0.5643 (-0.5676) time: 0.9306 data: 0.0003 [11-23 15:35:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [1251/1669] eta: 0:06:35 tlr: 0.00022 tnm: 0.20 Lm: 6.661 (6.585) Lt: 5.941 (5.845) Accm: 2.96 (3.27) Acct: 4.44 (4.92) proj_loss: -0.5643 (-0.5629) time: 0.9306 data: 0.0003 [11-23 15:35:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [1251/1669] eta: 0:06:35 tlr: 0.00022 tnm: 0.20 Lm: 6.593 (6.593) Lt: 5.836 (5.834) Accm: 3.04 (3.07) Acct: 4.96 (4.95) proj_loss: -0.5615 (-0.5641) time: 0.9306 data: 0.0003 [11-23 15:35:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [1251/1669] eta: 0:06:35 tlr: 0.00022 tnm: 0.20 Lm: 6.701 (6.691) Lt: 5.920 (5.889) Accm: 3.00 (2.91) Acct: 4.68 (4.59) proj_loss: -0.5734 (-0.5742) time: 0.9306 data: 0.0003 [11-23 15:35:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [1251/1669] eta: 0:06:35 tlr: 0.00022 tnm: 0.20 Lm: 6.688 (6.664) Lt: 5.876 (5.864) Accm: 2.80 (2.89) Acct: 4.84 (4.81) proj_loss: -0.5750 (-0.5722) time: 0.9306 data: 0.0003 [11-23 15:35:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [1251/1669] eta: 0:06:35 tlr: 0.00022 tnm: 0.20 Lm: 6.480 (6.466) Lt: 5.692 (5.678) Accm: 3.25 (3.42) Acct: 5.37 (5.42) proj_loss: -0.5636 (-0.5671) time: 0.9305 data: 0.0003 [11-23 15:35:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [1251/1669] eta: 0:06:35 tlr: 0.00022 tnm: 0.20 Lm: 6.654 (6.677) Lt: 5.880 (5.931) Accm: 3.18 (2.96) Acct: 5.13 (4.68) proj_loss: -0.5606 (-0.5609) time: 0.9306 data: 0.0003 [11-23 15:42:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.662 (6.689) Lt: 5.886 (5.940) Accm: 3.10 (2.94) Acct: 4.99 (4.64) proj_loss: -0.5634 (-0.5637) time: 1.1518 data: 0.0016 [11-23 15:42:17] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 52/350] Total time: 0:26:28 (0.952 s / it) [11-23 15:42:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.628 (6.583) Lt: 5.903 (5.824) Accm: 2.93 (3.08) Acct: 4.79 (5.01) proj_loss: -0.5755 (-0.5719) time: 1.1518 data: 0.0017 [11-23 15:42:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.647 (6.547) Lt: 5.860 (5.794) Accm: 3.02 (3.34) Acct: 4.68 (5.10) proj_loss: -0.5800 (-0.5680) time: 1.1518 data: 0.0018 [11-23 15:42:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.600 (6.594) Lt: 5.816 (5.830) Accm: 3.06 (3.09) Acct: 4.96 (4.98) proj_loss: -0.5596 (-0.5615) time: 1.1518 data: 0.0018 [11-23 15:42:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.709 (6.704) Lt: 5.898 (5.926) Accm: 2.74 (2.76) Acct: 4.72 (4.58) proj_loss: -0.5690 (-0.5715) time: 1.1518 data: 0.0017 [11-23 15:42:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.661 (6.651) Lt: 5.845 (5.839) Accm: 3.15 (3.01) Acct: 5.10 (4.84) proj_loss: -0.5645 (-0.5723) time: 1.1519 data: 0.0016 [11-23 15:42:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.504 (6.535) Lt: 5.803 (5.764) Accm: 3.03 (3.25) Acct: 5.06 (5.11) proj_loss: -0.5645 (-0.5707) time: 1.1518 data: 0.0017 [11-23 15:42:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 52/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.631 (6.643) Lt: 5.879 (5.921) Accm: 3.06 (2.99) Acct: 4.68 (4.61) proj_loss: -0.5668 (-0.5632) time: 1.1518 data: 0.0016 [11-23 15:42:17] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 52/350] Total time: 0:26:28 (0.952 s / it) [11-23 15:42:17] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 52/350] Total time: 0:26:28 (0.952 s / it) [11-23 15:42:17] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 52/350] Total time: 0:26:28 (0.952 s / it) [11-23 15:42:17] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 52/350] Total time: 0:26:28 (0.952 s / it) [11-23 15:42:17] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 52/350] Total time: 0:26:28 (0.952 s / it) [11-23 15:42:17] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 52/350] Total time: 0:26:28 (0.952 s / it) [11-23 15:42:17] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 52/350] Total time: 0:26:28 (0.952 s / it) [11-23 15:42:17] (/home/user/VAR/train.py , line 276)=> [ep52] (training ) Lm: 6.607 (6.607), Lt: 5.854 (5.854), Acc m&t: 3.12 4.96, Remain: 5 days, 9:20:01, Finish: 2024-11-28 09:02 [11-23 15:42:17] (/home/user/VAR/train.py , line 276)=> [ep52] (training ) Lm: 6.607 (6.607), Lt: 5.854 (5.854), Acc m&t: 3.12 4.96, Remain: 5 days, 9:17:14, Finish: 2024-11-28 08:59 [11-23 15:42:17] (/home/user/VAR/train.py , line 276)=> [ep52] (training ) Lm: 6.607 (6.607), Lt: 5.854 (5.854), Acc m&t: 3.12 4.96, Remain: 5 days, 9:16:19, Finish: 2024-11-28 08:58 [11-23 15:42:17] (/home/user/VAR/train.py , line 276)=> [ep52] (training ) Lm: 6.607 (6.607), Lt: 5.854 (5.854), Acc m&t: 3.12 4.96, Remain: 5 days, 9:22:14, Finish: 2024-11-28 09:04 [11-23 15:42:17] (/home/user/VAR/train.py , line 276)=> [ep52] (training ) Lm: 6.607 (6.607), Lt: 5.854 (5.854), Acc m&t: 3.12 4.96, Remain: 5 days, 9:19:23, Finish: 2024-11-28 09:01 [11-23 15:42:17] (/home/user/VAR/train.py , line 276)=> [ep52] (training ) Lm: 6.607 (6.607), Lt: 5.854 (5.854), Acc m&t: 3.12 4.96, Remain: 5 days, 9:26:17, Finish: 2024-11-28 09:08 [11-23 15:42:17] (/home/user/VAR/train.py , line 276)=> [ep52] (training ) Lm: 6.607 (6.607), Lt: 5.854 (5.854), Acc m&t: 3.12 4.96, Remain: 5 days, 9:21:08, Finish: 2024-11-28 09:03 [11-23 15:42:17] (/home/user/VAR/train.py , line 276)=> [ep52] (training ) Lm: 6.607 (6.607), Lt: 5.854 (5.854), Acc m&t: 3.12 4.96, Remain: 5 days, 9:18:19, Finish: 2024-11-28 09:00 [11-23 15:42:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 0/1669] eta: 0:24:54 tlr: 0.00022 tnm: 0.20 Lm: 6.625 (6.625) Lt: 5.857 (5.857) Accm: 2.75 (2.75) Acct: 4.65 (4.65) proj_loss: -0.5383 (-0.5383) time: 0.8954 data: 0.0003 [11-23 15:42:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 0/1669] eta: 0:24:54 tlr: 0.00022 tnm: 0.20 Lm: 6.670 (6.670) Lt: 6.016 (6.016) Accm: 2.81 (2.81) Acct: 4.17 (4.17) proj_loss: -0.5940 (-0.5940) time: 0.8954 data: 0.0004 [11-23 15:42:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 0/1669] eta: 0:24:54 tlr: 0.00022 tnm: 0.20 Lm: 6.769 (6.769) Lt: 6.061 (6.061) Accm: 2.74 (2.74) Acct: 4.17 (4.17) proj_loss: -0.5620 (-0.5620) time: 0.8954 data: 0.0004 [11-23 15:42:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 0/1669] eta: 0:24:54 tlr: 0.00022 tnm: 0.20 Lm: 6.509 (6.509) Lt: 5.748 (5.748) Accm: 3.37 (3.37) Acct: 5.58 (5.58) proj_loss: -0.6066 (-0.6066) time: 0.8956 data: 0.0004 [11-23 15:42:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 0/1669] eta: 0:24:53 tlr: 0.00022 tnm: 0.20 Lm: 6.775 (6.775) Lt: 6.094 (6.094) Accm: 2.56 (2.56) Acct: 4.34 (4.34) proj_loss: -0.6074 (-0.6074) time: 0.8947 data: 0.0004 [11-23 15:42:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 0/1669] eta: 0:24:55 tlr: 0.00022 tnm: 0.20 Lm: 6.536 (6.536) Lt: 5.769 (5.769) Accm: 3.23 (3.23) Acct: 4.96 (4.96) proj_loss: -0.5696 (-0.5696) time: 0.8959 data: 0.0004 [11-23 15:42:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 0/1669] eta: 0:24:55 tlr: 0.00022 tnm: 0.20 Lm: 6.576 (6.576) Lt: 5.938 (5.938) Accm: 3.16 (3.16) Acct: 4.82 (4.82) proj_loss: -0.6201 (-0.6201) time: 0.8963 data: 0.0004 [11-23 15:42:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 0/1669] eta: 0:24:55 tlr: 0.00022 tnm: 0.20 Lm: 6.623 (6.623) Lt: 5.909 (5.909) Accm: 3.13 (3.13) Acct: 5.13 (5.13) proj_loss: -0.5861 (-0.5861) time: 0.8960 data: 0.0004 [11-23 15:49:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 417/1669] eta: 0:20:06 tlr: 0.00022 tnm: 0.22 Lm: 6.483 (6.483) Lt: 5.699 (5.699) Accm: 3.74 (3.74) Acct: 5.84 (5.84) proj_loss: -0.5844 (-0.5844) time: 0.9327 data: 0.0003 [11-23 15:49:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 417/1669] eta: 0:20:06 tlr: 0.00022 tnm: 0.22 Lm: 6.745 (6.745) Lt: 6.020 (6.020) Accm: 2.79 (2.79) Acct: 4.30 (4.30) proj_loss: -0.5572 (-0.5572) time: 0.9327 data: 0.0003 [11-23 15:49:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 417/1669] eta: 0:20:06 tlr: 0.00022 tnm: 0.22 Lm: 6.674 (6.674) Lt: 5.939 (5.939) Accm: 2.56 (2.56) Acct: 4.39 (4.39) proj_loss: -0.5532 (-0.5532) time: 0.9327 data: 0.0003 [11-23 15:49:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 417/1669] eta: 0:20:06 tlr: 0.00022 tnm: 0.22 Lm: 6.522 (6.522) Lt: 5.770 (5.770) Accm: 3.23 (3.23) Acct: 5.29 (5.29) proj_loss: -0.5792 (-0.5792) time: 0.9327 data: 0.0003 [11-23 15:49:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 417/1669] eta: 0:20:06 tlr: 0.00022 tnm: 0.22 Lm: 6.557 (6.557) Lt: 5.843 (5.843) Accm: 3.11 (3.11) Acct: 4.79 (4.79) proj_loss: -0.5881 (-0.5881) time: 0.9327 data: 0.0003 [11-23 15:49:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 417/1669] eta: 0:20:06 tlr: 0.00022 tnm: 0.22 Lm: 6.709 (6.709) Lt: 5.993 (5.993) Accm: 2.75 (2.75) Acct: 4.36 (4.36) proj_loss: -0.6018 (-0.6018) time: 0.9327 data: 0.0003 [11-23 15:49:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 417/1669] eta: 0:20:06 tlr: 0.00022 tnm: 0.22 Lm: 6.508 (6.508) Lt: 5.749 (5.749) Accm: 3.31 (3.31) Acct: 5.10 (5.10) proj_loss: -0.5824 (-0.5824) time: 0.9327 data: 0.0003 [11-23 15:49:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 417/1669] eta: 0:20:06 tlr: 0.00022 tnm: 0.22 Lm: 6.732 (6.732) Lt: 6.141 (6.141) Accm: 2.67 (2.67) Acct: 3.98 (3.98) proj_loss: -0.5930 (-0.5930) time: 0.9327 data: 0.0003 [11-23 15:55:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 834/1669] eta: 0:13:11 tlr: 0.00022 tnm: 0.20 Lm: 6.613 (6.692) Lt: 5.938 (6.050) Accm: 3.12 (2.82) Acct: 4.82 (4.29) proj_loss: -0.5660 (-0.5751) time: 0.9345 data: 0.0003 [11-23 15:55:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 834/1669] eta: 0:13:11 tlr: 0.00022 tnm: 0.20 Lm: 6.721 (6.652) Lt: 5.978 (5.914) Accm: 2.84 (3.09) Acct: 4.44 (4.82) proj_loss: -0.5616 (-0.5587) time: 0.9345 data: 0.0003 [11-23 15:55:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 834/1669] eta: 0:13:11 tlr: 0.00022 tnm: 0.20 Lm: 6.625 (6.636) Lt: 5.908 (5.929) Accm: 2.72 (2.61) Acct: 4.13 (4.17) proj_loss: -0.5573 (-0.5546) time: 0.9345 data: 0.0003 [11-23 15:55:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 834/1669] eta: 0:13:11 tlr: 0.00022 tnm: 0.20 Lm: 6.534 (6.562) Lt: 5.749 (5.763) Accm: 3.10 (3.08) Acct: 5.06 (5.21) proj_loss: -0.5518 (-0.5692) time: 0.9345 data: 0.0003 [11-23 15:55:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 834/1669] eta: 0:13:11 tlr: 0.00022 tnm: 0.20 Lm: 6.604 (6.573) Lt: 5.870 (5.852) Accm: 3.28 (3.17) Acct: 5.37 (4.98) proj_loss: -0.5821 (-0.5818) time: 0.9345 data: 0.0003 [11-23 15:55:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 834/1669] eta: 0:13:11 tlr: 0.00022 tnm: 0.20 Lm: 6.704 (6.707) Lt: 6.056 (6.014) Accm: 2.94 (2.85) Acct: 4.34 (4.30) proj_loss: -0.5962 (-0.5969) time: 0.9345 data: 0.0003 [11-23 15:55:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 834/1669] eta: 0:13:11 tlr: 0.00022 tnm: 0.20 Lm: 6.536 (6.607) Lt: 5.769 (5.862) Accm: 3.23 (2.99) Acct: 4.96 (4.65) proj_loss: -0.5833 (-0.5827) time: 0.9345 data: 0.0003 [11-23 15:55:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [ 834/1669] eta: 0:13:11 tlr: 0.00022 tnm: 0.20 Lm: 6.556 (6.507) Lt: 5.805 (5.734) Accm: 3.13 (3.49) Acct: 5.13 (5.41) proj_loss: -0.5826 (-0.5725) time: 0.9345 data: 0.0003 [11-23 16:01:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.20 Lm: 6.462 (6.472) Lt: 5.647 (5.666) Accm: 3.60 (3.63) Acct: 5.84 (5.71) proj_loss: -0.5721 (-0.5698) time: 0.9322 data: 0.0003 [11-23 16:01:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.20 Lm: 6.674 (6.686) Lt: 5.965 (5.981) Accm: 2.54 (2.50) Acct: 3.93 (4.02) proj_loss: -0.5581 (-0.5557) time: 0.9322 data: 0.0003 [11-23 16:01:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.20 Lm: 6.673 (6.669) Lt: 5.974 (5.959) Accm: 2.99 (2.91) Acct: 4.36 (4.40) proj_loss: -0.5916 (-0.5875) time: 0.9322 data: 0.0003 [11-23 16:01:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.20 Lm: 6.588 (6.588) Lt: 5.770 (5.791) Accm: 2.98 (3.02) Acct: 5.03 (5.05) proj_loss: -0.5592 (-0.5686) time: 0.9322 data: 0.0003 [11-23 16:01:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.20 Lm: 6.663 (6.641) Lt: 5.928 (5.905) Accm: 2.96 (3.09) Acct: 4.65 (4.83) proj_loss: -0.5618 (-0.5665) time: 0.9322 data: 0.0003 [11-23 16:01:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.20 Lm: 6.576 (6.566) Lt: 5.811 (5.827) Accm: 3.30 (3.21) Acct: 5.39 (5.20) proj_loss: -0.5757 (-0.5783) time: 0.9322 data: 0.0003 [11-23 16:01:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.20 Lm: 6.598 (6.620) Lt: 5.821 (5.864) Accm: 3.14 (3.00) Acct: 4.75 (4.62) proj_loss: -0.5804 (-0.5814) time: 0.9322 data: 0.0003 [11-23 16:01:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.20 Lm: 6.595 (6.661) Lt: 5.902 (5.994) Accm: 3.14 (2.91) Acct: 4.87 (4.45) proj_loss: -0.5725 (-0.5761) time: 0.9322 data: 0.0003 [11-23 16:08:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.576 (6.634) Lt: 5.867 (5.952) Accm: 3.16 (3.04) Acct: 4.92 (4.61) proj_loss: -0.5791 (-0.5798) time: 0.9330 data: 0.0018 [11-23 16:08:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 53/350] Total time: 0:26:07 (0.939 s / it) [11-23 16:08:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.704 (6.677) Lt: 6.011 (5.969) Accm: 2.94 (2.90) Acct: 4.34 (4.37) proj_loss: -0.5870 (-0.5861) time: 0.9330 data: 0.0018 [11-23 16:08:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.599 (6.590) Lt: 5.792 (5.797) Accm: 2.97 (3.01) Acct: 4.99 (5.03) proj_loss: -0.5571 (-0.5663) time: 0.9330 data: 0.0020 [11-23 16:08:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.605 (6.632) Lt: 5.877 (5.892) Accm: 3.07 (3.11) Acct: 4.86 (4.88) proj_loss: -0.5620 (-0.5699) time: 0.9330 data: 0.0023 [11-23 16:08:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.575 (6.611) Lt: 5.832 (5.858) Accm: 3.13 (3.03) Acct: 4.96 (4.70) proj_loss: -0.5833 (-0.5859) time: 0.9330 data: 0.0018 [11-23 16:08:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.604 (6.588) Lt: 5.870 (5.837) Accm: 3.28 (3.10) Acct: 5.37 (5.03) proj_loss: -0.5693 (-0.5749) time: 0.9330 data: 0.0018 [11-23 16:08:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.645 (6.678) Lt: 5.915 (5.968) Accm: 2.72 (2.58) Acct: 4.13 (4.17) proj_loss: -0.5573 (-0.5549) time: 0.9330 data: 0.0018 [11-23 16:08:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 53/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.474 (6.473) Lt: 5.710 (5.675) Accm: 3.31 (3.57) Acct: 5.13 (5.54) proj_loss: -0.5617 (-0.5681) time: 0.9330 data: 0.0021 [11-23 16:08:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 53/350] Total time: 0:26:07 (0.939 s / it) [11-23 16:08:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 53/350] Total time: 0:26:07 (0.939 s / it) [11-23 16:08:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 53/350] Total time: 0:26:07 (0.939 s / it) [11-23 16:08:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 53/350] Total time: 0:26:07 (0.939 s / it) [11-23 16:08:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 53/350] Total time: 0:26:07 (0.939 s / it) [11-23 16:08:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 53/350] Total time: 0:26:07 (0.939 s / it) [11-23 16:08:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 53/350] Total time: 0:26:07 (0.939 s / it) [11-23 16:08:25] (/home/user/VAR/train.py , line 276)=> [ep53] (training ) Lm: 6.597 (6.597), Lt: 5.851 (5.851), Acc m&t: 3.12 4.96, Remain: 5 days, 8:44:35, Finish: 2024-11-28 08:52 [11-23 16:08:25] (/home/user/VAR/train.py , line 276)=> [ep53] (training ) Lm: 6.597 (6.597), Lt: 5.851 (5.851), Acc m&t: 3.12 4.96, Remain: 5 days, 8:51:38, Finish: 2024-11-28 09:00 [11-23 16:08:25] (/home/user/VAR/train.py , line 276)=> [ep53] (training ) Lm: 6.597 (6.597), Lt: 5.851 (5.851), Acc m&t: 3.12 4.96, Remain: 5 days, 8:46:44, Finish: 2024-11-28 08:55 [11-23 16:08:25] (/home/user/VAR/train.py , line 276)=> [ep53] (training ) Lm: 6.597 (6.597), Lt: 5.851 (5.851), Acc m&t: 3.12 4.96, Remain: 5 days, 8:44:24, Finish: 2024-11-28 08:52 [11-23 16:08:25] (/home/user/VAR/train.py , line 276)=> [ep53] (training ) Lm: 6.597 (6.597), Lt: 5.851 (5.851), Acc m&t: 3.12 4.96, Remain: 5 days, 8:45:15, Finish: 2024-11-28 08:53 [11-23 16:08:25] (/home/user/VAR/train.py , line 276)=> [ep53] (training ) Lm: 6.597 (6.597), Lt: 5.851 (5.851), Acc m&t: 3.12 4.96, Remain: 5 days, 8:44:25, Finish: 2024-11-28 08:52 [11-23 16:08:25] (/home/user/VAR/train.py , line 276)=> [ep53] (training ) Lm: 6.597 (6.597), Lt: 5.851 (5.851), Acc m&t: 3.12 4.96, Remain: 5 days, 8:44:34, Finish: 2024-11-28 08:52 [11-23 16:08:25] (/home/user/VAR/train.py , line 276)=> [ep53] (training ) Lm: 6.597 (6.597), Lt: 5.851 (5.851), Acc m&t: 3.12 4.96, Remain: 5 days, 8:46:45, Finish: 2024-11-28 08:55 [11-23 16:08:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 0/1669] eta: 0:25:36 tlr: 0.00022 tnm: 0.22 Lm: 6.890 (6.890) Lt: 6.191 (6.191) Accm: 2.20 (2.20) Acct: 3.44 (3.44) proj_loss: -0.5695 (-0.5695) time: 0.9206 data: 0.0003 [11-23 16:08:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 0/1669] eta: 0:25:37 tlr: 0.00022 tnm: 0.22 Lm: 6.565 (6.565) Lt: 5.802 (5.802) Accm: 3.25 (3.25) Acct: 5.17 (5.17) proj_loss: -0.5553 (-0.5553) time: 0.9210 data: 0.0004 [11-23 16:08:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 0/1669] eta: 0:25:36 tlr: 0.00022 tnm: 0.22 Lm: 6.521 (6.521) Lt: 5.788 (5.788) Accm: 3.67 (3.67) Acct: 5.34 (5.34) proj_loss: -0.5887 (-0.5887) time: 0.9207 data: 0.0004 [11-23 16:08:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 0/1669] eta: 0:25:36 tlr: 0.00022 tnm: 0.22 Lm: 6.590 (6.590) Lt: 5.815 (5.815) Accm: 3.28 (3.28) Acct: 5.13 (5.13) proj_loss: -0.5823 (-0.5823) time: 0.9204 data: 0.0003 [11-23 16:08:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 0/1669] eta: 0:25:37 tlr: 0.00022 tnm: 0.22 Lm: 6.600 (6.600) Lt: 5.854 (5.854) Accm: 3.03 (3.03) Acct: 4.65 (4.65) proj_loss: -0.5836 (-0.5836) time: 0.9213 data: 0.0004 [11-23 16:08:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 0/1669] eta: 0:25:38 tlr: 0.00022 tnm: 0.22 Lm: 6.350 (6.350) Lt: 5.644 (5.644) Accm: 3.72 (3.72) Acct: 5.34 (5.34) proj_loss: -0.6112 (-0.6112) time: 0.9215 data: 0.0004 [11-23 16:08:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 0/1669] eta: 0:25:37 tlr: 0.00022 tnm: 0.22 Lm: 6.734 (6.734) Lt: 6.000 (6.000) Accm: 2.70 (2.70) Acct: 4.34 (4.34) proj_loss: -0.5932 (-0.5932) time: 0.9210 data: 0.0004 [11-23 16:08:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 0/1669] eta: 0:25:37 tlr: 0.00022 tnm: 0.22 Lm: 6.349 (6.349) Lt: 5.581 (5.581) Accm: 3.96 (3.96) Acct: 6.16 (6.16) proj_loss: -0.6008 (-0.6008) time: 0.9215 data: 0.0004 [11-23 16:14:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 417/1669] eta: 0:19:32 tlr: 0.00022 tnm: 0.23 Lm: 6.566 (6.566) Lt: 5.846 (5.846) Accm: 3.34 (3.34) Acct: 5.03 (5.03) proj_loss: -0.5784 (-0.5784) time: 0.9312 data: 0.0003 [11-23 16:14:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 417/1669] eta: 0:19:32 tlr: 0.00022 tnm: 0.23 Lm: 6.664 (6.664) Lt: 5.965 (5.965) Accm: 2.90 (2.90) Acct: 4.42 (4.42) proj_loss: -0.5806 (-0.5806) time: 0.9312 data: 0.0003 [11-23 16:14:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 417/1669] eta: 0:19:32 tlr: 0.00022 tnm: 0.23 Lm: 6.560 (6.560) Lt: 5.795 (5.795) Accm: 2.99 (2.99) Acct: 4.73 (4.73) proj_loss: -0.5825 (-0.5825) time: 0.9312 data: 0.0003 [11-23 16:14:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 417/1669] eta: 0:19:32 tlr: 0.00022 tnm: 0.23 Lm: 6.478 (6.478) Lt: 5.761 (5.761) Accm: 3.37 (3.37) Acct: 4.86 (4.86) proj_loss: -0.6004 (-0.6004) time: 0.9312 data: 0.0003 [11-23 16:14:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 417/1669] eta: 0:19:32 tlr: 0.00022 tnm: 0.23 Lm: 6.535 (6.535) Lt: 5.754 (5.754) Accm: 3.47 (3.47) Acct: 5.46 (5.46) proj_loss: -0.5917 (-0.5917) time: 0.9312 data: 0.0003 [11-23 16:14:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 417/1669] eta: 0:19:33 tlr: 0.00022 tnm: 0.23 Lm: 6.818 (6.818) Lt: 6.097 (6.097) Accm: 2.37 (2.37) Acct: 3.63 (3.63) proj_loss: -0.5668 (-0.5668) time: 0.9312 data: 0.0003 [11-23 16:14:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 417/1669] eta: 0:19:32 tlr: 0.00022 tnm: 0.23 Lm: 6.492 (6.492) Lt: 5.682 (5.682) Accm: 3.37 (3.37) Acct: 5.34 (5.34) proj_loss: -0.5674 (-0.5674) time: 0.9312 data: 0.0003 [11-23 16:14:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 417/1669] eta: 0:19:32 tlr: 0.00022 tnm: 0.23 Lm: 6.537 (6.537) Lt: 5.791 (5.791) Accm: 3.54 (3.54) Acct: 5.29 (5.29) proj_loss: -0.5817 (-0.5817) time: 0.9313 data: 0.0003 [11-23 16:22:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 834/1669] eta: 0:13:36 tlr: 0.00022 tnm: 0.20 Lm: 6.554 (6.629) Lt: 5.795 (5.892) Accm: 3.41 (3.14) Acct: 5.23 (4.76) proj_loss: -0.5747 (-0.5767) time: 0.9325 data: 0.0003 [11-23 16:22:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 834/1669] eta: 0:13:36 tlr: 0.00022 tnm: 0.20 Lm: 6.728 (6.692) Lt: 6.009 (5.980) Accm: 2.77 (2.79) Acct: 4.20 (4.34) proj_loss: -0.5777 (-0.5723) time: 0.9325 data: 0.0003 [11-23 16:22:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 834/1669] eta: 0:13:36 tlr: 0.00022 tnm: 0.20 Lm: 6.590 (6.579) Lt: 5.815 (5.814) Accm: 3.28 (3.22) Acct: 5.13 (5.00) proj_loss: -0.5823 (-0.5876) time: 0.9325 data: 0.0003 [11-23 16:22:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 834/1669] eta: 0:13:36 tlr: 0.00022 tnm: 0.20 Lm: 6.606 (6.541) Lt: 5.879 (5.838) Accm: 3.03 (3.14) Acct: 4.37 (4.64) proj_loss: -0.6112 (-0.6047) time: 0.9325 data: 0.0003 [11-23 16:22:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 834/1669] eta: 0:13:36 tlr: 0.00022 tnm: 0.20 Lm: 6.408 (6.509) Lt: 5.607 (5.732) Accm: 3.28 (3.26) Acct: 5.13 (5.08) proj_loss: -0.5761 (-0.5804) time: 0.9325 data: 0.0003 [11-23 16:22:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 834/1669] eta: 0:13:36 tlr: 0.00022 tnm: 0.20 Lm: 6.565 (6.520) Lt: 5.802 (5.729) Accm: 3.50 (3.42) Acct: 5.51 (5.42) proj_loss: -0.5553 (-0.5616) time: 0.9325 data: 0.0003 [11-23 16:22:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 834/1669] eta: 0:13:36 tlr: 0.00022 tnm: 0.20 Lm: 6.349 (6.475) Lt: 5.581 (5.699) Accm: 3.96 (3.56) Acct: 6.16 (5.54) proj_loss: -0.5973 (-0.5847) time: 0.9325 data: 0.0003 [11-23 16:22:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [ 834/1669] eta: 0:13:36 tlr: 0.00022 tnm: 0.20 Lm: 6.746 (6.745) Lt: 6.003 (5.986) Accm: 2.53 (2.57) Acct: 3.82 (4.10) proj_loss: -0.5640 (-0.5611) time: 0.9326 data: 0.0003 [11-23 16:28:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [1251/1669] eta: 0:06:42 tlr: 0.00022 tnm: 0.22 Lm: 6.786 (6.765) Lt: 6.084 (6.031) Accm: 2.60 (2.59) Acct: 3.93 (4.08) proj_loss: -0.5653 (-0.5625) time: 0.9327 data: 0.0003 [11-23 16:28:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [1251/1669] eta: 0:06:42 tlr: 0.00022 tnm: 0.22 Lm: 6.664 (6.625) Lt: 5.932 (5.897) Accm: 2.90 (3.02) Acct: 4.42 (4.69) proj_loss: -0.5667 (-0.5647) time: 0.9326 data: 0.0003 [11-23 16:28:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [1251/1669] eta: 0:06:42 tlr: 0.00022 tnm: 0.22 Lm: 6.571 (6.579) Lt: 5.803 (5.817) Accm: 2.99 (3.08) Acct: 4.73 (4.76) proj_loss: -0.5739 (-0.5739) time: 0.9326 data: 0.0003 [11-23 16:28:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [1251/1669] eta: 0:06:42 tlr: 0.00022 tnm: 0.22 Lm: 6.570 (6.550) Lt: 5.812 (5.781) Accm: 3.37 (3.32) Acct: 5.34 (5.22) proj_loss: -0.5531 (-0.5589) time: 0.9327 data: 0.0003 [11-23 16:28:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [1251/1669] eta: 0:06:42 tlr: 0.00022 tnm: 0.22 Lm: 6.448 (6.493) Lt: 5.654 (5.706) Accm: 3.69 (3.53) Acct: 5.96 (5.60) proj_loss: -0.5899 (-0.5841) time: 0.9326 data: 0.0003 [11-23 16:28:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [1251/1669] eta: 0:06:42 tlr: 0.00022 tnm: 0.22 Lm: 6.535 (6.552) Lt: 5.786 (5.799) Accm: 3.47 (3.34) Acct: 5.42 (5.18) proj_loss: -0.5841 (-0.5872) time: 0.9327 data: 0.0003 [11-23 16:28:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [1251/1669] eta: 0:06:42 tlr: 0.00022 tnm: 0.22 Lm: 6.683 (6.678) Lt: 5.944 (5.957) Accm: 2.87 (2.87) Acct: 4.48 (4.42) proj_loss: -0.5706 (-0.5738) time: 0.9327 data: 0.0004 [11-23 16:28:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [1251/1669] eta: 0:06:42 tlr: 0.00022 tnm: 0.22 Lm: 6.637 (6.590) Lt: 5.934 (5.882) Accm: 2.98 (3.09) Acct: 4.60 (4.68) proj_loss: -0.6004 (-0.5980) time: 0.9326 data: 0.0003 [11-23 16:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.636 (6.599) Lt: 5.913 (5.888) Accm: 3.03 (3.10) Acct: 4.82 (4.73) proj_loss: -0.5921 (-0.5968) time: 0.9340 data: 0.0020 [11-23 16:35:00] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 54/350] Total time: 0:26:34 (0.956 s / it) [11-23 16:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.746 (6.716) Lt: 6.003 (5.984) Accm: 2.67 (2.80) Acct: 4.03 (4.39) proj_loss: -0.5666 (-0.5665) time: 0.9340 data: 0.0018 [11-23 16:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.611 (6.622) Lt: 5.891 (5.896) Accm: 2.81 (2.98) Acct: 4.44 (4.64) proj_loss: -0.5777 (-0.5729) time: 0.9340 data: 0.0017 [11-23 16:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.575 (6.559) Lt: 5.823 (5.793) Accm: 3.25 (3.25) Acct: 5.17 (5.15) proj_loss: -0.5553 (-0.5635) time: 0.9340 data: 0.0017 [11-23 16:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.554 (6.645) Lt: 5.795 (5.908) Accm: 3.32 (2.96) Acct: 5.23 (4.61) proj_loss: -0.5747 (-0.5762) time: 0.9340 data: 0.0016 [11-23 16:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.590 (6.594) Lt: 5.815 (5.843) Accm: 3.28 (3.17) Acct: 5.13 (4.95) proj_loss: -0.5823 (-0.5849) time: 0.9340 data: 0.0017 [11-23 16:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.547 (6.520) Lt: 5.727 (5.738) Accm: 3.42 (3.40) Acct: 5.75 (5.39) proj_loss: -0.5824 (-0.5797) time: 0.9340 data: 0.0018 [11-23 16:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 54/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.546 (6.572) Lt: 5.832 (5.820) Accm: 2.83 (3.03) Acct: 4.58 (4.72) proj_loss: -0.5718 (-0.5698) time: 0.9341 data: 0.0019 [11-23 16:35:00] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 54/350] Total time: 0:26:34 (0.956 s / it) [11-23 16:35:00] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 54/350] Total time: 0:26:34 (0.956 s / it) [11-23 16:35:00] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 54/350] Total time: 0:26:34 (0.956 s / it) [11-23 16:35:00] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 54/350] Total time: 0:26:34 (0.956 s / it) [11-23 16:35:00] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 54/350] Total time: 0:26:34 (0.956 s / it) [11-23 16:35:00] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 54/350] Total time: 0:26:34 (0.956 s / it) [11-23 16:35:00] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 54/350] Total time: 0:26:34 (0.956 s / it) [11-23 16:35:00] (/home/user/VAR/train.py , line 276)=> [ep54] (training ) Lm: 6.595 (6.595), Lt: 5.845 (5.845), Acc m&t: 3.12 4.96, Remain: 5 days, 8:37:20, Finish: 2024-11-28 09:12 [11-23 16:35:00] (/home/user/VAR/train.py , line 276)=> [ep54] (training ) Lm: 6.595 (6.595), Lt: 5.845 (5.845), Acc m&t: 3.12 4.96, Remain: 5 days, 8:36:55, Finish: 2024-11-28 09:11 [11-23 16:35:00] (/home/user/VAR/train.py , line 276)=> [ep54] (training ) Lm: 6.595 (6.595), Lt: 5.845 (5.845), Acc m&t: 3.12 4.96, Remain: 5 days, 8:35:54, Finish: 2024-11-28 09:10 [11-23 16:35:00] (/home/user/VAR/train.py , line 276)=> [ep54] (training ) Lm: 6.595 (6.595), Lt: 5.845 (5.845), Acc m&t: 3.12 4.96, Remain: 5 days, 8:36:38, Finish: 2024-11-28 09:11 [11-23 16:35:00] (/home/user/VAR/train.py , line 276)=> [ep54] (training ) Lm: 6.595 (6.595), Lt: 5.845 (5.845), Acc m&t: 3.12 4.96, Remain: 5 days, 8:36:04, Finish: 2024-11-28 09:11 [11-23 16:35:00] (/home/user/VAR/train.py , line 276)=> [ep54] (training ) Lm: 6.595 (6.595), Lt: 5.845 (5.845), Acc m&t: 3.12 4.96, Remain: 5 days, 8:37:06, Finish: 2024-11-28 09:12 [11-23 16:35:00] (/home/user/VAR/train.py , line 276)=> [ep54] (training ) Lm: 6.595 (6.595), Lt: 5.845 (5.845), Acc m&t: 3.12 4.96, Remain: 5 days, 8:37:15, Finish: 2024-11-28 09:12 [11-23 16:35:00] (/home/user/VAR/train.py , line 276)=> [ep54] (training ) Lm: 6.595 (6.595), Lt: 5.845 (5.845), Acc m&t: 3.12 4.96, Remain: 5 days, 8:38:30, Finish: 2024-11-28 09:13 [11-23 16:35:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 0/1669] eta: 0:24:53 tlr: 0.00022 tnm: 0.23 Lm: 6.510 (6.510) Lt: 5.744 (5.744) Accm: 3.23 (3.23) Acct: 5.27 (5.27) proj_loss: -0.5687 (-0.5687) time: 0.8951 data: 0.0004 [11-23 16:35:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 0/1669] eta: 0:24:53 tlr: 0.00022 tnm: 0.23 Lm: 6.770 (6.770) Lt: 6.125 (6.125) Accm: 3.00 (3.00) Acct: 4.48 (4.48) proj_loss: -0.6052 (-0.6052) time: 0.8947 data: 0.0004 [11-23 16:35:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 0/1669] eta: 0:24:54 tlr: 0.00022 tnm: 0.23 Lm: 6.361 (6.361) Lt: 5.619 (5.619) Accm: 3.61 (3.61) Acct: 5.72 (5.72) proj_loss: -0.5905 (-0.5905) time: 0.8955 data: 0.0004 [11-23 16:35:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 0/1669] eta: 0:25:07 tlr: 0.00022 tnm: 0.23 Lm: 6.660 (6.660) Lt: 5.849 (5.849) Accm: 2.72 (2.72) Acct: 4.17 (4.17) proj_loss: -0.5282 (-0.5282) time: 0.9035 data: 0.0004 [11-23 16:35:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 0/1669] eta: 0:24:54 tlr: 0.00022 tnm: 0.23 Lm: 6.774 (6.774) Lt: 6.102 (6.102) Accm: 2.64 (2.64) Acct: 4.24 (4.24) proj_loss: -0.6010 (-0.6010) time: 0.8956 data: 0.0003 [11-23 16:35:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 0/1669] eta: 0:24:54 tlr: 0.00022 tnm: 0.23 Lm: 6.259 (6.259) Lt: 5.490 (5.490) Accm: 3.93 (3.93) Acct: 5.96 (5.96) proj_loss: -0.5719 (-0.5719) time: 0.8953 data: 0.0004 [11-23 16:35:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 0/1669] eta: 0:24:54 tlr: 0.00022 tnm: 0.23 Lm: 6.832 (6.832) Lt: 6.172 (6.172) Accm: 2.59 (2.59) Acct: 3.72 (3.72) proj_loss: -0.5785 (-0.5785) time: 0.8957 data: 0.0004 [11-23 16:35:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 0/1669] eta: 0:25:07 tlr: 0.00022 tnm: 0.23 Lm: 6.451 (6.451) Lt: 5.685 (5.685) Accm: 3.21 (3.21) Acct: 4.72 (4.72) proj_loss: -0.6144 (-0.6144) time: 0.9035 data: 0.0004 [11-23 16:41:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.21 Lm: 6.491 (6.491) Lt: 5.772 (5.772) Accm: 3.17 (3.17) Acct: 4.58 (4.58) proj_loss: -0.6076 (-0.6076) time: 0.9301 data: 0.0003 [11-23 16:41:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.21 Lm: 6.570 (6.570) Lt: 5.854 (5.854) Accm: 3.13 (3.13) Acct: 4.89 (4.89) proj_loss: -0.5868 (-0.5868) time: 0.9301 data: 0.0003 [11-23 16:41:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.21 Lm: 6.734 (6.734) Lt: 6.006 (6.006) Accm: 2.83 (2.83) Acct: 4.30 (4.30) proj_loss: -0.5746 (-0.5746) time: 0.9301 data: 0.0003 [11-23 16:41:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.21 Lm: 6.707 (6.707) Lt: 6.019 (6.019) Accm: 2.91 (2.91) Acct: 4.70 (4.70) proj_loss: -0.6101 (-0.6101) time: 0.9301 data: 0.0003 [11-23 16:41:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.21 Lm: 6.784 (6.784) Lt: 6.127 (6.127) Accm: 2.83 (2.83) Acct: 4.30 (4.30) proj_loss: -0.5991 (-0.5991) time: 0.9301 data: 0.0003 [11-23 16:41:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.21 Lm: 6.564 (6.564) Lt: 5.815 (5.815) Accm: 3.26 (3.26) Acct: 4.99 (4.99) proj_loss: -0.5745 (-0.5745) time: 0.9301 data: 0.0003 [11-23 16:41:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.21 Lm: 6.482 (6.482) Lt: 5.719 (5.719) Accm: 3.40 (3.40) Acct: 5.44 (5.44) proj_loss: -0.5765 (-0.5765) time: 0.9301 data: 0.0003 [11-23 16:41:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.21 Lm: 6.523 (6.523) Lt: 5.735 (5.735) Accm: 3.21 (3.21) Acct: 4.91 (4.91) proj_loss: -0.5698 (-0.5698) time: 0.9301 data: 0.0003 [11-23 16:47:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.20 Lm: 6.593 (6.546) Lt: 5.816 (5.762) Accm: 3.37 (3.26) Acct: 5.54 (5.12) proj_loss: -0.5581 (-0.5659) time: 0.9329 data: 0.0003 [11-23 16:47:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.20 Lm: 6.636 (6.684) Lt: 5.916 (5.976) Accm: 3.06 (2.94) Acct: 4.68 (4.43) proj_loss: -0.5729 (-0.5741) time: 0.9329 data: 0.0003 [11-23 16:47:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.20 Lm: 6.641 (6.643) Lt: 5.936 (5.916) Accm: 3.00 (2.94) Acct: 4.79 (4.73) proj_loss: -0.6010 (-0.5967) time: 0.9329 data: 0.0003 [11-23 16:47:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.20 Lm: 6.510 (6.472) Lt: 5.744 (5.710) Accm: 3.23 (3.33) Acct: 5.27 (5.34) proj_loss: -0.6049 (-0.5935) time: 0.9329 data: 0.0003 [11-23 16:47:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.20 Lm: 6.533 (6.554) Lt: 5.781 (5.804) Accm: 3.53 (3.35) Acct: 5.48 (5.15) proj_loss: -0.5719 (-0.5732) time: 0.9329 data: 0.0003 [11-23 16:47:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.20 Lm: 6.603 (6.619) Lt: 5.819 (5.866) Accm: 3.19 (3.06) Acct: 5.17 (4.94) proj_loss: -0.5625 (-0.5679) time: 0.9329 data: 0.0003 [11-23 16:47:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.20 Lm: 6.770 (6.770) Lt: 6.125 (6.080) Accm: 2.84 (2.84) Acct: 4.48 (4.42) proj_loss: -0.5980 (-0.5988) time: 0.9329 data: 0.0003 [11-23 16:47:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [ 834/1669] eta: 0:12:57 tlr: 0.00022 tnm: 0.20 Lm: 6.531 (6.574) Lt: 5.858 (5.837) Accm: 3.21 (3.20) Acct: 4.72 (4.79) proj_loss: -0.6009 (-0.5932) time: 0.9329 data: 0.0003 [11-23 16:54:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.20 Lm: 6.539 (6.567) Lt: 5.827 (5.827) Accm: 3.17 (3.16) Acct: 4.73 (4.78) proj_loss: -0.5837 (-0.5865) time: 0.9335 data: 0.0003 [11-23 16:54:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.20 Lm: 6.690 (6.699) Lt: 5.962 (5.984) Accm: 2.83 (2.84) Acct: 4.32 (4.31) proj_loss: -0.5749 (-0.5748) time: 0.9335 data: 0.0003 [11-23 16:54:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.20 Lm: 6.496 (6.530) Lt: 5.742 (5.779) Accm: 3.69 (3.47) Acct: 5.72 (5.41) proj_loss: -0.5733 (-0.5736) time: 0.9335 data: 0.0003 [11-23 16:54:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.20 Lm: 6.536 (6.494) Lt: 5.761 (5.727) Accm: 3.38 (3.38) Acct: 5.56 (5.47) proj_loss: -0.5959 (-0.5918) time: 0.9335 data: 0.0003 [11-23 16:54:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.20 Lm: 6.626 (6.597) Lt: 5.832 (5.834) Accm: 3.19 (3.20) Acct: 5.11 (5.01) proj_loss: -0.5675 (-0.5687) time: 0.9335 data: 0.0003 [11-23 16:54:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.20 Lm: 6.605 (6.625) Lt: 5.823 (5.858) Accm: 3.10 (3.04) Acct: 4.98 (4.95) proj_loss: -0.5854 (-0.5878) time: 0.9335 data: 0.0003 [11-23 16:54:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.20 Lm: 6.756 (6.742) Lt: 6.056 (6.049) Accm: 2.75 (2.78) Acct: 4.30 (4.27) proj_loss: -0.5955 (-0.5955) time: 0.9335 data: 0.0003 [11-23 16:54:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [1251/1669] eta: 0:06:33 tlr: 0.00022 tnm: 0.20 Lm: 6.575 (6.601) Lt: 5.824 (5.857) Accm: 3.06 (3.03) Acct: 4.61 (4.72) proj_loss: -0.5765 (-0.5783) time: 0.9335 data: 0.0003 [11-23 17:01:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.22 Lm: 6.603 (6.610) Lt: 5.829 (5.872) Accm: 2.93 (2.97) Acct: 4.41 (4.66) proj_loss: -0.5905 (-0.5849) time: 0.9319 data: 0.0020 [11-23 17:01:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 55/350] Total time: 0:26:15 (0.944 s / it) [11-23 17:01:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.22 Lm: 6.531 (6.532) Lt: 5.795 (5.788) Accm: 3.21 (3.34) Acct: 4.75 (5.02) proj_loss: -0.5896 (-0.5871) time: 0.9319 data: 0.0019 [11-23 17:01:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.22 Lm: 6.636 (6.653) Lt: 5.916 (5.926) Accm: 3.06 (3.08) Acct: 4.68 (4.70) proj_loss: -0.5769 (-0.5812) time: 0.9319 data: 0.0018 [11-23 17:01:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.22 Lm: 6.743 (6.694) Lt: 5.986 (5.991) Accm: 2.84 (2.91) Acct: 4.48 (4.46) proj_loss: -0.5931 (-0.5925) time: 0.9319 data: 0.0018 [11-23 17:01:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.22 Lm: 6.531 (6.530) Lt: 5.781 (5.786) Accm: 3.53 (3.45) Acct: 5.51 (5.43) proj_loss: -0.5747 (-0.5780) time: 0.9319 data: 0.0016 [11-23 17:01:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.22 Lm: 6.593 (6.583) Lt: 5.816 (5.827) Accm: 3.34 (3.23) Acct: 4.89 (4.99) proj_loss: -0.5770 (-0.5748) time: 0.9319 data: 0.0016 [11-23 17:01:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.22 Lm: 6.563 (6.527) Lt: 5.779 (5.762) Accm: 3.42 (3.39) Acct: 5.27 (5.43) proj_loss: -0.5953 (-0.5925) time: 0.9319 data: 0.0019 [11-23 17:01:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 55/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.22 Lm: 6.570 (6.600) Lt: 5.737 (5.834) Accm: 3.19 (3.23) Acct: 5.17 (5.14) proj_loss: -0.6010 (-0.5950) time: 0.9319 data: 0.0019 [11-23 17:01:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 55/350] Total time: 0:26:15 (0.944 s / it) [11-23 17:01:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 55/350] Total time: 0:26:15 (0.944 s / it) [11-23 17:01:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 55/350] Total time: 0:26:15 (0.944 s / it) [11-23 17:01:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 55/350] Total time: 0:26:15 (0.944 s / it) [11-23 17:01:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 55/350] Total time: 0:26:15 (0.944 s / it) [11-23 17:01:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 55/350] Total time: 0:26:15 (0.944 s / it) [11-23 17:01:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 55/350] Total time: 0:26:15 (0.944 s / it) [11-23 17:01:15] (/home/user/VAR/train.py , line 276)=> [ep55] (training ) Lm: 6.595 (6.600), Lt: 5.845 (5.853), Acc m&t: 3.12 4.96, Remain: 5 days, 7:47:19, Finish: 2024-11-28 08:48 [11-23 17:01:15] (/home/user/VAR/train.py , line 276)=> [ep55] (training ) Lm: 6.595 (6.600), Lt: 5.845 (5.853), Acc m&t: 3.12 4.96, Remain: 5 days, 7:47:49, Finish: 2024-11-28 08:49 [11-23 17:01:15] (/home/user/VAR/train.py , line 276)=> [ep55] (training ) Lm: 6.595 (6.600), Lt: 5.845 (5.853), Acc m&t: 3.12 4.96, Remain: 5 days, 7:49:23, Finish: 2024-11-28 08:50 [11-23 17:01:15] (/home/user/VAR/train.py , line 276)=> [ep55] (training ) Lm: 6.595 (6.600), Lt: 5.845 (5.853), Acc m&t: 3.12 4.96, Remain: 5 days, 7:49:11, Finish: 2024-11-28 08:50 [11-23 17:01:15] (/home/user/VAR/train.py , line 276)=> [ep55] (training ) Lm: 6.595 (6.600), Lt: 5.845 (5.853), Acc m&t: 3.12 4.96, Remain: 5 days, 7:50:44, Finish: 2024-11-28 08:51 [11-23 17:01:15] (/home/user/VAR/train.py , line 276)=> [ep55] (training ) Lm: 6.595 (6.600), Lt: 5.845 (5.853), Acc m&t: 3.12 4.96, Remain: 5 days, 7:48:14, Finish: 2024-11-28 08:49 [11-23 17:01:15] (/home/user/VAR/train.py , line 276)=> [ep55] (training ) Lm: 6.595 (6.600), Lt: 5.845 (5.853), Acc m&t: 3.12 4.96, Remain: 5 days, 7:46:47, Finish: 2024-11-28 08:48 [11-23 17:01:15] (/home/user/VAR/train.py , line 276)=> [ep55] (training ) Lm: 6.595 (6.600), Lt: 5.845 (5.853), Acc m&t: 3.12 4.96, Remain: 5 days, 7:46:43, Finish: 2024-11-28 08:47 [11-23 17:01:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 0/1669] eta: 0:24:38 tlr: 0.00022 tnm: 0.21 Lm: 6.490 (6.490) Lt: 5.773 (5.773) Accm: 3.48 (3.48) Acct: 5.27 (5.27) proj_loss: -0.5932 (-0.5932) time: 0.8859 data: 0.0004 [11-23 17:01:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 0/1669] eta: 0:24:39 tlr: 0.00022 tnm: 0.21 Lm: 6.643 (6.643) Lt: 5.919 (5.919) Accm: 2.99 (2.99) Acct: 4.17 (4.17) proj_loss: -0.5594 (-0.5594) time: 0.8862 data: 0.0004 [11-23 17:01:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 0/1669] eta: 0:24:39 tlr: 0.00022 tnm: 0.21 Lm: 6.739 (6.739) Lt: 6.018 (6.018) Accm: 2.43 (2.43) Acct: 3.93 (3.93) proj_loss: -0.5781 (-0.5781) time: 0.8864 data: 0.0004 [11-23 17:01:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 0/1669] eta: 0:24:39 tlr: 0.00022 tnm: 0.21 Lm: 6.745 (6.745) Lt: 6.018 (6.018) Accm: 2.67 (2.67) Acct: 4.44 (4.44) proj_loss: -0.5818 (-0.5818) time: 0.8866 data: 0.0004 [11-23 17:01:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 0/1669] eta: 0:24:39 tlr: 0.00022 tnm: 0.21 Lm: 6.408 (6.408) Lt: 5.664 (5.664) Accm: 4.04 (4.04) Acct: 6.23 (6.23) proj_loss: -0.5864 (-0.5864) time: 0.8865 data: 0.0004 [11-23 17:01:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 0/1669] eta: 0:24:38 tlr: 0.00022 tnm: 0.21 Lm: 6.797 (6.797) Lt: 6.059 (6.059) Accm: 2.64 (2.64) Acct: 4.13 (4.13) proj_loss: -0.5667 (-0.5667) time: 0.8858 data: 0.0004 [11-23 17:01:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 0/1669] eta: 0:24:39 tlr: 0.00022 tnm: 0.21 Lm: 6.725 (6.725) Lt: 6.033 (6.033) Accm: 2.83 (2.83) Acct: 4.27 (4.27) proj_loss: -0.5835 (-0.5835) time: 0.8866 data: 0.0004 [11-23 17:01:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 0/1669] eta: 0:24:40 tlr: 0.00022 tnm: 0.21 Lm: 6.837 (6.837) Lt: 6.150 (6.150) Accm: 2.64 (2.64) Acct: 4.13 (4.13) proj_loss: -0.5549 (-0.5549) time: 0.8869 data: 0.0004 [11-23 17:08:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 417/1669] eta: 0:20:45 tlr: 0.00022 tnm: 0.22 Lm: 6.657 (6.657) Lt: 5.918 (5.918) Accm: 2.87 (2.87) Acct: 4.55 (4.55) proj_loss: -0.5744 (-0.5744) time: 0.9303 data: 0.0003 [11-23 17:08:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 417/1669] eta: 0:20:45 tlr: 0.00022 tnm: 0.22 Lm: 6.570 (6.570) Lt: 5.816 (5.816) Accm: 3.51 (3.51) Acct: 5.63 (5.63) proj_loss: -0.5910 (-0.5910) time: 0.9303 data: 0.0003 [11-23 17:08:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 417/1669] eta: 0:20:45 tlr: 0.00022 tnm: 0.22 Lm: 6.744 (6.744) Lt: 5.988 (5.988) Accm: 2.88 (2.88) Acct: 4.58 (4.58) proj_loss: -0.5917 (-0.5917) time: 0.9303 data: 0.0003 [11-23 17:08:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 417/1669] eta: 0:20:45 tlr: 0.00022 tnm: 0.22 Lm: 6.578 (6.578) Lt: 5.824 (5.824) Accm: 3.26 (3.26) Acct: 4.79 (4.79) proj_loss: -0.5689 (-0.5689) time: 0.9303 data: 0.0002 [11-23 17:08:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 417/1669] eta: 0:20:45 tlr: 0.00022 tnm: 0.22 Lm: 6.679 (6.679) Lt: 5.963 (5.963) Accm: 2.96 (2.96) Acct: 4.44 (4.44) proj_loss: -0.5648 (-0.5648) time: 0.9303 data: 0.0003 [11-23 17:08:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 417/1669] eta: 0:20:45 tlr: 0.00022 tnm: 0.22 Lm: 6.612 (6.612) Lt: 5.912 (5.912) Accm: 3.07 (3.07) Acct: 4.96 (4.96) proj_loss: -0.5816 (-0.5816) time: 0.9303 data: 0.0003 [11-23 17:08:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 417/1669] eta: 0:20:45 tlr: 0.00022 tnm: 0.22 Lm: 6.566 (6.566) Lt: 5.805 (5.805) Accm: 3.10 (3.10) Acct: 4.92 (4.92) proj_loss: -0.5633 (-0.5633) time: 0.9303 data: 0.0003 [11-23 17:08:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 417/1669] eta: 0:20:45 tlr: 0.00022 tnm: 0.22 Lm: 6.668 (6.668) Lt: 5.933 (5.933) Accm: 3.05 (3.05) Acct: 4.80 (4.80) proj_loss: -0.5726 (-0.5726) time: 0.9303 data: 0.0003 [11-23 17:14:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 834/1669] eta: 0:13:24 tlr: 0.00022 tnm: 0.21 Lm: 6.611 (6.629) Lt: 5.834 (5.873) Accm: 3.03 (3.04) Acct: 4.61 (4.74) proj_loss: -0.5618 (-0.5680) time: 0.9314 data: 0.0003 [11-23 17:14:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 834/1669] eta: 0:13:24 tlr: 0.00022 tnm: 0.21 Lm: 6.745 (6.664) Lt: 6.018 (5.948) Accm: 2.74 (2.96) Acct: 4.48 (4.80) proj_loss: -0.5818 (-0.5830) time: 0.9314 data: 0.0003 [11-23 17:14:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 834/1669] eta: 0:13:24 tlr: 0.00022 tnm: 0.21 Lm: 6.643 (6.605) Lt: 5.901 (5.850) Accm: 3.02 (3.18) Acct: 4.75 (4.78) proj_loss: -0.5605 (-0.5661) time: 0.9314 data: 0.0003 [11-23 17:14:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 834/1669] eta: 0:13:24 tlr: 0.00022 tnm: 0.21 Lm: 6.408 (6.493) Lt: 5.664 (5.693) Accm: 4.04 (3.70) Acct: 6.23 (5.83) proj_loss: -0.5864 (-0.5853) time: 0.9314 data: 0.0003 [11-23 17:14:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 834/1669] eta: 0:13:24 tlr: 0.00022 tnm: 0.21 Lm: 6.725 (6.738) Lt: 6.059 (6.012) Accm: 2.64 (2.77) Acct: 4.13 (4.41) proj_loss: -0.5931 (-0.5922) time: 0.9314 data: 0.0003 [11-23 17:14:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 834/1669] eta: 0:13:24 tlr: 0.00022 tnm: 0.21 Lm: 6.511 (6.608) Lt: 5.787 (5.875) Accm: 3.10 (3.00) Acct: 4.96 (4.86) proj_loss: -0.5939 (-0.5854) time: 0.9314 data: 0.0003 [11-23 17:14:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 834/1669] eta: 0:13:24 tlr: 0.00022 tnm: 0.21 Lm: 6.471 (6.534) Lt: 5.748 (5.786) Accm: 3.54 (3.24) Acct: 5.75 (5.20) proj_loss: -0.5781 (-0.5791) time: 0.9314 data: 0.0003 [11-23 17:14:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [ 834/1669] eta: 0:13:24 tlr: 0.00022 tnm: 0.21 Lm: 6.553 (6.637) Lt: 5.785 (5.904) Accm: 3.38 (3.10) Acct: 5.10 (4.66) proj_loss: -0.5624 (-0.5640) time: 0.9314 data: 0.0003 [11-23 17:21:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [1251/1669] eta: 0:06:38 tlr: 0.00022 tnm: 0.21 Lm: 6.711 (6.705) Lt: 5.969 (5.980) Accm: 2.91 (2.88) Acct: 4.36 (4.30) proj_loss: -0.5726 (-0.5687) time: 0.9304 data: 0.0003 [11-23 17:21:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [1251/1669] eta: 0:06:38 tlr: 0.00022 tnm: 0.21 Lm: 6.640 (6.648) Lt: 5.930 (5.924) Accm: 2.87 (2.91) Acct: 4.58 (4.69) proj_loss: -0.5902 (-0.5856) time: 0.9304 data: 0.0003 [11-23 17:21:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [1251/1669] eta: 0:06:38 tlr: 0.00022 tnm: 0.21 Lm: 6.708 (6.670) Lt: 5.988 (5.922) Accm: 2.88 (3.02) Acct: 4.58 (4.91) proj_loss: -0.5915 (-0.5916) time: 0.9304 data: 0.0003 [11-23 17:21:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [1251/1669] eta: 0:06:38 tlr: 0.00022 tnm: 0.21 Lm: 6.713 (6.668) Lt: 5.996 (5.954) Accm: 2.78 (2.93) Acct: 4.46 (4.69) proj_loss: -0.5816 (-0.5810) time: 0.9304 data: 0.0003 [11-23 17:21:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [1251/1669] eta: 0:06:38 tlr: 0.00022 tnm: 0.21 Lm: 6.600 (6.593) Lt: 5.819 (5.821) Accm: 3.17 (3.21) Acct: 5.08 (4.94) proj_loss: -0.5606 (-0.5648) time: 0.9304 data: 0.0003 [11-23 17:21:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [1251/1669] eta: 0:06:38 tlr: 0.00022 tnm: 0.21 Lm: 6.560 (6.563) Lt: 5.810 (5.808) Accm: 3.49 (3.29) Acct: 5.84 (5.42) proj_loss: -0.5767 (-0.5781) time: 0.9304 data: 0.0003 [11-23 17:21:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [1251/1669] eta: 0:06:38 tlr: 0.00022 tnm: 0.21 Lm: 6.619 (6.628) Lt: 5.836 (5.864) Accm: 2.98 (3.02) Acct: 4.77 (4.79) proj_loss: -0.5602 (-0.5616) time: 0.9304 data: 0.0003 [11-23 17:21:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [1251/1669] eta: 0:06:38 tlr: 0.00022 tnm: 0.21 Lm: 6.570 (6.554) Lt: 5.816 (5.777) Accm: 3.51 (3.36) Acct: 5.63 (5.34) proj_loss: -0.5801 (-0.5817) time: 0.9304 data: 0.0003 [11-23 17:27:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.711 (6.585) Lt: 5.928 (5.807) Accm: 2.99 (3.25) Acct: 5.03 (5.24) proj_loss: -0.5739 (-0.5785) time: 0.9339 data: 0.0016 [11-23 17:27:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 56/350] Total time: 0:26:20 (0.947 s / it) [11-23 17:27:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.627 (6.644) Lt: 5.839 (5.892) Accm: 2.93 (2.94) Acct: 4.61 (4.66) proj_loss: -0.5618 (-0.5647) time: 0.9339 data: 0.0016 [11-23 17:27:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.643 (6.604) Lt: 5.833 (5.824) Accm: 3.02 (3.14) Acct: 4.75 (4.78) proj_loss: -0.5607 (-0.5696) time: 0.9338 data: 0.0017 [11-23 17:27:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.603 (6.571) Lt: 5.872 (5.827) Accm: 3.44 (3.21) Acct: 5.75 (5.10) proj_loss: -0.5781 (-0.5800) time: 0.9339 data: 0.0020 [11-23 17:27:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.681 (6.605) Lt: 5.974 (5.880) Accm: 2.83 (3.11) Acct: 4.48 (5.03) proj_loss: -0.5818 (-0.5820) time: 0.9339 data: 0.0016 [11-23 17:27:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.692 (6.653) Lt: 5.917 (5.902) Accm: 3.12 (3.08) Acct: 5.03 (4.97) proj_loss: -0.5899 (-0.5905) time: 0.9339 data: 0.0016 [11-23 17:27:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.621 (6.643) Lt: 5.879 (5.915) Accm: 3.10 (2.98) Acct: 4.96 (4.79) proj_loss: -0.5939 (-0.5881) time: 0.9339 data: 0.0021 [11-23 17:27:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 56/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.553 (6.649) Lt: 5.785 (5.906) Accm: 3.38 (2.99) Acct: 4.96 (4.44) proj_loss: -0.5829 (-0.5734) time: 0.9339 data: 0.0017 [11-23 17:27:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 56/350] Total time: 0:26:20 (0.947 s / it) [11-23 17:27:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 56/350] Total time: 0:26:20 (0.947 s / it) [11-23 17:27:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 56/350] Total time: 0:26:20 (0.947 s / it) [11-23 17:27:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 56/350] Total time: 0:26:20 (0.947 s / it) [11-23 17:27:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 56/350] Total time: 0:26:20 (0.947 s / it) [11-23 17:27:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 56/350] Total time: 0:26:20 (0.947 s / it) [11-23 17:27:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 56/350] Total time: 0:26:20 (0.947 s / it) [11-23 17:27:36] (/home/user/VAR/train.py , line 276)=> [ep56] (training ) Lm: 6.595 (6.598), Lt: 5.845 (5.850), Acc m&t: 3.12 4.96, Remain: 5 days, 7:38:39, Finish: 2024-11-28 09:06 [11-23 17:27:36] (/home/user/VAR/train.py , line 276)=> [ep56] (training ) Lm: 6.595 (6.598), Lt: 5.845 (5.850), Acc m&t: 3.12 4.96, Remain: 5 days, 7:37:37, Finish: 2024-11-28 09:05 [11-23 17:27:36] (/home/user/VAR/train.py , line 276)=> [ep56] (training ) Lm: 6.595 (6.598), Lt: 5.845 (5.850), Acc m&t: 3.12 4.96, Remain: 5 days, 7:36:02, Finish: 2024-11-28 09:03 [11-23 17:27:36] (/home/user/VAR/train.py , line 276)=> [ep56] (training ) Lm: 6.595 (6.598), Lt: 5.845 (5.850), Acc m&t: 3.12 4.96, Remain: 5 days, 7:38:26, Finish: 2024-11-28 09:06 [11-23 17:27:36] (/home/user/VAR/train.py , line 276)=> [ep56] (training ) Lm: 6.595 (6.598), Lt: 5.845 (5.850), Acc m&t: 3.12 4.96, Remain: 5 days, 7:35:42, Finish: 2024-11-28 09:03 [11-23 17:27:36] (/home/user/VAR/train.py , line 276)=> [ep56] (training ) Lm: 6.595 (6.598), Lt: 5.845 (5.850), Acc m&t: 3.12 4.96, Remain: 5 days, 7:37:31, Finish: 2024-11-28 09:05 [11-23 17:27:36] (/home/user/VAR/train.py , line 276)=> [ep56] (training ) Lm: 6.595 (6.598), Lt: 5.845 (5.850), Acc m&t: 3.12 4.96, Remain: 5 days, 7:37:07, Finish: 2024-11-28 09:04 [11-23 17:27:36] (/home/user/VAR/train.py , line 276)=> [ep56] (training ) Lm: 6.595 (6.598), Lt: 5.845 (5.850), Acc m&t: 3.12 4.96, Remain: 5 days, 7:38:15, Finish: 2024-11-28 09:05 [11-23 17:27:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 0/1669] eta: 0:25:32 tlr: 0.00022 tnm: 0.21 Lm: 6.388 (6.388) Lt: 5.661 (5.661) Accm: 3.57 (3.57) Acct: 5.65 (5.65) proj_loss: -0.5770 (-0.5770) time: 0.9180 data: 0.0004 [11-23 17:27:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 0/1669] eta: 0:25:32 tlr: 0.00022 tnm: 0.21 Lm: 6.493 (6.493) Lt: 5.773 (5.773) Accm: 3.23 (3.23) Acct: 4.89 (4.89) proj_loss: -0.5775 (-0.5775) time: 0.9180 data: 0.0004 [11-23 17:27:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 0/1669] eta: 0:25:32 tlr: 0.00022 tnm: 0.21 Lm: 6.600 (6.600) Lt: 5.866 (5.866) Accm: 3.15 (3.15) Acct: 4.92 (4.92) proj_loss: -0.6018 (-0.6018) time: 0.9182 data: 0.0003 [11-23 17:27:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 0/1669] eta: 0:25:32 tlr: 0.00022 tnm: 0.21 Lm: 6.676 (6.676) Lt: 5.977 (5.977) Accm: 2.96 (2.96) Acct: 4.34 (4.34) proj_loss: -0.5869 (-0.5869) time: 0.9183 data: 0.0003 [11-23 17:27:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 0/1669] eta: 0:25:32 tlr: 0.00022 tnm: 0.21 Lm: 6.465 (6.465) Lt: 5.670 (5.670) Accm: 3.44 (3.44) Acct: 4.92 (4.92) proj_loss: -0.5483 (-0.5483) time: 0.9181 data: 0.0003 [11-23 17:27:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 0/1669] eta: 0:25:26 tlr: 0.00022 tnm: 0.21 Lm: 6.590 (6.590) Lt: 5.895 (5.895) Accm: 3.09 (3.09) Acct: 4.86 (4.86) proj_loss: -0.5795 (-0.5795) time: 0.9145 data: 0.0004 [11-23 17:27:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 0/1669] eta: 0:25:32 tlr: 0.00022 tnm: 0.21 Lm: 6.748 (6.748) Lt: 6.012 (6.012) Accm: 2.80 (2.80) Acct: 4.72 (4.72) proj_loss: -0.5918 (-0.5918) time: 0.9185 data: 0.0003 [11-23 17:27:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 0/1669] eta: 0:25:32 tlr: 0.00022 tnm: 0.21 Lm: 6.604 (6.604) Lt: 5.900 (5.900) Accm: 2.94 (2.94) Acct: 4.48 (4.48) proj_loss: -0.5549 (-0.5549) time: 0.9182 data: 0.0004 [11-23 17:34:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.22 Lm: 6.589 (6.589) Lt: 5.859 (5.859) Accm: 3.21 (3.21) Acct: 5.03 (5.03) proj_loss: -0.5578 (-0.5578) time: 0.9306 data: 0.0003 [11-23 17:34:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.22 Lm: 6.548 (6.548) Lt: 5.773 (5.773) Accm: 3.23 (3.23) Acct: 4.84 (4.84) proj_loss: -0.5681 (-0.5681) time: 0.9306 data: 0.0003 [11-23 17:34:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.22 Lm: 6.444 (6.444) Lt: 5.647 (5.647) Accm: 3.42 (3.42) Acct: 5.53 (5.53) proj_loss: -0.5681 (-0.5681) time: 0.9306 data: 0.0003 [11-23 17:34:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.22 Lm: 6.641 (6.641) Lt: 5.852 (5.852) Accm: 3.02 (3.02) Acct: 4.87 (4.87) proj_loss: -0.5910 (-0.5910) time: 0.9306 data: 0.0003 [11-23 17:34:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.22 Lm: 6.588 (6.588) Lt: 5.850 (5.850) Accm: 3.11 (3.11) Acct: 4.70 (4.70) proj_loss: -0.5871 (-0.5871) time: 0.9306 data: 0.0003 [11-23 17:34:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.22 Lm: 6.628 (6.628) Lt: 5.914 (5.914) Accm: 2.94 (2.94) Acct: 4.42 (4.42) proj_loss: -0.5726 (-0.5726) time: 0.9306 data: 0.0003 [11-23 17:34:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.22 Lm: 6.634 (6.634) Lt: 5.907 (5.907) Accm: 2.99 (2.99) Acct: 4.51 (4.51) proj_loss: -0.6015 (-0.6015) time: 0.9306 data: 0.0003 [11-23 17:34:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 417/1669] eta: 0:19:26 tlr: 0.00022 tnm: 0.22 Lm: 6.561 (6.561) Lt: 5.817 (5.817) Accm: 3.15 (3.15) Acct: 4.99 (4.99) proj_loss: -0.5703 (-0.5703) time: 0.9306 data: 0.0003 [11-23 17:41:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 834/1669] eta: 0:13:30 tlr: 0.00022 tnm: 0.21 Lm: 6.631 (6.650) Lt: 5.876 (5.890) Accm: 3.02 (2.99) Acct: 4.75 (4.53) proj_loss: -0.5880 (-0.5754) time: 1.1917 data: 0.0003 [11-23 17:41:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 834/1669] eta: 0:13:30 tlr: 0.00022 tnm: 0.21 Lm: 6.592 (6.595) Lt: 5.874 (5.896) Accm: 3.02 (3.04) Acct: 4.68 (4.58) proj_loss: -0.6014 (-0.6015) time: 1.1917 data: 0.0003 [11-23 17:41:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 834/1669] eta: 0:13:30 tlr: 0.00022 tnm: 0.21 Lm: 6.537 (6.606) Lt: 5.845 (5.850) Accm: 3.23 (3.09) Acct: 5.03 (4.98) proj_loss: -0.5918 (-0.5920) time: 1.1917 data: 0.0003 [11-23 17:41:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 834/1669] eta: 0:13:30 tlr: 0.00022 tnm: 0.21 Lm: 6.575 (6.561) Lt: 5.819 (5.787) Accm: 3.47 (3.32) Acct: 5.58 (5.26) proj_loss: -0.5549 (-0.5545) time: 1.1917 data: 0.0003 [11-23 17:41:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 834/1669] eta: 0:13:30 tlr: 0.00022 tnm: 0.21 Lm: 6.500 (6.506) Lt: 5.661 (5.728) Accm: 3.28 (3.19) Acct: 5.41 (5.17) proj_loss: -0.5690 (-0.5684) time: 1.1917 data: 0.0003 [11-23 17:41:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 834/1669] eta: 0:13:30 tlr: 0.00022 tnm: 0.21 Lm: 6.590 (6.600) Lt: 5.895 (5.860) Accm: 3.09 (3.05) Acct: 4.86 (4.90) proj_loss: -0.5795 (-0.5760) time: 1.1917 data: 0.0003 [11-23 17:41:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 834/1669] eta: 0:13:30 tlr: 0.00022 tnm: 0.21 Lm: 6.600 (6.616) Lt: 5.866 (5.865) Accm: 3.10 (3.11) Acct: 4.92 (4.86) proj_loss: -0.5724 (-0.5776) time: 1.1917 data: 0.0003 [11-23 17:41:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [ 834/1669] eta: 0:13:30 tlr: 0.00022 tnm: 0.21 Lm: 6.563 (6.607) Lt: 5.773 (5.851) Accm: 3.23 (3.06) Acct: 4.89 (4.67) proj_loss: -0.5678 (-0.5558) time: 1.1917 data: 0.0003 [11-23 17:47:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [1251/1669] eta: 0:06:44 tlr: 0.00022 tnm: 0.20 Lm: 6.598 (6.613) Lt: 5.865 (5.877) Accm: 3.01 (2.99) Acct: 4.61 (4.59) proj_loss: -0.5726 (-0.5630) time: 0.9326 data: 0.0003 [11-23 17:47:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [1251/1669] eta: 0:06:44 tlr: 0.00022 tnm: 0.20 Lm: 6.536 (6.580) Lt: 5.800 (5.826) Accm: 3.21 (3.12) Acct: 4.92 (4.94) proj_loss: -0.5926 (-0.5924) time: 0.9326 data: 0.0003 [11-23 17:47:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [1251/1669] eta: 0:06:44 tlr: 0.00022 tnm: 0.20 Lm: 6.640 (6.650) Lt: 5.866 (5.882) Accm: 2.77 (2.87) Acct: 4.53 (4.48) proj_loss: -0.5890 (-0.5819) time: 0.9326 data: 0.0003 [11-23 17:47:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [1251/1669] eta: 0:06:44 tlr: 0.00022 tnm: 0.20 Lm: 6.634 (6.638) Lt: 5.925 (5.930) Accm: 2.99 (2.96) Acct: 4.70 (4.66) proj_loss: -0.5941 (-0.5885) time: 0.9326 data: 0.0003 [11-23 17:47:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [1251/1669] eta: 0:06:44 tlr: 0.00022 tnm: 0.20 Lm: 6.588 (6.568) Lt: 5.850 (5.810) Accm: 3.13 (3.22) Acct: 5.04 (5.09) proj_loss: -0.5690 (-0.5746) time: 0.9326 data: 0.0003 [11-23 17:47:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [1251/1669] eta: 0:06:44 tlr: 0.00022 tnm: 0.20 Lm: 6.532 (6.520) Lt: 5.767 (5.764) Accm: 3.31 (3.23) Acct: 5.11 (5.08) proj_loss: -0.5730 (-0.5786) time: 0.9326 data: 0.0003 [11-23 17:47:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [1251/1669] eta: 0:06:44 tlr: 0.00022 tnm: 0.20 Lm: 6.539 (6.511) Lt: 5.730 (5.727) Accm: 3.51 (3.52) Acct: 5.65 (5.44) proj_loss: -0.5562 (-0.5553) time: 0.9326 data: 0.0003 [11-23 17:47:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [1251/1669] eta: 0:06:44 tlr: 0.00022 tnm: 0.20 Lm: 6.628 (6.616) Lt: 5.920 (5.909) Accm: 2.99 (3.01) Acct: 4.79 (4.80) proj_loss: -0.5836 (-0.5848) time: 0.9326 data: 0.0003 [11-23 17:54:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.590 (6.592) Lt: 5.895 (5.872) Accm: 3.09 (3.10) Acct: 4.86 (4.90) proj_loss: -0.5795 (-0.5825) time: 0.9335 data: 0.0020 [11-23 17:54:18] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 57/350] Total time: 0:26:42 (0.960 s / it) [11-23 17:54:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.631 (6.567) Lt: 5.856 (5.791) Accm: 3.02 (3.20) Acct: 4.75 (5.02) proj_loss: -0.5899 (-0.5850) time: 0.9335 data: 0.0017 [11-23 17:54:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.563 (6.586) Lt: 5.773 (5.842) Accm: 3.23 (3.15) Acct: 4.89 (4.80) proj_loss: -0.5711 (-0.5646) time: 0.9335 data: 0.0016 [11-23 17:54:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.535 (6.560) Lt: 5.755 (5.798) Accm: 3.19 (3.12) Acct: 5.03 (4.96) proj_loss: -0.5918 (-0.5897) time: 0.9335 data: 0.0017 [11-23 17:54:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.592 (6.604) Lt: 5.874 (5.877) Accm: 3.02 (3.10) Acct: 4.72 (4.86) proj_loss: -0.5869 (-0.5845) time: 0.9335 data: 0.0015 [11-23 17:54:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.565 (6.553) Lt: 5.873 (5.790) Accm: 3.28 (3.16) Acct: 4.82 (4.97) proj_loss: -0.5690 (-0.5764) time: 0.9335 data: 0.0019 [11-23 17:54:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.543 (6.517) Lt: 5.698 (5.721) Accm: 3.47 (3.46) Acct: 5.58 (5.39) proj_loss: -0.5575 (-0.5583) time: 0.9335 data: 0.0016 [11-23 17:54:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 57/350] [1668/1669] eta: 0:00:00 tlr: 0.00022 tnm: 0.21 Lm: 6.600 (6.589) Lt: 5.866 (5.844) Accm: 3.10 (3.11) Acct: 4.92 (4.95) proj_loss: -0.5724 (-0.5782) time: 0.9336 data: 0.0016 [11-23 17:54:18] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 57/350] Total time: 0:26:42 (0.960 s / it) [11-23 17:54:18] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 57/350] Total time: 0:26:42 (0.960 s / it) [11-23 17:54:18] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 57/350] Total time: 0:26:42 (0.960 s / it) [11-23 17:54:18] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 57/350] Total time: 0:26:42 (0.960 s / it) [11-23 17:54:18] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 57/350] Total time: 0:26:42 (0.960 s / it) [11-23 17:54:18] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 57/350] Total time: 0:26:42 (0.960 s / it) [11-23 17:54:18] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 57/350] Total time: 0:26:42 (0.960 s / it) [11-23 17:54:18] (/home/user/VAR/train.py , line 276)=> [ep57] (training ) Lm: 6.577 (6.577), Lt: 5.824 (5.824), Acc m&t: 3.18 4.99, Remain: 5 days, 7:10:13, Finish: 2024-11-28 09:04 [11-23 17:54:18] (/home/user/VAR/train.py , line 276)=> [ep57] (training ) Lm: 6.577 (6.577), Lt: 5.824 (5.824), Acc m&t: 3.18 4.99, Remain: 5 days, 7:07:44, Finish: 2024-11-28 09:02 [11-23 17:54:18] (/home/user/VAR/train.py , line 276)=> [ep57] (training ) Lm: 6.577 (6.577), Lt: 5.824 (5.824), Acc m&t: 3.18 4.99, Remain: 5 days, 7:08:35, Finish: 2024-11-28 09:02 [11-23 17:54:18] (/home/user/VAR/train.py , line 276)=> [ep57] (training ) Lm: 6.577 (6.577), Lt: 5.824 (5.824), Acc m&t: 3.18 4.99, Remain: 5 days, 7:09:37, Finish: 2024-11-28 09:03 [11-23 17:54:18] (/home/user/VAR/train.py , line 276)=> [ep57] (training ) Lm: 6.577 (6.577), Lt: 5.824 (5.824), Acc m&t: 3.18 4.99, Remain: 5 days, 7:08:12, Finish: 2024-11-28 09:02 [11-23 17:54:18] (/home/user/VAR/train.py , line 276)=> [ep57] (training ) Lm: 6.577 (6.577), Lt: 5.824 (5.824), Acc m&t: 3.18 4.99, Remain: 5 days, 7:11:10, Finish: 2024-11-28 09:05 [11-23 17:54:18] (/home/user/VAR/train.py , line 276)=> [ep57] (training ) Lm: 6.577 (6.577), Lt: 5.824 (5.824), Acc m&t: 3.18 4.99, Remain: 5 days, 7:12:42, Finish: 2024-11-28 09:07 [11-23 17:54:18] (/home/user/VAR/train.py , line 276)=> [ep57] (training ) Lm: 6.577 (6.577), Lt: 5.824 (5.824), Acc m&t: 3.18 4.99, Remain: 5 days, 7:08:34, Finish: 2024-11-28 09:02 [11-23 17:54:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 0/1669] eta: 0:25:22 tlr: 0.00022 tnm: 0.22 Lm: 6.668 (6.668) Lt: 5.929 (5.929) Accm: 2.61 (2.61) Acct: 3.99 (3.99) proj_loss: -0.5831 (-0.5831) time: 0.9122 data: 0.0003 [11-23 17:54:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 0/1669] eta: 0:25:23 tlr: 0.00022 tnm: 0.22 Lm: 6.849 (6.849) Lt: 6.193 (6.193) Accm: 2.42 (2.42) Acct: 3.93 (3.93) proj_loss: -0.5996 (-0.5996) time: 0.9127 data: 0.0003 [11-23 17:54:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 0/1669] eta: 0:25:39 tlr: 0.00022 tnm: 0.22 Lm: 6.671 (6.671) Lt: 5.981 (5.981) Accm: 2.67 (2.67) Acct: 3.99 (3.99) proj_loss: -0.5805 (-0.5805) time: 0.9225 data: 0.0004 [11-23 17:54:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 0/1669] eta: 0:25:23 tlr: 0.00022 tnm: 0.22 Lm: 6.785 (6.785) Lt: 6.047 (6.047) Accm: 2.97 (2.97) Acct: 4.99 (4.99) proj_loss: -0.5452 (-0.5452) time: 0.9128 data: 0.0003 [11-23 17:54:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 0/1669] eta: 0:25:23 tlr: 0.00022 tnm: 0.22 Lm: 6.367 (6.367) Lt: 5.652 (5.652) Accm: 4.06 (4.06) Acct: 5.99 (5.99) proj_loss: -0.6111 (-0.6111) time: 0.9128 data: 0.0003 [11-23 17:54:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 0/1669] eta: 0:25:21 tlr: 0.00022 tnm: 0.22 Lm: 6.613 (6.613) Lt: 5.847 (5.847) Accm: 3.09 (3.09) Acct: 4.79 (4.79) proj_loss: -0.5523 (-0.5523) time: 0.9119 data: 0.0004 [11-23 17:54:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 0/1669] eta: 0:25:22 tlr: 0.00022 tnm: 0.22 Lm: 6.577 (6.577) Lt: 5.864 (5.864) Accm: 3.18 (3.18) Acct: 5.06 (5.06) proj_loss: -0.5711 (-0.5711) time: 0.9120 data: 0.0003 [11-23 17:54:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 0/1669] eta: 0:25:24 tlr: 0.00022 tnm: 0.22 Lm: 6.608 (6.608) Lt: 5.832 (5.832) Accm: 2.86 (2.86) Acct: 4.27 (4.27) proj_loss: -0.5638 (-0.5638) time: 0.9136 data: 0.0004 [11-23 18:00:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.19 Lm: 6.564 (6.564) Lt: 5.809 (5.809) Accm: 3.34 (3.34) Acct: 5.20 (5.20) proj_loss: -0.5780 (-0.5780) time: 0.9291 data: 0.0003 [11-23 18:00:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.19 Lm: 6.652 (6.652) Lt: 5.900 (5.900) Accm: 3.00 (3.00) Acct: 4.68 (4.68) proj_loss: -0.5780 (-0.5780) time: 0.9291 data: 0.0003 [11-23 18:00:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.19 Lm: 6.496 (6.496) Lt: 5.793 (5.793) Accm: 3.42 (3.42) Acct: 5.34 (5.34) proj_loss: -0.5727 (-0.5727) time: 0.9291 data: 0.0003 [11-23 18:00:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.19 Lm: 6.827 (6.827) Lt: 6.131 (6.131) Accm: 2.52 (2.52) Acct: 3.82 (3.82) proj_loss: -0.5809 (-0.5809) time: 0.9291 data: 0.0003 [11-23 18:00:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.19 Lm: 6.617 (6.617) Lt: 5.899 (5.899) Accm: 3.21 (3.21) Acct: 5.25 (5.25) proj_loss: -0.5848 (-0.5848) time: 0.9291 data: 0.0003 [11-23 18:00:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.19 Lm: 6.628 (6.628) Lt: 5.899 (5.899) Accm: 3.11 (3.11) Acct: 5.20 (5.20) proj_loss: -0.5757 (-0.5757) time: 0.9291 data: 0.0003 [11-23 18:00:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.19 Lm: 6.620 (6.620) Lt: 5.881 (5.881) Accm: 2.93 (2.93) Acct: 4.42 (4.42) proj_loss: -0.5683 (-0.5683) time: 0.9291 data: 0.0003 [11-23 18:00:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 417/1669] eta: 0:19:25 tlr: 0.00022 tnm: 0.19 Lm: 6.507 (6.507) Lt: 5.726 (5.726) Accm: 3.58 (3.58) Acct: 5.72 (5.72) proj_loss: -0.5956 (-0.5956) time: 0.9291 data: 0.0003 [11-23 18:07:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.647 (6.558) Lt: 5.801 (5.793) Accm: 3.10 (3.31) Acct: 5.44 (5.13) proj_loss: -0.5913 (-0.5941) time: 0.9298 data: 0.0003 [11-23 18:07:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.668 (6.660) Lt: 5.929 (5.915) Accm: 2.94 (2.93) Acct: 4.48 (4.44) proj_loss: -0.5831 (-0.5824) time: 0.9298 data: 0.0003 [11-23 18:07:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.712 (6.788) Lt: 5.981 (6.080) Accm: 2.67 (2.58) Acct: 3.99 (4.05) proj_loss: -0.5813 (-0.5812) time: 0.9298 data: 0.0003 [11-23 18:07:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.613 (6.541) Lt: 5.847 (5.776) Accm: 3.09 (3.24) Acct: 4.79 (5.10) proj_loss: -0.5576 (-0.5712) time: 0.9298 data: 0.0003 [11-23 18:07:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.546 (6.513) Lt: 5.812 (5.799) Accm: 3.25 (3.37) Acct: 5.51 (5.39) proj_loss: -0.5744 (-0.5758) time: 0.9298 data: 0.0003 [11-23 18:07:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.520 (6.540) Lt: 5.787 (5.777) Accm: 3.28 (3.32) Acct: 5.30 (5.23) proj_loss: -0.5923 (-0.5830) time: 0.9298 data: 0.0003 [11-23 18:07:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.693 (6.650) Lt: 5.981 (5.926) Accm: 2.97 (3.04) Acct: 4.99 (5.13) proj_loss: -0.5940 (-0.5818) time: 0.9298 data: 0.0003 [11-23 18:07:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.794 (6.676) Lt: 6.062 (5.953) Accm: 2.53 (2.98) Acct: 4.03 (4.84) proj_loss: -0.5794 (-0.5830) time: 0.9298 data: 0.0003 [11-23 18:13:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.21 Lm: 6.667 (6.642) Lt: 5.912 (5.906) Accm: 2.80 (3.00) Acct: 4.51 (4.88) proj_loss: -0.5895 (-0.5875) time: 0.9302 data: 0.0003 [11-23 18:13:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.21 Lm: 6.551 (6.532) Lt: 5.739 (5.764) Accm: 3.28 (3.35) Acct: 5.44 (5.21) proj_loss: -0.5880 (-0.5918) time: 0.9302 data: 0.0003 [11-23 18:13:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.21 Lm: 6.561 (6.530) Lt: 5.781 (5.787) Accm: 3.21 (3.28) Acct: 5.29 (5.24) proj_loss: -0.5727 (-0.5649) time: 0.9302 data: 0.0003 [11-23 18:13:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.21 Lm: 6.691 (6.715) Lt: 5.979 (5.986) Accm: 2.68 (2.78) Acct: 4.25 (4.46) proj_loss: -0.5815 (-0.5825) time: 0.9302 data: 0.0003 [11-23 18:13:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.21 Lm: 6.506 (6.525) Lt: 5.750 (5.737) Accm: 3.31 (3.33) Acct: 5.34 (5.27) proj_loss: -0.5780 (-0.5757) time: 0.9302 data: 0.0003 [11-23 18:13:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.21 Lm: 6.642 (6.650) Lt: 5.881 (5.890) Accm: 3.08 (3.00) Acct: 4.67 (4.62) proj_loss: -0.5765 (-0.5793) time: 0.9302 data: 0.0003 [11-23 18:13:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.21 Lm: 6.653 (6.641) Lt: 5.919 (5.909) Accm: 2.94 (3.01) Acct: 4.99 (5.01) proj_loss: -0.5696 (-0.5719) time: 0.9302 data: 0.0003 [11-23 18:13:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.21 Lm: 6.637 (6.571) Lt: 5.899 (5.820) Accm: 3.06 (3.19) Acct: 5.04 (5.15) proj_loss: -0.5550 (-0.5664) time: 0.9302 data: 0.0003 [11-23 18:20:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.613 (6.568) Lt: 5.896 (5.835) Accm: 3.09 (3.23) Acct: 5.17 (5.15) proj_loss: -0.5576 (-0.5741) time: 0.9321 data: 0.0017 [11-23 18:20:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 58/350] Total time: 0:26:14 (0.943 s / it) [11-23 18:20:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.617 (6.601) Lt: 5.833 (5.825) Accm: 3.22 (3.19) Acct: 4.86 (4.99) proj_loss: -0.5831 (-0.5829) time: 0.9321 data: 0.0019 [11-23 18:20:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.556 (6.535) Lt: 5.792 (5.788) Accm: 3.25 (3.33) Acct: 5.51 (5.31) proj_loss: -0.5744 (-0.5695) time: 0.9321 data: 0.0017 [11-23 18:20:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.542 (6.534) Lt: 5.757 (5.763) Accm: 3.29 (3.34) Acct: 5.44 (5.18) proj_loss: -0.5913 (-0.5939) time: 0.9321 data: 0.0017 [11-23 18:20:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.671 (6.679) Lt: 5.978 (5.945) Accm: 2.70 (2.89) Acct: 4.51 (4.66) proj_loss: -0.5813 (-0.5775) time: 0.9321 data: 0.0017 [11-23 18:20:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.670 (6.647) Lt: 5.889 (5.902) Accm: 3.06 (3.01) Acct: 4.89 (4.88) proj_loss: -0.5794 (-0.5823) time: 0.9321 data: 0.0021 [11-23 18:20:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.520 (6.533) Lt: 5.769 (5.744) Accm: 3.28 (3.27) Acct: 5.30 (5.23) proj_loss: -0.5638 (-0.5731) time: 0.9321 data: 0.0017 [11-23 18:20:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 58/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.613 (6.635) Lt: 5.959 (5.919) Accm: 2.97 (3.01) Acct: 4.99 (4.86) proj_loss: -0.5940 (-0.5781) time: 0.9321 data: 0.0019 [11-23 18:20:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 58/350] Total time: 0:26:14 (0.943 s / it) [11-23 18:20:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 58/350] Total time: 0:26:14 (0.943 s / it) [11-23 18:20:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 58/350] Total time: 0:26:14 (0.943 s / it) [11-23 18:20:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 58/350] Total time: 0:26:14 (0.943 s / it) [11-23 18:20:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 58/350] Total time: 0:26:14 (0.943 s / it) [11-23 18:20:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 58/350] Total time: 0:26:14 (0.943 s / it) [11-23 18:20:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 58/350] Total time: 0:26:14 (0.943 s / it) [11-23 18:20:32] (/home/user/VAR/train.py , line 276)=> [ep58] (training ) Lm: 6.577 (6.584), Lt: 5.824 (5.837), Acc m&t: 3.18 4.99, Remain: 5 days, 6:40:07, Finish: 2024-11-28 09:00 [11-23 18:20:32] (/home/user/VAR/train.py , line 276)=> [ep58] (training ) Lm: 6.577 (6.584), Lt: 5.824 (5.837), Acc m&t: 3.18 4.99, Remain: 5 days, 6:43:43, Finish: 2024-11-28 09:04 [11-23 18:20:32] (/home/user/VAR/train.py , line 276)=> [ep58] (training ) Lm: 6.577 (6.584), Lt: 5.824 (5.837), Acc m&t: 3.18 4.99, Remain: 5 days, 6:45:56, Finish: 2024-11-28 09:06 [11-23 18:20:32] (/home/user/VAR/train.py , line 276)=> [ep58] (training ) Lm: 6.577 (6.584), Lt: 5.824 (5.837), Acc m&t: 3.18 4.99, Remain: 5 days, 6:41:44, Finish: 2024-11-28 09:02 [11-23 18:20:32] (/home/user/VAR/train.py , line 276)=> [ep58] (training ) Lm: 6.577 (6.584), Lt: 5.824 (5.837), Acc m&t: 3.18 4.99, Remain: 5 days, 6:44:12, Finish: 2024-11-28 09:04 [11-23 18:20:32] (/home/user/VAR/train.py , line 276)=> [ep58] (training ) Lm: 6.577 (6.584), Lt: 5.824 (5.837), Acc m&t: 3.18 4.99, Remain: 5 days, 6:41:29, Finish: 2024-11-28 09:02 [11-23 18:20:32] (/home/user/VAR/train.py , line 276)=> [ep58] (training ) Lm: 6.577 (6.584), Lt: 5.824 (5.837), Acc m&t: 3.18 4.99, Remain: 5 days, 6:39:16, Finish: 2024-11-28 08:59 [11-23 18:20:32] (/home/user/VAR/train.py , line 276)=> [ep58] (training ) Lm: 6.577 (6.584), Lt: 5.824 (5.837), Acc m&t: 3.18 4.99, Remain: 5 days, 6:44:45, Finish: 2024-11-28 09:05 [11-23 18:20:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 0/1669] eta: 0:25:16 tlr: 0.00021 tnm: 0.19 Lm: 6.644 (6.644) Lt: 5.921 (5.921) Accm: 2.71 (2.71) Acct: 4.20 (4.20) proj_loss: -0.5925 (-0.5925) time: 0.9088 data: 0.0003 [11-23 18:20:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 0/1669] eta: 0:25:24 tlr: 0.00021 tnm: 0.19 Lm: 6.525 (6.525) Lt: 5.666 (5.666) Accm: 3.67 (3.67) Acct: 5.85 (5.85) proj_loss: -0.5652 (-0.5652) time: 0.9133 data: 0.0004 [11-23 18:20:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 0/1669] eta: 0:25:11 tlr: 0.00021 tnm: 0.19 Lm: 6.773 (6.773) Lt: 6.091 (6.091) Accm: 2.52 (2.52) Acct: 3.72 (3.72) proj_loss: -0.5894 (-0.5894) time: 0.9056 data: 0.0003 [11-23 18:20:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 0/1669] eta: 0:25:23 tlr: 0.00021 tnm: 0.19 Lm: 6.744 (6.744) Lt: 6.017 (6.017) Accm: 3.00 (3.00) Acct: 4.92 (4.92) proj_loss: -0.5852 (-0.5852) time: 0.9131 data: 0.0003 [11-23 18:20:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 0/1669] eta: 0:25:24 tlr: 0.00021 tnm: 0.19 Lm: 6.638 (6.638) Lt: 5.923 (5.923) Accm: 2.80 (2.80) Acct: 4.34 (4.34) proj_loss: -0.5368 (-0.5368) time: 0.9136 data: 0.0003 [11-23 18:20:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 0/1669] eta: 0:25:25 tlr: 0.00021 tnm: 0.19 Lm: 6.524 (6.524) Lt: 5.761 (5.761) Accm: 3.09 (3.09) Acct: 5.10 (5.10) proj_loss: -0.5851 (-0.5851) time: 0.9138 data: 0.0004 [11-23 18:20:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 0/1669] eta: 0:25:24 tlr: 0.00021 tnm: 0.19 Lm: 6.538 (6.538) Lt: 5.746 (5.746) Accm: 3.21 (3.21) Acct: 5.06 (5.06) proj_loss: -0.6008 (-0.6008) time: 0.9136 data: 0.0004 [11-23 18:20:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 0/1669] eta: 0:25:25 tlr: 0.00021 tnm: 0.19 Lm: 6.405 (6.405) Lt: 5.661 (5.661) Accm: 3.53 (3.53) Acct: 5.34 (5.34) proj_loss: -0.5888 (-0.5888) time: 0.9140 data: 0.0004 [11-23 18:27:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 417/1669] eta: 0:20:12 tlr: 0.00021 tnm: 0.22 Lm: 6.308 (6.308) Lt: 5.549 (5.549) Accm: 3.82 (3.82) Acct: 5.82 (5.82) proj_loss: -0.5888 (-0.5888) time: 1.0603 data: 0.0003 [11-23 18:27:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 417/1669] eta: 0:20:12 tlr: 0.00021 tnm: 0.22 Lm: 6.520 (6.520) Lt: 5.763 (5.763) Accm: 3.44 (3.44) Acct: 5.29 (5.29) proj_loss: -0.5762 (-0.5762) time: 1.0602 data: 0.0003 [11-23 18:27:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 417/1669] eta: 0:20:12 tlr: 0.00021 tnm: 0.22 Lm: 6.593 (6.593) Lt: 5.891 (5.891) Accm: 2.94 (2.94) Acct: 4.53 (4.53) proj_loss: -0.5957 (-0.5957) time: 1.0602 data: 0.0003 [11-23 18:27:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 417/1669] eta: 0:20:12 tlr: 0.00021 tnm: 0.22 Lm: 6.519 (6.519) Lt: 5.816 (5.816) Accm: 3.34 (3.34) Acct: 5.11 (5.11) proj_loss: -0.5715 (-0.5715) time: 1.0602 data: 0.0003 [11-23 18:27:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 417/1669] eta: 0:20:12 tlr: 0.00021 tnm: 0.22 Lm: 6.567 (6.567) Lt: 5.802 (5.802) Accm: 3.07 (3.07) Acct: 5.08 (5.08) proj_loss: -0.5790 (-0.5790) time: 1.0602 data: 0.0003 [11-23 18:27:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 417/1669] eta: 0:20:12 tlr: 0.00021 tnm: 0.22 Lm: 6.698 (6.698) Lt: 6.005 (6.005) Accm: 2.66 (2.66) Acct: 4.08 (4.08) proj_loss: -0.6070 (-0.6070) time: 1.0603 data: 0.0003 [11-23 18:27:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 417/1669] eta: 0:20:12 tlr: 0.00021 tnm: 0.22 Lm: 6.574 (6.574) Lt: 5.815 (5.815) Accm: 3.17 (3.17) Acct: 5.11 (5.11) proj_loss: -0.6037 (-0.6037) time: 1.0603 data: 0.0003 [11-23 18:27:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 417/1669] eta: 0:20:12 tlr: 0.00021 tnm: 0.22 Lm: 6.668 (6.668) Lt: 5.919 (5.919) Accm: 3.07 (3.07) Acct: 4.94 (4.94) proj_loss: -0.5911 (-0.5911) time: 1.0603 data: 0.0003 [11-23 18:34:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 834/1669] eta: 0:13:28 tlr: 0.00021 tnm: 0.20 Lm: 6.604 (6.647) Lt: 5.886 (5.908) Accm: 3.00 (2.99) Acct: 4.92 (4.68) proj_loss: -0.5852 (-0.5847) time: 0.9333 data: 0.0003 [11-23 18:34:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 834/1669] eta: 0:13:28 tlr: 0.00021 tnm: 0.20 Lm: 6.524 (6.521) Lt: 5.756 (5.761) Accm: 3.25 (3.38) Acct: 5.13 (5.23) proj_loss: -0.5872 (-0.5800) time: 0.9333 data: 0.0003 [11-23 18:34:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 834/1669] eta: 0:13:28 tlr: 0.00021 tnm: 0.20 Lm: 6.405 (6.428) Lt: 5.661 (5.682) Accm: 3.53 (3.55) Acct: 5.34 (5.49) proj_loss: -0.5889 (-0.5899) time: 0.9333 data: 0.0003 [11-23 18:34:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 834/1669] eta: 0:13:28 tlr: 0.00021 tnm: 0.20 Lm: 6.644 (6.624) Lt: 5.921 (5.910) Accm: 2.80 (2.89) Acct: 4.20 (4.42) proj_loss: -0.5925 (-0.5912) time: 0.9333 data: 0.0003 [11-23 18:34:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 834/1669] eta: 0:13:28 tlr: 0.00021 tnm: 0.20 Lm: 6.624 (6.664) Lt: 5.964 (5.991) Accm: 2.80 (2.96) Acct: 4.44 (4.56) proj_loss: -0.6194 (-0.6112) time: 0.9333 data: 0.0003 [11-23 18:34:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 834/1669] eta: 0:13:28 tlr: 0.00021 tnm: 0.20 Lm: 6.524 (6.536) Lt: 5.761 (5.768) Accm: 3.09 (3.32) Acct: 5.10 (5.28) proj_loss: -0.5851 (-0.5854) time: 0.9333 data: 0.0003 [11-23 18:34:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 834/1669] eta: 0:13:28 tlr: 0.00021 tnm: 0.20 Lm: 6.595 (6.581) Lt: 5.746 (5.791) Accm: 3.21 (3.22) Acct: 5.17 (5.33) proj_loss: -0.6008 (-0.5862) time: 0.9333 data: 0.0003 [11-23 18:34:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [ 834/1669] eta: 0:13:28 tlr: 0.00021 tnm: 0.20 Lm: 6.401 (6.428) Lt: 5.708 (5.700) Accm: 3.89 (3.76) Acct: 5.89 (5.91) proj_loss: -0.5769 (-0.5733) time: 0.9333 data: 0.0003 [11-23 18:40:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [1251/1669] eta: 0:06:39 tlr: 0.00021 tnm: 0.20 Lm: 6.419 (6.430) Lt: 5.700 (5.698) Accm: 3.76 (3.73) Acct: 5.97 (5.95) proj_loss: -0.5895 (-0.5805) time: 0.9296 data: 0.0003 [11-23 18:40:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [1251/1669] eta: 0:06:39 tlr: 0.00021 tnm: 0.20 Lm: 6.533 (6.537) Lt: 5.766 (5.769) Accm: 3.10 (3.26) Acct: 5.08 (5.15) proj_loss: -0.5790 (-0.5788) time: 0.9295 data: 0.0003 [11-23 18:40:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [1251/1669] eta: 0:06:39 tlr: 0.00021 tnm: 0.20 Lm: 6.593 (6.600) Lt: 5.891 (5.890) Accm: 2.98 (3.09) Acct: 4.53 (4.72) proj_loss: -0.5874 (-0.5842) time: 0.9296 data: 0.0003 [11-23 18:40:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [1251/1669] eta: 0:06:39 tlr: 0.00021 tnm: 0.20 Lm: 6.524 (6.552) Lt: 5.808 (5.803) Accm: 3.23 (3.26) Acct: 4.92 (5.06) proj_loss: -0.5762 (-0.5751) time: 0.9296 data: 0.0003 [11-23 18:40:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [1251/1669] eta: 0:06:39 tlr: 0.00021 tnm: 0.20 Lm: 6.522 (6.481) Lt: 5.796 (5.744) Accm: 3.36 (3.46) Acct: 5.13 (5.35) proj_loss: -0.5902 (-0.5903) time: 0.9295 data: 0.0003 [11-23 18:40:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [1251/1669] eta: 0:06:39 tlr: 0.00021 tnm: 0.20 Lm: 6.632 (6.650) Lt: 5.871 (5.895) Accm: 2.91 (2.92) Acct: 4.58 (4.57) proj_loss: -0.5786 (-0.5805) time: 0.9295 data: 0.0003 [11-23 18:40:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [1251/1669] eta: 0:06:39 tlr: 0.00021 tnm: 0.20 Lm: 6.588 (6.581) Lt: 5.778 (5.796) Accm: 3.17 (3.13) Acct: 5.11 (5.11) proj_loss: -0.5876 (-0.5832) time: 0.9295 data: 0.0003 [11-23 18:40:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [1251/1669] eta: 0:06:39 tlr: 0.00021 tnm: 0.20 Lm: 6.640 (6.662) Lt: 5.965 (5.985) Accm: 2.83 (2.94) Acct: 4.44 (4.53) proj_loss: -0.6044 (-0.6018) time: 0.9296 data: 0.0003 [11-23 18:46:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.624 (6.625) Lt: 5.964 (5.912) Accm: 2.87 (3.06) Acct: 4.44 (4.79) proj_loss: -0.6026 (-0.6019) time: 0.9321 data: 0.0020 [11-23 18:46:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 59/350] Total time: 0:26:25 (0.950 s / it) [11-23 18:46:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.542 (6.563) Lt: 5.771 (5.789) Accm: 3.10 (3.23) Acct: 5.06 (5.12) proj_loss: -0.5729 (-0.5763) time: 0.9321 data: 0.0016 [11-23 18:46:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.640 (6.514) Lt: 5.931 (5.783) Accm: 3.19 (3.34) Acct: 4.92 (5.09) proj_loss: -0.5889 (-0.5899) time: 0.9321 data: 0.0021 [11-23 18:46:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.581 (6.579) Lt: 5.760 (5.789) Accm: 3.21 (3.19) Acct: 5.17 (5.21) proj_loss: -0.5888 (-0.5844) time: 0.9321 data: 0.0020 [11-23 18:46:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.604 (6.628) Lt: 5.856 (5.867) Accm: 3.00 (2.99) Acct: 4.92 (4.75) proj_loss: -0.5719 (-0.5757) time: 0.9321 data: 0.0020 [11-23 18:46:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.614 (6.603) Lt: 5.861 (5.883) Accm: 3.16 (3.15) Acct: 4.86 (4.86) proj_loss: -0.5925 (-0.5860) time: 0.9321 data: 0.0018 [11-23 18:46:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.525 (6.561) Lt: 5.860 (5.815) Accm: 3.21 (3.18) Acct: 4.96 (5.04) proj_loss: -0.5652 (-0.5713) time: 0.9321 data: 0.0015 [11-23 18:46:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 59/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.437 (6.484) Lt: 5.708 (5.760) Accm: 3.63 (3.56) Acct: 5.89 (5.67) proj_loss: -0.5769 (-0.5788) time: 0.9321 data: 0.0018 [11-23 18:46:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 59/350] Total time: 0:26:25 (0.950 s / it) [11-23 18:46:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 59/350] Total time: 0:26:25 (0.950 s / it) [11-23 18:46:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 59/350] Total time: 0:26:25 (0.950 s / it) [11-23 18:46:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 59/350] Total time: 0:26:25 (0.950 s / it) [11-23 18:46:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 59/350] Total time: 0:26:25 (0.950 s / it) [11-23 18:46:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 59/350] Total time: 0:26:25 (0.950 s / it) [11-23 18:46:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 59/350] Total time: 0:26:25 (0.950 s / it) [11-23 18:49:10] (home/user/VAR/trainer.py, line 114)=> FID: 4.242291151054928 [11-23 18:49:11] (/home/user/VAR/train.py , line 259)=> [*] [ep59] (val 50000) Lm: 6.5814, Lt: 5.8311, Acc m&t: 3.20 5.05, Val cost: 132.60s [11-23 18:49:11] (/home/user/VAR/train.py , line 264)=> [saving ckpt] ... [saving ckpt](*) finished! @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth [11-23 18:49:48] (/home/user/VAR/train.py , line 276)=> [ep59] (training ) Lm: 6.577 (6.581), Lt: 5.824 (5.831), Acc m&t: 3.20 5.05, Remain: 5 days, 6:04:46, Finish: 2024-11-28 08:51 [11-23 18:49:48] (/home/user/VAR/train.py , line 276)=> [ep59] (training ) Lm: 6.577 (6.581), Lt: 5.824 (5.831), Acc m&t: 3.20 5.05, Remain: 5 days, 6:06:28, Finish: 2024-11-28 08:53 [11-23 18:49:48] (/home/user/VAR/train.py , line 276)=> [ep59] (training ) Lm: 6.577 (6.581), Lt: 5.824 (5.831), Acc m&t: 3.20 5.05, Remain: 5 days, 6:04:43, Finish: 2024-11-28 08:51 [11-23 18:49:48] (/home/user/VAR/train.py , line 276)=> [ep59] (training ) Lm: 6.577 (6.581), Lt: 5.824 (5.831), Acc m&t: 3.20 5.05, Remain: 5 days, 6:04:37, Finish: 2024-11-28 08:51 [11-23 18:49:48] (/home/user/VAR/train.py , line 276)=> [ep59] (training ) Lm: 6.577 (6.581), Lt: 5.824 (5.831), Acc m&t: 3.20 5.05, Remain: 5 days, 6:05:37, Finish: 2024-11-28 08:52 [11-23 18:49:48] (/home/user/VAR/train.py , line 276)=> [ep59] (training ) Lm: 6.577 (6.581), Lt: 5.824 (5.831), Acc m&t: 3.20 5.05, Remain: 5 days, 6:05:16, Finish: 2024-11-28 08:52 [11-23 18:49:48] (/home/user/VAR/train.py , line 276)=> [ep59] (training ) Lm: 6.577 (6.581), Lt: 5.824 (5.831), Acc m&t: 3.20 5.05, Remain: 5 days, 6:05:20, Finish: 2024-11-28 08:52 [11-23 18:49:48] (/home/user/VAR/train.py , line 276)=> [ep59] (training ) Lm: 6.577 (6.581), Lt: 5.824 (5.831), Acc m&t: 3.20 5.05, Remain: 5 days, 6:04:09, Finish: 2024-11-28 08:51 [11-23 18:49:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 0/1669] eta: 0:24:52 tlr: 0.00021 tnm: 0.21 Lm: 6.605 (6.605) Lt: 5.838 (5.838) Accm: 2.99 (2.99) Acct: 4.58 (4.58) proj_loss: -0.5712 (-0.5712) time: 0.8945 data: 0.0004 [11-23 18:49:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 0/1669] eta: 0:24:49 tlr: 0.00021 tnm: 0.21 Lm: 6.821 (6.821) Lt: 6.008 (6.008) Accm: 2.71 (2.71) Acct: 4.34 (4.34) proj_loss: -0.5710 (-0.5710) time: 0.8926 data: 0.0004 [11-23 18:49:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 0/1669] eta: 0:24:51 tlr: 0.00021 tnm: 0.21 Lm: 6.784 (6.784) Lt: 6.037 (6.037) Accm: 2.78 (2.78) Acct: 4.44 (4.44) proj_loss: -0.5796 (-0.5796) time: 0.8935 data: 0.0003 [11-23 18:49:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 0/1669] eta: 0:25:12 tlr: 0.00021 tnm: 0.21 Lm: 6.431 (6.431) Lt: 5.696 (5.696) Accm: 3.31 (3.31) Acct: 5.20 (5.20) proj_loss: -0.6020 (-0.6020) time: 0.9062 data: 0.0004 [11-23 18:49:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 0/1669] eta: 0:24:50 tlr: 0.00021 tnm: 0.21 Lm: 6.628 (6.628) Lt: 5.872 (5.872) Accm: 3.16 (3.16) Acct: 4.96 (4.96) proj_loss: -0.5825 (-0.5825) time: 0.8932 data: 0.0004 [11-23 18:49:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 0/1669] eta: 0:25:12 tlr: 0.00021 tnm: 0.21 Lm: 6.579 (6.579) Lt: 5.842 (5.842) Accm: 3.09 (3.09) Acct: 5.23 (5.23) proj_loss: -0.5815 (-0.5815) time: 0.9063 data: 0.0004 [11-23 18:49:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 0/1669] eta: 0:24:48 tlr: 0.00021 tnm: 0.21 Lm: 6.740 (6.740) Lt: 6.058 (6.058) Accm: 2.77 (2.77) Acct: 4.44 (4.44) proj_loss: -0.6049 (-0.6049) time: 0.8921 data: 0.0004 [11-23 18:49:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 0/1669] eta: 0:24:51 tlr: 0.00021 tnm: 0.21 Lm: 6.742 (6.742) Lt: 6.045 (6.045) Accm: 2.74 (2.74) Acct: 4.17 (4.17) proj_loss: -0.6111 (-0.6111) time: 0.8937 data: 0.0004 [11-23 18:56:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 417/1669] eta: 0:19:26 tlr: 0.00021 tnm: 0.22 Lm: 6.654 (6.654) Lt: 5.925 (5.925) Accm: 2.97 (2.97) Acct: 4.68 (4.68) proj_loss: -0.5988 (-0.5988) time: 0.9306 data: 0.0003 [11-23 18:56:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 417/1669] eta: 0:19:26 tlr: 0.00021 tnm: 0.22 Lm: 6.512 (6.512) Lt: 5.746 (5.746) Accm: 3.43 (3.43) Acct: 5.37 (5.37) proj_loss: -0.5679 (-0.5679) time: 0.9306 data: 0.0003 [11-23 18:56:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 417/1669] eta: 0:19:26 tlr: 0.00021 tnm: 0.22 Lm: 6.605 (6.605) Lt: 5.865 (5.865) Accm: 3.05 (3.05) Acct: 5.10 (5.10) proj_loss: -0.5801 (-0.5801) time: 0.9306 data: 0.0003 [11-23 18:56:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 417/1669] eta: 0:19:26 tlr: 0.00021 tnm: 0.22 Lm: 6.446 (6.446) Lt: 5.713 (5.713) Accm: 3.21 (3.21) Acct: 4.99 (4.99) proj_loss: -0.6130 (-0.6130) time: 0.9306 data: 0.0003 [11-23 18:56:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 417/1669] eta: 0:19:26 tlr: 0.00021 tnm: 0.22 Lm: 6.689 (6.689) Lt: 5.860 (5.860) Accm: 2.96 (2.96) Acct: 4.89 (4.89) proj_loss: -0.5595 (-0.5595) time: 0.9306 data: 0.0003 [11-23 18:56:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 417/1669] eta: 0:19:26 tlr: 0.00021 tnm: 0.22 Lm: 6.616 (6.616) Lt: 5.892 (5.892) Accm: 3.08 (3.08) Acct: 4.56 (4.56) proj_loss: -0.5750 (-0.5750) time: 0.9306 data: 0.0003 [11-23 18:56:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 417/1669] eta: 0:19:26 tlr: 0.00021 tnm: 0.22 Lm: 6.647 (6.647) Lt: 5.895 (5.895) Accm: 2.88 (2.88) Acct: 4.65 (4.65) proj_loss: -0.5764 (-0.5764) time: 0.9306 data: 0.0003 [11-23 18:56:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 417/1669] eta: 0:19:26 tlr: 0.00021 tnm: 0.22 Lm: 6.687 (6.687) Lt: 5.947 (5.947) Accm: 2.94 (2.94) Acct: 4.46 (4.46) proj_loss: -0.5824 (-0.5824) time: 0.9306 data: 0.0003 [11-23 19:02:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 834/1669] eta: 0:13:00 tlr: 0.00021 tnm: 0.21 Lm: 6.621 (6.665) Lt: 5.839 (5.911) Accm: 2.90 (2.92) Acct: 4.34 (4.38) proj_loss: -0.5712 (-0.5705) time: 0.9312 data: 0.0003 [11-23 19:02:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 834/1669] eta: 0:13:00 tlr: 0.00021 tnm: 0.21 Lm: 6.623 (6.619) Lt: 5.872 (5.857) Accm: 3.00 (2.95) Acct: 4.34 (4.49) proj_loss: -0.5675 (-0.5691) time: 0.9312 data: 0.0003 [11-23 19:02:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 834/1669] eta: 0:13:00 tlr: 0.00021 tnm: 0.21 Lm: 6.632 (6.644) Lt: 5.888 (5.917) Accm: 3.02 (2.92) Acct: 4.96 (4.79) proj_loss: -0.5815 (-0.5807) time: 0.9312 data: 0.0003 [11-23 19:02:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 834/1669] eta: 0:13:00 tlr: 0.00021 tnm: 0.21 Lm: 6.694 (6.690) Lt: 5.902 (5.874) Accm: 3.09 (3.00) Acct: 4.72 (4.83) proj_loss: -0.5496 (-0.5562) time: 0.9312 data: 0.0003 [11-23 19:02:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 834/1669] eta: 0:13:00 tlr: 0.00021 tnm: 0.21 Lm: 6.680 (6.663) Lt: 5.855 (5.902) Accm: 2.91 (2.95) Acct: 4.89 (4.75) proj_loss: -0.5865 (-0.5837) time: 0.9312 data: 0.0003 [11-23 19:02:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 834/1669] eta: 0:13:00 tlr: 0.00021 tnm: 0.21 Lm: 6.460 (6.512) Lt: 5.730 (5.766) Accm: 3.18 (3.20) Acct: 5.20 (5.06) proj_loss: -0.6020 (-0.5970) time: 0.9312 data: 0.0003 [11-23 19:02:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 834/1669] eta: 0:13:00 tlr: 0.00021 tnm: 0.21 Lm: 6.585 (6.536) Lt: 5.901 (5.797) Accm: 2.87 (3.24) Acct: 4.44 (4.99) proj_loss: -0.5796 (-0.5746) time: 0.9312 data: 0.0003 [11-23 19:02:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [ 834/1669] eta: 0:13:00 tlr: 0.00021 tnm: 0.21 Lm: 6.554 (6.592) Lt: 5.741 (5.844) Accm: 3.00 (3.01) Acct: 4.86 (4.89) proj_loss: -0.5749 (-0.5759) time: 0.9312 data: 0.0003 [11-23 19:10:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.21 Lm: 6.518 (6.562) Lt: 5.781 (5.838) Accm: 3.13 (3.22) Acct: 5.11 (5.17) proj_loss: -0.5843 (-0.5804) time: 1.0025 data: 0.0003 [11-23 19:10:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.21 Lm: 6.552 (6.532) Lt: 5.838 (5.792) Accm: 2.94 (3.19) Acct: 4.49 (4.88) proj_loss: -0.5679 (-0.5691) time: 1.0025 data: 0.0003 [11-23 19:10:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.21 Lm: 6.511 (6.525) Lt: 5.748 (5.766) Accm: 3.23 (3.22) Acct: 5.20 (5.18) proj_loss: -0.5835 (-0.5889) time: 1.0025 data: 0.0003 [11-23 19:10:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.21 Lm: 6.675 (6.682) Lt: 5.925 (5.892) Accm: 3.15 (3.05) Acct: 4.82 (4.86) proj_loss: -0.5603 (-0.5630) time: 1.0025 data: 0.0003 [11-23 19:10:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.21 Lm: 6.614 (6.559) Lt: 5.829 (5.794) Accm: 3.08 (3.19) Acct: 4.65 (4.92) proj_loss: -0.5750 (-0.5739) time: 1.0025 data: 0.0003 [11-23 19:10:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.21 Lm: 6.647 (6.650) Lt: 5.886 (5.906) Accm: 2.88 (2.92) Acct: 4.53 (4.55) proj_loss: -0.5986 (-0.5905) time: 1.0025 data: 0.0003 [11-23 19:10:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.21 Lm: 6.605 (6.615) Lt: 5.865 (5.890) Accm: 3.05 (3.00) Acct: 4.82 (4.76) proj_loss: -0.5817 (-0.5814) time: 1.0025 data: 0.0003 [11-23 19:10:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.21 Lm: 6.665 (6.676) Lt: 5.899 (5.923) Accm: 2.88 (2.89) Acct: 4.30 (4.36) proj_loss: -0.5800 (-0.5750) time: 1.0025 data: 0.0003 [11-23 19:16:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.23 Lm: 6.621 (6.661) Lt: 5.839 (5.901) Accm: 2.90 (2.91) Acct: 4.34 (4.43) proj_loss: -0.5888 (-0.5779) time: 0.9320 data: 0.0020 [11-23 19:16:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 60/350] Total time: 0:26:43 (0.961 s / it) [11-23 19:16:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.23 Lm: 6.554 (6.570) Lt: 5.820 (5.835) Accm: 3.25 (3.30) Acct: 5.37 (5.38) proj_loss: -0.5749 (-0.5767) time: 0.9320 data: 0.0016 [11-23 19:16:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.23 Lm: 6.623 (6.615) Lt: 5.872 (5.859) Accm: 3.00 (3.04) Acct: 4.34 (4.70) proj_loss: -0.5675 (-0.5720) time: 0.9320 data: 0.0017 [11-23 19:16:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.23 Lm: 6.549 (6.530) Lt: 5.767 (5.777) Accm: 3.29 (3.26) Acct: 5.20 (5.24) proj_loss: -0.6019 (-0.5915) time: 0.9320 data: 0.0020 [11-23 19:16:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.23 Lm: 6.680 (6.658) Lt: 5.917 (5.921) Accm: 2.91 (2.97) Acct: 4.89 (4.63) proj_loss: -0.5865 (-0.5858) time: 0.9320 data: 0.0016 [11-23 19:16:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.23 Lm: 6.679 (6.681) Lt: 5.937 (5.901) Accm: 3.09 (2.92) Acct: 4.72 (4.63) proj_loss: -0.5710 (-0.5659) time: 0.9320 data: 0.0018 [11-23 19:16:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.23 Lm: 6.585 (6.548) Lt: 5.852 (5.804) Accm: 3.02 (3.17) Acct: 4.55 (4.90) proj_loss: -0.5760 (-0.5705) time: 0.9320 data: 0.0021 [11-23 19:16:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 60/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.23 Lm: 6.632 (6.637) Lt: 5.888 (5.907) Accm: 3.02 (2.92) Acct: 4.68 (4.60) proj_loss: -0.5819 (-0.5878) time: 0.9320 data: 0.0014 [11-23 19:16:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 60/350] Total time: 0:26:43 (0.961 s / it) [11-23 19:16:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 60/350] Total time: 0:26:43 (0.961 s / it) [11-23 19:16:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 60/350] Total time: 0:26:43 (0.961 s / it) [11-23 19:16:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 60/350] Total time: 0:26:43 (0.961 s / it) [11-23 19:16:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 60/350] Total time: 0:26:43 (0.961 s / it) [11-23 19:16:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 60/350] Total time: 0:26:43 (0.961 s / it) [11-23 19:16:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 60/350] Total time: 0:26:43 (0.961 s / it) [11-23 19:16:32] (/home/user/VAR/train.py , line 276)=> [ep60] (training ) Lm: 6.577 (6.588), Lt: 5.824 (5.836), Acc m&t: 3.20 5.05, Remain: 5 days, 5:48:31, Finish: 2024-11-28 09:05 [11-23 19:16:32] (/home/user/VAR/train.py , line 276)=> [ep60] (training ) Lm: 6.577 (6.588), Lt: 5.824 (5.836), Acc m&t: 3.20 5.05, Remain: 5 days, 5:48:11, Finish: 2024-11-28 09:04 [11-23 19:16:32] (/home/user/VAR/train.py , line 276)=> [ep60] (training ) Lm: 6.577 (6.588), Lt: 5.824 (5.836), Acc m&t: 3.20 5.05, Remain: 5 days, 5:49:15, Finish: 2024-11-28 09:05 [11-23 19:16:32] (/home/user/VAR/train.py , line 276)=> [ep60] (training ) Lm: 6.577 (6.588), Lt: 5.824 (5.836), Acc m&t: 3.20 5.05, Remain: 5 days, 5:49:53, Finish: 2024-11-28 09:06 [11-23 19:16:32] (/home/user/VAR/train.py , line 276)=> [ep60] (training ) Lm: 6.577 (6.588), Lt: 5.824 (5.836), Acc m&t: 3.20 5.05, Remain: 5 days, 5:49:01, Finish: 2024-11-28 09:05 [11-23 19:16:32] (/home/user/VAR/train.py , line 276)=> [ep60] (training ) Lm: 6.577 (6.588), Lt: 5.824 (5.836), Acc m&t: 3.20 5.05, Remain: 5 days, 5:47:46, Finish: 2024-11-28 09:04 [11-23 19:16:32] (/home/user/VAR/train.py , line 276)=> [ep60] (training ) Lm: 6.577 (6.588), Lt: 5.824 (5.836), Acc m&t: 3.20 5.05, Remain: 5 days, 5:47:20, Finish: 2024-11-28 09:03 [11-23 19:16:32] (/home/user/VAR/train.py , line 276)=> [ep60] (training ) Lm: 6.577 (6.588), Lt: 5.824 (5.836), Acc m&t: 3.20 5.05, Remain: 5 days, 5:47:56, Finish: 2024-11-28 09:04 [11-23 19:16:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 0/1669] eta: 0:24:44 tlr: 0.00021 tnm: 0.21 Lm: 6.516 (6.516) Lt: 5.746 (5.746) Accm: 3.26 (3.26) Acct: 5.23 (5.23) proj_loss: -0.5780 (-0.5780) time: 0.8893 data: 0.0004 [11-23 19:16:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 0/1669] eta: 0:24:44 tlr: 0.00021 tnm: 0.21 Lm: 6.535 (6.535) Lt: 5.789 (5.789) Accm: 3.28 (3.28) Acct: 5.75 (5.75) proj_loss: -0.6104 (-0.6104) time: 0.8896 data: 0.0003 [11-23 19:16:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 0/1669] eta: 0:24:46 tlr: 0.00021 tnm: 0.21 Lm: 6.356 (6.356) Lt: 5.580 (5.580) Accm: 3.77 (3.77) Acct: 6.44 (6.44) proj_loss: -0.6092 (-0.6092) time: 0.8908 data: 0.0004 [11-23 19:16:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 0/1669] eta: 0:24:45 tlr: 0.00021 tnm: 0.21 Lm: 6.459 (6.459) Lt: 5.631 (5.631) Accm: 3.34 (3.34) Acct: 4.92 (4.92) proj_loss: -0.5722 (-0.5722) time: 0.8902 data: 0.0004 [11-23 19:16:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 0/1669] eta: 0:25:00 tlr: 0.00021 tnm: 0.21 Lm: 6.590 (6.590) Lt: 5.888 (5.888) Accm: 3.21 (3.21) Acct: 4.65 (4.65) proj_loss: -0.5941 (-0.5941) time: 0.8989 data: 0.0003 [11-23 19:16:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 0/1669] eta: 0:24:51 tlr: 0.00021 tnm: 0.21 Lm: 6.494 (6.494) Lt: 5.740 (5.740) Accm: 3.72 (3.72) Acct: 5.99 (5.99) proj_loss: -0.5904 (-0.5904) time: 0.8934 data: 0.0004 [11-23 19:16:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 0/1669] eta: 0:24:47 tlr: 0.00021 tnm: 0.21 Lm: 6.516 (6.516) Lt: 5.740 (5.740) Accm: 3.31 (3.31) Acct: 5.20 (5.20) proj_loss: -0.6019 (-0.6019) time: 0.8915 data: 0.0003 [11-23 19:16:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 0/1669] eta: 0:24:47 tlr: 0.00021 tnm: 0.21 Lm: 6.719 (6.719) Lt: 6.125 (6.125) Accm: 2.83 (2.83) Acct: 4.44 (4.44) proj_loss: -0.5884 (-0.5884) time: 0.8914 data: 0.0004 [11-23 19:23:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.20 Lm: 6.522 (6.522) Lt: 5.836 (5.836) Accm: 3.54 (3.54) Acct: 5.49 (5.49) proj_loss: -0.5880 (-0.5880) time: 0.9310 data: 0.0003 [11-23 19:23:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.20 Lm: 6.370 (6.370) Lt: 5.593 (5.593) Accm: 3.88 (3.88) Acct: 6.18 (6.18) proj_loss: -0.5987 (-0.5987) time: 0.9310 data: 0.0003 [11-23 19:23:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.20 Lm: 6.564 (6.564) Lt: 5.781 (5.781) Accm: 3.47 (3.47) Acct: 5.66 (5.66) proj_loss: -0.5830 (-0.5830) time: 0.9310 data: 0.0003 [11-23 19:23:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.20 Lm: 6.543 (6.543) Lt: 5.750 (5.750) Accm: 3.07 (3.07) Acct: 4.77 (4.77) proj_loss: -0.5800 (-0.5800) time: 0.9309 data: 0.0003 [11-23 19:23:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.20 Lm: 6.594 (6.594) Lt: 5.829 (5.829) Accm: 3.03 (3.03) Acct: 4.79 (4.79) proj_loss: -0.5922 (-0.5922) time: 0.9310 data: 0.0003 [11-23 19:23:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.20 Lm: 6.602 (6.602) Lt: 5.837 (5.837) Accm: 3.07 (3.07) Acct: 5.25 (5.25) proj_loss: -0.6143 (-0.6143) time: 0.9309 data: 0.0003 [11-23 19:23:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.20 Lm: 6.495 (6.495) Lt: 5.731 (5.731) Accm: 3.15 (3.15) Acct: 4.91 (4.91) proj_loss: -0.5959 (-0.5959) time: 0.9310 data: 0.0003 [11-23 19:23:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.20 Lm: 6.535 (6.535) Lt: 5.819 (5.819) Accm: 3.29 (3.29) Acct: 4.96 (4.96) proj_loss: -0.5966 (-0.5966) time: 0.9310 data: 0.0003 [11-23 19:29:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.590 (6.614) Lt: 5.888 (5.896) Accm: 3.21 (2.94) Acct: 4.65 (4.47) proj_loss: -0.5941 (-0.5918) time: 0.9327 data: 0.0003 [11-23 19:29:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.634 (6.617) Lt: 5.822 (5.846) Accm: 3.22 (3.14) Acct: 5.34 (5.15) proj_loss: -0.5756 (-0.5721) time: 0.9327 data: 0.0003 [11-23 19:29:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.518 (6.521) Lt: 5.773 (5.815) Accm: 3.10 (3.39) Acct: 4.99 (5.33) proj_loss: -0.5875 (-0.5820) time: 0.9327 data: 0.0003 [11-23 19:29:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.474 (6.477) Lt: 5.722 (5.692) Accm: 3.31 (3.38) Acct: 5.20 (5.25) proj_loss: -0.5900 (-0.5831) time: 0.9327 data: 0.0003 [11-23 19:29:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.534 (6.574) Lt: 5.826 (5.828) Accm: 2.81 (2.96) Acct: 4.34 (4.64) proj_loss: -0.5927 (-0.5924) time: 0.9327 data: 0.0003 [11-23 19:29:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.597 (6.561) Lt: 5.861 (5.787) Accm: 3.25 (3.13) Acct: 4.92 (4.84) proj_loss: -0.5878 (-0.5843) time: 0.9327 data: 0.0003 [11-23 19:29:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.670 (6.631) Lt: 5.884 (5.883) Accm: 2.86 (2.97) Acct: 4.75 (4.92) proj_loss: -0.6104 (-0.5971) time: 0.9327 data: 0.0003 [11-23 19:29:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.383 (6.399) Lt: 5.606 (5.640) Accm: 3.77 (3.64) Acct: 5.92 (5.83) proj_loss: -0.5882 (-0.5931) time: 0.9327 data: 0.0003 [11-23 19:35:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.22 Lm: 6.420 (6.461) Lt: 5.670 (5.702) Accm: 3.47 (3.42) Acct: 5.53 (5.51) proj_loss: -0.5869 (-0.5912) time: 0.9304 data: 0.0003 [11-23 19:35:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.22 Lm: 6.588 (6.555) Lt: 5.870 (5.853) Accm: 3.14 (3.34) Acct: 4.80 (5.15) proj_loss: -0.5880 (-0.5856) time: 0.9304 data: 0.0003 [11-23 19:35:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.22 Lm: 6.602 (6.596) Lt: 5.837 (5.808) Accm: 3.00 (3.02) Acct: 4.68 (4.85) proj_loss: -0.5915 (-0.5909) time: 0.9304 data: 0.0003 [11-23 19:35:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.22 Lm: 6.576 (6.560) Lt: 5.821 (5.785) Accm: 3.29 (3.21) Acct: 4.96 (4.94) proj_loss: -0.5903 (-0.5865) time: 0.9304 data: 0.0003 [11-23 19:35:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.22 Lm: 6.495 (6.540) Lt: 5.731 (5.778) Accm: 3.15 (3.24) Acct: 4.91 (5.00) proj_loss: -0.5959 (-0.5899) time: 0.9304 data: 0.0003 [11-23 19:35:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.22 Lm: 6.549 (6.572) Lt: 5.816 (5.823) Accm: 2.80 (2.91) Acct: 4.42 (4.61) proj_loss: -0.5996 (-0.6012) time: 0.9304 data: 0.0003 [11-23 19:35:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.22 Lm: 6.603 (6.615) Lt: 5.861 (5.881) Accm: 3.03 (2.92) Acct: 4.61 (4.49) proj_loss: -0.5966 (-0.5946) time: 0.9305 data: 0.0003 [11-23 19:35:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.22 Lm: 6.641 (6.624) Lt: 5.900 (5.881) Accm: 2.96 (3.03) Acct: 4.73 (4.80) proj_loss: -0.5806 (-0.5755) time: 0.9305 data: 0.0003 [11-23 19:42:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.634 (6.620) Lt: 5.867 (5.878) Accm: 3.22 (3.08) Acct: 4.92 (4.83) proj_loss: -0.5856 (-0.5780) time: 0.9359 data: 0.0016 [11-23 19:42:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.516 (6.542) Lt: 5.740 (5.788) Accm: 3.09 (3.21) Acct: 4.61 (4.83) proj_loss: -0.5967 (-0.5913) time: 0.9359 data: 0.0016 [11-23 19:42:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.518 (6.519) Lt: 5.773 (5.785) Accm: 3.18 (3.41) Acct: 4.99 (5.30) proj_loss: -0.5875 (-0.5802) time: 0.9359 data: 0.0018 [11-23 19:42:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.590 (6.606) Lt: 5.834 (5.862) Accm: 2.88 (2.91) Acct: 4.65 (4.59) proj_loss: -0.5992 (-0.5968) time: 0.9359 data: 0.0020 [11-23 19:42:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.456 (6.485) Lt: 5.734 (5.740) Accm: 3.28 (3.39) Acct: 5.13 (5.39) proj_loss: -0.5882 (-0.5933) time: 0.9359 data: 0.0018 [11-23 19:42:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.535 (6.573) Lt: 5.789 (5.796) Accm: 3.15 (3.14) Acct: 4.75 (4.97) proj_loss: -0.5956 (-0.5919) time: 0.9359 data: 0.0017 [11-23 19:42:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.556 (6.533) Lt: 5.780 (5.740) Accm: 3.34 (3.32) Acct: 4.99 (5.15) proj_loss: -0.5925 (-0.5877) time: 0.9359 data: 0.0014 [11-23 19:42:42] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 61/350] Total time: 0:26:09 (0.941 s / it) [11-23 19:42:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 61/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.534 (6.562) Lt: 5.807 (5.807) Accm: 2.81 (2.97) Acct: 4.51 (4.69) proj_loss: -0.5927 (-0.5977) time: 0.9359 data: 0.0015 [11-23 19:42:42] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 61/350] Total time: 0:26:09 (0.941 s / it) [11-23 19:42:42] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 61/350] Total time: 0:26:09 (0.941 s / it) [11-23 19:42:42] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 61/350] Total time: 0:26:09 (0.941 s / it) [11-23 19:42:42] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 61/350] Total time: 0:26:09 (0.941 s / it) [11-23 19:42:42] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 61/350] Total time: 0:26:09 (0.941 s / it) [11-23 19:42:42] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 61/350] Total time: 0:26:09 (0.941 s / it) [11-23 19:42:42] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 61/350] Total time: 0:26:09 (0.941 s / it) [11-23 19:42:42] (/home/user/VAR/train.py , line 276)=> [ep61] (training ) Lm: 6.577 (6.577), Lt: 5.824 (5.827), Acc m&t: 3.20 5.05, Remain: 5 days, 6:01:08, Finish: 2024-11-28 09:43 [11-23 19:42:42] (/home/user/VAR/train.py , line 276)=> [ep61] (training ) Lm: 6.577 (6.577), Lt: 5.824 (5.827), Acc m&t: 3.20 5.05, Remain: 5 days, 5:57:43, Finish: 2024-11-28 09:40 [11-23 19:42:42] (/home/user/VAR/train.py , line 276)=> [ep61] (training ) Lm: 6.577 (6.577), Lt: 5.824 (5.827), Acc m&t: 3.20 5.05, Remain: 5 days, 5:59:30, Finish: 2024-11-28 09:42 [11-23 19:42:42] (/home/user/VAR/train.py , line 276)=> [ep61] (training ) Lm: 6.577 (6.577), Lt: 5.824 (5.827), Acc m&t: 3.20 5.05, Remain: 5 days, 6:00:52, Finish: 2024-11-28 09:43 [11-23 19:42:42] (/home/user/VAR/train.py , line 276)=> [ep61] (training ) Lm: 6.577 (6.577), Lt: 5.824 (5.827), Acc m&t: 3.20 5.05, Remain: 5 days, 5:58:52, Finish: 2024-11-28 09:41 [11-23 19:42:42] (/home/user/VAR/train.py , line 276)=> [ep61] (training ) Lm: 6.577 (6.577), Lt: 5.824 (5.827), Acc m&t: 3.20 5.05, Remain: 5 days, 6:01:32, Finish: 2024-11-28 09:44 [11-23 19:42:42] (/home/user/VAR/train.py , line 276)=> [ep61] (training ) Lm: 6.577 (6.577), Lt: 5.824 (5.827), Acc m&t: 3.20 5.05, Remain: 5 days, 6:00:55, Finish: 2024-11-28 09:43 [11-23 19:42:42] (/home/user/VAR/train.py , line 276)=> [ep61] (training ) Lm: 6.577 (6.577), Lt: 5.824 (5.827), Acc m&t: 3.20 5.05, Remain: 5 days, 5:58:43, Finish: 2024-11-28 09:41 [11-23 19:42:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 0/1669] eta: 0:25:01 tlr: 0.00021 tnm: 0.21 Lm: 6.504 (6.504) Lt: 5.722 (5.722) Accm: 3.10 (3.10) Acct: 5.20 (5.20) proj_loss: -0.6157 (-0.6157) time: 0.8996 data: 0.0004 [11-23 19:42:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 0/1669] eta: 0:25:02 tlr: 0.00021 tnm: 0.21 Lm: 6.703 (6.703) Lt: 5.948 (5.948) Accm: 3.04 (3.04) Acct: 4.99 (4.99) proj_loss: -0.5619 (-0.5619) time: 0.9000 data: 0.0004 [11-23 19:42:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 0/1669] eta: 0:25:03 tlr: 0.00021 tnm: 0.21 Lm: 6.670 (6.670) Lt: 5.918 (5.918) Accm: 2.72 (2.72) Acct: 4.79 (4.79) proj_loss: -0.5553 (-0.5553) time: 0.9009 data: 0.0004 [11-23 19:42:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 0/1669] eta: 0:25:03 tlr: 0.00021 tnm: 0.21 Lm: 6.517 (6.517) Lt: 5.881 (5.881) Accm: 3.28 (3.28) Acct: 5.13 (5.13) proj_loss: -0.6155 (-0.6155) time: 0.9007 data: 0.0004 [11-23 19:42:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 0/1669] eta: 0:25:03 tlr: 0.00021 tnm: 0.21 Lm: 6.464 (6.464) Lt: 5.770 (5.770) Accm: 3.34 (3.34) Acct: 4.96 (4.96) proj_loss: -0.5868 (-0.5868) time: 0.9010 data: 0.0004 [11-23 19:42:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 0/1669] eta: 0:25:04 tlr: 0.00021 tnm: 0.21 Lm: 6.504 (6.504) Lt: 5.801 (5.801) Accm: 3.73 (3.73) Acct: 5.23 (5.23) proj_loss: -0.5775 (-0.5775) time: 0.9013 data: 0.0003 [11-23 19:42:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 0/1669] eta: 0:25:04 tlr: 0.00021 tnm: 0.21 Lm: 6.362 (6.362) Lt: 5.580 (5.580) Accm: 3.54 (3.54) Acct: 5.79 (5.79) proj_loss: -0.6065 (-0.6065) time: 0.9012 data: 0.0004 [11-23 19:42:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 0/1669] eta: 0:25:01 tlr: 0.00021 tnm: 0.21 Lm: 6.621 (6.621) Lt: 5.927 (5.927) Accm: 2.77 (2.77) Acct: 3.75 (3.75) proj_loss: -0.5898 (-0.5898) time: 0.8996 data: 0.0004 [11-23 19:49:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 417/1669] eta: 0:19:50 tlr: 0.00021 tnm: 0.21 Lm: 6.571 (6.571) Lt: 5.847 (5.847) Accm: 3.03 (3.03) Acct: 4.58 (4.58) proj_loss: -0.5932 (-0.5932) time: 0.9310 data: 0.0003 [11-23 19:49:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 417/1669] eta: 0:19:50 tlr: 0.00021 tnm: 0.21 Lm: 6.618 (6.618) Lt: 5.850 (5.850) Accm: 2.83 (2.83) Acct: 4.46 (4.46) proj_loss: -0.5843 (-0.5843) time: 0.9310 data: 0.0003 [11-23 19:49:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 417/1669] eta: 0:19:50 tlr: 0.00021 tnm: 0.21 Lm: 6.627 (6.627) Lt: 5.977 (5.977) Accm: 3.08 (3.08) Acct: 4.79 (4.79) proj_loss: -0.5938 (-0.5938) time: 0.9310 data: 0.0003 [11-23 19:49:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 417/1669] eta: 0:19:50 tlr: 0.00021 tnm: 0.21 Lm: 6.476 (6.476) Lt: 5.734 (5.734) Accm: 3.70 (3.70) Acct: 5.51 (5.51) proj_loss: -0.5916 (-0.5916) time: 0.9310 data: 0.0003 [11-23 19:49:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 417/1669] eta: 0:19:50 tlr: 0.00021 tnm: 0.21 Lm: 6.592 (6.592) Lt: 5.785 (5.785) Accm: 3.43 (3.43) Acct: 5.60 (5.60) proj_loss: -0.5594 (-0.5594) time: 0.9310 data: 0.0003 [11-23 19:49:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 417/1669] eta: 0:19:50 tlr: 0.00021 tnm: 0.21 Lm: 6.408 (6.408) Lt: 5.667 (5.667) Accm: 3.37 (3.37) Acct: 5.32 (5.32) proj_loss: -0.5798 (-0.5798) time: 0.9310 data: 0.0003 [11-23 19:49:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 417/1669] eta: 0:19:50 tlr: 0.00021 tnm: 0.21 Lm: 6.586 (6.586) Lt: 5.850 (5.850) Accm: 3.13 (3.13) Acct: 5.22 (5.22) proj_loss: -0.5655 (-0.5655) time: 0.9310 data: 0.0003 [11-23 19:49:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 417/1669] eta: 0:19:50 tlr: 0.00021 tnm: 0.21 Lm: 6.489 (6.489) Lt: 5.700 (5.700) Accm: 3.18 (3.18) Acct: 5.13 (5.13) proj_loss: -0.5935 (-0.5935) time: 0.9310 data: 0.0003 [11-23 19:56:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 834/1669] eta: 0:13:31 tlr: 0.00021 tnm: 0.21 Lm: 6.421 (6.467) Lt: 5.587 (5.662) Accm: 3.54 (3.37) Acct: 5.79 (5.36) proj_loss: -0.5834 (-0.5901) time: 0.9324 data: 0.0003 [11-23 19:56:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 834/1669] eta: 0:13:31 tlr: 0.00021 tnm: 0.21 Lm: 6.464 (6.427) Lt: 5.590 (5.641) Accm: 3.39 (3.44) Acct: 5.68 (5.51) proj_loss: -0.5837 (-0.5811) time: 0.9324 data: 0.0003 [11-23 19:56:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 834/1669] eta: 0:13:31 tlr: 0.00021 tnm: 0.21 Lm: 6.448 (6.459) Lt: 5.667 (5.699) Accm: 3.70 (3.70) Acct: 5.79 (5.74) proj_loss: -0.5775 (-0.5842) time: 0.9324 data: 0.0003 [11-23 19:56:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 834/1669] eta: 0:13:31 tlr: 0.00021 tnm: 0.21 Lm: 6.544 (6.576) Lt: 5.693 (5.754) Accm: 3.16 (3.34) Acct: 5.51 (5.57) proj_loss: -0.5619 (-0.5662) time: 0.9324 data: 0.0003 [11-23 19:56:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 834/1669] eta: 0:13:31 tlr: 0.00021 tnm: 0.21 Lm: 6.502 (6.549) Lt: 5.783 (5.788) Accm: 3.54 (3.29) Acct: 5.65 (5.41) proj_loss: -0.5553 (-0.5618) time: 0.9324 data: 0.0003 [11-23 19:56:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 834/1669] eta: 0:13:31 tlr: 0.00021 tnm: 0.21 Lm: 6.612 (6.622) Lt: 5.881 (5.932) Accm: 2.88 (2.99) Acct: 4.44 (4.58) proj_loss: -0.5722 (-0.5798) time: 0.9324 data: 0.0003 [11-23 19:56:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 834/1669] eta: 0:13:31 tlr: 0.00021 tnm: 0.21 Lm: 6.504 (6.579) Lt: 5.722 (5.795) Accm: 3.10 (2.96) Acct: 4.99 (4.64) proj_loss: -0.5667 (-0.5784) time: 0.9324 data: 0.0003 [11-23 19:56:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [ 834/1669] eta: 0:13:31 tlr: 0.00021 tnm: 0.21 Lm: 6.621 (6.609) Lt: 5.923 (5.872) Accm: 2.77 (2.91) Acct: 3.82 (4.33) proj_loss: -0.5898 (-0.5821) time: 0.9324 data: 0.0003 [11-23 20:02:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [1251/1669] eta: 0:06:41 tlr: 0.00021 tnm: 0.21 Lm: 6.641 (6.622) Lt: 5.925 (5.901) Accm: 2.81 (2.90) Acct: 4.05 (4.31) proj_loss: -0.5864 (-0.5823) time: 0.9327 data: 0.0004 [11-23 20:02:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [1251/1669] eta: 0:06:41 tlr: 0.00021 tnm: 0.21 Lm: 6.464 (6.479) Lt: 5.680 (5.703) Accm: 3.37 (3.33) Acct: 5.32 (5.32) proj_loss: -0.5852 (-0.5831) time: 0.9327 data: 0.0003 [11-23 20:02:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [1251/1669] eta: 0:06:41 tlr: 0.00021 tnm: 0.21 Lm: 6.525 (6.549) Lt: 5.779 (5.785) Accm: 3.17 (3.17) Acct: 5.22 (5.13) proj_loss: -0.5548 (-0.5565) time: 0.9327 data: 0.0003 [11-23 20:02:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [1251/1669] eta: 0:06:41 tlr: 0.00021 tnm: 0.21 Lm: 6.550 (6.571) Lt: 5.776 (5.780) Accm: 3.11 (3.27) Acct: 5.25 (5.35) proj_loss: -0.5673 (-0.5679) time: 0.9327 data: 0.0003 [11-23 20:02:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [1251/1669] eta: 0:06:41 tlr: 0.00021 tnm: 0.21 Lm: 6.618 (6.635) Lt: 5.850 (5.872) Accm: 2.88 (2.88) Acct: 4.42 (4.44) proj_loss: -0.5735 (-0.5789) time: 0.9327 data: 0.0003 [11-23 20:02:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [1251/1669] eta: 0:06:41 tlr: 0.00021 tnm: 0.21 Lm: 6.391 (6.435) Lt: 5.597 (5.648) Accm: 3.63 (3.54) Acct: 5.80 (5.48) proj_loss: -0.5819 (-0.5861) time: 0.9327 data: 0.0003 [11-23 20:02:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [1251/1669] eta: 0:06:41 tlr: 0.00021 tnm: 0.21 Lm: 6.620 (6.623) Lt: 5.873 (5.915) Accm: 3.00 (3.02) Acct: 4.67 (4.66) proj_loss: -0.5866 (-0.5851) time: 0.9327 data: 0.0003 [11-23 20:02:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [1251/1669] eta: 0:06:41 tlr: 0.00021 tnm: 0.21 Lm: 6.437 (6.437) Lt: 5.648 (5.681) Accm: 3.69 (3.61) Acct: 5.54 (5.63) proj_loss: -0.5862 (-0.5869) time: 0.9327 data: 0.0002 [11-23 20:09:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.426 (6.405) Lt: 5.629 (5.650) Accm: 3.70 (3.73) Acct: 5.79 (5.85) proj_loss: -0.5949 (-0.5905) time: 0.9347 data: 0.0017 [11-23 20:09:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 62/350] Total time: 0:26:30 (0.953 s / it) [11-23 20:09:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.621 (6.617) Lt: 5.923 (5.896) Accm: 2.86 (2.95) Acct: 4.27 (4.41) proj_loss: -0.5829 (-0.5814) time: 0.9347 data: 0.0020 [11-23 20:09:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.549 (6.582) Lt: 5.783 (5.823) Accm: 2.80 (3.04) Acct: 4.79 (4.87) proj_loss: -0.5553 (-0.5569) time: 0.9347 data: 0.0016 [11-23 20:09:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.628 (6.652) Lt: 5.881 (5.937) Accm: 2.88 (2.93) Acct: 4.44 (4.56) proj_loss: -0.5951 (-0.5871) time: 0.9347 data: 0.0019 [11-23 20:09:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.544 (6.563) Lt: 5.719 (5.768) Accm: 3.16 (3.34) Acct: 5.51 (5.46) proj_loss: -0.5705 (-0.5684) time: 0.9347 data: 0.0019 [11-23 20:09:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.465 (6.545) Lt: 5.770 (5.791) Accm: 3.34 (3.11) Acct: 4.96 (4.95) proj_loss: -0.5868 (-0.5841) time: 0.9347 data: 0.0019 [11-23 20:09:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.421 (6.470) Lt: 5.607 (5.674) Accm: 3.54 (3.47) Acct: 5.79 (5.42) proj_loss: -0.5810 (-0.5851) time: 0.9347 data: 0.0019 [11-23 20:09:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 62/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.504 (6.595) Lt: 5.740 (5.846) Accm: 3.10 (2.97) Acct: 4.99 (4.59) proj_loss: -0.5803 (-0.5851) time: 0.9347 data: 0.0018 [11-23 20:09:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 62/350] Total time: 0:26:30 (0.953 s / it) [11-23 20:09:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 62/350] Total time: 0:26:30 (0.953 s / it) [11-23 20:09:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 62/350] Total time: 0:26:30 (0.953 s / it) [11-23 20:09:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 62/350] Total time: 0:26:30 (0.953 s / it) [11-23 20:09:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 62/350] Total time: 0:26:30 (0.953 s / it) [11-23 20:09:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 62/350] Total time: 0:26:30 (0.953 s / it) [11-23 20:09:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 62/350] Total time: 0:26:30 (0.953 s / it) [11-23 20:09:13] (/home/user/VAR/train.py , line 276)=> [ep62] (training ) Lm: 6.577 (6.582), Lt: 5.824 (5.831), Acc m&t: 3.20 5.05, Remain: 5 days, 4:54:47, Finish: 2024-11-28 09:04 [11-23 20:09:13] (/home/user/VAR/train.py , line 276)=> [ep62] (training ) Lm: 6.577 (6.582), Lt: 5.824 (5.831), Acc m&t: 3.20 5.05, Remain: 5 days, 4:53:44, Finish: 2024-11-28 09:02 [11-23 20:09:13] (/home/user/VAR/train.py , line 276)=> [ep62] (training ) Lm: 6.577 (6.582), Lt: 5.824 (5.831), Acc m&t: 3.20 5.05, Remain: 5 days, 4:53:47, Finish: 2024-11-28 09:03 [11-23 20:09:13] (/home/user/VAR/train.py , line 276)=> [ep62] (training ) Lm: 6.577 (6.582), Lt: 5.824 (5.831), Acc m&t: 3.20 5.05, Remain: 5 days, 4:52:14, Finish: 2024-11-28 09:01 [11-23 20:09:13] (/home/user/VAR/train.py , line 276)=> [ep62] (training ) Lm: 6.577 (6.582), Lt: 5.824 (5.831), Acc m&t: 3.20 5.05, Remain: 5 days, 4:50:32, Finish: 2024-11-28 08:59 [11-23 20:09:13] (/home/user/VAR/train.py , line 276)=> [ep62] (training ) Lm: 6.577 (6.582), Lt: 5.824 (5.831), Acc m&t: 3.20 5.05, Remain: 5 days, 4:52:12, Finish: 2024-11-28 09:01 [11-23 20:09:13] (/home/user/VAR/train.py , line 276)=> [ep62] (training ) Lm: 6.577 (6.582), Lt: 5.824 (5.831), Acc m&t: 3.20 5.05, Remain: 5 days, 4:54:05, Finish: 2024-11-28 09:03 [11-23 20:09:13] (/home/user/VAR/train.py , line 276)=> [ep62] (training ) Lm: 6.577 (6.582), Lt: 5.824 (5.831), Acc m&t: 3.20 5.05, Remain: 5 days, 4:53:34, Finish: 2024-11-28 09:02 [11-23 20:09:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 0/1669] eta: 0:24:45 tlr: 0.00021 tnm: 0.22 Lm: 6.607 (6.607) Lt: 5.814 (5.814) Accm: 3.28 (3.28) Acct: 5.06 (5.06) proj_loss: -0.5725 (-0.5725) time: 0.8899 data: 0.0004 [11-23 20:09:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 0/1669] eta: 0:24:45 tlr: 0.00021 tnm: 0.22 Lm: 6.732 (6.732) Lt: 6.067 (6.067) Accm: 2.33 (2.33) Acct: 3.89 (3.89) proj_loss: -0.5947 (-0.5947) time: 0.8903 data: 0.0003 [11-23 20:09:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 0/1669] eta: 0:24:56 tlr: 0.00021 tnm: 0.22 Lm: 6.570 (6.570) Lt: 5.768 (5.768) Accm: 3.31 (3.31) Acct: 5.68 (5.68) proj_loss: -0.5651 (-0.5651) time: 0.8967 data: 0.0004 [11-23 20:09:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 0/1669] eta: 0:24:45 tlr: 0.00021 tnm: 0.22 Lm: 6.555 (6.555) Lt: 5.751 (5.751) Accm: 3.45 (3.45) Acct: 5.54 (5.54) proj_loss: -0.5860 (-0.5860) time: 0.8902 data: 0.0004 [11-23 20:09:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 0/1669] eta: 0:24:47 tlr: 0.00021 tnm: 0.22 Lm: 6.276 (6.276) Lt: 5.499 (5.499) Accm: 3.73 (3.73) Acct: 5.61 (5.61) proj_loss: -0.6215 (-0.6215) time: 0.8910 data: 0.0003 [11-23 20:09:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 0/1669] eta: 0:24:47 tlr: 0.00021 tnm: 0.22 Lm: 6.346 (6.346) Lt: 5.568 (5.568) Accm: 3.42 (3.42) Acct: 5.51 (5.51) proj_loss: -0.5743 (-0.5743) time: 0.8913 data: 0.0004 [11-23 20:09:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 0/1669] eta: 0:24:46 tlr: 0.00021 tnm: 0.22 Lm: 6.588 (6.588) Lt: 5.891 (5.891) Accm: 2.91 (2.91) Acct: 4.51 (4.51) proj_loss: -0.5944 (-0.5944) time: 0.8908 data: 0.0004 [11-23 20:09:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 0/1669] eta: 0:24:48 tlr: 0.00021 tnm: 0.22 Lm: 6.760 (6.760) Lt: 6.102 (6.102) Accm: 2.30 (2.30) Acct: 3.58 (3.58) proj_loss: -0.6302 (-0.6302) time: 0.8919 data: 0.0004 [11-23 20:15:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.680 (6.680) Lt: 6.001 (6.001) Accm: 2.83 (2.83) Acct: 4.39 (4.39) proj_loss: -0.6014 (-0.6014) time: 0.9302 data: 0.0003 [11-23 20:15:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.631 (6.631) Lt: 5.963 (5.963) Accm: 2.74 (2.74) Acct: 4.22 (4.22) proj_loss: -0.5997 (-0.5997) time: 0.9302 data: 0.0003 [11-23 20:15:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.677 (6.677) Lt: 5.913 (5.913) Accm: 2.91 (2.91) Acct: 4.80 (4.80) proj_loss: -0.5612 (-0.5612) time: 0.9302 data: 0.0003 [11-23 20:15:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.449 (6.449) Lt: 5.623 (5.623) Accm: 3.93 (3.93) Acct: 6.18 (6.18) proj_loss: -0.5767 (-0.5767) time: 0.9302 data: 0.0003 [11-23 20:15:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.419 (6.419) Lt: 5.615 (5.615) Accm: 3.62 (3.62) Acct: 5.44 (5.44) proj_loss: -0.5817 (-0.5817) time: 0.9302 data: 0.0003 [11-23 20:15:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.562 (6.562) Lt: 5.795 (5.795) Accm: 3.15 (3.15) Acct: 4.91 (4.91) proj_loss: -0.5831 (-0.5831) time: 0.9302 data: 0.0003 [11-23 20:15:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.485 (6.485) Lt: 5.687 (5.687) Accm: 3.63 (3.63) Acct: 5.73 (5.73) proj_loss: -0.5806 (-0.5806) time: 0.9302 data: 0.0003 [11-23 20:15:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.529 (6.529) Lt: 5.753 (5.753) Accm: 3.23 (3.23) Acct: 5.15 (5.15) proj_loss: -0.5876 (-0.5876) time: 0.9302 data: 0.0003 [11-23 20:22:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.465 (6.507) Lt: 5.705 (5.737) Accm: 3.42 (3.32) Acct: 5.13 (5.14) proj_loss: -0.5995 (-0.5916) time: 0.9318 data: 0.0003 [11-23 20:22:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.440 (6.446) Lt: 5.618 (5.622) Accm: 3.50 (3.78) Acct: 5.27 (5.88) proj_loss: -0.5808 (-0.5802) time: 0.9318 data: 0.0003 [11-23 20:22:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.588 (6.617) Lt: 5.891 (5.885) Accm: 2.91 (2.98) Acct: 4.51 (4.41) proj_loss: -0.5907 (-0.5856) time: 0.9318 data: 0.0003 [11-23 20:22:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.601 (6.578) Lt: 5.900 (5.886) Accm: 3.37 (3.07) Acct: 5.20 (4.81) proj_loss: -0.5746 (-0.5925) time: 0.9318 data: 0.0003 [11-23 20:22:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.562 (6.506) Lt: 5.731 (5.714) Accm: 3.51 (3.42) Acct: 5.27 (5.17) proj_loss: -0.5604 (-0.5746) time: 0.9318 data: 0.0003 [11-23 20:22:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.618 (6.627) Lt: 5.859 (5.898) Accm: 2.99 (2.82) Acct: 4.55 (4.53) proj_loss: -0.5947 (-0.5927) time: 0.9318 data: 0.0003 [11-23 20:22:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.724 (6.693) Lt: 5.969 (5.932) Accm: 2.75 (2.86) Acct: 4.37 (4.66) proj_loss: -0.5651 (-0.5740) time: 0.9318 data: 0.0003 [11-23 20:22:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.415 (6.440) Lt: 5.622 (5.650) Accm: 3.61 (3.63) Acct: 5.54 (5.65) proj_loss: -0.5752 (-0.5730) time: 0.9318 data: 0.0003 [11-23 20:29:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [1251/1669] eta: 0:06:39 tlr: 0.00021 tnm: 0.22 Lm: 6.474 (6.463) Lt: 5.687 (5.687) Accm: 3.53 (3.55) Acct: 5.51 (5.54) proj_loss: -0.5806 (-0.5779) time: 1.1162 data: 0.0003 [11-23 20:29:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [1251/1669] eta: 0:06:39 tlr: 0.00021 tnm: 0.22 Lm: 6.562 (6.583) Lt: 5.804 (5.843) Accm: 3.15 (3.19) Acct: 4.91 (4.80) proj_loss: -0.5877 (-0.5854) time: 1.1162 data: 0.0003 [11-23 20:29:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [1251/1669] eta: 0:06:39 tlr: 0.00021 tnm: 0.22 Lm: 6.522 (6.500) Lt: 5.687 (5.696) Accm: 3.31 (3.34) Acct: 4.98 (5.04) proj_loss: -0.5706 (-0.5761) time: 1.1162 data: 0.0003 [11-23 20:29:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [1251/1669] eta: 0:06:39 tlr: 0.00021 tnm: 0.22 Lm: 6.611 (6.621) Lt: 5.884 (5.901) Accm: 2.97 (2.86) Acct: 4.58 (4.55) proj_loss: -0.5867 (-0.5880) time: 1.1162 data: 0.0003 [11-23 20:29:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [1251/1669] eta: 0:06:39 tlr: 0.00021 tnm: 0.22 Lm: 6.424 (6.476) Lt: 5.686 (5.720) Accm: 3.46 (3.40) Acct: 5.29 (5.22) proj_loss: -0.6002 (-0.5954) time: 1.1162 data: 0.0003 [11-23 20:29:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [1251/1669] eta: 0:06:39 tlr: 0.00021 tnm: 0.22 Lm: 6.647 (6.633) Lt: 5.868 (5.849) Accm: 3.03 (3.08) Acct: 5.03 (5.10) proj_loss: -0.5624 (-0.5704) time: 1.1162 data: 0.0003 [11-23 20:29:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [1251/1669] eta: 0:06:39 tlr: 0.00021 tnm: 0.22 Lm: 6.512 (6.480) Lt: 5.716 (5.672) Accm: 3.39 (3.55) Acct: 5.17 (5.54) proj_loss: -0.5840 (-0.5837) time: 1.1162 data: 0.0003 [11-23 20:29:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [1251/1669] eta: 0:06:39 tlr: 0.00021 tnm: 0.22 Lm: 6.556 (6.561) Lt: 5.853 (5.867) Accm: 3.27 (3.10) Acct: 5.10 (4.86) proj_loss: -0.6003 (-0.6008) time: 1.1162 data: 0.0003 [11-23 20:35:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.576 (6.564) Lt: 5.830 (5.859) Accm: 3.23 (3.13) Acct: 4.99 (4.79) proj_loss: -0.5884 (-0.5984) time: 0.9345 data: 0.0014 [11-23 20:35:51] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 63/350] Total time: 0:26:38 (0.958 s / it) [11-23 20:35:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.588 (6.587) Lt: 5.758 (5.826) Accm: 3.16 (3.19) Acct: 5.23 (4.89) proj_loss: -0.5892 (-0.5862) time: 0.9344 data: 0.0018 [11-23 20:35:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.532 (6.506) Lt: 5.731 (5.719) Accm: 3.19 (3.31) Acct: 4.92 (5.02) proj_loss: -0.5808 (-0.5783) time: 0.9345 data: 0.0018 [11-23 20:35:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.533 (6.498) Lt: 5.751 (5.724) Accm: 3.45 (3.48) Acct: 5.48 (5.46) proj_loss: -0.5752 (-0.5760) time: 0.9345 data: 0.0021 [11-23 20:35:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.604 (6.614) Lt: 5.859 (5.872) Accm: 2.99 (2.94) Acct: 4.61 (4.70) proj_loss: -0.5947 (-0.5921) time: 0.9345 data: 0.0020 [11-23 20:35:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.584 (6.504) Lt: 5.814 (5.715) Accm: 3.48 (3.54) Acct: 5.27 (5.52) proj_loss: -0.5872 (-0.5847) time: 0.9345 data: 0.0019 [11-23 20:35:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.465 (6.532) Lt: 5.705 (5.787) Accm: 3.42 (3.27) Acct: 5.13 (4.97) proj_loss: -0.5995 (-0.5929) time: 0.9345 data: 0.0021 [11-23 20:35:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 63/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.703 (6.647) Lt: 5.935 (5.866) Accm: 2.81 (3.03) Acct: 4.37 (4.93) proj_loss: -0.5597 (-0.5671) time: 0.9345 data: 0.0018 [11-23 20:35:51] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 63/350] Total time: 0:26:38 (0.958 s / it) [11-23 20:35:51] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 63/350] Total time: 0:26:38 (0.958 s / it) [11-23 20:35:51] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 63/350] Total time: 0:26:38 (0.958 s / it) [11-23 20:35:51] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 63/350] Total time: 0:26:38 (0.958 s / it) [11-23 20:35:51] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 63/350] Total time: 0:26:38 (0.958 s / it) [11-23 20:35:51] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 63/350] Total time: 0:26:38 (0.958 s / it) [11-23 20:35:51] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 63/350] Total time: 0:26:38 (0.958 s / it) [11-23 20:35:51] (/home/user/VAR/train.py , line 276)=> [ep63] (training ) Lm: 6.574 (6.574), Lt: 5.815 (5.815), Acc m&t: 3.20 5.05, Remain: 5 days, 4:36:41, Finish: 2024-11-28 09:12 [11-23 20:35:51] (/home/user/VAR/train.py , line 276)=> [ep63] (training ) Lm: 6.574 (6.574), Lt: 5.815 (5.815), Acc m&t: 3.20 5.05, Remain: 5 days, 4:37:11, Finish: 2024-11-28 09:13 [11-23 20:35:51] (/home/user/VAR/train.py , line 276)=> [ep63] (training ) Lm: 6.574 (6.574), Lt: 5.815 (5.815), Acc m&t: 3.20 5.05, Remain: 5 days, 4:36:46, Finish: 2024-11-28 09:12 [11-23 20:35:51] (/home/user/VAR/train.py , line 276)=> [ep63] (training ) Lm: 6.574 (6.574), Lt: 5.815 (5.815), Acc m&t: 3.20 5.05, Remain: 5 days, 4:36:43, Finish: 2024-11-28 09:12 [11-23 20:35:51] (/home/user/VAR/train.py , line 276)=> [ep63] (training ) Lm: 6.574 (6.574), Lt: 5.815 (5.815), Acc m&t: 3.20 5.05, Remain: 5 days, 4:37:58, Finish: 2024-11-28 09:13 [11-23 20:35:51] (/home/user/VAR/train.py , line 276)=> [ep63] (training ) Lm: 6.574 (6.574), Lt: 5.815 (5.815), Acc m&t: 3.20 5.05, Remain: 5 days, 4:36:40, Finish: 2024-11-28 09:12 [11-23 20:35:51] (/home/user/VAR/train.py , line 276)=> [ep63] (training ) Lm: 6.574 (6.574), Lt: 5.815 (5.815), Acc m&t: 3.20 5.05, Remain: 5 days, 4:37:26, Finish: 2024-11-28 09:13 [11-23 20:35:51] (/home/user/VAR/train.py , line 276)=> [ep63] (training ) Lm: 6.574 (6.574), Lt: 5.815 (5.815), Acc m&t: 3.20 5.05, Remain: 5 days, 4:36:23, Finish: 2024-11-28 09:12 [11-23 20:35:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 0/1669] eta: 0:25:23 tlr: 0.00021 tnm: 0.21 Lm: 6.439 (6.439) Lt: 5.611 (5.611) Accm: 3.45 (3.45) Acct: 5.85 (5.85) proj_loss: -0.5825 (-0.5825) time: 0.9130 data: 0.0004 [11-23 20:35:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 0/1669] eta: 0:25:24 tlr: 0.00021 tnm: 0.21 Lm: 6.857 (6.857) Lt: 6.104 (6.104) Accm: 2.70 (2.70) Acct: 4.68 (4.68) proj_loss: -0.5326 (-0.5326) time: 0.9133 data: 0.0004 [11-23 20:35:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 0/1669] eta: 0:25:24 tlr: 0.00021 tnm: 0.21 Lm: 6.878 (6.878) Lt: 6.161 (6.161) Accm: 2.30 (2.30) Acct: 3.89 (3.89) proj_loss: -0.5804 (-0.5804) time: 0.9134 data: 0.0004 [11-23 20:35:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 0/1669] eta: 0:25:24 tlr: 0.00021 tnm: 0.21 Lm: 6.819 (6.819) Lt: 6.148 (6.148) Accm: 2.74 (2.74) Acct: 3.93 (3.93) proj_loss: -0.5593 (-0.5593) time: 0.9134 data: 0.0004 [11-23 20:35:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 0/1669] eta: 0:25:24 tlr: 0.00021 tnm: 0.21 Lm: 6.384 (6.384) Lt: 5.608 (5.608) Accm: 4.01 (4.01) Acct: 6.10 (6.10) proj_loss: -0.6158 (-0.6158) time: 0.9136 data: 0.0004 [11-23 20:35:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 0/1669] eta: 0:25:24 tlr: 0.00021 tnm: 0.21 Lm: 6.512 (6.512) Lt: 5.710 (5.710) Accm: 3.38 (3.38) Acct: 5.34 (5.34) proj_loss: -0.5593 (-0.5593) time: 0.9134 data: 0.0005 [11-23 20:35:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 0/1669] eta: 0:25:25 tlr: 0.00021 tnm: 0.21 Lm: 6.426 (6.426) Lt: 5.568 (5.568) Accm: 3.41 (3.41) Acct: 5.68 (5.68) proj_loss: -0.5668 (-0.5668) time: 0.9137 data: 0.0004 [11-23 20:35:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 0/1669] eta: 0:25:26 tlr: 0.00021 tnm: 0.21 Lm: 6.423 (6.423) Lt: 5.572 (5.572) Accm: 3.51 (3.51) Acct: 5.58 (5.58) proj_loss: -0.6079 (-0.6079) time: 0.9149 data: 0.0004 [11-23 20:42:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.507 (6.507) Lt: 5.701 (5.701) Accm: 3.32 (3.32) Acct: 5.22 (5.22) proj_loss: -0.5998 (-0.5998) time: 0.9318 data: 0.0003 [11-23 20:42:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.754 (6.754) Lt: 5.985 (5.985) Accm: 2.80 (2.80) Acct: 4.60 (4.60) proj_loss: -0.5774 (-0.5774) time: 0.9318 data: 0.0003 [11-23 20:42:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.820 (6.820) Lt: 6.079 (6.079) Accm: 2.51 (2.51) Acct: 4.18 (4.18) proj_loss: -0.5851 (-0.5851) time: 0.9318 data: 0.0003 [11-23 20:42:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.530 (6.530) Lt: 5.768 (5.768) Accm: 3.29 (3.29) Acct: 5.29 (5.29) proj_loss: -0.5806 (-0.5806) time: 0.9318 data: 0.0003 [11-23 20:42:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.747 (6.747) Lt: 6.054 (6.054) Accm: 3.00 (3.00) Acct: 4.61 (4.61) proj_loss: -0.5752 (-0.5752) time: 0.9318 data: 0.0003 [11-23 20:42:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.584 (6.584) Lt: 5.778 (5.778) Accm: 3.21 (3.21) Acct: 4.99 (4.99) proj_loss: -0.5648 (-0.5648) time: 0.9318 data: 0.0003 [11-23 20:42:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.418 (6.418) Lt: 5.645 (5.645) Accm: 3.77 (3.77) Acct: 5.66 (5.66) proj_loss: -0.5772 (-0.5772) time: 0.9318 data: 0.0003 [11-23 20:42:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.519 (6.519) Lt: 5.742 (5.742) Accm: 3.08 (3.08) Acct: 5.03 (5.03) proj_loss: -0.5859 (-0.5859) time: 0.9318 data: 0.0003 [11-23 20:48:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.499 (6.512) Lt: 5.750 (5.745) Accm: 3.34 (3.17) Acct: 5.30 (5.12) proj_loss: -0.5959 (-0.5892) time: 0.9328 data: 0.0003 [11-23 20:48:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.451 (6.488) Lt: 5.681 (5.702) Accm: 3.54 (3.50) Acct: 5.23 (5.41) proj_loss: -0.6020 (-0.5855) time: 0.9328 data: 0.0003 [11-23 20:48:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.591 (6.557) Lt: 5.829 (5.765) Accm: 3.13 (3.23) Acct: 4.86 (5.05) proj_loss: -0.5942 (-0.5979) time: 0.9328 data: 0.0003 [11-23 20:48:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.439 (6.497) Lt: 5.719 (5.751) Accm: 3.45 (3.40) Acct: 5.48 (5.35) proj_loss: -0.5825 (-0.5850) time: 0.9328 data: 0.0003 [11-23 20:48:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.651 (6.674) Lt: 5.867 (5.893) Accm: 2.90 (3.05) Acct: 4.68 (4.96) proj_loss: -0.5507 (-0.5685) time: 0.9328 data: 0.0003 [11-23 20:48:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.738 (6.744) Lt: 5.982 (6.030) Accm: 2.74 (2.82) Acct: 4.10 (4.44) proj_loss: -0.5911 (-0.5847) time: 0.9328 data: 0.0003 [11-23 20:48:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.657 (6.632) Lt: 5.847 (5.833) Accm: 3.04 (3.06) Acct: 4.65 (4.86) proj_loss: -0.5702 (-0.5699) time: 0.9328 data: 0.0003 [11-23 20:48:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.21 Lm: 6.761 (6.777) Lt: 6.018 (6.059) Accm: 2.71 (2.68) Acct: 4.48 (4.35) proj_loss: -0.5813 (-0.5839) time: 0.9328 data: 0.0003 [11-23 20:55:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.22 Lm: 6.727 (6.748) Lt: 6.007 (6.020) Accm: 2.81 (2.74) Acct: 4.46 (4.37) proj_loss: -0.5856 (-0.5880) time: 0.9319 data: 0.0002 [11-23 20:55:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.22 Lm: 6.435 (6.452) Lt: 5.665 (5.686) Accm: 3.54 (3.55) Acct: 5.66 (5.59) proj_loss: -0.5812 (-0.5837) time: 0.9318 data: 0.0003 [11-23 20:55:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.22 Lm: 6.623 (6.603) Lt: 5.861 (5.798) Accm: 3.09 (3.13) Acct: 4.84 (4.99) proj_loss: -0.5929 (-0.5939) time: 0.9318 data: 0.0003 [11-23 20:55:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.22 Lm: 6.555 (6.604) Lt: 5.833 (5.861) Accm: 3.04 (2.98) Acct: 4.84 (4.84) proj_loss: -0.6005 (-0.5938) time: 0.9319 data: 0.0003 [11-23 20:55:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.22 Lm: 6.707 (6.682) Lt: 5.971 (5.950) Accm: 3.00 (3.03) Acct: 4.70 (4.81) proj_loss: -0.5793 (-0.5804) time: 0.9319 data: 0.0003 [11-23 20:55:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.22 Lm: 6.584 (6.578) Lt: 5.778 (5.801) Accm: 3.21 (3.29) Acct: 4.99 (5.13) proj_loss: -0.5752 (-0.5775) time: 0.9318 data: 0.0003 [11-23 20:55:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.22 Lm: 6.469 (6.488) Lt: 5.707 (5.710) Accm: 3.58 (3.53) Acct: 5.42 (5.46) proj_loss: -0.5980 (-0.5876) time: 0.9319 data: 0.0003 [11-23 20:55:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.22 Lm: 6.582 (6.612) Lt: 5.787 (5.810) Accm: 3.23 (3.22) Acct: 5.18 (5.20) proj_loss: -0.5605 (-0.5689) time: 0.9318 data: 0.0003 [11-23 21:01:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.439 (6.483) Lt: 5.719 (5.735) Accm: 3.45 (3.44) Acct: 5.48 (5.31) proj_loss: -0.5825 (-0.5859) time: 0.9337 data: 0.0015 [11-23 21:01:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.591 (6.578) Lt: 5.829 (5.763) Accm: 3.13 (3.20) Acct: 4.86 (5.06) proj_loss: -0.5916 (-0.5811) time: 0.9337 data: 0.0021 [11-23 21:01:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.692 (6.728) Lt: 5.997 (5.992) Accm: 2.91 (2.82) Acct: 4.48 (4.55) proj_loss: -0.5864 (-0.5877) time: 0.9337 data: 0.0017 [11-23 21:01:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.512 (6.544) Lt: 5.710 (5.766) Accm: 3.38 (3.35) Acct: 5.34 (5.25) proj_loss: -0.5702 (-0.5727) time: 0.9337 data: 0.0016 [11-23 21:01:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.738 (6.707) Lt: 5.982 (5.970) Accm: 2.83 (2.99) Acct: 4.41 (4.73) proj_loss: -0.5911 (-0.5852) time: 0.9337 data: 0.0017 [11-23 21:01:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.488 (6.502) Lt: 5.733 (5.739) Accm: 3.58 (3.54) Acct: 5.61 (5.53) proj_loss: -0.6020 (-0.5907) time: 0.9337 data: 0.0017 [11-23 21:01:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.611 (6.608) Lt: 5.807 (5.850) Accm: 2.75 (2.93) Acct: 4.48 (4.77) proj_loss: -0.6051 (-0.5962) time: 0.9337 data: 0.0016 [11-23 21:01:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 64/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.513 (6.577) Lt: 5.708 (5.785) Accm: 3.57 (3.31) Acct: 5.68 (5.38) proj_loss: -0.5703 (-0.5738) time: 0.9337 data: 0.0019 [11-23 21:01:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 64/350] Total time: 0:25:53 (0.931 s / it) [11-23 21:01:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 64/350] Total time: 0:25:53 (0.931 s / it) [11-23 21:01:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 64/350] Total time: 0:25:53 (0.931 s / it) [11-23 21:01:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 64/350] Total time: 0:25:53 (0.931 s / it) [11-23 21:01:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 64/350] Total time: 0:25:53 (0.931 s / it) [11-23 21:01:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 64/350] Total time: 0:25:53 (0.931 s / it) [11-23 21:01:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 64/350] Total time: 0:25:53 (0.931 s / it) [11-23 21:01:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 64/350] Total time: 0:25:53 (0.931 s / it) [11-23 21:01:45] (/home/user/VAR/train.py , line 276)=> [ep64] (training ) Lm: 6.574 (6.578), Lt: 5.815 (5.829), Acc m&t: 3.20 5.05, Remain: 5 days, 4:10:08, Finish: 2024-11-28 09:11 [11-23 21:01:45] (/home/user/VAR/train.py , line 276)=> [ep64] (training ) Lm: 6.574 (6.578), Lt: 5.815 (5.829), Acc m&t: 3.20 5.05, Remain: 5 days, 4:09:48, Finish: 2024-11-28 09:11 [11-23 21:01:45] (/home/user/VAR/train.py , line 276)=> [ep64] (training ) Lm: 6.574 (6.578), Lt: 5.815 (5.829), Acc m&t: 3.20 5.05, Remain: 5 days, 4:13:06, Finish: 2024-11-28 09:14 [11-23 21:01:45] (/home/user/VAR/train.py , line 276)=> [ep64] (training ) Lm: 6.574 (6.578), Lt: 5.815 (5.829), Acc m&t: 3.20 5.05, Remain: 5 days, 4:13:21, Finish: 2024-11-28 09:15 [11-23 21:01:45] (/home/user/VAR/train.py , line 276)=> [ep64] (training ) Lm: 6.574 (6.578), Lt: 5.815 (5.829), Acc m&t: 3.20 5.05, Remain: 5 days, 4:12:27, Finish: 2024-11-28 09:14 [11-23 21:01:45] (/home/user/VAR/train.py , line 276)=> [ep64] (training ) Lm: 6.574 (6.578), Lt: 5.815 (5.829), Acc m&t: 3.20 5.05, Remain: 5 days, 4:10:55, Finish: 2024-11-28 09:12 [11-23 21:01:45] (/home/user/VAR/train.py , line 276)=> [ep64] (training ) Lm: 6.574 (6.578), Lt: 5.815 (5.829), Acc m&t: 3.20 5.05, Remain: 5 days, 4:10:56, Finish: 2024-11-28 09:12 [11-23 21:01:45] (/home/user/VAR/train.py , line 276)=> [ep64] (training ) Lm: 6.574 (6.578), Lt: 5.815 (5.829), Acc m&t: 3.20 5.05, Remain: 5 days, 4:08:21, Finish: 2024-11-28 09:10 [11-23 21:01:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 0/1669] eta: 0:24:45 tlr: 0.00021 tnm: 0.21 Lm: 6.431 (6.431) Lt: 5.755 (5.755) Accm: 3.64 (3.64) Acct: 5.20 (5.20) proj_loss: -0.6105 (-0.6105) time: 0.8902 data: 0.0003 [11-23 21:01:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 0/1669] eta: 0:25:12 tlr: 0.00021 tnm: 0.21 Lm: 6.607 (6.607) Lt: 5.904 (5.904) Accm: 3.10 (3.10) Acct: 5.20 (5.20) proj_loss: -0.6023 (-0.6023) time: 0.9063 data: 0.0005 [11-23 21:01:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 0/1669] eta: 0:24:46 tlr: 0.00021 tnm: 0.21 Lm: 6.672 (6.672) Lt: 5.899 (5.899) Accm: 3.09 (3.09) Acct: 4.79 (4.79) proj_loss: -0.5959 (-0.5959) time: 0.8905 data: 0.0004 [11-23 21:01:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 0/1669] eta: 0:24:46 tlr: 0.00021 tnm: 0.21 Lm: 6.859 (6.859) Lt: 6.119 (6.119) Accm: 2.17 (2.17) Acct: 3.37 (3.37) proj_loss: -0.5888 (-0.5888) time: 0.8907 data: 0.0004 [11-23 21:01:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 0/1669] eta: 0:24:58 tlr: 0.00021 tnm: 0.21 Lm: 6.315 (6.315) Lt: 5.556 (5.556) Accm: 3.74 (3.74) Acct: 5.85 (5.85) proj_loss: -0.5838 (-0.5838) time: 0.8980 data: 0.0004 [11-23 21:01:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 0/1669] eta: 0:24:46 tlr: 0.00021 tnm: 0.21 Lm: 6.622 (6.622) Lt: 5.768 (5.768) Accm: 2.84 (2.84) Acct: 4.48 (4.48) proj_loss: -0.5632 (-0.5632) time: 0.8905 data: 0.0004 [11-23 21:01:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 0/1669] eta: 0:24:46 tlr: 0.00021 tnm: 0.21 Lm: 6.520 (6.520) Lt: 5.744 (5.744) Accm: 3.28 (3.28) Acct: 4.89 (4.89) proj_loss: -0.6126 (-0.6126) time: 0.8904 data: 0.0004 [11-23 21:01:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 0/1669] eta: 0:24:47 tlr: 0.00021 tnm: 0.21 Lm: 6.492 (6.492) Lt: 5.721 (5.721) Accm: 3.32 (3.32) Acct: 5.13 (5.13) proj_loss: -0.5939 (-0.5939) time: 0.8914 data: 0.0004 [11-23 21:08:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 417/1669] eta: 0:20:30 tlr: 0.00021 tnm: 0.21 Lm: 6.541 (6.541) Lt: 5.739 (5.739) Accm: 3.23 (3.23) Acct: 5.32 (5.32) proj_loss: -0.5689 (-0.5689) time: 0.9320 data: 0.0003 [11-23 21:08:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 417/1669] eta: 0:20:30 tlr: 0.00021 tnm: 0.21 Lm: 6.516 (6.516) Lt: 5.797 (5.797) Accm: 3.32 (3.32) Acct: 5.10 (5.10) proj_loss: -0.6040 (-0.6040) time: 0.9319 data: 0.0003 [11-23 21:08:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 417/1669] eta: 0:20:30 tlr: 0.00021 tnm: 0.21 Lm: 6.437 (6.437) Lt: 5.655 (5.655) Accm: 3.52 (3.52) Acct: 5.63 (5.63) proj_loss: -0.5867 (-0.5867) time: 0.9319 data: 0.0003 [11-23 21:08:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 417/1669] eta: 0:20:30 tlr: 0.00021 tnm: 0.21 Lm: 6.714 (6.714) Lt: 5.967 (5.967) Accm: 2.65 (2.65) Acct: 4.25 (4.25) proj_loss: -0.5945 (-0.5945) time: 0.9319 data: 0.0003 [11-23 21:08:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 417/1669] eta: 0:20:30 tlr: 0.00021 tnm: 0.21 Lm: 6.533 (6.533) Lt: 5.774 (5.774) Accm: 3.41 (3.41) Acct: 5.37 (5.37) proj_loss: -0.5809 (-0.5809) time: 0.9320 data: 0.0003 [11-23 21:08:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 417/1669] eta: 0:20:30 tlr: 0.00021 tnm: 0.21 Lm: 6.506 (6.506) Lt: 5.728 (5.728) Accm: 3.48 (3.48) Acct: 5.39 (5.39) proj_loss: -0.5877 (-0.5877) time: 0.9320 data: 0.0003 [11-23 21:08:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 417/1669] eta: 0:20:30 tlr: 0.00021 tnm: 0.21 Lm: 6.606 (6.606) Lt: 5.768 (5.768) Accm: 3.11 (3.11) Acct: 4.82 (4.82) proj_loss: -0.5826 (-0.5826) time: 0.9320 data: 0.0003 [11-23 21:08:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 417/1669] eta: 0:20:30 tlr: 0.00021 tnm: 0.21 Lm: 6.598 (6.598) Lt: 5.853 (5.853) Accm: 3.01 (3.01) Acct: 5.13 (5.13) proj_loss: -0.5878 (-0.5878) time: 0.9320 data: 0.0003 [11-23 21:15:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 834/1669] eta: 0:13:33 tlr: 0.00021 tnm: 0.20 Lm: 6.597 (6.598) Lt: 5.801 (5.821) Accm: 2.91 (2.94) Acct: 5.06 (4.95) proj_loss: -0.5733 (-0.5764) time: 1.0381 data: 0.0003 [11-23 21:15:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 834/1669] eta: 0:13:33 tlr: 0.00021 tnm: 0.20 Lm: 6.431 (6.410) Lt: 5.755 (5.680) Accm: 3.64 (3.88) Acct: 5.20 (6.16) proj_loss: -0.6003 (-0.6028) time: 1.0382 data: 0.0002 [11-23 21:15:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 834/1669] eta: 0:13:33 tlr: 0.00021 tnm: 0.20 Lm: 6.569 (6.639) Lt: 5.816 (5.875) Accm: 3.13 (3.00) Acct: 5.13 (4.82) proj_loss: -0.5888 (-0.5907) time: 1.0382 data: 0.0003 [11-23 21:15:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 834/1669] eta: 0:13:33 tlr: 0.00021 tnm: 0.20 Lm: 6.591 (6.580) Lt: 5.769 (5.776) Accm: 3.38 (3.23) Acct: 5.17 (4.98) proj_loss: -0.6020 (-0.5903) time: 1.0381 data: 0.0003 [11-23 21:15:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 834/1669] eta: 0:13:33 tlr: 0.00021 tnm: 0.20 Lm: 6.570 (6.545) Lt: 5.811 (5.786) Accm: 3.45 (3.42) Acct: 5.61 (5.45) proj_loss: -0.5959 (-0.5868) time: 1.0382 data: 0.0003 [11-23 21:15:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 834/1669] eta: 0:13:33 tlr: 0.00021 tnm: 0.20 Lm: 6.520 (6.574) Lt: 5.744 (5.828) Accm: 3.28 (3.23) Acct: 4.89 (5.08) proj_loss: -0.6079 (-0.5944) time: 1.0382 data: 0.0003 [11-23 21:15:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 834/1669] eta: 0:13:33 tlr: 0.00021 tnm: 0.20 Lm: 6.492 (6.485) Lt: 5.721 (5.692) Accm: 3.32 (3.32) Acct: 5.37 (5.34) proj_loss: -0.5789 (-0.5722) time: 1.0382 data: 0.0003 [11-23 21:15:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [ 834/1669] eta: 0:13:33 tlr: 0.00021 tnm: 0.20 Lm: 6.559 (6.523) Lt: 5.754 (5.773) Accm: 3.29 (3.21) Acct: 5.41 (5.04) proj_loss: -0.5895 (-0.5913) time: 1.0382 data: 0.0003 [11-23 21:22:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.20 Lm: 6.487 (6.496) Lt: 5.716 (5.749) Accm: 3.45 (3.31) Acct: 5.41 (5.13) proj_loss: -0.5867 (-0.5877) time: 0.9310 data: 0.0003 [11-23 21:22:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.20 Lm: 6.541 (6.585) Lt: 5.739 (5.813) Accm: 3.23 (3.22) Acct: 5.25 (5.15) proj_loss: -0.5699 (-0.5694) time: 0.9310 data: 0.0003 [11-23 21:22:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.20 Lm: 6.506 (6.460) Lt: 5.728 (5.705) Accm: 3.48 (3.56) Acct: 5.39 (5.44) proj_loss: -0.6102 (-0.6044) time: 0.9310 data: 0.0003 [11-23 21:22:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.20 Lm: 6.597 (6.597) Lt: 5.853 (5.844) Accm: 3.01 (3.05) Acct: 5.11 (5.00) proj_loss: -0.5778 (-0.5778) time: 0.9310 data: 0.0003 [11-23 21:22:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.20 Lm: 6.621 (6.610) Lt: 5.855 (5.845) Accm: 3.27 (3.24) Acct: 5.20 (5.17) proj_loss: -0.5817 (-0.5820) time: 0.9310 data: 0.0003 [11-23 21:22:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.20 Lm: 6.582 (6.629) Lt: 5.817 (5.861) Accm: 2.95 (2.94) Acct: 4.77 (4.72) proj_loss: -0.5858 (-0.5866) time: 0.9310 data: 0.0003 [11-23 21:22:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.20 Lm: 6.438 (6.419) Lt: 5.684 (5.663) Accm: 3.71 (3.85) Acct: 5.54 (6.10) proj_loss: -0.5989 (-0.5877) time: 0.9310 data: 0.0003 [11-23 21:22:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.20 Lm: 6.606 (6.611) Lt: 5.781 (5.807) Accm: 3.18 (3.17) Acct: 5.06 (4.98) proj_loss: -0.5826 (-0.5771) time: 0.9310 data: 0.0003 [11-23 21:28:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.591 (6.562) Lt: 5.769 (5.766) Accm: 3.38 (3.30) Acct: 5.17 (5.13) proj_loss: -0.5781 (-0.5773) time: 0.9322 data: 0.0022 [11-23 21:28:30] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 65/350] Total time: 0:26:44 (0.961 s / it) [11-23 21:28:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.597 (6.632) Lt: 5.904 (5.886) Accm: 2.91 (2.95) Acct: 5.06 (4.84) proj_loss: -0.5767 (-0.5776) time: 0.9322 data: 0.0017 [11-23 21:28:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.444 (6.491) Lt: 5.755 (5.731) Accm: 3.64 (3.64) Acct: 5.20 (5.75) proj_loss: -0.5975 (-0.5860) time: 0.9322 data: 0.0017 [11-23 21:28:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.414 (6.454) Lt: 5.679 (5.700) Accm: 3.60 (3.43) Acct: 5.41 (5.36) proj_loss: -0.5838 (-0.5857) time: 0.9322 data: 0.0018 [11-23 21:28:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.532 (6.574) Lt: 5.756 (5.804) Accm: 3.32 (3.28) Acct: 5.13 (5.08) proj_loss: -0.5789 (-0.5766) time: 0.9322 data: 0.0015 [11-23 21:28:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.569 (6.615) Lt: 5.816 (5.844) Accm: 3.13 (2.98) Acct: 5.13 (4.83) proj_loss: -0.5829 (-0.5840) time: 0.9322 data: 0.0018 [11-23 21:28:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.520 (6.493) Lt: 5.744 (5.732) Accm: 3.28 (3.40) Acct: 4.89 (5.30) proj_loss: -0.6079 (-0.5935) time: 0.9322 data: 0.0015 [11-23 21:28:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 65/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.22 Lm: 6.570 (6.562) Lt: 5.811 (5.804) Accm: 3.45 (3.33) Acct: 5.61 (5.30) proj_loss: -0.5959 (-0.5867) time: 0.9322 data: 0.0018 [11-23 21:28:30] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 65/350] Total time: 0:26:44 (0.961 s / it) [11-23 21:28:30] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 65/350] Total time: 0:26:44 (0.961 s / it) [11-23 21:28:30] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 65/350] Total time: 0:26:44 (0.961 s / it) [11-23 21:28:30] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 65/350] Total time: 0:26:44 (0.961 s / it) [11-23 21:28:30] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 65/350] Total time: 0:26:44 (0.961 s / it) [11-23 21:28:30] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 65/350] Total time: 0:26:44 (0.961 s / it) [11-23 21:28:30] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 65/350] Total time: 0:26:44 (0.961 s / it) [11-23 21:28:30] (/home/user/VAR/train.py , line 276)=> [ep65] (training ) Lm: 6.574 (6.576), Lt: 5.815 (5.819), Acc m&t: 3.20 5.05, Remain: 5 days, 3:49:27, Finish: 2024-11-28 09:17 [11-23 21:28:30] (/home/user/VAR/train.py , line 276)=> [ep65] (training ) Lm: 6.574 (6.576), Lt: 5.815 (5.819), Acc m&t: 3.20 5.05, Remain: 5 days, 3:48:32, Finish: 2024-11-28 09:17 [11-23 21:28:30] (/home/user/VAR/train.py , line 276)=> [ep65] (training ) Lm: 6.574 (6.576), Lt: 5.815 (5.819), Acc m&t: 3.20 5.05, Remain: 5 days, 3:46:56, Finish: 2024-11-28 09:15 [11-23 21:28:30] (/home/user/VAR/train.py , line 276)=> [ep65] (training ) Lm: 6.574 (6.576), Lt: 5.815 (5.819), Acc m&t: 3.20 5.05, Remain: 5 days, 3:45:42, Finish: 2024-11-28 09:14 [11-23 21:28:30] (/home/user/VAR/train.py , line 276)=> [ep65] (training ) Lm: 6.574 (6.576), Lt: 5.815 (5.819), Acc m&t: 3.20 5.05, Remain: 5 days, 3:48:25, Finish: 2024-11-28 09:16 [11-23 21:28:30] (/home/user/VAR/train.py , line 276)=> [ep65] (training ) Lm: 6.574 (6.576), Lt: 5.815 (5.819), Acc m&t: 3.20 5.05, Remain: 5 days, 3:46:48, Finish: 2024-11-28 09:15 [11-23 21:28:30] (/home/user/VAR/train.py , line 276)=> [ep65] (training ) Lm: 6.574 (6.576), Lt: 5.815 (5.819), Acc m&t: 3.20 5.05, Remain: 5 days, 3:46:20, Finish: 2024-11-28 09:14 [11-23 21:28:30] (/home/user/VAR/train.py , line 276)=> [ep65] (training ) Lm: 6.574 (6.576), Lt: 5.815 (5.819), Acc m&t: 3.20 5.05, Remain: 5 days, 3:50:07, Finish: 2024-11-28 09:18 [11-23 21:28:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 0/1669] eta: 0:25:47 tlr: 0.00021 tnm: 0.22 Lm: 6.726 (6.726) Lt: 6.048 (6.048) Accm: 2.96 (2.96) Acct: 4.79 (4.79) proj_loss: -0.5680 (-0.5680) time: 0.9270 data: 0.0003 [11-23 21:28:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 0/1669] eta: 0:25:50 tlr: 0.00021 tnm: 0.22 Lm: 6.605 (6.605) Lt: 5.848 (5.848) Accm: 3.22 (3.22) Acct: 5.34 (5.34) proj_loss: -0.6218 (-0.6218) time: 0.9293 data: 0.0004 [11-23 21:28:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 0/1669] eta: 0:25:50 tlr: 0.00021 tnm: 0.22 Lm: 6.720 (6.720) Lt: 5.954 (5.954) Accm: 2.56 (2.56) Acct: 3.99 (3.99) proj_loss: -0.5777 (-0.5777) time: 0.9292 data: 0.0003 [11-23 21:28:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 0/1669] eta: 0:25:51 tlr: 0.00021 tnm: 0.22 Lm: 6.677 (6.677) Lt: 5.962 (5.962) Accm: 2.81 (2.81) Acct: 4.61 (4.61) proj_loss: -0.5829 (-0.5829) time: 0.9295 data: 0.0004 [11-23 21:28:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 0/1669] eta: 0:25:51 tlr: 0.00021 tnm: 0.22 Lm: 6.669 (6.669) Lt: 5.917 (5.917) Accm: 2.64 (2.64) Acct: 4.20 (4.20) proj_loss: -0.6243 (-0.6243) time: 0.9293 data: 0.0004 [11-23 21:28:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 0/1669] eta: 0:25:51 tlr: 0.00021 tnm: 0.22 Lm: 6.505 (6.505) Lt: 5.768 (5.768) Accm: 3.47 (3.47) Acct: 5.51 (5.51) proj_loss: -0.5964 (-0.5964) time: 0.9295 data: 0.0004 [11-23 21:28:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 0/1669] eta: 0:25:51 tlr: 0.00021 tnm: 0.22 Lm: 6.406 (6.406) Lt: 5.593 (5.593) Accm: 3.47 (3.47) Acct: 5.79 (5.79) proj_loss: -0.5696 (-0.5696) time: 0.9296 data: 0.0004 [11-23 21:28:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 0/1669] eta: 0:25:51 tlr: 0.00021 tnm: 0.22 Lm: 6.348 (6.348) Lt: 5.548 (5.548) Accm: 3.70 (3.70) Acct: 5.44 (5.44) proj_loss: -0.6050 (-0.6050) time: 0.9298 data: 0.0004 [11-23 21:34:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 417/1669] eta: 0:19:26 tlr: 0.00021 tnm: 0.21 Lm: 6.608 (6.608) Lt: 5.829 (5.829) Accm: 3.04 (3.04) Acct: 4.67 (4.67) proj_loss: -0.5817 (-0.5817) time: 0.9314 data: 0.0003 [11-23 21:34:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 417/1669] eta: 0:19:26 tlr: 0.00021 tnm: 0.21 Lm: 6.536 (6.536) Lt: 5.793 (5.793) Accm: 3.40 (3.40) Acct: 5.20 (5.20) proj_loss: -0.6073 (-0.6073) time: 0.9313 data: 0.0003 [11-23 21:34:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 417/1669] eta: 0:19:26 tlr: 0.00021 tnm: 0.21 Lm: 6.670 (6.670) Lt: 5.920 (5.920) Accm: 2.72 (2.72) Acct: 4.05 (4.05) proj_loss: -0.5802 (-0.5802) time: 0.9314 data: 0.0003 [11-23 21:34:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 417/1669] eta: 0:19:26 tlr: 0.00021 tnm: 0.21 Lm: 6.683 (6.683) Lt: 5.972 (5.972) Accm: 2.81 (2.81) Acct: 4.80 (4.80) proj_loss: -0.5813 (-0.5813) time: 0.9314 data: 0.0003 [11-23 21:34:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 417/1669] eta: 0:19:26 tlr: 0.00021 tnm: 0.21 Lm: 6.395 (6.395) Lt: 5.570 (5.570) Accm: 3.80 (3.80) Acct: 6.06 (6.06) proj_loss: -0.6063 (-0.6063) time: 0.9314 data: 0.0003 [11-23 21:34:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 417/1669] eta: 0:19:26 tlr: 0.00021 tnm: 0.21 Lm: 6.636 (6.636) Lt: 5.891 (5.891) Accm: 3.07 (3.07) Acct: 4.86 (4.86) proj_loss: -0.5854 (-0.5854) time: 0.9313 data: 0.0003 [11-23 21:34:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 417/1669] eta: 0:19:26 tlr: 0.00021 tnm: 0.21 Lm: 6.687 (6.687) Lt: 5.955 (5.955) Accm: 2.81 (2.81) Acct: 4.58 (4.58) proj_loss: -0.5787 (-0.5787) time: 0.9314 data: 0.0003 [11-23 21:34:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 417/1669] eta: 0:19:26 tlr: 0.00021 tnm: 0.21 Lm: 6.441 (6.441) Lt: 5.645 (5.645) Accm: 3.52 (3.52) Acct: 5.72 (5.72) proj_loss: -0.5793 (-0.5793) time: 0.9313 data: 0.0004 [11-23 21:41:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.23 Lm: 6.476 (6.499) Lt: 5.697 (5.717) Accm: 3.47 (3.40) Acct: 5.65 (5.50) proj_loss: -0.5827 (-0.5804) time: 0.9317 data: 0.0003 [11-23 21:41:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.23 Lm: 6.640 (6.621) Lt: 5.897 (5.905) Accm: 2.96 (2.94) Acct: 4.82 (4.94) proj_loss: -0.5853 (-0.5827) time: 0.9316 data: 0.0003 [11-23 21:41:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.23 Lm: 6.670 (6.700) Lt: 5.923 (5.992) Accm: 2.64 (2.65) Acct: 3.89 (3.91) proj_loss: -0.5747 (-0.5784) time: 0.9317 data: 0.0003 [11-23 21:41:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.23 Lm: 6.524 (6.438) Lt: 5.761 (5.634) Accm: 3.32 (3.64) Acct: 5.58 (5.90) proj_loss: -0.6007 (-0.6044) time: 0.9317 data: 0.0003 [11-23 21:41:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.23 Lm: 6.348 (6.488) Lt: 5.548 (5.697) Accm: 3.70 (3.35) Acct: 5.44 (5.23) proj_loss: -0.5788 (-0.5808) time: 0.9316 data: 0.0003 [11-23 21:41:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.23 Lm: 6.522 (6.531) Lt: 5.768 (5.747) Accm: 3.41 (3.40) Acct: 5.48 (5.29) proj_loss: -0.5964 (-0.5958) time: 0.9317 data: 0.0003 [11-23 21:41:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.23 Lm: 6.655 (6.656) Lt: 5.954 (5.919) Accm: 2.99 (2.87) Acct: 4.86 (4.67) proj_loss: -0.5797 (-0.5837) time: 0.9317 data: 0.0003 [11-23 21:41:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.23 Lm: 6.595 (6.617) Lt: 5.853 (5.879) Accm: 2.91 (3.02) Acct: 4.61 (4.76) proj_loss: -0.5829 (-0.5800) time: 0.9317 data: 0.0003 [11-23 21:47:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.587 (6.538) Lt: 5.837 (5.778) Accm: 3.12 (3.24) Acct: 4.86 (5.08) proj_loss: -0.5789 (-0.5787) time: 0.9316 data: 0.0003 [11-23 21:47:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.670 (6.614) Lt: 5.920 (5.876) Accm: 2.72 (2.83) Acct: 4.05 (4.31) proj_loss: -0.5810 (-0.5806) time: 0.9316 data: 0.0003 [11-23 21:47:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.526 (6.531) Lt: 5.763 (5.750) Accm: 3.44 (3.46) Acct: 5.49 (5.41) proj_loss: -0.5871 (-0.5913) time: 0.9316 data: 0.0003 [11-23 21:47:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.302 (6.430) Lt: 5.509 (5.640) Accm: 3.84 (3.59) Acct: 5.91 (5.58) proj_loss: -0.5911 (-0.5864) time: 0.9316 data: 0.0003 [11-23 21:47:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.569 (6.585) Lt: 5.834 (5.846) Accm: 3.08 (3.06) Acct: 5.01 (5.00) proj_loss: -0.5767 (-0.5777) time: 0.9316 data: 0.0003 [11-23 21:47:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.449 (6.422) Lt: 5.657 (5.613) Accm: 3.58 (3.69) Acct: 5.60 (5.83) proj_loss: -0.5958 (-0.5943) time: 0.9316 data: 0.0003 [11-23 21:47:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.545 (6.545) Lt: 5.779 (5.797) Accm: 3.31 (3.31) Acct: 5.35 (5.23) proj_loss: -0.5858 (-0.5913) time: 0.9316 data: 0.0003 [11-23 21:47:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.624 (6.553) Lt: 5.901 (5.799) Accm: 3.02 (3.34) Acct: 5.01 (5.28) proj_loss: -0.5787 (-0.5804) time: 0.9316 data: 0.0003 [11-23 21:55:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.593 (6.549) Lt: 5.848 (5.794) Accm: 3.06 (3.40) Acct: 5.17 (5.37) proj_loss: -0.5777 (-0.5762) time: 0.9318 data: 0.0017 [11-23 21:55:08] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 66/350] Total time: 0:26:37 (0.957 s / it) [11-23 21:55:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.373 (6.407) Lt: 5.556 (5.602) Accm: 3.61 (3.67) Acct: 5.61 (5.81) proj_loss: -0.5909 (-0.5918) time: 0.9318 data: 0.0017 [11-23 21:55:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.670 (6.641) Lt: 5.923 (5.905) Accm: 2.78 (2.82) Acct: 4.17 (4.28) proj_loss: -0.5873 (-0.5825) time: 0.9318 data: 0.0017 [11-23 21:55:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.348 (6.474) Lt: 5.548 (5.692) Accm: 3.70 (3.51) Acct: 5.44 (5.39) proj_loss: -0.5799 (-0.5851) time: 0.9318 data: 0.0016 [11-23 21:55:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.640 (6.650) Lt: 5.897 (5.923) Accm: 2.96 (2.85) Acct: 4.82 (4.66) proj_loss: -0.5680 (-0.5721) time: 0.9318 data: 0.0014 [11-23 21:55:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.614 (6.567) Lt: 5.861 (5.821) Accm: 3.16 (3.23) Acct: 5.06 (5.08) proj_loss: -0.5827 (-0.5896) time: 0.9318 data: 0.0020 [11-23 21:55:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.579 (6.544) Lt: 5.821 (5.777) Accm: 2.91 (3.14) Acct: 4.61 (4.88) proj_loss: -0.5829 (-0.5850) time: 0.9318 data: 0.0020 [11-23 21:55:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 66/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.530 (6.556) Lt: 5.768 (5.779) Accm: 3.41 (3.34) Acct: 5.48 (5.31) proj_loss: -0.5778 (-0.5842) time: 0.9318 data: 0.0020 [11-23 21:55:08] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 66/350] Total time: 0:26:37 (0.957 s / it) [11-23 21:55:08] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 66/350] Total time: 0:26:37 (0.957 s / it) [11-23 21:55:08] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 66/350] Total time: 0:26:37 (0.957 s / it) [11-23 21:55:08] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 66/350] Total time: 0:26:37 (0.957 s / it) [11-23 21:55:08] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 66/350] Total time: 0:26:37 (0.957 s / it) [11-23 21:55:08] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 66/350] Total time: 0:26:37 (0.957 s / it) [11-23 21:55:08] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 66/350] Total time: 0:26:37 (0.957 s / it) [11-23 21:55:08] (/home/user/VAR/train.py , line 276)=> [ep66] (training ) Lm: 6.574 (6.575), Lt: 5.815 (5.822), Acc m&t: 3.20 5.05, Remain: 5 days, 3:06:21, Finish: 2024-11-28 09:01 [11-23 21:55:08] (/home/user/VAR/train.py , line 276)=> [ep66] (training ) Lm: 6.574 (6.575), Lt: 5.815 (5.822), Acc m&t: 3.20 5.05, Remain: 5 days, 3:04:21, Finish: 2024-11-28 08:59 [11-23 21:55:08] (/home/user/VAR/train.py , line 276)=> [ep66] (training ) Lm: 6.574 (6.575), Lt: 5.815 (5.822), Acc m&t: 3.20 5.05, Remain: 5 days, 3:07:16, Finish: 2024-11-28 09:02 [11-23 21:55:08] (/home/user/VAR/train.py , line 276)=> [ep66] (training ) Lm: 6.574 (6.575), Lt: 5.815 (5.822), Acc m&t: 3.20 5.05, Remain: 5 days, 3:06:30, Finish: 2024-11-28 09:01 [11-23 21:55:08] (/home/user/VAR/train.py , line 276)=> [ep66] (training ) Lm: 6.574 (6.575), Lt: 5.815 (5.822), Acc m&t: 3.20 5.05, Remain: 5 days, 3:05:02, Finish: 2024-11-28 09:00 [11-23 21:55:08] (/home/user/VAR/train.py , line 276)=> [ep66] (training ) Lm: 6.574 (6.575), Lt: 5.815 (5.822), Acc m&t: 3.20 5.05, Remain: 5 days, 3:04:45, Finish: 2024-11-28 08:59 [11-23 21:55:08] (/home/user/VAR/train.py , line 276)=> [ep66] (training ) Lm: 6.574 (6.575), Lt: 5.815 (5.822), Acc m&t: 3.20 5.05, Remain: 5 days, 3:07:51, Finish: 2024-11-28 09:02 [11-23 21:55:08] (/home/user/VAR/train.py , line 276)=> [ep66] (training ) Lm: 6.574 (6.575), Lt: 5.815 (5.822), Acc m&t: 3.20 5.05, Remain: 5 days, 3:05:51, Finish: 2024-11-28 09:00 [11-23 21:55:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 0/1669] eta: 0:24:59 tlr: 0.00021 tnm: 0.20 Lm: 6.639 (6.639) Lt: 5.882 (5.882) Accm: 2.90 (2.90) Acct: 4.65 (4.65) proj_loss: -0.5659 (-0.5659) time: 0.8984 data: 0.0003 [11-23 21:55:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 0/1669] eta: 0:24:53 tlr: 0.00021 tnm: 0.20 Lm: 6.792 (6.792) Lt: 6.165 (6.165) Accm: 2.42 (2.42) Acct: 3.37 (3.37) proj_loss: -0.6157 (-0.6157) time: 0.8948 data: 0.0004 [11-23 21:55:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 0/1669] eta: 0:24:53 tlr: 0.00021 tnm: 0.20 Lm: 6.503 (6.503) Lt: 5.679 (5.679) Accm: 3.51 (3.51) Acct: 5.44 (5.44) proj_loss: -0.6012 (-0.6012) time: 0.8948 data: 0.0004 [11-23 21:55:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 0/1669] eta: 0:24:53 tlr: 0.00021 tnm: 0.20 Lm: 6.617 (6.617) Lt: 5.867 (5.867) Accm: 2.71 (2.71) Acct: 4.13 (4.13) proj_loss: -0.5892 (-0.5892) time: 0.8951 data: 0.0004 [11-23 21:55:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 0/1669] eta: 0:24:54 tlr: 0.00021 tnm: 0.20 Lm: 6.547 (6.547) Lt: 5.820 (5.820) Accm: 3.54 (3.54) Acct: 5.61 (5.61) proj_loss: -0.5956 (-0.5956) time: 0.8953 data: 0.0004 [11-23 21:55:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 0/1669] eta: 0:24:54 tlr: 0.00021 tnm: 0.20 Lm: 6.411 (6.411) Lt: 5.632 (5.632) Accm: 3.63 (3.63) Acct: 5.61 (5.61) proj_loss: -0.5744 (-0.5744) time: 0.8952 data: 0.0004 [11-23 21:55:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 0/1669] eta: 0:24:54 tlr: 0.00021 tnm: 0.20 Lm: 6.821 (6.821) Lt: 6.129 (6.129) Accm: 2.37 (2.37) Acct: 3.93 (3.93) proj_loss: -0.6158 (-0.6158) time: 0.8953 data: 0.0004 [11-23 21:55:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 0/1669] eta: 0:24:55 tlr: 0.00021 tnm: 0.20 Lm: 6.594 (6.594) Lt: 5.875 (5.875) Accm: 3.04 (3.04) Acct: 4.86 (4.86) proj_loss: -0.5513 (-0.5513) time: 0.8963 data: 0.0004 [11-23 22:01:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 417/1669] eta: 0:19:32 tlr: 0.00021 tnm: 0.20 Lm: 6.504 (6.504) Lt: 5.762 (5.762) Accm: 3.08 (3.08) Acct: 4.82 (4.82) proj_loss: -0.5482 (-0.5482) time: 0.9303 data: 0.0003 [11-23 22:01:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 417/1669] eta: 0:19:32 tlr: 0.00021 tnm: 0.20 Lm: 6.538 (6.538) Lt: 5.714 (5.714) Accm: 3.33 (3.33) Acct: 5.48 (5.48) proj_loss: -0.5695 (-0.5695) time: 0.9303 data: 0.0003 [11-23 22:01:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 417/1669] eta: 0:19:32 tlr: 0.00021 tnm: 0.20 Lm: 6.585 (6.585) Lt: 5.890 (5.890) Accm: 3.05 (3.05) Acct: 4.48 (4.48) proj_loss: -0.5989 (-0.5989) time: 0.9303 data: 0.0003 [11-23 22:01:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 417/1669] eta: 0:19:32 tlr: 0.00021 tnm: 0.20 Lm: 6.583 (6.583) Lt: 5.814 (5.814) Accm: 2.96 (2.96) Acct: 4.75 (4.75) proj_loss: -0.5759 (-0.5759) time: 0.9303 data: 0.0003 [11-23 22:01:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 417/1669] eta: 0:19:32 tlr: 0.00021 tnm: 0.20 Lm: 6.529 (6.529) Lt: 5.781 (5.781) Accm: 3.03 (3.03) Acct: 4.86 (4.86) proj_loss: -0.5838 (-0.5838) time: 0.9303 data: 0.0003 [11-23 22:01:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 417/1669] eta: 0:19:32 tlr: 0.00021 tnm: 0.20 Lm: 6.696 (6.696) Lt: 5.981 (5.981) Accm: 2.70 (2.70) Acct: 4.30 (4.30) proj_loss: -0.6031 (-0.6031) time: 0.9303 data: 0.0003 [11-23 22:01:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 417/1669] eta: 0:19:32 tlr: 0.00021 tnm: 0.20 Lm: 6.559 (6.559) Lt: 5.800 (5.800) Accm: 3.15 (3.15) Acct: 4.61 (4.61) proj_loss: -0.5963 (-0.5963) time: 0.9303 data: 0.0003 [11-23 22:01:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 417/1669] eta: 0:19:32 tlr: 0.00021 tnm: 0.20 Lm: 6.562 (6.562) Lt: 5.835 (5.835) Accm: 3.45 (3.45) Acct: 5.25 (5.25) proj_loss: -0.5952 (-0.5952) time: 0.9303 data: 0.0003 [11-23 22:08:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 834/1669] eta: 0:12:59 tlr: 0.00021 tnm: 0.20 Lm: 6.576 (6.572) Lt: 5.846 (5.839) Accm: 3.35 (3.34) Acct: 4.89 (5.13) proj_loss: -0.5956 (-0.5968) time: 0.9296 data: 0.0003 [11-23 22:08:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 834/1669] eta: 0:12:59 tlr: 0.00021 tnm: 0.20 Lm: 6.639 (6.677) Lt: 5.882 (5.912) Accm: 2.90 (2.80) Acct: 4.65 (4.47) proj_loss: -0.5859 (-0.5826) time: 0.9296 data: 0.0003 [11-23 22:08:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 834/1669] eta: 0:12:59 tlr: 0.00021 tnm: 0.20 Lm: 6.515 (6.561) Lt: 5.728 (5.836) Accm: 3.32 (3.14) Acct: 5.27 (4.74) proj_loss: -0.5820 (-0.5915) time: 0.9296 data: 0.0003 [11-23 22:08:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 834/1669] eta: 0:12:59 tlr: 0.00021 tnm: 0.20 Lm: 6.441 (6.483) Lt: 5.695 (5.708) Accm: 3.35 (3.16) Acct: 5.58 (5.15) proj_loss: -0.5784 (-0.5764) time: 0.9296 data: 0.0003 [11-23 22:08:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 834/1669] eta: 0:12:59 tlr: 0.00021 tnm: 0.20 Lm: 6.513 (6.507) Lt: 5.716 (5.747) Accm: 3.12 (3.22) Acct: 4.86 (5.15) proj_loss: -0.5513 (-0.5617) time: 0.9296 data: 0.0003 [11-23 22:08:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 834/1669] eta: 0:12:59 tlr: 0.00021 tnm: 0.20 Lm: 6.614 (6.577) Lt: 5.812 (5.804) Accm: 3.35 (3.21) Acct: 5.44 (4.89) proj_loss: -0.6012 (-0.6008) time: 0.9296 data: 0.0003 [11-23 22:08:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 834/1669] eta: 0:12:59 tlr: 0.00021 tnm: 0.20 Lm: 6.572 (6.650) Lt: 5.840 (5.934) Accm: 3.02 (2.94) Acct: 4.68 (4.68) proj_loss: -0.5905 (-0.5976) time: 0.9296 data: 0.0003 [11-23 22:08:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [ 834/1669] eta: 0:12:59 tlr: 0.00021 tnm: 0.20 Lm: 6.579 (6.552) Lt: 5.796 (5.757) Accm: 3.03 (3.22) Acct: 5.34 (5.12) proj_loss: -0.5744 (-0.5885) time: 0.9296 data: 0.0003 [11-23 22:14:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.573 (6.556) Lt: 5.804 (5.770) Accm: 3.09 (3.21) Acct: 5.01 (5.01) proj_loss: -0.5774 (-0.5865) time: 0.9298 data: 0.0003 [11-23 22:14:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.529 (6.538) Lt: 5.781 (5.775) Accm: 3.03 (2.99) Acct: 4.86 (4.81) proj_loss: -0.5796 (-0.5775) time: 0.9298 data: 0.0003 [11-23 22:14:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.626 (6.660) Lt: 5.882 (5.905) Accm: 2.96 (2.93) Acct: 4.75 (4.61) proj_loss: -0.5788 (-0.5799) time: 0.9298 data: 0.0003 [11-23 22:14:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.614 (6.639) Lt: 5.867 (5.885) Accm: 3.07 (3.02) Acct: 4.65 (4.63) proj_loss: -0.5963 (-0.5961) time: 0.9298 data: 0.0003 [11-23 22:14:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.553 (6.545) Lt: 5.796 (5.788) Accm: 3.10 (3.19) Acct: 4.94 (5.12) proj_loss: -0.5533 (-0.5601) time: 0.9298 data: 0.0003 [11-23 22:14:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.576 (6.580) Lt: 5.807 (5.849) Accm: 3.10 (3.08) Acct: 4.96 (4.72) proj_loss: -0.5810 (-0.5886) time: 0.9298 data: 0.0003 [11-23 22:14:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.585 (6.578) Lt: 5.833 (5.830) Accm: 3.23 (3.26) Acct: 4.89 (4.98) proj_loss: -0.5952 (-0.5913) time: 0.9298 data: 0.0003 [11-23 22:14:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.619 (6.654) Lt: 5.913 (5.947) Accm: 3.08 (2.99) Acct: 4.86 (4.77) proj_loss: -0.5997 (-0.6004) time: 0.9298 data: 0.0003 [11-23 22:21:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.666 (6.658) Lt: 5.927 (5.943) Accm: 3.02 (2.95) Acct: 4.68 (4.66) proj_loss: -0.5905 (-0.5954) time: 0.9356 data: 0.0018 [11-23 22:21:04] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 67/350] Total time: 0:25:56 (0.933 s / it) [11-23 22:21:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.637 (6.603) Lt: 5.887 (5.875) Accm: 2.88 (3.00) Acct: 4.65 (4.57) proj_loss: -0.5820 (-0.5878) time: 0.9356 data: 0.0016 [11-23 22:21:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.612 (6.650) Lt: 5.882 (5.881) Accm: 2.90 (2.91) Acct: 4.86 (4.75) proj_loss: -0.5717 (-0.5779) time: 0.9356 data: 0.0019 [11-23 22:21:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.614 (6.587) Lt: 5.812 (5.833) Accm: 3.35 (3.12) Acct: 5.44 (4.82) proj_loss: -0.5942 (-0.5957) time: 0.9356 data: 0.0021 [11-23 22:21:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.568 (6.535) Lt: 5.796 (5.770) Accm: 3.15 (3.23) Acct: 5.06 (5.02) proj_loss: -0.5804 (-0.5855) time: 0.9356 data: 0.0018 [11-23 22:21:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.594 (6.586) Lt: 5.846 (5.840) Accm: 3.12 (3.18) Acct: 4.89 (4.85) proj_loss: -0.5948 (-0.5873) time: 0.9356 data: 0.0017 [11-23 22:21:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.513 (6.477) Lt: 5.716 (5.708) Accm: 3.12 (3.41) Acct: 5.03 (5.45) proj_loss: -0.5553 (-0.5649) time: 0.9356 data: 0.0019 [11-23 22:21:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 67/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.580 (6.547) Lt: 5.812 (5.782) Accm: 3.21 (3.03) Acct: 5.17 (4.88) proj_loss: -0.5808 (-0.5818) time: 0.9356 data: 0.0018 [11-23 22:21:04] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 67/350] Total time: 0:25:56 (0.933 s / it) [11-23 22:21:04] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 67/350] Total time: 0:25:56 (0.933 s / it) [11-23 22:21:04] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 67/350] Total time: 0:25:56 (0.933 s / it) [11-23 22:21:04] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 67/350] Total time: 0:25:56 (0.933 s / it) [11-23 22:21:04] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 67/350] Total time: 0:25:56 (0.933 s / it) [11-23 22:21:04] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 67/350] Total time: 0:25:56 (0.933 s / it) [11-23 22:21:04] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 67/350] Total time: 0:25:56 (0.933 s / it) [11-23 22:21:04] (/home/user/VAR/train.py , line 276)=> [ep67] (training ) Lm: 6.573 (6.573), Lt: 5.815 (5.822), Acc m&t: 3.20 5.05, Remain: 5 days, 3:19:53, Finish: 2024-11-28 09:40 [11-23 22:21:04] (/home/user/VAR/train.py , line 276)=> [ep67] (training ) Lm: 6.573 (6.573), Lt: 5.815 (5.822), Acc m&t: 3.20 5.05, Remain: 5 days, 3:20:12, Finish: 2024-11-28 09:41 [11-23 22:21:04] (/home/user/VAR/train.py , line 276)=> [ep67] (training ) Lm: 6.573 (6.573), Lt: 5.815 (5.822), Acc m&t: 3.20 5.05, Remain: 5 days, 3:19:46, Finish: 2024-11-28 09:40 [11-23 22:21:04] (/home/user/VAR/train.py , line 276)=> [ep67] (training ) Lm: 6.573 (6.573), Lt: 5.815 (5.822), Acc m&t: 3.20 5.05, Remain: 5 days, 3:22:28, Finish: 2024-11-28 09:43 [11-23 22:21:04] (/home/user/VAR/train.py , line 276)=> [ep67] (training ) Lm: 6.573 (6.573), Lt: 5.815 (5.822), Acc m&t: 3.20 5.05, Remain: 5 days, 3:21:42, Finish: 2024-11-28 09:42 [11-23 22:21:04] (/home/user/VAR/train.py , line 276)=> [ep67] (training ) Lm: 6.573 (6.573), Lt: 5.815 (5.822), Acc m&t: 3.20 5.05, Remain: 5 days, 3:21:06, Finish: 2024-11-28 09:42 [11-23 22:21:04] (/home/user/VAR/train.py , line 276)=> [ep67] (training ) Lm: 6.573 (6.573), Lt: 5.815 (5.822), Acc m&t: 3.20 5.05, Remain: 5 days, 3:21:26, Finish: 2024-11-28 09:42 [11-23 22:21:04] (/home/user/VAR/train.py , line 276)=> [ep67] (training ) Lm: 6.573 (6.573), Lt: 5.815 (5.822), Acc m&t: 3.20 5.05, Remain: 5 days, 3:20:05, Finish: 2024-11-28 09:41 [11-23 22:21:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 0/1669] eta: 0:25:07 tlr: 0.00021 tnm: 0.22 Lm: 6.396 (6.396) Lt: 5.619 (5.619) Accm: 3.58 (3.58) Acct: 4.99 (4.99) proj_loss: -0.5904 (-0.5904) time: 0.9035 data: 0.0004 [11-23 22:21:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 0/1669] eta: 0:25:09 tlr: 0.00021 tnm: 0.22 Lm: 6.733 (6.733) Lt: 5.929 (5.929) Accm: 2.80 (2.80) Acct: 4.24 (4.24) proj_loss: -0.5603 (-0.5603) time: 0.9044 data: 0.0004 [11-23 22:21:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 0/1669] eta: 0:25:09 tlr: 0.00021 tnm: 0.22 Lm: 6.751 (6.751) Lt: 6.044 (6.044) Accm: 2.91 (2.91) Acct: 4.51 (4.51) proj_loss: -0.5810 (-0.5810) time: 0.9047 data: 0.0004 [11-23 22:21:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 0/1669] eta: 0:25:10 tlr: 0.00021 tnm: 0.22 Lm: 6.474 (6.474) Lt: 5.630 (5.630) Accm: 3.96 (3.96) Acct: 6.44 (6.44) proj_loss: -0.6019 (-0.6019) time: 0.9048 data: 0.0004 [11-23 22:21:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 0/1669] eta: 0:25:15 tlr: 0.00021 tnm: 0.22 Lm: 6.489 (6.489) Lt: 5.752 (5.752) Accm: 3.22 (3.22) Acct: 5.10 (5.10) proj_loss: -0.5680 (-0.5680) time: 0.9079 data: 0.0004 [11-23 22:21:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 0/1669] eta: 0:25:10 tlr: 0.00021 tnm: 0.22 Lm: 6.690 (6.690) Lt: 5.921 (5.921) Accm: 2.99 (2.99) Acct: 4.72 (4.72) proj_loss: -0.5820 (-0.5820) time: 0.9050 data: 0.0004 [11-23 22:21:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 0/1669] eta: 0:25:10 tlr: 0.00021 tnm: 0.22 Lm: 6.717 (6.717) Lt: 5.988 (5.988) Accm: 2.94 (2.94) Acct: 4.37 (4.37) proj_loss: -0.6127 (-0.6127) time: 0.9049 data: 0.0004 [11-23 22:21:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 0/1669] eta: 0:25:21 tlr: 0.00021 tnm: 0.22 Lm: 6.471 (6.471) Lt: 5.767 (5.767) Accm: 3.18 (3.18) Acct: 5.03 (5.03) proj_loss: -0.6032 (-0.6032) time: 0.9115 data: 0.0003 [11-23 22:27:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 417/1669] eta: 0:20:18 tlr: 0.00021 tnm: 0.22 Lm: 6.648 (6.648) Lt: 5.920 (5.920) Accm: 2.89 (2.89) Acct: 4.63 (4.63) proj_loss: -0.5955 (-0.5955) time: 0.9324 data: 0.0003 [11-23 22:27:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 417/1669] eta: 0:20:18 tlr: 0.00021 tnm: 0.22 Lm: 6.602 (6.602) Lt: 5.795 (5.795) Accm: 3.23 (3.23) Acct: 5.04 (5.04) proj_loss: -0.5787 (-0.5787) time: 0.9324 data: 0.0003 [11-23 22:27:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 417/1669] eta: 0:20:18 tlr: 0.00021 tnm: 0.22 Lm: 6.457 (6.457) Lt: 5.642 (5.642) Accm: 3.53 (3.53) Acct: 5.27 (5.27) proj_loss: -0.5690 (-0.5690) time: 0.9324 data: 0.0003 [11-23 22:27:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 417/1669] eta: 0:20:18 tlr: 0.00021 tnm: 0.22 Lm: 6.676 (6.676) Lt: 5.913 (5.913) Accm: 3.04 (3.04) Acct: 4.91 (4.91) proj_loss: -0.6103 (-0.6103) time: 0.9324 data: 0.0003 [11-23 22:27:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 417/1669] eta: 0:20:18 tlr: 0.00021 tnm: 0.22 Lm: 6.533 (6.533) Lt: 5.751 (5.751) Accm: 3.62 (3.62) Acct: 5.61 (5.61) proj_loss: -0.5984 (-0.5984) time: 0.9324 data: 0.0003 [11-23 22:27:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 417/1669] eta: 0:20:18 tlr: 0.00021 tnm: 0.22 Lm: 6.563 (6.563) Lt: 5.798 (5.798) Accm: 3.37 (3.37) Acct: 5.17 (5.17) proj_loss: -0.6008 (-0.6008) time: 0.9324 data: 0.0003 [11-23 22:27:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 417/1669] eta: 0:20:18 tlr: 0.00021 tnm: 0.22 Lm: 6.602 (6.602) Lt: 5.842 (5.842) Accm: 3.03 (3.03) Acct: 4.91 (4.91) proj_loss: -0.5701 (-0.5701) time: 0.9324 data: 0.0003 [11-23 22:27:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 417/1669] eta: 0:20:18 tlr: 0.00021 tnm: 0.22 Lm: 6.544 (6.544) Lt: 5.786 (5.786) Accm: 3.45 (3.45) Acct: 5.34 (5.34) proj_loss: -0.5782 (-0.5782) time: 0.9324 data: 0.0003 [11-23 22:34:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 834/1669] eta: 0:13:22 tlr: 0.00021 tnm: 0.21 Lm: 6.690 (6.603) Lt: 5.921 (5.844) Accm: 2.99 (3.18) Acct: 4.72 (4.92) proj_loss: -0.5820 (-0.5797) time: 0.9317 data: 0.0003 [11-23 22:34:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 834/1669] eta: 0:13:22 tlr: 0.00021 tnm: 0.21 Lm: 6.685 (6.604) Lt: 5.938 (5.844) Accm: 2.99 (3.24) Acct: 4.61 (4.98) proj_loss: -0.5888 (-0.5953) time: 0.9317 data: 0.0003 [11-23 22:34:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 834/1669] eta: 0:13:22 tlr: 0.00021 tnm: 0.21 Lm: 6.518 (6.490) Lt: 5.664 (5.703) Accm: 3.47 (3.44) Acct: 5.03 (5.19) proj_loss: -0.5904 (-0.5804) time: 0.9317 data: 0.0003 [11-23 22:34:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 834/1669] eta: 0:13:22 tlr: 0.00021 tnm: 0.21 Lm: 6.611 (6.655) Lt: 5.808 (5.878) Accm: 3.04 (3.04) Acct: 5.30 (5.05) proj_loss: -0.5810 (-0.5972) time: 0.9317 data: 0.0003 [11-23 22:34:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 834/1669] eta: 0:13:22 tlr: 0.00021 tnm: 0.21 Lm: 6.527 (6.531) Lt: 5.735 (5.746) Accm: 3.39 (3.55) Acct: 5.58 (5.60) proj_loss: -0.6019 (-0.6020) time: 0.9317 data: 0.0003 [11-23 22:34:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 834/1669] eta: 0:13:22 tlr: 0.00021 tnm: 0.21 Lm: 6.679 (6.628) Lt: 5.931 (5.887) Accm: 2.84 (2.93) Acct: 4.72 (4.68) proj_loss: -0.5722 (-0.5796) time: 0.9317 data: 0.0003 [11-23 22:34:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 834/1669] eta: 0:13:22 tlr: 0.00021 tnm: 0.21 Lm: 6.693 (6.632) Lt: 5.929 (5.857) Accm: 3.06 (3.18) Acct: 4.58 (4.89) proj_loss: -0.5971 (-0.5858) time: 0.9317 data: 0.0003 [11-23 22:34:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [ 834/1669] eta: 0:13:22 tlr: 0.00021 tnm: 0.21 Lm: 6.623 (6.640) Lt: 5.810 (5.883) Accm: 2.68 (2.82) Acct: 4.24 (4.44) proj_loss: -0.6032 (-0.5984) time: 0.9317 data: 0.0003 [11-23 22:41:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.21 Lm: 6.580 (6.614) Lt: 5.788 (5.854) Accm: 2.93 (2.91) Acct: 4.63 (4.66) proj_loss: -0.6025 (-0.5993) time: 0.9321 data: 0.0003 [11-23 22:41:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.21 Lm: 6.537 (6.519) Lt: 5.746 (5.737) Accm: 3.37 (3.31) Acct: 5.01 (5.00) proj_loss: -0.5707 (-0.5730) time: 0.9321 data: 0.0003 [11-23 22:41:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.21 Lm: 6.675 (6.675) Lt: 5.923 (5.918) Accm: 3.04 (3.04) Acct: 5.11 (5.02) proj_loss: -0.5847 (-0.5950) time: 0.9321 data: 0.0003 [11-23 22:41:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.21 Lm: 6.629 (6.615) Lt: 5.861 (5.841) Accm: 3.29 (3.26) Acct: 5.18 (5.11) proj_loss: -0.5986 (-0.5899) time: 0.9321 data: 0.0003 [11-23 22:41:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.21 Lm: 6.604 (6.584) Lt: 5.875 (5.836) Accm: 3.17 (3.27) Acct: 4.70 (4.93) proj_loss: -0.5866 (-0.5855) time: 0.9321 data: 0.0003 [11-23 22:41:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.21 Lm: 6.584 (6.568) Lt: 5.842 (5.810) Accm: 3.03 (3.13) Acct: 4.91 (5.03) proj_loss: -0.5701 (-0.5762) time: 0.9321 data: 0.0003 [11-23 22:41:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.21 Lm: 6.649 (6.605) Lt: 5.913 (5.859) Accm: 2.83 (3.06) Acct: 4.41 (4.70) proj_loss: -0.5822 (-0.5821) time: 0.9321 data: 0.0003 [11-23 22:41:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [1251/1669] eta: 0:06:45 tlr: 0.00021 tnm: 0.21 Lm: 6.559 (6.566) Lt: 5.804 (5.784) Accm: 3.34 (3.33) Acct: 5.18 (5.23) proj_loss: -0.5984 (-0.5914) time: 0.9322 data: 0.0003 [11-23 22:47:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.592 (6.585) Lt: 5.872 (5.815) Accm: 3.28 (3.27) Acct: 4.79 (5.14) proj_loss: -0.5948 (-0.5916) time: 0.9316 data: 0.0016 [11-23 22:47:49] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 68/350] Total time: 0:26:44 (0.961 s / it) [11-23 22:47:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.718 (6.684) Lt: 6.037 (5.945) Accm: 3.04 (2.96) Acct: 4.92 (4.84) proj_loss: -0.5883 (-0.5967) time: 0.9316 data: 0.0017 [11-23 22:47:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.518 (6.515) Lt: 5.664 (5.722) Accm: 3.45 (3.34) Acct: 5.03 (5.17) proj_loss: -0.5566 (-0.5697) time: 0.9316 data: 0.0014 [11-23 22:47:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.608 (6.592) Lt: 5.904 (5.854) Accm: 2.99 (3.11) Acct: 4.72 (4.75) proj_loss: -0.5825 (-0.5842) time: 0.9316 data: 0.0016 [11-23 22:47:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.584 (6.571) Lt: 5.828 (5.814) Accm: 3.00 (3.11) Acct: 4.82 (4.99) proj_loss: -0.5680 (-0.5724) time: 0.9316 data: 0.0016 [11-23 22:47:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.623 (6.656) Lt: 5.810 (5.915) Accm: 2.68 (2.75) Acct: 4.24 (4.35) proj_loss: -0.6018 (-0.5989) time: 0.9316 data: 0.0019 [11-23 22:47:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.564 (6.598) Lt: 5.801 (5.833) Accm: 3.06 (3.21) Acct: 4.58 (4.94) proj_loss: -0.6000 (-0.5937) time: 0.9316 data: 0.0019 [11-23 22:47:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 68/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.524 (6.568) Lt: 5.811 (5.812) Accm: 3.35 (3.32) Acct: 4.79 (5.08) proj_loss: -0.5844 (-0.5815) time: 0.9316 data: 0.0016 [11-23 22:47:49] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 68/350] Total time: 0:26:44 (0.961 s / it) [11-23 22:47:49] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 68/350] Total time: 0:26:44 (0.961 s / it) [11-23 22:47:49] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 68/350] Total time: 0:26:44 (0.961 s / it) [11-23 22:47:49] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 68/350] Total time: 0:26:44 (0.961 s / it) [11-23 22:47:49] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 68/350] Total time: 0:26:44 (0.961 s / it) [11-23 22:47:49] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 68/350] Total time: 0:26:44 (0.961 s / it) [11-23 22:47:49] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 68/350] Total time: 0:26:44 (0.961 s / it) [11-23 22:47:49] (/home/user/VAR/train.py , line 276)=> [ep68] (training ) Lm: 6.573 (6.576), Lt: 5.815 (5.820), Acc m&t: 3.20 5.05, Remain: 5 days, 2:09:09, Finish: 2024-11-28 08:56 [11-23 22:47:49] (/home/user/VAR/train.py , line 276)=> [ep68] (training ) Lm: 6.573 (6.576), Lt: 5.815 (5.820), Acc m&t: 3.20 5.05, Remain: 5 days, 2:12:57, Finish: 2024-11-28 09:00 [11-23 22:47:49] (/home/user/VAR/train.py , line 276)=> [ep68] (training ) Lm: 6.573 (6.576), Lt: 5.815 (5.820), Acc m&t: 3.20 5.05, Remain: 5 days, 2:11:38, Finish: 2024-11-28 08:59 [11-23 22:47:49] (/home/user/VAR/train.py , line 276)=> [ep68] (training ) Lm: 6.573 (6.576), Lt: 5.815 (5.820), Acc m&t: 3.20 5.05, Remain: 5 days, 2:08:56, Finish: 2024-11-28 08:56 [11-23 22:47:49] (/home/user/VAR/train.py , line 276)=> [ep68] (training ) Lm: 6.573 (6.576), Lt: 5.815 (5.820), Acc m&t: 3.20 5.05, Remain: 5 days, 2:13:15, Finish: 2024-11-28 09:01 [11-23 22:47:49] (/home/user/VAR/train.py , line 276)=> [ep68] (training ) Lm: 6.573 (6.576), Lt: 5.815 (5.820), Acc m&t: 3.20 5.05, Remain: 5 days, 2:08:41, Finish: 2024-11-28 08:56 [11-23 22:47:49] (/home/user/VAR/train.py , line 276)=> [ep68] (training ) Lm: 6.573 (6.576), Lt: 5.815 (5.820), Acc m&t: 3.20 5.05, Remain: 5 days, 2:08:59, Finish: 2024-11-28 08:56 [11-23 22:47:49] (/home/user/VAR/train.py , line 276)=> [ep68] (training ) Lm: 6.573 (6.576), Lt: 5.815 (5.820), Acc m&t: 3.20 5.05, Remain: 5 days, 2:12:57, Finish: 2024-11-28 09:00 [11-23 22:47:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 0/1669] eta: 0:25:18 tlr: 0.00021 tnm: 0.21 Lm: 6.638 (6.638) Lt: 5.935 (5.935) Accm: 3.10 (3.10) Acct: 4.58 (4.58) proj_loss: -0.5965 (-0.5965) time: 0.9096 data: 0.0004 [11-23 22:47:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 0/1669] eta: 0:25:19 tlr: 0.00021 tnm: 0.21 Lm: 6.713 (6.713) Lt: 6.042 (6.042) Accm: 3.16 (3.16) Acct: 5.06 (5.06) proj_loss: -0.5901 (-0.5901) time: 0.9101 data: 0.0004 [11-23 22:47:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 0/1669] eta: 0:25:19 tlr: 0.00021 tnm: 0.21 Lm: 6.487 (6.487) Lt: 5.714 (5.714) Accm: 3.63 (3.63) Acct: 5.51 (5.51) proj_loss: -0.5977 (-0.5977) time: 0.9102 data: 0.0003 [11-23 22:47:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 0/1669] eta: 0:25:19 tlr: 0.00021 tnm: 0.21 Lm: 6.414 (6.414) Lt: 5.773 (5.773) Accm: 3.48 (3.48) Acct: 5.44 (5.44) proj_loss: -0.6246 (-0.6246) time: 0.9102 data: 0.0004 [11-23 22:47:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 0/1669] eta: 0:25:19 tlr: 0.00021 tnm: 0.21 Lm: 6.551 (6.551) Lt: 5.860 (5.860) Accm: 3.32 (3.32) Acct: 5.54 (5.54) proj_loss: -0.5737 (-0.5737) time: 0.9103 data: 0.0003 [11-23 22:47:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 0/1669] eta: 0:25:19 tlr: 0.00021 tnm: 0.21 Lm: 6.807 (6.807) Lt: 6.162 (6.162) Accm: 2.49 (2.49) Acct: 3.79 (3.79) proj_loss: -0.6159 (-0.6159) time: 0.9102 data: 0.0004 [11-23 22:47:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 0/1669] eta: 0:25:19 tlr: 0.00021 tnm: 0.21 Lm: 6.741 (6.741) Lt: 5.899 (5.899) Accm: 2.68 (2.68) Acct: 4.79 (4.79) proj_loss: -0.5979 (-0.5979) time: 0.9105 data: 0.0004 [11-23 22:47:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 0/1669] eta: 0:25:19 tlr: 0.00021 tnm: 0.21 Lm: 6.524 (6.524) Lt: 5.746 (5.746) Accm: 3.57 (3.57) Acct: 5.75 (5.75) proj_loss: -0.5653 (-0.5653) time: 0.9104 data: 0.0004 [11-23 22:54:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.22 Lm: 6.545 (6.545) Lt: 5.744 (5.744) Accm: 3.39 (3.39) Acct: 5.42 (5.42) proj_loss: -0.5603 (-0.5603) time: 0.9312 data: 0.0002 [11-23 22:54:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.22 Lm: 6.687 (6.687) Lt: 5.892 (5.892) Accm: 2.75 (2.75) Acct: 4.44 (4.44) proj_loss: -0.5947 (-0.5947) time: 0.9312 data: 0.0003 [11-23 22:54:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.22 Lm: 6.590 (6.590) Lt: 5.870 (5.870) Accm: 3.15 (3.15) Acct: 5.06 (5.06) proj_loss: -0.5665 (-0.5665) time: 0.9312 data: 0.0003 [11-23 22:54:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.22 Lm: 6.554 (6.554) Lt: 5.790 (5.790) Accm: 3.29 (3.29) Acct: 4.96 (4.96) proj_loss: -0.5960 (-0.5960) time: 0.9312 data: 0.0003 [11-23 22:54:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.22 Lm: 6.421 (6.421) Lt: 5.642 (5.642) Accm: 3.79 (3.79) Acct: 5.73 (5.73) proj_loss: -0.5890 (-0.5890) time: 0.9312 data: 0.0003 [11-23 22:54:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.22 Lm: 6.645 (6.645) Lt: 5.970 (5.970) Accm: 2.80 (2.80) Acct: 4.25 (4.25) proj_loss: -0.5845 (-0.5845) time: 0.9312 data: 0.0003 [11-23 22:54:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.22 Lm: 6.597 (6.597) Lt: 5.927 (5.927) Accm: 3.27 (3.27) Acct: 5.03 (5.03) proj_loss: -0.5914 (-0.5914) time: 0.9312 data: 0.0003 [11-23 22:54:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.22 Lm: 6.675 (6.675) Lt: 5.961 (5.961) Accm: 2.86 (2.86) Acct: 4.41 (4.41) proj_loss: -0.5872 (-0.5872) time: 0.9312 data: 0.0004 [11-23 23:00:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.23 Lm: 6.542 (6.621) Lt: 5.759 (5.887) Accm: 3.04 (2.92) Acct: 4.61 (4.48) proj_loss: -0.6040 (-0.5928) time: 0.9292 data: 0.0003 [11-23 23:00:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.23 Lm: 6.633 (6.653) Lt: 5.885 (5.864) Accm: 2.83 (2.86) Acct: 4.79 (4.57) proj_loss: -0.5979 (-0.6060) time: 0.9292 data: 0.0003 [11-23 23:00:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.23 Lm: 6.514 (6.452) Lt: 5.835 (5.706) Accm: 3.47 (3.68) Acct: 5.37 (5.61) proj_loss: -0.5886 (-0.5889) time: 0.9292 data: 0.0003 [11-23 23:00:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.23 Lm: 6.686 (6.659) Lt: 5.905 (5.948) Accm: 3.13 (2.91) Acct: 5.10 (4.53) proj_loss: -0.5668 (-0.5786) time: 0.9292 data: 0.0003 [11-23 23:00:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.23 Lm: 6.501 (6.537) Lt: 5.738 (5.773) Accm: 3.63 (3.45) Acct: 5.51 (5.18) proj_loss: -0.5944 (-0.5929) time: 0.9292 data: 0.0003 [11-23 23:00:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.23 Lm: 6.674 (6.623) Lt: 6.006 (5.953) Accm: 3.16 (3.19) Acct: 4.99 (4.74) proj_loss: -0.5905 (-0.5911) time: 0.9292 data: 0.0003 [11-23 23:00:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.23 Lm: 6.566 (6.554) Lt: 5.746 (5.753) Accm: 3.22 (3.23) Acct: 5.10 (5.08) proj_loss: -0.5653 (-0.5693) time: 0.9292 data: 0.0002 [11-23 23:00:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [ 834/1669] eta: 0:12:57 tlr: 0.00021 tnm: 0.23 Lm: 6.551 (6.540) Lt: 5.860 (5.804) Accm: 3.32 (3.27) Acct: 5.51 (5.21) proj_loss: -0.5593 (-0.5628) time: 0.9292 data: 0.0003 [11-23 23:07:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.534 (6.534) Lt: 5.831 (5.803) Accm: 3.18 (3.21) Acct: 5.04 (5.02) proj_loss: -0.5665 (-0.5687) time: 0.9311 data: 0.0003 [11-23 23:07:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.562 (6.584) Lt: 5.802 (5.830) Accm: 3.29 (3.17) Acct: 4.96 (4.77) proj_loss: -0.5914 (-0.5918) time: 0.9311 data: 0.0003 [11-23 23:07:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.545 (6.482) Lt: 5.744 (5.688) Accm: 3.39 (3.54) Acct: 5.42 (5.63) proj_loss: -0.5763 (-0.5798) time: 0.9311 data: 0.0003 [11-23 23:07:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.612 (6.605) Lt: 5.922 (5.924) Accm: 3.15 (3.18) Acct: 4.94 (4.78) proj_loss: -0.5916 (-0.5934) time: 0.9311 data: 0.0003 [11-23 23:07:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.566 (6.605) Lt: 5.839 (5.873) Accm: 3.31 (3.11) Acct: 5.27 (4.93) proj_loss: -0.5811 (-0.5828) time: 0.9311 data: 0.0003 [11-23 23:07:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.549 (6.485) Lt: 5.849 (5.746) Accm: 3.29 (3.51) Acct: 4.98 (5.28) proj_loss: -0.5918 (-0.5904) time: 0.9311 data: 0.0003 [11-23 23:07:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.609 (6.578) Lt: 5.847 (5.808) Accm: 2.94 (3.02) Acct: 4.80 (4.73) proj_loss: -0.6034 (-0.6067) time: 0.9311 data: 0.0003 [11-23 23:07:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [1251/1669] eta: 0:06:29 tlr: 0.00021 tnm: 0.20 Lm: 6.528 (6.585) Lt: 5.750 (5.840) Accm: 3.13 (3.13) Acct: 4.82 (4.95) proj_loss: -0.5969 (-0.5920) time: 0.9311 data: 0.0003 [11-23 23:14:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.542 (6.600) Lt: 5.759 (5.865) Accm: 3.04 (3.10) Acct: 4.61 (4.86) proj_loss: -0.6040 (-0.5990) time: 1.1149 data: 0.0018 [11-23 23:14:14] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 69/350] Total time: 0:26:25 (0.950 s / it) [11-23 23:14:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.551 (6.563) Lt: 5.860 (5.862) Accm: 3.04 (3.14) Acct: 4.58 (4.89) proj_loss: -0.5737 (-0.5789) time: 1.1149 data: 0.0016 [11-23 23:14:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.566 (6.531) Lt: 5.746 (5.736) Accm: 3.22 (3.42) Acct: 5.10 (5.45) proj_loss: -0.5673 (-0.5773) time: 1.1149 data: 0.0018 [11-23 23:14:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.584 (6.511) Lt: 5.863 (5.773) Accm: 3.10 (3.36) Acct: 4.58 (5.08) proj_loss: -0.5950 (-0.5935) time: 1.1149 data: 0.0017 [11-23 23:14:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.622 (6.612) Lt: 5.866 (5.857) Accm: 2.96 (3.09) Acct: 4.41 (4.68) proj_loss: -0.5936 (-0.5922) time: 1.1149 data: 0.0015 [11-23 23:14:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.633 (6.596) Lt: 5.885 (5.849) Accm: 2.90 (3.00) Acct: 4.79 (4.61) proj_loss: -0.5979 (-0.6008) time: 1.1149 data: 0.0022 [11-23 23:14:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.527 (6.590) Lt: 5.842 (5.867) Accm: 3.48 (3.22) Acct: 5.44 (5.03) proj_loss: -0.5955 (-0.5888) time: 1.1149 data: 0.0015 [11-23 23:14:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 69/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.674 (6.620) Lt: 5.894 (5.918) Accm: 3.15 (3.11) Acct: 4.89 (4.76) proj_loss: -0.5905 (-0.5911) time: 1.1149 data: 0.0022 [11-23 23:14:14] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 69/350] Total time: 0:26:25 (0.950 s / it) [11-23 23:14:14] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 69/350] Total time: 0:26:25 (0.950 s / it) [11-23 23:14:14] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 69/350] Total time: 0:26:25 (0.950 s / it) [11-23 23:14:14] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 69/350] Total time: 0:26:25 (0.950 s / it) [11-23 23:14:14] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 69/350] Total time: 0:26:25 (0.950 s / it) [11-23 23:14:14] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 69/350] Total time: 0:26:25 (0.950 s / it) [11-23 23:14:14] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 69/350] Total time: 0:26:25 (0.950 s / it) [11-23 23:16:24] (home/user/VAR/trainer.py, line 114)=> FID: 3.861167064070173 [11-23 23:16:24] (/home/user/VAR/train.py , line 259)=> [*] [ep69] (val 50000) Lm: 6.5647, Lt: 5.8101, Acc m&t: 3.21 5.02, Val cost: 129.66s [11-23 23:16:24] (/home/user/VAR/train.py , line 264)=> [saving ckpt] ... [saving ckpt](*) finished! @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth [11-23 23:17:31] (/home/user/VAR/train.py , line 276)=> [ep69] (training ) Lm: 6.565 (6.565), Lt: 5.810 (5.810), Acc m&t: 3.21 5.05, Remain: 5 days, 2:19:56, Finish: 2024-11-28 09:34 [11-23 23:17:31] (/home/user/VAR/train.py , line 276)=> [ep69] (training ) Lm: 6.565 (6.565), Lt: 5.810 (5.810), Acc m&t: 3.21 5.05, Remain: 5 days, 2:19:12, Finish: 2024-11-28 09:33 [11-23 23:17:31] (/home/user/VAR/train.py , line 276)=> [ep69] (training ) Lm: 6.565 (6.565), Lt: 5.810 (5.810), Acc m&t: 3.21 5.05, Remain: 5 days, 2:22:07, Finish: 2024-11-28 09:36 [11-23 23:17:31] (/home/user/VAR/train.py , line 276)=> [ep69] (training ) Lm: 6.565 (6.565), Lt: 5.810 (5.810), Acc m&t: 3.21 5.05, Remain: 5 days, 2:20:55, Finish: 2024-11-28 09:35 [11-23 23:17:31] (/home/user/VAR/train.py , line 276)=> [ep69] (training ) Lm: 6.565 (6.565), Lt: 5.810 (5.810), Acc m&t: 3.21 5.05, Remain: 5 days, 2:22:55, Finish: 2024-11-28 09:37 [11-23 23:17:31] (/home/user/VAR/train.py , line 276)=> [ep69] (training ) Lm: 6.565 (6.565), Lt: 5.810 (5.810), Acc m&t: 3.21 5.05, Remain: 5 days, 2:21:08, Finish: 2024-11-28 09:35 [11-23 23:17:31] (/home/user/VAR/train.py , line 276)=> [ep69] (training ) Lm: 6.565 (6.565), Lt: 5.810 (5.810), Acc m&t: 3.21 5.05, Remain: 5 days, 2:21:47, Finish: 2024-11-28 09:36 [11-23 23:17:31] (/home/user/VAR/train.py , line 276)=> [ep69] (training ) Lm: 6.565 (6.565), Lt: 5.810 (5.810), Acc m&t: 3.21 5.05, Remain: 5 days, 2:19:40, Finish: 2024-11-28 09:33 [11-23 23:17:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 0/1669] eta: 0:25:28 tlr: 0.00021 tnm: 0.23 Lm: 6.688 (6.688) Lt: 5.999 (5.999) Accm: 3.10 (3.10) Acct: 4.68 (4.68) proj_loss: -0.6276 (-0.6276) time: 0.9156 data: 0.0003 [11-23 23:17:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 0/1669] eta: 0:25:36 tlr: 0.00021 tnm: 0.23 Lm: 6.382 (6.382) Lt: 5.540 (5.540) Accm: 3.60 (3.60) Acct: 5.92 (5.92) proj_loss: -0.5472 (-0.5472) time: 0.9205 data: 0.0004 [11-23 23:17:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 0/1669] eta: 0:25:24 tlr: 0.00021 tnm: 0.23 Lm: 6.566 (6.566) Lt: 5.828 (5.828) Accm: 3.32 (3.32) Acct: 5.06 (5.06) proj_loss: -0.5707 (-0.5707) time: 0.9132 data: 0.0004 [11-23 23:17:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 0/1669] eta: 0:25:25 tlr: 0.00021 tnm: 0.23 Lm: 6.461 (6.461) Lt: 5.649 (5.649) Accm: 3.48 (3.48) Acct: 5.75 (5.75) proj_loss: -0.5622 (-0.5622) time: 0.9137 data: 0.0004 [11-23 23:17:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 0/1669] eta: 0:25:23 tlr: 0.00021 tnm: 0.23 Lm: 6.565 (6.565) Lt: 5.786 (5.786) Accm: 3.10 (3.10) Acct: 4.86 (4.86) proj_loss: -0.6046 (-0.6046) time: 0.9129 data: 0.0004 [11-23 23:17:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 0/1669] eta: 0:25:28 tlr: 0.00021 tnm: 0.23 Lm: 6.377 (6.377) Lt: 5.683 (5.683) Accm: 4.36 (4.36) Acct: 6.71 (6.71) proj_loss: -0.6073 (-0.6073) time: 0.9158 data: 0.0004 [11-23 23:17:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 0/1669] eta: 0:25:27 tlr: 0.00021 tnm: 0.23 Lm: 6.742 (6.742) Lt: 6.058 (6.058) Accm: 3.07 (3.07) Acct: 5.06 (5.06) proj_loss: -0.6192 (-0.6192) time: 0.9153 data: 0.0004 [11-23 23:17:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 0/1669] eta: 0:25:28 tlr: 0.00021 tnm: 0.23 Lm: 6.523 (6.523) Lt: 5.760 (5.760) Accm: 3.29 (3.29) Acct: 5.65 (5.65) proj_loss: -0.5832 (-0.5832) time: 0.9161 data: 0.0003 [11-23 23:24:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 417/1669] eta: 0:19:54 tlr: 0.00021 tnm: 0.22 Lm: 6.513 (6.513) Lt: 5.761 (5.761) Accm: 3.27 (3.27) Acct: 5.39 (5.39) proj_loss: -0.6002 (-0.6002) time: 0.9310 data: 0.0003 [11-23 23:24:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 417/1669] eta: 0:19:54 tlr: 0.00021 tnm: 0.22 Lm: 6.664 (6.664) Lt: 5.881 (5.881) Accm: 2.98 (2.98) Acct: 4.73 (4.73) proj_loss: -0.5947 (-0.5947) time: 0.9310 data: 0.0003 [11-23 23:24:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 417/1669] eta: 0:19:54 tlr: 0.00021 tnm: 0.22 Lm: 6.534 (6.534) Lt: 5.755 (5.755) Accm: 3.31 (3.31) Acct: 5.29 (5.29) proj_loss: -0.5799 (-0.5799) time: 0.9310 data: 0.0003 [11-23 23:24:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 417/1669] eta: 0:19:54 tlr: 0.00021 tnm: 0.22 Lm: 6.552 (6.552) Lt: 5.817 (5.817) Accm: 3.39 (3.39) Acct: 5.42 (5.42) proj_loss: -0.5954 (-0.5954) time: 0.9310 data: 0.0003 [11-23 23:24:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 417/1669] eta: 0:19:54 tlr: 0.00021 tnm: 0.22 Lm: 6.428 (6.428) Lt: 5.731 (5.731) Accm: 3.70 (3.70) Acct: 5.61 (5.61) proj_loss: -0.6102 (-0.6102) time: 0.9310 data: 0.0003 [11-23 23:24:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 417/1669] eta: 0:19:54 tlr: 0.00021 tnm: 0.22 Lm: 6.648 (6.648) Lt: 5.939 (5.939) Accm: 3.04 (3.04) Acct: 4.56 (4.56) proj_loss: -0.5757 (-0.5757) time: 0.9310 data: 0.0003 [11-23 23:24:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 417/1669] eta: 0:19:54 tlr: 0.00021 tnm: 0.22 Lm: 6.506 (6.506) Lt: 5.733 (5.733) Accm: 3.31 (3.31) Acct: 5.42 (5.42) proj_loss: -0.5656 (-0.5656) time: 0.9310 data: 0.0003 [11-23 23:24:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 417/1669] eta: 0:19:54 tlr: 0.00021 tnm: 0.22 Lm: 6.594 (6.594) Lt: 5.845 (5.845) Accm: 2.94 (2.94) Acct: 4.56 (4.56) proj_loss: -0.5932 (-0.5932) time: 0.9310 data: 0.0003 [11-23 23:30:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 834/1669] eta: 0:13:09 tlr: 0.00021 tnm: 0.22 Lm: 6.565 (6.581) Lt: 5.786 (5.815) Accm: 2.77 (2.88) Acct: 4.27 (4.42) proj_loss: -0.6014 (-0.5959) time: 0.9317 data: 0.0003 [11-23 23:30:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 834/1669] eta: 0:13:09 tlr: 0.00021 tnm: 0.22 Lm: 6.688 (6.676) Lt: 5.999 (5.941) Accm: 2.86 (2.85) Acct: 4.68 (4.47) proj_loss: -0.5980 (-0.5958) time: 0.9317 data: 0.0003 [11-23 23:30:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 834/1669] eta: 0:13:09 tlr: 0.00021 tnm: 0.22 Lm: 6.539 (6.536) Lt: 5.789 (5.766) Accm: 3.13 (3.20) Acct: 4.82 (5.12) proj_loss: -0.5764 (-0.5787) time: 0.9317 data: 0.0003 [11-23 23:30:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 834/1669] eta: 0:13:09 tlr: 0.00021 tnm: 0.22 Lm: 6.557 (6.523) Lt: 5.809 (5.759) Accm: 3.31 (3.31) Acct: 5.10 (5.31) proj_loss: -0.5840 (-0.5812) time: 0.9317 data: 0.0003 [11-23 23:30:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 834/1669] eta: 0:13:09 tlr: 0.00021 tnm: 0.22 Lm: 6.589 (6.564) Lt: 5.854 (5.829) Accm: 3.07 (3.17) Acct: 5.06 (4.96) proj_loss: -0.5717 (-0.5843) time: 0.9318 data: 0.0003 [11-23 23:30:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 834/1669] eta: 0:13:09 tlr: 0.00021 tnm: 0.22 Lm: 6.566 (6.570) Lt: 5.828 (5.832) Accm: 3.32 (3.16) Acct: 5.06 (4.99) proj_loss: -0.5808 (-0.5866) time: 0.9318 data: 0.0003 [11-23 23:30:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 834/1669] eta: 0:13:09 tlr: 0.00021 tnm: 0.22 Lm: 6.479 (6.486) Lt: 5.780 (5.789) Accm: 3.04 (3.48) Acct: 4.51 (5.20) proj_loss: -0.6112 (-0.6105) time: 0.9318 data: 0.0003 [11-23 23:30:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [ 834/1669] eta: 0:13:09 tlr: 0.00021 tnm: 0.22 Lm: 6.503 (6.496) Lt: 5.760 (5.738) Accm: 3.29 (3.28) Acct: 5.13 (5.28) proj_loss: -0.5832 (-0.5886) time: 0.9318 data: 0.0003 [11-23 23:37:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [1251/1669] eta: 0:06:33 tlr: 0.00021 tnm: 0.20 Lm: 6.513 (6.533) Lt: 5.761 (5.751) Accm: 3.27 (3.15) Acct: 5.10 (5.17) proj_loss: -0.5772 (-0.5842) time: 0.9310 data: 0.0003 [11-23 23:37:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [1251/1669] eta: 0:06:33 tlr: 0.00021 tnm: 0.20 Lm: 6.503 (6.497) Lt: 5.806 (5.800) Accm: 3.28 (3.49) Acct: 5.06 (5.30) proj_loss: -0.6092 (-0.6060) time: 0.9310 data: 0.0003 [11-23 23:37:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [1251/1669] eta: 0:06:33 tlr: 0.00021 tnm: 0.20 Lm: 6.612 (6.582) Lt: 5.878 (5.847) Accm: 3.19 (3.21) Acct: 5.15 (5.03) proj_loss: -0.5915 (-0.5911) time: 0.9310 data: 0.0003 [11-23 23:37:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [1251/1669] eta: 0:06:33 tlr: 0.00021 tnm: 0.20 Lm: 6.594 (6.583) Lt: 5.851 (5.842) Accm: 3.04 (3.06) Acct: 4.82 (4.89) proj_loss: -0.5772 (-0.5833) time: 0.9310 data: 0.0003 [11-23 23:37:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [1251/1669] eta: 0:06:33 tlr: 0.00021 tnm: 0.20 Lm: 6.594 (6.627) Lt: 5.845 (5.886) Accm: 2.77 (2.84) Acct: 4.44 (4.47) proj_loss: -0.6005 (-0.5968) time: 0.9310 data: 0.0003 [11-23 23:37:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [1251/1669] eta: 0:06:33 tlr: 0.00021 tnm: 0.20 Lm: 6.578 (6.542) Lt: 5.844 (5.789) Accm: 3.45 (3.38) Acct: 5.34 (5.38) proj_loss: -0.5829 (-0.5813) time: 0.9310 data: 0.0003 [11-23 23:37:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [1251/1669] eta: 0:06:33 tlr: 0.00021 tnm: 0.20 Lm: 6.518 (6.526) Lt: 5.796 (5.775) Accm: 3.26 (3.25) Acct: 5.08 (5.17) proj_loss: -0.5850 (-0.5824) time: 0.9310 data: 0.0003 [11-23 23:37:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [1251/1669] eta: 0:06:33 tlr: 0.00021 tnm: 0.20 Lm: 6.664 (6.629) Lt: 5.881 (5.888) Accm: 2.98 (3.03) Acct: 4.73 (4.57) proj_loss: -0.5953 (-0.5950) time: 0.9311 data: 0.0003 [11-23 23:43:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.688 (6.647) Lt: 5.955 (5.901) Accm: 2.86 (2.96) Acct: 4.72 (4.60) proj_loss: -0.5927 (-0.5907) time: 0.9322 data: 0.0016 [11-23 23:43:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 70/350] Total time: 0:26:06 (0.938 s / it) [11-23 23:43:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.557 (6.520) Lt: 5.809 (5.781) Accm: 3.55 (3.41) Acct: 5.41 (5.39) proj_loss: -0.5840 (-0.5837) time: 0.9322 data: 0.0013 [11-23 23:43:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.623 (6.607) Lt: 5.873 (5.870) Accm: 3.02 (3.05) Acct: 4.89 (4.89) proj_loss: -0.5808 (-0.5889) time: 0.9322 data: 0.0019 [11-23 23:43:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.565 (6.600) Lt: 5.878 (5.885) Accm: 2.77 (2.91) Acct: 4.61 (4.51) proj_loss: -0.6014 (-0.6008) time: 0.9322 data: 0.0017 [11-23 23:43:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.635 (6.628) Lt: 5.903 (5.910) Accm: 3.07 (3.11) Acct: 5.06 (4.80) proj_loss: -0.5717 (-0.5836) time: 0.9322 data: 0.0016 [11-23 23:43:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.539 (6.562) Lt: 5.802 (5.823) Accm: 3.13 (3.15) Acct: 4.82 (5.01) proj_loss: -0.5892 (-0.5838) time: 0.9322 data: 0.0015 [11-23 23:43:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.523 (6.545) Lt: 5.762 (5.769) Accm: 3.25 (3.13) Acct: 5.06 (5.14) proj_loss: -0.5832 (-0.5881) time: 0.9322 data: 0.0018 [11-23 23:43:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 70/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.21 Lm: 6.479 (6.478) Lt: 5.780 (5.784) Accm: 3.38 (3.46) Acct: 5.37 (5.32) proj_loss: -0.6073 (-0.5989) time: 0.9322 data: 0.0017 [11-23 23:43:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 70/350] Total time: 0:26:06 (0.938 s / it) [11-23 23:43:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 70/350] Total time: 0:26:06 (0.938 s / it) [11-23 23:43:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 70/350] Total time: 0:26:06 (0.938 s / it) [11-23 23:43:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 70/350] Total time: 0:26:06 (0.938 s / it) [11-23 23:43:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 70/350] Total time: 0:26:06 (0.938 s / it) [11-23 23:43:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 70/350] Total time: 0:26:06 (0.938 s / it) [11-23 23:43:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 70/350] Total time: 0:26:06 (0.938 s / it) [11-23 23:43:37] (/home/user/VAR/train.py , line 276)=> [ep70] (training ) Lm: 6.565 (6.570), Lt: 5.810 (5.819), Acc m&t: 3.21 5.05, Remain: 5 days, 1:30:57, Finish: 2024-11-28 09:14 [11-23 23:43:37] (/home/user/VAR/train.py , line 276)=> [ep70] (training ) Lm: 6.565 (6.570), Lt: 5.810 (5.819), Acc m&t: 3.21 5.05, Remain: 5 days, 1:33:04, Finish: 2024-11-28 09:16 [11-23 23:43:37] (/home/user/VAR/train.py , line 276)=> [ep70] (training ) Lm: 6.565 (6.570), Lt: 5.810 (5.819), Acc m&t: 3.21 5.05, Remain: 5 days, 1:29:33, Finish: 2024-11-28 09:13 [11-23 23:43:37] (/home/user/VAR/train.py , line 276)=> [ep70] (training ) Lm: 6.565 (6.570), Lt: 5.810 (5.819), Acc m&t: 3.21 5.05, Remain: 5 days, 1:29:55, Finish: 2024-11-28 09:13 [11-23 23:43:37] (/home/user/VAR/train.py , line 276)=> [ep70] (training ) Lm: 6.565 (6.570), Lt: 5.810 (5.819), Acc m&t: 3.21 5.05, Remain: 5 days, 1:30:21, Finish: 2024-11-28 09:13 [11-23 23:43:37] (/home/user/VAR/train.py , line 276)=> [ep70] (training ) Lm: 6.565 (6.570), Lt: 5.810 (5.819), Acc m&t: 3.21 5.05, Remain: 5 days, 1:31:15, Finish: 2024-11-28 09:14 [11-23 23:43:37] (/home/user/VAR/train.py , line 276)=> [ep70] (training ) Lm: 6.565 (6.570), Lt: 5.810 (5.819), Acc m&t: 3.21 5.05, Remain: 5 days, 1:32:36, Finish: 2024-11-28 09:16 [11-23 23:43:37] (/home/user/VAR/train.py , line 276)=> [ep70] (training ) Lm: 6.565 (6.570), Lt: 5.810 (5.819), Acc m&t: 3.21 5.05, Remain: 5 days, 1:29:31, Finish: 2024-11-28 09:13 [11-23 23:43:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 0/1669] eta: 0:25:53 tlr: 0.00021 tnm: 0.20 Lm: 6.565 (6.565) Lt: 5.825 (5.825) Accm: 3.32 (3.32) Acct: 5.41 (5.41) proj_loss: -0.5392 (-0.5392) time: 0.9305 data: 0.0003 [11-23 23:43:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 0/1669] eta: 0:25:49 tlr: 0.00021 tnm: 0.20 Lm: 6.596 (6.596) Lt: 5.780 (5.780) Accm: 3.67 (3.67) Acct: 6.10 (6.10) proj_loss: -0.5945 (-0.5945) time: 0.9283 data: 0.0004 [11-23 23:43:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 0/1669] eta: 0:25:52 tlr: 0.00021 tnm: 0.20 Lm: 6.355 (6.355) Lt: 5.554 (5.554) Accm: 3.64 (3.64) Acct: 5.75 (5.75) proj_loss: -0.6226 (-0.6226) time: 0.9305 data: 0.0003 [11-23 23:43:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 0/1669] eta: 0:25:53 tlr: 0.00021 tnm: 0.20 Lm: 6.460 (6.460) Lt: 5.692 (5.692) Accm: 3.80 (3.80) Acct: 6.10 (6.10) proj_loss: -0.5522 (-0.5522) time: 0.9308 data: 0.0003 [11-23 23:43:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 0/1669] eta: 0:25:53 tlr: 0.00021 tnm: 0.20 Lm: 6.339 (6.339) Lt: 5.544 (5.544) Accm: 3.63 (3.63) Acct: 5.72 (5.72) proj_loss: -0.5735 (-0.5735) time: 0.9307 data: 0.0004 [11-23 23:43:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 0/1669] eta: 0:25:53 tlr: 0.00021 tnm: 0.20 Lm: 6.434 (6.434) Lt: 5.518 (5.518) Accm: 3.32 (3.32) Acct: 5.79 (5.79) proj_loss: -0.5773 (-0.5773) time: 0.9305 data: 0.0004 [11-23 23:43:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 0/1669] eta: 0:25:52 tlr: 0.00021 tnm: 0.20 Lm: 6.366 (6.366) Lt: 5.581 (5.581) Accm: 3.67 (3.67) Acct: 5.41 (5.41) proj_loss: -0.5948 (-0.5948) time: 0.9302 data: 0.0005 [11-23 23:43:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 0/1669] eta: 0:26:34 tlr: 0.00021 tnm: 0.20 Lm: 6.426 (6.426) Lt: 5.657 (5.657) Accm: 3.47 (3.47) Acct: 5.37 (5.37) proj_loss: -0.5942 (-0.5942) time: 0.9553 data: 0.0004 [11-23 23:50:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.461 (6.461) Lt: 5.709 (5.709) Accm: 3.41 (3.41) Acct: 5.18 (5.18) proj_loss: -0.5850 (-0.5850) time: 0.9302 data: 0.0003 [11-23 23:50:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.555 (6.555) Lt: 5.789 (5.789) Accm: 3.13 (3.13) Acct: 4.96 (4.96) proj_loss: -0.5995 (-0.5995) time: 0.9302 data: 0.0003 [11-23 23:50:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.529 (6.529) Lt: 5.697 (5.697) Accm: 3.13 (3.13) Acct: 5.23 (5.23) proj_loss: -0.5915 (-0.5915) time: 0.9302 data: 0.0003 [11-23 23:50:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.438 (6.438) Lt: 5.648 (5.648) Accm: 3.59 (3.59) Acct: 5.53 (5.53) proj_loss: -0.5919 (-0.5919) time: 0.9302 data: 0.0003 [11-23 23:50:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.554 (6.554) Lt: 5.781 (5.781) Accm: 3.64 (3.64) Acct: 5.77 (5.77) proj_loss: -0.5769 (-0.5769) time: 0.9302 data: 0.0003 [11-23 23:50:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.526 (6.526) Lt: 5.794 (5.794) Accm: 3.34 (3.34) Acct: 5.34 (5.34) proj_loss: -0.5703 (-0.5703) time: 0.9302 data: 0.0003 [11-23 23:50:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.449 (6.449) Lt: 5.686 (5.686) Accm: 3.49 (3.49) Acct: 5.51 (5.51) proj_loss: -0.5929 (-0.5929) time: 0.9302 data: 0.0003 [11-23 23:50:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 417/1669] eta: 0:19:25 tlr: 0.00021 tnm: 0.21 Lm: 6.562 (6.562) Lt: 5.764 (5.764) Accm: 3.22 (3.22) Acct: 5.25 (5.25) proj_loss: -0.5862 (-0.5862) time: 0.9302 data: 0.0003 [11-23 23:56:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 834/1669] eta: 0:13:21 tlr: 0.00021 tnm: 0.20 Lm: 6.596 (6.594) Lt: 5.780 (5.817) Accm: 3.26 (3.23) Acct: 5.17 (5.22) proj_loss: -0.5945 (-0.5978) time: 0.9300 data: 0.0003 [11-23 23:56:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 834/1669] eta: 0:13:21 tlr: 0.00021 tnm: 0.20 Lm: 6.549 (6.534) Lt: 5.762 (5.782) Accm: 3.35 (3.37) Acct: 5.41 (5.43) proj_loss: -0.5820 (-0.5742) time: 0.9300 data: 0.0003 [11-23 23:56:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 834/1669] eta: 0:13:21 tlr: 0.00021 tnm: 0.20 Lm: 6.575 (6.561) Lt: 5.859 (5.812) Accm: 2.88 (3.04) Acct: 4.51 (4.79) proj_loss: -0.5948 (-0.5849) time: 0.9300 data: 0.0003 [11-23 23:56:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 834/1669] eta: 0:13:21 tlr: 0.00021 tnm: 0.20 Lm: 6.522 (6.475) Lt: 5.742 (5.701) Accm: 3.54 (3.41) Acct: 5.30 (5.18) proj_loss: -0.5822 (-0.5886) time: 0.9300 data: 0.0003 [11-23 23:56:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 834/1669] eta: 0:13:21 tlr: 0.00021 tnm: 0.20 Lm: 6.448 (6.449) Lt: 5.742 (5.705) Accm: 3.63 (3.54) Acct: 5.68 (5.57) proj_loss: -0.5772 (-0.5877) time: 0.9300 data: 0.0003 [11-23 23:56:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 834/1669] eta: 0:13:21 tlr: 0.00021 tnm: 0.20 Lm: 6.497 (6.491) Lt: 5.755 (5.724) Accm: 3.35 (3.24) Acct: 4.99 (4.92) proj_loss: -0.5758 (-0.5810) time: 0.9300 data: 0.0003 [11-23 23:56:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 834/1669] eta: 0:13:21 tlr: 0.00021 tnm: 0.20 Lm: 6.543 (6.550) Lt: 5.789 (5.783) Accm: 3.48 (3.41) Acct: 5.44 (5.46) proj_loss: -0.5961 (-0.5833) time: 0.9300 data: 0.0003 [11-23 23:56:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [ 834/1669] eta: 0:13:21 tlr: 0.00021 tnm: 0.20 Lm: 6.625 (6.572) Lt: 5.871 (5.755) Accm: 2.93 (3.01) Acct: 4.68 (5.02) proj_loss: -0.5990 (-0.5940) time: 0.9300 data: 0.0003 [11-24 00:03:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [1251/1669] eta: 0:06:42 tlr: 0.00021 tnm: 0.22 Lm: 6.529 (6.528) Lt: 5.722 (5.709) Accm: 3.13 (3.13) Acct: 5.15 (5.17) proj_loss: -0.5900 (-0.5908) time: 1.0447 data: 0.0003 [11-24 00:03:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [1251/1669] eta: 0:06:42 tlr: 0.00021 tnm: 0.22 Lm: 6.534 (6.544) Lt: 5.790 (5.785) Accm: 3.30 (3.34) Acct: 5.27 (5.37) proj_loss: -0.5901 (-0.5835) time: 1.0447 data: 0.0003 [11-24 00:03:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [1251/1669] eta: 0:06:42 tlr: 0.00021 tnm: 0.22 Lm: 6.557 (6.590) Lt: 5.794 (5.855) Accm: 3.34 (3.20) Acct: 5.34 (5.14) proj_loss: -0.5662 (-0.5683) time: 1.0447 data: 0.0003 [11-24 00:03:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [1251/1669] eta: 0:06:42 tlr: 0.00021 tnm: 0.22 Lm: 6.544 (6.549) Lt: 5.771 (5.780) Accm: 3.13 (3.13) Acct: 4.96 (4.98) proj_loss: -0.5982 (-0.5891) time: 1.0447 data: 0.0003 [11-24 00:03:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [1251/1669] eta: 0:06:42 tlr: 0.00021 tnm: 0.22 Lm: 6.562 (6.566) Lt: 5.764 (5.791) Accm: 3.42 (3.32) Acct: 5.41 (5.33) proj_loss: -0.5933 (-0.5964) time: 1.0447 data: 0.0003 [11-24 00:03:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [1251/1669] eta: 0:06:42 tlr: 0.00021 tnm: 0.22 Lm: 6.523 (6.524) Lt: 5.758 (5.775) Accm: 3.16 (3.17) Acct: 4.80 (4.85) proj_loss: -0.5850 (-0.5883) time: 1.0447 data: 0.0003 [11-24 00:03:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [1251/1669] eta: 0:06:42 tlr: 0.00021 tnm: 0.22 Lm: 6.535 (6.496) Lt: 5.750 (5.715) Accm: 3.45 (3.40) Acct: 5.41 (5.26) proj_loss: -0.5838 (-0.5878) time: 1.0447 data: 0.0003 [11-24 00:03:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [1251/1669] eta: 0:06:42 tlr: 0.00021 tnm: 0.22 Lm: 6.411 (6.430) Lt: 5.643 (5.661) Accm: 3.63 (3.57) Acct: 5.70 (5.61) proj_loss: -0.5898 (-0.5914) time: 1.0447 data: 0.0003 [11-24 00:10:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.375 (6.407) Lt: 5.544 (5.629) Accm: 3.64 (3.63) Acct: 5.72 (5.76) proj_loss: -0.5772 (-0.5846) time: 0.9336 data: 0.0019 [11-24 00:10:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 71/350] Total time: 0:26:43 (0.961 s / it) [11-24 00:10:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.549 (6.530) Lt: 5.761 (5.777) Accm: 3.15 (3.17) Acct: 4.79 (4.83) proj_loss: -0.5892 (-0.5885) time: 0.9336 data: 0.0019 [11-24 00:10:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.565 (6.602) Lt: 5.825 (5.858) Accm: 3.32 (3.20) Acct: 5.41 (5.20) proj_loss: -0.5820 (-0.5715) time: 0.9336 data: 0.0019 [11-24 00:10:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.552 (6.550) Lt: 5.779 (5.780) Accm: 3.37 (3.22) Acct: 5.41 (5.15) proj_loss: -0.5948 (-0.5864) time: 0.9336 data: 0.0017 [11-24 00:10:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.483 (6.519) Lt: 5.729 (5.713) Accm: 3.15 (3.14) Acct: 4.79 (5.09) proj_loss: -0.5811 (-0.5857) time: 0.9336 data: 0.0019 [11-24 00:10:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.522 (6.471) Lt: 5.742 (5.692) Accm: 3.54 (3.46) Acct: 5.51 (5.32) proj_loss: -0.5854 (-0.5910) time: 0.9336 data: 0.0017 [11-24 00:10:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.543 (6.571) Lt: 5.792 (5.815) Accm: 3.12 (3.23) Acct: 5.10 (5.21) proj_loss: -0.5842 (-0.5777) time: 0.9336 data: 0.0018 [11-24 00:10:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 71/350] [1668/1669] eta: 0:00:00 tlr: 0.00021 tnm: 0.20 Lm: 6.528 (6.534) Lt: 5.748 (5.772) Accm: 3.48 (3.35) Acct: 5.65 (5.41) proj_loss: -0.5945 (-0.6025) time: 0.9336 data: 0.0017 [11-24 00:10:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 71/350] Total time: 0:26:43 (0.961 s / it) [11-24 00:10:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 71/350] Total time: 0:26:43 (0.961 s / it) [11-24 00:10:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 71/350] Total time: 0:26:43 (0.961 s / it) [11-24 00:10:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 71/350] Total time: 0:26:43 (0.961 s / it) [11-24 00:10:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 71/350] Total time: 0:26:43 (0.961 s / it) [11-24 00:10:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 71/350] Total time: 0:26:43 (0.961 s / it) [11-24 00:10:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 71/350] Total time: 0:26:43 (0.961 s / it) [11-24 00:10:21] (/home/user/VAR/train.py , line 276)=> [ep71] (training ) Lm: 6.543 (6.543), Lt: 5.784 (5.784), Acc m&t: 3.26 5.17, Remain: 5 days, 1:04:27, Finish: 2024-11-28 09:14 [11-24 00:10:21] (/home/user/VAR/train.py , line 276)=> [ep71] (training ) Lm: 6.543 (6.543), Lt: 5.784 (5.784), Acc m&t: 3.26 5.17, Remain: 5 days, 1:04:49, Finish: 2024-11-28 09:15 [11-24 00:10:21] (/home/user/VAR/train.py , line 276)=> [ep71] (training ) Lm: 6.543 (6.543), Lt: 5.784 (5.784), Acc m&t: 3.26 5.17, Remain: 5 days, 1:05:28, Finish: 2024-11-28 09:15 [11-24 00:10:21] (/home/user/VAR/train.py , line 276)=> [ep71] (training ) Lm: 6.543 (6.543), Lt: 5.784 (5.784), Acc m&t: 3.26 5.17, Remain: 5 days, 1:05:31, Finish: 2024-11-28 09:15 [11-24 00:10:21] (/home/user/VAR/train.py , line 276)=> [ep71] (training ) Lm: 6.543 (6.543), Lt: 5.784 (5.784), Acc m&t: 3.26 5.17, Remain: 5 days, 1:06:11, Finish: 2024-11-28 09:16 [11-24 00:10:21] (/home/user/VAR/train.py , line 276)=> [ep71] (training ) Lm: 6.543 (6.543), Lt: 5.784 (5.784), Acc m&t: 3.26 5.17, Remain: 5 days, 1:05:26, Finish: 2024-11-28 09:15 [11-24 00:10:21] (/home/user/VAR/train.py , line 276)=> [ep71] (training ) Lm: 6.543 (6.543), Lt: 5.784 (5.784), Acc m&t: 3.26 5.17, Remain: 5 days, 1:04:29, Finish: 2024-11-28 09:14 [11-24 00:10:21] (/home/user/VAR/train.py , line 276)=> [ep71] (training ) Lm: 6.543 (6.543), Lt: 5.784 (5.784), Acc m&t: 3.26 5.17, Remain: 5 days, 1:07:07, Finish: 2024-11-28 09:17 [11-24 00:10:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 0/1669] eta: 0:25:08 tlr: 0.00021 tnm: 0.20 Lm: 6.586 (6.586) Lt: 5.884 (5.884) Accm: 3.48 (3.48) Acct: 4.92 (4.92) proj_loss: -0.5742 (-0.5742) time: 0.9036 data: 0.0004 [11-24 00:10:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 0/1669] eta: 0:25:07 tlr: 0.00021 tnm: 0.20 Lm: 6.661 (6.661) Lt: 5.933 (5.933) Accm: 3.38 (3.38) Acct: 5.44 (5.44) proj_loss: -0.5920 (-0.5920) time: 0.9034 data: 0.0004 [11-24 00:10:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 0/1669] eta: 0:24:58 tlr: 0.00021 tnm: 0.20 Lm: 6.321 (6.321) Lt: 5.601 (5.601) Accm: 3.89 (3.89) Acct: 5.99 (5.99) proj_loss: -0.6150 (-0.6150) time: 0.8979 data: 0.0004 [11-24 00:10:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 0/1669] eta: 0:25:08 tlr: 0.00021 tnm: 0.20 Lm: 6.479 (6.479) Lt: 5.700 (5.700) Accm: 3.39 (3.39) Acct: 5.23 (5.23) proj_loss: -0.6010 (-0.6010) time: 0.9039 data: 0.0004 [11-24 00:10:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 0/1669] eta: 0:25:08 tlr: 0.00021 tnm: 0.20 Lm: 6.673 (6.673) Lt: 5.993 (5.993) Accm: 2.93 (2.93) Acct: 4.51 (4.51) proj_loss: -0.6053 (-0.6053) time: 0.9039 data: 0.0004 [11-24 00:10:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 0/1669] eta: 0:24:59 tlr: 0.00021 tnm: 0.20 Lm: 6.534 (6.534) Lt: 5.778 (5.778) Accm: 2.86 (2.86) Acct: 4.24 (4.24) proj_loss: -0.5654 (-0.5654) time: 0.8983 data: 0.0004 [11-24 00:10:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 0/1669] eta: 0:25:08 tlr: 0.00021 tnm: 0.20 Lm: 6.486 (6.486) Lt: 5.764 (5.764) Accm: 3.60 (3.60) Acct: 5.44 (5.44) proj_loss: -0.6215 (-0.6215) time: 0.9040 data: 0.0004 [11-24 00:10:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 0/1669] eta: 0:24:59 tlr: 0.00021 tnm: 0.20 Lm: 6.335 (6.335) Lt: 5.595 (5.595) Accm: 3.93 (3.93) Acct: 5.99 (5.99) proj_loss: -0.5668 (-0.5668) time: 0.8985 data: 0.0003 [11-24 00:16:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 417/1669] eta: 0:19:30 tlr: 0.0002 tnm: 0.20 Lm: 6.522 (6.522) Lt: 5.776 (5.776) Accm: 3.26 (3.26) Acct: 4.98 (4.98) proj_loss: -0.5768 (-0.5768) time: 0.9306 data: 0.0003 [11-24 00:16:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 417/1669] eta: 0:19:30 tlr: 0.0002 tnm: 0.20 Lm: 6.597 (6.597) Lt: 5.865 (5.865) Accm: 2.94 (2.94) Acct: 4.39 (4.39) proj_loss: -0.5800 (-0.5800) time: 0.9306 data: 0.0003 [11-24 00:16:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 417/1669] eta: 0:19:30 tlr: 0.0002 tnm: 0.20 Lm: 6.665 (6.665) Lt: 5.948 (5.948) Accm: 3.10 (3.10) Acct: 4.92 (4.92) proj_loss: -0.5756 (-0.5756) time: 0.9306 data: 0.0002 [11-24 00:16:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 417/1669] eta: 0:19:30 tlr: 0.0002 tnm: 0.20 Lm: 6.463 (6.463) Lt: 5.704 (5.704) Accm: 3.26 (3.26) Acct: 4.99 (4.99) proj_loss: -0.6093 (-0.6093) time: 0.9306 data: 0.0003 [11-24 00:16:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 417/1669] eta: 0:19:30 tlr: 0.0002 tnm: 0.20 Lm: 6.405 (6.405) Lt: 5.683 (5.683) Accm: 3.77 (3.77) Acct: 5.79 (5.79) proj_loss: -0.5955 (-0.5955) time: 0.9306 data: 0.0003 [11-24 00:16:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 417/1669] eta: 0:19:30 tlr: 0.0002 tnm: 0.20 Lm: 6.568 (6.568) Lt: 5.844 (5.844) Accm: 3.07 (3.07) Acct: 4.87 (4.87) proj_loss: -0.6016 (-0.6016) time: 0.9306 data: 0.0003 [11-24 00:16:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 417/1669] eta: 0:19:30 tlr: 0.0002 tnm: 0.20 Lm: 6.576 (6.576) Lt: 5.802 (5.802) Accm: 3.02 (3.02) Acct: 4.84 (4.84) proj_loss: -0.5985 (-0.5985) time: 0.9306 data: 0.0003 [11-24 00:16:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 417/1669] eta: 0:19:30 tlr: 0.0002 tnm: 0.20 Lm: 6.602 (6.602) Lt: 5.878 (5.878) Accm: 3.19 (3.19) Acct: 4.77 (4.77) proj_loss: -0.5914 (-0.5914) time: 0.9306 data: 0.0003 [11-24 00:23:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 834/1669] eta: 0:12:58 tlr: 0.0002 tnm: 0.22 Lm: 6.618 (6.661) Lt: 5.884 (5.902) Accm: 2.90 (2.93) Acct: 4.61 (4.59) proj_loss: -0.5742 (-0.5854) time: 0.9312 data: 0.0003 [11-24 00:23:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 834/1669] eta: 0:12:58 tlr: 0.0002 tnm: 0.22 Lm: 6.669 (6.729) Lt: 5.963 (6.020) Accm: 2.81 (2.80) Acct: 4.41 (4.51) proj_loss: -0.5920 (-0.5820) time: 0.9312 data: 0.0003 [11-24 00:23:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 834/1669] eta: 0:12:58 tlr: 0.0002 tnm: 0.22 Lm: 6.488 (6.531) Lt: 5.764 (5.803) Accm: 3.66 (3.41) Acct: 5.58 (5.34) proj_loss: -0.6080 (-0.5996) time: 0.9312 data: 0.0003 [11-24 00:23:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 834/1669] eta: 0:12:58 tlr: 0.0002 tnm: 0.22 Lm: 6.464 (6.509) Lt: 5.696 (5.773) Accm: 3.21 (3.24) Acct: 5.23 (5.12) proj_loss: -0.5990 (-0.6007) time: 0.9312 data: 0.0003 [11-24 00:23:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 834/1669] eta: 0:12:58 tlr: 0.0002 tnm: 0.22 Lm: 6.479 (6.510) Lt: 5.700 (5.741) Accm: 3.39 (3.34) Acct: 5.23 (5.14) proj_loss: -0.5961 (-0.5921) time: 0.9312 data: 0.0003 [11-24 00:23:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 834/1669] eta: 0:12:58 tlr: 0.0002 tnm: 0.22 Lm: 6.611 (6.602) Lt: 5.830 (5.853) Accm: 3.02 (3.01) Acct: 4.55 (4.63) proj_loss: -0.5945 (-0.5861) time: 0.9312 data: 0.0003 [11-24 00:23:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 834/1669] eta: 0:12:58 tlr: 0.0002 tnm: 0.22 Lm: 6.709 (6.585) Lt: 5.956 (5.854) Accm: 2.83 (3.11) Acct: 3.99 (4.65) proj_loss: -0.5867 (-0.5862) time: 0.9312 data: 0.0003 [11-24 00:23:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [ 834/1669] eta: 0:12:58 tlr: 0.0002 tnm: 0.22 Lm: 6.486 (6.484) Lt: 5.764 (5.734) Accm: 3.51 (3.35) Acct: 5.44 (5.18) proj_loss: -0.5972 (-0.5962) time: 0.9312 data: 0.0003 [11-24 00:29:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.22 Lm: 6.505 (6.524) Lt: 5.779 (5.799) Accm: 3.22 (3.23) Acct: 4.99 (4.95) proj_loss: -0.5944 (-0.5951) time: 0.9307 data: 0.0003 [11-24 00:29:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.22 Lm: 6.429 (6.461) Lt: 5.659 (5.687) Accm: 3.69 (3.58) Acct: 5.49 (5.54) proj_loss: -0.5985 (-0.6008) time: 0.9307 data: 0.0002 [11-24 00:29:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.22 Lm: 6.636 (6.636) Lt: 5.891 (5.885) Accm: 2.94 (2.92) Acct: 4.58 (4.62) proj_loss: -0.5957 (-0.5888) time: 0.9307 data: 0.0003 [11-24 00:29:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.22 Lm: 6.665 (6.692) Lt: 5.948 (5.970) Accm: 2.88 (2.84) Acct: 4.56 (4.56) proj_loss: -0.5934 (-0.5908) time: 0.9307 data: 0.0003 [11-24 00:29:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.22 Lm: 6.624 (6.653) Lt: 5.900 (5.905) Accm: 2.86 (2.90) Acct: 4.58 (4.58) proj_loss: -0.5738 (-0.5819) time: 0.9307 data: 0.0003 [11-24 00:29:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.22 Lm: 6.567 (6.550) Lt: 5.825 (5.818) Accm: 3.08 (3.17) Acct: 5.13 (5.10) proj_loss: -0.6001 (-0.6009) time: 0.9307 data: 0.0003 [11-24 00:29:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.22 Lm: 6.446 (6.499) Lt: 5.693 (5.758) Accm: 3.71 (3.50) Acct: 5.77 (5.49) proj_loss: -0.6051 (-0.6003) time: 0.9307 data: 0.0003 [11-24 00:29:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.22 Lm: 6.663 (6.593) Lt: 5.939 (5.871) Accm: 3.01 (3.13) Acct: 4.48 (4.73) proj_loss: -0.5905 (-0.5882) time: 0.9307 data: 0.0003 [11-24 00:36:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.617 (6.573) Lt: 5.922 (5.856) Accm: 3.19 (3.17) Acct: 4.96 (4.78) proj_loss: -0.5942 (-0.5941) time: 0.9308 data: 0.0019 [11-24 00:36:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 72/350] Total time: 0:25:57 (0.933 s / it) [11-24 00:36:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.611 (6.599) Lt: 5.830 (5.843) Accm: 3.02 (3.06) Acct: 4.61 (4.81) proj_loss: -0.5969 (-0.5904) time: 0.9308 data: 0.0017 [11-24 00:36:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.525 (6.581) Lt: 5.793 (5.868) Accm: 2.93 (3.07) Acct: 4.55 (4.69) proj_loss: -0.5917 (-0.5937) time: 0.9308 data: 0.0021 [11-24 00:36:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.444 (6.458) Lt: 5.689 (5.687) Accm: 3.54 (3.58) Acct: 5.30 (5.50) proj_loss: -0.5961 (-0.5972) time: 0.9308 data: 0.0017 [11-24 00:36:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.661 (6.656) Lt: 5.933 (5.930) Accm: 2.96 (2.97) Acct: 4.72 (4.76) proj_loss: -0.5948 (-0.5918) time: 0.9308 data: 0.0016 [11-24 00:36:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.629 (6.667) Lt: 5.916 (5.922) Accm: 2.83 (2.88) Acct: 4.55 (4.57) proj_loss: -0.5742 (-0.5811) time: 0.9308 data: 0.0013 [11-24 00:36:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.546 (6.549) Lt: 5.836 (5.821) Accm: 3.21 (3.19) Acct: 5.23 (5.14) proj_loss: -0.5990 (-0.5962) time: 0.9308 data: 0.0023 [11-24 00:36:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 72/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.488 (6.521) Lt: 5.721 (5.750) Accm: 3.66 (3.43) Acct: 5.58 (5.41) proj_loss: -0.6023 (-0.5971) time: 0.9308 data: 0.0018 [11-24 00:36:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 72/350] Total time: 0:25:57 (0.933 s / it) [11-24 00:36:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 72/350] Total time: 0:25:57 (0.933 s / it) [11-24 00:36:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 72/350] Total time: 0:25:57 (0.933 s / it) [11-24 00:36:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 72/350] Total time: 0:25:57 (0.933 s / it) [11-24 00:36:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 72/350] Total time: 0:25:57 (0.933 s / it) [11-24 00:36:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 72/350] Total time: 0:25:57 (0.933 s / it) [11-24 00:36:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 72/350] Total time: 0:25:57 (0.933 s / it) [11-24 00:36:19] (/home/user/VAR/train.py , line 276)=> [ep72] (training ) Lm: 6.543 (6.565), Lt: 5.784 (5.818), Acc m&t: 3.26 5.17, Remain: 5 days, 0:17:48, Finish: 2024-11-28 08:54 [11-24 00:36:19] (/home/user/VAR/train.py , line 276)=> [ep72] (training ) Lm: 6.543 (6.565), Lt: 5.784 (5.818), Acc m&t: 3.26 5.17, Remain: 5 days, 0:21:54, Finish: 2024-11-28 08:58 [11-24 00:36:19] (/home/user/VAR/train.py , line 276)=> [ep72] (training ) Lm: 6.543 (6.565), Lt: 5.784 (5.818), Acc m&t: 3.26 5.17, Remain: 5 days, 0:20:44, Finish: 2024-11-28 08:57 [11-24 00:36:19] (/home/user/VAR/train.py , line 276)=> [ep72] (training ) Lm: 6.543 (6.565), Lt: 5.784 (5.818), Acc m&t: 3.26 5.17, Remain: 5 days, 0:18:43, Finish: 2024-11-28 08:55 [11-24 00:36:19] (/home/user/VAR/train.py , line 276)=> [ep72] (training ) Lm: 6.543 (6.565), Lt: 5.784 (5.818), Acc m&t: 3.26 5.17, Remain: 5 days, 0:20:41, Finish: 2024-11-28 08:57 [11-24 00:36:19] (/home/user/VAR/train.py , line 276)=> [ep72] (training ) Lm: 6.543 (6.565), Lt: 5.784 (5.818), Acc m&t: 3.26 5.17, Remain: 5 days, 0:20:58, Finish: 2024-11-28 08:57 [11-24 00:36:19] (/home/user/VAR/train.py , line 276)=> [ep72] (training ) Lm: 6.543 (6.565), Lt: 5.784 (5.818), Acc m&t: 3.26 5.17, Remain: 5 days, 0:20:55, Finish: 2024-11-28 08:57 [11-24 00:36:19] (/home/user/VAR/train.py , line 276)=> [ep72] (training ) Lm: 6.543 (6.565), Lt: 5.784 (5.818), Acc m&t: 3.26 5.17, Remain: 5 days, 0:20:57, Finish: 2024-11-28 08:57 [11-24 00:36:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 0/1669] eta: 0:25:20 tlr: 0.0002 tnm: 0.22 Lm: 6.685 (6.685) Lt: 5.874 (5.874) Accm: 2.81 (2.81) Acct: 4.65 (4.65) proj_loss: -0.6072 (-0.6072) time: 0.9112 data: 0.0004 [11-24 00:36:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 0/1669] eta: 0:25:21 tlr: 0.0002 tnm: 0.22 Lm: 6.357 (6.357) Lt: 5.552 (5.552) Accm: 3.79 (3.79) Acct: 5.68 (5.68) proj_loss: -0.6191 (-0.6191) time: 0.9114 data: 0.0004 [11-24 00:36:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 0/1669] eta: 0:25:22 tlr: 0.0002 tnm: 0.22 Lm: 6.548 (6.548) Lt: 5.820 (5.820) Accm: 3.23 (3.23) Acct: 4.79 (4.79) proj_loss: -0.5739 (-0.5739) time: 0.9120 data: 0.0004 [11-24 00:36:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 0/1669] eta: 0:25:21 tlr: 0.0002 tnm: 0.22 Lm: 6.580 (6.580) Lt: 5.839 (5.839) Accm: 2.88 (2.88) Acct: 4.55 (4.55) proj_loss: -0.5959 (-0.5959) time: 0.9115 data: 0.0004 [11-24 00:36:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 0/1669] eta: 0:25:21 tlr: 0.0002 tnm: 0.22 Lm: 6.723 (6.723) Lt: 5.970 (5.970) Accm: 2.55 (2.55) Acct: 4.13 (4.13) proj_loss: -0.6199 (-0.6199) time: 0.9117 data: 0.0004 [11-24 00:36:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 0/1669] eta: 0:25:22 tlr: 0.0002 tnm: 0.22 Lm: 6.793 (6.793) Lt: 6.102 (6.102) Accm: 2.96 (2.96) Acct: 4.75 (4.75) proj_loss: -0.5855 (-0.5855) time: 0.9121 data: 0.0004 [11-24 00:36:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 0/1669] eta: 0:25:22 tlr: 0.0002 tnm: 0.22 Lm: 6.633 (6.633) Lt: 5.915 (5.915) Accm: 2.90 (2.90) Acct: 4.51 (4.51) proj_loss: -0.5950 (-0.5950) time: 0.9120 data: 0.0004 [11-24 00:36:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 0/1669] eta: 0:25:22 tlr: 0.0002 tnm: 0.22 Lm: 6.609 (6.609) Lt: 5.779 (5.779) Accm: 3.29 (3.29) Acct: 5.34 (5.34) proj_loss: -0.6063 (-0.6063) time: 0.9120 data: 0.0004 [11-24 00:43:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 417/1669] eta: 0:21:32 tlr: 0.0002 tnm: 0.22 Lm: 6.459 (6.459) Lt: 5.683 (5.683) Accm: 3.77 (3.77) Acct: 5.92 (5.92) proj_loss: -0.5881 (-0.5881) time: 0.9834 data: 0.0003 [11-24 00:43:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 417/1669] eta: 0:21:32 tlr: 0.0002 tnm: 0.22 Lm: 6.715 (6.715) Lt: 5.932 (5.932) Accm: 2.56 (2.56) Acct: 4.13 (4.13) proj_loss: -0.5949 (-0.5949) time: 0.9834 data: 0.0003 [11-24 00:43:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 417/1669] eta: 0:21:32 tlr: 0.0002 tnm: 0.22 Lm: 6.525 (6.525) Lt: 5.835 (5.835) Accm: 3.34 (3.34) Acct: 4.86 (4.86) proj_loss: -0.6152 (-0.6152) time: 0.9834 data: 0.0003 [11-24 00:43:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 417/1669] eta: 0:21:32 tlr: 0.0002 tnm: 0.22 Lm: 6.522 (6.522) Lt: 5.729 (5.729) Accm: 3.17 (3.17) Acct: 5.06 (5.06) proj_loss: -0.5923 (-0.5923) time: 0.9834 data: 0.0003 [11-24 00:43:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 417/1669] eta: 0:21:32 tlr: 0.0002 tnm: 0.22 Lm: 6.666 (6.666) Lt: 5.920 (5.920) Accm: 2.78 (2.78) Acct: 4.42 (4.42) proj_loss: -0.5944 (-0.5944) time: 0.9835 data: 0.0003 [11-24 00:43:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 417/1669] eta: 0:21:32 tlr: 0.0002 tnm: 0.22 Lm: 6.426 (6.426) Lt: 5.673 (5.673) Accm: 3.54 (3.54) Acct: 5.18 (5.18) proj_loss: -0.6008 (-0.6008) time: 0.9835 data: 0.0003 [11-24 00:43:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 417/1669] eta: 0:21:32 tlr: 0.0002 tnm: 0.22 Lm: 6.543 (6.543) Lt: 5.829 (5.829) Accm: 3.45 (3.45) Acct: 5.41 (5.41) proj_loss: -0.5936 (-0.5936) time: 0.9835 data: 0.0003 [11-24 00:43:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 417/1669] eta: 0:21:32 tlr: 0.0002 tnm: 0.22 Lm: 6.517 (6.517) Lt: 5.760 (5.760) Accm: 3.37 (3.37) Acct: 5.03 (5.03) proj_loss: -0.5760 (-0.5760) time: 0.9834 data: 0.0003 [11-24 00:49:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 834/1669] eta: 0:13:39 tlr: 0.0002 tnm: 0.22 Lm: 6.548 (6.580) Lt: 5.820 (5.812) Accm: 3.23 (3.22) Acct: 4.89 (4.98) proj_loss: -0.5739 (-0.5725) time: 0.9294 data: 0.0003 [11-24 00:49:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 834/1669] eta: 0:13:39 tlr: 0.0002 tnm: 0.22 Lm: 6.294 (6.450) Lt: 5.555 (5.687) Accm: 3.95 (3.65) Acct: 6.06 (5.77) proj_loss: -0.5855 (-0.5909) time: 0.9294 data: 0.0003 [11-24 00:49:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 834/1669] eta: 0:13:39 tlr: 0.0002 tnm: 0.22 Lm: 6.647 (6.561) Lt: 5.874 (5.794) Accm: 2.81 (3.19) Acct: 4.65 (5.02) proj_loss: -0.5961 (-0.5950) time: 0.9294 data: 0.0003 [11-24 00:49:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 834/1669] eta: 0:13:39 tlr: 0.0002 tnm: 0.22 Lm: 6.723 (6.733) Lt: 5.970 (5.953) Accm: 2.56 (2.59) Acct: 4.13 (4.20) proj_loss: -0.5735 (-0.5878) time: 0.9294 data: 0.0007 [11-24 00:49:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 834/1669] eta: 0:13:39 tlr: 0.0002 tnm: 0.22 Lm: 6.609 (6.550) Lt: 5.779 (5.798) Accm: 3.29 (3.44) Acct: 5.34 (5.44) proj_loss: -0.6004 (-0.5922) time: 0.9294 data: 0.0003 [11-24 00:49:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 834/1669] eta: 0:13:39 tlr: 0.0002 tnm: 0.22 Lm: 6.513 (6.521) Lt: 5.755 (5.807) Accm: 3.47 (3.38) Acct: 5.06 (4.92) proj_loss: -0.6099 (-0.6134) time: 0.9294 data: 0.0003 [11-24 00:49:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 834/1669] eta: 0:13:39 tlr: 0.0002 tnm: 0.22 Lm: 6.464 (6.494) Lt: 5.723 (5.727) Accm: 3.45 (3.27) Acct: 5.41 (5.18) proj_loss: -0.5959 (-0.6026) time: 0.9294 data: 0.0003 [11-24 00:49:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [ 834/1669] eta: 0:13:39 tlr: 0.0002 tnm: 0.22 Lm: 6.495 (6.486) Lt: 5.794 (5.734) Accm: 3.29 (3.39) Acct: 4.72 (5.03) proj_loss: -0.5826 (-0.5935) time: 0.9294 data: 0.0003 [11-24 00:56:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [1251/1669] eta: 0:06:43 tlr: 0.0002 tnm: 0.21 Lm: 6.483 (6.482) Lt: 5.718 (5.711) Accm: 3.42 (3.43) Acct: 5.20 (5.20) proj_loss: -0.5937 (-0.5964) time: 0.9302 data: 0.0003 [11-24 00:56:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [1251/1669] eta: 0:06:43 tlr: 0.0002 tnm: 0.21 Lm: 6.531 (6.526) Lt: 5.697 (5.752) Accm: 3.37 (3.44) Acct: 5.29 (5.39) proj_loss: -0.5968 (-0.5924) time: 0.9302 data: 0.0003 [11-24 00:56:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [1251/1669] eta: 0:06:43 tlr: 0.0002 tnm: 0.21 Lm: 6.666 (6.606) Lt: 5.920 (5.860) Accm: 2.78 (2.96) Acct: 4.42 (4.65) proj_loss: -0.5953 (-0.5948) time: 0.9302 data: 0.0003 [11-24 00:56:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [1251/1669] eta: 0:06:43 tlr: 0.0002 tnm: 0.21 Lm: 6.451 (6.462) Lt: 5.671 (5.699) Accm: 3.36 (3.27) Acct: 5.49 (5.28) proj_loss: -0.6092 (-0.6076) time: 0.9302 data: 0.0003 [11-24 00:56:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [1251/1669] eta: 0:06:43 tlr: 0.0002 tnm: 0.21 Lm: 6.715 (6.683) Lt: 5.932 (5.893) Accm: 2.61 (2.87) Acct: 4.24 (4.64) proj_loss: -0.5967 (-0.5973) time: 0.9302 data: 0.0003 [11-24 00:56:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [1251/1669] eta: 0:06:43 tlr: 0.0002 tnm: 0.21 Lm: 6.404 (6.466) Lt: 5.692 (5.722) Accm: 3.66 (3.58) Acct: 5.48 (5.55) proj_loss: -0.5871 (-0.5903) time: 0.9302 data: 0.0003 [11-24 00:56:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [1251/1669] eta: 0:06:43 tlr: 0.0002 tnm: 0.21 Lm: 6.572 (6.549) Lt: 5.818 (5.825) Accm: 3.25 (3.30) Acct: 5.08 (4.97) proj_loss: -0.6108 (-0.6130) time: 0.9302 data: 0.0003 [11-24 00:56:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [1251/1669] eta: 0:06:43 tlr: 0.0002 tnm: 0.21 Lm: 6.582 (6.589) Lt: 5.867 (5.838) Accm: 3.11 (3.17) Acct: 4.84 (4.84) proj_loss: -0.5760 (-0.5751) time: 0.9302 data: 0.0003 [11-24 01:02:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.604 (6.592) Lt: 5.845 (5.839) Accm: 3.21 (3.17) Acct: 4.89 (4.92) proj_loss: -0.5781 (-0.5804) time: 0.9330 data: 0.0016 [11-24 01:02:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 73/350] Total time: 0:26:38 (0.957 s / it) [11-24 01:02:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.647 (6.555) Lt: 5.874 (5.799) Accm: 2.81 (3.10) Acct: 4.65 (4.86) proj_loss: -0.5944 (-0.5898) time: 0.9330 data: 0.0013 [11-24 01:02:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.514 (6.478) Lt: 5.743 (5.727) Accm: 3.38 (3.47) Acct: 4.92 (5.43) proj_loss: -0.5855 (-0.5869) time: 0.9330 data: 0.0016 [11-24 01:02:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.513 (6.501) Lt: 5.755 (5.768) Accm: 3.47 (3.43) Acct: 5.10 (5.13) proj_loss: -0.6099 (-0.6080) time: 0.9330 data: 0.0017 [11-24 01:02:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.706 (6.636) Lt: 5.895 (5.849) Accm: 2.65 (3.00) Acct: 4.34 (4.77) proj_loss: -0.5747 (-0.5928) time: 0.9330 data: 0.0016 [11-24 01:02:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.464 (6.490) Lt: 5.723 (5.739) Accm: 3.26 (3.16) Acct: 5.41 (5.06) proj_loss: -0.5959 (-0.6036) time: 0.9330 data: 0.0016 [11-24 01:02:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.470 (6.476) Lt: 5.714 (5.712) Accm: 3.55 (3.50) Acct: 5.68 (5.33) proj_loss: -0.6049 (-0.5994) time: 0.9330 data: 0.0016 [11-24 01:02:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 73/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.454 (6.498) Lt: 5.629 (5.727) Accm: 3.44 (3.52) Acct: 5.34 (5.52) proj_loss: -0.5931 (-0.5919) time: 0.9330 data: 0.0021 [11-24 01:02:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 73/350] Total time: 0:26:38 (0.957 s / it) [11-24 01:02:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 73/350] Total time: 0:26:38 (0.957 s / it) [11-24 01:02:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 73/350] Total time: 0:26:38 (0.957 s / it) [11-24 01:02:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 73/350] Total time: 0:26:38 (0.957 s / it) [11-24 01:02:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 73/350] Total time: 0:26:38 (0.957 s / it) [11-24 01:02:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 73/350] Total time: 0:26:38 (0.957 s / it) [11-24 01:02:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 73/350] Total time: 0:26:38 (0.957 s / it) [11-24 01:02:57] (/home/user/VAR/train.py , line 276)=> [ep73] (training ) Lm: 6.543 (6.549), Lt: 5.784 (5.795), Acc m&t: 3.26 5.17, Remain: 5 days, 0:20:09, Finish: 2024-11-28 09:23 [11-24 01:02:57] (/home/user/VAR/train.py , line 276)=> [ep73] (training ) Lm: 6.543 (6.549), Lt: 5.784 (5.795), Acc m&t: 3.26 5.17, Remain: 5 days, 0:18:38, Finish: 2024-11-28 09:21 [11-24 01:02:57] (/home/user/VAR/train.py , line 276)=> [ep73] (training ) Lm: 6.543 (6.549), Lt: 5.784 (5.795), Acc m&t: 3.26 5.17, Remain: 5 days, 0:19:26, Finish: 2024-11-28 09:22 [11-24 01:02:57] (/home/user/VAR/train.py , line 276)=> [ep73] (training ) Lm: 6.543 (6.549), Lt: 5.784 (5.795), Acc m&t: 3.26 5.17, Remain: 5 days, 0:18:48, Finish: 2024-11-28 09:21 [11-24 01:02:57] (/home/user/VAR/train.py , line 276)=> [ep73] (training ) Lm: 6.543 (6.549), Lt: 5.784 (5.795), Acc m&t: 3.26 5.17, Remain: 5 days, 0:20:17, Finish: 2024-11-28 09:23 [11-24 01:02:57] (/home/user/VAR/train.py , line 276)=> [ep73] (training ) Lm: 6.543 (6.549), Lt: 5.784 (5.795), Acc m&t: 3.26 5.17, Remain: 5 days, 0:19:48, Finish: 2024-11-28 09:22 [11-24 01:02:57] (/home/user/VAR/train.py , line 276)=> [ep73] (training ) Lm: 6.543 (6.549), Lt: 5.784 (5.795), Acc m&t: 3.26 5.17, Remain: 5 days, 0:19:55, Finish: 2024-11-28 09:22 [11-24 01:02:57] (/home/user/VAR/train.py , line 276)=> [ep73] (training ) Lm: 6.543 (6.549), Lt: 5.784 (5.795), Acc m&t: 3.26 5.17, Remain: 5 days, 0:17:47, Finish: 2024-11-28 09:20 [11-24 01:02:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 0/1669] eta: 0:25:16 tlr: 0.0002 tnm: 0.22 Lm: 6.610 (6.610) Lt: 5.828 (5.828) Accm: 2.61 (2.61) Acct: 4.44 (4.44) proj_loss: -0.5781 (-0.5781) time: 0.9086 data: 0.0004 [11-24 01:02:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 0/1669] eta: 0:25:23 tlr: 0.0002 tnm: 0.22 Lm: 6.537 (6.537) Lt: 5.806 (5.806) Accm: 3.53 (3.53) Acct: 5.85 (5.85) proj_loss: -0.5844 (-0.5844) time: 0.9129 data: 0.0004 [11-24 01:02:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 0/1669] eta: 0:25:22 tlr: 0.0002 tnm: 0.22 Lm: 6.620 (6.620) Lt: 5.933 (5.933) Accm: 3.10 (3.10) Acct: 4.79 (4.79) proj_loss: -0.6137 (-0.6137) time: 0.9124 data: 0.0004 [11-24 01:02:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 0/1669] eta: 0:25:18 tlr: 0.0002 tnm: 0.22 Lm: 6.607 (6.607) Lt: 5.796 (5.796) Accm: 2.86 (2.86) Acct: 5.03 (5.03) proj_loss: -0.5751 (-0.5751) time: 0.9097 data: 0.0004 [11-24 01:02:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 0/1669] eta: 0:25:23 tlr: 0.0002 tnm: 0.22 Lm: 6.655 (6.655) Lt: 5.895 (5.895) Accm: 2.94 (2.94) Acct: 4.72 (4.72) proj_loss: -0.5695 (-0.5695) time: 0.9130 data: 0.0004 [11-24 01:02:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 0/1669] eta: 0:25:24 tlr: 0.0002 tnm: 0.22 Lm: 6.792 (6.792) Lt: 6.020 (6.020) Accm: 2.71 (2.71) Acct: 4.75 (4.75) proj_loss: -0.5952 (-0.5952) time: 0.9136 data: 0.0004 [11-24 01:02:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 0/1669] eta: 0:25:18 tlr: 0.0002 tnm: 0.22 Lm: 6.702 (6.702) Lt: 6.026 (6.026) Accm: 2.80 (2.80) Acct: 4.55 (4.55) proj_loss: -0.6076 (-0.6076) time: 0.9099 data: 0.0004 [11-24 01:02:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 0/1669] eta: 0:25:24 tlr: 0.0002 tnm: 0.22 Lm: 6.461 (6.461) Lt: 5.649 (5.649) Accm: 3.32 (3.32) Acct: 5.20 (5.20) proj_loss: -0.5921 (-0.5921) time: 0.9137 data: 0.0004 [11-24 01:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.21 Lm: 6.409 (6.409) Lt: 5.615 (5.615) Accm: 3.45 (3.45) Acct: 5.42 (5.42) proj_loss: -0.5919 (-0.5919) time: 0.9313 data: 0.0003 [11-24 01:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.21 Lm: 6.595 (6.595) Lt: 5.817 (5.817) Accm: 3.28 (3.28) Acct: 5.32 (5.32) proj_loss: -0.5679 (-0.5679) time: 0.9313 data: 0.0003 [11-24 01:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.21 Lm: 6.625 (6.625) Lt: 5.873 (5.873) Accm: 3.34 (3.34) Acct: 5.27 (5.27) proj_loss: -0.6051 (-0.6051) time: 0.9313 data: 0.0003 [11-24 01:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.21 Lm: 6.487 (6.487) Lt: 5.677 (5.677) Accm: 3.80 (3.80) Acct: 6.42 (6.42) proj_loss: -0.5745 (-0.5745) time: 0.9313 data: 0.0003 [11-24 01:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.21 Lm: 6.601 (6.601) Lt: 5.863 (5.863) Accm: 2.78 (2.78) Acct: 4.61 (4.61) proj_loss: -0.5963 (-0.5963) time: 0.9313 data: 0.0003 [11-24 01:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.21 Lm: 6.534 (6.534) Lt: 5.763 (5.763) Accm: 3.23 (3.23) Acct: 5.39 (5.39) proj_loss: -0.5907 (-0.5907) time: 0.9313 data: 0.0003 [11-24 01:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.21 Lm: 6.667 (6.667) Lt: 5.959 (5.959) Accm: 3.18 (3.18) Acct: 5.17 (5.17) proj_loss: -0.6122 (-0.6122) time: 0.9313 data: 0.0003 [11-24 01:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.21 Lm: 6.662 (6.662) Lt: 5.909 (5.909) Accm: 2.88 (2.88) Acct: 4.32 (4.32) proj_loss: -0.5756 (-0.5756) time: 0.9313 data: 0.0003 [11-24 01:16:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 834/1669] eta: 0:13:17 tlr: 0.0002 tnm: 0.21 Lm: 6.620 (6.549) Lt: 5.884 (5.771) Accm: 3.10 (3.28) Acct: 4.79 (4.92) proj_loss: -0.5503 (-0.5672) time: 0.9327 data: 0.0003 [11-24 01:16:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 834/1669] eta: 0:13:17 tlr: 0.0002 tnm: 0.21 Lm: 6.465 (6.571) Lt: 5.727 (5.815) Accm: 3.54 (3.40) Acct: 5.37 (5.30) proj_loss: -0.6008 (-0.6036) time: 0.9328 data: 0.0003 [11-24 01:16:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 834/1669] eta: 0:13:17 tlr: 0.0002 tnm: 0.21 Lm: 6.592 (6.568) Lt: 5.828 (5.832) Accm: 2.96 (3.09) Acct: 4.79 (5.11) proj_loss: -0.5914 (-0.5947) time: 0.9327 data: 0.0003 [11-24 01:16:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 834/1669] eta: 0:13:17 tlr: 0.0002 tnm: 0.21 Lm: 6.461 (6.466) Lt: 5.649 (5.699) Accm: 3.32 (3.31) Acct: 5.20 (5.15) proj_loss: -0.5917 (-0.5804) time: 0.9327 data: 0.0003 [11-24 01:16:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 834/1669] eta: 0:13:17 tlr: 0.0002 tnm: 0.21 Lm: 6.537 (6.548) Lt: 5.806 (5.764) Accm: 3.53 (3.52) Acct: 5.85 (5.72) proj_loss: -0.5785 (-0.5758) time: 0.9328 data: 0.0003 [11-24 01:16:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 834/1669] eta: 0:13:17 tlr: 0.0002 tnm: 0.21 Lm: 6.607 (6.562) Lt: 5.796 (5.843) Accm: 3.35 (3.27) Acct: 5.06 (5.28) proj_loss: -0.5882 (-0.5899) time: 0.9327 data: 0.0003 [11-24 01:16:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 834/1669] eta: 0:13:17 tlr: 0.0002 tnm: 0.21 Lm: 6.631 (6.627) Lt: 5.891 (5.914) Accm: 3.12 (3.16) Acct: 4.96 (5.10) proj_loss: -0.6076 (-0.6059) time: 0.9328 data: 0.0003 [11-24 01:16:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [ 834/1669] eta: 0:13:17 tlr: 0.0002 tnm: 0.21 Lm: 6.536 (6.558) Lt: 5.750 (5.795) Accm: 3.58 (3.38) Acct: 5.92 (5.53) proj_loss: -0.5695 (-0.5746) time: 0.9327 data: 0.0003 [11-24 01:22:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.510 (6.517) Lt: 5.745 (5.750) Accm: 3.60 (3.46) Acct: 5.75 (5.54) proj_loss: -0.5787 (-0.5831) time: 0.9314 data: 0.0003 [11-24 01:22:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.582 (6.568) Lt: 5.832 (5.788) Accm: 3.24 (3.33) Acct: 5.08 (5.36) proj_loss: -0.5779 (-0.5762) time: 0.9314 data: 0.0003 [11-24 01:22:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.546 (6.509) Lt: 5.799 (5.789) Accm: 3.26 (3.21) Acct: 5.06 (5.17) proj_loss: -0.5848 (-0.5889) time: 0.9314 data: 0.0003 [11-24 01:22:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.530 (6.578) Lt: 5.822 (5.840) Accm: 3.31 (3.33) Acct: 5.06 (5.12) proj_loss: -0.6079 (-0.6089) time: 0.9314 data: 0.0003 [11-24 01:22:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.613 (6.632) Lt: 5.899 (5.905) Accm: 3.10 (3.07) Acct: 5.04 (4.92) proj_loss: -0.5904 (-0.5906) time: 0.9314 data: 0.0003 [11-24 01:22:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.442 (6.455) Lt: 5.677 (5.700) Accm: 3.37 (3.34) Acct: 5.32 (5.23) proj_loss: -0.5919 (-0.5863) time: 0.9314 data: 0.0003 [11-24 01:22:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.590 (6.607) Lt: 5.859 (5.885) Accm: 3.23 (3.21) Acct: 5.23 (5.20) proj_loss: -0.6005 (-0.5971) time: 0.9314 data: 0.0003 [11-24 01:22:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.662 (6.641) Lt: 5.909 (5.897) Accm: 2.88 (3.09) Acct: 4.34 (4.67) proj_loss: -0.5737 (-0.5747) time: 0.9314 data: 0.0003 [11-24 01:29:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.620 (6.592) Lt: 5.884 (5.841) Accm: 3.10 (3.23) Acct: 4.79 (4.88) proj_loss: -0.5956 (-0.5788) time: 0.9320 data: 0.0016 [11-24 01:29:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 74/350] Total time: 0:26:46 (0.963 s / it) [11-24 01:29:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.596 (6.585) Lt: 5.916 (5.861) Accm: 3.18 (3.30) Acct: 4.86 (5.07) proj_loss: -0.6053 (-0.6082) time: 0.9320 data: 0.0023 [11-24 01:29:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.592 (6.548) Lt: 5.828 (5.840) Accm: 2.96 (3.12) Acct: 4.79 (5.01) proj_loss: -0.5782 (-0.5868) time: 0.9320 data: 0.0016 [11-24 01:29:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.484 (6.509) Lt: 5.739 (5.736) Accm: 3.58 (3.44) Acct: 5.58 (5.45) proj_loss: -0.5879 (-0.5849) time: 0.9320 data: 0.0016 [11-24 01:29:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.549 (6.581) Lt: 5.826 (5.867) Accm: 3.34 (3.34) Acct: 5.51 (5.30) proj_loss: -0.6076 (-0.6002) time: 0.9320 data: 0.0018 [11-24 01:29:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.627 (6.582) Lt: 5.857 (5.823) Accm: 2.96 (3.20) Acct: 4.30 (5.10) proj_loss: -0.5785 (-0.5796) time: 0.9320 data: 0.0017 [11-24 01:29:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.422 (6.439) Lt: 5.649 (5.678) Accm: 3.41 (3.35) Acct: 5.27 (5.23) proj_loss: -0.5921 (-0.5885) time: 0.9320 data: 0.0015 [11-24 01:29:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 74/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.607 (6.614) Lt: 5.796 (5.877) Accm: 3.35 (3.16) Acct: 5.06 (5.17) proj_loss: -0.5882 (-0.5897) time: 0.9320 data: 0.0019 [11-24 01:29:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 74/350] Total time: 0:26:46 (0.963 s / it) [11-24 01:29:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 74/350] Total time: 0:26:46 (0.963 s / it) [11-24 01:29:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 74/350] Total time: 0:26:46 (0.963 s / it) [11-24 01:29:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 74/350] Total time: 0:26:46 (0.963 s / it) [11-24 01:29:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 74/350] Total time: 0:26:46 (0.963 s / it) [11-24 01:29:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 74/350] Total time: 0:26:46 (0.963 s / it) [11-24 01:29:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 74/350] Total time: 0:26:46 (0.963 s / it) [11-24 01:29:44] (/home/user/VAR/train.py , line 276)=> [ep74] (training ) Lm: 6.541 (6.541), Lt: 5.784 (5.790), Acc m&t: 3.27 5.17, Remain: 4 days, 23:23:35, Finish: 2024-11-28 08:53 [11-24 01:29:44] (/home/user/VAR/train.py , line 276)=> [ep74] (training ) Lm: 6.541 (6.541), Lt: 5.784 (5.790), Acc m&t: 3.27 5.17, Remain: 4 days, 23:22:10, Finish: 2024-11-28 08:51 [11-24 01:29:44] (/home/user/VAR/train.py , line 276)=> [ep74] (training ) Lm: 6.541 (6.541), Lt: 5.784 (5.790), Acc m&t: 3.27 5.17, Remain: 4 days, 23:23:43, Finish: 2024-11-28 08:53 [11-24 01:29:44] (/home/user/VAR/train.py , line 276)=> [ep74] (training ) Lm: 6.541 (6.541), Lt: 5.784 (5.790), Acc m&t: 3.27 5.17, Remain: 4 days, 23:23:11, Finish: 2024-11-28 08:52 [11-24 01:29:44] (/home/user/VAR/train.py , line 276)=> [ep74] (training ) Lm: 6.541 (6.541), Lt: 5.784 (5.790), Acc m&t: 3.27 5.17, Remain: 4 days, 23:23:04, Finish: 2024-11-28 08:52 [11-24 01:29:44] (/home/user/VAR/train.py , line 276)=> [ep74] (training ) Lm: 6.541 (6.541), Lt: 5.784 (5.790), Acc m&t: 3.27 5.17, Remain: 4 days, 23:23:59, Finish: 2024-11-28 08:53 [11-24 01:29:44] (/home/user/VAR/train.py , line 276)=> [ep74] (training ) Lm: 6.541 (6.541), Lt: 5.784 (5.790), Acc m&t: 3.27 5.17, Remain: 4 days, 23:24:13, Finish: 2024-11-28 08:53 [11-24 01:29:44] (/home/user/VAR/train.py , line 276)=> [ep74] (training ) Lm: 6.541 (6.541), Lt: 5.784 (5.790), Acc m&t: 3.27 5.17, Remain: 4 days, 23:24:19, Finish: 2024-11-28 08:54 [11-24 01:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 0/1669] eta: 0:25:17 tlr: 0.0002 tnm: 0.21 Lm: 6.485 (6.485) Lt: 5.804 (5.804) Accm: 3.37 (3.37) Acct: 4.99 (4.99) proj_loss: -0.5983 (-0.5983) time: 0.9090 data: 0.0004 [11-24 01:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 0/1669] eta: 0:25:17 tlr: 0.0002 tnm: 0.21 Lm: 6.498 (6.498) Lt: 5.761 (5.761) Accm: 2.87 (2.87) Acct: 4.27 (4.27) proj_loss: -0.5903 (-0.5903) time: 0.9094 data: 0.0003 [11-24 01:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 0/1669] eta: 0:25:17 tlr: 0.0002 tnm: 0.21 Lm: 6.656 (6.656) Lt: 5.926 (5.926) Accm: 3.29 (3.29) Acct: 5.06 (5.06) proj_loss: -0.5814 (-0.5814) time: 0.9093 data: 0.0004 [11-24 01:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 0/1669] eta: 0:25:17 tlr: 0.0002 tnm: 0.21 Lm: 6.693 (6.693) Lt: 5.958 (5.958) Accm: 2.81 (2.81) Acct: 4.30 (4.30) proj_loss: -0.6026 (-0.6026) time: 0.9094 data: 0.0004 [11-24 01:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 0/1669] eta: 0:25:24 tlr: 0.0002 tnm: 0.21 Lm: 6.638 (6.638) Lt: 5.971 (5.971) Accm: 2.80 (2.80) Acct: 4.03 (4.03) proj_loss: -0.6087 (-0.6087) time: 0.9132 data: 0.0004 [11-24 01:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 0/1669] eta: 0:25:17 tlr: 0.0002 tnm: 0.21 Lm: 6.344 (6.344) Lt: 5.489 (5.489) Accm: 4.14 (4.14) Acct: 6.78 (6.78) proj_loss: -0.6228 (-0.6228) time: 0.9094 data: 0.0004 [11-24 01:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 0/1669] eta: 0:25:17 tlr: 0.0002 tnm: 0.21 Lm: 6.505 (6.505) Lt: 5.791 (5.791) Accm: 3.12 (3.12) Acct: 4.86 (4.86) proj_loss: -0.6129 (-0.6129) time: 0.9095 data: 0.0004 [11-24 01:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 0/1669] eta: 0:25:19 tlr: 0.0002 tnm: 0.21 Lm: 6.599 (6.599) Lt: 5.793 (5.793) Accm: 2.71 (2.71) Acct: 4.30 (4.30) proj_loss: -0.5796 (-0.5796) time: 0.9107 data: 0.0003 [11-24 01:36:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.20 Lm: 6.537 (6.537) Lt: 5.785 (5.785) Accm: 3.02 (3.02) Acct: 4.68 (4.68) proj_loss: -0.6064 (-0.6064) time: 0.9323 data: 0.0003 [11-24 01:36:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.20 Lm: 6.540 (6.540) Lt: 5.855 (5.855) Accm: 3.44 (3.44) Acct: 5.11 (5.11) proj_loss: -0.6061 (-0.6061) time: 0.9323 data: 0.0003 [11-24 01:36:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.20 Lm: 6.590 (6.590) Lt: 5.872 (5.872) Accm: 2.80 (2.80) Acct: 4.46 (4.46) proj_loss: -0.5970 (-0.5970) time: 0.9323 data: 0.0002 [11-24 01:36:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.20 Lm: 6.552 (6.552) Lt: 5.766 (5.766) Accm: 3.29 (3.29) Acct: 5.41 (5.41) proj_loss: -0.6075 (-0.6075) time: 0.9323 data: 0.0003 [11-24 01:36:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.20 Lm: 6.665 (6.665) Lt: 5.926 (5.926) Accm: 3.02 (3.02) Acct: 4.72 (4.72) proj_loss: -0.5765 (-0.5765) time: 0.9323 data: 0.0003 [11-24 01:36:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.20 Lm: 6.528 (6.528) Lt: 5.767 (5.767) Accm: 3.10 (3.10) Acct: 4.92 (4.92) proj_loss: -0.6045 (-0.6045) time: 0.9323 data: 0.0003 [11-24 01:36:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.20 Lm: 6.539 (6.539) Lt: 5.851 (5.851) Accm: 3.31 (3.31) Acct: 5.04 (5.04) proj_loss: -0.5888 (-0.5888) time: 0.9323 data: 0.0003 [11-24 01:36:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.20 Lm: 6.636 (6.636) Lt: 5.916 (5.916) Accm: 3.01 (3.01) Acct: 4.53 (4.53) proj_loss: -0.6027 (-0.6027) time: 0.9323 data: 0.0003 [11-24 01:42:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 834/1669] eta: 0:12:59 tlr: 0.0002 tnm: 0.21 Lm: 6.580 (6.596) Lt: 5.874 (5.835) Accm: 3.21 (3.18) Acct: 4.75 (5.03) proj_loss: -0.6026 (-0.5861) time: 0.9306 data: 0.0003 [11-24 01:42:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 834/1669] eta: 0:12:59 tlr: 0.0002 tnm: 0.21 Lm: 6.619 (6.599) Lt: 5.948 (5.897) Accm: 3.12 (2.96) Acct: 4.86 (4.59) proj_loss: -0.6038 (-0.5993) time: 0.9306 data: 0.0003 [11-24 01:42:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 834/1669] eta: 0:12:59 tlr: 0.0002 tnm: 0.21 Lm: 6.656 (6.633) Lt: 5.926 (5.909) Accm: 3.09 (3.04) Acct: 4.37 (4.60) proj_loss: -0.5814 (-0.5814) time: 0.9306 data: 0.0003 [11-24 01:42:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 834/1669] eta: 0:12:59 tlr: 0.0002 tnm: 0.21 Lm: 6.559 (6.596) Lt: 5.772 (5.876) Accm: 2.87 (2.95) Acct: 4.27 (4.42) proj_loss: -0.6003 (-0.6031) time: 0.9306 data: 0.0003 [11-24 01:42:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 834/1669] eta: 0:12:59 tlr: 0.0002 tnm: 0.21 Lm: 6.509 (6.530) Lt: 5.804 (5.806) Accm: 3.51 (3.46) Acct: 5.23 (5.38) proj_loss: -0.5983 (-0.6001) time: 0.9306 data: 0.0004 [11-24 01:42:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 834/1669] eta: 0:12:59 tlr: 0.0002 tnm: 0.21 Lm: 6.489 (6.522) Lt: 5.731 (5.795) Accm: 3.42 (3.35) Acct: 5.41 (5.17) proj_loss: -0.5960 (-0.5912) time: 0.9306 data: 0.0003 [11-24 01:42:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 834/1669] eta: 0:12:59 tlr: 0.0002 tnm: 0.21 Lm: 6.475 (6.515) Lt: 5.778 (5.757) Accm: 3.32 (3.15) Acct: 5.06 (5.05) proj_loss: -0.5961 (-0.6030) time: 0.9306 data: 0.0003 [11-24 01:42:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [ 834/1669] eta: 0:12:59 tlr: 0.0002 tnm: 0.21 Lm: 6.459 (6.521) Lt: 5.753 (5.762) Accm: 3.74 (3.44) Acct: 5.44 (5.42) proj_loss: -0.6172 (-0.6107) time: 0.9306 data: 0.0003 [11-24 01:49:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.21 Lm: 6.415 (6.483) Lt: 5.673 (5.720) Accm: 3.80 (3.55) Acct: 5.60 (5.50) proj_loss: -0.6046 (-0.6037) time: 0.9306 data: 0.0003 [11-24 01:49:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.21 Lm: 6.513 (6.526) Lt: 5.836 (5.821) Accm: 3.51 (3.50) Acct: 5.23 (5.35) proj_loss: -0.5953 (-0.5982) time: 0.9307 data: 0.0003 [11-24 01:49:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.21 Lm: 6.563 (6.583) Lt: 5.842 (5.829) Accm: 3.32 (3.25) Acct: 5.03 (5.10) proj_loss: -0.5957 (-0.5868) time: 0.9307 data: 0.0003 [11-24 01:49:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.21 Lm: 6.665 (6.655) Lt: 5.926 (5.926) Accm: 2.92 (2.96) Acct: 4.37 (4.54) proj_loss: -0.5765 (-0.5781) time: 0.9307 data: 0.0004 [11-24 01:49:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.21 Lm: 6.627 (6.608) Lt: 5.920 (5.896) Accm: 3.09 (2.98) Acct: 4.86 (4.70) proj_loss: -0.5925 (-0.5939) time: 0.9307 data: 0.0003 [11-24 01:49:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.21 Lm: 6.537 (6.550) Lt: 5.785 (5.779) Accm: 3.02 (2.99) Acct: 4.68 (4.85) proj_loss: -0.5888 (-0.5976) time: 0.9307 data: 0.0003 [11-24 01:49:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.21 Lm: 6.464 (6.475) Lt: 5.707 (5.735) Accm: 3.62 (3.48) Acct: 5.73 (5.45) proj_loss: -0.5992 (-0.5940) time: 0.9307 data: 0.0003 [11-24 01:49:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.21 Lm: 6.574 (6.594) Lt: 5.825 (5.877) Accm: 3.10 (3.06) Acct: 4.87 (4.68) proj_loss: -0.6094 (-0.6115) time: 0.9307 data: 0.0003 [11-24 01:55:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.22 Lm: 6.583 (6.592) Lt: 5.879 (5.879) Accm: 3.07 (3.06) Acct: 4.75 (4.70) proj_loss: -0.6186 (-0.6131) time: 0.9293 data: 0.0019 [11-24 01:55:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 75/350] Total time: 0:25:55 (0.932 s / it) [11-24 01:55:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.22 Lm: 6.580 (6.601) Lt: 5.874 (5.843) Accm: 3.21 (3.17) Acct: 4.75 (5.01) proj_loss: -0.5888 (-0.5844) time: 0.9293 data: 0.0017 [11-24 01:55:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.22 Lm: 6.511 (6.542) Lt: 5.792 (5.781) Accm: 3.32 (3.07) Acct: 4.89 (4.86) proj_loss: -0.5961 (-0.5997) time: 0.9293 data: 0.0013 [11-24 01:55:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.22 Lm: 6.619 (6.583) Lt: 5.893 (5.872) Accm: 3.12 (3.05) Acct: 4.86 (4.71) proj_loss: -0.5866 (-0.5924) time: 0.9293 data: 0.0016 [11-24 01:55:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.22 Lm: 6.489 (6.488) Lt: 5.731 (5.762) Accm: 3.42 (3.39) Acct: 5.41 (5.32) proj_loss: -0.5960 (-0.5927) time: 0.9293 data: 0.0018 [11-24 01:55:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.22 Lm: 6.395 (6.466) Lt: 5.606 (5.697) Accm: 3.74 (3.58) Acct: 5.75 (5.64) proj_loss: -0.6099 (-0.6049) time: 0.9293 data: 0.0016 [11-24 01:55:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.22 Lm: 6.656 (6.606) Lt: 5.926 (5.876) Accm: 3.09 (3.09) Acct: 4.37 (4.77) proj_loss: -0.5814 (-0.5804) time: 0.9293 data: 0.0018 [11-24 01:55:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 75/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.22 Lm: 6.516 (6.536) Lt: 5.804 (5.815) Accm: 3.51 (3.40) Acct: 5.23 (5.25) proj_loss: -0.5922 (-0.5939) time: 0.9293 data: 0.0021 [11-24 01:55:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 75/350] Total time: 0:25:55 (0.932 s / it) [11-24 01:55:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 75/350] Total time: 0:25:55 (0.932 s / it) [11-24 01:55:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 75/350] Total time: 0:25:55 (0.932 s / it) [11-24 01:55:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 75/350] Total time: 0:25:55 (0.932 s / it) [11-24 01:55:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 75/350] Total time: 0:25:55 (0.932 s / it) [11-24 01:55:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 75/350] Total time: 0:25:55 (0.932 s / it) [11-24 01:55:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 75/350] Total time: 0:25:55 (0.932 s / it) [11-24 01:55:40] (/home/user/VAR/train.py , line 276)=> [ep75] (training ) Lm: 6.541 (6.555), Lt: 5.784 (5.801), Acc m&t: 3.27 5.17, Remain: 4 days, 23:01:50, Finish: 2024-11-28 08:57 [11-24 01:55:40] (/home/user/VAR/train.py , line 276)=> [ep75] (training ) Lm: 6.541 (6.555), Lt: 5.784 (5.801), Acc m&t: 3.27 5.17, Remain: 4 days, 23:02:04, Finish: 2024-11-28 08:57 [11-24 01:55:40] (/home/user/VAR/train.py , line 276)=> [ep75] (training ) Lm: 6.541 (6.555), Lt: 5.784 (5.801), Acc m&t: 3.27 5.17, Remain: 4 days, 23:01:22, Finish: 2024-11-28 08:57 [11-24 01:55:40] (/home/user/VAR/train.py , line 276)=> [ep75] (training ) Lm: 6.541 (6.555), Lt: 5.784 (5.801), Acc m&t: 3.27 5.17, Remain: 4 days, 23:03:06, Finish: 2024-11-28 08:58 [11-24 01:55:40] (/home/user/VAR/train.py , line 276)=> [ep75] (training ) Lm: 6.541 (6.555), Lt: 5.784 (5.801), Acc m&t: 3.27 5.17, Remain: 4 days, 23:04:29, Finish: 2024-11-28 09:00 [11-24 01:55:40] (/home/user/VAR/train.py , line 276)=> [ep75] (training ) Lm: 6.541 (6.555), Lt: 5.784 (5.801), Acc m&t: 3.27 5.17, Remain: 4 days, 23:02:54, Finish: 2024-11-28 08:58 [11-24 01:55:40] (/home/user/VAR/train.py , line 276)=> [ep75] (training ) Lm: 6.541 (6.555), Lt: 5.784 (5.801), Acc m&t: 3.27 5.17, Remain: 4 days, 23:04:30, Finish: 2024-11-28 09:00 [11-24 01:55:40] (/home/user/VAR/train.py , line 276)=> [ep75] (training ) Lm: 6.541 (6.555), Lt: 5.784 (5.801), Acc m&t: 3.27 5.17, Remain: 4 days, 23:01:27, Finish: 2024-11-28 08:57 [11-24 01:55:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 0/1669] eta: 0:25:10 tlr: 0.0002 tnm: 0.21 Lm: 6.817 (6.817) Lt: 6.080 (6.080) Accm: 2.43 (2.43) Acct: 4.06 (4.06) proj_loss: -0.5854 (-0.5854) time: 0.9053 data: 0.0003 [11-24 01:55:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 0/1669] eta: 0:25:11 tlr: 0.0002 tnm: 0.21 Lm: 6.569 (6.569) Lt: 5.791 (5.791) Accm: 3.38 (3.38) Acct: 5.68 (5.68) proj_loss: -0.6065 (-0.6065) time: 0.9055 data: 0.0004 [11-24 01:55:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 0/1669] eta: 0:25:11 tlr: 0.0002 tnm: 0.21 Lm: 6.398 (6.398) Lt: 5.677 (5.677) Accm: 3.73 (3.73) Acct: 5.96 (5.96) proj_loss: -0.5915 (-0.5915) time: 0.9057 data: 0.0003 [11-24 01:55:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 0/1669] eta: 0:25:11 tlr: 0.0002 tnm: 0.21 Lm: 6.678 (6.678) Lt: 5.920 (5.920) Accm: 2.72 (2.72) Acct: 3.96 (3.96) proj_loss: -0.5977 (-0.5977) time: 0.9059 data: 0.0004 [11-24 01:55:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 0/1669] eta: 0:25:12 tlr: 0.0002 tnm: 0.21 Lm: 6.590 (6.590) Lt: 5.922 (5.922) Accm: 3.00 (3.00) Acct: 4.65 (4.65) proj_loss: -0.5951 (-0.5951) time: 0.9060 data: 0.0004 [11-24 01:55:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 0/1669] eta: 0:25:12 tlr: 0.0002 tnm: 0.21 Lm: 6.328 (6.328) Lt: 5.521 (5.521) Accm: 3.57 (3.57) Acct: 5.41 (5.41) proj_loss: -0.6030 (-0.6030) time: 0.9059 data: 0.0004 [11-24 01:55:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 0/1669] eta: 0:25:11 tlr: 0.0002 tnm: 0.21 Lm: 6.513 (6.513) Lt: 5.787 (5.787) Accm: 3.55 (3.55) Acct: 5.82 (5.82) proj_loss: -0.6481 (-0.6481) time: 0.9058 data: 0.0004 [11-24 01:55:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 0/1669] eta: 0:25:12 tlr: 0.0002 tnm: 0.21 Lm: 6.321 (6.321) Lt: 5.566 (5.566) Accm: 3.77 (3.77) Acct: 6.03 (6.03) proj_loss: -0.5958 (-0.5958) time: 0.9062 data: 0.0004 [11-24 02:02:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 417/1669] eta: 0:21:02 tlr: 0.0002 tnm: 0.21 Lm: 6.365 (6.365) Lt: 5.620 (5.620) Accm: 3.53 (3.53) Acct: 5.42 (5.42) proj_loss: -0.6066 (-0.6066) time: 1.1038 data: 0.0003 [11-24 02:02:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 417/1669] eta: 0:21:02 tlr: 0.0002 tnm: 0.21 Lm: 6.565 (6.565) Lt: 5.827 (5.827) Accm: 3.23 (3.23) Acct: 5.25 (5.25) proj_loss: -0.6217 (-0.6217) time: 1.1038 data: 0.0003 [11-24 02:02:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 417/1669] eta: 0:21:02 tlr: 0.0002 tnm: 0.21 Lm: 6.643 (6.643) Lt: 5.885 (5.885) Accm: 2.99 (2.99) Acct: 5.04 (5.04) proj_loss: -0.5728 (-0.5728) time: 1.1037 data: 0.0003 [11-24 02:02:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 417/1669] eta: 0:21:02 tlr: 0.0002 tnm: 0.21 Lm: 6.385 (6.385) Lt: 5.639 (5.639) Accm: 3.39 (3.39) Acct: 5.15 (5.15) proj_loss: -0.5932 (-0.5932) time: 1.1038 data: 0.0003 [11-24 02:02:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 417/1669] eta: 0:21:02 tlr: 0.0002 tnm: 0.21 Lm: 6.839 (6.839) Lt: 6.144 (6.144) Accm: 2.51 (2.51) Acct: 3.86 (3.86) proj_loss: -0.6092 (-0.6092) time: 1.1037 data: 0.0003 [11-24 02:02:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 417/1669] eta: 0:21:02 tlr: 0.0002 tnm: 0.21 Lm: 6.533 (6.533) Lt: 5.813 (5.813) Accm: 3.29 (3.29) Acct: 5.20 (5.20) proj_loss: -0.5918 (-0.5918) time: 1.1038 data: 0.0003 [11-24 02:02:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 417/1669] eta: 0:21:02 tlr: 0.0002 tnm: 0.21 Lm: 6.494 (6.494) Lt: 5.769 (5.769) Accm: 3.19 (3.19) Acct: 5.06 (5.06) proj_loss: -0.5884 (-0.5884) time: 1.1037 data: 0.0003 [11-24 02:02:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 417/1669] eta: 0:21:02 tlr: 0.0002 tnm: 0.21 Lm: 6.741 (6.741) Lt: 6.033 (6.033) Accm: 2.83 (2.83) Acct: 4.06 (4.06) proj_loss: -0.6072 (-0.6072) time: 1.1038 data: 0.0003 [11-24 02:09:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 834/1669] eta: 0:13:42 tlr: 0.0002 tnm: 0.22 Lm: 6.678 (6.694) Lt: 5.920 (5.962) Accm: 2.94 (2.95) Acct: 4.17 (4.43) proj_loss: -0.5977 (-0.5938) time: 0.9303 data: 0.0003 [11-24 02:09:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 834/1669] eta: 0:13:42 tlr: 0.0002 tnm: 0.22 Lm: 6.590 (6.548) Lt: 5.896 (5.812) Accm: 3.00 (3.07) Acct: 4.65 (4.92) proj_loss: -0.5951 (-0.6044) time: 0.9303 data: 0.0003 [11-24 02:09:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 834/1669] eta: 0:13:42 tlr: 0.0002 tnm: 0.22 Lm: 6.569 (6.594) Lt: 5.794 (5.854) Accm: 3.38 (3.21) Acct: 5.27 (5.12) proj_loss: -0.5885 (-0.5780) time: 0.9303 data: 0.0003 [11-24 02:09:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 834/1669] eta: 0:13:42 tlr: 0.0002 tnm: 0.22 Lm: 6.668 (6.582) Lt: 5.946 (5.857) Accm: 3.04 (3.21) Acct: 4.48 (4.96) proj_loss: -0.5915 (-0.5851) time: 0.9303 data: 0.0003 [11-24 02:09:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 834/1669] eta: 0:13:42 tlr: 0.0002 tnm: 0.22 Lm: 6.443 (6.409) Lt: 5.696 (5.658) Accm: 3.57 (3.46) Acct: 5.41 (5.37) proj_loss: -0.5835 (-0.5864) time: 0.9303 data: 0.0003 [11-24 02:09:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 834/1669] eta: 0:13:42 tlr: 0.0002 tnm: 0.22 Lm: 6.513 (6.543) Lt: 5.787 (5.809) Accm: 3.15 (3.20) Acct: 4.86 (5.12) proj_loss: -0.5953 (-0.6106) time: 0.9303 data: 0.0003 [11-24 02:09:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 834/1669] eta: 0:13:42 tlr: 0.0002 tnm: 0.22 Lm: 6.817 (6.717) Lt: 6.080 (5.963) Accm: 2.58 (2.88) Acct: 4.06 (4.49) proj_loss: -0.5854 (-0.6011) time: 0.9303 data: 0.0003 [11-24 02:09:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [ 834/1669] eta: 0:13:42 tlr: 0.0002 tnm: 0.22 Lm: 6.321 (6.336) Lt: 5.566 (5.586) Accm: 3.66 (3.57) Acct: 5.58 (5.48) proj_loss: -0.6122 (-0.6085) time: 0.9303 data: 0.0003 [11-24 02:15:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [1251/1669] eta: 0:06:44 tlr: 0.0002 tnm: 0.22 Lm: 6.365 (6.426) Lt: 5.620 (5.699) Accm: 3.47 (3.35) Acct: 5.20 (5.14) proj_loss: -0.6040 (-0.5989) time: 0.9328 data: 0.0003 [11-24 02:15:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [1251/1669] eta: 0:06:44 tlr: 0.0002 tnm: 0.22 Lm: 6.649 (6.658) Lt: 5.898 (5.902) Accm: 2.88 (2.96) Acct: 4.70 (4.70) proj_loss: -0.5852 (-0.5888) time: 0.9328 data: 0.0003 [11-24 02:15:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [1251/1669] eta: 0:06:44 tlr: 0.0002 tnm: 0.22 Lm: 6.674 (6.622) Lt: 5.948 (5.910) Accm: 2.95 (2.98) Acct: 4.46 (4.67) proj_loss: -0.5910 (-0.5865) time: 0.9328 data: 0.0003 [11-24 02:15:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [1251/1669] eta: 0:06:44 tlr: 0.0002 tnm: 0.22 Lm: 6.494 (6.508) Lt: 5.762 (5.766) Accm: 3.19 (3.20) Acct: 5.06 (5.09) proj_loss: -0.6121 (-0.6105) time: 0.9328 data: 0.0003 [11-24 02:15:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [1251/1669] eta: 0:06:44 tlr: 0.0002 tnm: 0.22 Lm: 6.559 (6.582) Lt: 5.792 (5.831) Accm: 3.31 (3.21) Acct: 5.23 (5.14) proj_loss: -0.5906 (-0.5817) time: 0.9328 data: 0.0003 [11-24 02:15:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [1251/1669] eta: 0:06:44 tlr: 0.0002 tnm: 0.22 Lm: 6.639 (6.667) Lt: 5.880 (5.931) Accm: 2.97 (2.96) Acct: 4.34 (4.45) proj_loss: -0.5950 (-0.5934) time: 0.9328 data: 0.0003 [11-24 02:15:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [1251/1669] eta: 0:06:44 tlr: 0.0002 tnm: 0.22 Lm: 6.516 (6.537) Lt: 5.790 (5.805) Accm: 3.35 (3.31) Acct: 5.17 (5.21) proj_loss: -0.6074 (-0.6128) time: 0.9328 data: 0.0003 [11-24 02:15:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [1251/1669] eta: 0:06:44 tlr: 0.0002 tnm: 0.22 Lm: 6.449 (6.465) Lt: 5.727 (5.720) Accm: 3.39 (3.37) Acct: 5.15 (5.22) proj_loss: -0.5808 (-0.5843) time: 0.9328 data: 0.0003 [11-24 02:22:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.513 (6.500) Lt: 5.787 (5.778) Accm: 3.55 (3.37) Acct: 5.27 (5.22) proj_loss: -0.6107 (-0.6124) time: 0.9335 data: 0.0020 [11-24 02:22:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.613 (6.656) Lt: 5.920 (5.934) Accm: 3.00 (3.01) Acct: 4.51 (4.54) proj_loss: -0.5977 (-0.5996) time: 0.9335 data: 0.0016 [11-24 02:22:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.548 (6.562) Lt: 5.791 (5.803) Accm: 3.38 (3.28) Acct: 5.27 (5.21) proj_loss: -0.5926 (-0.5869) time: 0.9335 data: 0.0020 [11-24 02:22:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.481 (6.568) Lt: 5.717 (5.806) Accm: 3.19 (3.25) Acct: 5.34 (5.25) proj_loss: -0.5854 (-0.5959) time: 0.9335 data: 0.0017 [11-24 02:22:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.330 (6.407) Lt: 5.581 (5.676) Accm: 3.66 (3.45) Acct: 5.48 (5.21) proj_loss: -0.6057 (-0.6003) time: 0.9335 data: 0.0019 [11-24 02:22:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.668 (6.606) Lt: 5.946 (5.885) Accm: 3.04 (3.02) Acct: 4.48 (4.76) proj_loss: -0.5915 (-0.5883) time: 0.9335 data: 0.0015 [11-24 02:22:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.467 (6.499) Lt: 5.677 (5.748) Accm: 3.38 (3.26) Acct: 5.48 (5.24) proj_loss: -0.5951 (-0.6057) time: 0.9335 data: 0.0018 [11-24 02:22:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 76/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.455 (6.469) Lt: 5.758 (5.732) Accm: 3.48 (3.39) Acct: 5.41 (5.36) proj_loss: -0.5835 (-0.5906) time: 0.9335 data: 0.0017 [11-24 02:22:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 76/350] Total time: 0:26:40 (0.959 s / it) [11-24 02:22:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 76/350] Total time: 0:26:40 (0.959 s / it) [11-24 02:22:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 76/350] Total time: 0:26:40 (0.959 s / it) [11-24 02:22:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 76/350] Total time: 0:26:40 (0.959 s / it) [11-24 02:22:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 76/350] Total time: 0:26:40 (0.959 s / it) [11-24 02:22:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 76/350] Total time: 0:26:40 (0.959 s / it) [11-24 02:22:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 76/350] Total time: 0:26:40 (0.959 s / it) [11-24 02:22:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 76/350] Total time: 0:26:40 (0.959 s / it) [11-24 02:22:21] (/home/user/VAR/train.py , line 276)=> [ep76] (training ) Lm: 6.541 (6.551), Lt: 5.784 (5.799), Acc m&t: 3.27 5.17, Remain: 4 days, 22:47:51, Finish: 2024-11-28 09:10 [11-24 02:22:21] (/home/user/VAR/train.py , line 276)=> [ep76] (training ) Lm: 6.541 (6.551), Lt: 5.784 (5.799), Acc m&t: 3.27 5.17, Remain: 4 days, 22:48:37, Finish: 2024-11-28 09:10 [11-24 02:22:21] (/home/user/VAR/train.py , line 276)=> [ep76] (training ) Lm: 6.541 (6.551), Lt: 5.784 (5.799), Acc m&t: 3.27 5.17, Remain: 4 days, 22:47:35, Finish: 2024-11-28 09:09 [11-24 02:22:21] (/home/user/VAR/train.py , line 276)=> [ep76] (training ) Lm: 6.541 (6.551), Lt: 5.784 (5.799), Acc m&t: 3.27 5.17, Remain: 4 days, 22:45:56, Finish: 2024-11-28 09:08 [11-24 02:22:21] (/home/user/VAR/train.py , line 276)=> [ep76] (training ) Lm: 6.541 (6.551), Lt: 5.784 (5.799), Acc m&t: 3.27 5.17, Remain: 4 days, 22:48:15, Finish: 2024-11-28 09:10 [11-24 02:22:21] (/home/user/VAR/train.py , line 276)=> [ep76] (training ) Lm: 6.541 (6.551), Lt: 5.784 (5.799), Acc m&t: 3.27 5.17, Remain: 4 days, 22:47:39, Finish: 2024-11-28 09:10 [11-24 02:22:21] (/home/user/VAR/train.py , line 276)=> [ep76] (training ) Lm: 6.541 (6.551), Lt: 5.784 (5.799), Acc m&t: 3.27 5.17, Remain: 4 days, 22:46:22, Finish: 2024-11-28 09:08 [11-24 02:22:21] (/home/user/VAR/train.py , line 276)=> [ep76] (training ) Lm: 6.541 (6.551), Lt: 5.784 (5.799), Acc m&t: 3.27 5.17, Remain: 4 days, 22:46:49, Finish: 2024-11-28 09:09 [11-24 02:22:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 0/1669] eta: 0:25:34 tlr: 0.0002 tnm: 0.21 Lm: 6.445 (6.445) Lt: 5.625 (5.625) Accm: 3.13 (3.13) Acct: 4.99 (4.99) proj_loss: -0.5974 (-0.5974) time: 0.9193 data: 0.0004 [11-24 02:22:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 0/1669] eta: 0:25:27 tlr: 0.0002 tnm: 0.21 Lm: 6.777 (6.777) Lt: 6.133 (6.133) Accm: 2.81 (2.81) Acct: 4.20 (4.20) proj_loss: -0.5784 (-0.5784) time: 0.9152 data: 0.0004 [11-24 02:22:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 0/1669] eta: 0:25:27 tlr: 0.0002 tnm: 0.21 Lm: 6.547 (6.547) Lt: 5.888 (5.888) Accm: 2.90 (2.90) Acct: 4.55 (4.55) proj_loss: -0.5914 (-0.5914) time: 0.9155 data: 0.0004 [11-24 02:22:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 0/1669] eta: 0:25:23 tlr: 0.0002 tnm: 0.21 Lm: 6.568 (6.568) Lt: 5.896 (5.896) Accm: 3.31 (3.31) Acct: 4.96 (4.96) proj_loss: -0.5976 (-0.5976) time: 0.9131 data: 0.0004 [11-24 02:22:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 0/1669] eta: 0:25:28 tlr: 0.0002 tnm: 0.21 Lm: 6.847 (6.847) Lt: 6.191 (6.191) Accm: 2.40 (2.40) Acct: 3.72 (3.72) proj_loss: -0.6093 (-0.6093) time: 0.9155 data: 0.0004 [11-24 02:22:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 0/1669] eta: 0:25:27 tlr: 0.0002 tnm: 0.21 Lm: 6.504 (6.504) Lt: 5.843 (5.843) Accm: 3.22 (3.22) Acct: 4.79 (4.79) proj_loss: -0.5837 (-0.5837) time: 0.9150 data: 0.0002 [11-24 02:22:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 0/1669] eta: 0:25:27 tlr: 0.0002 tnm: 0.21 Lm: 6.665 (6.665) Lt: 5.914 (5.914) Accm: 3.03 (3.03) Acct: 5.03 (5.03) proj_loss: -0.5912 (-0.5912) time: 0.9155 data: 0.0004 [11-24 02:22:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 0/1669] eta: 0:25:28 tlr: 0.0002 tnm: 0.21 Lm: 6.306 (6.306) Lt: 5.477 (5.477) Accm: 3.99 (3.99) Acct: 6.34 (6.34) proj_loss: -0.5596 (-0.5596) time: 0.9158 data: 0.0004 [11-24 02:28:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.21 Lm: 6.355 (6.355) Lt: 5.577 (5.577) Accm: 4.01 (4.01) Acct: 6.13 (6.13) proj_loss: -0.5669 (-0.5669) time: 0.9297 data: 0.0003 [11-24 02:28:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.21 Lm: 6.581 (6.581) Lt: 5.859 (5.859) Accm: 3.15 (3.15) Acct: 5.03 (5.03) proj_loss: -0.5859 (-0.5859) time: 0.9297 data: 0.0003 [11-24 02:28:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.21 Lm: 6.534 (6.534) Lt: 5.820 (5.820) Accm: 3.49 (3.49) Acct: 5.23 (5.23) proj_loss: -0.5910 (-0.5910) time: 0.9297 data: 0.0003 [11-24 02:28:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.21 Lm: 6.495 (6.495) Lt: 5.691 (5.691) Accm: 3.14 (3.14) Acct: 5.06 (5.06) proj_loss: -0.5951 (-0.5951) time: 0.9297 data: 0.0003 [11-24 02:28:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.21 Lm: 6.615 (6.615) Lt: 5.906 (5.906) Accm: 3.10 (3.10) Acct: 4.94 (4.94) proj_loss: -0.5873 (-0.5873) time: 0.9297 data: 0.0003 [11-24 02:28:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.21 Lm: 6.583 (6.583) Lt: 5.820 (5.820) Accm: 3.18 (3.18) Acct: 5.18 (5.18) proj_loss: -0.5833 (-0.5833) time: 0.9297 data: 0.0003 [11-24 02:28:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.21 Lm: 6.630 (6.630) Lt: 5.916 (5.916) Accm: 2.96 (2.96) Acct: 4.55 (4.55) proj_loss: -0.6051 (-0.6051) time: 0.9297 data: 0.0003 [11-24 02:28:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.21 Lm: 6.600 (6.600) Lt: 5.876 (5.876) Accm: 2.83 (2.83) Acct: 4.42 (4.42) proj_loss: -0.5946 (-0.5946) time: 0.9297 data: 0.0003 [11-24 02:35:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 834/1669] eta: 0:12:57 tlr: 0.0002 tnm: 0.22 Lm: 6.653 (6.624) Lt: 5.888 (5.908) Accm: 2.75 (2.76) Acct: 4.30 (4.21) proj_loss: -0.5920 (-0.5938) time: 0.9309 data: 0.0003 [11-24 02:35:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 834/1669] eta: 0:12:57 tlr: 0.0002 tnm: 0.22 Lm: 6.595 (6.619) Lt: 5.811 (5.881) Accm: 3.34 (3.09) Acct: 4.99 (4.69) proj_loss: -0.6009 (-0.6030) time: 0.9309 data: 0.0003 [11-24 02:35:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 834/1669] eta: 0:12:57 tlr: 0.0002 tnm: 0.22 Lm: 6.545 (6.600) Lt: 5.757 (5.801) Accm: 3.13 (2.86) Acct: 4.99 (4.57) proj_loss: -0.5928 (-0.5874) time: 0.9309 data: 0.0003 [11-24 02:35:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 834/1669] eta: 0:12:57 tlr: 0.0002 tnm: 0.22 Lm: 6.528 (6.586) Lt: 5.761 (5.858) Accm: 3.39 (3.28) Acct: 5.48 (5.12) proj_loss: -0.5962 (-0.6014) time: 0.9309 data: 0.0003 [11-24 02:35:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 834/1669] eta: 0:12:57 tlr: 0.0002 tnm: 0.22 Lm: 6.500 (6.546) Lt: 5.727 (5.788) Accm: 3.32 (3.27) Acct: 5.17 (5.18) proj_loss: -0.5912 (-0.5888) time: 0.9309 data: 0.0003 [11-24 02:35:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 834/1669] eta: 0:12:57 tlr: 0.0002 tnm: 0.22 Lm: 6.565 (6.576) Lt: 5.843 (5.840) Accm: 3.22 (3.20) Acct: 5.17 (5.07) proj_loss: -0.5872 (-0.5863) time: 0.9309 data: 0.0003 [11-24 02:35:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 834/1669] eta: 0:12:57 tlr: 0.0002 tnm: 0.22 Lm: 6.568 (6.571) Lt: 5.896 (5.858) Accm: 3.31 (3.35) Acct: 4.96 (5.08) proj_loss: -0.5844 (-0.5878) time: 0.9309 data: 0.0003 [11-24 02:35:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [ 834/1669] eta: 0:12:57 tlr: 0.0002 tnm: 0.22 Lm: 6.403 (6.387) Lt: 5.678 (5.615) Accm: 4.04 (4.04) Acct: 6.27 (6.18) proj_loss: -0.5662 (-0.5667) time: 0.9309 data: 0.0003 [11-24 02:42:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.22 Lm: 6.374 (6.376) Lt: 5.581 (5.582) Accm: 4.01 (3.92) Acct: 6.10 (6.05) proj_loss: -0.5659 (-0.5664) time: 0.9286 data: 0.0003 [11-24 02:42:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.22 Lm: 6.490 (6.543) Lt: 5.720 (5.812) Accm: 3.52 (3.42) Acct: 5.46 (5.20) proj_loss: -0.6005 (-0.6023) time: 0.9286 data: 0.0003 [11-24 02:42:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.22 Lm: 6.600 (6.576) Lt: 5.876 (5.837) Accm: 2.83 (2.96) Acct: 4.42 (4.65) proj_loss: -0.5917 (-0.5927) time: 0.9286 data: 0.0003 [11-24 02:42:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.22 Lm: 6.495 (6.528) Lt: 5.691 (5.730) Accm: 3.14 (3.07) Acct: 5.06 (4.85) proj_loss: -0.5923 (-0.5885) time: 0.9286 data: 0.0003 [11-24 02:42:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.22 Lm: 6.588 (6.580) Lt: 5.836 (5.837) Accm: 3.18 (3.23) Acct: 4.87 (4.95) proj_loss: -0.5829 (-0.5802) time: 0.9286 data: 0.0003 [11-24 02:42:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.22 Lm: 6.486 (6.526) Lt: 5.724 (5.738) Accm: 3.39 (3.32) Acct: 5.25 (5.29) proj_loss: -0.5833 (-0.5829) time: 0.9286 data: 0.0003 [11-24 02:42:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.22 Lm: 6.600 (6.590) Lt: 5.859 (5.862) Accm: 3.15 (3.10) Acct: 4.98 (4.89) proj_loss: -0.5876 (-0.5919) time: 0.9286 data: 0.0003 [11-24 02:42:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.22 Lm: 6.504 (6.524) Lt: 5.726 (5.777) Accm: 3.43 (3.42) Acct: 5.18 (5.25) proj_loss: -0.5999 (-0.6020) time: 0.9286 data: 0.0003 [11-24 02:48:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.413 (6.491) Lt: 5.641 (5.740) Accm: 3.53 (3.49) Acct: 5.37 (5.36) proj_loss: -0.5989 (-0.5978) time: 1.0421 data: 0.0015 [11-24 02:48:59] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 77/350] Total time: 0:26:38 (0.958 s / it) [11-24 02:48:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.545 (6.541) Lt: 5.757 (5.765) Accm: 3.13 (3.06) Acct: 4.99 (4.75) proj_loss: -0.5928 (-0.5913) time: 1.0421 data: 0.0017 [11-24 02:48:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.568 (6.559) Lt: 5.775 (5.818) Accm: 3.31 (3.26) Acct: 4.96 (5.02) proj_loss: -0.5844 (-0.5913) time: 1.0421 data: 0.0016 [11-24 02:48:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.403 (6.443) Lt: 5.678 (5.677) Accm: 3.99 (3.70) Acct: 5.92 (5.71) proj_loss: -0.5662 (-0.5672) time: 1.0421 data: 0.0017 [11-24 02:48:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.653 (6.610) Lt: 5.888 (5.872) Accm: 2.75 (2.86) Acct: 4.30 (4.52) proj_loss: -0.5914 (-0.5919) time: 1.0421 data: 0.0018 [11-24 02:48:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.472 (6.513) Lt: 5.722 (5.725) Accm: 3.37 (3.33) Acct: 5.34 (5.35) proj_loss: -0.5912 (-0.5866) time: 1.0421 data: 0.0016 [11-24 02:48:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.528 (6.546) Lt: 5.761 (5.803) Accm: 3.39 (3.37) Acct: 5.44 (5.19) proj_loss: -0.5973 (-0.6013) time: 1.0421 data: 0.0020 [11-24 02:48:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 77/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.565 (6.569) Lt: 5.843 (5.835) Accm: 3.07 (3.08) Acct: 4.79 (4.81) proj_loss: -0.5880 (-0.5980) time: 1.0421 data: 0.0013 [11-24 02:48:59] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 77/350] Total time: 0:26:38 (0.958 s / it) [11-24 02:48:59] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 77/350] Total time: 0:26:38 (0.958 s / it) [11-24 02:48:59] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 77/350] Total time: 0:26:38 (0.958 s / it) [11-24 02:48:59] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 77/350] Total time: 0:26:38 (0.958 s / it) [11-24 02:48:59] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 77/350] Total time: 0:26:38 (0.958 s / it) [11-24 02:48:59] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 77/350] Total time: 0:26:38 (0.958 s / it) [11-24 02:48:59] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 77/350] Total time: 0:26:38 (0.958 s / it) [11-24 02:48:59] (/home/user/VAR/train.py , line 276)=> [ep77] (training ) Lm: 6.540 (6.540), Lt: 5.784 (5.786), Acc m&t: 3.28 5.17, Remain: 4 days, 22:27:40, Finish: 2024-11-28 09:16 [11-24 02:48:59] (/home/user/VAR/train.py , line 276)=> [ep77] (training ) Lm: 6.540 (6.540), Lt: 5.784 (5.786), Acc m&t: 3.28 5.17, Remain: 4 days, 22:28:17, Finish: 2024-11-28 09:17 [11-24 02:48:59] (/home/user/VAR/train.py , line 276)=> [ep77] (training ) Lm: 6.540 (6.540), Lt: 5.784 (5.786), Acc m&t: 3.28 5.17, Remain: 4 days, 22:27:48, Finish: 2024-11-28 09:16 [11-24 02:48:59] (/home/user/VAR/train.py , line 276)=> [ep77] (training ) Lm: 6.540 (6.540), Lt: 5.784 (5.786), Acc m&t: 3.28 5.17, Remain: 4 days, 22:28:08, Finish: 2024-11-28 09:17 [11-24 02:48:59] (/home/user/VAR/train.py , line 276)=> [ep77] (training ) Lm: 6.540 (6.540), Lt: 5.784 (5.786), Acc m&t: 3.28 5.17, Remain: 4 days, 22:27:50, Finish: 2024-11-28 09:16 [11-24 02:48:59] (/home/user/VAR/train.py , line 276)=> [ep77] (training ) Lm: 6.540 (6.540), Lt: 5.784 (5.786), Acc m&t: 3.28 5.17, Remain: 4 days, 22:26:15, Finish: 2024-11-28 09:15 [11-24 02:48:59] (/home/user/VAR/train.py , line 276)=> [ep77] (training ) Lm: 6.540 (6.540), Lt: 5.784 (5.786), Acc m&t: 3.28 5.17, Remain: 4 days, 22:28:37, Finish: 2024-11-28 09:17 [11-24 02:48:59] (/home/user/VAR/train.py , line 276)=> [ep77] (training ) Lm: 6.540 (6.540), Lt: 5.784 (5.786), Acc m&t: 3.28 5.17, Remain: 4 days, 22:29:05, Finish: 2024-11-28 09:18 [11-24 02:49:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 0/1669] eta: 0:25:00 tlr: 0.0002 tnm: 0.21 Lm: 6.342 (6.342) Lt: 5.590 (5.590) Accm: 4.30 (4.30) Acct: 6.40 (6.40) proj_loss: -0.6031 (-0.6031) time: 0.8988 data: 0.0004 [11-24 02:49:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 0/1669] eta: 0:25:00 tlr: 0.0002 tnm: 0.21 Lm: 6.403 (6.403) Lt: 5.668 (5.668) Accm: 3.44 (3.44) Acct: 5.37 (5.37) proj_loss: -0.5836 (-0.5836) time: 0.8988 data: 0.0004 [11-24 02:49:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 0/1669] eta: 0:24:52 tlr: 0.0002 tnm: 0.21 Lm: 6.380 (6.380) Lt: 5.602 (5.602) Accm: 4.08 (4.08) Acct: 6.23 (6.23) proj_loss: -0.5822 (-0.5822) time: 0.8941 data: 0.0004 [11-24 02:49:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 0/1669] eta: 0:24:52 tlr: 0.0002 tnm: 0.21 Lm: 6.639 (6.639) Lt: 5.861 (5.861) Accm: 3.35 (3.35) Acct: 5.92 (5.92) proj_loss: -0.5809 (-0.5809) time: 0.8942 data: 0.0003 [11-24 02:49:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 0/1669] eta: 0:24:52 tlr: 0.0002 tnm: 0.21 Lm: 6.612 (6.612) Lt: 5.915 (5.915) Accm: 3.02 (3.02) Acct: 4.51 (4.51) proj_loss: -0.5995 (-0.5995) time: 0.8941 data: 0.0003 [11-24 02:49:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 0/1669] eta: 0:24:52 tlr: 0.0002 tnm: 0.21 Lm: 6.603 (6.603) Lt: 5.868 (5.868) Accm: 3.41 (3.41) Acct: 5.44 (5.44) proj_loss: -0.5741 (-0.5741) time: 0.8941 data: 0.0004 [11-24 02:49:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 0/1669] eta: 0:25:01 tlr: 0.0002 tnm: 0.21 Lm: 6.619 (6.619) Lt: 5.883 (5.883) Accm: 3.10 (3.10) Acct: 4.96 (4.96) proj_loss: -0.5952 (-0.5952) time: 0.8994 data: 0.0004 [11-24 02:49:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 0/1669] eta: 0:24:52 tlr: 0.0002 tnm: 0.21 Lm: 6.375 (6.375) Lt: 5.689 (5.689) Accm: 3.45 (3.45) Acct: 5.30 (5.30) proj_loss: -0.5950 (-0.5950) time: 0.8945 data: 0.0004 [11-24 02:55:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 417/1669] eta: 0:19:55 tlr: 0.0002 tnm: 0.22 Lm: 6.551 (6.551) Lt: 5.861 (5.861) Accm: 3.15 (3.15) Acct: 4.96 (4.96) proj_loss: -0.5941 (-0.5941) time: 0.9303 data: 0.0003 [11-24 02:55:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 417/1669] eta: 0:19:55 tlr: 0.0002 tnm: 0.22 Lm: 6.595 (6.595) Lt: 5.840 (5.840) Accm: 3.24 (3.24) Acct: 5.42 (5.42) proj_loss: -0.5785 (-0.5785) time: 0.9303 data: 0.0003 [11-24 02:55:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 417/1669] eta: 0:19:55 tlr: 0.0002 tnm: 0.22 Lm: 6.469 (6.469) Lt: 5.704 (5.704) Accm: 3.58 (3.58) Acct: 5.87 (5.87) proj_loss: -0.5828 (-0.5828) time: 0.9303 data: 0.0003 [11-24 02:55:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 417/1669] eta: 0:19:55 tlr: 0.0002 tnm: 0.22 Lm: 6.439 (6.439) Lt: 5.705 (5.705) Accm: 3.79 (3.79) Acct: 5.53 (5.53) proj_loss: -0.6019 (-0.6019) time: 0.9303 data: 0.0003 [11-24 02:55:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 417/1669] eta: 0:19:55 tlr: 0.0002 tnm: 0.22 Lm: 6.612 (6.612) Lt: 5.888 (5.888) Accm: 2.97 (2.97) Acct: 4.56 (4.56) proj_loss: -0.5814 (-0.5814) time: 0.9303 data: 0.0003 [11-24 02:55:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 417/1669] eta: 0:19:55 tlr: 0.0002 tnm: 0.22 Lm: 6.421 (6.421) Lt: 5.683 (5.683) Accm: 3.39 (3.39) Acct: 5.35 (5.35) proj_loss: -0.5975 (-0.5975) time: 0.9303 data: 0.0003 [11-24 02:55:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 417/1669] eta: 0:19:55 tlr: 0.0002 tnm: 0.22 Lm: 6.440 (6.440) Lt: 5.723 (5.723) Accm: 3.45 (3.45) Acct: 5.22 (5.22) proj_loss: -0.6018 (-0.6018) time: 0.9303 data: 0.0003 [11-24 02:55:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 417/1669] eta: 0:19:55 tlr: 0.0002 tnm: 0.22 Lm: 6.415 (6.415) Lt: 5.698 (5.698) Accm: 3.81 (3.81) Acct: 5.84 (5.84) proj_loss: -0.5687 (-0.5687) time: 0.9303 data: 0.0003 [11-24 03:02:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 834/1669] eta: 0:13:07 tlr: 0.0002 tnm: 0.21 Lm: 6.450 (6.528) Lt: 5.793 (5.787) Accm: 3.54 (3.45) Acct: 5.44 (5.36) proj_loss: -0.5822 (-0.5736) time: 0.9290 data: 0.0003 [11-24 03:02:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 834/1669] eta: 0:13:07 tlr: 0.0002 tnm: 0.21 Lm: 6.551 (6.506) Lt: 5.819 (5.710) Accm: 3.35 (3.38) Acct: 5.89 (5.58) proj_loss: -0.5809 (-0.5818) time: 0.9290 data: 0.0003 [11-24 03:02:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 834/1669] eta: 0:13:07 tlr: 0.0002 tnm: 0.21 Lm: 6.536 (6.512) Lt: 5.820 (5.764) Accm: 3.28 (3.59) Acct: 4.86 (5.30) proj_loss: -0.6031 (-0.6054) time: 0.9290 data: 0.0003 [11-24 03:02:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 834/1669] eta: 0:13:07 tlr: 0.0002 tnm: 0.21 Lm: 6.439 (6.495) Lt: 5.699 (5.749) Accm: 3.35 (3.12) Acct: 5.34 (4.89) proj_loss: -0.5836 (-0.5903) time: 0.9290 data: 0.0003 [11-24 03:02:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 834/1669] eta: 0:13:07 tlr: 0.0002 tnm: 0.21 Lm: 6.389 (6.497) Lt: 5.689 (5.782) Accm: 3.45 (3.35) Acct: 5.30 (5.37) proj_loss: -0.5950 (-0.5952) time: 0.9290 data: 0.0003 [11-24 03:02:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 834/1669] eta: 0:13:07 tlr: 0.0002 tnm: 0.21 Lm: 6.578 (6.505) Lt: 5.847 (5.751) Accm: 3.41 (3.39) Acct: 5.44 (5.49) proj_loss: -0.5916 (-0.5882) time: 0.9290 data: 0.0003 [11-24 03:02:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 834/1669] eta: 0:13:07 tlr: 0.0002 tnm: 0.21 Lm: 6.606 (6.579) Lt: 5.883 (5.830) Accm: 3.07 (3.01) Acct: 4.86 (4.66) proj_loss: -0.5677 (-0.5725) time: 0.9290 data: 0.0002 [11-24 03:02:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [ 834/1669] eta: 0:13:07 tlr: 0.0002 tnm: 0.21 Lm: 6.478 (6.453) Lt: 5.605 (5.684) Accm: 3.89 (3.67) Acct: 5.92 (5.79) proj_loss: -0.5995 (-0.6000) time: 0.9290 data: 0.0003 [11-24 03:08:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [1251/1669] eta: 0:06:32 tlr: 0.0002 tnm: 0.20 Lm: 6.545 (6.520) Lt: 5.760 (5.764) Accm: 3.45 (3.42) Acct: 5.22 (5.35) proj_loss: -0.5979 (-0.5971) time: 0.9324 data: 0.0003 [11-24 03:08:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [1251/1669] eta: 0:06:32 tlr: 0.0002 tnm: 0.20 Lm: 6.595 (6.542) Lt: 5.839 (5.747) Accm: 3.24 (3.22) Acct: 5.41 (5.30) proj_loss: -0.5846 (-0.5842) time: 0.9324 data: 0.0003 [11-24 03:08:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [1251/1669] eta: 0:06:32 tlr: 0.0002 tnm: 0.20 Lm: 6.533 (6.528) Lt: 5.781 (5.778) Accm: 3.04 (3.02) Acct: 4.92 (4.80) proj_loss: -0.5872 (-0.5905) time: 0.9324 data: 0.0003 [11-24 03:08:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [1251/1669] eta: 0:06:32 tlr: 0.0002 tnm: 0.20 Lm: 6.494 (6.522) Lt: 5.769 (5.798) Accm: 3.25 (3.27) Acct: 5.29 (5.35) proj_loss: -0.5941 (-0.5879) time: 0.9324 data: 0.0003 [11-24 03:08:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [1251/1669] eta: 0:06:32 tlr: 0.0002 tnm: 0.20 Lm: 6.439 (6.463) Lt: 5.710 (5.723) Accm: 3.76 (3.76) Acct: 5.42 (5.48) proj_loss: -0.6077 (-0.6130) time: 0.9324 data: 0.0003 [11-24 03:08:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [1251/1669] eta: 0:06:32 tlr: 0.0002 tnm: 0.20 Lm: 6.566 (6.566) Lt: 5.879 (5.835) Accm: 3.16 (3.28) Acct: 5.10 (5.21) proj_loss: -0.5827 (-0.5778) time: 0.9324 data: 0.0003 [11-24 03:08:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [1251/1669] eta: 0:06:32 tlr: 0.0002 tnm: 0.20 Lm: 6.485 (6.477) Lt: 5.709 (5.706) Accm: 3.51 (3.45) Acct: 5.70 (5.60) proj_loss: -0.5952 (-0.5912) time: 0.9324 data: 0.0003 [11-24 03:08:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [1251/1669] eta: 0:06:32 tlr: 0.0002 tnm: 0.20 Lm: 6.560 (6.531) Lt: 5.799 (5.790) Accm: 3.09 (3.09) Acct: 4.91 (4.75) proj_loss: -0.5814 (-0.5793) time: 0.9324 data: 0.0003 [11-24 03:15:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.606 (6.570) Lt: 5.883 (5.830) Accm: 3.07 (2.94) Acct: 4.86 (4.53) proj_loss: -0.5841 (-0.5802) time: 0.9324 data: 0.0018 [11-24 03:15:05] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 78/350] Total time: 0:26:05 (0.938 s / it) [11-24 03:15:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.427 (6.456) Lt: 5.671 (5.713) Accm: 3.57 (3.72) Acct: 5.23 (5.43) proj_loss: -0.6037 (-0.6112) time: 0.9324 data: 0.0014 [11-24 03:15:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.551 (6.500) Lt: 5.819 (5.693) Accm: 3.35 (3.41) Acct: 5.89 (5.57) proj_loss: -0.5871 (-0.5848) time: 0.9324 data: 0.0017 [11-24 03:15:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.463 (6.511) Lt: 5.744 (5.788) Accm: 3.45 (3.32) Acct: 5.30 (5.41) proj_loss: -0.5932 (-0.5876) time: 0.9324 data: 0.0019 [11-24 03:15:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.612 (6.541) Lt: 5.878 (5.786) Accm: 3.02 (3.31) Acct: 4.51 (5.15) proj_loss: -0.5968 (-0.5970) time: 0.9324 data: 0.0018 [11-24 03:15:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.525 (6.558) Lt: 5.793 (5.804) Accm: 3.35 (3.30) Acct: 5.20 (5.21) proj_loss: -0.5822 (-0.5744) time: 0.9324 data: 0.0018 [11-24 03:15:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.481 (6.478) Lt: 5.667 (5.698) Accm: 3.42 (3.44) Acct: 5.61 (5.61) proj_loss: -0.5989 (-0.6015) time: 0.9324 data: 0.0021 [11-24 03:15:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 78/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.439 (6.498) Lt: 5.699 (5.737) Accm: 3.35 (3.14) Acct: 5.34 (5.02) proj_loss: -0.5909 (-0.5966) time: 0.9324 data: 0.0019 [11-24 03:15:05] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 78/350] Total time: 0:26:05 (0.938 s / it) [11-24 03:15:05] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 78/350] Total time: 0:26:05 (0.938 s / it) [11-24 03:15:05] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 78/350] Total time: 0:26:05 (0.938 s / it) [11-24 03:15:05] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 78/350] Total time: 0:26:05 (0.938 s / it) [11-24 03:15:05] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 78/350] Total time: 0:26:05 (0.938 s / it) [11-24 03:15:05] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 78/350] Total time: 0:26:05 (0.938 s / it) [11-24 03:15:05] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 78/350] Total time: 0:26:05 (0.938 s / it) [11-24 03:15:05] (/home/user/VAR/train.py , line 276)=> [ep78] (training ) Lm: 6.540 (6.548), Lt: 5.784 (5.791), Acc m&t: 3.28 5.17, Remain: 4 days, 21:53:33, Finish: 2024-11-28 09:08 [11-24 03:15:05] (/home/user/VAR/train.py , line 276)=> [ep78] (training ) Lm: 6.540 (6.548), Lt: 5.784 (5.791), Acc m&t: 3.28 5.17, Remain: 4 days, 21:57:05, Finish: 2024-11-28 09:12 [11-24 03:15:05] (/home/user/VAR/train.py , line 276)=> [ep78] (training ) Lm: 6.540 (6.548), Lt: 5.784 (5.791), Acc m&t: 3.28 5.17, Remain: 4 days, 21:55:28, Finish: 2024-11-28 09:10 [11-24 03:15:05] (/home/user/VAR/train.py , line 276)=> [ep78] (training ) Lm: 6.540 (6.548), Lt: 5.784 (5.791), Acc m&t: 3.28 5.17, Remain: 4 days, 21:52:29, Finish: 2024-11-28 09:07 [11-24 03:15:05] (/home/user/VAR/train.py , line 276)=> [ep78] (training ) Lm: 6.540 (6.548), Lt: 5.784 (5.791), Acc m&t: 3.28 5.17, Remain: 4 days, 21:56:28, Finish: 2024-11-28 09:11 [11-24 03:15:05] (/home/user/VAR/train.py , line 276)=> [ep78] (training ) Lm: 6.540 (6.548), Lt: 5.784 (5.791), Acc m&t: 3.28 5.17, Remain: 4 days, 21:53:03, Finish: 2024-11-28 09:08 [11-24 03:15:05] (/home/user/VAR/train.py , line 276)=> [ep78] (training ) Lm: 6.540 (6.548), Lt: 5.784 (5.791), Acc m&t: 3.28 5.17, Remain: 4 days, 21:51:41, Finish: 2024-11-28 09:06 [11-24 03:15:05] (/home/user/VAR/train.py , line 276)=> [ep78] (training ) Lm: 6.540 (6.548), Lt: 5.784 (5.791), Acc m&t: 3.28 5.17, Remain: 4 days, 21:55:52, Finish: 2024-11-28 09:10 [11-24 03:15:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 0/1669] eta: 0:25:24 tlr: 0.0002 tnm: 0.21 Lm: 6.770 (6.770) Lt: 6.058 (6.058) Accm: 2.67 (2.67) Acct: 4.06 (4.06) proj_loss: -0.6165 (-0.6165) time: 0.9132 data: 0.0003 [11-24 03:15:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 0/1669] eta: 0:25:24 tlr: 0.0002 tnm: 0.21 Lm: 6.560 (6.560) Lt: 5.755 (5.755) Accm: 3.37 (3.37) Acct: 5.23 (5.23) proj_loss: -0.5587 (-0.5587) time: 0.9133 data: 0.0004 [11-24 03:15:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 0/1669] eta: 0:25:25 tlr: 0.0002 tnm: 0.21 Lm: 6.735 (6.735) Lt: 5.913 (5.913) Accm: 2.84 (2.84) Acct: 4.61 (4.61) proj_loss: -0.5627 (-0.5627) time: 0.9142 data: 0.0004 [11-24 03:15:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 0/1669] eta: 0:25:26 tlr: 0.0002 tnm: 0.21 Lm: 6.525 (6.525) Lt: 5.703 (5.703) Accm: 3.57 (3.57) Acct: 5.82 (5.82) proj_loss: -0.6140 (-0.6140) time: 0.9144 data: 0.0004 [11-24 03:15:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 0/1669] eta: 0:25:26 tlr: 0.0002 tnm: 0.21 Lm: 6.551 (6.551) Lt: 5.758 (5.758) Accm: 3.50 (3.50) Acct: 5.37 (5.37) proj_loss: -0.5667 (-0.5667) time: 0.9145 data: 0.0004 [11-24 03:15:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 0/1669] eta: 0:25:26 tlr: 0.0002 tnm: 0.21 Lm: 6.490 (6.490) Lt: 5.783 (5.783) Accm: 3.18 (3.18) Acct: 4.92 (4.92) proj_loss: -0.6265 (-0.6265) time: 0.9146 data: 0.0004 [11-24 03:15:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 0/1669] eta: 0:25:26 tlr: 0.0002 tnm: 0.21 Lm: 6.636 (6.636) Lt: 5.915 (5.915) Accm: 2.80 (2.80) Acct: 4.13 (4.13) proj_loss: -0.6244 (-0.6244) time: 0.9146 data: 0.0004 [11-24 03:15:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 0/1669] eta: 0:25:26 tlr: 0.0002 tnm: 0.21 Lm: 6.582 (6.582) Lt: 5.863 (5.863) Accm: 2.84 (2.84) Acct: 4.27 (4.27) proj_loss: -0.6128 (-0.6128) time: 0.9146 data: 0.0004 [11-24 03:21:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 417/1669] eta: 0:19:33 tlr: 0.0002 tnm: 0.22 Lm: 6.460 (6.460) Lt: 5.678 (5.678) Accm: 3.37 (3.37) Acct: 5.25 (5.25) proj_loss: -0.6095 (-0.6095) time: 0.9312 data: 0.0003 [11-24 03:21:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 417/1669] eta: 0:19:33 tlr: 0.0002 tnm: 0.22 Lm: 6.453 (6.453) Lt: 5.717 (5.717) Accm: 3.47 (3.47) Acct: 5.32 (5.32) proj_loss: -0.6049 (-0.6049) time: 0.9312 data: 0.0003 [11-24 03:21:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 417/1669] eta: 0:19:33 tlr: 0.0002 tnm: 0.22 Lm: 6.683 (6.683) Lt: 5.936 (5.936) Accm: 2.86 (2.86) Acct: 4.51 (4.51) proj_loss: -0.6102 (-0.6102) time: 0.9312 data: 0.0003 [11-24 03:21:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 417/1669] eta: 0:19:33 tlr: 0.0002 tnm: 0.22 Lm: 6.552 (6.552) Lt: 5.831 (5.831) Accm: 3.15 (3.15) Acct: 4.72 (4.72) proj_loss: -0.5969 (-0.5969) time: 0.9312 data: 0.0003 [11-24 03:21:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 417/1669] eta: 0:19:33 tlr: 0.0002 tnm: 0.22 Lm: 6.417 (6.417) Lt: 5.585 (5.585) Accm: 3.58 (3.58) Acct: 5.84 (5.84) proj_loss: -0.6063 (-0.6063) time: 0.9312 data: 0.0003 [11-24 03:21:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 417/1669] eta: 0:19:33 tlr: 0.0002 tnm: 0.22 Lm: 6.502 (6.502) Lt: 5.723 (5.723) Accm: 3.57 (3.57) Acct: 5.53 (5.53) proj_loss: -0.5804 (-0.5804) time: 0.9312 data: 0.0003 [11-24 03:21:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 417/1669] eta: 0:19:33 tlr: 0.0002 tnm: 0.22 Lm: 6.632 (6.632) Lt: 5.860 (5.860) Accm: 2.95 (2.95) Acct: 4.80 (4.80) proj_loss: -0.5980 (-0.5980) time: 0.9313 data: 0.0003 [11-24 03:21:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 417/1669] eta: 0:19:33 tlr: 0.0002 tnm: 0.22 Lm: 6.609 (6.609) Lt: 5.828 (5.828) Accm: 3.22 (3.22) Acct: 5.15 (5.15) proj_loss: -0.5772 (-0.5772) time: 0.9312 data: 0.0003 [11-24 03:28:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 834/1669] eta: 0:13:44 tlr: 0.0002 tnm: 0.22 Lm: 6.546 (6.588) Lt: 5.787 (5.814) Accm: 3.15 (3.20) Acct: 5.27 (5.19) proj_loss: -0.5700 (-0.5748) time: 0.9320 data: 0.0003 [11-24 03:28:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 834/1669] eta: 0:13:44 tlr: 0.0002 tnm: 0.22 Lm: 6.665 (6.643) Lt: 5.917 (5.879) Accm: 2.77 (2.89) Acct: 4.37 (4.66) proj_loss: -0.5795 (-0.5868) time: 0.9320 data: 0.0003 [11-24 03:28:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 834/1669] eta: 0:13:44 tlr: 0.0002 tnm: 0.22 Lm: 6.525 (6.472) Lt: 5.703 (5.640) Accm: 3.57 (3.47) Acct: 5.82 (5.67) proj_loss: -0.5986 (-0.6013) time: 0.9320 data: 0.0003 [11-24 03:28:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 834/1669] eta: 0:13:44 tlr: 0.0002 tnm: 0.22 Lm: 6.490 (6.477) Lt: 5.776 (5.737) Accm: 3.25 (3.40) Acct: 4.92 (5.17) proj_loss: -0.5832 (-0.5957) time: 0.9320 data: 0.0002 [11-24 03:28:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 834/1669] eta: 0:13:44 tlr: 0.0002 tnm: 0.22 Lm: 6.551 (6.548) Lt: 5.758 (5.789) Accm: 3.50 (3.25) Acct: 5.37 (5.05) proj_loss: -0.5910 (-0.5840) time: 0.9320 data: 0.0004 [11-24 03:28:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 834/1669] eta: 0:13:44 tlr: 0.0002 tnm: 0.22 Lm: 6.495 (6.472) Lt: 5.760 (5.705) Accm: 3.26 (3.33) Acct: 5.30 (5.27) proj_loss: -0.6061 (-0.6061) time: 0.9320 data: 0.0003 [11-24 03:28:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 834/1669] eta: 0:13:44 tlr: 0.0002 tnm: 0.22 Lm: 6.636 (6.664) Lt: 5.921 (5.931) Accm: 2.87 (2.86) Acct: 4.48 (4.50) proj_loss: -0.6041 (-0.6081) time: 0.9320 data: 0.0003 [11-24 03:28:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [ 834/1669] eta: 0:13:44 tlr: 0.0002 tnm: 0.22 Lm: 6.560 (6.604) Lt: 5.907 (5.872) Accm: 2.93 (2.98) Acct: 4.20 (4.41) proj_loss: -0.6056 (-0.5998) time: 0.9320 data: 0.0003 [11-24 03:35:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [1251/1669] eta: 0:06:45 tlr: 0.0002 tnm: 0.22 Lm: 6.552 (6.552) Lt: 5.831 (5.802) Accm: 3.15 (3.13) Acct: 4.72 (4.77) proj_loss: -0.6069 (-0.6019) time: 0.9324 data: 0.0003 [11-24 03:35:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [1251/1669] eta: 0:06:45 tlr: 0.0002 tnm: 0.22 Lm: 6.544 (6.495) Lt: 5.726 (5.668) Accm: 3.41 (3.39) Acct: 5.58 (5.54) proj_loss: -0.6063 (-0.6064) time: 0.9324 data: 0.0003 [11-24 03:35:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [1251/1669] eta: 0:06:45 tlr: 0.0002 tnm: 0.22 Lm: 6.487 (6.479) Lt: 5.750 (5.733) Accm: 3.33 (3.40) Acct: 5.32 (5.30) proj_loss: -0.5803 (-0.5895) time: 0.9324 data: 0.0002 [11-24 03:35:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [1251/1669] eta: 0:06:45 tlr: 0.0002 tnm: 0.22 Lm: 6.472 (6.466) Lt: 5.706 (5.692) Accm: 3.58 (3.52) Acct: 5.75 (5.50) proj_loss: -0.6028 (-0.5948) time: 0.9324 data: 0.0003 [11-24 03:35:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [1251/1669] eta: 0:06:45 tlr: 0.0002 tnm: 0.22 Lm: 6.599 (6.604) Lt: 5.850 (5.857) Accm: 2.99 (3.03) Acct: 4.94 (4.91) proj_loss: -0.5809 (-0.5830) time: 0.9324 data: 0.0003 [11-24 03:35:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [1251/1669] eta: 0:06:45 tlr: 0.0002 tnm: 0.22 Lm: 6.665 (6.649) Lt: 5.935 (5.897) Accm: 2.72 (2.83) Acct: 4.27 (4.54) proj_loss: -0.5848 (-0.5877) time: 0.9324 data: 0.0003 [11-24 03:35:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [1251/1669] eta: 0:06:45 tlr: 0.0002 tnm: 0.22 Lm: 6.667 (6.673) Lt: 5.939 (5.955) Accm: 2.83 (2.80) Acct: 4.42 (4.47) proj_loss: -0.6034 (-0.6068) time: 0.9325 data: 0.0003 [11-24 03:35:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [1251/1669] eta: 0:06:45 tlr: 0.0002 tnm: 0.22 Lm: 6.597 (6.595) Lt: 5.839 (5.836) Accm: 3.05 (3.03) Acct: 4.73 (4.77) proj_loss: -0.5789 (-0.5790) time: 0.9325 data: 0.0003 [11-24 03:41:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.20 Lm: 6.642 (6.616) Lt: 5.920 (5.875) Accm: 2.84 (3.00) Acct: 4.61 (4.74) proj_loss: -0.5910 (-0.5827) time: 0.9328 data: 0.0016 [11-24 03:41:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 79/350] Total time: 0:26:45 (0.962 s / it) [11-24 03:41:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.20 Lm: 6.495 (6.474) Lt: 5.760 (5.706) Accm: 3.39 (3.49) Acct: 5.30 (5.45) proj_loss: -0.6061 (-0.5978) time: 0.9328 data: 0.0017 [11-24 03:41:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.20 Lm: 6.525 (6.477) Lt: 5.703 (5.656) Accm: 3.57 (3.43) Acct: 5.41 (5.51) proj_loss: -0.5986 (-0.6025) time: 0.9328 data: 0.0021 [11-24 03:41:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.20 Lm: 6.560 (6.583) Lt: 5.907 (5.829) Accm: 2.93 (3.04) Acct: 4.58 (4.73) proj_loss: -0.6056 (-0.5958) time: 0.9327 data: 0.0015 [11-24 03:41:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.20 Lm: 6.665 (6.660) Lt: 5.953 (5.919) Accm: 2.77 (2.86) Acct: 4.37 (4.52) proj_loss: -0.5902 (-0.5922) time: 0.9327 data: 0.0014 [11-24 03:41:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.20 Lm: 6.490 (6.489) Lt: 5.723 (5.728) Accm: 3.41 (3.42) Acct: 5.72 (5.39) proj_loss: -0.5832 (-0.5921) time: 0.9328 data: 0.0016 [11-24 03:41:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.20 Lm: 6.636 (6.652) Lt: 5.921 (5.943) Accm: 2.87 (2.83) Acct: 4.48 (4.57) proj_loss: -0.6028 (-0.6035) time: 0.9328 data: 0.0018 [11-24 03:41:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 79/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.20 Lm: 6.546 (6.571) Lt: 5.787 (5.818) Accm: 3.15 (3.21) Acct: 5.27 (5.17) proj_loss: -0.5917 (-0.5849) time: 0.9328 data: 0.0019 [11-24 03:41:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 79/350] Total time: 0:26:45 (0.962 s / it) [11-24 03:41:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 79/350] Total time: 0:26:45 (0.962 s / it) [11-24 03:41:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 79/350] Total time: 0:26:45 (0.962 s / it) [11-24 03:41:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 79/350] Total time: 0:26:45 (0.962 s / it) [11-24 03:41:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 79/350] Total time: 0:26:45 (0.962 s / it) [11-24 03:41:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 79/350] Total time: 0:26:45 (0.962 s / it) [11-24 03:41:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 79/350] Total time: 0:26:45 (0.962 s / it) [11-24 03:43:57] (home/user/VAR/trainer.py, line 114)=> FID: 3.753925665414613 [11-24 03:43:58] (/home/user/VAR/train.py , line 259)=> [*] [ep79] (val 50000) Lm: 6.5465, Lt: 5.7952, Acc m&t: 3.23 5.07, Val cost: 127.60s [11-24 03:43:58] (/home/user/VAR/train.py , line 264)=> [saving ckpt] ... [saving ckpt](*) finished! @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth [11-24 03:45:02] (/home/user/VAR/train.py , line 276)=> [ep79] (training ) Lm: 6.540 (6.547), Lt: 5.784 (5.795), Acc m&t: 3.28 5.17, Remain: 4 days, 21:31:46, Finish: 2024-11-28 09:13 [11-24 03:45:02] (/home/user/VAR/train.py , line 276)=> [ep79] (training ) Lm: 6.540 (6.547), Lt: 5.784 (5.795), Acc m&t: 3.28 5.17, Remain: 4 days, 21:29:23, Finish: 2024-11-28 09:11 [11-24 03:45:02] (/home/user/VAR/train.py , line 276)=> [ep79] (training ) Lm: 6.540 (6.547), Lt: 5.784 (5.795), Acc m&t: 3.28 5.17, Remain: 4 days, 21:33:30, Finish: 2024-11-28 09:15 [11-24 03:45:02] (/home/user/VAR/train.py , line 276)=> [ep79] (training ) Lm: 6.540 (6.547), Lt: 5.784 (5.795), Acc m&t: 3.28 5.17, Remain: 4 days, 21:33:31, Finish: 2024-11-28 09:15 [11-24 03:45:02] (/home/user/VAR/train.py , line 276)=> [ep79] (training ) Lm: 6.540 (6.547), Lt: 5.784 (5.795), Acc m&t: 3.28 5.17, Remain: 4 days, 21:33:11, Finish: 2024-11-28 09:15 [11-24 03:45:02] (/home/user/VAR/train.py , line 276)=> [ep79] (training ) Lm: 6.540 (6.547), Lt: 5.784 (5.795), Acc m&t: 3.28 5.17, Remain: 4 days, 21:31:25, Finish: 2024-11-28 09:13 [11-24 03:45:02] (/home/user/VAR/train.py , line 276)=> [ep79] (training ) Lm: 6.540 (6.547), Lt: 5.784 (5.795), Acc m&t: 3.28 5.17, Remain: 4 days, 21:33:15, Finish: 2024-11-28 09:15 [11-24 03:45:02] (/home/user/VAR/train.py , line 276)=> [ep79] (training ) Lm: 6.540 (6.547), Lt: 5.784 (5.795), Acc m&t: 3.28 5.17, Remain: 4 days, 21:34:26, Finish: 2024-11-28 09:16 [11-24 03:45:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 0/1669] eta: 0:24:56 tlr: 0.0002 tnm: 0.20 Lm: 6.683 (6.683) Lt: 5.952 (5.952) Accm: 3.02 (3.02) Acct: 4.68 (4.68) proj_loss: -0.6129 (-0.6129) time: 0.8968 data: 0.0004 [11-24 03:45:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 0/1669] eta: 0:24:55 tlr: 0.0002 tnm: 0.20 Lm: 6.364 (6.364) Lt: 5.486 (5.486) Accm: 4.01 (4.01) Acct: 6.40 (6.40) proj_loss: -0.5948 (-0.5948) time: 0.8959 data: 0.0003 [11-24 03:45:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 0/1669] eta: 0:24:54 tlr: 0.0002 tnm: 0.20 Lm: 6.715 (6.715) Lt: 5.998 (5.998) Accm: 2.58 (2.58) Acct: 4.30 (4.30) proj_loss: -0.5970 (-0.5970) time: 0.8957 data: 0.0004 [11-24 03:45:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 0/1669] eta: 0:24:55 tlr: 0.0002 tnm: 0.20 Lm: 6.373 (6.373) Lt: 5.528 (5.528) Accm: 3.69 (3.69) Acct: 6.20 (6.20) proj_loss: -0.5843 (-0.5843) time: 0.8958 data: 0.0004 [11-24 03:45:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 0/1669] eta: 0:25:07 tlr: 0.0002 tnm: 0.20 Lm: 6.763 (6.763) Lt: 6.004 (6.004) Accm: 2.62 (2.62) Acct: 4.65 (4.65) proj_loss: -0.6095 (-0.6095) time: 0.9034 data: 0.0004 [11-24 03:45:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 0/1669] eta: 0:25:40 tlr: 0.0002 tnm: 0.20 Lm: 6.585 (6.585) Lt: 5.897 (5.897) Accm: 3.12 (3.12) Acct: 4.92 (4.92) proj_loss: -0.5918 (-0.5918) time: 0.9229 data: 0.0004 [11-24 03:45:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 0/1669] eta: 0:24:50 tlr: 0.0002 tnm: 0.20 Lm: 6.403 (6.403) Lt: 5.602 (5.602) Accm: 3.82 (3.82) Acct: 6.40 (6.40) proj_loss: -0.5896 (-0.5896) time: 0.8928 data: 0.0004 [11-24 03:45:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 0/1669] eta: 0:24:55 tlr: 0.0002 tnm: 0.20 Lm: 6.507 (6.507) Lt: 5.775 (5.775) Accm: 3.18 (3.18) Acct: 4.41 (4.41) proj_loss: -0.6178 (-0.6178) time: 0.8960 data: 0.0004 [11-24 03:51:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.22 Lm: 6.545 (6.545) Lt: 5.754 (5.754) Accm: 3.33 (3.33) Acct: 5.10 (5.10) proj_loss: -0.5928 (-0.5928) time: 0.9309 data: 0.0003 [11-24 03:51:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.22 Lm: 6.448 (6.448) Lt: 5.633 (5.633) Accm: 3.48 (3.48) Acct: 5.34 (5.34) proj_loss: -0.5983 (-0.5983) time: 0.9309 data: 0.0003 [11-24 03:51:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.22 Lm: 6.515 (6.515) Lt: 5.798 (5.798) Accm: 3.35 (3.35) Acct: 5.17 (5.17) proj_loss: -0.5944 (-0.5944) time: 0.9309 data: 0.0003 [11-24 03:51:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.22 Lm: 6.749 (6.749) Lt: 6.020 (6.020) Accm: 2.70 (2.70) Acct: 4.37 (4.37) proj_loss: -0.5929 (-0.5929) time: 0.9309 data: 0.0003 [11-24 03:51:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.22 Lm: 6.647 (6.647) Lt: 5.912 (5.912) Accm: 3.15 (3.15) Acct: 5.22 (5.22) proj_loss: -0.5949 (-0.5949) time: 0.9309 data: 0.0003 [11-24 03:51:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.22 Lm: 6.595 (6.595) Lt: 5.815 (5.815) Accm: 3.24 (3.24) Acct: 5.25 (5.25) proj_loss: -0.5965 (-0.5965) time: 0.9309 data: 0.0003 [11-24 03:51:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.22 Lm: 6.649 (6.649) Lt: 5.925 (5.925) Accm: 2.94 (2.94) Acct: 4.46 (4.46) proj_loss: -0.6070 (-0.6070) time: 0.9309 data: 0.0003 [11-24 03:51:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.22 Lm: 6.433 (6.433) Lt: 5.646 (5.646) Accm: 3.69 (3.69) Acct: 5.85 (5.85) proj_loss: -0.5769 (-0.5769) time: 0.9309 data: 0.0003 [11-24 03:58:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 834/1669] eta: 0:12:57 tlr: 0.0002 tnm: 0.22 Lm: 6.373 (6.389) Lt: 5.528 (5.577) Accm: 3.69 (3.79) Acct: 6.20 (5.99) proj_loss: -0.5696 (-0.5703) time: 0.9320 data: 0.0003 [11-24 03:58:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 834/1669] eta: 0:12:57 tlr: 0.0002 tnm: 0.22 Lm: 6.470 (6.588) Lt: 5.676 (5.834) Accm: 3.16 (3.15) Acct: 4.79 (5.07) proj_loss: -0.5939 (-0.5946) time: 0.9320 data: 0.0003 [11-24 03:58:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 834/1669] eta: 0:12:57 tlr: 0.0002 tnm: 0.22 Lm: 6.446 (6.473) Lt: 5.699 (5.745) Accm: 3.44 (3.38) Acct: 5.06 (5.13) proj_loss: -0.5970 (-0.5966) time: 0.9320 data: 0.0003 [11-24 03:58:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 834/1669] eta: 0:12:57 tlr: 0.0002 tnm: 0.22 Lm: 6.617 (6.638) Lt: 5.927 (5.926) Accm: 2.87 (2.81) Acct: 4.24 (4.22) proj_loss: -0.6126 (-0.6089) time: 0.9320 data: 0.0003 [11-24 03:58:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 834/1669] eta: 0:12:57 tlr: 0.0002 tnm: 0.22 Lm: 6.762 (6.650) Lt: 6.004 (5.921) Accm: 2.62 (3.01) Acct: 4.65 (4.75) proj_loss: -0.5968 (-0.5966) time: 0.9321 data: 0.0003 [11-24 03:58:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 834/1669] eta: 0:12:57 tlr: 0.0002 tnm: 0.22 Lm: 6.715 (6.728) Lt: 5.998 (5.979) Accm: 2.83 (2.79) Acct: 4.44 (4.43) proj_loss: -0.5970 (-0.5961) time: 0.9321 data: 0.0003 [11-24 03:58:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 834/1669] eta: 0:12:57 tlr: 0.0002 tnm: 0.22 Lm: 6.443 (6.446) Lt: 5.674 (5.647) Accm: 3.47 (3.48) Acct: 5.72 (5.46) proj_loss: -0.6017 (-0.6017) time: 0.9321 data: 0.0003 [11-24 03:58:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [ 834/1669] eta: 0:12:57 tlr: 0.0002 tnm: 0.22 Lm: 6.507 (6.486) Lt: 5.734 (5.681) Accm: 3.48 (3.57) Acct: 5.79 (5.54) proj_loss: -0.5745 (-0.5867) time: 0.9321 data: 0.0003 [11-24 04:04:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [1251/1669] eta: 0:06:36 tlr: 0.0002 tnm: 0.21 Lm: 6.457 (6.466) Lt: 5.673 (5.664) Accm: 3.66 (3.64) Acct: 6.03 (5.72) proj_loss: -0.5894 (-0.5911) time: 0.9287 data: 0.0003 [11-24 04:04:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [1251/1669] eta: 0:06:36 tlr: 0.0002 tnm: 0.21 Lm: 6.433 (6.443) Lt: 5.646 (5.636) Accm: 3.69 (3.53) Acct: 5.85 (5.49) proj_loss: -0.5769 (-0.5817) time: 0.9287 data: 0.0003 [11-24 04:04:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [1251/1669] eta: 0:06:36 tlr: 0.0002 tnm: 0.21 Lm: 6.699 (6.640) Lt: 5.947 (5.883) Accm: 2.89 (3.12) Acct: 4.49 (4.93) proj_loss: -0.5998 (-0.5993) time: 0.9287 data: 0.0003 [11-24 04:04:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [1251/1669] eta: 0:06:36 tlr: 0.0002 tnm: 0.21 Lm: 6.472 (6.560) Lt: 5.657 (5.785) Accm: 3.29 (3.22) Acct: 5.18 (5.20) proj_loss: -0.5918 (-0.5913) time: 0.9287 data: 0.0003 [11-24 04:04:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [1251/1669] eta: 0:06:36 tlr: 0.0002 tnm: 0.21 Lm: 6.473 (6.480) Lt: 5.674 (5.721) Accm: 3.51 (3.49) Acct: 5.23 (5.61) proj_loss: -0.5944 (-0.5934) time: 0.9287 data: 0.0003 [11-24 04:04:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [1251/1669] eta: 0:06:36 tlr: 0.0002 tnm: 0.21 Lm: 6.648 (6.621) Lt: 5.869 (5.874) Accm: 2.95 (3.07) Acct: 4.92 (4.86) proj_loss: -0.5940 (-0.5952) time: 0.9287 data: 0.0003 [11-24 04:04:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [1251/1669] eta: 0:06:36 tlr: 0.0002 tnm: 0.21 Lm: 6.615 (6.594) Lt: 5.913 (5.853) Accm: 2.94 (2.88) Acct: 4.46 (4.49) proj_loss: -0.6069 (-0.6059) time: 0.9287 data: 0.0003 [11-24 04:04:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [1251/1669] eta: 0:06:36 tlr: 0.0002 tnm: 0.21 Lm: 6.404 (6.384) Lt: 5.580 (5.568) Accm: 3.74 (3.85) Acct: 6.06 (6.04) proj_loss: -0.5983 (-0.5995) time: 0.9287 data: 0.0003 [11-24 04:11:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.443 (6.416) Lt: 5.674 (5.610) Accm: 3.47 (3.66) Acct: 5.72 (5.72) proj_loss: -0.5948 (-0.5981) time: 0.9334 data: 0.0016 [11-24 04:11:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 80/350] Total time: 0:26:23 (0.949 s / it) [11-24 04:11:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.658 (6.629) Lt: 5.999 (5.899) Accm: 2.83 (3.02) Acct: 4.65 (4.80) proj_loss: -0.5968 (-0.5997) time: 0.9334 data: 0.0017 [11-24 04:11:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.475 (6.595) Lt: 5.676 (5.835) Accm: 3.16 (3.04) Acct: 4.79 (4.87) proj_loss: -0.5896 (-0.5900) time: 0.9334 data: 0.0019 [11-24 04:11:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.441 (6.442) Lt: 5.715 (5.652) Accm: 3.69 (3.64) Acct: 6.20 (5.70) proj_loss: -0.5843 (-0.5855) time: 0.9334 data: 0.0018 [11-24 04:11:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.507 (6.487) Lt: 5.734 (5.703) Accm: 3.48 (3.47) Acct: 5.79 (5.44) proj_loss: -0.5967 (-0.5922) time: 0.9334 data: 0.0021 [11-24 04:11:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.715 (6.679) Lt: 5.998 (5.931) Accm: 2.83 (2.98) Acct: 4.44 (4.75) proj_loss: -0.5970 (-0.5953) time: 0.9334 data: 0.0018 [11-24 04:11:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.614 (6.541) Lt: 5.899 (5.791) Accm: 3.02 (3.08) Acct: 4.68 (4.80) proj_loss: -0.6012 (-0.6047) time: 0.9334 data: 0.0022 [11-24 04:11:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 80/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.501 (6.552) Lt: 5.699 (5.815) Accm: 3.44 (3.31) Acct: 5.06 (5.22) proj_loss: -0.5918 (-0.5930) time: 0.9334 data: 0.0012 [11-24 04:11:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 80/350] Total time: 0:26:23 (0.949 s / it) [11-24 04:11:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 80/350] Total time: 0:26:23 (0.949 s / it) [11-24 04:11:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 80/350] Total time: 0:26:23 (0.949 s / it) [11-24 04:11:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 80/350] Total time: 0:26:23 (0.949 s / it) [11-24 04:11:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 80/350] Total time: 0:26:23 (0.949 s / it) [11-24 04:11:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 80/350] Total time: 0:26:23 (0.949 s / it) [11-24 04:11:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 80/350] Total time: 0:26:23 (0.949 s / it) [11-24 04:11:26] (/home/user/VAR/train.py , line 276)=> [ep80] (training ) Lm: 6.540 (6.545), Lt: 5.784 (5.789), Acc m&t: 3.28 5.17, Remain: 4 days, 21:06:09, Finish: 2024-11-28 09:17 [11-24 04:11:26] (/home/user/VAR/train.py , line 276)=> [ep80] (training ) Lm: 6.540 (6.545), Lt: 5.784 (5.789), Acc m&t: 3.28 5.17, Remain: 4 days, 21:06:49, Finish: 2024-11-28 09:18 [11-24 04:11:26] (/home/user/VAR/train.py , line 276)=> [ep80] (training ) Lm: 6.540 (6.545), Lt: 5.784 (5.789), Acc m&t: 3.28 5.17, Remain: 4 days, 21:05:31, Finish: 2024-11-28 09:16 [11-24 04:11:26] (/home/user/VAR/train.py , line 276)=> [ep80] (training ) Lm: 6.540 (6.545), Lt: 5.784 (5.789), Acc m&t: 3.28 5.17, Remain: 4 days, 21:05:45, Finish: 2024-11-28 09:17 [11-24 04:11:26] (/home/user/VAR/train.py , line 276)=> [ep80] (training ) Lm: 6.540 (6.545), Lt: 5.784 (5.789), Acc m&t: 3.28 5.17, Remain: 4 days, 21:15:23, Finish: 2024-11-28 09:26 [11-24 04:11:26] (/home/user/VAR/train.py , line 276)=> [ep80] (training ) Lm: 6.540 (6.545), Lt: 5.784 (5.789), Acc m&t: 3.28 5.17, Remain: 4 days, 21:05:39, Finish: 2024-11-28 09:17 [11-24 04:11:26] (/home/user/VAR/train.py , line 276)=> [ep80] (training ) Lm: 6.540 (6.545), Lt: 5.784 (5.789), Acc m&t: 3.28 5.17, Remain: 4 days, 21:05:22, Finish: 2024-11-28 09:16 [11-24 04:11:26] (/home/user/VAR/train.py , line 276)=> [ep80] (training ) Lm: 6.540 (6.545), Lt: 5.784 (5.789), Acc m&t: 3.28 5.17, Remain: 4 days, 21:06:52, Finish: 2024-11-28 09:18 [11-24 04:11:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 0/1669] eta: 0:24:51 tlr: 0.0002 tnm: 0.21 Lm: 6.552 (6.552) Lt: 5.857 (5.857) Accm: 3.18 (3.18) Acct: 4.75 (4.75) proj_loss: -0.6183 (-0.6183) time: 0.8937 data: 0.0004 [11-24 04:11:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 0/1669] eta: 0:24:53 tlr: 0.0002 tnm: 0.21 Lm: 6.345 (6.345) Lt: 5.631 (5.631) Accm: 3.47 (3.47) Acct: 5.41 (5.41) proj_loss: -0.6188 (-0.6188) time: 0.8949 data: 0.0004 [11-24 04:11:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 0/1669] eta: 0:24:52 tlr: 0.0002 tnm: 0.21 Lm: 6.173 (6.173) Lt: 5.348 (5.348) Accm: 4.56 (4.56) Acct: 6.96 (6.96) proj_loss: -0.5923 (-0.5923) time: 0.8943 data: 0.0004 [11-24 04:11:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 0/1669] eta: 0:24:51 tlr: 0.0002 tnm: 0.21 Lm: 6.580 (6.580) Lt: 5.797 (5.797) Accm: 3.03 (3.03) Acct: 4.75 (4.75) proj_loss: -0.5988 (-0.5988) time: 0.8934 data: 0.0003 [11-24 04:11:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 0/1669] eta: 0:25:58 tlr: 0.0002 tnm: 0.21 Lm: 6.727 (6.727) Lt: 6.056 (6.056) Accm: 3.19 (3.19) Acct: 4.99 (4.99) proj_loss: -0.5913 (-0.5913) time: 0.9337 data: 0.0004 [11-24 04:11:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 0/1669] eta: 0:24:54 tlr: 0.0002 tnm: 0.21 Lm: 6.386 (6.386) Lt: 5.607 (5.607) Accm: 3.82 (3.82) Acct: 5.89 (5.89) proj_loss: -0.5806 (-0.5806) time: 0.8952 data: 0.0004 [11-24 04:11:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 0/1669] eta: 0:24:52 tlr: 0.0002 tnm: 0.21 Lm: 6.319 (6.319) Lt: 5.523 (5.523) Accm: 3.82 (3.82) Acct: 5.85 (5.85) proj_loss: -0.6253 (-0.6253) time: 0.8941 data: 0.0003 [11-24 04:11:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 0/1669] eta: 0:24:51 tlr: 0.0002 tnm: 0.21 Lm: 6.476 (6.476) Lt: 5.628 (5.628) Accm: 3.25 (3.25) Acct: 5.23 (5.23) proj_loss: -0.5999 (-0.5999) time: 0.8937 data: 0.0004 [11-24 04:18:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 417/1669] eta: 0:20:43 tlr: 0.0002 tnm: 0.21 Lm: 6.512 (6.512) Lt: 5.691 (5.691) Accm: 3.17 (3.17) Acct: 5.23 (5.23) proj_loss: -0.5889 (-0.5889) time: 0.9906 data: 0.0003 [11-24 04:18:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 417/1669] eta: 0:20:43 tlr: 0.0002 tnm: 0.21 Lm: 6.426 (6.426) Lt: 5.679 (5.679) Accm: 3.30 (3.30) Acct: 5.10 (5.10) proj_loss: -0.6128 (-0.6128) time: 0.9906 data: 0.0003 [11-24 04:18:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 417/1669] eta: 0:20:43 tlr: 0.0002 tnm: 0.21 Lm: 6.463 (6.463) Lt: 5.729 (5.729) Accm: 3.60 (3.60) Acct: 5.73 (5.73) proj_loss: -0.6021 (-0.6021) time: 0.9906 data: 0.0003 [11-24 04:18:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 417/1669] eta: 0:20:43 tlr: 0.0002 tnm: 0.21 Lm: 6.540 (6.540) Lt: 5.740 (5.740) Accm: 3.21 (3.21) Acct: 5.29 (5.29) proj_loss: -0.5931 (-0.5931) time: 0.9906 data: 0.0003 [11-24 04:18:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 417/1669] eta: 0:20:43 tlr: 0.0002 tnm: 0.21 Lm: 6.705 (6.705) Lt: 6.033 (6.033) Accm: 3.10 (3.10) Acct: 4.80 (4.80) proj_loss: -0.5974 (-0.5974) time: 0.9906 data: 0.0003 [11-24 04:18:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 417/1669] eta: 0:20:43 tlr: 0.0002 tnm: 0.21 Lm: 6.509 (6.509) Lt: 5.830 (5.830) Accm: 3.49 (3.49) Acct: 5.18 (5.18) proj_loss: -0.6153 (-0.6153) time: 0.9906 data: 0.0003 [11-24 04:18:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 417/1669] eta: 0:20:43 tlr: 0.0002 tnm: 0.21 Lm: 6.419 (6.419) Lt: 5.671 (5.671) Accm: 3.59 (3.59) Acct: 5.53 (5.53) proj_loss: -0.5970 (-0.5970) time: 0.9906 data: 0.0003 [11-24 04:18:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 417/1669] eta: 0:20:43 tlr: 0.0002 tnm: 0.21 Lm: 6.417 (6.417) Lt: 5.684 (5.684) Accm: 3.34 (3.34) Acct: 5.11 (5.11) proj_loss: -0.6150 (-0.6150) time: 0.9906 data: 0.0003 [11-24 04:24:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 834/1669] eta: 0:13:23 tlr: 0.0002 tnm: 0.22 Lm: 6.489 (6.474) Lt: 5.738 (5.749) Accm: 3.21 (3.23) Acct: 4.86 (5.03) proj_loss: -0.6112 (-0.6123) time: 0.9322 data: 0.0003 [11-24 04:24:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 834/1669] eta: 0:13:23 tlr: 0.0002 tnm: 0.22 Lm: 6.580 (6.572) Lt: 5.797 (5.778) Accm: 3.34 (3.25) Acct: 5.17 (5.25) proj_loss: -0.5874 (-0.5860) time: 0.9323 data: 0.0003 [11-24 04:24:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 834/1669] eta: 0:13:23 tlr: 0.0002 tnm: 0.22 Lm: 6.517 (6.511) Lt: 5.803 (5.792) Accm: 3.53 (3.50) Acct: 5.58 (5.31) proj_loss: -0.6123 (-0.6092) time: 0.9322 data: 0.0003 [11-24 04:24:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 834/1669] eta: 0:13:23 tlr: 0.0002 tnm: 0.22 Lm: 6.445 (6.428) Lt: 5.693 (5.678) Accm: 3.67 (3.62) Acct: 5.54 (5.53) proj_loss: -0.6011 (-0.5984) time: 0.9322 data: 0.0003 [11-24 04:24:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 834/1669] eta: 0:13:23 tlr: 0.0002 tnm: 0.22 Lm: 6.503 (6.509) Lt: 5.755 (5.713) Accm: 3.25 (3.32) Acct: 5.23 (5.34) proj_loss: -0.5999 (-0.5975) time: 0.9322 data: 0.0003 [11-24 04:24:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 834/1669] eta: 0:13:23 tlr: 0.0002 tnm: 0.22 Lm: 6.682 (6.610) Lt: 6.009 (5.907) Accm: 3.19 (3.21) Acct: 4.99 (4.99) proj_loss: -0.6035 (-0.6040) time: 0.9322 data: 0.0003 [11-24 04:24:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 834/1669] eta: 0:13:23 tlr: 0.0002 tnm: 0.22 Lm: 6.619 (6.515) Lt: 5.966 (5.808) Accm: 3.00 (3.40) Acct: 4.89 (5.45) proj_loss: -0.5923 (-0.5965) time: 0.9323 data: 0.0003 [11-24 04:24:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [ 834/1669] eta: 0:13:23 tlr: 0.0002 tnm: 0.22 Lm: 6.533 (6.481) Lt: 5.808 (5.722) Accm: 3.22 (3.27) Acct: 5.23 (5.14) proj_loss: -0.6003 (-0.6034) time: 0.9323 data: 0.0003 [11-24 04:31:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.502 (6.478) Lt: 5.725 (5.702) Accm: 3.25 (3.27) Acct: 5.30 (5.20) proj_loss: -0.5936 (-0.5993) time: 0.9317 data: 0.0003 [11-24 04:31:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.610 (6.536) Lt: 5.894 (5.812) Accm: 2.92 (3.26) Acct: 4.73 (5.23) proj_loss: -0.5888 (-0.5890) time: 0.9317 data: 0.0003 [11-24 04:31:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.559 (6.563) Lt: 5.740 (5.735) Accm: 3.36 (3.31) Acct: 5.49 (5.40) proj_loss: -0.5849 (-0.5851) time: 0.9317 data: 0.0003 [11-24 04:31:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.534 (6.531) Lt: 5.824 (5.805) Accm: 3.35 (3.30) Acct: 5.17 (5.14) proj_loss: -0.6078 (-0.6077) time: 0.9317 data: 0.0003 [11-24 04:31:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.525 (6.530) Lt: 5.756 (5.741) Accm: 3.17 (3.22) Acct: 5.23 (5.18) proj_loss: -0.5986 (-0.5974) time: 0.9317 data: 0.0003 [11-24 04:31:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.625 (6.599) Lt: 5.907 (5.881) Accm: 3.16 (3.19) Acct: 5.15 (5.07) proj_loss: -0.5984 (-0.6014) time: 0.9317 data: 0.0003 [11-24 04:31:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.417 (6.434) Lt: 5.684 (5.708) Accm: 3.34 (3.39) Acct: 5.13 (5.33) proj_loss: -0.6091 (-0.6043) time: 0.9317 data: 0.0003 [11-24 04:31:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.415 (6.411) Lt: 5.650 (5.635) Accm: 3.74 (3.71) Acct: 5.72 (5.66) proj_loss: -0.5909 (-0.5920) time: 0.9318 data: 0.0003 [11-24 04:37:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.445 (6.426) Lt: 5.693 (5.652) Accm: 3.67 (3.60) Acct: 5.54 (5.52) proj_loss: -0.6011 (-0.5954) time: 0.9314 data: 0.0017 [11-24 04:37:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 81/350] Total time: 0:26:21 (0.948 s / it) [11-24 04:37:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.607 (6.550) Lt: 5.887 (5.827) Accm: 3.00 (3.21) Acct: 4.75 (5.14) proj_loss: -0.5923 (-0.5920) time: 0.9314 data: 0.0013 [11-24 04:37:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.569 (6.574) Lt: 5.805 (5.852) Accm: 3.19 (3.23) Acct: 5.30 (5.14) proj_loss: -0.6035 (-0.6069) time: 0.9314 data: 0.0016 [11-24 04:37:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.533 (6.510) Lt: 5.808 (5.740) Accm: 3.22 (3.15) Acct: 5.23 (4.95) proj_loss: -0.6003 (-0.6024) time: 0.9314 data: 0.0019 [11-24 04:37:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.547 (6.565) Lt: 5.758 (5.788) Accm: 3.09 (3.09) Acct: 5.23 (4.97) proj_loss: -0.5999 (-0.5989) time: 0.9314 data: 0.0018 [11-24 04:37:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.580 (6.583) Lt: 5.797 (5.766) Accm: 3.34 (3.18) Acct: 5.17 (5.09) proj_loss: -0.5823 (-0.5805) time: 0.9314 data: 0.0020 [11-24 04:37:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.552 (6.550) Lt: 5.843 (5.813) Accm: 3.18 (3.23) Acct: 4.75 (5.04) proj_loss: -0.6032 (-0.5991) time: 0.9314 data: 0.0018 [11-24 04:37:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 81/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.462 (6.439) Lt: 5.715 (5.709) Accm: 3.47 (3.44) Acct: 5.41 (5.41) proj_loss: -0.6070 (-0.6038) time: 0.9314 data: 0.0020 [11-24 04:37:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 81/350] Total time: 0:26:21 (0.948 s / it) [11-24 04:37:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 81/350] Total time: 0:26:21 (0.948 s / it) [11-24 04:37:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 81/350] Total time: 0:26:21 (0.948 s / it) [11-24 04:37:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 81/350] Total time: 0:26:21 (0.948 s / it) [11-24 04:37:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 81/350] Total time: 0:26:21 (0.948 s / it) [11-24 04:37:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 81/350] Total time: 0:26:21 (0.948 s / it) [11-24 04:37:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 81/350] Total time: 0:26:21 (0.948 s / it) [11-24 04:37:48] (/home/user/VAR/train.py , line 276)=> [ep81] (training ) Lm: 6.535 (6.535), Lt: 5.781 (5.781), Acc m&t: 3.28 5.17, Remain: 4 days, 20:26:57, Finish: 2024-11-28 09:04 [11-24 04:37:48] (/home/user/VAR/train.py , line 276)=> [ep81] (training ) Lm: 6.535 (6.535), Lt: 5.781 (5.781), Acc m&t: 3.28 5.17, Remain: 4 days, 20:27:58, Finish: 2024-11-28 09:05 [11-24 04:37:48] (/home/user/VAR/train.py , line 276)=> [ep81] (training ) Lm: 6.535 (6.535), Lt: 5.781 (5.781), Acc m&t: 3.28 5.17, Remain: 4 days, 20:26:35, Finish: 2024-11-28 09:04 [11-24 04:37:48] (/home/user/VAR/train.py , line 276)=> [ep81] (training ) Lm: 6.535 (6.535), Lt: 5.781 (5.781), Acc m&t: 3.28 5.17, Remain: 4 days, 20:30:24, Finish: 2024-11-28 09:08 [11-24 04:37:48] (/home/user/VAR/train.py , line 276)=> [ep81] (training ) Lm: 6.535 (6.535), Lt: 5.781 (5.781), Acc m&t: 3.28 5.17, Remain: 4 days, 20:27:06, Finish: 2024-11-28 09:04 [11-24 04:37:48] (/home/user/VAR/train.py , line 276)=> [ep81] (training ) Lm: 6.535 (6.535), Lt: 5.781 (5.781), Acc m&t: 3.28 5.17, Remain: 4 days, 20:25:56, Finish: 2024-11-28 09:03 [11-24 04:37:48] (/home/user/VAR/train.py , line 276)=> [ep81] (training ) Lm: 6.535 (6.535), Lt: 5.781 (5.781), Acc m&t: 3.28 5.17, Remain: 4 days, 20:25:22, Finish: 2024-11-28 09:03 [11-24 04:37:48] (/home/user/VAR/train.py , line 276)=> [ep81] (training ) Lm: 6.535 (6.535), Lt: 5.781 (5.781), Acc m&t: 3.28 5.17, Remain: 4 days, 20:25:29, Finish: 2024-11-28 09:03 [11-24 04:37:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 0/1669] eta: 0:25:04 tlr: 0.0002 tnm: 0.22 Lm: 6.689 (6.689) Lt: 5.964 (5.964) Accm: 2.75 (2.75) Acct: 4.17 (4.17) proj_loss: -0.5801 (-0.5801) time: 0.9014 data: 0.0003 [11-24 04:37:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 0/1669] eta: 0:25:14 tlr: 0.0002 tnm: 0.22 Lm: 6.299 (6.299) Lt: 5.597 (5.597) Accm: 3.99 (3.99) Acct: 5.85 (5.85) proj_loss: -0.6087 (-0.6087) time: 0.9072 data: 0.0004 [11-24 04:37:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 0/1669] eta: 0:25:13 tlr: 0.0002 tnm: 0.22 Lm: 6.697 (6.697) Lt: 5.959 (5.959) Accm: 2.96 (2.96) Acct: 4.75 (4.75) proj_loss: -0.6158 (-0.6158) time: 0.9069 data: 0.0004 [11-24 04:37:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 0/1669] eta: 0:25:13 tlr: 0.0002 tnm: 0.22 Lm: 6.737 (6.737) Lt: 6.014 (6.014) Accm: 2.58 (2.58) Acct: 4.10 (4.10) proj_loss: -0.5888 (-0.5888) time: 0.9069 data: 0.0004 [11-24 04:37:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 0/1669] eta: 0:25:13 tlr: 0.0002 tnm: 0.22 Lm: 6.475 (6.475) Lt: 5.706 (5.706) Accm: 3.98 (3.98) Acct: 6.34 (6.34) proj_loss: -0.6123 (-0.6123) time: 0.9071 data: 0.0003 [11-24 04:37:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 0/1669] eta: 0:25:13 tlr: 0.0002 tnm: 0.22 Lm: 6.547 (6.547) Lt: 5.793 (5.793) Accm: 2.78 (2.78) Acct: 4.72 (4.72) proj_loss: -0.6060 (-0.6060) time: 0.9068 data: 0.0004 [11-24 04:37:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 0/1669] eta: 0:25:12 tlr: 0.0002 tnm: 0.22 Lm: 6.463 (6.463) Lt: 5.696 (5.696) Accm: 3.21 (3.21) Acct: 4.82 (4.82) proj_loss: -0.6137 (-0.6137) time: 0.9062 data: 0.0004 [11-24 04:37:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 0/1669] eta: 0:25:14 tlr: 0.0002 tnm: 0.22 Lm: 6.631 (6.631) Lt: 5.974 (5.974) Accm: 2.71 (2.71) Acct: 4.03 (4.03) proj_loss: -0.6212 (-0.6212) time: 0.9075 data: 0.0004 [11-24 04:44:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.20 Lm: 6.647 (6.647) Lt: 6.041 (6.041) Accm: 2.64 (2.64) Acct: 3.72 (3.72) proj_loss: -0.6316 (-0.6316) time: 0.9319 data: 0.0003 [11-24 04:44:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.20 Lm: 6.632 (6.632) Lt: 5.905 (5.905) Accm: 2.92 (2.92) Acct: 4.75 (4.75) proj_loss: -0.5962 (-0.5962) time: 0.9319 data: 0.0003 [11-24 04:44:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.20 Lm: 6.357 (6.357) Lt: 5.630 (5.630) Accm: 3.77 (3.77) Acct: 5.68 (5.68) proj_loss: -0.6051 (-0.6051) time: 0.9319 data: 0.0002 [11-24 04:44:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.20 Lm: 6.650 (6.650) Lt: 5.958 (5.958) Accm: 3.04 (3.04) Acct: 4.61 (4.61) proj_loss: -0.6158 (-0.6158) time: 0.9319 data: 0.0003 [11-24 04:44:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.20 Lm: 6.483 (6.483) Lt: 5.688 (5.688) Accm: 3.95 (3.95) Acct: 6.22 (6.22) proj_loss: -0.5907 (-0.5907) time: 0.9319 data: 0.0003 [11-24 04:44:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.20 Lm: 6.616 (6.616) Lt: 5.837 (5.837) Accm: 2.91 (2.91) Acct: 4.82 (4.82) proj_loss: -0.6009 (-0.6009) time: 0.9319 data: 0.0003 [11-24 04:44:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.20 Lm: 6.664 (6.664) Lt: 5.933 (5.933) Accm: 2.85 (2.85) Acct: 4.63 (4.63) proj_loss: -0.5852 (-0.5852) time: 0.9319 data: 0.0003 [11-24 04:44:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 417/1669] eta: 0:19:25 tlr: 0.0002 tnm: 0.20 Lm: 6.500 (6.500) Lt: 5.748 (5.748) Accm: 3.38 (3.38) Acct: 5.29 (5.29) proj_loss: -0.5962 (-0.5962) time: 0.9319 data: 0.0003 [11-24 04:51:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 834/1669] eta: 0:13:32 tlr: 0.0002 tnm: 0.21 Lm: 6.537 (6.549) Lt: 5.800 (5.786) Accm: 3.21 (3.31) Acct: 5.41 (5.33) proj_loss: -0.5936 (-0.5953) time: 1.1034 data: 0.0003 [11-24 04:51:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 834/1669] eta: 0:13:32 tlr: 0.0002 tnm: 0.21 Lm: 6.491 (6.507) Lt: 5.706 (5.700) Accm: 3.92 (3.73) Acct: 6.10 (5.99) proj_loss: -0.5691 (-0.5833) time: 1.1034 data: 0.0003 [11-24 04:51:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 834/1669] eta: 0:13:32 tlr: 0.0002 tnm: 0.21 Lm: 6.581 (6.604) Lt: 5.823 (5.832) Accm: 3.04 (3.00) Acct: 4.89 (4.84) proj_loss: -0.5959 (-0.5912) time: 1.1034 data: 0.0003 [11-24 04:51:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 834/1669] eta: 0:13:32 tlr: 0.0002 tnm: 0.21 Lm: 6.737 (6.675) Lt: 5.981 (5.931) Accm: 2.58 (2.79) Acct: 4.10 (4.48) proj_loss: -0.5888 (-0.5886) time: 1.1034 data: 0.0003 [11-24 04:51:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 834/1669] eta: 0:13:32 tlr: 0.0002 tnm: 0.21 Lm: 6.604 (6.629) Lt: 5.957 (5.940) Accm: 2.96 (3.00) Acct: 4.55 (4.59) proj_loss: -0.6158 (-0.6153) time: 1.1034 data: 0.0003 [11-24 04:51:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 834/1669] eta: 0:13:32 tlr: 0.0002 tnm: 0.21 Lm: 6.656 (6.661) Lt: 5.964 (5.945) Accm: 2.75 (2.74) Acct: 4.17 (4.40) proj_loss: -0.5903 (-0.5878) time: 1.1034 data: 0.0003 [11-24 04:51:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 834/1669] eta: 0:13:32 tlr: 0.0002 tnm: 0.21 Lm: 6.408 (6.374) Lt: 5.638 (5.633) Accm: 3.54 (3.68) Acct: 5.51 (5.43) proj_loss: -0.6015 (-0.6000) time: 1.1034 data: 0.0003 [11-24 04:51:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [ 834/1669] eta: 0:13:32 tlr: 0.0002 tnm: 0.21 Lm: 6.631 (6.639) Lt: 5.998 (6.026) Accm: 2.71 (2.73) Acct: 4.03 (4.03) proj_loss: -0.6212 (-0.6151) time: 1.1034 data: 0.0003 [11-24 04:58:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [1251/1669] eta: 0:06:44 tlr: 0.0002 tnm: 0.23 Lm: 6.628 (6.604) Lt: 5.986 (5.957) Accm: 2.82 (2.87) Acct: 4.34 (4.30) proj_loss: -0.6070 (-0.6095) time: 0.9297 data: 0.0003 [11-24 04:58:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [1251/1669] eta: 0:06:44 tlr: 0.0002 tnm: 0.23 Lm: 6.647 (6.619) Lt: 5.933 (5.892) Accm: 2.85 (2.90) Acct: 4.63 (4.67) proj_loss: -0.5916 (-0.5957) time: 0.9297 data: 0.0003 [11-24 04:58:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [1251/1669] eta: 0:06:44 tlr: 0.0002 tnm: 0.23 Lm: 6.657 (6.650) Lt: 5.912 (5.909) Accm: 2.72 (2.81) Acct: 4.30 (4.49) proj_loss: -0.5904 (-0.5895) time: 0.9297 data: 0.0003 [11-24 04:58:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [1251/1669] eta: 0:06:44 tlr: 0.0002 tnm: 0.23 Lm: 6.633 (6.627) Lt: 5.852 (5.887) Accm: 2.91 (2.91) Acct: 4.80 (4.67) proj_loss: -0.6009 (-0.5975) time: 0.9297 data: 0.0003 [11-24 04:58:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [1251/1669] eta: 0:06:44 tlr: 0.0002 tnm: 0.23 Lm: 6.523 (6.519) Lt: 5.711 (5.704) Accm: 3.75 (3.69) Acct: 6.18 (6.06) proj_loss: -0.5732 (-0.5818) time: 0.9297 data: 0.0003 [11-24 04:58:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [1251/1669] eta: 0:06:44 tlr: 0.0002 tnm: 0.23 Lm: 6.604 (6.622) Lt: 5.930 (5.931) Accm: 3.04 (3.10) Acct: 4.65 (4.80) proj_loss: -0.6150 (-0.6147) time: 0.9297 data: 0.0003 [11-24 04:58:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [1251/1669] eta: 0:06:44 tlr: 0.0002 tnm: 0.23 Lm: 6.412 (6.404) Lt: 5.651 (5.654) Accm: 3.52 (3.57) Acct: 5.27 (5.33) proj_loss: -0.5956 (-0.5932) time: 0.9297 data: 0.0003 [11-24 04:58:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [1251/1669] eta: 0:06:44 tlr: 0.0002 tnm: 0.23 Lm: 6.538 (6.547) Lt: 5.780 (5.780) Accm: 3.29 (3.33) Acct: 5.30 (5.29) proj_loss: -0.5875 (-0.5918) time: 0.9297 data: 0.0003 [11-24 05:04:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.22 Lm: 6.539 (6.545) Lt: 5.764 (5.776) Accm: 3.21 (3.30) Acct: 5.20 (5.23) proj_loss: -0.5936 (-0.5939) time: 0.9318 data: 0.0015 [11-24 05:04:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 82/350] Total time: 0:26:41 (0.959 s / it) [11-24 05:04:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.22 Lm: 6.416 (6.424) Lt: 5.664 (5.676) Accm: 3.50 (3.55) Acct: 5.51 (5.37) proj_loss: -0.6015 (-0.5963) time: 0.9318 data: 0.0020 [11-24 05:04:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.22 Lm: 6.577 (6.620) Lt: 5.843 (5.856) Accm: 2.87 (2.95) Acct: 4.51 (4.70) proj_loss: -0.5919 (-0.5960) time: 0.9318 data: 0.0017 [11-24 05:04:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.22 Lm: 6.625 (6.583) Lt: 5.974 (5.916) Accm: 2.93 (2.91) Acct: 4.65 (4.41) proj_loss: -0.6049 (-0.6086) time: 0.9318 data: 0.0019 [11-24 05:04:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.22 Lm: 6.581 (6.615) Lt: 5.823 (5.855) Accm: 3.04 (2.97) Acct: 4.89 (4.81) proj_loss: -0.5969 (-0.5974) time: 0.9318 data: 0.0018 [11-24 05:04:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.22 Lm: 6.554 (6.538) Lt: 5.716 (5.744) Accm: 3.58 (3.53) Acct: 6.10 (5.75) proj_loss: -0.5772 (-0.5887) time: 0.9318 data: 0.0018 [11-24 05:04:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.22 Lm: 6.604 (6.565) Lt: 5.904 (5.842) Accm: 3.12 (3.30) Acct: 4.75 (5.11) proj_loss: -0.6142 (-0.6073) time: 0.9318 data: 0.0018 [11-24 05:04:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 82/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.22 Lm: 6.638 (6.598) Lt: 5.901 (5.857) Accm: 2.94 (2.94) Acct: 5.10 (4.77) proj_loss: -0.5903 (-0.5900) time: 0.9318 data: 0.0013 [11-24 05:04:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 82/350] Total time: 0:26:41 (0.959 s / it) [11-24 05:04:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 82/350] Total time: 0:26:41 (0.959 s / it) [11-24 05:04:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 82/350] Total time: 0:26:41 (0.959 s / it) [11-24 05:04:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 82/350] Total time: 0:26:41 (0.959 s / it) [11-24 05:04:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 82/350] Total time: 0:26:41 (0.959 s / it) [11-24 05:04:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 82/350] Total time: 0:26:41 (0.959 s / it) [11-24 05:04:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 82/350] Total time: 0:26:41 (0.959 s / it) [11-24 05:04:29] (/home/user/VAR/train.py , line 276)=> [ep82] (training ) Lm: 6.535 (6.548), Lt: 5.781 (5.792), Acc m&t: 3.28 5.17, Remain: 4 days, 20:10:41, Finish: 2024-11-28 09:15 [11-24 05:04:29] (/home/user/VAR/train.py , line 276)=> [ep82] (training ) Lm: 6.535 (6.548), Lt: 5.781 (5.792), Acc m&t: 3.28 5.17, Remain: 4 days, 20:10:34, Finish: 2024-11-28 09:15 [11-24 05:04:29] (/home/user/VAR/train.py , line 276)=> [ep82] (training ) Lm: 6.535 (6.548), Lt: 5.781 (5.792), Acc m&t: 3.28 5.17, Remain: 4 days, 20:10:51, Finish: 2024-11-28 09:15 [11-24 05:04:29] (/home/user/VAR/train.py , line 276)=> [ep82] (training ) Lm: 6.535 (6.548), Lt: 5.781 (5.792), Acc m&t: 3.28 5.17, Remain: 4 days, 20:11:09, Finish: 2024-11-28 09:15 [11-24 05:04:29] (/home/user/VAR/train.py , line 276)=> [ep82] (training ) Lm: 6.535 (6.548), Lt: 5.781 (5.792), Acc m&t: 3.28 5.17, Remain: 4 days, 20:11:47, Finish: 2024-11-28 09:16 [11-24 05:04:29] (/home/user/VAR/train.py , line 276)=> [ep82] (training ) Lm: 6.535 (6.548), Lt: 5.781 (5.792), Acc m&t: 3.28 5.17, Remain: 4 days, 20:10:46, Finish: 2024-11-28 09:15 [11-24 05:04:29] (/home/user/VAR/train.py , line 276)=> [ep82] (training ) Lm: 6.535 (6.548), Lt: 5.781 (5.792), Acc m&t: 3.28 5.17, Remain: 4 days, 20:11:53, Finish: 2024-11-28 09:16 [11-24 05:04:29] (/home/user/VAR/train.py , line 276)=> [ep82] (training ) Lm: 6.535 (6.548), Lt: 5.781 (5.792), Acc m&t: 3.28 5.17, Remain: 4 days, 20:10:11, Finish: 2024-11-28 09:14 [11-24 05:04:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 0/1669] eta: 0:24:44 tlr: 0.0002 tnm: 0.22 Lm: 6.502 (6.502) Lt: 5.643 (5.643) Accm: 3.13 (3.13) Acct: 4.72 (4.72) proj_loss: -0.5982 (-0.5982) time: 0.8896 data: 0.0003 [11-24 05:04:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 0/1669] eta: 0:24:49 tlr: 0.0002 tnm: 0.22 Lm: 6.436 (6.436) Lt: 5.701 (5.701) Accm: 3.29 (3.29) Acct: 4.75 (4.75) proj_loss: -0.6021 (-0.6021) time: 0.8926 data: 0.0003 [11-24 05:04:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 0/1669] eta: 0:24:49 tlr: 0.0002 tnm: 0.22 Lm: 6.531 (6.531) Lt: 5.780 (5.780) Accm: 3.50 (3.50) Acct: 5.72 (5.72) proj_loss: -0.6066 (-0.6066) time: 0.8926 data: 0.0004 [11-24 05:04:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 0/1669] eta: 0:24:50 tlr: 0.0002 tnm: 0.22 Lm: 6.780 (6.780) Lt: 6.029 (6.029) Accm: 2.51 (2.51) Acct: 3.79 (3.79) proj_loss: -0.5891 (-0.5891) time: 0.8928 data: 0.0004 [11-24 05:04:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 0/1669] eta: 0:24:50 tlr: 0.0002 tnm: 0.22 Lm: 6.675 (6.675) Lt: 5.976 (5.976) Accm: 2.99 (2.99) Acct: 4.34 (4.34) proj_loss: -0.6063 (-0.6063) time: 0.8928 data: 0.0004 [11-24 05:04:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 0/1669] eta: 0:24:49 tlr: 0.0002 tnm: 0.22 Lm: 6.366 (6.366) Lt: 5.510 (5.510) Accm: 4.08 (4.08) Acct: 6.85 (6.85) proj_loss: -0.5974 (-0.5974) time: 0.8927 data: 0.0003 [11-24 05:04:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 0/1669] eta: 0:24:50 tlr: 0.0002 tnm: 0.22 Lm: 6.374 (6.374) Lt: 5.591 (5.591) Accm: 3.88 (3.88) Acct: 5.82 (5.82) proj_loss: -0.5934 (-0.5934) time: 0.8930 data: 0.0004 [11-24 05:04:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 0/1669] eta: 0:24:50 tlr: 0.0002 tnm: 0.22 Lm: 6.644 (6.644) Lt: 5.933 (5.933) Accm: 2.96 (2.96) Acct: 4.44 (4.44) proj_loss: -0.6100 (-0.6100) time: 0.8932 data: 0.0004 [11-24 05:11:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 417/1669] eta: 0:19:31 tlr: 0.0002 tnm: 0.21 Lm: 6.480 (6.480) Lt: 5.745 (5.745) Accm: 3.53 (3.53) Acct: 5.65 (5.65) proj_loss: -0.6092 (-0.6092) time: 0.9280 data: 0.0003 [11-24 05:11:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 417/1669] eta: 0:19:31 tlr: 0.0002 tnm: 0.21 Lm: 6.600 (6.600) Lt: 5.890 (5.890) Accm: 3.04 (3.04) Acct: 4.72 (4.72) proj_loss: -0.5950 (-0.5950) time: 0.9280 data: 0.0003 [11-24 05:11:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 417/1669] eta: 0:19:31 tlr: 0.0002 tnm: 0.21 Lm: 6.512 (6.512) Lt: 5.699 (5.699) Accm: 3.26 (3.26) Acct: 5.01 (5.01) proj_loss: -0.5933 (-0.5933) time: 0.9281 data: 0.0003 [11-24 05:11:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 417/1669] eta: 0:19:31 tlr: 0.0002 tnm: 0.21 Lm: 6.470 (6.470) Lt: 5.704 (5.704) Accm: 3.39 (3.39) Acct: 5.22 (5.22) proj_loss: -0.5935 (-0.5935) time: 0.9281 data: 0.0003 [11-24 05:11:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 417/1669] eta: 0:19:31 tlr: 0.0002 tnm: 0.21 Lm: 6.411 (6.411) Lt: 5.636 (5.636) Accm: 3.90 (3.90) Acct: 6.27 (6.27) proj_loss: -0.5883 (-0.5883) time: 0.9281 data: 0.0003 [11-24 05:11:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 417/1669] eta: 0:19:31 tlr: 0.0002 tnm: 0.21 Lm: 6.580 (6.580) Lt: 5.802 (5.802) Accm: 3.02 (3.02) Acct: 4.82 (4.82) proj_loss: -0.5874 (-0.5874) time: 0.9280 data: 0.0003 [11-24 05:11:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 417/1669] eta: 0:19:31 tlr: 0.0002 tnm: 0.21 Lm: 6.454 (6.454) Lt: 5.638 (5.638) Accm: 3.69 (3.69) Acct: 5.70 (5.70) proj_loss: -0.5968 (-0.5968) time: 0.9280 data: 0.0003 [11-24 05:11:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 417/1669] eta: 0:19:31 tlr: 0.0002 tnm: 0.21 Lm: 6.459 (6.459) Lt: 5.716 (5.716) Accm: 3.57 (3.57) Acct: 5.66 (5.66) proj_loss: -0.5970 (-0.5970) time: 0.9280 data: 0.0003 [11-24 05:17:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 834/1669] eta: 0:12:59 tlr: 0.0002 tnm: 0.20 Lm: 6.531 (6.539) Lt: 5.780 (5.784) Accm: 3.50 (3.27) Acct: 5.61 (5.12) proj_loss: -0.5888 (-0.5943) time: 0.9298 data: 0.0003 [11-24 05:17:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 834/1669] eta: 0:12:59 tlr: 0.0002 tnm: 0.20 Lm: 6.464 (6.542) Lt: 5.752 (5.785) Accm: 3.32 (3.12) Acct: 5.27 (4.97) proj_loss: -0.5891 (-0.5925) time: 0.9298 data: 0.0003 [11-24 05:17:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 834/1669] eta: 0:12:59 tlr: 0.0002 tnm: 0.20 Lm: 6.423 (6.444) Lt: 5.632 (5.636) Accm: 3.51 (3.59) Acct: 5.58 (5.64) proj_loss: -0.5934 (-0.5933) time: 0.9298 data: 0.0003 [11-24 05:17:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 834/1669] eta: 0:12:59 tlr: 0.0002 tnm: 0.20 Lm: 6.523 (6.538) Lt: 5.755 (5.757) Accm: 3.16 (3.22) Acct: 5.30 (5.11) proj_loss: -0.5885 (-0.5883) time: 0.9298 data: 0.0003 [11-24 05:17:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 834/1669] eta: 0:12:59 tlr: 0.0002 tnm: 0.20 Lm: 6.504 (6.520) Lt: 5.706 (5.760) Accm: 3.29 (3.28) Acct: 4.96 (5.13) proj_loss: -0.5850 (-0.5868) time: 0.9298 data: 0.0003 [11-24 05:17:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 834/1669] eta: 0:12:59 tlr: 0.0002 tnm: 0.20 Lm: 6.633 (6.611) Lt: 5.924 (5.902) Accm: 3.10 (3.14) Acct: 4.92 (4.79) proj_loss: -0.6063 (-0.6010) time: 0.9298 data: 0.0003 [11-24 05:17:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 834/1669] eta: 0:12:59 tlr: 0.0002 tnm: 0.20 Lm: 6.644 (6.545) Lt: 5.911 (5.801) Accm: 2.96 (3.19) Acct: 4.44 (5.13) proj_loss: -0.6084 (-0.6078) time: 0.9298 data: 0.0003 [11-24 05:17:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [ 834/1669] eta: 0:12:59 tlr: 0.0002 tnm: 0.20 Lm: 6.456 (6.492) Lt: 5.762 (5.734) Accm: 3.72 (3.57) Acct: 5.68 (5.60) proj_loss: -0.5974 (-0.5921) time: 0.9298 data: 0.0003 [11-24 05:23:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.22 Lm: 6.438 (6.474) Lt: 5.676 (5.698) Accm: 3.53 (3.51) Acct: 5.58 (5.57) proj_loss: -0.5890 (-0.5892) time: 0.9309 data: 0.0003 [11-24 05:23:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.22 Lm: 6.423 (6.495) Lt: 5.688 (5.745) Accm: 3.43 (3.40) Acct: 5.56 (5.47) proj_loss: -0.5958 (-0.5950) time: 0.9309 data: 0.0003 [11-24 05:23:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.22 Lm: 6.406 (6.430) Lt: 5.611 (5.618) Accm: 3.69 (3.66) Acct: 5.70 (5.73) proj_loss: -0.5941 (-0.5936) time: 0.9309 data: 0.0003 [11-24 05:23:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.22 Lm: 6.505 (6.501) Lt: 5.742 (5.744) Accm: 3.40 (3.35) Acct: 5.22 (5.35) proj_loss: -0.6089 (-0.6082) time: 0.9309 data: 0.0003 [11-24 05:23:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.22 Lm: 6.537 (6.541) Lt: 5.735 (5.746) Accm: 3.23 (3.25) Acct: 5.30 (5.20) proj_loss: -0.5834 (-0.5848) time: 0.9309 data: 0.0003 [11-24 05:23:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.22 Lm: 6.604 (6.602) Lt: 5.864 (5.872) Accm: 3.04 (3.07) Acct: 4.86 (4.79) proj_loss: -0.6097 (-0.6084) time: 0.9309 data: 0.0003 [11-24 05:23:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.22 Lm: 6.535 (6.539) Lt: 5.725 (5.755) Accm: 3.31 (3.23) Acct: 5.34 (5.11) proj_loss: -0.5881 (-0.5908) time: 0.9309 data: 0.0003 [11-24 05:23:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [1251/1669] eta: 0:06:29 tlr: 0.0002 tnm: 0.22 Lm: 6.494 (6.511) Lt: 5.716 (5.752) Accm: 3.35 (3.31) Acct: 5.18 (5.20) proj_loss: -0.5935 (-0.5944) time: 0.9309 data: 0.0003 [11-24 05:30:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.483 (6.500) Lt: 5.706 (5.728) Accm: 3.29 (3.30) Acct: 4.96 (5.15) proj_loss: -0.5850 (-0.5914) time: 0.9336 data: 0.0017 [11-24 05:30:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 83/350] Total time: 0:26:24 (0.950 s / it) [11-24 05:30:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.464 (6.547) Lt: 5.752 (5.806) Accm: 3.32 (3.37) Acct: 5.27 (5.41) proj_loss: -0.6024 (-0.5977) time: 0.9336 data: 0.0017 [11-24 05:30:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.423 (6.429) Lt: 5.632 (5.630) Accm: 3.73 (3.67) Acct: 5.82 (5.76) proj_loss: -0.5948 (-0.5958) time: 0.9336 data: 0.0020 [11-24 05:30:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.475 (6.495) Lt: 5.711 (5.737) Accm: 3.77 (3.44) Acct: 5.48 (5.37) proj_loss: -0.6084 (-0.6077) time: 0.9336 data: 0.0020 [11-24 05:30:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.540 (6.556) Lt: 5.780 (5.798) Accm: 3.12 (3.21) Acct: 5.06 (4.99) proj_loss: -0.5888 (-0.5930) time: 0.9336 data: 0.0017 [11-24 05:30:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.523 (6.529) Lt: 5.755 (5.753) Accm: 3.31 (3.28) Acct: 5.30 (5.10) proj_loss: -0.5878 (-0.5854) time: 0.9336 data: 0.0017 [11-24 05:30:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.575 (6.571) Lt: 5.805 (5.832) Accm: 3.10 (3.25) Acct: 4.92 (5.06) proj_loss: -0.6063 (-0.6025) time: 0.9336 data: 0.0021 [11-24 05:30:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 83/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.456 (6.513) Lt: 5.762 (5.745) Accm: 3.34 (3.35) Acct: 5.48 (5.36) proj_loss: -0.5805 (-0.5870) time: 0.9336 data: 0.0015 [11-24 05:30:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 83/350] Total time: 0:26:24 (0.950 s / it) [11-24 05:30:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 83/350] Total time: 0:26:24 (0.950 s / it) [11-24 05:30:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 83/350] Total time: 0:26:24 (0.950 s / it) [11-24 05:30:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 83/350] Total time: 0:26:24 (0.950 s / it) [11-24 05:30:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 83/350] Total time: 0:26:24 (0.950 s / it) [11-24 05:30:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 83/350] Total time: 0:26:24 (0.950 s / it) [11-24 05:30:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 83/350] Total time: 0:26:24 (0.950 s / it) [11-24 05:30:54] (/home/user/VAR/train.py , line 276)=> [ep83] (training ) Lm: 6.524 (6.524), Lt: 5.763 (5.763), Acc m&t: 3.33 5.26, Remain: 4 days, 19:59:43, Finish: 2024-11-28 09:30 [11-24 05:30:54] (/home/user/VAR/train.py , line 276)=> [ep83] (training ) Lm: 6.524 (6.524), Lt: 5.763 (5.763), Acc m&t: 3.33 5.26, Remain: 4 days, 19:58:49, Finish: 2024-11-28 09:29 [11-24 05:30:54] (/home/user/VAR/train.py , line 276)=> [ep83] (training ) Lm: 6.524 (6.524), Lt: 5.763 (5.763), Acc m&t: 3.33 5.26, Remain: 4 days, 19:59:55, Finish: 2024-11-28 09:30 [11-24 05:30:54] (/home/user/VAR/train.py , line 276)=> [ep83] (training ) Lm: 6.524 (6.524), Lt: 5.763 (5.763), Acc m&t: 3.33 5.26, Remain: 4 days, 19:58:52, Finish: 2024-11-28 09:29 [11-24 05:30:54] (/home/user/VAR/train.py , line 276)=> [ep83] (training ) Lm: 6.524 (6.524), Lt: 5.763 (5.763), Acc m&t: 3.33 5.26, Remain: 4 days, 19:58:53, Finish: 2024-11-28 09:29 [11-24 05:30:54] (/home/user/VAR/train.py , line 276)=> [ep83] (training ) Lm: 6.524 (6.524), Lt: 5.763 (5.763), Acc m&t: 3.33 5.26, Remain: 4 days, 19:59:09, Finish: 2024-11-28 09:30 [11-24 05:30:54] (/home/user/VAR/train.py , line 276)=> [ep83] (training ) Lm: 6.524 (6.524), Lt: 5.763 (5.763), Acc m&t: 3.33 5.26, Remain: 4 days, 19:58:51, Finish: 2024-11-28 09:29 [11-24 05:30:54] (/home/user/VAR/train.py , line 276)=> [ep83] (training ) Lm: 6.524 (6.524), Lt: 5.763 (5.763), Acc m&t: 3.33 5.26, Remain: 4 days, 20:01:48, Finish: 2024-11-28 09:32 [11-24 05:30:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 0/1669] eta: 0:25:20 tlr: 0.0002 tnm: 0.20 Lm: 6.575 (6.575) Lt: 5.886 (5.886) Accm: 2.87 (2.87) Acct: 4.30 (4.30) proj_loss: -0.6259 (-0.6259) time: 0.9111 data: 0.0003 [11-24 05:30:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 0/1669] eta: 0:25:21 tlr: 0.0002 tnm: 0.20 Lm: 6.334 (6.334) Lt: 5.585 (5.585) Accm: 3.96 (3.96) Acct: 6.06 (6.06) proj_loss: -0.6077 (-0.6077) time: 0.9118 data: 0.0004 [11-24 05:30:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 0/1669] eta: 0:25:21 tlr: 0.0002 tnm: 0.20 Lm: 6.641 (6.641) Lt: 5.820 (5.820) Accm: 3.29 (3.29) Acct: 5.68 (5.68) proj_loss: -0.5776 (-0.5776) time: 0.9119 data: 0.0004 [11-24 05:30:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 0/1669] eta: 0:25:22 tlr: 0.0002 tnm: 0.20 Lm: 6.600 (6.600) Lt: 5.863 (5.863) Accm: 2.90 (2.90) Acct: 4.82 (4.82) proj_loss: -0.5889 (-0.5889) time: 0.9120 data: 0.0004 [11-24 05:30:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 0/1669] eta: 0:25:21 tlr: 0.0002 tnm: 0.20 Lm: 6.547 (6.547) Lt: 5.716 (5.716) Accm: 3.16 (3.16) Acct: 5.17 (5.17) proj_loss: -0.5879 (-0.5879) time: 0.9119 data: 0.0032 [11-24 05:30:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 0/1669] eta: 0:25:22 tlr: 0.0002 tnm: 0.20 Lm: 6.549 (6.549) Lt: 5.800 (5.800) Accm: 2.94 (2.94) Acct: 4.51 (4.51) proj_loss: -0.6206 (-0.6206) time: 0.9121 data: 0.0004 [11-24 05:30:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 0/1669] eta: 0:25:22 tlr: 0.0002 tnm: 0.20 Lm: 6.828 (6.828) Lt: 6.062 (6.062) Accm: 2.88 (2.88) Acct: 5.03 (5.03) proj_loss: -0.5701 (-0.5701) time: 0.9123 data: 0.0003 [11-24 05:30:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 0/1669] eta: 0:25:22 tlr: 0.0002 tnm: 0.20 Lm: 6.463 (6.463) Lt: 5.701 (5.701) Accm: 3.67 (3.67) Acct: 5.79 (5.79) proj_loss: -0.5860 (-0.5860) time: 0.9123 data: 0.0004 [11-24 05:37:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 417/1669] eta: 0:20:22 tlr: 0.0002 tnm: 0.21 Lm: 6.346 (6.346) Lt: 5.564 (5.564) Accm: 3.99 (3.99) Acct: 6.20 (6.20) proj_loss: -0.5907 (-0.5907) time: 1.0427 data: 0.0003 [11-24 05:37:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 417/1669] eta: 0:20:22 tlr: 0.0002 tnm: 0.21 Lm: 6.608 (6.608) Lt: 5.812 (5.812) Accm: 3.10 (3.10) Acct: 4.92 (4.92) proj_loss: -0.5733 (-0.5733) time: 1.0427 data: 0.0003 [11-24 05:37:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 417/1669] eta: 0:20:22 tlr: 0.0002 tnm: 0.21 Lm: 6.600 (6.600) Lt: 5.805 (5.805) Accm: 3.38 (3.38) Acct: 5.79 (5.79) proj_loss: -0.5754 (-0.5754) time: 1.0427 data: 0.0003 [11-24 05:37:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 417/1669] eta: 0:20:22 tlr: 0.0002 tnm: 0.21 Lm: 6.545 (6.545) Lt: 5.801 (5.801) Accm: 3.27 (3.27) Acct: 5.25 (5.25) proj_loss: -0.6305 (-0.6305) time: 1.0427 data: 0.0003 [11-24 05:37:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 417/1669] eta: 0:20:22 tlr: 0.0002 tnm: 0.21 Lm: 6.632 (6.632) Lt: 5.874 (5.874) Accm: 3.01 (3.01) Acct: 5.03 (5.03) proj_loss: -0.5903 (-0.5903) time: 1.0427 data: 0.0003 [11-24 05:37:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 417/1669] eta: 0:20:22 tlr: 0.0002 tnm: 0.21 Lm: 6.541 (6.541) Lt: 5.830 (5.830) Accm: 3.02 (3.02) Acct: 4.70 (4.70) proj_loss: -0.6268 (-0.6268) time: 1.0427 data: 0.0003 [11-24 05:37:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 417/1669] eta: 0:20:22 tlr: 0.0002 tnm: 0.21 Lm: 6.594 (6.594) Lt: 5.823 (5.823) Accm: 3.04 (3.04) Acct: 5.08 (5.08) proj_loss: -0.5961 (-0.5961) time: 1.0427 data: 0.0003 [11-24 05:37:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 417/1669] eta: 0:20:22 tlr: 0.0002 tnm: 0.21 Lm: 6.388 (6.388) Lt: 5.642 (5.642) Accm: 3.58 (3.58) Acct: 5.56 (5.56) proj_loss: -0.5984 (-0.5984) time: 1.0427 data: 0.0003 [11-24 05:44:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 834/1669] eta: 0:13:26 tlr: 0.0002 tnm: 0.22 Lm: 6.390 (6.389) Lt: 5.647 (5.644) Accm: 3.45 (3.54) Acct: 5.30 (5.48) proj_loss: -0.5977 (-0.5982) time: 0.9295 data: 0.0003 [11-24 05:44:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 834/1669] eta: 0:13:26 tlr: 0.0002 tnm: 0.22 Lm: 6.508 (6.497) Lt: 5.774 (5.775) Accm: 3.18 (3.14) Acct: 4.99 (4.80) proj_loss: -0.6259 (-0.6256) time: 0.9295 data: 0.0003 [11-24 05:44:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 834/1669] eta: 0:13:26 tlr: 0.0002 tnm: 0.22 Lm: 6.623 (6.602) Lt: 5.820 (5.853) Accm: 3.29 (3.11) Acct: 4.99 (5.02) proj_loss: -0.6030 (-0.5966) time: 0.9295 data: 0.0003 [11-24 05:44:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 834/1669] eta: 0:13:26 tlr: 0.0002 tnm: 0.22 Lm: 6.373 (6.504) Lt: 5.621 (5.743) Accm: 3.77 (3.51) Acct: 5.79 (5.79) proj_loss: -0.5806 (-0.5914) time: 0.9295 data: 0.0003 [11-24 05:44:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 834/1669] eta: 0:13:26 tlr: 0.0002 tnm: 0.22 Lm: 6.541 (6.536) Lt: 5.800 (5.793) Accm: 3.60 (3.39) Acct: 5.34 (5.28) proj_loss: -0.6206 (-0.6214) time: 0.9295 data: 0.0003 [11-24 05:44:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 834/1669] eta: 0:13:26 tlr: 0.0002 tnm: 0.22 Lm: 6.229 (6.294) Lt: 5.481 (5.536) Accm: 3.92 (3.97) Acct: 5.79 (6.00) proj_loss: -0.5955 (-0.6066) time: 0.9295 data: 0.0003 [11-24 05:44:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 834/1669] eta: 0:13:26 tlr: 0.0002 tnm: 0.22 Lm: 6.588 (6.575) Lt: 5.784 (5.798) Accm: 3.19 (3.15) Acct: 5.34 (5.26) proj_loss: -0.6034 (-0.6033) time: 0.9295 data: 0.0003 [11-24 05:44:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [ 834/1669] eta: 0:13:26 tlr: 0.0002 tnm: 0.22 Lm: 6.561 (6.592) Lt: 5.822 (5.815) Accm: 3.15 (3.11) Acct: 5.13 (4.99) proj_loss: -0.5879 (-0.5782) time: 0.9295 data: 0.0003 [11-24 05:50:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.554 (6.542) Lt: 5.769 (5.761) Accm: 3.15 (3.31) Acct: 5.15 (5.31) proj_loss: -0.5880 (-0.5827) time: 0.9307 data: 0.0003 [11-24 05:50:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.545 (6.551) Lt: 5.801 (5.805) Accm: 3.27 (3.27) Acct: 4.92 (5.00) proj_loss: -0.6129 (-0.6173) time: 0.9307 data: 0.0003 [11-24 05:50:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.525 (6.547) Lt: 5.801 (5.803) Accm: 3.42 (3.40) Acct: 5.41 (5.54) proj_loss: -0.5754 (-0.5820) time: 0.9307 data: 0.0003 [11-24 05:50:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.632 (6.646) Lt: 5.874 (5.925) Accm: 3.01 (2.97) Acct: 4.68 (4.72) proj_loss: -0.6037 (-0.5986) time: 0.9307 data: 0.0003 [11-24 05:50:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.346 (6.362) Lt: 5.591 (5.588) Accm: 3.80 (3.80) Acct: 5.70 (5.90) proj_loss: -0.5989 (-0.6056) time: 0.9307 data: 0.0003 [11-24 05:50:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.562 (6.529) Lt: 5.765 (5.762) Accm: 3.27 (3.33) Acct: 5.48 (5.42) proj_loss: -0.6069 (-0.6051) time: 0.9307 data: 0.0003 [11-24 05:50:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.416 (6.451) Lt: 5.673 (5.703) Accm: 3.32 (3.41) Acct: 5.18 (5.29) proj_loss: -0.5934 (-0.5924) time: 0.9307 data: 0.0003 [11-24 05:50:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [1251/1669] eta: 0:06:38 tlr: 0.0002 tnm: 0.21 Lm: 6.458 (6.462) Lt: 5.720 (5.713) Accm: 3.28 (3.39) Acct: 5.04 (5.33) proj_loss: -0.6246 (-0.6136) time: 0.9307 data: 0.0003 [11-24 05:57:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.508 (6.495) Lt: 5.774 (5.732) Accm: 3.18 (3.29) Acct: 4.99 (5.26) proj_loss: -0.6232 (-0.6111) time: 0.9312 data: 0.0014 [11-24 05:57:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 84/350] Total time: 0:26:24 (0.949 s / it) [11-24 05:57:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.549 (6.588) Lt: 5.803 (5.833) Accm: 2.94 (3.15) Acct: 4.55 (4.91) proj_loss: -0.6052 (-0.6128) time: 0.9312 data: 0.0017 [11-24 05:57:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.623 (6.594) Lt: 5.820 (5.859) Accm: 3.29 (3.08) Acct: 4.99 (4.83) proj_loss: -0.6044 (-0.6048) time: 0.9312 data: 0.0017 [11-24 05:57:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.677 (6.575) Lt: 5.948 (5.832) Accm: 3.07 (3.25) Acct: 5.03 (5.24) proj_loss: -0.5806 (-0.5818) time: 0.9312 data: 0.0021 [11-24 05:57:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.442 (6.471) Lt: 5.700 (5.740) Accm: 3.19 (3.35) Acct: 5.06 (5.18) proj_loss: -0.5918 (-0.5923) time: 0.9312 data: 0.0016 [11-24 05:57:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.463 (6.409) Lt: 5.701 (5.625) Accm: 3.67 (3.63) Acct: 5.61 (5.65) proj_loss: -0.5968 (-0.6038) time: 0.9312 data: 0.0019 [11-24 05:57:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.551 (6.544) Lt: 5.769 (5.763) Accm: 3.16 (3.33) Acct: 5.17 (5.37) proj_loss: -0.5881 (-0.5858) time: 0.9312 data: 0.0017 [11-24 05:57:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 84/350] [1668/1669] eta: 0:00:00 tlr: 0.0002 tnm: 0.21 Lm: 6.536 (6.523) Lt: 5.784 (5.772) Accm: 3.35 (3.41) Acct: 5.41 (5.42) proj_loss: -0.6080 (-0.6057) time: 0.9312 data: 0.0020 [11-24 05:57:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 84/350] Total time: 0:26:24 (0.949 s / it) [11-24 05:57:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 84/350] Total time: 0:26:24 (0.949 s / it) [11-24 05:57:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 84/350] Total time: 0:26:24 (0.949 s / it) [11-24 05:57:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 84/350] Total time: 0:26:24 (0.949 s / it) [11-24 05:57:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 84/350] Total time: 0:26:24 (0.949 s / it) [11-24 05:57:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 84/350] Total time: 0:26:24 (0.949 s / it) [11-24 05:57:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 84/350] Total time: 0:26:24 (0.949 s / it) [11-24 05:57:19] (/home/user/VAR/train.py , line 276)=> [ep84] (training ) Lm: 6.524 (6.533), Lt: 5.763 (5.784), Acc m&t: 3.33 5.26, Remain: 4 days, 18:53:32, Finish: 2024-11-28 08:50 [11-24 05:57:19] (/home/user/VAR/train.py , line 276)=> [ep84] (training ) Lm: 6.524 (6.533), Lt: 5.763 (5.784), Acc m&t: 3.33 5.26, Remain: 4 days, 18:56:03, Finish: 2024-11-28 08:53 [11-24 05:57:19] (/home/user/VAR/train.py , line 276)=> [ep84] (training ) Lm: 6.524 (6.533), Lt: 5.763 (5.784), Acc m&t: 3.33 5.26, Remain: 4 days, 18:55:21, Finish: 2024-11-28 08:52 [11-24 05:57:19] (/home/user/VAR/train.py , line 276)=> [ep84] (training ) Lm: 6.524 (6.533), Lt: 5.763 (5.784), Acc m&t: 3.33 5.26, Remain: 4 days, 18:56:52, Finish: 2024-11-28 08:54 [11-24 05:57:19] (/home/user/VAR/train.py , line 276)=> [ep84] (training ) Lm: 6.524 (6.533), Lt: 5.763 (5.784), Acc m&t: 3.33 5.26, Remain: 4 days, 19:02:49, Finish: 2024-11-28 09:00 [11-24 05:57:19] (/home/user/VAR/train.py , line 276)=> [ep84] (training ) Lm: 6.524 (6.533), Lt: 5.763 (5.784), Acc m&t: 3.33 5.26, Remain: 4 days, 18:58:15, Finish: 2024-11-28 08:55 [11-24 05:57:19] (/home/user/VAR/train.py , line 276)=> [ep84] (training ) Lm: 6.524 (6.533), Lt: 5.763 (5.784), Acc m&t: 3.33 5.26, Remain: 4 days, 18:57:22, Finish: 2024-11-28 08:54 [11-24 05:57:19] (/home/user/VAR/train.py , line 276)=> [ep84] (training ) Lm: 6.524 (6.533), Lt: 5.763 (5.784), Acc m&t: 3.33 5.26, Remain: 4 days, 18:57:19, Finish: 2024-11-28 08:54 [11-24 05:57:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 0/1669] eta: 0:25:08 tlr: 0.0002 tnm: 0.22 Lm: 6.699 (6.699) Lt: 5.996 (5.996) Accm: 2.75 (2.75) Acct: 4.48 (4.48) proj_loss: -0.6009 (-0.6009) time: 0.9038 data: 0.0003 [11-24 05:57:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 0/1669] eta: 0:25:09 tlr: 0.0002 tnm: 0.22 Lm: 6.573 (6.573) Lt: 5.804 (5.804) Accm: 3.57 (3.57) Acct: 5.72 (5.72) proj_loss: -0.6109 (-0.6109) time: 0.9043 data: 0.0004 [11-24 05:57:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 0/1669] eta: 0:25:09 tlr: 0.0002 tnm: 0.22 Lm: 6.721 (6.721) Lt: 5.960 (5.960) Accm: 2.91 (2.91) Acct: 4.82 (4.82) proj_loss: -0.5733 (-0.5733) time: 0.9044 data: 0.0004 [11-24 05:57:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 0/1669] eta: 0:25:08 tlr: 0.0002 tnm: 0.22 Lm: 6.641 (6.641) Lt: 5.842 (5.842) Accm: 3.25 (3.25) Acct: 5.03 (5.03) proj_loss: -0.5902 (-0.5902) time: 0.9041 data: 0.0004 [11-24 05:57:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 0/1669] eta: 0:25:05 tlr: 0.0002 tnm: 0.22 Lm: 6.576 (6.576) Lt: 5.882 (5.882) Accm: 3.06 (3.06) Acct: 4.48 (4.48) proj_loss: -0.6006 (-0.6006) time: 0.9020 data: 0.0003 [11-24 05:57:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 0/1669] eta: 0:25:08 tlr: 0.0002 tnm: 0.22 Lm: 6.528 (6.528) Lt: 5.755 (5.755) Accm: 3.61 (3.61) Acct: 5.48 (5.48) proj_loss: -0.6074 (-0.6074) time: 0.9040 data: 0.0004 [11-24 05:57:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 0/1669] eta: 0:25:07 tlr: 0.0002 tnm: 0.22 Lm: 6.363 (6.363) Lt: 5.508 (5.508) Accm: 4.09 (4.09) Acct: 6.99 (6.99) proj_loss: -0.5989 (-0.5989) time: 0.9032 data: 0.0004 [11-24 05:57:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 0/1669] eta: 0:25:10 tlr: 0.0002 tnm: 0.22 Lm: 6.773 (6.773) Lt: 6.102 (6.102) Accm: 2.51 (2.51) Acct: 3.48 (3.48) proj_loss: -0.6056 (-0.6056) time: 0.9047 data: 0.0004 [11-24 06:03:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.20 Lm: 6.685 (6.685) Lt: 5.952 (5.952) Accm: 2.75 (2.75) Acct: 4.08 (4.08) proj_loss: -0.5938 (-0.5938) time: 0.9326 data: 0.0003 [11-24 06:03:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.20 Lm: 6.606 (6.606) Lt: 5.874 (5.874) Accm: 3.18 (3.18) Acct: 5.15 (5.15) proj_loss: -0.5968 (-0.5968) time: 0.9326 data: 0.0003 [11-24 06:03:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.20 Lm: 6.501 (6.501) Lt: 5.699 (5.699) Accm: 3.41 (3.41) Acct: 5.34 (5.34) proj_loss: -0.6041 (-0.6041) time: 0.9326 data: 0.0003 [11-24 06:03:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.20 Lm: 6.655 (6.655) Lt: 5.881 (5.881) Accm: 3.31 (3.31) Acct: 5.53 (5.53) proj_loss: -0.5779 (-0.5779) time: 0.9326 data: 0.0003 [11-24 06:03:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.20 Lm: 6.552 (6.552) Lt: 5.820 (5.820) Accm: 3.37 (3.37) Acct: 5.35 (5.35) proj_loss: -0.6090 (-0.6090) time: 0.9326 data: 0.0003 [11-24 06:03:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.20 Lm: 6.355 (6.355) Lt: 5.563 (5.563) Accm: 3.88 (3.88) Acct: 6.16 (6.16) proj_loss: -0.6004 (-0.6004) time: 0.9326 data: 0.0003 [11-24 06:03:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.20 Lm: 6.587 (6.587) Lt: 5.796 (5.796) Accm: 3.42 (3.42) Acct: 5.42 (5.42) proj_loss: -0.5997 (-0.5997) time: 0.9326 data: 0.0003 [11-24 06:03:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 417/1669] eta: 0:19:26 tlr: 0.0002 tnm: 0.20 Lm: 6.484 (6.484) Lt: 5.764 (5.764) Accm: 3.25 (3.25) Acct: 4.84 (4.84) proj_loss: -0.6086 (-0.6086) time: 0.9326 data: 0.0003 [11-24 06:10:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 834/1669] eta: 0:13:01 tlr: 0.0002 tnm: 0.22 Lm: 6.391 (6.400) Lt: 5.647 (5.685) Accm: 3.44 (3.64) Acct: 5.20 (5.54) proj_loss: -0.6165 (-0.6143) time: 1.0023 data: 0.0003 [11-24 06:10:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 834/1669] eta: 0:13:01 tlr: 0.0002 tnm: 0.22 Lm: 6.513 (6.507) Lt: 5.752 (5.744) Accm: 3.60 (3.44) Acct: 5.82 (5.49) proj_loss: -0.6009 (-0.6027) time: 1.0023 data: 0.0003 [11-24 06:10:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 834/1669] eta: 0:13:01 tlr: 0.0002 tnm: 0.22 Lm: 6.597 (6.562) Lt: 5.801 (5.828) Accm: 2.99 (3.22) Acct: 4.68 (4.74) proj_loss: -0.5876 (-0.5918) time: 1.0023 data: 0.0003 [11-24 06:10:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 834/1669] eta: 0:13:01 tlr: 0.0002 tnm: 0.22 Lm: 6.589 (6.630) Lt: 5.841 (5.868) Accm: 3.28 (3.30) Acct: 5.13 (5.39) proj_loss: -0.5824 (-0.5918) time: 1.0023 data: 0.0003 [11-24 06:10:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 834/1669] eta: 0:13:01 tlr: 0.0002 tnm: 0.22 Lm: 6.363 (6.513) Lt: 5.618 (5.745) Accm: 3.66 (3.40) Acct: 5.34 (5.54) proj_loss: -0.6020 (-0.6065) time: 1.0023 data: 0.0003 [11-24 06:10:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 834/1669] eta: 0:13:01 tlr: 0.0002 tnm: 0.22 Lm: 6.573 (6.620) Lt: 5.837 (5.893) Accm: 3.16 (3.16) Acct: 4.99 (4.92) proj_loss: -0.6071 (-0.5998) time: 1.0023 data: 0.0003 [11-24 06:10:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 834/1669] eta: 0:13:01 tlr: 0.0002 tnm: 0.22 Lm: 6.474 (6.459) Lt: 5.644 (5.658) Accm: 3.61 (3.63) Acct: 5.48 (5.49) proj_loss: -0.6009 (-0.5952) time: 1.0023 data: 0.0003 [11-24 06:10:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [ 834/1669] eta: 0:13:01 tlr: 0.0002 tnm: 0.22 Lm: 6.581 (6.585) Lt: 5.772 (5.788) Accm: 3.25 (3.28) Acct: 5.13 (5.33) proj_loss: -0.5902 (-0.5893) time: 1.0023 data: 0.0003 [11-24 06:17:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [1251/1669] eta: 0:06:45 tlr: 0.0002 tnm: 0.22 Lm: 6.605 (6.596) Lt: 5.807 (5.821) Accm: 3.13 (3.19) Acct: 5.08 (5.14) proj_loss: -0.5997 (-0.5961) time: 0.9331 data: 0.0003 [11-24 06:17:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [1251/1669] eta: 0:06:45 tlr: 0.0002 tnm: 0.22 Lm: 6.627 (6.635) Lt: 5.859 (5.890) Accm: 2.98 (3.07) Acct: 4.91 (4.90) proj_loss: -0.5943 (-0.5920) time: 0.9331 data: 0.0003 [11-24 06:17:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [1251/1669] eta: 0:06:45 tlr: 0.0002 tnm: 0.22 Lm: 6.484 (6.486) Lt: 5.764 (5.784) Accm: 3.25 (3.35) Acct: 4.84 (5.10) proj_loss: -0.6086 (-0.6079) time: 0.9331 data: 0.0003 [11-24 06:17:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [1251/1669] eta: 0:06:45 tlr: 0.0002 tnm: 0.22 Lm: 6.606 (6.577) Lt: 5.874 (5.826) Accm: 3.18 (3.25) Acct: 5.15 (5.20) proj_loss: -0.5968 (-0.5958) time: 0.9331 data: 0.0003 [11-24 06:17:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [1251/1669] eta: 0:06:45 tlr: 0.0002 tnm: 0.22 Lm: 6.414 (6.501) Lt: 5.685 (5.747) Accm: 3.43 (3.35) Acct: 5.17 (5.41) proj_loss: -0.6004 (-0.6022) time: 0.9331 data: 0.0003 [11-24 06:17:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [1251/1669] eta: 0:06:45 tlr: 0.0002 tnm: 0.22 Lm: 6.500 (6.475) Lt: 5.699 (5.686) Accm: 3.74 (3.69) Acct: 5.63 (5.57) proj_loss: -0.6041 (-0.6015) time: 0.9331 data: 0.0003 [11-24 06:17:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [1251/1669] eta: 0:06:45 tlr: 0.0002 tnm: 0.22 Lm: 6.584 (6.612) Lt: 5.872 (5.877) Accm: 3.31 (3.31) Acct: 5.04 (5.29) proj_loss: -0.6010 (-0.6007) time: 0.9331 data: 0.0003 [11-24 06:17:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [1251/1669] eta: 0:06:45 tlr: 0.0002 tnm: 0.22 Lm: 6.685 (6.632) Lt: 5.952 (5.920) Accm: 2.75 (3.00) Acct: 4.27 (4.52) proj_loss: -0.5966 (-0.6038) time: 0.9331 data: 0.0003 [11-24 06:24:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.597 (6.602) Lt: 5.801 (5.884) Accm: 2.99 (3.07) Acct: 4.68 (4.61) proj_loss: -0.6035 (-0.6037) time: 0.9310 data: 0.0016 [11-24 06:24:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 85/350] Total time: 0:26:43 (0.961 s / it) [11-24 06:24:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.589 (6.621) Lt: 5.904 (5.888) Accm: 3.28 (3.22) Acct: 4.96 (5.12) proj_loss: -0.5824 (-0.5947) time: 0.9310 data: 0.0017 [11-24 06:24:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.433 (6.487) Lt: 5.627 (5.723) Accm: 3.66 (3.44) Acct: 5.34 (5.54) proj_loss: -0.5989 (-0.5982) time: 0.9310 data: 0.0016 [11-24 06:24:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.609 (6.598) Lt: 5.801 (5.817) Accm: 3.25 (3.26) Acct: 5.13 (5.27) proj_loss: -0.5902 (-0.5920) time: 0.9310 data: 0.0018 [11-24 06:24:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.550 (6.499) Lt: 5.876 (5.803) Accm: 3.25 (3.33) Acct: 4.58 (4.99) proj_loss: -0.6006 (-0.6060) time: 0.9310 data: 0.0015 [11-24 06:24:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.573 (6.618) Lt: 5.837 (5.869) Accm: 2.97 (3.05) Acct: 4.82 (4.87) proj_loss: -0.6071 (-0.5965) time: 0.9310 data: 0.0018 [11-24 06:24:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.525 (6.505) Lt: 5.755 (5.721) Accm: 3.61 (3.58) Acct: 5.48 (5.53) proj_loss: -0.6009 (-0.5955) time: 0.9310 data: 0.0022 [11-24 06:24:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 85/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.699 (6.604) Lt: 5.996 (5.864) Accm: 2.84 (3.17) Acct: 4.48 (4.99) proj_loss: -0.6009 (-0.6007) time: 0.9310 data: 0.0015 [11-24 06:24:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 85/350] Total time: 0:26:43 (0.961 s / it) [11-24 06:24:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 85/350] Total time: 0:26:43 (0.961 s / it) [11-24 06:24:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 85/350] Total time: 0:26:43 (0.961 s / it) [11-24 06:24:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 85/350] Total time: 0:26:43 (0.961 s / it) [11-24 06:24:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 85/350] Total time: 0:26:43 (0.961 s / it) [11-24 06:24:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 85/350] Total time: 0:26:43 (0.961 s / it) [11-24 06:24:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 85/350] Total time: 0:26:43 (0.961 s / it) [11-24 06:24:03] (/home/user/VAR/train.py , line 276)=> [ep85] (training ) Lm: 6.524 (6.534), Lt: 5.763 (5.781), Acc m&t: 3.33 5.26, Remain: 4 days, 18:48:05, Finish: 2024-11-28 09:12 [11-24 06:24:03] (/home/user/VAR/train.py , line 276)=> [ep85] (training ) Lm: 6.524 (6.534), Lt: 5.763 (5.781), Acc m&t: 3.33 5.26, Remain: 4 days, 18:48:00, Finish: 2024-11-28 09:12 [11-24 06:24:03] (/home/user/VAR/train.py , line 276)=> [ep85] (training ) Lm: 6.524 (6.534), Lt: 5.763 (5.781), Acc m&t: 3.33 5.26, Remain: 4 days, 18:47:18, Finish: 2024-11-28 09:11 [11-24 06:24:03] (/home/user/VAR/train.py , line 276)=> [ep85] (training ) Lm: 6.524 (6.534), Lt: 5.763 (5.781), Acc m&t: 3.33 5.26, Remain: 4 days, 18:47:34, Finish: 2024-11-28 09:11 [11-24 06:24:03] (/home/user/VAR/train.py , line 276)=> [ep85] (training ) Lm: 6.524 (6.534), Lt: 5.763 (5.781), Acc m&t: 3.33 5.26, Remain: 4 days, 18:48:23, Finish: 2024-11-28 09:12 [11-24 06:24:03] (/home/user/VAR/train.py , line 276)=> [ep85] (training ) Lm: 6.524 (6.534), Lt: 5.763 (5.781), Acc m&t: 3.33 5.26, Remain: 4 days, 18:49:34, Finish: 2024-11-28 09:13 [11-24 06:24:03] (/home/user/VAR/train.py , line 276)=> [ep85] (training ) Lm: 6.524 (6.534), Lt: 5.763 (5.781), Acc m&t: 3.33 5.26, Remain: 4 days, 18:47:51, Finish: 2024-11-28 09:11 [11-24 06:24:03] (/home/user/VAR/train.py , line 276)=> [ep85] (training ) Lm: 6.524 (6.534), Lt: 5.763 (5.781), Acc m&t: 3.33 5.26, Remain: 4 days, 18:48:01, Finish: 2024-11-28 09:12 [11-24 06:24:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 0/1669] eta: 0:25:45 tlr: 0.00019 tnm: 0.20 Lm: 6.402 (6.402) Lt: 5.585 (5.585) Accm: 3.98 (3.98) Acct: 6.40 (6.40) proj_loss: -0.6321 (-0.6321) time: 0.9259 data: 0.0003 [11-24 06:24:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 0/1669] eta: 0:25:46 tlr: 0.00019 tnm: 0.20 Lm: 6.557 (6.557) Lt: 5.762 (5.762) Accm: 3.25 (3.25) Acct: 5.03 (5.03) proj_loss: -0.5868 (-0.5868) time: 0.9267 data: 0.0003 [11-24 06:24:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 0/1669] eta: 0:25:49 tlr: 0.00019 tnm: 0.20 Lm: 6.678 (6.678) Lt: 5.927 (5.927) Accm: 2.51 (2.51) Acct: 4.24 (4.24) proj_loss: -0.6087 (-0.6087) time: 0.9284 data: 0.0003 [11-24 06:24:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 0/1669] eta: 0:25:48 tlr: 0.00019 tnm: 0.20 Lm: 6.460 (6.460) Lt: 5.687 (5.687) Accm: 3.67 (3.67) Acct: 5.68 (5.68) proj_loss: -0.5973 (-0.5973) time: 0.9278 data: 0.0003 [11-24 06:24:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 0/1669] eta: 0:25:50 tlr: 0.00019 tnm: 0.20 Lm: 6.559 (6.559) Lt: 5.791 (5.791) Accm: 3.23 (3.23) Acct: 5.27 (5.27) proj_loss: -0.5957 (-0.5957) time: 0.9288 data: 0.0004 [11-24 06:24:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 0/1669] eta: 0:25:51 tlr: 0.00019 tnm: 0.20 Lm: 6.484 (6.484) Lt: 5.754 (5.754) Accm: 3.28 (3.28) Acct: 5.27 (5.27) proj_loss: -0.5916 (-0.5916) time: 0.9296 data: 0.0004 [11-24 06:24:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 0/1669] eta: 0:25:45 tlr: 0.00019 tnm: 0.20 Lm: 6.506 (6.506) Lt: 5.762 (5.762) Accm: 3.13 (3.13) Acct: 4.82 (4.82) proj_loss: -0.6039 (-0.6039) time: 0.9258 data: 0.0004 [11-24 06:24:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 0/1669] eta: 0:25:47 tlr: 0.00019 tnm: 0.20 Lm: 6.480 (6.480) Lt: 5.720 (5.720) Accm: 3.34 (3.34) Acct: 5.30 (5.30) proj_loss: -0.6137 (-0.6137) time: 0.9275 data: 0.0004 [11-24 06:30:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 417/1669] eta: 0:19:24 tlr: 0.00019 tnm: 0.21 Lm: 6.559 (6.559) Lt: 5.821 (5.821) Accm: 3.04 (3.04) Acct: 4.96 (4.96) proj_loss: -0.6070 (-0.6070) time: 0.9285 data: 0.0003 [11-24 06:30:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 417/1669] eta: 0:19:24 tlr: 0.00019 tnm: 0.21 Lm: 6.564 (6.564) Lt: 5.857 (5.857) Accm: 3.11 (3.11) Acct: 4.67 (4.67) proj_loss: -0.5955 (-0.5955) time: 0.9285 data: 0.0003 [11-24 06:30:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 417/1669] eta: 0:19:24 tlr: 0.00019 tnm: 0.21 Lm: 6.405 (6.405) Lt: 5.596 (5.596) Accm: 3.89 (3.89) Acct: 6.01 (6.01) proj_loss: -0.5881 (-0.5881) time: 0.9285 data: 0.0003 [11-24 06:30:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 417/1669] eta: 0:19:24 tlr: 0.00019 tnm: 0.21 Lm: 6.471 (6.471) Lt: 5.676 (5.676) Accm: 3.55 (3.55) Acct: 5.42 (5.42) proj_loss: -0.5989 (-0.5989) time: 0.9285 data: 0.0003 [11-24 06:30:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 417/1669] eta: 0:19:24 tlr: 0.00019 tnm: 0.21 Lm: 6.435 (6.435) Lt: 5.661 (5.661) Accm: 3.72 (3.72) Acct: 6.08 (6.08) proj_loss: -0.6166 (-0.6166) time: 0.9285 data: 0.0003 [11-24 06:30:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 417/1669] eta: 0:19:24 tlr: 0.00019 tnm: 0.21 Lm: 6.463 (6.463) Lt: 5.688 (5.688) Accm: 3.34 (3.34) Acct: 5.23 (5.23) proj_loss: -0.5824 (-0.5824) time: 0.9285 data: 0.0003 [11-24 06:30:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 417/1669] eta: 0:19:24 tlr: 0.00019 tnm: 0.21 Lm: 6.746 (6.746) Lt: 6.060 (6.060) Accm: 2.48 (2.48) Acct: 3.91 (3.91) proj_loss: -0.6030 (-0.6030) time: 0.9285 data: 0.0003 [11-24 06:30:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 417/1669] eta: 0:19:24 tlr: 0.00019 tnm: 0.21 Lm: 6.546 (6.546) Lt: 5.773 (5.773) Accm: 3.47 (3.47) Acct: 5.23 (5.23) proj_loss: -0.5831 (-0.5831) time: 0.9285 data: 0.0003 [11-24 06:37:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 834/1669] eta: 0:12:59 tlr: 0.00019 tnm: 0.21 Lm: 6.559 (6.590) Lt: 5.791 (5.851) Accm: 3.23 (3.27) Acct: 5.20 (4.97) proj_loss: -0.5957 (-0.5949) time: 0.9295 data: 0.0003 [11-24 06:37:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 834/1669] eta: 0:12:59 tlr: 0.00019 tnm: 0.21 Lm: 6.384 (6.438) Lt: 5.609 (5.654) Accm: 3.82 (3.64) Acct: 5.82 (5.58) proj_loss: -0.5868 (-0.5945) time: 0.9295 data: 0.0003 [11-24 06:37:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 834/1669] eta: 0:12:59 tlr: 0.00019 tnm: 0.21 Lm: 6.678 (6.663) Lt: 5.927 (5.967) Accm: 2.51 (2.77) Acct: 4.24 (4.30) proj_loss: -0.6061 (-0.6040) time: 0.9295 data: 0.0003 [11-24 06:37:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 834/1669] eta: 0:12:59 tlr: 0.00019 tnm: 0.21 Lm: 6.506 (6.507) Lt: 5.762 (5.713) Accm: 3.13 (3.23) Acct: 5.06 (5.18) proj_loss: -0.6039 (-0.5929) time: 0.9295 data: 0.0003 [11-24 06:37:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 834/1669] eta: 0:12:59 tlr: 0.00019 tnm: 0.21 Lm: 6.460 (6.474) Lt: 5.687 (5.675) Accm: 3.67 (3.62) Acct: 5.68 (5.73) proj_loss: -0.5789 (-0.5838) time: 0.9295 data: 0.0003 [11-24 06:37:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 834/1669] eta: 0:12:59 tlr: 0.00019 tnm: 0.21 Lm: 6.534 (6.554) Lt: 5.754 (5.818) Accm: 3.18 (3.13) Acct: 4.92 (4.75) proj_loss: -0.5916 (-0.5934) time: 0.9295 data: 0.0003 [11-24 06:37:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 834/1669] eta: 0:12:59 tlr: 0.00019 tnm: 0.21 Lm: 6.469 (6.474) Lt: 5.737 (5.711) Accm: 3.47 (3.46) Acct: 5.75 (5.67) proj_loss: -0.6042 (-0.6125) time: 0.9295 data: 0.0003 [11-24 06:37:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [ 834/1669] eta: 0:12:59 tlr: 0.00019 tnm: 0.21 Lm: 6.511 (6.543) Lt: 5.770 (5.804) Accm: 3.34 (3.17) Acct: 5.30 (5.21) proj_loss: -0.6003 (-0.6004) time: 0.9295 data: 0.0003 [11-24 06:43:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [1251/1669] eta: 0:06:29 tlr: 0.00019 tnm: 0.23 Lm: 6.528 (6.543) Lt: 5.795 (5.808) Accm: 3.38 (3.26) Acct: 5.35 (5.26) proj_loss: -0.6070 (-0.6039) time: 0.9310 data: 0.0003 [11-24 06:43:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [1251/1669] eta: 0:06:29 tlr: 0.00019 tnm: 0.23 Lm: 6.536 (6.513) Lt: 5.760 (5.738) Accm: 3.37 (3.46) Acct: 5.44 (5.60) proj_loss: -0.5870 (-0.5866) time: 0.9310 data: 0.0003 [11-24 06:43:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [1251/1669] eta: 0:06:29 tlr: 0.00019 tnm: 0.23 Lm: 6.440 (6.459) Lt: 5.692 (5.695) Accm: 3.47 (3.46) Acct: 5.80 (5.72) proj_loss: -0.6027 (-0.6086) time: 0.9310 data: 0.0003 [11-24 06:43:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [1251/1669] eta: 0:06:29 tlr: 0.00019 tnm: 0.23 Lm: 6.378 (6.421) Lt: 5.639 (5.658) Accm: 3.68 (3.61) Acct: 5.54 (5.50) proj_loss: -0.5980 (-0.5982) time: 0.9310 data: 0.0003 [11-24 06:43:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [1251/1669] eta: 0:06:29 tlr: 0.00019 tnm: 0.23 Lm: 6.587 (6.620) Lt: 5.858 (5.922) Accm: 2.93 (2.97) Acct: 4.67 (4.58) proj_loss: -0.6016 (-0.6000) time: 0.9310 data: 0.0003 [11-24 06:43:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [1251/1669] eta: 0:06:29 tlr: 0.00019 tnm: 0.23 Lm: 6.550 (6.533) Lt: 5.763 (5.747) Accm: 3.11 (3.20) Acct: 5.03 (5.13) proj_loss: -0.5997 (-0.5936) time: 0.9310 data: 0.0003 [11-24 06:43:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [1251/1669] eta: 0:06:29 tlr: 0.00019 tnm: 0.23 Lm: 6.588 (6.597) Lt: 5.846 (5.863) Accm: 3.23 (3.26) Acct: 5.23 (5.11) proj_loss: -0.6071 (-0.6022) time: 0.9310 data: 0.0003 [11-24 06:43:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [1251/1669] eta: 0:06:29 tlr: 0.00019 tnm: 0.23 Lm: 6.589 (6.581) Lt: 5.840 (5.845) Accm: 3.06 (3.04) Acct: 4.56 (4.61) proj_loss: -0.5955 (-0.5973) time: 0.9310 data: 0.0003 [11-24 06:50:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.20 Lm: 6.534 (6.563) Lt: 5.808 (5.837) Accm: 3.18 (3.16) Acct: 4.92 (4.79) proj_loss: -0.5995 (-0.6033) time: 0.9344 data: 0.0016 [11-24 06:50:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 86/350] Total time: 0:26:17 (0.945 s / it) [11-24 06:50:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.20 Lm: 6.532 (6.517) Lt: 5.773 (5.745) Accm: 3.21 (3.41) Acct: 5.20 (5.43) proj_loss: -0.5951 (-0.5893) time: 0.9344 data: 0.0017 [11-24 06:50:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.20 Lm: 6.544 (6.561) Lt: 5.821 (5.826) Accm: 3.34 (3.22) Acct: 5.30 (5.22) proj_loss: -0.6025 (-0.6036) time: 0.9344 data: 0.0016 [11-24 06:50:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.20 Lm: 6.594 (6.561) Lt: 5.765 (5.799) Accm: 3.09 (3.11) Acct: 4.99 (5.01) proj_loss: -0.6039 (-0.5971) time: 0.9344 data: 0.0015 [11-24 06:50:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.20 Lm: 6.412 (6.447) Lt: 5.648 (5.672) Accm: 3.47 (3.48) Acct: 5.82 (5.74) proj_loss: -0.6042 (-0.6083) time: 0.9344 data: 0.0013 [11-24 06:50:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.20 Lm: 6.384 (6.439) Lt: 5.668 (5.661) Accm: 3.54 (3.56) Acct: 5.27 (5.45) proj_loss: -0.6077 (-0.6001) time: 0.9344 data: 0.0016 [11-24 06:50:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.20 Lm: 6.616 (6.604) Lt: 5.873 (5.865) Accm: 3.23 (3.23) Acct: 5.20 (5.12) proj_loss: -0.5991 (-0.6016) time: 0.9344 data: 0.0017 [11-24 06:50:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 86/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.20 Lm: 6.678 (6.666) Lt: 5.927 (5.976) Accm: 2.51 (2.87) Acct: 4.24 (4.42) proj_loss: -0.5999 (-0.6000) time: 0.9344 data: 0.0019 [11-24 06:50:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 86/350] Total time: 0:26:17 (0.945 s / it) [11-24 06:50:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 86/350] Total time: 0:26:17 (0.945 s / it) [11-24 06:50:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 86/350] Total time: 0:26:17 (0.945 s / it) [11-24 06:50:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 86/350] Total time: 0:26:17 (0.945 s / it) [11-24 06:50:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 86/350] Total time: 0:26:17 (0.945 s / it) [11-24 06:50:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 86/350] Total time: 0:26:17 (0.945 s / it) [11-24 06:50:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 86/350] Total time: 0:26:17 (0.945 s / it) [11-24 06:50:21] (/home/user/VAR/train.py , line 276)=> [ep86] (training ) Lm: 6.524 (6.529), Lt: 5.763 (5.781), Acc m&t: 3.33 5.26, Remain: 4 days, 18:55:16, Finish: 2024-11-28 09:45 [11-24 06:50:21] (/home/user/VAR/train.py , line 276)=> [ep86] (training ) Lm: 6.524 (6.529), Lt: 5.763 (5.781), Acc m&t: 3.33 5.26, Remain: 4 days, 18:54:45, Finish: 2024-11-28 09:45 [11-24 06:50:21] (/home/user/VAR/train.py , line 276)=> [ep86] (training ) Lm: 6.524 (6.529), Lt: 5.763 (5.781), Acc m&t: 3.33 5.26, Remain: 4 days, 18:54:30, Finish: 2024-11-28 09:44 [11-24 06:50:21] (/home/user/VAR/train.py , line 276)=> [ep86] (training ) Lm: 6.524 (6.529), Lt: 5.763 (5.781), Acc m&t: 3.33 5.26, Remain: 4 days, 18:53:59, Finish: 2024-11-28 09:44 [11-24 06:50:21] (/home/user/VAR/train.py , line 276)=> [ep86] (training ) Lm: 6.524 (6.529), Lt: 5.763 (5.781), Acc m&t: 3.33 5.26, Remain: 4 days, 18:52:46, Finish: 2024-11-28 09:43 [11-24 06:50:21] (/home/user/VAR/train.py , line 276)=> [ep86] (training ) Lm: 6.524 (6.529), Lt: 5.763 (5.781), Acc m&t: 3.33 5.26, Remain: 4 days, 18:54:49, Finish: 2024-11-28 09:45 [11-24 06:50:21] (/home/user/VAR/train.py , line 276)=> [ep86] (training ) Lm: 6.524 (6.529), Lt: 5.763 (5.781), Acc m&t: 3.33 5.26, Remain: 4 days, 18:54:13, Finish: 2024-11-28 09:44 [11-24 06:50:21] (/home/user/VAR/train.py , line 276)=> [ep86] (training ) Lm: 6.524 (6.529), Lt: 5.763 (5.781), Acc m&t: 3.33 5.26, Remain: 4 days, 18:55:30, Finish: 2024-11-28 09:45 [11-24 06:50:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 0/1669] eta: 0:25:12 tlr: 0.00019 tnm: 0.22 Lm: 6.537 (6.537) Lt: 5.842 (5.842) Accm: 3.38 (3.38) Acct: 5.06 (5.06) proj_loss: -0.6045 (-0.6045) time: 0.9065 data: 0.0004 [11-24 06:50:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 0/1669] eta: 0:25:13 tlr: 0.00019 tnm: 0.22 Lm: 6.787 (6.787) Lt: 6.072 (6.072) Accm: 2.84 (2.84) Acct: 4.72 (4.72) proj_loss: -0.5751 (-0.5751) time: 0.9066 data: 0.0003 [11-24 06:50:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 0/1669] eta: 0:25:20 tlr: 0.00019 tnm: 0.22 Lm: 6.565 (6.565) Lt: 5.820 (5.820) Accm: 3.42 (3.42) Acct: 5.06 (5.06) proj_loss: -0.5864 (-0.5864) time: 0.9112 data: 0.0004 [11-24 06:50:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 0/1669] eta: 0:25:21 tlr: 0.00019 tnm: 0.22 Lm: 6.550 (6.550) Lt: 5.760 (5.760) Accm: 3.47 (3.47) Acct: 5.54 (5.54) proj_loss: -0.5956 (-0.5956) time: 0.9114 data: 0.0004 [11-24 06:50:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 0/1669] eta: 0:25:14 tlr: 0.00019 tnm: 0.22 Lm: 6.507 (6.507) Lt: 5.796 (5.796) Accm: 3.54 (3.54) Acct: 5.58 (5.58) proj_loss: -0.6033 (-0.6033) time: 0.9071 data: 0.0004 [11-24 06:50:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 0/1669] eta: 0:25:14 tlr: 0.00019 tnm: 0.22 Lm: 6.440 (6.440) Lt: 5.737 (5.737) Accm: 3.74 (3.74) Acct: 5.82 (5.82) proj_loss: -0.5953 (-0.5953) time: 0.9072 data: 0.0004 [11-24 06:50:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 0/1669] eta: 0:25:13 tlr: 0.00019 tnm: 0.22 Lm: 6.487 (6.487) Lt: 5.652 (5.652) Accm: 3.47 (3.47) Acct: 5.51 (5.51) proj_loss: -0.5622 (-0.5622) time: 0.9071 data: 0.0003 [11-24 06:50:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 0/1669] eta: 0:25:07 tlr: 0.00019 tnm: 0.22 Lm: 6.560 (6.560) Lt: 5.716 (5.716) Accm: 3.28 (3.28) Acct: 5.41 (5.41) proj_loss: -0.5665 (-0.5665) time: 0.9030 data: 0.0003 [11-24 06:56:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 417/1669] eta: 0:19:50 tlr: 0.00019 tnm: 0.21 Lm: 6.607 (6.607) Lt: 5.840 (5.840) Accm: 3.04 (3.04) Acct: 4.87 (4.87) proj_loss: -0.5954 (-0.5954) time: 0.9883 data: 0.0003 [11-24 06:56:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 417/1669] eta: 0:19:50 tlr: 0.00019 tnm: 0.21 Lm: 6.728 (6.728) Lt: 6.003 (6.003) Accm: 2.80 (2.80) Acct: 4.58 (4.58) proj_loss: -0.5864 (-0.5864) time: 0.9883 data: 0.0003 [11-24 06:56:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 417/1669] eta: 0:19:50 tlr: 0.00019 tnm: 0.21 Lm: 6.519 (6.519) Lt: 5.794 (5.794) Accm: 3.35 (3.35) Acct: 4.91 (4.91) proj_loss: -0.5931 (-0.5931) time: 0.9883 data: 0.0003 [11-24 06:56:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 417/1669] eta: 0:19:50 tlr: 0.00019 tnm: 0.21 Lm: 6.433 (6.433) Lt: 5.689 (5.689) Accm: 3.64 (3.64) Acct: 5.61 (5.61) proj_loss: -0.5934 (-0.5934) time: 0.9883 data: 0.0003 [11-24 06:56:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 417/1669] eta: 0:19:50 tlr: 0.00019 tnm: 0.21 Lm: 6.578 (6.578) Lt: 5.771 (5.771) Accm: 3.35 (3.35) Acct: 5.44 (5.44) proj_loss: -0.5900 (-0.5900) time: 0.9883 data: 0.0003 [11-24 06:56:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 417/1669] eta: 0:19:50 tlr: 0.00019 tnm: 0.21 Lm: 6.594 (6.594) Lt: 5.874 (5.874) Accm: 3.10 (3.10) Acct: 4.77 (4.77) proj_loss: -0.5932 (-0.5932) time: 0.9883 data: 0.0003 [11-24 06:56:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 417/1669] eta: 0:19:50 tlr: 0.00019 tnm: 0.21 Lm: 6.605 (6.605) Lt: 5.883 (5.883) Accm: 3.08 (3.08) Acct: 4.67 (4.67) proj_loss: -0.5787 (-0.5787) time: 0.9883 data: 0.0003 [11-24 06:56:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 417/1669] eta: 0:19:50 tlr: 0.00019 tnm: 0.21 Lm: 6.454 (6.454) Lt: 5.694 (5.694) Accm: 3.65 (3.65) Acct: 5.58 (5.58) proj_loss: -0.5887 (-0.5887) time: 0.9883 data: 0.0003 [11-24 07:03:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 834/1669] eta: 0:13:32 tlr: 0.00019 tnm: 0.21 Lm: 6.487 (6.539) Lt: 5.736 (5.771) Accm: 3.47 (3.52) Acct: 5.51 (5.54) proj_loss: -0.5955 (-0.5910) time: 0.9876 data: 0.0003 [11-24 07:03:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 834/1669] eta: 0:13:32 tlr: 0.00019 tnm: 0.21 Lm: 6.631 (6.614) Lt: 5.871 (5.879) Accm: 3.26 (3.14) Acct: 5.06 (4.83) proj_loss: -0.6018 (-0.5864) time: 0.9876 data: 0.0003 [11-24 07:03:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 834/1669] eta: 0:13:32 tlr: 0.00019 tnm: 0.21 Lm: 6.550 (6.528) Lt: 5.760 (5.743) Accm: 3.47 (3.42) Acct: 5.48 (5.45) proj_loss: -0.5898 (-0.5899) time: 0.9876 data: 0.0003 [11-24 07:03:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 834/1669] eta: 0:13:32 tlr: 0.00019 tnm: 0.21 Lm: 6.565 (6.582) Lt: 5.820 (5.888) Accm: 3.28 (3.18) Acct: 4.75 (4.78) proj_loss: -0.5991 (-0.5951) time: 0.9876 data: 0.0003 [11-24 07:03:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 834/1669] eta: 0:13:32 tlr: 0.00019 tnm: 0.21 Lm: 6.560 (6.542) Lt: 5.716 (5.777) Accm: 3.28 (3.21) Acct: 5.41 (5.08) proj_loss: -0.6134 (-0.6014) time: 0.9876 data: 0.0004 [11-24 07:03:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 834/1669] eta: 0:13:32 tlr: 0.00019 tnm: 0.21 Lm: 6.681 (6.623) Lt: 5.952 (5.906) Accm: 2.67 (2.91) Acct: 3.96 (4.49) proj_loss: -0.6033 (-0.6062) time: 0.9876 data: 0.0003 [11-24 07:03:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 834/1669] eta: 0:13:32 tlr: 0.00019 tnm: 0.21 Lm: 6.440 (6.503) Lt: 5.737 (5.779) Accm: 3.54 (3.47) Acct: 5.41 (5.29) proj_loss: -0.5915 (-0.5881) time: 0.9876 data: 0.0003 [11-24 07:03:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [ 834/1669] eta: 0:13:32 tlr: 0.00019 tnm: 0.21 Lm: 6.669 (6.650) Lt: 5.934 (5.910) Accm: 2.84 (3.11) Acct: 4.72 (4.92) proj_loss: -0.5978 (-0.5907) time: 0.9876 data: 0.0003 [11-24 07:10:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [1251/1669] eta: 0:06:40 tlr: 0.00019 tnm: 0.22 Lm: 6.582 (6.568) Lt: 5.829 (5.805) Accm: 3.29 (3.27) Acct: 5.17 (5.23) proj_loss: -0.5916 (-0.5894) time: 0.9281 data: 0.0003 [11-24 07:10:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [1251/1669] eta: 0:06:40 tlr: 0.00019 tnm: 0.22 Lm: 6.652 (6.644) Lt: 5.898 (5.917) Accm: 3.02 (3.04) Acct: 4.72 (4.72) proj_loss: -0.6004 (-0.5896) time: 0.9280 data: 0.0003 [11-24 07:10:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [1251/1669] eta: 0:06:40 tlr: 0.00019 tnm: 0.22 Lm: 6.566 (6.541) Lt: 5.771 (5.754) Accm: 3.35 (3.29) Acct: 5.41 (5.26) proj_loss: -0.5870 (-0.5857) time: 0.9281 data: 0.0003 [11-24 07:10:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [1251/1669] eta: 0:06:40 tlr: 0.00019 tnm: 0.22 Lm: 6.533 (6.561) Lt: 5.794 (5.836) Accm: 3.21 (3.17) Acct: 4.63 (4.69) proj_loss: -0.5994 (-0.5973) time: 0.9281 data: 0.0002 [11-24 07:10:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [1251/1669] eta: 0:06:40 tlr: 0.00019 tnm: 0.22 Lm: 6.440 (6.487) Lt: 5.689 (5.743) Accm: 3.55 (3.49) Acct: 5.61 (5.42) proj_loss: -0.5906 (-0.5885) time: 0.9281 data: 0.0003 [11-24 07:10:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [1251/1669] eta: 0:06:40 tlr: 0.00019 tnm: 0.22 Lm: 6.594 (6.555) Lt: 5.874 (5.818) Accm: 3.10 (3.17) Acct: 4.77 (4.91) proj_loss: -0.5949 (-0.6013) time: 0.9281 data: 0.0003 [11-24 07:10:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [1251/1669] eta: 0:06:40 tlr: 0.00019 tnm: 0.22 Lm: 6.513 (6.523) Lt: 5.743 (5.775) Accm: 3.35 (3.26) Acct: 5.29 (5.11) proj_loss: -0.5977 (-0.5966) time: 0.9281 data: 0.0003 [11-24 07:10:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [1251/1669] eta: 0:06:40 tlr: 0.00019 tnm: 0.22 Lm: 6.550 (6.558) Lt: 5.830 (5.810) Accm: 3.37 (3.42) Acct: 5.49 (5.39) proj_loss: -0.5935 (-0.5911) time: 0.9281 data: 0.0003 [11-24 07:16:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.487 (6.494) Lt: 5.736 (5.727) Accm: 3.47 (3.54) Acct: 5.51 (5.57) proj_loss: -0.5915 (-0.5882) time: 0.9328 data: 0.0020 [11-24 07:16:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 87/350] Total time: 0:26:28 (0.952 s / it) [11-24 07:16:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.550 (6.535) Lt: 5.760 (5.742) Accm: 3.32 (3.30) Acct: 5.37 (5.28) proj_loss: -0.5898 (-0.5924) time: 0.9328 data: 0.0016 [11-24 07:16:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.500 (6.523) Lt: 5.768 (5.798) Accm: 3.28 (3.37) Acct: 4.75 (5.08) proj_loss: -0.5998 (-0.6021) time: 0.9328 data: 0.0018 [11-24 07:16:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.440 (6.492) Lt: 5.737 (5.756) Accm: 3.54 (3.46) Acct: 5.41 (5.35) proj_loss: -0.5915 (-0.5922) time: 0.9328 data: 0.0016 [11-24 07:16:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.507 (6.515) Lt: 5.796 (5.766) Accm: 3.54 (3.30) Acct: 5.58 (5.12) proj_loss: -0.6027 (-0.6015) time: 0.9328 data: 0.0020 [11-24 07:16:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.471 (6.513) Lt: 5.716 (5.763) Accm: 3.42 (3.35) Acct: 5.41 (5.31) proj_loss: -0.5819 (-0.5916) time: 0.9328 data: 0.0017 [11-24 07:16:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.631 (6.577) Lt: 5.871 (5.826) Accm: 3.26 (3.22) Acct: 5.06 (5.00) proj_loss: -0.5990 (-0.5865) time: 0.9328 data: 0.0013 [11-24 07:16:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 87/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.587 (6.572) Lt: 5.839 (5.812) Accm: 3.38 (3.29) Acct: 5.20 (5.23) proj_loss: -0.5872 (-0.5889) time: 0.9328 data: 0.0019 [11-24 07:16:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 87/350] Total time: 0:26:28 (0.952 s / it) [11-24 07:16:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 87/350] Total time: 0:26:28 (0.952 s / it) [11-24 07:16:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 87/350] Total time: 0:26:28 (0.952 s / it) [11-24 07:16:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 87/350] Total time: 0:26:28 (0.952 s / it) [11-24 07:16:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 87/350] Total time: 0:26:28 (0.952 s / it) [11-24 07:16:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 87/350] Total time: 0:26:28 (0.952 s / it) [11-24 07:16:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 87/350] Total time: 0:26:28 (0.952 s / it) [11-24 07:16:50] (/home/user/VAR/train.py , line 276)=> [ep87] (training ) Lm: 6.524 (6.532), Lt: 5.763 (5.775), Acc m&t: 3.33 5.26, Remain: 4 days, 18:18:07, Finish: 2024-11-28 09:34 [11-24 07:16:50] (/home/user/VAR/train.py , line 276)=> [ep87] (training ) Lm: 6.524 (6.532), Lt: 5.763 (5.775), Acc m&t: 3.33 5.26, Remain: 4 days, 18:18:49, Finish: 2024-11-28 09:35 [11-24 07:16:50] (/home/user/VAR/train.py , line 276)=> [ep87] (training ) Lm: 6.524 (6.532), Lt: 5.763 (5.775), Acc m&t: 3.33 5.26, Remain: 4 days, 18:16:51, Finish: 2024-11-28 09:33 [11-24 07:16:50] (/home/user/VAR/train.py , line 276)=> [ep87] (training ) Lm: 6.524 (6.532), Lt: 5.763 (5.775), Acc m&t: 3.33 5.26, Remain: 4 days, 18:19:00, Finish: 2024-11-28 09:35 [11-24 07:16:50] (/home/user/VAR/train.py , line 276)=> [ep87] (training ) Lm: 6.524 (6.532), Lt: 5.763 (5.775), Acc m&t: 3.33 5.26, Remain: 4 days, 18:18:45, Finish: 2024-11-28 09:35 [11-24 07:16:50] (/home/user/VAR/train.py , line 276)=> [ep87] (training ) Lm: 6.524 (6.532), Lt: 5.763 (5.775), Acc m&t: 3.33 5.26, Remain: 4 days, 18:18:21, Finish: 2024-11-28 09:35 [11-24 07:16:50] (/home/user/VAR/train.py , line 276)=> [ep87] (training ) Lm: 6.524 (6.532), Lt: 5.763 (5.775), Acc m&t: 3.33 5.26, Remain: 4 days, 18:18:18, Finish: 2024-11-28 09:35 [11-24 07:16:50] (/home/user/VAR/train.py , line 276)=> [ep87] (training ) Lm: 6.524 (6.532), Lt: 5.763 (5.775), Acc m&t: 3.33 5.26, Remain: 4 days, 18:17:06, Finish: 2024-11-28 09:33 [11-24 07:16:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 0/1669] eta: 0:25:57 tlr: 0.00019 tnm: 0.22 Lm: 6.461 (6.461) Lt: 5.749 (5.749) Accm: 3.61 (3.61) Acct: 5.82 (5.82) proj_loss: -0.6160 (-0.6160) time: 0.9332 data: 0.0003 [11-24 07:16:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 0/1669] eta: 0:25:56 tlr: 0.00019 tnm: 0.22 Lm: 6.663 (6.663) Lt: 5.930 (5.930) Accm: 2.83 (2.83) Acct: 4.34 (4.34) proj_loss: -0.6153 (-0.6153) time: 0.9326 data: 0.0003 [11-24 07:16:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 0/1669] eta: 0:25:56 tlr: 0.00019 tnm: 0.22 Lm: 6.659 (6.659) Lt: 5.862 (5.862) Accm: 2.81 (2.81) Acct: 4.20 (4.20) proj_loss: -0.5899 (-0.5899) time: 0.9329 data: 0.0004 [11-24 07:16:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 0/1669] eta: 0:25:57 tlr: 0.00019 tnm: 0.22 Lm: 6.647 (6.647) Lt: 5.959 (5.959) Accm: 2.93 (2.93) Acct: 4.48 (4.48) proj_loss: -0.6097 (-0.6097) time: 0.9330 data: 0.0004 [11-24 07:16:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 0/1669] eta: 0:25:56 tlr: 0.00019 tnm: 0.22 Lm: 6.491 (6.491) Lt: 5.715 (5.715) Accm: 3.21 (3.21) Acct: 5.13 (5.13) proj_loss: -0.5948 (-0.5948) time: 0.9323 data: 0.0004 [11-24 07:16:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 0/1669] eta: 0:25:57 tlr: 0.00019 tnm: 0.22 Lm: 6.424 (6.424) Lt: 5.718 (5.718) Accm: 3.29 (3.29) Acct: 4.86 (4.86) proj_loss: -0.6287 (-0.6287) time: 0.9332 data: 0.0004 [11-24 07:16:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 0/1669] eta: 0:25:58 tlr: 0.00019 tnm: 0.22 Lm: 6.689 (6.689) Lt: 6.005 (6.005) Accm: 2.81 (2.81) Acct: 4.24 (4.24) proj_loss: -0.5964 (-0.5964) time: 0.9337 data: 0.0004 [11-24 07:16:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 0/1669] eta: 0:25:59 tlr: 0.00019 tnm: 0.22 Lm: 6.641 (6.641) Lt: 5.932 (5.932) Accm: 2.91 (2.91) Acct: 5.13 (5.13) proj_loss: -0.5647 (-0.5647) time: 0.9342 data: 0.0004 [11-24 07:23:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 417/1669] eta: 0:19:30 tlr: 0.00019 tnm: 0.22 Lm: 6.699 (6.699) Lt: 6.001 (6.001) Accm: 2.59 (2.59) Acct: 4.24 (4.24) proj_loss: -0.5846 (-0.5846) time: 0.9294 data: 0.0003 [11-24 07:23:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 417/1669] eta: 0:19:30 tlr: 0.00019 tnm: 0.22 Lm: 6.524 (6.524) Lt: 5.795 (5.795) Accm: 3.24 (3.24) Acct: 4.87 (4.87) proj_loss: -0.6101 (-0.6101) time: 0.9294 data: 0.0003 [11-24 07:23:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 417/1669] eta: 0:19:30 tlr: 0.00019 tnm: 0.22 Lm: 6.571 (6.571) Lt: 5.804 (5.804) Accm: 3.15 (3.15) Acct: 4.86 (4.86) proj_loss: -0.5967 (-0.5967) time: 0.9294 data: 0.0003 [11-24 07:23:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 417/1669] eta: 0:19:30 tlr: 0.00019 tnm: 0.22 Lm: 6.352 (6.352) Lt: 5.620 (5.620) Accm: 4.07 (4.07) Acct: 6.46 (6.46) proj_loss: -0.6170 (-0.6170) time: 0.9294 data: 0.0003 [11-24 07:23:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 417/1669] eta: 0:19:30 tlr: 0.00019 tnm: 0.22 Lm: 6.633 (6.633) Lt: 5.844 (5.844) Accm: 3.06 (3.06) Acct: 4.87 (4.87) proj_loss: -0.5909 (-0.5909) time: 0.9294 data: 0.0003 [11-24 07:23:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 417/1669] eta: 0:19:30 tlr: 0.00019 tnm: 0.22 Lm: 6.599 (6.599) Lt: 5.915 (5.915) Accm: 2.95 (2.95) Acct: 4.58 (4.58) proj_loss: -0.6168 (-0.6168) time: 0.9294 data: 0.0003 [11-24 07:23:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 417/1669] eta: 0:19:30 tlr: 0.00019 tnm: 0.22 Lm: 6.589 (6.589) Lt: 5.843 (5.843) Accm: 3.31 (3.31) Acct: 5.10 (5.10) proj_loss: -0.5909 (-0.5909) time: 0.9294 data: 0.0003 [11-24 07:23:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 417/1669] eta: 0:19:30 tlr: 0.00019 tnm: 0.22 Lm: 6.632 (6.632) Lt: 5.941 (5.941) Accm: 2.98 (2.98) Acct: 4.55 (4.55) proj_loss: -0.6235 (-0.6235) time: 0.9293 data: 0.0004 [11-24 07:29:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 834/1669] eta: 0:12:58 tlr: 0.00019 tnm: 0.21 Lm: 6.616 (6.612) Lt: 5.924 (5.934) Accm: 3.03 (3.05) Acct: 4.61 (4.69) proj_loss: -0.6112 (-0.6194) time: 0.9295 data: 0.0003 [11-24 07:29:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 834/1669] eta: 0:12:58 tlr: 0.00019 tnm: 0.21 Lm: 6.734 (6.644) Lt: 6.031 (5.953) Accm: 2.61 (2.78) Acct: 4.30 (4.33) proj_loss: -0.6050 (-0.6066) time: 0.9295 data: 0.0003 [11-24 07:29:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 834/1669] eta: 0:12:58 tlr: 0.00019 tnm: 0.21 Lm: 6.461 (6.420) Lt: 5.749 (5.720) Accm: 3.61 (3.77) Acct: 5.82 (5.89) proj_loss: -0.6160 (-0.6144) time: 0.9295 data: 0.0003 [11-24 07:29:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 834/1669] eta: 0:12:58 tlr: 0.00019 tnm: 0.21 Lm: 6.608 (6.506) Lt: 5.827 (5.709) Accm: 3.31 (3.50) Acct: 5.54 (5.64) proj_loss: -0.5920 (-0.5924) time: 0.9295 data: 0.0003 [11-24 07:29:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 834/1669] eta: 0:12:58 tlr: 0.00019 tnm: 0.21 Lm: 6.520 (6.554) Lt: 5.746 (5.785) Accm: 3.10 (3.07) Acct: 4.68 (4.80) proj_loss: -0.5987 (-0.6026) time: 0.9295 data: 0.0003 [11-24 07:29:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 834/1669] eta: 0:12:58 tlr: 0.00019 tnm: 0.21 Lm: 6.488 (6.547) Lt: 5.681 (5.786) Accm: 3.29 (3.31) Acct: 5.37 (5.19) proj_loss: -0.5964 (-0.5951) time: 0.9295 data: 0.0003 [11-24 07:29:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 834/1669] eta: 0:12:58 tlr: 0.00019 tnm: 0.21 Lm: 6.641 (6.675) Lt: 5.934 (5.979) Accm: 2.91 (2.79) Acct: 4.48 (4.32) proj_loss: -0.5888 (-0.5860) time: 0.9295 data: 0.0003 [11-24 07:29:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [ 834/1669] eta: 0:12:58 tlr: 0.00019 tnm: 0.21 Lm: 6.599 (6.549) Lt: 5.846 (5.812) Accm: 2.87 (3.12) Acct: 4.61 (4.79) proj_loss: -0.6048 (-0.6007) time: 0.9295 data: 0.0003 [11-24 07:36:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [1251/1669] eta: 0:06:42 tlr: 0.00019 tnm: 0.23 Lm: 6.602 (6.563) Lt: 5.842 (5.819) Accm: 2.85 (3.04) Acct: 4.49 (4.68) proj_loss: -0.5933 (-0.5891) time: 1.1061 data: 0.0003 [11-24 07:36:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [1251/1669] eta: 0:06:42 tlr: 0.00019 tnm: 0.23 Lm: 6.633 (6.571) Lt: 5.844 (5.792) Accm: 3.06 (3.31) Acct: 4.87 (5.23) proj_loss: -0.5909 (-0.5821) time: 1.1061 data: 0.0003 [11-24 07:36:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [1251/1669] eta: 0:06:42 tlr: 0.00019 tnm: 0.23 Lm: 6.481 (6.440) Lt: 5.771 (5.738) Accm: 3.39 (3.61) Acct: 5.34 (5.63) proj_loss: -0.6170 (-0.6229) time: 1.1061 data: 0.0003 [11-24 07:36:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [1251/1669] eta: 0:06:42 tlr: 0.00019 tnm: 0.23 Lm: 6.579 (6.578) Lt: 5.776 (5.807) Accm: 3.07 (3.19) Acct: 5.11 (5.11) proj_loss: -0.5973 (-0.5959) time: 1.1061 data: 0.0003 [11-24 07:36:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [1251/1669] eta: 0:06:42 tlr: 0.00019 tnm: 0.23 Lm: 6.536 (6.553) Lt: 5.756 (5.780) Accm: 3.15 (3.19) Acct: 4.91 (5.04) proj_loss: -0.6030 (-0.6038) time: 1.1061 data: 0.0003 [11-24 07:36:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [1251/1669] eta: 0:06:42 tlr: 0.00019 tnm: 0.23 Lm: 6.634 (6.571) Lt: 5.933 (5.845) Accm: 3.06 (3.17) Acct: 4.80 (4.98) proj_loss: -0.5914 (-0.5880) time: 1.1061 data: 0.0003 [11-24 07:36:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [1251/1669] eta: 0:06:42 tlr: 0.00019 tnm: 0.23 Lm: 6.594 (6.588) Lt: 5.921 (5.898) Accm: 3.10 (3.08) Acct: 4.77 (4.75) proj_loss: -0.6105 (-0.6123) time: 1.1061 data: 0.0003 [11-24 07:36:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [1251/1669] eta: 0:06:42 tlr: 0.00019 tnm: 0.23 Lm: 6.615 (6.607) Lt: 5.912 (5.913) Accm: 2.90 (2.88) Acct: 4.39 (4.36) proj_loss: -0.6049 (-0.6062) time: 1.1062 data: 0.0003 [11-24 07:43:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.495 (6.577) Lt: 5.794 (5.881) Accm: 3.19 (3.05) Acct: 4.48 (4.64) proj_loss: -0.6048 (-0.6058) time: 0.9333 data: 0.0016 [11-24 07:43:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 88/350] Total time: 0:26:45 (0.962 s / it) [11-24 07:43:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.599 (6.556) Lt: 5.838 (5.808) Accm: 2.87 (3.12) Acct: 4.61 (4.79) proj_loss: -0.5837 (-0.5880) time: 0.9333 data: 0.0016 [11-24 07:43:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.488 (6.498) Lt: 5.681 (5.713) Accm: 3.29 (3.47) Acct: 5.37 (5.49) proj_loss: -0.5964 (-0.5949) time: 0.9333 data: 0.0016 [11-24 07:43:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.616 (6.597) Lt: 5.919 (5.888) Accm: 3.03 (3.02) Acct: 4.61 (4.70) proj_loss: -0.6097 (-0.6091) time: 0.9333 data: 0.0020 [11-24 07:43:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.627 (6.577) Lt: 5.932 (5.837) Accm: 2.99 (3.14) Acct: 4.75 (4.94) proj_loss: -0.5888 (-0.5875) time: 0.9333 data: 0.0020 [11-24 07:43:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.659 (6.596) Lt: 5.862 (5.826) Accm: 2.81 (3.21) Acct: 4.20 (5.03) proj_loss: -0.5899 (-0.5815) time: 0.9333 data: 0.0019 [11-24 07:43:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.501 (6.468) Lt: 5.794 (5.776) Accm: 3.19 (3.53) Acct: 4.86 (5.45) proj_loss: -0.6160 (-0.6211) time: 0.9333 data: 0.0018 [11-24 07:43:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 88/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.520 (6.533) Lt: 5.746 (5.739) Accm: 3.21 (3.26) Acct: 5.13 (5.23) proj_loss: -0.5987 (-0.5963) time: 0.9333 data: 0.0017 [11-24 07:43:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 88/350] Total time: 0:26:45 (0.962 s / it) [11-24 07:43:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 88/350] Total time: 0:26:45 (0.962 s / it) [11-24 07:43:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 88/350] Total time: 0:26:45 (0.962 s / it) [11-24 07:43:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 88/350] Total time: 0:26:45 (0.962 s / it) [11-24 07:43:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 88/350] Total time: 0:26:45 (0.962 s / it) [11-24 07:43:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 88/350] Total time: 0:26:45 (0.962 s / it) [11-24 07:43:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 88/350] Total time: 0:26:45 (0.962 s / it) [11-24 07:43:35] (/home/user/VAR/train.py , line 276)=> [ep88] (training ) Lm: 6.514 (6.514), Lt: 5.763 (5.763), Acc m&t: 3.34 5.26, Remain: 4 days, 17:43:08, Finish: 2024-11-28 09:26 [11-24 07:43:35] (/home/user/VAR/train.py , line 276)=> [ep88] (training ) Lm: 6.514 (6.514), Lt: 5.763 (5.763), Acc m&t: 3.34 5.26, Remain: 4 days, 17:42:59, Finish: 2024-11-28 09:26 [11-24 07:43:35] (/home/user/VAR/train.py , line 276)=> [ep88] (training ) Lm: 6.514 (6.514), Lt: 5.763 (5.763), Acc m&t: 3.34 5.26, Remain: 4 days, 17:43:13, Finish: 2024-11-28 09:26 [11-24 07:43:35] (/home/user/VAR/train.py , line 276)=> [ep88] (training ) Lm: 6.514 (6.514), Lt: 5.763 (5.763), Acc m&t: 3.34 5.26, Remain: 4 days, 17:43:15, Finish: 2024-11-28 09:26 [11-24 07:43:35] (/home/user/VAR/train.py , line 276)=> [ep88] (training ) Lm: 6.514 (6.514), Lt: 5.763 (5.763), Acc m&t: 3.34 5.26, Remain: 4 days, 17:42:46, Finish: 2024-11-28 09:26 [11-24 07:43:35] (/home/user/VAR/train.py , line 276)=> [ep88] (training ) Lm: 6.514 (6.514), Lt: 5.763 (5.763), Acc m&t: 3.34 5.26, Remain: 4 days, 17:42:42, Finish: 2024-11-28 09:26 [11-24 07:43:35] (/home/user/VAR/train.py , line 276)=> [ep88] (training ) Lm: 6.514 (6.514), Lt: 5.763 (5.763), Acc m&t: 3.34 5.26, Remain: 4 days, 17:42:07, Finish: 2024-11-28 09:25 [11-24 07:43:35] (/home/user/VAR/train.py , line 276)=> [ep88] (training ) Lm: 6.514 (6.514), Lt: 5.763 (5.763), Acc m&t: 3.34 5.26, Remain: 4 days, 17:43:30, Finish: 2024-11-28 09:27 [11-24 07:43:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 0/1669] eta: 0:24:58 tlr: 0.00019 tnm: 0.21 Lm: 6.500 (6.500) Lt: 5.737 (5.737) Accm: 3.06 (3.06) Acct: 5.27 (5.27) proj_loss: -0.6162 (-0.6162) time: 0.8976 data: 0.0004 [11-24 07:43:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 0/1669] eta: 0:24:58 tlr: 0.00019 tnm: 0.21 Lm: 6.560 (6.560) Lt: 5.802 (5.802) Accm: 3.60 (3.60) Acct: 5.51 (5.51) proj_loss: -0.5815 (-0.5815) time: 0.8980 data: 0.0004 [11-24 07:43:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 0/1669] eta: 0:24:59 tlr: 0.00019 tnm: 0.21 Lm: 6.360 (6.360) Lt: 5.552 (5.552) Accm: 3.88 (3.88) Acct: 6.44 (6.44) proj_loss: -0.6067 (-0.6067) time: 0.8982 data: 0.0003 [11-24 07:43:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 0/1669] eta: 0:24:59 tlr: 0.00019 tnm: 0.21 Lm: 6.475 (6.475) Lt: 5.732 (5.732) Accm: 3.85 (3.85) Acct: 6.23 (6.23) proj_loss: -0.5696 (-0.5696) time: 0.8983 data: 0.0004 [11-24 07:43:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 0/1669] eta: 0:24:59 tlr: 0.00019 tnm: 0.21 Lm: 6.590 (6.590) Lt: 5.843 (5.843) Accm: 3.32 (3.32) Acct: 5.13 (5.13) proj_loss: -0.5999 (-0.5999) time: 0.8983 data: 0.0003 [11-24 07:43:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 0/1669] eta: 0:24:59 tlr: 0.00019 tnm: 0.21 Lm: 6.425 (6.425) Lt: 5.694 (5.694) Accm: 3.50 (3.50) Acct: 5.61 (5.61) proj_loss: -0.6233 (-0.6233) time: 0.8985 data: 0.0004 [11-24 07:43:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 0/1669] eta: 0:24:59 tlr: 0.00019 tnm: 0.21 Lm: 6.669 (6.669) Lt: 5.928 (5.928) Accm: 2.80 (2.80) Acct: 4.58 (4.58) proj_loss: -0.5801 (-0.5801) time: 0.8987 data: 0.0004 [11-24 07:43:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 0/1669] eta: 0:25:00 tlr: 0.00019 tnm: 0.21 Lm: 6.747 (6.747) Lt: 5.963 (5.963) Accm: 2.81 (2.81) Acct: 4.51 (4.51) proj_loss: -0.6022 (-0.6022) time: 0.8988 data: 0.0003 [11-24 07:50:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 417/1669] eta: 0:19:24 tlr: 0.00019 tnm: 0.23 Lm: 6.700 (6.700) Lt: 5.983 (5.983) Accm: 2.91 (2.91) Acct: 4.61 (4.61) proj_loss: -0.6077 (-0.6077) time: 0.9309 data: 0.0004 [11-24 07:50:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 417/1669] eta: 0:19:24 tlr: 0.00019 tnm: 0.23 Lm: 6.491 (6.491) Lt: 5.711 (5.711) Accm: 3.25 (3.25) Acct: 5.22 (5.22) proj_loss: -0.6081 (-0.6081) time: 0.9309 data: 0.0003 [11-24 07:50:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 417/1669] eta: 0:19:24 tlr: 0.00019 tnm: 0.23 Lm: 6.548 (6.548) Lt: 5.793 (5.793) Accm: 3.25 (3.25) Acct: 5.08 (5.08) proj_loss: -0.5974 (-0.5974) time: 0.9309 data: 0.0003 [11-24 07:50:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 417/1669] eta: 0:19:24 tlr: 0.00019 tnm: 0.23 Lm: 6.364 (6.364) Lt: 5.604 (5.604) Accm: 3.94 (3.94) Acct: 6.49 (6.49) proj_loss: -0.6106 (-0.6106) time: 0.9309 data: 0.0003 [11-24 07:50:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 417/1669] eta: 0:19:24 tlr: 0.00019 tnm: 0.23 Lm: 6.659 (6.659) Lt: 5.880 (5.880) Accm: 2.92 (2.92) Acct: 4.79 (4.79) proj_loss: -0.5838 (-0.5838) time: 0.9309 data: 0.0003 [11-24 07:50:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 417/1669] eta: 0:19:24 tlr: 0.00019 tnm: 0.23 Lm: 6.508 (6.508) Lt: 5.718 (5.718) Accm: 3.48 (3.48) Acct: 5.82 (5.82) proj_loss: -0.5769 (-0.5769) time: 0.9309 data: 0.0003 [11-24 07:50:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 417/1669] eta: 0:19:24 tlr: 0.00019 tnm: 0.23 Lm: 6.579 (6.579) Lt: 5.883 (5.883) Accm: 3.26 (3.26) Acct: 4.89 (4.89) proj_loss: -0.6077 (-0.6077) time: 0.9309 data: 0.0003 [11-24 07:50:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 417/1669] eta: 0:19:24 tlr: 0.00019 tnm: 0.23 Lm: 6.635 (6.635) Lt: 5.850 (5.850) Accm: 3.23 (3.23) Acct: 5.22 (5.22) proj_loss: -0.5964 (-0.5964) time: 0.9309 data: 0.0003 [11-24 07:56:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 834/1669] eta: 0:12:57 tlr: 0.00019 tnm: 0.22 Lm: 6.560 (6.600) Lt: 5.804 (5.835) Accm: 3.13 (3.20) Acct: 4.92 (5.04) proj_loss: -0.6002 (-0.5977) time: 0.9322 data: 0.0003 [11-24 07:56:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 834/1669] eta: 0:12:57 tlr: 0.00019 tnm: 0.22 Lm: 6.368 (6.372) Lt: 5.552 (5.582) Accm: 3.88 (3.81) Acct: 6.44 (6.16) proj_loss: -0.6067 (-0.5999) time: 0.9322 data: 0.0003 [11-24 07:56:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 834/1669] eta: 0:12:57 tlr: 0.00019 tnm: 0.22 Lm: 6.542 (6.527) Lt: 5.732 (5.760) Accm: 3.12 (3.30) Acct: 5.41 (5.44) proj_loss: -0.5842 (-0.5856) time: 0.9322 data: 0.0003 [11-24 07:56:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 834/1669] eta: 0:12:57 tlr: 0.00019 tnm: 0.22 Lm: 6.650 (6.604) Lt: 5.833 (5.836) Accm: 3.04 (3.03) Acct: 4.99 (4.89) proj_loss: -0.5874 (-0.5984) time: 0.9322 data: 0.0003 [11-24 07:56:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 834/1669] eta: 0:12:57 tlr: 0.00019 tnm: 0.22 Lm: 6.747 (6.723) Lt: 6.003 (6.020) Accm: 2.81 (2.77) Acct: 4.51 (4.28) proj_loss: -0.6131 (-0.6127) time: 0.9322 data: 0.0003 [11-24 07:56:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 834/1669] eta: 0:12:57 tlr: 0.00019 tnm: 0.22 Lm: 6.495 (6.492) Lt: 5.684 (5.701) Accm: 3.44 (3.33) Acct: 5.27 (5.27) proj_loss: -0.6000 (-0.6039) time: 0.9322 data: 0.0003 [11-24 07:56:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 834/1669] eta: 0:12:57 tlr: 0.00019 tnm: 0.22 Lm: 6.474 (6.544) Lt: 5.694 (5.796) Accm: 3.50 (3.44) Acct: 5.61 (5.31) proj_loss: -0.5921 (-0.5985) time: 0.9322 data: 0.0003 [11-24 07:56:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [ 834/1669] eta: 0:12:57 tlr: 0.00019 tnm: 0.22 Lm: 6.536 (6.544) Lt: 5.743 (5.771) Accm: 3.32 (3.27) Acct: 5.13 (5.19) proj_loss: -0.5949 (-0.5904) time: 0.9322 data: 0.0003 [11-24 08:03:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [1251/1669] eta: 0:06:29 tlr: 0.00019 tnm: 0.21 Lm: 6.563 (6.558) Lt: 5.792 (5.789) Accm: 3.25 (3.23) Acct: 5.11 (5.17) proj_loss: -0.5974 (-0.5936) time: 0.9302 data: 0.0003 [11-24 08:03:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [1251/1669] eta: 0:06:29 tlr: 0.00019 tnm: 0.21 Lm: 6.546 (6.562) Lt: 5.787 (5.817) Accm: 3.26 (3.33) Acct: 4.99 (5.08) proj_loss: -0.5990 (-0.6003) time: 0.9302 data: 0.0003 [11-24 08:03:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [1251/1669] eta: 0:06:29 tlr: 0.00019 tnm: 0.21 Lm: 6.566 (6.593) Lt: 5.815 (5.833) Accm: 3.13 (3.18) Acct: 4.80 (4.90) proj_loss: -0.5985 (-0.5975) time: 0.9302 data: 0.0003 [11-24 08:03:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [1251/1669] eta: 0:06:29 tlr: 0.00019 tnm: 0.21 Lm: 6.572 (6.522) Lt: 5.790 (5.768) Accm: 3.15 (3.26) Acct: 5.04 (5.17) proj_loss: -0.5840 (-0.5940) time: 0.9302 data: 0.0003 [11-24 08:03:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [1251/1669] eta: 0:06:29 tlr: 0.00019 tnm: 0.21 Lm: 6.553 (6.586) Lt: 5.788 (5.842) Accm: 3.02 (3.19) Acct: 5.04 (5.16) proj_loss: -0.5925 (-0.5894) time: 0.9302 data: 0.0003 [11-24 08:03:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [1251/1669] eta: 0:06:29 tlr: 0.00019 tnm: 0.21 Lm: 6.378 (6.429) Lt: 5.604 (5.644) Accm: 3.71 (3.64) Acct: 5.97 (5.85) proj_loss: -0.5926 (-0.5929) time: 0.9302 data: 0.0003 [11-24 08:03:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [1251/1669] eta: 0:06:29 tlr: 0.00019 tnm: 0.21 Lm: 6.498 (6.505) Lt: 5.711 (5.717) Accm: 3.31 (3.29) Acct: 5.22 (5.21) proj_loss: -0.6020 (-0.6039) time: 0.9302 data: 0.0003 [11-24 08:03:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [1251/1669] eta: 0:06:29 tlr: 0.00019 tnm: 0.21 Lm: 6.700 (6.693) Lt: 5.983 (5.962) Accm: 2.91 (2.84) Acct: 4.61 (4.54) proj_loss: -0.6077 (-0.6082) time: 0.9302 data: 0.0003 [11-24 08:09:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.653 (6.662) Lt: 5.963 (5.918) Accm: 3.02 (2.94) Acct: 4.72 (4.67) proj_loss: -0.6022 (-0.6070) time: 0.9359 data: 0.0019 [11-24 08:09:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 89/350] Total time: 0:25:55 (0.932 s / it) [11-24 08:09:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.474 (6.528) Lt: 5.694 (5.765) Accm: 3.50 (3.44) Acct: 5.61 (5.25) proj_loss: -0.5921 (-0.5966) time: 0.9359 data: 0.0017 [11-24 08:09:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.542 (6.567) Lt: 5.752 (5.824) Accm: 3.12 (3.30) Acct: 5.41 (5.30) proj_loss: -0.6008 (-0.5944) time: 0.9359 data: 0.0020 [11-24 08:09:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.536 (6.549) Lt: 5.840 (5.800) Accm: 3.18 (3.19) Acct: 5.10 (5.09) proj_loss: -0.5999 (-0.6014) time: 0.9359 data: 0.0017 [11-24 08:09:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.538 (6.525) Lt: 5.791 (5.773) Accm: 3.25 (3.32) Acct: 5.10 (5.15) proj_loss: -0.5806 (-0.5894) time: 0.9359 data: 0.0021 [11-24 08:09:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.500 (6.537) Lt: 5.737 (5.758) Accm: 3.18 (3.22) Acct: 5.17 (5.09) proj_loss: -0.6040 (-0.6043) time: 0.9359 data: 0.0013 [11-24 08:09:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.388 (6.477) Lt: 5.656 (5.690) Accm: 3.54 (3.44) Acct: 5.51 (5.56) proj_loss: -0.5836 (-0.5911) time: 0.9359 data: 0.0015 [11-24 08:09:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 89/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.560 (6.577) Lt: 5.804 (5.811) Accm: 3.13 (3.23) Acct: 4.92 (5.01) proj_loss: -0.5967 (-0.5973) time: 0.9359 data: 0.0017 [11-24 08:09:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 89/350] Total time: 0:25:55 (0.932 s / it) [11-24 08:09:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 89/350] Total time: 0:25:55 (0.932 s / it) [11-24 08:09:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 89/350] Total time: 0:25:55 (0.932 s / it) [11-24 08:09:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 89/350] Total time: 0:25:55 (0.932 s / it) [11-24 08:09:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 89/350] Total time: 0:25:55 (0.932 s / it) [11-24 08:09:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 89/350] Total time: 0:25:55 (0.932 s / it) [11-24 08:09:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 89/350] Total time: 0:25:55 (0.932 s / it) [11-24 08:11:42] (home/user/VAR/trainer.py, line 114)=> FID: 3.8620839937050278 [11-24 08:11:43] (/home/user/VAR/train.py , line 259)=> [*] [ep89] (val 50000) Lm: 6.5132, Lt: 5.7576, Acc m&t: 3.35 5.27, Val cost: 131.46s [11-24 08:11:43] (/home/user/VAR/train.py , line 264)=> [saving ckpt] ... [saving ckpt](*) finished! @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth [11-24 08:12:26] (/home/user/VAR/train.py , line 276)=> [ep89] (training ) Lm: 6.513 (6.513), Lt: 5.758 (5.758), Acc m&t: 3.35 5.27, Remain: 4 days, 17:34:18, Finish: 2024-11-28 09:43 [11-24 08:12:26] (/home/user/VAR/train.py , line 276)=> [ep89] (training ) Lm: 6.513 (6.513), Lt: 5.758 (5.758), Acc m&t: 3.35 5.27, Remain: 4 days, 17:34:59, Finish: 2024-11-28 09:44 [11-24 08:12:26] (/home/user/VAR/train.py , line 276)=> [ep89] (training ) Lm: 6.513 (6.513), Lt: 5.758 (5.758), Acc m&t: 3.35 5.27, Remain: 4 days, 17:36:15, Finish: 2024-11-28 09:45 [11-24 08:12:26] (/home/user/VAR/train.py , line 276)=> [ep89] (training ) Lm: 6.513 (6.513), Lt: 5.758 (5.758), Acc m&t: 3.35 5.27, Remain: 4 days, 17:35:27, Finish: 2024-11-28 09:44 [11-24 08:12:26] (/home/user/VAR/train.py , line 276)=> [ep89] (training ) Lm: 6.513 (6.513), Lt: 5.758 (5.758), Acc m&t: 3.35 5.27, Remain: 4 days, 17:33:17, Finish: 2024-11-28 09:42 [11-24 08:12:26] (/home/user/VAR/train.py , line 276)=> [ep89] (training ) Lm: 6.513 (6.513), Lt: 5.758 (5.758), Acc m&t: 3.35 5.27, Remain: 4 days, 17:37:33, Finish: 2024-11-28 09:47 [11-24 08:12:26] (/home/user/VAR/train.py , line 276)=> [ep89] (training ) Lm: 6.513 (6.513), Lt: 5.758 (5.758), Acc m&t: 3.35 5.27, Remain: 4 days, 17:38:10, Finish: 2024-11-28 09:47 [11-24 08:12:26] (/home/user/VAR/train.py , line 276)=> [ep89] (training ) Lm: 6.513 (6.513), Lt: 5.758 (5.758), Acc m&t: 3.35 5.27, Remain: 4 days, 17:36:07, Finish: 2024-11-28 09:45 [11-24 08:12:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 0/1669] eta: 0:24:49 tlr: 0.00019 tnm: 0.22 Lm: 6.694 (6.694) Lt: 5.956 (5.956) Accm: 2.75 (2.75) Acct: 4.37 (4.37) proj_loss: -0.5929 (-0.5929) time: 0.8925 data: 0.0004 [11-24 08:12:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 0/1669] eta: 0:24:49 tlr: 0.00019 tnm: 0.22 Lm: 6.597 (6.597) Lt: 5.729 (5.729) Accm: 3.00 (3.00) Acct: 4.82 (4.82) proj_loss: -0.5975 (-0.5975) time: 0.8922 data: 0.0003 [11-24 08:12:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 0/1669] eta: 0:24:48 tlr: 0.00019 tnm: 0.22 Lm: 6.461 (6.461) Lt: 5.705 (5.705) Accm: 3.88 (3.88) Acct: 5.89 (5.89) proj_loss: -0.5850 (-0.5850) time: 0.8919 data: 0.0004 [11-24 08:12:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 0/1669] eta: 0:24:49 tlr: 0.00019 tnm: 0.22 Lm: 6.389 (6.389) Lt: 5.617 (5.617) Accm: 3.60 (3.60) Acct: 5.85 (5.85) proj_loss: -0.6137 (-0.6137) time: 0.8923 data: 0.0004 [11-24 08:12:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 0/1669] eta: 0:24:48 tlr: 0.00019 tnm: 0.22 Lm: 6.457 (6.457) Lt: 5.684 (5.684) Accm: 3.39 (3.39) Acct: 5.37 (5.37) proj_loss: -0.6320 (-0.6320) time: 0.8921 data: 0.0004 [11-24 08:12:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 0/1669] eta: 0:24:47 tlr: 0.00019 tnm: 0.22 Lm: 6.374 (6.374) Lt: 5.595 (5.595) Accm: 3.48 (3.48) Acct: 5.82 (5.82) proj_loss: -0.5865 (-0.5865) time: 0.8911 data: 0.0004 [11-24 08:12:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 0/1669] eta: 0:24:48 tlr: 0.00019 tnm: 0.22 Lm: 6.601 (6.601) Lt: 5.840 (5.840) Accm: 3.23 (3.23) Acct: 4.89 (4.89) proj_loss: -0.5886 (-0.5886) time: 0.8916 data: 0.0004 [11-24 08:12:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 0/1669] eta: 0:25:24 tlr: 0.00019 tnm: 0.22 Lm: 6.402 (6.402) Lt: 5.531 (5.531) Accm: 3.32 (3.32) Acct: 5.44 (5.44) proj_loss: -0.5869 (-0.5869) time: 0.9136 data: 0.0004 [11-24 08:19:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 417/1669] eta: 0:20:43 tlr: 0.00019 tnm: 0.22 Lm: 6.361 (6.361) Lt: 5.516 (5.516) Accm: 3.73 (3.73) Acct: 5.99 (5.99) proj_loss: -0.6040 (-0.6040) time: 1.0051 data: 0.0003 [11-24 08:19:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 417/1669] eta: 0:20:43 tlr: 0.00019 tnm: 0.22 Lm: 6.519 (6.519) Lt: 5.754 (5.754) Accm: 3.32 (3.32) Acct: 5.49 (5.49) proj_loss: -0.5990 (-0.5990) time: 1.0051 data: 0.0003 [11-24 08:19:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 417/1669] eta: 0:20:43 tlr: 0.00019 tnm: 0.22 Lm: 6.596 (6.596) Lt: 5.820 (5.820) Accm: 3.27 (3.27) Acct: 5.06 (5.06) proj_loss: -0.6087 (-0.6087) time: 1.0051 data: 0.0003 [11-24 08:19:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 417/1669] eta: 0:20:43 tlr: 0.00019 tnm: 0.22 Lm: 6.397 (6.397) Lt: 5.586 (5.586) Accm: 3.66 (3.66) Acct: 5.77 (5.77) proj_loss: -0.6101 (-0.6101) time: 1.0051 data: 0.0003 [11-24 08:19:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 417/1669] eta: 0:20:43 tlr: 0.00019 tnm: 0.22 Lm: 6.735 (6.735) Lt: 5.983 (5.983) Accm: 2.64 (2.64) Acct: 4.24 (4.24) proj_loss: -0.5882 (-0.5882) time: 1.0051 data: 0.0003 [11-24 08:19:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 417/1669] eta: 0:20:43 tlr: 0.00019 tnm: 0.22 Lm: 6.389 (6.389) Lt: 5.613 (5.613) Accm: 3.43 (3.43) Acct: 5.60 (5.60) proj_loss: -0.5930 (-0.5930) time: 1.0051 data: 0.0003 [11-24 08:19:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 417/1669] eta: 0:20:43 tlr: 0.00019 tnm: 0.22 Lm: 6.704 (6.704) Lt: 5.959 (5.959) Accm: 2.96 (2.96) Acct: 4.60 (4.60) proj_loss: -0.5991 (-0.5991) time: 1.0051 data: 0.0003 [11-24 08:19:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 417/1669] eta: 0:20:43 tlr: 0.00019 tnm: 0.22 Lm: 6.468 (6.468) Lt: 5.731 (5.731) Accm: 3.55 (3.55) Acct: 5.49 (5.49) proj_loss: -0.5932 (-0.5932) time: 1.0051 data: 0.0003 [11-24 08:26:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 834/1669] eta: 0:13:43 tlr: 0.00019 tnm: 0.21 Lm: 6.475 (6.507) Lt: 5.757 (5.777) Accm: 3.22 (3.37) Acct: 5.10 (5.19) proj_loss: -0.6013 (-0.5963) time: 0.9789 data: 0.0003 [11-24 08:26:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 834/1669] eta: 0:13:43 tlr: 0.00019 tnm: 0.21 Lm: 6.622 (6.553) Lt: 5.891 (5.819) Accm: 3.21 (3.28) Acct: 5.13 (5.26) proj_loss: -0.6137 (-0.6060) time: 0.9789 data: 0.0003 [11-24 08:26:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 834/1669] eta: 0:13:43 tlr: 0.00019 tnm: 0.21 Lm: 6.402 (6.404) Lt: 5.531 (5.608) Accm: 3.32 (3.42) Acct: 5.44 (5.36) proj_loss: -0.5960 (-0.6014) time: 0.9789 data: 0.0003 [11-24 08:26:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 834/1669] eta: 0:13:43 tlr: 0.00019 tnm: 0.21 Lm: 6.634 (6.681) Lt: 5.883 (5.934) Accm: 3.22 (3.05) Acct: 4.89 (4.88) proj_loss: -0.5963 (-0.5982) time: 0.9789 data: 0.0003 [11-24 08:26:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 834/1669] eta: 0:13:43 tlr: 0.00019 tnm: 0.21 Lm: 6.403 (6.449) Lt: 5.632 (5.678) Accm: 3.38 (3.31) Acct: 5.37 (5.44) proj_loss: -0.5995 (-0.5968) time: 0.9789 data: 0.0003 [11-24 08:26:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 834/1669] eta: 0:13:43 tlr: 0.00019 tnm: 0.21 Lm: 6.595 (6.561) Lt: 5.762 (5.801) Accm: 3.21 (3.25) Acct: 5.23 (5.12) proj_loss: -0.6016 (-0.6063) time: 0.9789 data: 0.0003 [11-24 08:26:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 834/1669] eta: 0:13:43 tlr: 0.00019 tnm: 0.21 Lm: 6.457 (6.423) Lt: 5.684 (5.636) Accm: 3.54 (3.62) Acct: 5.75 (5.76) proj_loss: -0.5883 (-0.5957) time: 0.9789 data: 0.0003 [11-24 08:26:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 834/1669] eta: 0:13:43 tlr: 0.00019 tnm: 0.21 Lm: 6.694 (6.675) Lt: 5.956 (5.895) Accm: 2.75 (2.83) Acct: 4.37 (4.68) proj_loss: -0.5836 (-0.5819) time: 0.9789 data: 0.0003 [11-24 08:32:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1251/1669] eta: 0:06:47 tlr: 0.00019 tnm: 0.22 Lm: 6.624 (6.618) Lt: 5.838 (5.844) Accm: 2.98 (2.96) Acct: 4.98 (4.93) proj_loss: -0.5873 (-0.5842) time: 0.9306 data: 0.0003 [11-24 08:32:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1251/1669] eta: 0:06:47 tlr: 0.00019 tnm: 0.22 Lm: 6.565 (6.555) Lt: 5.774 (5.797) Accm: 3.17 (3.22) Acct: 5.04 (5.05) proj_loss: -0.6034 (-0.6061) time: 0.9306 data: 0.0002 [11-24 08:32:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1251/1669] eta: 0:06:47 tlr: 0.00019 tnm: 0.22 Lm: 6.436 (6.454) Lt: 5.692 (5.697) Accm: 3.35 (3.31) Acct: 5.29 (5.38) proj_loss: -0.6020 (-0.6050) time: 0.9306 data: 0.0003 [11-24 08:32:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1251/1669] eta: 0:06:47 tlr: 0.00019 tnm: 0.22 Lm: 6.636 (6.599) Lt: 5.920 (5.882) Accm: 3.13 (3.13) Acct: 4.96 (4.98) proj_loss: -0.5990 (-0.5933) time: 0.9306 data: 0.0003 [11-24 08:32:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1251/1669] eta: 0:06:47 tlr: 0.00019 tnm: 0.22 Lm: 6.400 (6.402) Lt: 5.555 (5.601) Accm: 3.58 (3.53) Acct: 5.96 (5.64) proj_loss: -0.6022 (-0.6031) time: 0.9306 data: 0.0003 [11-24 08:32:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1251/1669] eta: 0:06:47 tlr: 0.00019 tnm: 0.22 Lm: 6.513 (6.518) Lt: 5.780 (5.783) Accm: 3.25 (3.34) Acct: 4.99 (5.11) proj_loss: -0.6019 (-0.6019) time: 0.9306 data: 0.0003 [11-24 08:32:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1251/1669] eta: 0:06:47 tlr: 0.00019 tnm: 0.22 Lm: 6.617 (6.602) Lt: 5.862 (5.843) Accm: 3.23 (3.23) Acct: 5.17 (5.19) proj_loss: -0.6017 (-0.6004) time: 0.9306 data: 0.0003 [11-24 08:32:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1251/1669] eta: 0:06:47 tlr: 0.00019 tnm: 0.22 Lm: 6.466 (6.509) Lt: 5.711 (5.724) Accm: 3.47 (3.39) Acct: 5.56 (5.43) proj_loss: -0.5859 (-0.5926) time: 0.9306 data: 0.0003 [11-24 08:39:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.457 (6.479) Lt: 5.684 (5.684) Accm: 3.54 (3.49) Acct: 5.75 (5.69) proj_loss: -0.5883 (-0.5979) time: 0.9351 data: 0.0020 [11-24 08:39:16] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 90/350] Total time: 0:26:49 (0.964 s / it) [11-24 08:39:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.402 (6.426) Lt: 5.578 (5.644) Accm: 3.32 (3.48) Acct: 5.44 (5.51) proj_loss: -0.5960 (-0.6009) time: 0.9351 data: 0.0012 [11-24 08:39:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.650 (6.618) Lt: 5.948 (5.897) Accm: 3.04 (3.08) Acct: 4.79 (4.94) proj_loss: -0.5949 (-0.5936) time: 0.9351 data: 0.0017 [11-24 08:39:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.553 (6.595) Lt: 5.778 (5.831) Accm: 3.21 (3.02) Acct: 5.13 (4.97) proj_loss: -0.5911 (-0.5865) time: 0.9351 data: 0.0017 [11-24 08:39:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.535 (6.548) Lt: 5.762 (5.790) Accm: 3.13 (3.15) Acct: 4.86 (4.97) proj_loss: -0.6038 (-0.6056) time: 0.9351 data: 0.0015 [11-24 08:39:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.435 (6.450) Lt: 5.632 (5.674) Accm: 3.35 (3.32) Acct: 5.23 (5.35) proj_loss: -0.6044 (-0.6066) time: 0.9351 data: 0.0015 [11-24 08:39:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.634 (6.627) Lt: 5.883 (5.868) Accm: 3.22 (3.09) Acct: 4.89 (4.99) proj_loss: -0.5963 (-0.5921) time: 0.9351 data: 0.0016 [11-24 08:39:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.475 (6.462) Lt: 5.757 (5.717) Accm: 3.28 (3.39) Acct: 5.10 (5.18) proj_loss: -0.6013 (-0.5971) time: 0.9351 data: 0.0018 [11-24 08:39:16] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 90/350] Total time: 0:26:49 (0.964 s / it) [11-24 08:39:16] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 90/350] Total time: 0:26:49 (0.964 s / it) [11-24 08:39:16] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 90/350] Total time: 0:26:49 (0.964 s / it) [11-24 08:39:16] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 90/350] Total time: 0:26:49 (0.964 s / it) [11-24 08:39:16] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 90/350] Total time: 0:26:49 (0.964 s / it) [11-24 08:39:16] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 90/350] Total time: 0:26:49 (0.964 s / it) [11-24 08:39:16] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 90/350] Total time: 0:26:49 (0.964 s / it) [11-24 08:39:16] (/home/user/VAR/train.py , line 276)=> [ep90] (training ) Lm: 6.513 (6.530), Lt: 5.758 (5.779), Acc m&t: 3.35 5.27, Remain: 4 days, 16:53:20, Finish: 2024-11-28 09:32 [11-24 08:39:16] (/home/user/VAR/train.py , line 276)=> [ep90] (training ) Lm: 6.513 (6.530), Lt: 5.758 (5.779), Acc m&t: 3.35 5.27, Remain: 4 days, 16:49:08, Finish: 2024-11-28 09:28 [11-24 08:39:16] (/home/user/VAR/train.py , line 276)=> [ep90] (training ) Lm: 6.513 (6.530), Lt: 5.758 (5.779), Acc m&t: 3.35 5.27, Remain: 4 days, 16:55:09, Finish: 2024-11-28 09:34 [11-24 08:39:16] (/home/user/VAR/train.py , line 276)=> [ep90] (training ) Lm: 6.513 (6.530), Lt: 5.758 (5.779), Acc m&t: 3.35 5.27, Remain: 4 days, 16:54:19, Finish: 2024-11-28 09:33 [11-24 08:39:16] (/home/user/VAR/train.py , line 276)=> [ep90] (training ) Lm: 6.513 (6.530), Lt: 5.758 (5.779), Acc m&t: 3.35 5.27, Remain: 4 days, 16:54:17, Finish: 2024-11-28 09:33 [11-24 08:39:16] (/home/user/VAR/train.py , line 276)=> [ep90] (training ) Lm: 6.513 (6.530), Lt: 5.758 (5.779), Acc m&t: 3.35 5.27, Remain: 4 days, 16:54:22, Finish: 2024-11-28 09:33 [11-24 08:39:16] (/home/user/VAR/train.py , line 276)=> [ep90] (training ) Lm: 6.513 (6.530), Lt: 5.758 (5.779), Acc m&t: 3.35 5.27, Remain: 4 days, 16:53:20, Finish: 2024-11-28 09:32 [11-24 08:39:16] (/home/user/VAR/train.py , line 276)=> [ep90] (training ) Lm: 6.513 (6.530), Lt: 5.758 (5.779), Acc m&t: 3.35 5.27, Remain: 4 days, 16:54:22, Finish: 2024-11-28 09:33 [11-24 08:39:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 0/1669] eta: 0:24:44 tlr: 0.00019 tnm: 0.21 Lm: 6.592 (6.592) Lt: 5.844 (5.844) Accm: 2.90 (2.90) Acct: 4.51 (4.51) proj_loss: -0.5902 (-0.5902) time: 0.8894 data: 0.0004 [11-24 08:39:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 0/1669] eta: 0:24:45 tlr: 0.00019 tnm: 0.21 Lm: 6.391 (6.391) Lt: 5.621 (5.621) Accm: 3.70 (3.70) Acct: 6.03 (6.03) proj_loss: -0.5758 (-0.5758) time: 0.8902 data: 0.0004 [11-24 08:39:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 0/1669] eta: 0:26:06 tlr: 0.00019 tnm: 0.21 Lm: 6.428 (6.428) Lt: 5.641 (5.641) Accm: 3.58 (3.58) Acct: 6.37 (6.37) proj_loss: -0.6081 (-0.6081) time: 0.9386 data: 0.0004 [11-24 08:39:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 0/1669] eta: 0:25:24 tlr: 0.00019 tnm: 0.21 Lm: 6.291 (6.291) Lt: 5.510 (5.510) Accm: 3.66 (3.66) Acct: 5.79 (5.79) proj_loss: -0.6071 (-0.6071) time: 0.9135 data: 0.0005 [11-24 08:39:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 0/1669] eta: 0:24:57 tlr: 0.00019 tnm: 0.21 Lm: 6.496 (6.496) Lt: 5.658 (5.658) Accm: 3.67 (3.67) Acct: 5.82 (5.82) proj_loss: -0.5438 (-0.5438) time: 0.8971 data: 0.0003 [11-24 08:39:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 0/1669] eta: 0:25:45 tlr: 0.00019 tnm: 0.21 Lm: 6.473 (6.473) Lt: 5.603 (5.603) Accm: 3.67 (3.67) Acct: 5.58 (5.58) proj_loss: -0.6329 (-0.6329) time: 0.9262 data: 0.0004 [11-24 08:39:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 0/1669] eta: 0:26:06 tlr: 0.00019 tnm: 0.21 Lm: 6.578 (6.578) Lt: 5.861 (5.861) Accm: 3.37 (3.37) Acct: 5.17 (5.17) proj_loss: -0.6052 (-0.6052) time: 0.9388 data: 0.0004 [11-24 08:39:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 0/1669] eta: 0:24:46 tlr: 0.00019 tnm: 0.21 Lm: 6.637 (6.637) Lt: 5.961 (5.961) Accm: 3.00 (3.00) Acct: 4.48 (4.48) proj_loss: -0.6052 (-0.6052) time: 0.8904 data: 0.0005 [11-24 08:45:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 417/1669] eta: 0:19:25 tlr: 0.00019 tnm: 0.21 Lm: 6.534 (6.534) Lt: 5.803 (5.803) Accm: 3.27 (3.27) Acct: 4.92 (4.92) proj_loss: -0.5877 (-0.5877) time: 0.9313 data: 0.0003 [11-24 08:45:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 417/1669] eta: 0:19:25 tlr: 0.00019 tnm: 0.21 Lm: 6.544 (6.544) Lt: 5.807 (5.807) Accm: 3.21 (3.21) Acct: 4.94 (4.94) proj_loss: -0.5934 (-0.5934) time: 0.9313 data: 0.0003 [11-24 08:45:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 417/1669] eta: 0:19:25 tlr: 0.00019 tnm: 0.21 Lm: 6.441 (6.441) Lt: 5.686 (5.686) Accm: 3.44 (3.44) Acct: 5.23 (5.23) proj_loss: -0.6015 (-0.6015) time: 0.9313 data: 0.0003 [11-24 08:45:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 417/1669] eta: 0:19:25 tlr: 0.00019 tnm: 0.21 Lm: 6.444 (6.444) Lt: 5.653 (5.653) Accm: 3.55 (3.55) Acct: 5.56 (5.56) proj_loss: -0.5718 (-0.5718) time: 0.9313 data: 0.0003 [11-24 08:45:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 417/1669] eta: 0:19:25 tlr: 0.00019 tnm: 0.21 Lm: 6.497 (6.497) Lt: 5.630 (5.630) Accm: 3.68 (3.68) Acct: 5.96 (5.96) proj_loss: -0.6101 (-0.6101) time: 0.9313 data: 0.0003 [11-24 08:45:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 417/1669] eta: 0:19:25 tlr: 0.00019 tnm: 0.21 Lm: 6.543 (6.543) Lt: 5.835 (5.835) Accm: 3.53 (3.53) Acct: 5.20 (5.20) proj_loss: -0.6203 (-0.6203) time: 0.9313 data: 0.0003 [11-24 08:45:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 417/1669] eta: 0:19:25 tlr: 0.00019 tnm: 0.21 Lm: 6.606 (6.606) Lt: 5.833 (5.833) Accm: 3.15 (3.15) Acct: 5.04 (5.04) proj_loss: -0.5845 (-0.5845) time: 0.9313 data: 0.0003 [11-24 08:45:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 417/1669] eta: 0:19:25 tlr: 0.00019 tnm: 0.21 Lm: 6.549 (6.549) Lt: 5.805 (5.805) Accm: 3.04 (3.04) Acct: 5.13 (5.13) proj_loss: -0.6028 (-0.6028) time: 0.9313 data: 0.0003 [11-24 08:52:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 834/1669] eta: 0:12:59 tlr: 0.00019 tnm: 0.22 Lm: 6.471 (6.523) Lt: 5.708 (5.773) Accm: 3.58 (3.30) Acct: 5.92 (5.39) proj_loss: -0.6081 (-0.6100) time: 0.9327 data: 0.0003 [11-24 08:52:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 834/1669] eta: 0:12:58 tlr: 0.00019 tnm: 0.22 Lm: 6.496 (6.526) Lt: 5.658 (5.720) Accm: 3.44 (3.32) Acct: 5.30 (5.46) proj_loss: -0.5842 (-0.5759) time: 0.9327 data: 0.0003 [11-24 08:52:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 834/1669] eta: 0:12:58 tlr: 0.00019 tnm: 0.22 Lm: 6.630 (6.614) Lt: 5.918 (5.861) Accm: 3.18 (3.16) Acct: 4.72 (4.94) proj_loss: -0.5758 (-0.5763) time: 0.9327 data: 0.0003 [11-24 08:52:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 834/1669] eta: 0:12:59 tlr: 0.00019 tnm: 0.22 Lm: 6.590 (6.493) Lt: 5.781 (5.718) Accm: 3.51 (3.46) Acct: 5.75 (5.41) proj_loss: -0.6071 (-0.6036) time: 0.9327 data: 0.0003 [11-24 08:52:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 834/1669] eta: 0:12:58 tlr: 0.00019 tnm: 0.22 Lm: 6.495 (6.474) Lt: 5.770 (5.716) Accm: 3.51 (3.44) Acct: 5.37 (5.31) proj_loss: -0.5951 (-0.5940) time: 0.9327 data: 0.0003 [11-24 08:52:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 834/1669] eta: 0:12:59 tlr: 0.00019 tnm: 0.22 Lm: 6.578 (6.582) Lt: 5.861 (5.871) Accm: 3.37 (3.24) Acct: 5.17 (4.91) proj_loss: -0.6154 (-0.6186) time: 0.9327 data: 0.0003 [11-24 08:52:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 834/1669] eta: 0:12:59 tlr: 0.00019 tnm: 0.22 Lm: 6.522 (6.508) Lt: 5.658 (5.665) Accm: 3.67 (3.56) Acct: 5.58 (5.60) proj_loss: -0.5966 (-0.6056) time: 0.9327 data: 0.0003 [11-24 08:52:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 834/1669] eta: 0:12:58 tlr: 0.00019 tnm: 0.22 Lm: 6.637 (6.590) Lt: 5.961 (5.880) Accm: 3.00 (3.09) Acct: 4.48 (4.76) proj_loss: -0.6052 (-0.5964) time: 0.9327 data: 0.0003 [11-24 08:58:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1251/1669] eta: 0:06:31 tlr: 0.00019 tnm: 0.22 Lm: 6.621 (6.594) Lt: 5.918 (5.879) Accm: 3.04 (3.09) Acct: 4.84 (4.87) proj_loss: -0.6038 (-0.5979) time: 1.0623 data: 0.0002 [11-24 08:58:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1251/1669] eta: 0:06:31 tlr: 0.00019 tnm: 0.22 Lm: 6.464 (6.464) Lt: 5.737 (5.713) Accm: 3.53 (3.46) Acct: 5.51 (5.40) proj_loss: -0.5958 (-0.5978) time: 1.0623 data: 0.0003 [11-24 08:58:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1251/1669] eta: 0:06:31 tlr: 0.00019 tnm: 0.22 Lm: 6.444 (6.458) Lt: 5.653 (5.656) Accm: 3.55 (3.54) Acct: 5.56 (5.67) proj_loss: -0.5920 (-0.5866) time: 1.0623 data: 0.0003 [11-24 08:58:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1251/1669] eta: 0:06:31 tlr: 0.00019 tnm: 0.22 Lm: 6.543 (6.547) Lt: 5.835 (5.790) Accm: 3.36 (3.27) Acct: 5.20 (5.00) proj_loss: -0.6103 (-0.6066) time: 1.0623 data: 0.0003 [11-24 08:58:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1251/1669] eta: 0:06:31 tlr: 0.00019 tnm: 0.22 Lm: 6.587 (6.596) Lt: 5.884 (5.858) Accm: 3.31 (3.23) Acct: 4.98 (5.01) proj_loss: -0.5845 (-0.5943) time: 1.0623 data: 0.0003 [11-24 08:58:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1251/1669] eta: 0:06:31 tlr: 0.00019 tnm: 0.22 Lm: 6.567 (6.558) Lt: 5.838 (5.830) Accm: 3.18 (3.17) Acct: 4.98 (5.05) proj_loss: -0.6028 (-0.6049) time: 1.0623 data: 0.0003 [11-24 08:58:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1251/1669] eta: 0:06:31 tlr: 0.00019 tnm: 0.22 Lm: 6.574 (6.509) Lt: 5.808 (5.747) Accm: 3.37 (3.39) Acct: 5.25 (5.24) proj_loss: -0.6075 (-0.6075) time: 1.0623 data: 0.0003 [11-24 08:58:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1251/1669] eta: 0:06:31 tlr: 0.00019 tnm: 0.22 Lm: 6.526 (6.555) Lt: 5.696 (5.749) Accm: 3.50 (3.31) Acct: 5.23 (5.11) proj_loss: -0.5970 (-0.6035) time: 1.0623 data: 0.0003 [11-24 09:06:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.529 (6.561) Lt: 5.735 (5.765) Accm: 3.32 (3.28) Acct: 5.37 (5.16) proj_loss: -0.5966 (-0.5989) time: 0.9924 data: 0.0018 [11-24 09:06:01] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 91/350] Total time: 0:26:44 (0.961 s / it) [11-24 09:06:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.605 (6.575) Lt: 5.876 (5.853) Accm: 3.09 (3.18) Acct: 5.20 (5.08) proj_loss: -0.6024 (-0.5960) time: 0.9924 data: 0.0020 [11-24 09:06:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.525 (6.551) Lt: 5.766 (5.817) Accm: 3.26 (3.19) Acct: 4.92 (5.03) proj_loss: -0.5975 (-0.6015) time: 0.9924 data: 0.0015 [11-24 09:06:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.456 (6.462) Lt: 5.704 (5.702) Accm: 3.54 (3.51) Acct: 5.65 (5.48) proj_loss: -0.5951 (-0.5965) time: 0.9924 data: 0.0013 [11-24 09:06:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.547 (6.547) Lt: 5.816 (5.795) Accm: 3.35 (3.25) Acct: 5.17 (4.99) proj_loss: -0.6052 (-0.5958) time: 0.9924 data: 0.0018 [11-24 09:06:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.590 (6.536) Lt: 5.834 (5.784) Accm: 3.22 (3.30) Acct: 4.75 (5.10) proj_loss: -0.6071 (-0.6024) time: 0.9924 data: 0.0018 [11-24 09:06:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.544 (6.567) Lt: 5.850 (5.822) Accm: 3.45 (3.30) Acct: 5.23 (5.14) proj_loss: -0.5932 (-0.5941) time: 0.9924 data: 0.0018 [11-24 09:06:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.417 (6.450) Lt: 5.649 (5.646) Accm: 3.64 (3.56) Acct: 5.68 (5.67) proj_loss: -0.5998 (-0.5910) time: 0.9924 data: 0.0017 [11-24 09:06:01] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 91/350] Total time: 0:26:44 (0.961 s / it) [11-24 09:06:01] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 91/350] Total time: 0:26:44 (0.961 s / it) [11-24 09:06:01] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 91/350] Total time: 0:26:44 (0.961 s / it) [11-24 09:06:01] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 91/350] Total time: 0:26:44 (0.961 s / it) [11-24 09:06:01] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 91/350] Total time: 0:26:44 (0.961 s / it) [11-24 09:06:01] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 91/350] Total time: 0:26:44 (0.961 s / it) [11-24 09:06:01] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 91/350] Total time: 0:26:44 (0.961 s / it) [11-24 09:06:01] (/home/user/VAR/train.py , line 276)=> [ep91] (training ) Lm: 6.507 (6.507), Lt: 5.752 (5.752), Acc m&t: 3.35 5.28, Remain: 4 days, 16:38:00, Finish: 2024-11-28 09:44 [11-24 09:06:01] (/home/user/VAR/train.py , line 276)=> [ep91] (training ) Lm: 6.507 (6.507), Lt: 5.752 (5.752), Acc m&t: 3.35 5.28, Remain: 4 days, 16:39:03, Finish: 2024-11-28 09:45 [11-24 09:06:01] (/home/user/VAR/train.py , line 276)=> [ep91] (training ) Lm: 6.507 (6.507), Lt: 5.752 (5.752), Acc m&t: 3.35 5.28, Remain: 4 days, 16:37:51, Finish: 2024-11-28 09:43 [11-24 09:06:01] (/home/user/VAR/train.py , line 276)=> [ep91] (training ) Lm: 6.507 (6.507), Lt: 5.752 (5.752), Acc m&t: 3.35 5.28, Remain: 4 days, 16:39:30, Finish: 2024-11-28 09:45 [11-24 09:06:01] (/home/user/VAR/train.py , line 276)=> [ep91] (training ) Lm: 6.507 (6.507), Lt: 5.752 (5.752), Acc m&t: 3.35 5.28, Remain: 4 days, 16:38:40, Finish: 2024-11-28 09:44 [11-24 09:06:01] (/home/user/VAR/train.py , line 276)=> [ep91] (training ) Lm: 6.507 (6.507), Lt: 5.752 (5.752), Acc m&t: 3.35 5.28, Remain: 4 days, 16:38:46, Finish: 2024-11-28 09:44 [11-24 09:06:01] (/home/user/VAR/train.py , line 276)=> [ep91] (training ) Lm: 6.507 (6.507), Lt: 5.752 (5.752), Acc m&t: 3.35 5.28, Remain: 4 days, 16:37:50, Finish: 2024-11-28 09:43 [11-24 09:06:01] (/home/user/VAR/train.py , line 276)=> [ep91] (training ) Lm: 6.507 (6.507), Lt: 5.752 (5.752), Acc m&t: 3.35 5.28, Remain: 4 days, 16:39:33, Finish: 2024-11-28 09:45 [11-24 09:06:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 0/1669] eta: 0:24:48 tlr: 0.00019 tnm: 0.22 Lm: 6.345 (6.345) Lt: 5.506 (5.506) Accm: 3.69 (3.69) Acct: 5.79 (5.79) proj_loss: -0.5991 (-0.5991) time: 0.8918 data: 0.0003 [11-24 09:06:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 0/1669] eta: 0:24:50 tlr: 0.00019 tnm: 0.22 Lm: 6.321 (6.321) Lt: 5.636 (5.636) Accm: 3.88 (3.88) Acct: 5.75 (5.75) proj_loss: -0.6162 (-0.6162) time: 0.8933 data: 0.0004 [11-24 09:06:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 0/1669] eta: 0:24:50 tlr: 0.00019 tnm: 0.22 Lm: 6.554 (6.554) Lt: 5.807 (5.807) Accm: 3.44 (3.44) Acct: 5.10 (5.10) proj_loss: -0.6080 (-0.6080) time: 0.8929 data: 0.0004 [11-24 09:06:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 0/1669] eta: 0:24:51 tlr: 0.00019 tnm: 0.22 Lm: 6.520 (6.520) Lt: 5.720 (5.720) Accm: 3.50 (3.50) Acct: 5.61 (5.61) proj_loss: -0.5966 (-0.5966) time: 0.8937 data: 0.0004 [11-24 09:06:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 0/1669] eta: 0:24:50 tlr: 0.00019 tnm: 0.22 Lm: 6.557 (6.557) Lt: 5.869 (5.869) Accm: 2.86 (2.86) Acct: 4.24 (4.24) proj_loss: -0.5877 (-0.5877) time: 0.8928 data: 0.0004 [11-24 09:06:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 0/1669] eta: 0:24:51 tlr: 0.00019 tnm: 0.22 Lm: 6.220 (6.220) Lt: 5.406 (5.406) Accm: 4.66 (4.66) Acct: 7.09 (7.09) proj_loss: -0.6183 (-0.6183) time: 0.8937 data: 0.0003 [11-24 09:06:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 0/1669] eta: 0:24:51 tlr: 0.00019 tnm: 0.22 Lm: 6.517 (6.517) Lt: 5.769 (5.769) Accm: 3.12 (3.12) Acct: 4.65 (4.65) proj_loss: -0.6083 (-0.6083) time: 0.8938 data: 0.0004 [11-24 09:06:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 0/1669] eta: 0:24:52 tlr: 0.00019 tnm: 0.22 Lm: 6.476 (6.476) Lt: 5.702 (5.702) Accm: 3.53 (3.53) Acct: 5.54 (5.54) proj_loss: -0.6205 (-0.6205) time: 0.8941 data: 0.0004 [11-24 09:12:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 417/1669] eta: 0:19:29 tlr: 0.00019 tnm: 0.20 Lm: 6.501 (6.501) Lt: 5.774 (5.774) Accm: 3.47 (3.47) Acct: 5.23 (5.23) proj_loss: -0.6089 (-0.6089) time: 0.9306 data: 0.0003 [11-24 09:12:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 417/1669] eta: 0:19:29 tlr: 0.00019 tnm: 0.20 Lm: 6.474 (6.474) Lt: 5.685 (5.685) Accm: 3.26 (3.26) Acct: 4.99 (4.99) proj_loss: -0.5905 (-0.5905) time: 0.9306 data: 0.0003 [11-24 09:12:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 417/1669] eta: 0:19:29 tlr: 0.00019 tnm: 0.20 Lm: 6.545 (6.545) Lt: 5.858 (5.858) Accm: 3.18 (3.18) Acct: 4.86 (4.86) proj_loss: -0.6091 (-0.6091) time: 0.9306 data: 0.0003 [11-24 09:12:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 417/1669] eta: 0:19:29 tlr: 0.00019 tnm: 0.20 Lm: 6.370 (6.370) Lt: 5.599 (5.599) Accm: 3.89 (3.89) Acct: 6.03 (6.03) proj_loss: -0.6027 (-0.6027) time: 0.9306 data: 0.0003 [11-24 09:12:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 417/1669] eta: 0:19:29 tlr: 0.00019 tnm: 0.20 Lm: 6.321 (6.321) Lt: 5.558 (5.558) Accm: 4.17 (4.17) Acct: 6.22 (6.22) proj_loss: -0.6085 (-0.6085) time: 0.9306 data: 0.0003 [11-24 09:12:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 417/1669] eta: 0:19:29 tlr: 0.00019 tnm: 0.20 Lm: 6.588 (6.588) Lt: 5.860 (5.860) Accm: 2.91 (2.91) Acct: 4.56 (4.56) proj_loss: -0.5959 (-0.5959) time: 0.9306 data: 0.0003 [11-24 09:12:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 417/1669] eta: 0:19:29 tlr: 0.00019 tnm: 0.20 Lm: 6.446 (6.446) Lt: 5.648 (5.648) Accm: 3.62 (3.62) Acct: 5.96 (5.96) proj_loss: -0.5975 (-0.5975) time: 0.9306 data: 0.0003 [11-24 09:12:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 417/1669] eta: 0:19:29 tlr: 0.00019 tnm: 0.20 Lm: 6.301 (6.301) Lt: 5.523 (5.523) Accm: 3.70 (3.70) Acct: 5.89 (5.89) proj_loss: -0.5925 (-0.5925) time: 0.9306 data: 0.0003 [11-24 09:19:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 834/1669] eta: 0:12:58 tlr: 0.00019 tnm: 0.22 Lm: 6.272 (6.291) Lt: 5.506 (5.479) Accm: 3.69 (3.66) Acct: 5.79 (5.84) proj_loss: -0.5991 (-0.5963) time: 0.9308 data: 0.0003 [11-24 09:19:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 834/1669] eta: 0:12:58 tlr: 0.00019 tnm: 0.22 Lm: 6.554 (6.422) Lt: 5.807 (5.663) Accm: 3.44 (3.80) Acct: 5.10 (5.70) proj_loss: -0.6091 (-0.6165) time: 0.9308 data: 0.0003 [11-24 09:19:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 834/1669] eta: 0:12:58 tlr: 0.00019 tnm: 0.22 Lm: 6.518 (6.470) Lt: 5.720 (5.678) Accm: 3.74 (3.72) Acct: 6.10 (6.00) proj_loss: -0.5966 (-0.5946) time: 0.9308 data: 0.0003 [11-24 09:19:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 834/1669] eta: 0:12:58 tlr: 0.00019 tnm: 0.22 Lm: 6.520 (6.508) Lt: 5.818 (5.789) Accm: 3.42 (3.45) Acct: 4.92 (5.07) proj_loss: -0.6192 (-0.6123) time: 0.9308 data: 0.0003 [11-24 09:19:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 834/1669] eta: 0:12:58 tlr: 0.00019 tnm: 0.22 Lm: 6.517 (6.530) Lt: 5.769 (5.763) Accm: 3.12 (3.16) Acct: 4.75 (4.91) proj_loss: -0.6083 (-0.5991) time: 0.9308 data: 0.0003 [11-24 09:19:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 834/1669] eta: 0:12:58 tlr: 0.00019 tnm: 0.22 Lm: 6.564 (6.580) Lt: 5.865 (5.862) Accm: 2.97 (2.98) Acct: 4.55 (4.56) proj_loss: -0.6041 (-0.6012) time: 0.9308 data: 0.0003 [11-24 09:19:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 834/1669] eta: 0:12:58 tlr: 0.00019 tnm: 0.22 Lm: 6.478 (6.523) Lt: 5.765 (5.827) Accm: 3.66 (3.34) Acct: 5.37 (5.03) proj_loss: -0.6044 (-0.6075) time: 0.9309 data: 0.0003 [11-24 09:19:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 834/1669] eta: 0:12:58 tlr: 0.00019 tnm: 0.22 Lm: 6.474 (6.405) Lt: 5.710 (5.636) Accm: 3.41 (3.73) Acct: 5.23 (5.76) proj_loss: -0.5980 (-0.6011) time: 0.9308 data: 0.0003 [11-24 09:25:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [1251/1669] eta: 0:06:30 tlr: 0.00019 tnm: 0.22 Lm: 6.493 (6.432) Lt: 5.751 (5.675) Accm: 3.53 (3.71) Acct: 5.35 (5.69) proj_loss: -0.6082 (-0.6070) time: 1.0039 data: 0.0003 [11-24 09:25:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [1251/1669] eta: 0:06:30 tlr: 0.00019 tnm: 0.22 Lm: 6.558 (6.551) Lt: 5.826 (5.842) Accm: 3.22 (3.20) Acct: 4.87 (4.86) proj_loss: -0.6032 (-0.6053) time: 1.0039 data: 0.0003 [11-24 09:25:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [1251/1669] eta: 0:06:30 tlr: 0.00019 tnm: 0.22 Lm: 6.560 (6.538) Lt: 5.859 (5.820) Accm: 3.04 (3.07) Acct: 4.58 (4.57) proj_loss: -0.6079 (-0.6073) time: 1.0039 data: 0.0003 [11-24 09:25:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [1251/1669] eta: 0:06:30 tlr: 0.00019 tnm: 0.22 Lm: 6.499 (6.500) Lt: 5.776 (5.775) Accm: 3.42 (3.38) Acct: 5.08 (5.11) proj_loss: -0.6082 (-0.6079) time: 1.0039 data: 0.0003 [11-24 09:25:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [1251/1669] eta: 0:06:30 tlr: 0.00019 tnm: 0.22 Lm: 6.308 (6.364) Lt: 5.523 (5.559) Accm: 3.63 (3.53) Acct: 5.77 (5.60) proj_loss: -0.5969 (-0.5959) time: 1.0040 data: 0.0004 [11-24 09:25:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [1251/1669] eta: 0:06:30 tlr: 0.00019 tnm: 0.22 Lm: 6.564 (6.460) Lt: 5.840 (5.721) Accm: 3.41 (3.69) Acct: 5.17 (5.59) proj_loss: -0.6085 (-0.6105) time: 1.0039 data: 0.0003 [11-24 09:25:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [1251/1669] eta: 0:06:30 tlr: 0.00019 tnm: 0.22 Lm: 6.519 (6.528) Lt: 5.773 (5.766) Accm: 3.26 (3.22) Acct: 5.01 (5.00) proj_loss: -0.6097 (-0.6021) time: 1.0040 data: 0.0003 [11-24 09:25:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [1251/1669] eta: 0:06:30 tlr: 0.00019 tnm: 0.22 Lm: 6.447 (6.446) Lt: 5.652 (5.654) Accm: 3.73 (3.72) Acct: 6.06 (6.01) proj_loss: -0.5928 (-0.5864) time: 1.0040 data: 0.0003 ======================================================= RESTART [11-24 10:12:30] ======================================================= ======================================================= RESTART [11-24 10:12:30] ======================================================= ======================================================= RESTART [11-24 10:12:30] ======================================================= ======================================================= RESTART [11-24 10:12:30] ======================================================= ======================================================= RESTART [11-24 10:12:30] ======================================================= ======================================================= RESTART [11-24 10:12:30] ======================================================= [11-24 10:12:30] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-24 10:12:30] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-24 10:12:30] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-24 10:14:10] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=16 [11-24 10:14:10] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 16 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main } [11-24 10:14:10] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-24 10:14:13] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-24 10:14:13] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> [11-24 10:14:13] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-24 10:14:13] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> [11-24 10:14:13] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-24 10:14:13] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-24 10:14:13] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep90, it0 [11-24 10:14:13] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-24 10:12:30] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-24 10:12:30] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-24 10:12:30] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-24 10:14:10] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=16 [11-24 10:14:10] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 16 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main commit_msg : add } [11-24 10:14:10] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-24 10:14:13] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-24 10:14:13] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> [11-24 10:14:13] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-24 10:14:13] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> [11-24 10:14:13] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-24 10:14:13] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-24 10:14:13] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep90, it0 [11-24 10:14:13] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-24 10:12:30] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-24 10:12:30] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-24 10:12:30] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-24 10:14:10] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=16 [11-24 10:14:10] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 16 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add branch : main } [11-24 10:14:10] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-24 10:14:13] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-24 10:14:13] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> [11-24 10:14:13] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-24 10:14:13] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> [11-24 10:14:13] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-24 10:14:13] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-24 10:14:13] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep90, it0 [11-24 10:14:13] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-24 10:12:30] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-24 10:12:30] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-24 10:12:30] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-24 10:14:10] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=16 [11-24 10:14:10] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 16 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main } [11-24 10:14:10] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-24 10:14:13] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-24 10:14:13] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> [11-24 10:14:13] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-24 10:14:13] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> [11-24 10:14:13] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-24 10:14:13] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-24 10:14:13] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep90, it0 [11-24 10:14:13] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-24 10:12:30] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-24 10:12:30] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-24 10:12:30] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-24 10:14:10] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=16 [11-24 10:14:10] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 16 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add branch : main } [11-24 10:14:10] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-24 10:14:13] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-24 10:14:13] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> [11-24 10:14:13] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-24 10:14:13] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> [11-24 10:14:13] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-24 10:14:13] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-24 10:14:13] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep90, it0 [11-24 10:14:13] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-24 10:12:30] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-24 10:12:30] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-24 10:12:30] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-24 10:14:10] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=16 [11-24 10:14:10] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 16 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-24 10:14:10] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-24 10:14:13] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-24 10:14:13] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> [11-24 10:14:13] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-24 10:14:13] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-24 10:14:13] (e/user/VAR/utils/data.py, line 51)=> [11-24 10:14:13] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-24 10:14:13] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-24 10:14:13] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep90, it0 [11-24 10:14:13] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ... [dataloader multi processing](*) finished! (47.24s) [dataloader multi processing](*) finished! (47.24s) [dataloader multi processing](*) finished! (48.66s) [dataloader multi processing](*) finished! (48.68s) [dataloader multi processing](*) finished! (49.11s) [dataloader multi processing](*) finished! (50.75s) [11-24 10:15:00] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=16, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-24 10:15:03] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-24 10:15:03] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-24 10:15:04] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-24 10:15:00] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=16, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-24 10:15:05] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-24 10:15:05] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-24 10:15:06] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-24 10:15:02] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=16, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-24 10:15:06] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-24 10:15:06] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-24 10:15:08] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-24 10:15:02] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=16, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-24 10:15:06] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-24 10:15:06] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-24 10:15:08] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-24 10:15:01] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=16, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-24 10:15:06] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-24 10:15:06] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-24 10:15:08] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-24 10:15:04] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=16, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-24 10:15:08] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-24 10:15:08] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-24 10:15:09] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-24 10:15:07] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-24 10:15:33] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-24 10:15:33] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-24 10:15:33] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-24 10:15:33] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-24 10:15:34] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank0] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-24 10:15:11] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-24 10:15:33] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-24 10:15:33] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-24 10:15:33] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-24 10:15:33] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-24 10:15:34] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank8] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-24 10:15:11] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-24 10:15:33] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-24 10:15:33] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-24 10:15:33] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-24 10:15:33] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-24 10:15:34] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank16] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-24 10:15:09] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-24 10:15:33] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-24 10:15:33] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-24 10:15:33] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-24 10:15:33] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-24 10:15:34] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank24] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-24 10:15:13] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-24 10:15:33] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-24 10:15:33] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-24 10:15:33] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-24 10:15:33] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-24 10:15:34] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank32] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-24 10:15:11] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-24 10:15:33] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-24 10:15:33] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-24 10:15:33] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-24 10:15:33] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-24 10:15:34] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank40] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-24 10:15:34] (/VAR/utils/lr_control.py, line 105)=> [11-24 10:15:34] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-24 10:15:36] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-24 10:15:36] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-24 10:15:36] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-24 10:15:36] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-24 10:33:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 0/1669] eta: 20 days, 8:37:13 tlr: 0.00019 tnm: 0.21 Lm: 6.477 (6.477) Lt: 5.787 (5.787) Accm: 3.30 (3.30) Acct: 4.83 (4.83) proj_loss: -0.6217 (-0.6217) time: 1053.9447 data: 0.0005 [11-24 10:15:34] (/VAR/utils/lr_control.py, line 105)=> [11-24 10:15:34] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-24 10:15:36] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-24 10:15:36] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-24 10:15:37] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-24 10:15:37] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-24 10:33:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 0/1669] eta: 20 days, 9:02:03 tlr: 0.00019 tnm: 0.21 Lm: 6.513 (6.513) Lt: 5.795 (5.795) Accm: 3.17 (3.17) Acct: 4.96 (4.96) proj_loss: -0.5725 (-0.5725) time: 1054.8371 data: 0.0007 [11-24 10:15:34] (/VAR/utils/lr_control.py, line 105)=> [11-24 10:15:34] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-24 10:15:36] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-24 10:15:36] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-24 10:15:37] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-24 10:15:37] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-24 10:33:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 0/1669] eta: 20 days, 8:31:04 tlr: 0.00019 tnm: 0.21 Lm: 6.446 (6.446) Lt: 5.682 (5.682) Accm: 3.49 (3.49) Acct: 5.45 (5.45) proj_loss: -0.6085 (-0.6085) time: 1053.7237 data: 0.0007 [11-24 10:15:34] (/VAR/utils/lr_control.py, line 105)=> [11-24 10:15:34] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-24 10:15:36] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-24 10:15:36] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-24 10:15:37] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-24 10:15:37] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-24 10:33:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 0/1669] eta: 20 days, 9:07:09 tlr: 0.00019 tnm: 0.21 Lm: 6.482 (6.482) Lt: 5.779 (5.779) Accm: 3.54 (3.54) Acct: 5.37 (5.37) proj_loss: -0.6079 (-0.6079) time: 1055.0205 data: 0.0007 [11-24 10:15:34] (/VAR/utils/lr_control.py, line 105)=> [11-24 10:15:34] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-24 10:15:36] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-24 10:15:36] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-24 10:15:37] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-24 10:15:37] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-24 10:33:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 0/1669] eta: 20 days, 8:07:17 tlr: 0.00019 tnm: 0.21 Lm: 6.442 (6.442) Lt: 5.640 (5.640) Accm: 3.73 (3.73) Acct: 5.86 (5.86) proj_loss: -0.5949 (-0.5949) time: 1052.8686 data: 0.0006 [11-24 10:15:34] (/VAR/utils/lr_control.py, line 105)=> [11-24 10:15:34] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-24 10:15:37] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-24 10:15:37] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-24 10:15:37] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-24 10:15:37] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-24 10:33:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 0/1669] eta: 20 days, 8:37:23 tlr: 0.00019 tnm: 0.21 Lm: 6.497 (6.497) Lt: 5.731 (5.731) Accm: 3.65 (3.65) Acct: 5.55 (5.55) proj_loss: -0.5951 (-0.5951) time: 1053.9505 data: 0.0007 [11-24 10:48:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 417/1669] eta: 1:36:38 tlr: 0.00019 tnm: 0.22 Lm: 6.531 (6.531) Lt: 5.777 (5.777) Accm: 3.35 (3.35) Acct: 5.19 (5.19) proj_loss: -0.5968 (-0.5968) time: 0.9346 data: 0.0003 [11-24 10:48:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 417/1669] eta: 1:36:41 tlr: 0.00019 tnm: 0.22 Lm: 6.575 (6.575) Lt: 5.856 (5.856) Accm: 3.09 (3.09) Acct: 4.75 (4.75) proj_loss: -0.5928 (-0.5928) time: 0.9346 data: 0.0003 [11-24 10:48:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 417/1669] eta: 1:36:37 tlr: 0.00019 tnm: 0.22 Lm: 6.442 (6.442) Lt: 5.673 (5.673) Accm: 3.50 (3.50) Acct: 5.51 (5.51) proj_loss: -0.6213 (-0.6213) time: 0.9346 data: 0.0003 [11-24 10:48:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 417/1669] eta: 1:36:38 tlr: 0.00019 tnm: 0.22 Lm: 6.420 (6.420) Lt: 5.654 (5.654) Accm: 3.50 (3.50) Acct: 5.37 (5.37) proj_loss: -0.5979 (-0.5979) time: 0.9346 data: 0.0003 [11-24 10:48:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 417/1669] eta: 1:36:35 tlr: 0.00019 tnm: 0.22 Lm: 6.558 (6.558) Lt: 5.787 (5.787) Accm: 3.27 (3.27) Acct: 5.13 (5.13) proj_loss: -0.5905 (-0.5905) time: 0.9346 data: 0.0003 [11-24 10:48:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 417/1669] eta: 1:36:41 tlr: 0.00019 tnm: 0.22 Lm: 6.457 (6.457) Lt: 5.697 (5.697) Accm: 3.47 (3.47) Acct: 5.40 (5.40) proj_loss: -0.5942 (-0.5942) time: 0.9346 data: 0.0003 [11-24 10:54:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 834/1669] eta: 0:38:48 tlr: 0.00019 tnm: 0.22 Lm: 6.482 (6.526) Lt: 5.779 (5.797) Accm: 3.40 (3.29) Acct: 5.37 (5.19) proj_loss: -0.5992 (-0.5959) time: 0.9399 data: 0.0003 [11-24 10:54:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 834/1669] eta: 0:38:47 tlr: 0.00019 tnm: 0.22 Lm: 6.497 (6.483) Lt: 5.731 (5.722) Accm: 3.65 (3.57) Acct: 5.55 (5.56) proj_loss: -0.5985 (-0.6000) time: 0.9399 data: 0.0003 [11-24 10:54:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 834/1669] eta: 0:38:46 tlr: 0.00019 tnm: 0.22 Lm: 6.673 (6.597) Lt: 5.892 (5.822) Accm: 2.98 (3.18) Acct: 4.80 (5.02) proj_loss: -0.5861 (-0.5864) time: 0.9399 data: 0.0003 [11-24 10:54:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 834/1669] eta: 0:38:48 tlr: 0.00019 tnm: 0.22 Lm: 6.513 (6.467) Lt: 5.795 (5.713) Accm: 3.17 (3.43) Acct: 4.96 (5.28) proj_loss: -0.5968 (-0.5942) time: 0.9399 data: 0.0003 [11-24 10:54:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 834/1669] eta: 0:38:47 tlr: 0.00019 tnm: 0.22 Lm: 6.437 (6.413) Lt: 5.665 (5.654) Accm: 3.51 (3.52) Acct: 5.58 (5.54) proj_loss: -0.6085 (-0.6130) time: 0.9399 data: 0.0003 [11-24 10:54:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [ 834/1669] eta: 0:38:47 tlr: 0.00019 tnm: 0.22 Lm: 6.404 (6.415) Lt: 5.606 (5.638) Accm: 3.34 (3.45) Acct: 5.68 (5.48) proj_loss: -0.5905 (-0.5954) time: 0.9399 data: 0.0003 [11-24 11:01:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1251/1669] eta: 0:15:07 tlr: 0.00019 tnm: 0.21 Lm: 6.430 (6.425) Lt: 5.657 (5.655) Accm: 3.42 (3.46) Acct: 5.57 (5.47) proj_loss: -0.5901 (-0.5940) time: 0.9390 data: 0.0003 [11-24 11:01:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1251/1669] eta: 0:15:07 tlr: 0.00019 tnm: 0.21 Lm: 6.512 (6.494) Lt: 5.705 (5.711) Accm: 3.45 (3.49) Acct: 5.50 (5.53) proj_loss: -0.5968 (-0.5887) time: 0.9390 data: 0.0003 [11-24 11:01:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1251/1669] eta: 0:15:07 tlr: 0.00019 tnm: 0.21 Lm: 6.397 (6.381) Lt: 5.640 (5.618) Accm: 3.54 (3.63) Acct: 5.58 (5.69) proj_loss: -0.6025 (-0.6071) time: 0.9390 data: 0.0003 [11-24 11:01:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1251/1669] eta: 0:15:08 tlr: 0.00019 tnm: 0.21 Lm: 6.564 (6.556) Lt: 5.841 (5.824) Accm: 3.17 (3.19) Acct: 5.07 (5.00) proj_loss: -0.5981 (-0.5961) time: 0.9390 data: 0.0003 [11-24 11:01:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1251/1669] eta: 0:15:07 tlr: 0.00019 tnm: 0.21 Lm: 6.598 (6.578) Lt: 5.824 (5.806) Accm: 3.11 (3.19) Acct: 4.93 (5.03) proj_loss: -0.5903 (-0.5885) time: 0.9390 data: 0.0002 [11-24 11:01:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1251/1669] eta: 0:15:08 tlr: 0.00019 tnm: 0.21 Lm: 6.528 (6.486) Lt: 5.782 (5.727) Accm: 3.12 (3.34) Acct: 5.07 (5.26) proj_loss: -0.5890 (-0.5909) time: 0.9390 data: 0.0003 [11-24 11:07:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1668/1669] eta: 0:00:01 tlr: 0.00019 tnm: 0.22 Lm: 6.542 (6.521) Lt: 5.795 (5.752) Accm: 3.08 (3.25) Acct: 4.96 (5.19) proj_loss: -0.5813 (-0.5877) time: 0.9429 data: 0.0016 [11-24 11:07:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 90/350] Total time: 0:51:51 (1.864 s / it) [11-24 11:07:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1668/1669] eta: 0:00:01 tlr: 0.00019 tnm: 0.22 Lm: 6.437 (6.405) Lt: 5.665 (5.655) Accm: 3.51 (3.59) Acct: 5.58 (5.56) proj_loss: -0.6006 (-0.6058) time: 0.9429 data: 0.0020 [11-24 11:07:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1668/1669] eta: 0:00:01 tlr: 0.00019 tnm: 0.22 Lm: 6.497 (6.448) Lt: 5.679 (5.672) Accm: 3.65 (3.62) Acct: 5.55 (5.66) proj_loss: -0.5985 (-0.5962) time: 0.9429 data: 0.0018 [11-24 11:07:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1668/1669] eta: 0:00:01 tlr: 0.00019 tnm: 0.22 Lm: 6.482 (6.527) Lt: 5.779 (5.804) Accm: 3.40 (3.30) Acct: 5.37 (5.19) proj_loss: -0.5992 (-0.6000) time: 0.9429 data: 0.0016 [11-24 11:07:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1668/1669] eta: 0:00:01 tlr: 0.00019 tnm: 0.22 Lm: 6.456 (6.485) Lt: 5.707 (5.729) Accm: 3.34 (3.31) Acct: 5.45 (5.22) proj_loss: -0.5905 (-0.5948) time: 0.9429 data: 0.0018 [11-24 11:07:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 90/350] [1668/1669] eta: 0:00:01 tlr: 0.00019 tnm: 0.22 Lm: 6.522 (6.542) Lt: 5.757 (5.763) Accm: 3.25 (3.29) Acct: 5.06 (5.21) proj_loss: -0.5861 (-0.5864) time: 0.9429 data: 0.0017 [11-24 11:07:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 90/350] Total time: 0:51:50 (1.864 s / it) [11-24 11:07:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 90/350] Total time: 0:51:50 (1.864 s / it) [11-24 11:07:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 90/350] Total time: 0:51:51 (1.864 s / it) [11-24 11:07:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 90/350] Total time: 0:51:50 (1.864 s / it) [11-24 11:07:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 90/350] Total time: 0:51:49 (1.863 s / it) [11-24 11:07:37] (/home/user/VAR/train.py , line 276)=> [ep90] (training ) Lm: 6.527 (6.527), Lt: 5.775 (5.775), Acc m&t: 3.31 5.21, Remain: 4 days, 18:04:06, Finish: 2024-11-28 13:11 [11-24 11:07:37] (/home/user/VAR/train.py , line 276)=> [ep90] (training ) Lm: 6.527 (6.527), Lt: 5.775 (5.775), Acc m&t: 3.31 5.21, Remain: 4 days, 18:07:57, Finish: 2024-11-28 13:15 [11-24 11:07:37] (/home/user/VAR/train.py , line 276)=> [ep90] (training ) Lm: 6.527 (6.527), Lt: 5.775 (5.775), Acc m&t: 3.31 5.21, Remain: 4 days, 18:06:48, Finish: 2024-11-28 13:14 [11-24 11:07:37] (/home/user/VAR/train.py , line 276)=> [ep90] (training ) Lm: 6.527 (6.527), Lt: 5.775 (5.775), Acc m&t: 3.31 5.21, Remain: 4 days, 18:09:25, Finish: 2024-11-28 13:17 [11-24 11:07:37] (/home/user/VAR/train.py , line 276)=> [ep90] (training ) Lm: 6.527 (6.527), Lt: 5.775 (5.775), Acc m&t: 3.31 5.21, Remain: 4 days, 18:07:57, Finish: 2024-11-28 13:15 [11-24 11:07:37] (/home/user/VAR/train.py , line 276)=> [ep90] (training ) Lm: 6.527 (6.527), Lt: 5.775 (5.775), Acc m&t: 3.31 5.21, Remain: 4 days, 18:06:27, Finish: 2024-11-28 13:14 [11-24 11:07:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 0/1669] eta: 0:25:36 tlr: 0.00019 tnm: 0.23 Lm: 6.299 (6.299) Lt: 5.554 (5.554) Accm: 4.00 (4.00) Acct: 6.04 (6.04) proj_loss: -0.5903 (-0.5903) time: 0.9207 data: 0.0003 [11-24 11:07:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 0/1669] eta: 0:25:35 tlr: 0.00019 tnm: 0.23 Lm: 6.543 (6.543) Lt: 5.869 (5.869) Accm: 3.07 (3.07) Acct: 4.57 (4.57) proj_loss: -0.5889 (-0.5889) time: 0.9201 data: 0.0005 [11-24 11:07:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 0/1669] eta: 0:25:38 tlr: 0.00019 tnm: 0.23 Lm: 6.466 (6.466) Lt: 5.678 (5.678) Accm: 3.58 (3.58) Acct: 5.32 (5.32) proj_loss: -0.6094 (-0.6094) time: 0.9215 data: 0.0003 [11-24 11:07:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 0/1669] eta: 0:26:11 tlr: 0.00019 tnm: 0.23 Lm: 6.442 (6.442) Lt: 5.709 (5.709) Accm: 3.45 (3.45) Acct: 5.79 (5.79) proj_loss: -0.6023 (-0.6023) time: 0.9417 data: 0.0004 [11-24 11:07:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 0/1669] eta: 0:26:13 tlr: 0.00019 tnm: 0.23 Lm: 6.523 (6.523) Lt: 5.773 (5.773) Accm: 3.05 (3.05) Acct: 4.75 (4.75) proj_loss: -0.5932 (-0.5932) time: 0.9425 data: 0.0004 [11-24 11:07:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 0/1669] eta: 0:26:12 tlr: 0.00019 tnm: 0.23 Lm: 6.409 (6.409) Lt: 5.673 (5.673) Accm: 3.55 (3.55) Acct: 5.35 (5.35) proj_loss: -0.6195 (-0.6195) time: 0.9421 data: 0.0004 [11-24 11:14:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 417/1669] eta: 0:19:51 tlr: 0.00019 tnm: 0.23 Lm: 6.525 (6.525) Lt: 5.786 (5.786) Accm: 3.23 (3.23) Acct: 5.02 (5.02) proj_loss: -0.6012 (-0.6012) time: 0.9354 data: 0.0003 [11-24 11:14:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 417/1669] eta: 0:19:51 tlr: 0.00019 tnm: 0.23 Lm: 6.343 (6.343) Lt: 5.596 (5.596) Accm: 3.85 (3.85) Acct: 5.77 (5.77) proj_loss: -0.6043 (-0.6043) time: 0.9354 data: 0.0003 [11-24 11:14:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 417/1669] eta: 0:19:51 tlr: 0.00019 tnm: 0.23 Lm: 6.540 (6.540) Lt: 5.808 (5.808) Accm: 3.12 (3.12) Acct: 4.80 (4.80) proj_loss: -0.5899 (-0.5899) time: 0.9354 data: 0.0003 [11-24 11:14:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 417/1669] eta: 0:19:51 tlr: 0.00019 tnm: 0.23 Lm: 6.466 (6.466) Lt: 5.736 (5.736) Accm: 3.45 (3.45) Acct: 5.60 (5.60) proj_loss: -0.6133 (-0.6133) time: 0.9354 data: 0.0003 [11-24 11:14:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 417/1669] eta: 0:19:51 tlr: 0.00019 tnm: 0.23 Lm: 6.444 (6.444) Lt: 5.694 (5.694) Accm: 3.33 (3.33) Acct: 5.13 (5.13) proj_loss: -0.5958 (-0.5958) time: 0.9354 data: 0.0003 [11-24 11:14:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 417/1669] eta: 0:19:51 tlr: 0.00019 tnm: 0.23 Lm: 6.457 (6.457) Lt: 5.681 (5.681) Accm: 3.57 (3.57) Acct: 5.40 (5.40) proj_loss: -0.6030 (-0.6030) time: 0.9355 data: 0.0003 [11-24 11:20:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 834/1669] eta: 0:13:09 tlr: 0.00019 tnm: 0.21 Lm: 6.448 (6.409) Lt: 5.678 (5.630) Accm: 3.58 (3.80) Acct: 5.48 (5.80) proj_loss: -0.6003 (-0.6021) time: 0.9426 data: 0.0003 [11-24 11:20:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 834/1669] eta: 0:13:09 tlr: 0.00019 tnm: 0.21 Lm: 6.387 (6.405) Lt: 5.637 (5.636) Accm: 3.69 (3.56) Acct: 5.50 (5.49) proj_loss: -0.5917 (-0.6001) time: 0.9426 data: 0.0003 [11-24 11:20:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 834/1669] eta: 0:13:09 tlr: 0.00019 tnm: 0.21 Lm: 6.543 (6.594) Lt: 5.869 (5.841) Accm: 3.07 (2.99) Acct: 4.57 (4.67) proj_loss: -0.5889 (-0.5882) time: 0.9426 data: 0.0003 [11-24 11:20:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 834/1669] eta: 0:13:09 tlr: 0.00019 tnm: 0.21 Lm: 6.455 (6.448) Lt: 5.678 (5.689) Accm: 3.42 (3.36) Acct: 5.50 (5.26) proj_loss: -0.5958 (-0.5958) time: 0.9426 data: 0.0003 [11-24 11:20:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 834/1669] eta: 0:13:09 tlr: 0.00019 tnm: 0.21 Lm: 6.641 (6.589) Lt: 5.899 (5.860) Accm: 2.92 (3.07) Acct: 4.70 (4.89) proj_loss: -0.6066 (-0.6030) time: 0.9426 data: 0.0003 [11-24 11:20:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [ 834/1669] eta: 0:13:09 tlr: 0.00019 tnm: 0.21 Lm: 6.490 (6.476) Lt: 5.709 (5.726) Accm: 3.44 (3.43) Acct: 5.53 (5.58) proj_loss: -0.6023 (-0.5998) time: 0.9426 data: 0.0003 [11-24 11:27:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1251/1669] eta: 0:06:34 tlr: 0.00019 tnm: 0.21 Lm: 6.493 (6.482) Lt: 5.707 (5.716) Accm: 3.44 (3.43) Acct: 5.48 (5.49) proj_loss: -0.5875 (-0.5921) time: 0.9371 data: 0.0002 [11-24 11:27:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1251/1669] eta: 0:06:34 tlr: 0.00019 tnm: 0.21 Lm: 6.457 (6.486) Lt: 5.681 (5.729) Accm: 3.57 (3.61) Acct: 5.40 (5.46) proj_loss: -0.5984 (-0.5996) time: 0.9371 data: 0.0002 [11-24 11:27:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1251/1669] eta: 0:06:34 tlr: 0.00019 tnm: 0.21 Lm: 6.343 (6.378) Lt: 5.596 (5.597) Accm: 3.85 (3.70) Acct: 5.77 (5.73) proj_loss: -0.5973 (-0.6008) time: 0.9371 data: 0.0003 [11-24 11:27:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1251/1669] eta: 0:06:34 tlr: 0.00019 tnm: 0.21 Lm: 6.540 (6.568) Lt: 5.811 (5.819) Accm: 3.12 (3.11) Acct: 4.80 (4.95) proj_loss: -0.5899 (-0.5903) time: 0.9371 data: 0.0003 [11-24 11:27:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1251/1669] eta: 0:06:34 tlr: 0.00019 tnm: 0.21 Lm: 6.580 (6.571) Lt: 5.845 (5.842) Accm: 3.05 (3.10) Acct: 4.78 (4.88) proj_loss: -0.6130 (-0.6109) time: 0.9371 data: 0.0003 [11-24 11:27:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1251/1669] eta: 0:06:34 tlr: 0.00019 tnm: 0.21 Lm: 6.428 (6.436) Lt: 5.678 (5.686) Accm: 3.51 (3.42) Acct: 5.51 (5.40) proj_loss: -0.5945 (-0.5951) time: 0.9371 data: 0.0003 [11-24 11:33:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.455 (6.457) Lt: 5.679 (5.694) Accm: 3.42 (3.40) Acct: 5.50 (5.41) proj_loss: -0.5932 (-0.5924) time: 0.9412 data: 0.0019 [11-24 11:33:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 91/350] Total time: 0:26:12 (0.942 s / it) [11-24 11:33:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.346 (6.372) Lt: 5.579 (5.593) Accm: 3.69 (3.67) Acct: 5.50 (5.66) proj_loss: -0.5917 (-0.5979) time: 0.9411 data: 0.0015 [11-24 11:33:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.466 (6.491) Lt: 5.685 (5.740) Accm: 3.58 (3.61) Acct: 5.45 (5.46) proj_loss: -0.6003 (-0.6007) time: 0.9412 data: 0.0020 [11-24 11:33:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.621 (6.581) Lt: 5.868 (5.847) Accm: 3.03 (3.09) Acct: 4.80 (4.87) proj_loss: -0.6066 (-0.6009) time: 0.9412 data: 0.0018 [11-24 11:33:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.495 (6.490) Lt: 5.709 (5.720) Accm: 3.43 (3.35) Acct: 5.42 (5.36) proj_loss: -0.6023 (-0.5952) time: 0.9412 data: 0.0017 [11-24 11:33:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 91/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.21 Lm: 6.538 (6.548) Lt: 5.754 (5.800) Accm: 3.17 (3.16) Acct: 5.04 (4.99) proj_loss: -0.5909 (-0.5927) time: 0.9412 data: 0.0019 [11-24 11:33:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 91/350] Total time: 0:26:12 (0.942 s / it) [11-24 11:33:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 91/350] Total time: 0:26:12 (0.942 s / it) [11-24 11:33:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 91/350] Total time: 0:26:12 (0.942 s / it) [11-24 11:33:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 91/350] Total time: 0:26:12 (0.942 s / it) [11-24 11:33:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 91/350] Total time: 0:26:12 (0.942 s / it) [11-24 11:33:50] (/home/user/VAR/train.py , line 276)=> [ep91] (training ) Lm: 6.504 (6.504), Lt: 5.750 (5.750), Acc m&t: 3.35 5.27, Remain: 4 days, 17:28:19, Finish: 2024-11-28 13:02 [11-24 11:33:50] (/home/user/VAR/train.py , line 276)=> [ep91] (training ) Lm: 6.504 (6.504), Lt: 5.750 (5.750), Acc m&t: 3.35 5.27, Remain: 4 days, 17:27:56, Finish: 2024-11-28 13:01 [11-24 11:33:50] (/home/user/VAR/train.py , line 276)=> [ep91] (training ) Lm: 6.504 (6.504), Lt: 5.750 (5.750), Acc m&t: 3.35 5.27, Remain: 4 days, 17:28:20, Finish: 2024-11-28 13:02 [11-24 11:33:50] (/home/user/VAR/train.py , line 276)=> [ep91] (training ) Lm: 6.504 (6.504), Lt: 5.750 (5.750), Acc m&t: 3.35 5.27, Remain: 4 days, 17:28:14, Finish: 2024-11-28 13:02 [11-24 11:33:50] (/home/user/VAR/train.py , line 276)=> [ep91] (training ) Lm: 6.504 (6.504), Lt: 5.750 (5.750), Acc m&t: 3.35 5.27, Remain: 4 days, 17:29:02, Finish: 2024-11-28 13:02 [11-24 11:33:50] (/home/user/VAR/train.py , line 276)=> [ep91] (training ) Lm: 6.504 (6.504), Lt: 5.750 (5.750), Acc m&t: 3.35 5.27, Remain: 4 days, 17:27:46, Finish: 2024-11-28 13:01 [11-24 11:33:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 0/1669] eta: 0:25:13 tlr: 0.00019 tnm: 0.22 Lm: 6.443 (6.443) Lt: 5.669 (5.669) Accm: 3.58 (3.58) Acct: 5.81 (5.81) proj_loss: -0.6111 (-0.6111) time: 0.9070 data: 0.0003 [11-24 11:33:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 0/1669] eta: 0:25:15 tlr: 0.00019 tnm: 0.22 Lm: 6.284 (6.284) Lt: 5.393 (5.393) Accm: 4.00 (4.00) Acct: 6.92 (6.92) proj_loss: -0.5913 (-0.5913) time: 0.9079 data: 0.0003 [11-24 11:33:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 0/1669] eta: 0:25:15 tlr: 0.00019 tnm: 0.22 Lm: 6.561 (6.561) Lt: 5.825 (5.825) Accm: 3.03 (3.03) Acct: 4.65 (4.65) proj_loss: -0.6000 (-0.6000) time: 0.9079 data: 0.0003 [11-24 11:33:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 0/1669] eta: 0:25:16 tlr: 0.00019 tnm: 0.22 Lm: 6.657 (6.657) Lt: 5.917 (5.917) Accm: 3.09 (3.09) Acct: 5.01 (5.01) proj_loss: -0.6015 (-0.6015) time: 0.9084 data: 0.0004 [11-24 11:33:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 0/1669] eta: 0:25:16 tlr: 0.00019 tnm: 0.22 Lm: 6.517 (6.517) Lt: 5.712 (5.712) Accm: 3.23 (3.23) Acct: 5.06 (5.06) proj_loss: -0.6067 (-0.6067) time: 0.9088 data: 0.0004 [11-24 11:33:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 0/1669] eta: 0:25:16 tlr: 0.00019 tnm: 0.22 Lm: 6.540 (6.540) Lt: 5.818 (5.818) Accm: 3.42 (3.42) Acct: 5.35 (5.35) proj_loss: -0.6209 (-0.6209) time: 0.9088 data: 0.0004 [11-24 11:40:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 417/1669] eta: 0:19:34 tlr: 0.00019 tnm: 0.22 Lm: 6.567 (6.567) Lt: 5.839 (5.839) Accm: 3.32 (3.32) Acct: 5.09 (5.09) proj_loss: -0.6172 (-0.6172) time: 0.9364 data: 0.0003 [11-24 11:40:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 417/1669] eta: 0:19:34 tlr: 0.00019 tnm: 0.22 Lm: 6.658 (6.658) Lt: 5.899 (5.899) Accm: 2.99 (2.99) Acct: 4.91 (4.91) proj_loss: -0.6004 (-0.6004) time: 0.9363 data: 0.0002 [11-24 11:40:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 417/1669] eta: 0:19:34 tlr: 0.00019 tnm: 0.22 Lm: 6.600 (6.600) Lt: 5.870 (5.870) Accm: 3.09 (3.09) Acct: 4.73 (4.73) proj_loss: -0.6019 (-0.6019) time: 0.9363 data: 0.0003 [11-24 11:40:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 417/1669] eta: 0:19:34 tlr: 0.00019 tnm: 0.22 Lm: 6.394 (6.394) Lt: 5.558 (5.558) Accm: 3.51 (3.51) Acct: 5.85 (5.85) proj_loss: -0.5858 (-0.5858) time: 0.9363 data: 0.0003 [11-24 11:40:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 417/1669] eta: 0:19:34 tlr: 0.00019 tnm: 0.22 Lm: 6.404 (6.404) Lt: 5.613 (5.613) Accm: 3.61 (3.61) Acct: 5.81 (5.81) proj_loss: -0.6182 (-0.6182) time: 0.9363 data: 0.0002 [11-24 11:40:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 417/1669] eta: 0:19:34 tlr: 0.00019 tnm: 0.22 Lm: 6.641 (6.641) Lt: 5.902 (5.902) Accm: 2.95 (2.95) Acct: 4.56 (4.56) proj_loss: -0.6157 (-0.6157) time: 0.9364 data: 0.0003 [11-24 11:46:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 834/1669] eta: 0:13:04 tlr: 0.00019 tnm: 0.21 Lm: 6.517 (6.555) Lt: 5.712 (5.800) Accm: 3.23 (3.06) Acct: 4.83 (4.65) proj_loss: -0.6067 (-0.6126) time: 0.9390 data: 0.0003 [11-24 11:46:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 834/1669] eta: 0:13:04 tlr: 0.00019 tnm: 0.21 Lm: 6.443 (6.476) Lt: 5.669 (5.705) Accm: 3.58 (3.51) Acct: 5.81 (5.61) proj_loss: -0.6111 (-0.6053) time: 0.9390 data: 0.0002 [11-24 11:46:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 834/1669] eta: 0:13:04 tlr: 0.00019 tnm: 0.21 Lm: 6.561 (6.554) Lt: 5.825 (5.779) Accm: 3.15 (3.30) Acct: 4.80 (5.14) proj_loss: -0.6037 (-0.6076) time: 0.9390 data: 0.0003 [11-24 11:46:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 834/1669] eta: 0:13:04 tlr: 0.00019 tnm: 0.21 Lm: 6.658 (6.679) Lt: 5.917 (5.944) Accm: 2.90 (2.94) Acct: 4.80 (4.67) proj_loss: -0.6015 (-0.6017) time: 0.9390 data: 0.0002 [11-24 11:46:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 834/1669] eta: 0:13:04 tlr: 0.00019 tnm: 0.21 Lm: 6.594 (6.591) Lt: 5.859 (5.863) Accm: 3.22 (3.26) Acct: 5.04 (5.07) proj_loss: -0.6134 (-0.6139) time: 0.9390 data: 0.0003 [11-24 11:46:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [ 834/1669] eta: 0:13:04 tlr: 0.00019 tnm: 0.21 Lm: 6.489 (6.425) Lt: 5.723 (5.618) Accm: 3.12 (3.38) Acct: 5.06 (5.59) proj_loss: -0.5913 (-0.5939) time: 0.9390 data: 0.0003 [11-24 11:53:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [1251/1669] eta: 0:06:35 tlr: 0.00019 tnm: 0.21 Lm: 6.496 (6.472) Lt: 5.731 (5.662) Accm: 3.08 (3.26) Acct: 4.92 (5.31) proj_loss: -0.5977 (-0.5964) time: 0.9396 data: 0.0003 [11-24 11:53:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [1251/1669] eta: 0:06:35 tlr: 0.00019 tnm: 0.21 Lm: 6.404 (6.446) Lt: 5.613 (5.659) Accm: 3.61 (3.59) Acct: 5.81 (5.75) proj_loss: -0.6000 (-0.6012) time: 0.9396 data: 0.0002 [11-24 11:53:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [1251/1669] eta: 0:06:35 tlr: 0.00019 tnm: 0.21 Lm: 6.660 (6.675) Lt: 5.920 (5.939) Accm: 2.87 (2.92) Acct: 4.79 (4.69) proj_loss: -0.6030 (-0.6029) time: 0.9396 data: 0.0002 [11-24 11:53:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [1251/1669] eta: 0:06:35 tlr: 0.00019 tnm: 0.21 Lm: 6.589 (6.589) Lt: 5.847 (5.856) Accm: 3.24 (3.26) Acct: 5.04 (5.06) proj_loss: -0.6103 (-0.6101) time: 0.9396 data: 0.0002 [11-24 11:53:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [1251/1669] eta: 0:06:35 tlr: 0.00019 tnm: 0.21 Lm: 6.600 (6.589) Lt: 5.870 (5.833) Accm: 3.09 (3.20) Acct: 4.73 (4.97) proj_loss: -0.6019 (-0.6019) time: 0.9396 data: 0.0002 [11-24 11:53:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [1251/1669] eta: 0:06:35 tlr: 0.00019 tnm: 0.21 Lm: 6.631 (6.602) Lt: 5.876 (5.860) Accm: 2.95 (2.94) Acct: 4.44 (4.49) proj_loss: -0.6066 (-0.6023) time: 0.9396 data: 0.0003 [11-24 12:00:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.717 (6.625) Lt: 5.989 (5.886) Accm: 3.03 (2.95) Acct: 4.80 (4.55) proj_loss: -0.6065 (-0.6017) time: 0.9436 data: 0.0020 [11-24 12:00:05] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 92/350] Total time: 0:26:15 (0.944 s / it) [11-24 12:00:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.443 (6.460) Lt: 5.669 (5.685) Accm: 3.58 (3.51) Acct: 5.81 (5.65) proj_loss: -0.5928 (-0.5995) time: 0.9436 data: 0.0016 [11-24 12:00:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.503 (6.502) Lt: 5.738 (5.706) Accm: 3.12 (3.24) Acct: 5.06 (5.28) proj_loss: -0.5913 (-0.5938) time: 0.9436 data: 0.0016 [11-24 12:00:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.658 (6.627) Lt: 5.917 (5.893) Accm: 2.90 (3.09) Acct: 4.80 (4.98) proj_loss: -0.6044 (-0.6043) time: 0.9436 data: 0.0016 [11-24 12:00:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.591 (6.589) Lt: 5.857 (5.838) Accm: 3.03 (3.11) Acct: 4.65 (4.90) proj_loss: -0.6037 (-0.6037) time: 0.9436 data: 0.0017 [11-24 12:00:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 92/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.584 (6.561) Lt: 5.834 (5.830) Accm: 3.22 (3.25) Acct: 5.04 (5.04) proj_loss: -0.6132 (-0.6107) time: 0.9436 data: 0.0018 [11-24 12:00:05] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 92/350] Total time: 0:26:15 (0.944 s / it) [11-24 12:00:05] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 92/350] Total time: 0:26:15 (0.944 s / it) [11-24 12:00:05] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 92/350] Total time: 0:26:15 (0.944 s / it) [11-24 12:00:05] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 92/350] Total time: 0:26:15 (0.944 s / it) [11-24 12:00:05] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 92/350] Total time: 0:26:15 (0.944 s / it) [11-24 12:00:05] (/home/user/VAR/train.py , line 276)=> [ep92] (training ) Lm: 6.504 (6.522), Lt: 5.750 (5.769), Acc m&t: 3.35 5.27, Remain: 4 days, 17:26:47, Finish: 2024-11-28 13:26 [11-24 12:00:05] (/home/user/VAR/train.py , line 276)=> [ep92] (training ) Lm: 6.504 (6.522), Lt: 5.750 (5.769), Acc m&t: 3.35 5.27, Remain: 4 days, 17:28:50, Finish: 2024-11-28 13:28 [11-24 12:00:05] (/home/user/VAR/train.py , line 276)=> [ep92] (training ) Lm: 6.504 (6.522), Lt: 5.750 (5.769), Acc m&t: 3.35 5.27, Remain: 4 days, 17:28:46, Finish: 2024-11-28 13:28 [11-24 12:00:05] (/home/user/VAR/train.py , line 276)=> [ep92] (training ) Lm: 6.504 (6.522), Lt: 5.750 (5.769), Acc m&t: 3.35 5.27, Remain: 4 days, 17:27:19, Finish: 2024-11-28 13:27 [11-24 12:00:05] (/home/user/VAR/train.py , line 276)=> [ep92] (training ) Lm: 6.504 (6.522), Lt: 5.750 (5.769), Acc m&t: 3.35 5.27, Remain: 4 days, 17:26:51, Finish: 2024-11-28 13:26 [11-24 12:00:05] (/home/user/VAR/train.py , line 276)=> [ep92] (training ) Lm: 6.504 (6.522), Lt: 5.750 (5.769), Acc m&t: 3.35 5.27, Remain: 4 days, 17:27:44, Finish: 2024-11-28 13:27 [11-24 12:00:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [ 0/1669] eta: 0:25:07 tlr: 0.00019 tnm: 0.22 Lm: 6.447 (6.447) Lt: 5.732 (5.732) Accm: 3.10 (3.10) Acct: 4.39 (4.39) proj_loss: -0.6250 (-0.6250) time: 0.9034 data: 0.0003 [11-24 12:00:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [ 0/1669] eta: 0:25:19 tlr: 0.00019 tnm: 0.22 Lm: 6.528 (6.528) Lt: 5.654 (5.654) Accm: 3.39 (3.39) Acct: 5.71 (5.71) proj_loss: -0.5850 (-0.5850) time: 0.9103 data: 0.0004 [11-24 12:00:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [ 0/1669] eta: 0:25:09 tlr: 0.00019 tnm: 0.22 Lm: 6.478 (6.478) Lt: 5.788 (5.788) Accm: 3.52 (3.52) Acct: 5.63 (5.63) proj_loss: -0.6161 (-0.6161) time: 0.9043 data: 0.0004 [11-24 12:00:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [ 0/1669] eta: 0:25:18 tlr: 0.00019 tnm: 0.22 Lm: 6.404 (6.404) Lt: 5.530 (5.530) Accm: 3.88 (3.88) Acct: 6.10 (6.10) proj_loss: -0.5604 (-0.5604) time: 0.9098 data: 0.0004 [11-24 12:00:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [ 0/1669] eta: 0:25:20 tlr: 0.00019 tnm: 0.22 Lm: 6.799 (6.799) Lt: 6.098 (6.098) Accm: 2.49 (2.49) Acct: 3.98 (3.98) proj_loss: -0.5913 (-0.5913) time: 0.9110 data: 0.0003 [11-24 12:00:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [ 0/1669] eta: 0:25:09 tlr: 0.00019 tnm: 0.22 Lm: 6.857 (6.857) Lt: 6.246 (6.246) Accm: 2.40 (2.40) Acct: 3.82 (3.82) proj_loss: -0.6134 (-0.6134) time: 0.9045 data: 0.0004 [11-24 12:06:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.640 (6.640) Lt: 5.967 (5.967) Accm: 2.93 (2.93) Acct: 4.65 (4.65) proj_loss: -0.6039 (-0.6039) time: 0.9412 data: 0.0003 [11-24 12:06:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.418 (6.418) Lt: 5.657 (5.657) Accm: 3.76 (3.76) Acct: 6.12 (6.12) proj_loss: -0.6021 (-0.6021) time: 0.9411 data: 0.0003 [11-24 12:06:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.458 (6.458) Lt: 5.675 (5.675) Accm: 3.47 (3.47) Acct: 5.26 (5.26) proj_loss: -0.5989 (-0.5989) time: 0.9411 data: 0.0003 [11-24 12:06:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.475 (6.475) Lt: 5.678 (5.678) Accm: 3.40 (3.40) Acct: 5.36 (5.36) proj_loss: -0.5950 (-0.5950) time: 0.9412 data: 0.0003 [11-24 12:06:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.547 (6.547) Lt: 5.739 (5.739) Accm: 3.44 (3.44) Acct: 5.36 (5.36) proj_loss: -0.5851 (-0.5851) time: 0.9412 data: 0.0003 [11-24 12:06:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.706 (6.706) Lt: 5.968 (5.968) Accm: 2.77 (2.77) Acct: 4.43 (4.43) proj_loss: -0.5921 (-0.5921) time: 0.9412 data: 0.0003 [11-24 12:13:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.21 Lm: 6.613 (6.671) Lt: 5.837 (5.922) Accm: 2.64 (2.73) Acct: 4.21 (4.36) proj_loss: -0.5913 (-0.5909) time: 0.9412 data: 0.0002 [11-24 12:13:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.21 Lm: 6.644 (6.642) Lt: 5.943 (5.959) Accm: 2.98 (2.95) Acct: 4.73 (4.67) proj_loss: -0.6077 (-0.6052) time: 0.9412 data: 0.0002 [11-24 12:13:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.21 Lm: 6.510 (6.487) Lt: 5.701 (5.694) Accm: 3.42 (3.55) Acct: 5.71 (5.66) proj_loss: -0.6051 (-0.5992) time: 0.9412 data: 0.0003 [11-24 12:13:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.21 Lm: 6.478 (6.480) Lt: 5.784 (5.699) Accm: 3.52 (3.47) Acct: 5.63 (5.65) proj_loss: -0.5970 (-0.6004) time: 0.9412 data: 0.0003 [11-24 12:13:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.21 Lm: 6.447 (6.446) Lt: 5.638 (5.663) Accm: 3.65 (3.53) Acct: 5.53 (5.35) proj_loss: -0.5917 (-0.5965) time: 0.9412 data: 0.0002 [11-24 12:13:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.21 Lm: 6.547 (6.547) Lt: 5.750 (5.743) Accm: 3.38 (3.42) Acct: 5.32 (5.35) proj_loss: -0.6018 (-0.5906) time: 0.9412 data: 0.0003 [11-24 12:19:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [1251/1669] eta: 0:06:34 tlr: 0.00019 tnm: 0.21 Lm: 6.500 (6.523) Lt: 5.762 (5.751) Accm: 3.58 (3.51) Acct: 5.50 (5.43) proj_loss: -0.6058 (-0.6002) time: 1.0014 data: 0.0003 [11-24 12:19:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [1251/1669] eta: 0:06:34 tlr: 0.00019 tnm: 0.21 Lm: 6.458 (6.472) Lt: 5.685 (5.714) Accm: 3.38 (3.39) Acct: 5.17 (5.21) proj_loss: -0.5950 (-0.5970) time: 1.0014 data: 0.0002 [11-24 12:19:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [1251/1669] eta: 0:06:34 tlr: 0.00019 tnm: 0.21 Lm: 6.519 (6.560) Lt: 5.714 (5.773) Accm: 3.40 (3.30) Acct: 5.36 (5.24) proj_loss: -0.5950 (-0.5934) time: 1.0014 data: 0.0003 [11-24 12:19:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [1251/1669] eta: 0:06:34 tlr: 0.00019 tnm: 0.21 Lm: 6.540 (6.510) Lt: 5.786 (5.749) Accm: 3.27 (3.36) Acct: 5.27 (5.46) proj_loss: -0.6034 (-0.6027) time: 1.0014 data: 0.0003 [11-24 12:19:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [1251/1669] eta: 0:06:34 tlr: 0.00019 tnm: 0.21 Lm: 6.607 (6.637) Lt: 5.834 (5.876) Accm: 2.85 (2.86) Acct: 4.55 (4.54) proj_loss: -0.5898 (-0.5897) time: 1.0014 data: 0.0003 [11-24 12:19:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [1251/1669] eta: 0:06:34 tlr: 0.00019 tnm: 0.21 Lm: 6.549 (6.595) Lt: 5.824 (5.896) Accm: 3.08 (3.00) Acct: 4.97 (4.81) proj_loss: -0.6011 (-0.5923) time: 1.0014 data: 0.0002 [11-24 12:26:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.544 (6.585) Lt: 5.780 (5.872) Accm: 3.17 (3.08) Acct: 5.22 (4.94) proj_loss: -0.5944 (-0.5832) time: 0.9440 data: 0.0016 [11-24 12:26:28] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 93/350] Total time: 0:26:22 (0.948 s / it) [11-24 12:26:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.447 (6.444) Lt: 5.638 (5.684) Accm: 3.61 (3.43) Acct: 5.53 (5.30) proj_loss: -0.5983 (-0.6026) time: 0.9440 data: 0.0021 [11-24 12:26:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.510 (6.523) Lt: 5.701 (5.735) Accm: 3.42 (3.40) Acct: 5.71 (5.46) proj_loss: -0.5946 (-0.5936) time: 0.9440 data: 0.0015 [11-24 12:26:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.547 (6.535) Lt: 5.774 (5.763) Accm: 3.38 (3.44) Acct: 5.32 (5.38) proj_loss: -0.6097 (-0.6032) time: 0.9440 data: 0.0016 [11-24 12:26:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.524 (6.513) Lt: 5.788 (5.761) Accm: 3.10 (3.31) Acct: 4.91 (5.34) proj_loss: -0.5970 (-0.5976) time: 0.9440 data: 0.0017 [11-24 12:26:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 93/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.600 (6.613) Lt: 5.832 (5.859) Accm: 3.05 (2.99) Acct: 4.88 (4.71) proj_loss: -0.5913 (-0.5942) time: 0.9440 data: 0.0019 [11-24 12:26:28] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 93/350] Total time: 0:26:22 (0.948 s / it) [11-24 12:26:28] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 93/350] Total time: 0:26:22 (0.948 s / it) [11-24 12:26:28] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 93/350] Total time: 0:26:22 (0.948 s / it) [11-24 12:26:28] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 93/350] Total time: 0:26:22 (0.948 s / it) [11-24 12:26:28] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 93/350] Total time: 0:26:22 (0.948 s / it) [11-24 12:26:28] (/home/user/VAR/train.py , line 276)=> [ep93] (training ) Lm: 6.496 (6.496), Lt: 5.738 (5.738), Acc m&t: 3.38 5.31, Remain: 4 days, 16:52:53, Finish: 2024-11-28 13:19 [11-24 12:26:28] (/home/user/VAR/train.py , line 276)=> [ep93] (training ) Lm: 6.496 (6.496), Lt: 5.738 (5.738), Acc m&t: 3.38 5.31, Remain: 4 days, 16:52:56, Finish: 2024-11-28 13:19 [11-24 12:26:28] (/home/user/VAR/train.py , line 276)=> [ep93] (training ) Lm: 6.496 (6.496), Lt: 5.738 (5.738), Acc m&t: 3.38 5.31, Remain: 4 days, 16:50:46, Finish: 2024-11-28 13:17 [11-24 12:26:28] (/home/user/VAR/train.py , line 276)=> [ep93] (training ) Lm: 6.496 (6.496), Lt: 5.738 (5.738), Acc m&t: 3.38 5.31, Remain: 4 days, 16:53:24, Finish: 2024-11-28 13:19 [11-24 12:26:28] (/home/user/VAR/train.py , line 276)=> [ep93] (training ) Lm: 6.496 (6.496), Lt: 5.738 (5.738), Acc m&t: 3.38 5.31, Remain: 4 days, 16:54:58, Finish: 2024-11-28 13:21 [11-24 12:26:28] (/home/user/VAR/train.py , line 276)=> [ep93] (training ) Lm: 6.496 (6.496), Lt: 5.738 (5.738), Acc m&t: 3.38 5.31, Remain: 4 days, 16:50:13, Finish: 2024-11-28 13:16 [11-24 12:26:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [ 0/1669] eta: 0:25:22 tlr: 0.00019 tnm: 0.20 Lm: 6.483 (6.483) Lt: 5.729 (5.729) Accm: 3.38 (3.38) Acct: 5.37 (5.37) proj_loss: -0.5968 (-0.5968) time: 0.9119 data: 0.0004 [11-24 12:26:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [ 0/1669] eta: 0:25:21 tlr: 0.00019 tnm: 0.20 Lm: 6.635 (6.635) Lt: 5.833 (5.833) Accm: 2.98 (2.98) Acct: 4.70 (4.70) proj_loss: -0.5738 (-0.5738) time: 0.9117 data: 0.0004 [11-24 12:26:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [ 0/1669] eta: 0:25:22 tlr: 0.00019 tnm: 0.20 Lm: 6.654 (6.654) Lt: 6.021 (6.021) Accm: 2.68 (2.68) Acct: 4.36 (4.36) proj_loss: -0.6047 (-0.6047) time: 0.9123 data: 0.0005 [11-24 12:26:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [ 0/1669] eta: 0:25:23 tlr: 0.00019 tnm: 0.20 Lm: 6.634 (6.634) Lt: 5.881 (5.881) Accm: 2.98 (2.98) Acct: 4.67 (4.67) proj_loss: -0.5916 (-0.5916) time: 0.9130 data: 0.0003 [11-24 12:26:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [ 0/1669] eta: 0:25:24 tlr: 0.00019 tnm: 0.20 Lm: 6.653 (6.653) Lt: 5.968 (5.968) Accm: 2.90 (2.90) Acct: 4.57 (4.57) proj_loss: -0.6102 (-0.6102) time: 0.9132 data: 0.0004 [11-24 12:26:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [ 0/1669] eta: 0:25:24 tlr: 0.00019 tnm: 0.20 Lm: 6.699 (6.699) Lt: 5.904 (5.904) Accm: 2.91 (2.91) Acct: 4.86 (4.86) proj_loss: -0.5913 (-0.5913) time: 0.9132 data: 0.0004 [11-24 12:33:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.562 (6.562) Lt: 5.757 (5.757) Accm: 3.32 (3.32) Acct: 5.11 (5.11) proj_loss: -0.5944 (-0.5944) time: 0.9440 data: 0.0003 [11-24 12:33:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.464 (6.464) Lt: 5.724 (5.724) Accm: 3.58 (3.58) Acct: 5.79 (5.79) proj_loss: -0.5989 (-0.5989) time: 0.9440 data: 0.0003 [11-24 12:33:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.456 (6.456) Lt: 5.710 (5.710) Accm: 3.37 (3.37) Acct: 5.23 (5.23) proj_loss: -0.6020 (-0.6020) time: 0.9439 data: 0.0003 [11-24 12:33:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.630 (6.630) Lt: 5.873 (5.873) Accm: 3.04 (3.04) Acct: 4.71 (4.71) proj_loss: -0.5937 (-0.5937) time: 0.9440 data: 0.0002 [11-24 12:33:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.518 (6.518) Lt: 5.778 (5.778) Accm: 3.21 (3.21) Acct: 5.09 (5.09) proj_loss: -0.6003 (-0.6003) time: 0.9439 data: 0.0003 [11-24 12:33:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.627 (6.627) Lt: 5.847 (5.847) Accm: 2.96 (2.96) Acct: 4.71 (4.71) proj_loss: -0.6083 (-0.6083) time: 0.9439 data: 0.0003 [11-24 12:39:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.22 Lm: 6.555 (6.570) Lt: 5.790 (5.796) Accm: 3.00 (3.13) Acct: 4.86 (5.07) proj_loss: -0.6209 (-0.6125) time: 0.9405 data: 0.0003 [11-24 12:39:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.22 Lm: 6.383 (6.463) Lt: 5.588 (5.706) Accm: 3.52 (3.34) Acct: 5.60 (5.28) proj_loss: -0.6004 (-0.6003) time: 0.9405 data: 0.0002 [11-24 12:39:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.22 Lm: 6.625 (6.471) Lt: 5.865 (5.738) Accm: 3.10 (3.35) Acct: 4.75 (5.09) proj_loss: -0.5958 (-0.6062) time: 0.9405 data: 0.0002 [11-24 12:39:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.22 Lm: 6.497 (6.540) Lt: 5.681 (5.714) Accm: 3.37 (3.33) Acct: 5.53 (5.34) proj_loss: -0.5983 (-0.5957) time: 0.9404 data: 0.0003 [11-24 12:39:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.22 Lm: 6.274 (6.373) Lt: 5.426 (5.603) Accm: 4.08 (3.75) Acct: 6.66 (6.08) proj_loss: -0.6047 (-0.6016) time: 0.9404 data: 0.0002 [11-24 12:39:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.22 Lm: 6.483 (6.475) Lt: 5.692 (5.687) Accm: 3.35 (3.29) Acct: 5.24 (5.23) proj_loss: -0.5998 (-0.6013) time: 0.9405 data: 0.0003 [11-24 12:46:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [1251/1669] eta: 0:06:33 tlr: 0.00019 tnm: 0.21 Lm: 6.456 (6.447) Lt: 5.665 (5.673) Accm: 3.37 (3.49) Acct: 5.31 (5.38) proj_loss: -0.6016 (-0.6018) time: 0.9431 data: 0.0003 [11-24 12:46:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [1251/1669] eta: 0:06:33 tlr: 0.00019 tnm: 0.21 Lm: 6.464 (6.449) Lt: 5.693 (5.692) Accm: 3.38 (3.48) Acct: 5.51 (5.65) proj_loss: -0.6058 (-0.6044) time: 0.9431 data: 0.0002 [11-24 12:46:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [1251/1669] eta: 0:06:33 tlr: 0.00019 tnm: 0.21 Lm: 6.597 (6.496) Lt: 5.836 (5.755) Accm: 3.04 (3.25) Acct: 4.71 (4.93) proj_loss: -0.6045 (-0.6080) time: 0.9431 data: 0.0002 [11-24 12:46:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [1251/1669] eta: 0:06:33 tlr: 0.00019 tnm: 0.21 Lm: 6.566 (6.585) Lt: 5.757 (5.777) Accm: 3.17 (3.25) Acct: 5.11 (5.16) proj_loss: -0.5860 (-0.5860) time: 0.9432 data: 0.0003 [11-24 12:46:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [1251/1669] eta: 0:06:33 tlr: 0.00019 tnm: 0.21 Lm: 6.450 (6.476) Lt: 5.693 (5.729) Accm: 3.29 (3.27) Acct: 5.15 (5.13) proj_loss: -0.6053 (-0.6106) time: 0.9432 data: 0.0002 [11-24 12:46:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [1251/1669] eta: 0:06:33 tlr: 0.00019 tnm: 0.21 Lm: 6.506 (6.511) Lt: 5.742 (5.727) Accm: 3.24 (3.35) Acct: 5.32 (5.40) proj_loss: -0.6117 (-0.6100) time: 0.9431 data: 0.0003 [11-24 12:52:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.458 (6.493) Lt: 5.695 (5.708) Accm: 3.35 (3.35) Acct: 5.50 (5.42) proj_loss: -0.6114 (-0.6103) time: 0.9420 data: 0.0016 [11-24 12:52:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 94/350] Total time: 0:26:10 (0.941 s / it) [11-24 12:52:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.483 (6.488) Lt: 5.692 (5.733) Accm: 3.35 (3.42) Acct: 5.24 (5.27) proj_loss: -0.6035 (-0.6071) time: 0.9420 data: 0.0016 [11-24 12:52:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.517 (6.489) Lt: 5.761 (5.736) Accm: 3.32 (3.28) Acct: 5.40 (5.19) proj_loss: -0.6004 (-0.6063) time: 0.9420 data: 0.0019 [11-24 12:52:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.569 (6.495) Lt: 5.811 (5.766) Accm: 3.10 (3.28) Acct: 4.75 (4.95) proj_loss: -0.5958 (-0.6042) time: 0.9420 data: 0.0016 [11-24 12:52:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.581 (6.584) Lt: 5.833 (5.802) Accm: 3.33 (3.26) Acct: 5.22 (5.17) proj_loss: -0.5983 (-0.5929) time: 0.9420 data: 0.0020 [11-24 12:52:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 94/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.586 (6.477) Lt: 5.810 (5.716) Accm: 3.33 (3.45) Acct: 5.24 (5.57) proj_loss: -0.6068 (-0.6049) time: 0.9420 data: 0.0015 [11-24 12:52:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 94/350] Total time: 0:26:10 (0.941 s / it) [11-24 12:52:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 94/350] Total time: 0:26:10 (0.941 s / it) [11-24 12:52:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 94/350] Total time: 0:26:10 (0.941 s / it) [11-24 12:52:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 94/350] Total time: 0:26:10 (0.941 s / it) [11-24 12:52:39] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 94/350] Total time: 0:26:10 (0.941 s / it) [11-24 12:52:39] (/home/user/VAR/train.py , line 276)=> [ep94] (training ) Lm: 6.496 (6.504), Lt: 5.738 (5.747), Acc m&t: 3.38 5.31, Remain: 4 days, 16:22:04, Finish: 2024-11-28 13:14 [11-24 12:52:39] (/home/user/VAR/train.py , line 276)=> [ep94] (training ) Lm: 6.496 (6.504), Lt: 5.738 (5.747), Acc m&t: 3.38 5.31, Remain: 4 days, 16:23:04, Finish: 2024-11-28 13:15 [11-24 12:52:39] (/home/user/VAR/train.py , line 276)=> [ep94] (training ) Lm: 6.496 (6.504), Lt: 5.738 (5.747), Acc m&t: 3.38 5.31, Remain: 4 days, 16:21:00, Finish: 2024-11-28 13:13 [11-24 12:52:39] (/home/user/VAR/train.py , line 276)=> [ep94] (training ) Lm: 6.496 (6.504), Lt: 5.738 (5.747), Acc m&t: 3.38 5.31, Remain: 4 days, 16:22:12, Finish: 2024-11-28 13:14 [11-24 12:52:39] (/home/user/VAR/train.py , line 276)=> [ep94] (training ) Lm: 6.496 (6.504), Lt: 5.738 (5.747), Acc m&t: 3.38 5.31, Remain: 4 days, 16:22:21, Finish: 2024-11-28 13:14 [11-24 12:52:39] (/home/user/VAR/train.py , line 276)=> [ep94] (training ) Lm: 6.496 (6.504), Lt: 5.738 (5.747), Acc m&t: 3.38 5.31, Remain: 4 days, 16:21:40, Finish: 2024-11-28 13:14 [11-24 12:52:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [ 0/1669] eta: 0:25:54 tlr: 0.00019 tnm: 0.22 Lm: 6.542 (6.542) Lt: 5.869 (5.869) Accm: 3.30 (3.30) Acct: 5.32 (5.32) proj_loss: -0.6085 (-0.6085) time: 0.9313 data: 0.0004 [11-24 12:52:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [ 0/1669] eta: 0:26:00 tlr: 0.00019 tnm: 0.22 Lm: 6.561 (6.561) Lt: 5.766 (5.766) Accm: 3.30 (3.30) Acct: 4.80 (4.80) proj_loss: -0.6002 (-0.6002) time: 0.9349 data: 0.0003 [11-24 12:52:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [ 0/1669] eta: 0:26:01 tlr: 0.00019 tnm: 0.22 Lm: 6.305 (6.305) Lt: 5.447 (5.447) Accm: 4.05 (4.05) Acct: 6.51 (6.51) proj_loss: -0.6135 (-0.6135) time: 0.9355 data: 0.0004 [11-24 12:52:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [ 0/1669] eta: 0:26:01 tlr: 0.00019 tnm: 0.22 Lm: 6.213 (6.213) Lt: 5.396 (5.396) Accm: 4.48 (4.48) Acct: 6.56 (6.56) proj_loss: -0.6151 (-0.6151) time: 0.9354 data: 0.0004 [11-24 12:52:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [ 0/1669] eta: 0:25:55 tlr: 0.00019 tnm: 0.22 Lm: 6.435 (6.435) Lt: 5.665 (5.665) Accm: 3.91 (3.91) Acct: 6.43 (6.43) proj_loss: -0.5879 (-0.5879) time: 0.9319 data: 0.0003 [11-24 12:52:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [ 0/1669] eta: 0:26:01 tlr: 0.00019 tnm: 0.22 Lm: 6.538 (6.538) Lt: 5.758 (5.758) Accm: 3.49 (3.49) Acct: 5.35 (5.35) proj_loss: -0.5783 (-0.5783) time: 0.9355 data: 0.0004 [11-24 12:59:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [ 417/1669] eta: 0:19:40 tlr: 0.00019 tnm: 0.21 Lm: 6.591 (6.591) Lt: 5.846 (5.846) Accm: 3.25 (3.25) Acct: 5.13 (5.13) proj_loss: -0.5966 (-0.5966) time: 0.9417 data: 0.0002 [11-24 12:59:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [ 417/1669] eta: 0:19:40 tlr: 0.00019 tnm: 0.21 Lm: 6.496 (6.496) Lt: 5.786 (5.786) Accm: 3.33 (3.33) Acct: 5.09 (5.09) proj_loss: -0.6002 (-0.6002) time: 0.9417 data: 0.0003 [11-24 12:59:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [ 417/1669] eta: 0:19:40 tlr: 0.00019 tnm: 0.21 Lm: 6.538 (6.538) Lt: 5.770 (5.770) Accm: 3.20 (3.20) Acct: 4.79 (4.79) proj_loss: -0.5962 (-0.5962) time: 0.9417 data: 0.0003 [11-24 12:59:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [ 417/1669] eta: 0:19:44 tlr: 0.00019 tnm: 0.21 Lm: 6.398 (6.398) Lt: 5.607 (5.607) Accm: 3.80 (3.80) Acct: 5.77 (5.77) proj_loss: -0.6036 (-0.6036) time: 0.9860 data: 0.0003 [11-24 12:59:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [ 417/1669] eta: 0:19:45 tlr: 0.00019 tnm: 0.21 Lm: 6.388 (6.388) Lt: 5.608 (5.608) Accm: 3.71 (3.71) Acct: 5.86 (5.86) proj_loss: -0.6217 (-0.6217) time: 0.9870 data: 0.0004 [11-24 12:59:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [ 417/1669] eta: 0:19:45 tlr: 0.00019 tnm: 0.21 Lm: 6.459 (6.459) Lt: 5.669 (5.669) Accm: 3.60 (3.60) Acct: 5.91 (5.91) proj_loss: -0.5841 (-0.5841) time: 0.9891 data: 0.0003 [11-24 13:05:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [ 834/1669] eta: 0:13:16 tlr: 0.00019 tnm: 0.21 Lm: 6.482 (6.501) Lt: 5.672 (5.722) Accm: 3.29 (3.35) Acct: 5.40 (5.34) proj_loss: -0.5879 (-0.5903) time: 0.9400 data: 0.0003 [11-24 13:05:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [ 834/1669] eta: 0:13:16 tlr: 0.00019 tnm: 0.21 Lm: 6.451 (6.455) Lt: 5.702 (5.728) Accm: 3.37 (3.39) Acct: 5.32 (5.23) proj_loss: -0.6027 (-0.6010) time: 0.9400 data: 0.0002 [11-24 13:05:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [ 834/1669] eta: 0:13:16 tlr: 0.00019 tnm: 0.21 Lm: 6.553 (6.578) Lt: 5.907 (5.867) Accm: 3.07 (3.19) Acct: 5.01 (5.09) proj_loss: -0.6024 (-0.5986) time: 0.9400 data: 0.0002 [11-24 13:05:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [ 834/1669] eta: 0:13:16 tlr: 0.00019 tnm: 0.21 Lm: 6.515 (6.508) Lt: 5.766 (5.725) Accm: 3.30 (3.49) Acct: 4.80 (5.43) proj_loss: -0.6002 (-0.6005) time: 0.9400 data: 0.0002 [11-24 13:05:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [ 834/1669] eta: 0:13:16 tlr: 0.00019 tnm: 0.21 Lm: 6.471 (6.486) Lt: 5.769 (5.706) Accm: 3.37 (3.38) Acct: 5.22 (5.36) proj_loss: -0.6135 (-0.6148) time: 0.9400 data: 0.0003 [11-24 13:05:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [ 834/1669] eta: 0:13:16 tlr: 0.00019 tnm: 0.21 Lm: 6.583 (6.482) Lt: 5.818 (5.706) Accm: 3.11 (3.52) Acct: 4.98 (5.41) proj_loss: -0.6071 (-0.6047) time: 0.9400 data: 0.0002 [11-24 13:12:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [1251/1669] eta: 0:06:36 tlr: 0.00019 tnm: 0.21 Lm: 6.547 (6.489) Lt: 5.783 (5.717) Accm: 3.20 (3.46) Acct: 5.13 (5.37) proj_loss: -0.6029 (-0.6032) time: 0.9431 data: 0.0002 [11-24 13:12:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [1251/1669] eta: 0:06:36 tlr: 0.00019 tnm: 0.21 Lm: 6.545 (6.505) Lt: 5.832 (5.779) Accm: 3.28 (3.46) Acct: 5.18 (5.43) proj_loss: -0.6023 (-0.5995) time: 0.9431 data: 0.0003 [11-24 13:12:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [1251/1669] eta: 0:06:36 tlr: 0.00019 tnm: 0.21 Lm: 6.466 (6.461) Lt: 5.746 (5.743) Accm: 3.44 (3.49) Acct: 5.42 (5.40) proj_loss: -0.6056 (-0.6062) time: 0.9431 data: 0.0002 [11-24 13:12:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [1251/1669] eta: 0:06:36 tlr: 0.00019 tnm: 0.21 Lm: 6.538 (6.524) Lt: 5.770 (5.741) Accm: 3.26 (3.42) Acct: 4.92 (5.33) proj_loss: -0.6021 (-0.6013) time: 0.9431 data: 0.0003 [11-24 13:12:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [1251/1669] eta: 0:06:36 tlr: 0.00019 tnm: 0.21 Lm: 6.552 (6.523) Lt: 5.836 (5.768) Accm: 3.05 (3.21) Acct: 4.79 (5.08) proj_loss: -0.6130 (-0.6142) time: 0.9431 data: 0.0003 [11-24 13:12:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [1251/1669] eta: 0:06:36 tlr: 0.00019 tnm: 0.21 Lm: 6.510 (6.510) Lt: 5.708 (5.727) Accm: 3.29 (3.34) Acct: 5.32 (5.31) proj_loss: -0.5901 (-0.5908) time: 0.9431 data: 0.0003 [11-24 13:19:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.537 (6.520) Lt: 5.744 (5.754) Accm: 3.30 (3.39) Acct: 5.40 (5.35) proj_loss: -0.5923 (-0.5991) time: 0.9418 data: 0.0017 [11-24 13:19:00] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 95/350] Total time: 0:26:20 (0.947 s / it) [11-24 13:19:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.480 (6.465) Lt: 5.734 (5.742) Accm: 3.37 (3.46) Acct: 5.32 (5.35) proj_loss: -0.6085 (-0.6096) time: 0.9418 data: 0.0019 [11-24 13:19:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.471 (6.509) Lt: 5.769 (5.756) Accm: 3.37 (3.28) Acct: 5.22 (5.15) proj_loss: -0.6125 (-0.6128) time: 0.9418 data: 0.0017 [11-24 13:19:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.561 (6.531) Lt: 5.775 (5.757) Accm: 3.21 (3.34) Acct: 4.80 (5.18) proj_loss: -0.6040 (-0.6022) time: 0.9418 data: 0.0015 [11-24 13:19:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.553 (6.515) Lt: 5.835 (5.790) Accm: 3.07 (3.36) Acct: 5.01 (5.27) proj_loss: -0.6024 (-0.6024) time: 0.9418 data: 0.0015 [11-24 13:19:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 95/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.22 Lm: 6.512 (6.471) Lt: 5.748 (5.694) Accm: 3.28 (3.51) Acct: 5.27 (5.48) proj_loss: -0.5986 (-0.6006) time: 0.9418 data: 0.0015 [11-24 13:19:00] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 95/350] Total time: 0:26:20 (0.947 s / it) [11-24 13:19:00] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 95/350] Total time: 0:26:20 (0.947 s / it) [11-24 13:19:00] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 95/350] Total time: 0:26:20 (0.947 s / it) [11-24 13:19:00] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 95/350] Total time: 0:26:20 (0.947 s / it) [11-24 13:19:00] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 95/350] Total time: 0:26:20 (0.947 s / it) [11-24 13:19:00] (/home/user/VAR/train.py , line 276)=> [ep95] (training ) Lm: 6.496 (6.520), Lt: 5.738 (5.768), Acc m&t: 3.38 5.31, Remain: 4 days, 15:51:11, Finish: 2024-11-28 13:10 [11-24 13:19:00] (/home/user/VAR/train.py , line 276)=> [ep95] (training ) Lm: 6.496 (6.520), Lt: 5.738 (5.768), Acc m&t: 3.38 5.31, Remain: 4 days, 15:49:53, Finish: 2024-11-28 13:08 [11-24 13:19:00] (/home/user/VAR/train.py , line 276)=> [ep95] (training ) Lm: 6.496 (6.520), Lt: 5.738 (5.768), Acc m&t: 3.38 5.31, Remain: 4 days, 15:51:54, Finish: 2024-11-28 13:10 [11-24 13:19:00] (/home/user/VAR/train.py , line 276)=> [ep95] (training ) Lm: 6.496 (6.520), Lt: 5.738 (5.768), Acc m&t: 3.38 5.31, Remain: 4 days, 15:52:04, Finish: 2024-11-28 13:11 [11-24 13:19:00] (/home/user/VAR/train.py , line 276)=> [ep95] (training ) Lm: 6.496 (6.520), Lt: 5.738 (5.768), Acc m&t: 3.38 5.31, Remain: 4 days, 15:52:16, Finish: 2024-11-28 13:11 [11-24 13:19:00] (/home/user/VAR/train.py , line 276)=> [ep95] (training ) Lm: 6.496 (6.520), Lt: 5.738 (5.768), Acc m&t: 3.38 5.31, Remain: 4 days, 15:50:26, Finish: 2024-11-28 13:09 [11-24 13:19:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [ 0/1669] eta: 0:25:30 tlr: 0.00019 tnm: 0.22 Lm: 6.381 (6.381) Lt: 5.636 (5.636) Accm: 3.55 (3.55) Acct: 5.53 (5.53) proj_loss: -0.6222 (-0.6222) time: 0.9173 data: 0.0003 [11-24 13:19:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [ 0/1669] eta: 0:25:31 tlr: 0.00019 tnm: 0.22 Lm: 6.554 (6.554) Lt: 5.767 (5.767) Accm: 3.03 (3.03) Acct: 4.96 (4.96) proj_loss: -0.5801 (-0.5801) time: 0.9174 data: 0.0004 [11-24 13:19:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [ 0/1669] eta: 0:25:33 tlr: 0.00019 tnm: 0.22 Lm: 6.481 (6.481) Lt: 5.670 (5.670) Accm: 3.66 (3.66) Acct: 5.81 (5.81) proj_loss: -0.5939 (-0.5939) time: 0.9189 data: 0.0004 [11-24 13:19:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [ 0/1669] eta: 0:25:34 tlr: 0.00019 tnm: 0.22 Lm: 6.648 (6.648) Lt: 5.914 (5.914) Accm: 3.15 (3.15) Acct: 4.78 (4.78) proj_loss: -0.6107 (-0.6107) time: 0.9192 data: 0.0004 [11-24 13:19:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [ 0/1669] eta: 0:25:34 tlr: 0.00019 tnm: 0.22 Lm: 6.404 (6.404) Lt: 5.494 (5.494) Accm: 3.67 (3.67) Acct: 5.97 (5.97) proj_loss: -0.5607 (-0.5607) time: 0.9192 data: 0.0004 [11-24 13:19:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [ 0/1669] eta: 0:25:34 tlr: 0.00019 tnm: 0.22 Lm: 6.698 (6.698) Lt: 6.059 (6.059) Accm: 2.44 (2.44) Acct: 3.51 (3.51) proj_loss: -0.6167 (-0.6167) time: 0.9196 data: 0.0004 [11-24 13:25:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.538 (6.538) Lt: 5.835 (5.835) Accm: 3.10 (3.10) Acct: 4.75 (4.75) proj_loss: -0.6075 (-0.6075) time: 0.9390 data: 0.0003 [11-24 13:25:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.485 (6.485) Lt: 5.732 (5.732) Accm: 3.32 (3.32) Acct: 5.15 (5.15) proj_loss: -0.5812 (-0.5812) time: 0.9390 data: 0.0003 [11-24 13:25:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.407 (6.407) Lt: 5.636 (5.636) Accm: 3.93 (3.93) Acct: 6.31 (6.31) proj_loss: -0.6086 (-0.6086) time: 0.9390 data: 0.0003 [11-24 13:25:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.503 (6.503) Lt: 5.753 (5.753) Accm: 3.37 (3.37) Acct: 5.41 (5.41) proj_loss: -0.5914 (-0.5914) time: 0.9390 data: 0.0002 [11-24 13:25:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.562 (6.562) Lt: 5.853 (5.853) Accm: 3.14 (3.14) Acct: 4.70 (4.70) proj_loss: -0.6102 (-0.6102) time: 0.9390 data: 0.0003 [11-24 13:25:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.444 (6.444) Lt: 5.629 (5.629) Accm: 3.47 (3.47) Acct: 5.69 (5.69) proj_loss: -0.5692 (-0.5692) time: 0.9390 data: 0.0003 [11-24 13:32:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [ 834/1669] eta: 0:13:21 tlr: 0.00019 tnm: 0.21 Lm: 6.484 (6.473) Lt: 5.678 (5.646) Accm: 3.57 (3.51) Acct: 5.63 (5.67) proj_loss: -0.5777 (-0.5750) time: 0.9398 data: 0.0003 [11-24 13:32:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [ 834/1669] eta: 0:13:21 tlr: 0.00019 tnm: 0.21 Lm: 6.648 (6.600) Lt: 5.914 (5.879) Accm: 3.12 (3.02) Acct: 4.62 (4.59) proj_loss: -0.6097 (-0.6005) time: 0.9398 data: 0.0003 [11-24 13:32:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [ 834/1669] eta: 0:13:21 tlr: 0.00019 tnm: 0.21 Lm: 6.481 (6.468) Lt: 5.670 (5.692) Accm: 3.66 (3.76) Acct: 5.81 (5.98) proj_loss: -0.5939 (-0.5998) time: 0.9398 data: 0.0003 [11-24 13:32:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [ 834/1669] eta: 0:13:21 tlr: 0.00019 tnm: 0.21 Lm: 6.432 (6.468) Lt: 5.697 (5.691) Accm: 3.53 (3.39) Acct: 5.35 (5.33) proj_loss: -0.5823 (-0.5912) time: 0.9399 data: 0.0003 [11-24 13:32:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [ 834/1669] eta: 0:13:21 tlr: 0.00019 tnm: 0.21 Lm: 6.381 (6.421) Lt: 5.636 (5.654) Accm: 3.55 (3.50) Acct: 5.53 (5.65) proj_loss: -0.5940 (-0.5922) time: 0.9398 data: 0.0002 [11-24 13:32:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [ 834/1669] eta: 0:13:21 tlr: 0.00019 tnm: 0.21 Lm: 6.632 (6.570) Lt: 5.943 (5.871) Accm: 2.96 (3.06) Acct: 4.44 (4.65) proj_loss: -0.5983 (-0.5983) time: 0.9398 data: 0.0003 [11-24 13:38:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [1251/1669] eta: 0:06:38 tlr: 0.00019 tnm: 0.22 Lm: 6.594 (6.566) Lt: 5.872 (5.854) Accm: 3.12 (3.11) Acct: 4.66 (4.71) proj_loss: -0.5956 (-0.5970) time: 0.9414 data: 0.0003 [11-24 13:38:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [1251/1669] eta: 0:06:38 tlr: 0.00019 tnm: 0.22 Lm: 6.503 (6.487) Lt: 5.753 (5.735) Accm: 3.37 (3.33) Acct: 5.41 (5.36) proj_loss: -0.5993 (-0.5953) time: 0.9414 data: 0.0003 [11-24 13:38:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [1251/1669] eta: 0:06:38 tlr: 0.00019 tnm: 0.22 Lm: 6.568 (6.572) Lt: 5.853 (5.838) Accm: 3.14 (3.16) Acct: 4.70 (4.78) proj_loss: -0.6074 (-0.6017) time: 0.9414 data: 0.0003 [11-24 13:38:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [1251/1669] eta: 0:06:38 tlr: 0.00019 tnm: 0.22 Lm: 6.473 (6.479) Lt: 5.678 (5.683) Accm: 3.39 (3.35) Acct: 5.19 (5.26) proj_loss: -0.5854 (-0.5905) time: 0.9414 data: 0.0003 [11-24 13:38:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [1251/1669] eta: 0:06:38 tlr: 0.00019 tnm: 0.22 Lm: 6.530 (6.496) Lt: 5.723 (5.713) Accm: 3.53 (3.56) Acct: 5.57 (5.60) proj_loss: -0.5880 (-0.5946) time: 0.9414 data: 0.0003 [11-24 13:38:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [1251/1669] eta: 0:06:38 tlr: 0.00019 tnm: 0.22 Lm: 6.471 (6.469) Lt: 5.716 (5.673) Accm: 3.49 (3.48) Acct: 5.55 (5.62) proj_loss: -0.5821 (-0.5864) time: 0.9414 data: 0.0003 [11-24 13:45:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.458 (6.466) Lt: 5.701 (5.678) Accm: 3.41 (3.46) Acct: 5.48 (5.54) proj_loss: -0.5865 (-0.5878) time: 0.9409 data: 0.0016 [11-24 13:45:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 96/350] Total time: 0:26:26 (0.950 s / it) [11-24 13:45:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.486 (6.487) Lt: 5.756 (5.739) Accm: 3.55 (3.40) Acct: 5.53 (5.42) proj_loss: -0.5957 (-0.5954) time: 0.9409 data: 0.0018 [11-24 13:45:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.514 (6.509) Lt: 5.697 (5.735) Accm: 3.25 (3.25) Acct: 5.04 (5.06) proj_loss: -0.5884 (-0.5936) time: 0.9409 data: 0.0019 [11-24 13:45:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.556 (6.522) Lt: 5.801 (5.788) Accm: 3.29 (3.27) Acct: 4.88 (5.03) proj_loss: -0.5940 (-0.5964) time: 0.9409 data: 0.0016 [11-24 13:45:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.489 (6.537) Lt: 5.792 (5.784) Accm: 3.15 (3.25) Acct: 4.78 (4.97) proj_loss: -0.6097 (-0.6044) time: 0.9409 data: 0.0015 [11-24 13:45:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 96/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.499 (6.497) Lt: 5.767 (5.724) Accm: 3.41 (3.52) Acct: 5.35 (5.55) proj_loss: -0.5939 (-0.5955) time: 0.9409 data: 0.0015 [11-24 13:45:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 96/350] Total time: 0:26:26 (0.950 s / it) [11-24 13:45:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 96/350] Total time: 0:26:26 (0.950 s / it) [11-24 13:45:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 96/350] Total time: 0:26:26 (0.950 s / it) [11-24 13:45:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 96/350] Total time: 0:26:26 (0.950 s / it) [11-24 13:45:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 96/350] Total time: 0:26:26 (0.950 s / it) [11-24 13:45:26] (/home/user/VAR/train.py , line 276)=> [ep96] (training ) Lm: 6.496 (6.512), Lt: 5.738 (5.755), Acc m&t: 3.38 5.31, Remain: 4 days, 15:24:20, Finish: 2024-11-28 13:09 [11-24 13:45:26] (/home/user/VAR/train.py , line 276)=> [ep96] (training ) Lm: 6.496 (6.512), Lt: 5.738 (5.755), Acc m&t: 3.38 5.31, Remain: 4 days, 15:22:26, Finish: 2024-11-28 13:07 [11-24 13:45:26] (/home/user/VAR/train.py , line 276)=> [ep96] (training ) Lm: 6.496 (6.512), Lt: 5.738 (5.755), Acc m&t: 3.38 5.31, Remain: 4 days, 15:22:41, Finish: 2024-11-28 13:08 [11-24 13:45:26] (/home/user/VAR/train.py , line 276)=> [ep96] (training ) Lm: 6.496 (6.512), Lt: 5.738 (5.755), Acc m&t: 3.38 5.31, Remain: 4 days, 15:23:42, Finish: 2024-11-28 13:09 [11-24 13:45:26] (/home/user/VAR/train.py , line 276)=> [ep96] (training ) Lm: 6.496 (6.512), Lt: 5.738 (5.755), Acc m&t: 3.38 5.31, Remain: 4 days, 15:22:35, Finish: 2024-11-28 13:08 [11-24 13:45:26] (/home/user/VAR/train.py , line 276)=> [ep96] (training ) Lm: 6.496 (6.512), Lt: 5.738 (5.755), Acc m&t: 3.38 5.31, Remain: 4 days, 15:22:02, Finish: 2024-11-28 13:07 [11-24 13:45:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [ 0/1669] eta: 0:25:24 tlr: 0.00019 tnm: 0.22 Lm: 6.628 (6.628) Lt: 5.899 (5.899) Accm: 2.94 (2.94) Acct: 4.57 (4.57) proj_loss: -0.5794 (-0.5794) time: 0.9137 data: 0.0004 [11-24 13:45:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [ 0/1669] eta: 0:25:25 tlr: 0.00019 tnm: 0.22 Lm: 6.477 (6.477) Lt: 5.696 (5.696) Accm: 3.26 (3.26) Acct: 4.98 (4.98) proj_loss: -0.6232 (-0.6232) time: 0.9141 data: 0.0004 [11-24 13:45:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [ 0/1669] eta: 0:25:25 tlr: 0.00019 tnm: 0.22 Lm: 6.663 (6.663) Lt: 5.932 (5.932) Accm: 2.81 (2.81) Acct: 4.34 (4.34) proj_loss: -0.6035 (-0.6035) time: 0.9143 data: 0.0004 [11-24 13:45:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [ 0/1669] eta: 0:25:26 tlr: 0.00019 tnm: 0.22 Lm: 6.379 (6.379) Lt: 5.619 (5.619) Accm: 3.78 (3.78) Acct: 5.81 (5.81) proj_loss: -0.6023 (-0.6023) time: 0.9143 data: 0.0004 [11-24 13:45:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [ 0/1669] eta: 0:25:26 tlr: 0.00019 tnm: 0.22 Lm: 6.532 (6.532) Lt: 5.764 (5.764) Accm: 3.30 (3.30) Acct: 5.19 (5.19) proj_loss: -0.6107 (-0.6107) time: 0.9148 data: 0.0004 [11-24 13:45:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [ 0/1669] eta: 0:25:26 tlr: 0.00019 tnm: 0.22 Lm: 6.499 (6.499) Lt: 5.817 (5.817) Accm: 3.51 (3.51) Acct: 5.42 (5.42) proj_loss: -0.6436 (-0.6436) time: 0.9147 data: 0.0004 [11-24 13:51:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.467 (6.467) Lt: 5.747 (5.747) Accm: 3.55 (3.55) Acct: 5.37 (5.37) proj_loss: -0.6177 (-0.6177) time: 0.9411 data: 0.0003 [11-24 13:51:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.595 (6.595) Lt: 5.850 (5.850) Accm: 3.16 (3.16) Acct: 5.02 (5.02) proj_loss: -0.5980 (-0.5980) time: 0.9411 data: 0.0003 [11-24 13:51:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.502 (6.502) Lt: 5.762 (5.762) Accm: 3.40 (3.40) Acct: 5.24 (5.24) proj_loss: -0.6151 (-0.6151) time: 0.9411 data: 0.0002 [11-24 13:51:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.539 (6.539) Lt: 5.748 (5.748) Accm: 3.23 (3.23) Acct: 5.01 (5.01) proj_loss: -0.5931 (-0.5931) time: 0.9411 data: 0.0003 [11-24 13:51:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.524 (6.524) Lt: 5.802 (5.802) Accm: 3.23 (3.23) Acct: 4.91 (4.91) proj_loss: -0.6071 (-0.6071) time: 0.9411 data: 0.0003 [11-24 13:51:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [ 417/1669] eta: 0:19:37 tlr: 0.00019 tnm: 0.22 Lm: 6.544 (6.544) Lt: 5.787 (5.787) Accm: 3.32 (3.32) Acct: 5.33 (5.33) proj_loss: -0.5881 (-0.5881) time: 0.9411 data: 0.0002 [11-24 13:58:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.22 Lm: 6.477 (6.522) Lt: 5.679 (5.751) Accm: 3.43 (3.36) Acct: 5.58 (5.41) proj_loss: -0.5794 (-0.5815) time: 0.9407 data: 0.0003 [11-24 13:58:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.22 Lm: 6.532 (6.523) Lt: 5.764 (5.767) Accm: 3.30 (3.42) Acct: 5.19 (5.39) proj_loss: -0.6107 (-0.6029) time: 0.9407 data: 0.0003 [11-24 13:58:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.22 Lm: 6.475 (6.493) Lt: 5.675 (5.733) Accm: 3.42 (3.41) Acct: 5.55 (5.35) proj_loss: -0.6035 (-0.6040) time: 0.9407 data: 0.0002 [11-24 13:58:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.22 Lm: 6.515 (6.521) Lt: 5.788 (5.798) Accm: 3.21 (3.23) Acct: 4.83 (4.88) proj_loss: -0.6023 (-0.6003) time: 0.9407 data: 0.0002 [11-24 13:58:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.22 Lm: 6.558 (6.546) Lt: 5.726 (5.741) Accm: 3.21 (3.22) Acct: 5.04 (5.12) proj_loss: -0.5919 (-0.5927) time: 0.9407 data: 0.0003 [11-24 13:58:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.22 Lm: 6.436 (6.407) Lt: 5.677 (5.672) Accm: 3.59 (3.73) Acct: 5.42 (5.75) proj_loss: -0.5967 (-0.6107) time: 0.9407 data: 0.0003 [11-24 14:05:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [1251/1669] eta: 0:06:33 tlr: 0.00019 tnm: 0.22 Lm: 6.427 (6.409) Lt: 5.679 (5.674) Accm: 3.73 (3.76) Acct: 5.75 (5.83) proj_loss: -0.5972 (-0.6075) time: 0.9407 data: 0.0003 [11-24 14:05:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [1251/1669] eta: 0:06:33 tlr: 0.00019 tnm: 0.22 Lm: 6.553 (6.558) Lt: 5.789 (5.800) Accm: 3.19 (3.25) Acct: 5.31 (5.32) proj_loss: -0.5881 (-0.5891) time: 0.9406 data: 0.0003 [11-24 14:05:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [1251/1669] eta: 0:06:33 tlr: 0.00019 tnm: 0.22 Lm: 6.456 (6.478) Lt: 5.682 (5.703) Accm: 3.58 (3.53) Acct: 5.49 (5.49) proj_loss: -0.6090 (-0.6040) time: 0.9406 data: 0.0003 [11-24 14:05:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [1251/1669] eta: 0:06:33 tlr: 0.00019 tnm: 0.22 Lm: 6.539 (6.531) Lt: 5.817 (5.810) Accm: 3.29 (3.26) Acct: 5.04 (4.97) proj_loss: -0.6065 (-0.6029) time: 0.9407 data: 0.0002 [11-24 14:05:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [1251/1669] eta: 0:06:33 tlr: 0.00019 tnm: 0.22 Lm: 6.409 (6.441) Lt: 5.633 (5.680) Accm: 3.71 (3.57) Acct: 5.85 (5.61) proj_loss: -0.5927 (-0.5984) time: 0.9407 data: 0.0003 [11-24 14:05:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [1251/1669] eta: 0:06:33 tlr: 0.00019 tnm: 0.22 Lm: 6.518 (6.529) Lt: 5.716 (5.732) Accm: 3.23 (3.29) Acct: 5.19 (5.22) proj_loss: -0.5893 (-0.5912) time: 0.9407 data: 0.0003 [11-24 14:11:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.481 (6.519) Lt: 5.726 (5.741) Accm: 3.26 (3.32) Acct: 5.32 (5.24) proj_loss: -0.5919 (-0.5975) time: 0.9442 data: 0.0017 [11-24 14:11:51] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 97/350] Total time: 0:26:25 (0.950 s / it) [11-24 14:11:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.515 (6.487) Lt: 5.788 (5.743) Accm: 3.37 (3.51) Acct: 5.24 (5.38) proj_loss: -0.6103 (-0.6044) time: 0.9442 data: 0.0016 [11-24 14:11:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.522 (6.551) Lt: 5.839 (5.808) Accm: 3.23 (3.24) Acct: 5.04 (5.25) proj_loss: -0.5953 (-0.5903) time: 0.9442 data: 0.0019 [11-24 14:11:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.532 (6.514) Lt: 5.764 (5.756) Accm: 3.30 (3.40) Acct: 5.19 (5.22) proj_loss: -0.6072 (-0.6026) time: 0.9442 data: 0.0020 [11-24 14:11:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.475 (6.465) Lt: 5.675 (5.694) Accm: 3.42 (3.45) Acct: 5.55 (5.42) proj_loss: -0.5819 (-0.5947) time: 0.9442 data: 0.0017 [11-24 14:11:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 97/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.436 (6.432) Lt: 5.680 (5.686) Accm: 3.59 (3.66) Acct: 5.45 (5.75) proj_loss: -0.5976 (-0.6076) time: 0.9442 data: 0.0018 [11-24 14:11:51] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 97/350] Total time: 0:26:25 (0.950 s / it) [11-24 14:11:51] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 97/350] Total time: 0:26:25 (0.950 s / it) [11-24 14:11:51] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 97/350] Total time: 0:26:25 (0.950 s / it) [11-24 14:11:51] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 97/350] Total time: 0:26:25 (0.950 s / it) [11-24 14:11:51] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 97/350] Total time: 0:26:25 (0.950 s / it) [11-24 14:11:51] (/home/user/VAR/train.py , line 276)=> [ep97] (training ) Lm: 6.496 (6.508), Lt: 5.738 (5.755), Acc m&t: 3.38 5.31, Remain: 4 days, 15:13:27, Finish: 2024-11-28 13:25 [11-24 14:11:51] (/home/user/VAR/train.py , line 276)=> [ep97] (training ) Lm: 6.496 (6.508), Lt: 5.738 (5.755), Acc m&t: 3.38 5.31, Remain: 4 days, 15:11:23, Finish: 2024-11-28 13:23 [11-24 14:11:51] (/home/user/VAR/train.py , line 276)=> [ep97] (training ) Lm: 6.496 (6.508), Lt: 5.738 (5.755), Acc m&t: 3.38 5.31, Remain: 4 days, 15:17:11, Finish: 2024-11-28 13:29 [11-24 14:11:51] (/home/user/VAR/train.py , line 276)=> [ep97] (training ) Lm: 6.496 (6.508), Lt: 5.738 (5.755), Acc m&t: 3.38 5.31, Remain: 4 days, 15:15:53, Finish: 2024-11-28 13:27 [11-24 14:11:51] (/home/user/VAR/train.py , line 276)=> [ep97] (training ) Lm: 6.496 (6.508), Lt: 5.738 (5.755), Acc m&t: 3.38 5.31, Remain: 4 days, 15:16:40, Finish: 2024-11-28 13:28 [11-24 14:11:51] (/home/user/VAR/train.py , line 276)=> [ep97] (training ) Lm: 6.496 (6.508), Lt: 5.738 (5.755), Acc m&t: 3.38 5.31, Remain: 4 days, 15:14:51, Finish: 2024-11-28 13:26 [11-24 14:11:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [ 0/1669] eta: 0:25:32 tlr: 0.00019 tnm: 0.22 Lm: 6.520 (6.520) Lt: 5.803 (5.803) Accm: 3.14 (3.14) Acct: 4.91 (4.91) proj_loss: -0.6216 (-0.6216) time: 0.9185 data: 0.0003 [11-24 14:11:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [ 0/1669] eta: 0:25:33 tlr: 0.00019 tnm: 0.22 Lm: 6.537 (6.537) Lt: 5.866 (5.866) Accm: 3.19 (3.19) Acct: 4.91 (4.91) proj_loss: -0.6034 (-0.6034) time: 0.9186 data: 0.0004 [11-24 14:11:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [ 0/1669] eta: 0:25:32 tlr: 0.00019 tnm: 0.22 Lm: 6.408 (6.408) Lt: 5.637 (5.637) Accm: 3.51 (3.51) Acct: 5.50 (5.50) proj_loss: -0.5881 (-0.5881) time: 0.9184 data: 0.0003 [11-24 14:11:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [ 0/1669] eta: 0:25:34 tlr: 0.00019 tnm: 0.22 Lm: 6.335 (6.335) Lt: 5.591 (5.591) Accm: 3.73 (3.73) Acct: 5.68 (5.68) proj_loss: -0.6166 (-0.6166) time: 0.9193 data: 0.0004 [11-24 14:11:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [ 0/1669] eta: 0:25:35 tlr: 0.00019 tnm: 0.22 Lm: 6.541 (6.541) Lt: 5.773 (5.773) Accm: 3.42 (3.42) Acct: 5.45 (5.45) proj_loss: -0.6018 (-0.6018) time: 0.9199 data: 0.0004 [11-24 14:11:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [ 0/1669] eta: 0:25:34 tlr: 0.00019 tnm: 0.22 Lm: 6.506 (6.506) Lt: 5.686 (5.686) Accm: 3.33 (3.33) Acct: 5.24 (5.24) proj_loss: -0.6232 (-0.6232) time: 0.9196 data: 0.0004 [11-24 14:18:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [ 417/1669] eta: 0:19:38 tlr: 0.00019 tnm: 0.22 Lm: 6.556 (6.556) Lt: 5.780 (5.780) Accm: 3.27 (3.27) Acct: 5.29 (5.29) proj_loss: -0.6193 (-0.6193) time: 0.9404 data: 0.0003 [11-24 14:18:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [ 417/1669] eta: 0:19:38 tlr: 0.00019 tnm: 0.22 Lm: 6.529 (6.529) Lt: 5.787 (5.787) Accm: 3.12 (3.12) Acct: 4.86 (4.86) proj_loss: -0.6251 (-0.6251) time: 0.9404 data: 0.0003 [11-24 14:18:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [ 417/1669] eta: 0:19:38 tlr: 0.00019 tnm: 0.22 Lm: 6.419 (6.419) Lt: 5.635 (5.635) Accm: 3.56 (3.56) Acct: 5.55 (5.55) proj_loss: -0.5994 (-0.5994) time: 0.9404 data: 0.0003 [11-24 14:18:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [ 417/1669] eta: 0:19:38 tlr: 0.00019 tnm: 0.22 Lm: 6.450 (6.450) Lt: 5.699 (5.699) Accm: 3.55 (3.55) Acct: 5.41 (5.41) proj_loss: -0.6103 (-0.6103) time: 0.9404 data: 0.0002 [11-24 14:18:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [ 417/1669] eta: 0:19:38 tlr: 0.00019 tnm: 0.22 Lm: 6.487 (6.487) Lt: 5.740 (5.740) Accm: 3.38 (3.38) Acct: 5.31 (5.31) proj_loss: -0.6136 (-0.6136) time: 0.9404 data: 0.0002 [11-24 14:18:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [ 417/1669] eta: 0:19:38 tlr: 0.00019 tnm: 0.22 Lm: 6.518 (6.518) Lt: 5.759 (5.759) Accm: 3.63 (3.63) Acct: 5.68 (5.68) proj_loss: -0.6051 (-0.6051) time: 0.9404 data: 0.0003 [11-24 14:24:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.22 Lm: 6.504 (6.513) Lt: 5.770 (5.763) Accm: 3.42 (3.53) Acct: 5.45 (5.57) proj_loss: -0.6082 (-0.6062) time: 0.9424 data: 0.0003 [11-24 14:24:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.22 Lm: 6.520 (6.489) Lt: 5.771 (5.732) Accm: 3.14 (3.43) Acct: 4.91 (5.39) proj_loss: -0.6216 (-0.6159) time: 0.9424 data: 0.0003 [11-24 14:24:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.22 Lm: 6.430 (6.483) Lt: 5.637 (5.723) Accm: 3.51 (3.42) Acct: 5.50 (5.35) proj_loss: -0.6074 (-0.6021) time: 0.9424 data: 0.0003 [11-24 14:24:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.22 Lm: 6.438 (6.349) Lt: 5.613 (5.573) Accm: 3.57 (3.93) Acct: 5.71 (6.15) proj_loss: -0.6099 (-0.6124) time: 0.9424 data: 0.0002 [11-24 14:24:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.22 Lm: 6.477 (6.459) Lt: 5.636 (5.678) Accm: 3.73 (3.63) Acct: 5.68 (5.62) proj_loss: -0.6039 (-0.6063) time: 0.9424 data: 0.0002 [11-24 14:24:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [ 834/1669] eta: 0:13:05 tlr: 0.00019 tnm: 0.22 Lm: 6.515 (6.542) Lt: 5.760 (5.773) Accm: 3.28 (3.27) Acct: 5.24 (5.17) proj_loss: -0.6155 (-0.6180) time: 0.9424 data: 0.0003 [11-24 14:31:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [1251/1669] eta: 0:06:33 tlr: 0.00019 tnm: 0.22 Lm: 6.510 (6.510) Lt: 5.723 (5.750) Accm: 3.31 (3.29) Acct: 5.29 (5.22) proj_loss: -0.6181 (-0.6187) time: 0.9414 data: 0.0003 [11-24 14:31:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [1251/1669] eta: 0:06:33 tlr: 0.00019 tnm: 0.22 Lm: 6.505 (6.507) Lt: 5.741 (5.753) Accm: 3.37 (3.37) Acct: 5.38 (5.33) proj_loss: -0.6060 (-0.6027) time: 0.9414 data: 0.0003 [11-24 14:31:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [1251/1669] eta: 0:06:33 tlr: 0.00019 tnm: 0.22 Lm: 6.529 (6.503) Lt: 5.787 (5.755) Accm: 3.15 (3.37) Acct: 4.88 (5.26) proj_loss: -0.6184 (-0.6157) time: 0.9414 data: 0.0003 [11-24 14:31:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [1251/1669] eta: 0:06:33 tlr: 0.00019 tnm: 0.22 Lm: 6.499 (6.438) Lt: 5.758 (5.694) Accm: 3.63 (3.75) Acct: 5.68 (5.90) proj_loss: -0.6083 (-0.6078) time: 0.9413 data: 0.0003 [11-24 14:31:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [1251/1669] eta: 0:06:33 tlr: 0.00019 tnm: 0.22 Lm: 6.522 (6.510) Lt: 5.722 (5.752) Accm: 3.55 (3.47) Acct: 5.41 (5.39) proj_loss: -0.6049 (-0.6062) time: 0.9414 data: 0.0002 [11-24 14:31:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [1251/1669] eta: 0:06:33 tlr: 0.00019 tnm: 0.22 Lm: 6.431 (6.368) Lt: 5.666 (5.610) Accm: 3.54 (3.82) Acct: 5.42 (5.89) proj_loss: -0.6084 (-0.6110) time: 0.9414 data: 0.0002 [11-24 14:38:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.438 (6.433) Lt: 5.719 (5.687) Accm: 3.51 (3.65) Acct: 5.14 (5.57) proj_loss: -0.6069 (-0.6090) time: 0.9426 data: 0.0015 [11-24 14:38:04] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 98/350] Total time: 0:26:12 (0.942 s / it) [11-24 14:38:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.563 (6.519) Lt: 5.739 (5.750) Accm: 3.27 (3.35) Acct: 5.27 (5.30) proj_loss: -0.6074 (-0.6051) time: 0.9426 data: 0.0016 [11-24 14:38:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.504 (6.454) Lt: 5.745 (5.693) Accm: 3.42 (3.66) Acct: 5.50 (5.82) proj_loss: -0.6082 (-0.5999) time: 0.9426 data: 0.0019 [11-24 14:38:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.537 (6.534) Lt: 5.803 (5.775) Accm: 3.14 (3.27) Acct: 4.86 (5.17) proj_loss: -0.6152 (-0.6096) time: 0.9426 data: 0.0020 [11-24 14:38:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.515 (6.539) Lt: 5.760 (5.782) Accm: 3.28 (3.25) Acct: 5.24 (5.21) proj_loss: -0.6155 (-0.6176) time: 0.9426 data: 0.0016 [11-24 14:38:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 98/350] [1668/1669] eta: 0:00:00 tlr: 0.00019 tnm: 0.23 Lm: 6.506 (6.509) Lt: 5.742 (5.750) Accm: 3.37 (3.42) Acct: 5.14 (5.33) proj_loss: -0.6059 (-0.6062) time: 0.9426 data: 0.0020 [11-24 14:38:04] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 98/350] Total time: 0:26:12 (0.942 s / it) [11-24 14:38:04] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 98/350] Total time: 0:26:12 (0.942 s / it) [11-24 14:38:04] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 98/350] Total time: 0:26:12 (0.942 s / it) [11-24 14:38:04] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 98/350] Total time: 0:26:12 (0.942 s / it) [11-24 14:38:04] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 98/350] Total time: 0:26:12 (0.942 s / it) [11-24 14:38:04] (/home/user/VAR/train.py , line 276)=> [ep98] (training ) Lm: 6.496 (6.504), Lt: 5.738 (5.753), Acc m&t: 3.38 5.31, Remain: 4 days, 14:23:34, Finish: 2024-11-28 13:01 [11-24 14:38:04] (/home/user/VAR/train.py , line 276)=> [ep98] (training ) Lm: 6.496 (6.504), Lt: 5.738 (5.753), Acc m&t: 3.38 5.31, Remain: 4 days, 14:22:27, Finish: 2024-11-28 13:00 [11-24 14:38:04] (/home/user/VAR/train.py , line 276)=> [ep98] (training ) Lm: 6.496 (6.504), Lt: 5.738 (5.753), Acc m&t: 3.38 5.31, Remain: 4 days, 14:24:26, Finish: 2024-11-28 13:02 [11-24 14:38:04] (/home/user/VAR/train.py , line 276)=> [ep98] (training ) Lm: 6.496 (6.504), Lt: 5.738 (5.753), Acc m&t: 3.38 5.31, Remain: 4 days, 14:21:58, Finish: 2024-11-28 13:00 [11-24 14:38:04] (/home/user/VAR/train.py , line 276)=> [ep98] (training ) Lm: 6.496 (6.504), Lt: 5.738 (5.753), Acc m&t: 3.38 5.31, Remain: 4 days, 14:24:32, Finish: 2024-11-28 13:02 [11-24 14:38:04] (/home/user/VAR/train.py , line 276)=> [ep98] (training ) Lm: 6.496 (6.504), Lt: 5.738 (5.753), Acc m&t: 3.38 5.31, Remain: 4 days, 14:22:05, Finish: 2024-11-28 13:00 [11-24 14:38:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [ 0/1669] eta: 0:25:49 tlr: 0.00019 tnm: 0.22 Lm: 6.502 (6.502) Lt: 5.719 (5.719) Accm: 3.11 (3.11) Acct: 4.88 (4.88) proj_loss: -0.6001 (-0.6001) time: 0.9283 data: 0.0003 [11-24 14:38:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [ 0/1669] eta: 0:26:01 tlr: 0.00019 tnm: 0.22 Lm: 6.566 (6.566) Lt: 5.835 (5.835) Accm: 3.15 (3.15) Acct: 4.88 (4.88) proj_loss: -0.5964 (-0.5964) time: 0.9355 data: 0.0003 [11-24 14:38:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [ 0/1669] eta: 0:25:32 tlr: 0.00019 tnm: 0.22 Lm: 6.586 (6.586) Lt: 5.757 (5.757) Accm: 3.06 (3.06) Acct: 4.83 (4.83) proj_loss: -0.5963 (-0.5963) time: 0.9180 data: 0.0004 [11-24 14:38:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [ 0/1669] eta: 0:25:56 tlr: 0.00019 tnm: 0.22 Lm: 6.647 (6.647) Lt: 5.903 (5.903) Accm: 3.17 (3.17) Acct: 5.19 (5.19) proj_loss: -0.6037 (-0.6037) time: 0.9324 data: 0.0003 [11-24 14:38:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [ 0/1669] eta: 0:25:56 tlr: 0.00019 tnm: 0.22 Lm: 6.276 (6.276) Lt: 5.526 (5.526) Accm: 4.48 (4.48) Acct: 6.71 (6.71) proj_loss: -0.5961 (-0.5961) time: 0.9325 data: 0.0004 [11-24 14:38:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [ 0/1669] eta: 0:25:56 tlr: 0.00019 tnm: 0.22 Lm: 6.367 (6.367) Lt: 5.557 (5.557) Accm: 3.56 (3.56) Acct: 5.63 (5.63) proj_loss: -0.5891 (-0.5891) time: 0.9328 data: 0.0004 [11-24 14:44:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [ 417/1669] eta: 0:20:34 tlr: 0.00019 tnm: 0.21 Lm: 6.345 (6.345) Lt: 5.544 (5.544) Accm: 3.80 (3.80) Acct: 5.98 (5.98) proj_loss: -0.6186 (-0.6186) time: 0.9405 data: 0.0003 [11-24 14:44:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [ 417/1669] eta: 0:20:34 tlr: 0.00019 tnm: 0.21 Lm: 6.514 (6.514) Lt: 5.814 (5.814) Accm: 3.31 (3.31) Acct: 5.05 (5.05) proj_loss: -0.6093 (-0.6093) time: 0.9404 data: 0.0003 [11-24 14:44:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [ 417/1669] eta: 0:20:34 tlr: 0.00019 tnm: 0.21 Lm: 6.599 (6.599) Lt: 5.828 (5.828) Accm: 2.85 (2.85) Acct: 4.53 (4.53) proj_loss: -0.5848 (-0.5848) time: 0.9405 data: 0.0002 [11-24 14:44:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [ 417/1669] eta: 0:20:34 tlr: 0.00019 tnm: 0.21 Lm: 6.554 (6.554) Lt: 5.691 (5.691) Accm: 3.25 (3.25) Acct: 5.17 (5.17) proj_loss: -0.5985 (-0.5985) time: 0.9404 data: 0.0002 [11-24 14:44:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [ 417/1669] eta: 0:20:34 tlr: 0.00019 tnm: 0.21 Lm: 6.364 (6.364) Lt: 5.599 (5.599) Accm: 4.00 (4.00) Acct: 6.07 (6.07) proj_loss: -0.5948 (-0.5948) time: 0.9404 data: 0.0003 [11-24 14:44:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [ 417/1669] eta: 0:20:34 tlr: 0.00019 tnm: 0.21 Lm: 6.568 (6.568) Lt: 5.820 (5.820) Accm: 3.26 (3.26) Acct: 5.09 (5.09) proj_loss: -0.6020 (-0.6020) time: 0.9405 data: 0.0003 [11-24 14:51:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [ 834/1669] eta: 0:13:24 tlr: 0.00019 tnm: 0.22 Lm: 6.489 (6.523) Lt: 5.738 (5.747) Accm: 3.34 (3.40) Acct: 5.19 (5.40) proj_loss: -0.6003 (-0.5996) time: 0.9415 data: 0.0002 [11-24 14:51:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [ 834/1669] eta: 0:13:24 tlr: 0.00019 tnm: 0.22 Lm: 6.558 (6.585) Lt: 5.879 (5.845) Accm: 3.11 (2.97) Acct: 4.60 (4.55) proj_loss: -0.6001 (-0.5957) time: 0.9415 data: 0.0002 [11-24 14:51:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [ 834/1669] eta: 0:13:24 tlr: 0.00019 tnm: 0.22 Lm: 6.367 (6.385) Lt: 5.557 (5.629) Accm: 3.57 (3.73) Acct: 5.63 (5.70) proj_loss: -0.6208 (-0.6193) time: 0.9415 data: 0.0003 [11-24 14:51:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [ 834/1669] eta: 0:13:24 tlr: 0.00019 tnm: 0.22 Lm: 6.543 (6.524) Lt: 5.824 (5.817) Accm: 3.15 (3.25) Acct: 4.88 (4.97) proj_loss: -0.6030 (-0.6072) time: 0.9415 data: 0.0003 [11-24 14:51:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [ 834/1669] eta: 0:13:24 tlr: 0.00019 tnm: 0.22 Lm: 6.453 (6.420) Lt: 5.673 (5.663) Accm: 3.52 (3.73) Acct: 5.42 (5.72) proj_loss: -0.5935 (-0.5907) time: 0.9415 data: 0.0003 [11-24 14:51:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [ 834/1669] eta: 0:13:24 tlr: 0.00019 tnm: 0.22 Lm: 6.586 (6.584) Lt: 5.757 (5.739) Accm: 3.06 (3.15) Acct: 4.83 (5.04) proj_loss: -0.5963 (-0.5884) time: 0.9415 data: 0.0003 [11-24 14:58:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [1251/1669] eta: 0:06:39 tlr: 0.00018 tnm: 0.22 Lm: 6.579 (6.581) Lt: 5.772 (5.751) Accm: 3.07 (3.13) Acct: 4.89 (5.02) proj_loss: -0.5912 (-0.5879) time: 0.9427 data: 0.0003 [11-24 14:58:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [1251/1669] eta: 0:06:39 tlr: 0.00018 tnm: 0.22 Lm: 6.484 (6.444) Lt: 5.690 (5.674) Accm: 3.39 (3.61) Acct: 5.38 (5.62) proj_loss: -0.5889 (-0.5891) time: 0.9427 data: 0.0003 [11-24 14:58:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [1251/1669] eta: 0:06:39 tlr: 0.00018 tnm: 0.22 Lm: 6.503 (6.477) Lt: 5.808 (5.746) Accm: 3.31 (3.39) Acct: 5.05 (5.19) proj_loss: -0.6044 (-0.6069) time: 0.9427 data: 0.0003 [11-24 14:58:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [1251/1669] eta: 0:06:39 tlr: 0.00018 tnm: 0.22 Lm: 6.564 (6.552) Lt: 5.819 (5.785) Accm: 3.26 (3.28) Acct: 5.09 (5.18) proj_loss: -0.5975 (-0.5961) time: 0.9427 data: 0.0003 [11-24 14:58:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [1251/1669] eta: 0:06:39 tlr: 0.00018 tnm: 0.22 Lm: 6.530 (6.550) Lt: 5.799 (5.802) Accm: 3.16 (3.12) Acct: 4.74 (4.82) proj_loss: -0.6045 (-0.5990) time: 0.9427 data: 0.0002 [11-24 14:58:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [1251/1669] eta: 0:06:39 tlr: 0.00018 tnm: 0.22 Lm: 6.417 (6.411) Lt: 5.617 (5.641) Accm: 3.80 (3.80) Acct: 5.98 (5.95) proj_loss: -0.6159 (-0.6173) time: 0.9426 data: 0.0003 [11-24 15:04:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.417 (6.412) Lt: 5.673 (5.647) Accm: 3.57 (3.76) Acct: 5.66 (5.89) proj_loss: -0.6117 (-0.6161) time: 0.9423 data: 0.0017 [11-24 15:04:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 99/350] Total time: 0:26:29 (0.952 s / it) [11-24 15:04:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.558 (6.555) Lt: 5.832 (5.808) Accm: 3.11 (3.09) Acct: 4.70 (4.79) proj_loss: -0.6089 (-0.6028) time: 0.9423 data: 0.0018 [11-24 15:04:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.515 (6.470) Lt: 5.707 (5.707) Accm: 3.37 (3.56) Acct: 5.42 (5.63) proj_loss: -0.5935 (-0.5919) time: 0.9423 data: 0.0016 [11-24 15:04:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.620 (6.565) Lt: 5.900 (5.810) Accm: 3.17 (3.24) Acct: 4.98 (5.12) proj_loss: -0.5948 (-0.5945) time: 0.9423 data: 0.0016 [11-24 15:04:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.536 (6.489) Lt: 5.824 (5.762) Accm: 3.15 (3.34) Acct: 4.88 (5.08) proj_loss: -0.6059 (-0.6102) time: 0.9423 data: 0.0016 [11-24 15:04:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 99/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.572 (6.578) Lt: 5.788 (5.766) Accm: 3.06 (3.10) Acct: 4.83 (4.96) proj_loss: -0.5963 (-0.5907) time: 0.9423 data: 0.0014 [11-24 15:04:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 99/350] Total time: 0:26:29 (0.952 s / it) [11-24 15:04:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 99/350] Total time: 0:26:29 (0.952 s / it) [11-24 15:04:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 99/350] Total time: 0:26:29 (0.952 s / it) [11-24 15:04:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 99/350] Total time: 0:26:29 (0.952 s / it) [11-24 15:04:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 99/350] Total time: 0:26:29 (0.952 s / it) [11-24 15:09:40] (home/user/VAR/trainer.py, line 114)=> FID: 3.7060169866437036 [11-24 15:09:41] (/home/user/VAR/train.py , line 259)=> [*] [ep99] (val 50000) Lm: 6.5127, Lt: 5.7604, Acc m&t: 3.37 5.29, Val cost: 307.60s [11-24 15:09:41] (/home/user/VAR/train.py , line 264)=> [saving ckpt] ... [saving ckpt](*) finished! @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth [11-24 15:10:47] (/home/user/VAR/train.py , line 276)=> [ep99] (training ) Lm: 6.496 (6.513), Lt: 5.738 (5.760), Acc m&t: 3.38 5.31, Remain: 4 days, 14:16:23, Finish: 2024-11-28 13:20 [11-24 15:10:47] (/home/user/VAR/train.py , line 276)=> [ep99] (training ) Lm: 6.496 (6.513), Lt: 5.738 (5.760), Acc m&t: 3.38 5.31, Remain: 4 days, 14:19:59, Finish: 2024-11-28 13:24 [11-24 15:10:47] (/home/user/VAR/train.py , line 276)=> [ep99] (training ) Lm: 6.496 (6.513), Lt: 5.738 (5.760), Acc m&t: 3.38 5.31, Remain: 4 days, 14:19:57, Finish: 2024-11-28 13:24 [11-24 15:10:47] (/home/user/VAR/train.py , line 276)=> [ep99] (training ) Lm: 6.496 (6.513), Lt: 5.738 (5.760), Acc m&t: 3.38 5.31, Remain: 4 days, 14:20:12, Finish: 2024-11-28 13:24 [11-24 15:10:47] (/home/user/VAR/train.py , line 276)=> [ep99] (training ) Lm: 6.496 (6.513), Lt: 5.738 (5.760), Acc m&t: 3.38 5.31, Remain: 4 days, 14:16:57, Finish: 2024-11-28 13:21 [11-24 15:10:47] (/home/user/VAR/train.py , line 276)=> [ep99] (training ) Lm: 6.496 (6.513), Lt: 5.738 (5.760), Acc m&t: 3.38 5.31, Remain: 4 days, 14:17:40, Finish: 2024-11-28 13:22 [11-24 15:10:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [ 0/1669] eta: 0:28:11 tlr: 0.00018 tnm: 0.23 Lm: 6.401 (6.401) Lt: 5.668 (5.668) Accm: 3.97 (3.97) Acct: 6.04 (6.04) proj_loss: -0.6099 (-0.6099) time: 1.0137 data: 0.0003 [11-24 15:10:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [ 0/1669] eta: 0:26:24 tlr: 0.00018 tnm: 0.23 Lm: 6.381 (6.381) Lt: 5.615 (5.615) Accm: 3.43 (3.43) Acct: 5.86 (5.86) proj_loss: -0.5847 (-0.5847) time: 0.9492 data: 0.0004 [11-24 15:10:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [ 0/1669] eta: 0:26:24 tlr: 0.00018 tnm: 0.23 Lm: 6.338 (6.338) Lt: 5.499 (5.499) Accm: 3.81 (3.81) Acct: 6.15 (6.15) proj_loss: -0.5941 (-0.5941) time: 0.9497 data: 0.0004 [11-24 15:10:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [ 0/1669] eta: 0:26:25 tlr: 0.00018 tnm: 0.23 Lm: 6.480 (6.480) Lt: 5.769 (5.769) Accm: 3.59 (3.59) Acct: 5.45 (5.45) proj_loss: -0.6056 (-0.6056) time: 0.9498 data: 0.0004 [11-24 15:10:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [ 0/1669] eta: 0:26:24 tlr: 0.00018 tnm: 0.23 Lm: 6.268 (6.268) Lt: 5.507 (5.507) Accm: 4.15 (4.15) Acct: 6.56 (6.56) proj_loss: -0.6107 (-0.6107) time: 0.9496 data: 0.0003 [11-24 15:10:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [ 0/1669] eta: 0:26:25 tlr: 0.00018 tnm: 0.23 Lm: 6.581 (6.581) Lt: 5.860 (5.860) Accm: 3.29 (3.29) Acct: 5.29 (5.29) proj_loss: -0.6071 (-0.6071) time: 0.9499 data: 0.0004 [11-24 15:17:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [ 417/1669] eta: 0:19:39 tlr: 0.00018 tnm: 0.22 Lm: 6.563 (6.563) Lt: 5.819 (5.819) Accm: 3.33 (3.33) Acct: 5.32 (5.32) proj_loss: -0.6003 (-0.6003) time: 0.9403 data: 0.0003 [11-24 15:17:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [ 417/1669] eta: 0:19:39 tlr: 0.00018 tnm: 0.22 Lm: 6.501 (6.501) Lt: 5.711 (5.711) Accm: 3.22 (3.22) Acct: 5.09 (5.09) proj_loss: -0.5977 (-0.5977) time: 0.9403 data: 0.0003 [11-24 15:17:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [ 417/1669] eta: 0:19:39 tlr: 0.00018 tnm: 0.22 Lm: 6.387 (6.387) Lt: 5.578 (5.578) Accm: 3.59 (3.59) Acct: 5.73 (5.73) proj_loss: -0.6036 (-0.6036) time: 0.9403 data: 0.0003 [11-24 15:17:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [ 417/1669] eta: 0:19:39 tlr: 0.00018 tnm: 0.22 Lm: 6.381 (6.381) Lt: 5.602 (5.602) Accm: 3.51 (3.51) Acct: 5.75 (5.75) proj_loss: -0.5918 (-0.5918) time: 0.9403 data: 0.0003 [11-24 15:17:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [ 417/1669] eta: 0:19:39 tlr: 0.00018 tnm: 0.22 Lm: 6.561 (6.561) Lt: 5.826 (5.826) Accm: 3.31 (3.31) Acct: 5.27 (5.27) proj_loss: -0.6056 (-0.6056) time: 0.9403 data: 0.0003 [11-24 15:17:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [ 417/1669] eta: 0:19:39 tlr: 0.00018 tnm: 0.22 Lm: 6.410 (6.410) Lt: 5.644 (5.644) Accm: 3.74 (3.74) Acct: 5.84 (5.84) proj_loss: -0.5954 (-0.5954) time: 0.9403 data: 0.0003 [11-24 15:29:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [ 834/1669] eta: 0:13:06 tlr: 0.00018 tnm: 0.23 Lm: 6.418 (6.443) Lt: 5.668 (5.680) Accm: 3.52 (3.62) Acct: 5.63 (5.67) proj_loss: -0.5852 (-0.5920) time: 0.9415 data: 0.0003 [11-24 15:29:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.23 Lm: 6.382 (6.477) Lt: 5.615 (5.723) Accm: 3.43 (3.29) Acct: 5.63 (5.28) proj_loss: -0.5957 (-0.5931) time: 0.9415 data: 0.0003 [11-24 15:29:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [ 834/1669] eta: 0:13:11 tlr: 0.00018 tnm: 0.23 Lm: 6.544 (6.472) Lt: 5.778 (5.705) Accm: 3.38 (3.45) Acct: 5.35 (5.44) proj_loss: -0.6071 (-0.6040) time: 0.9415 data: 0.0003 [11-24 15:29:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [ 834/1669] eta: 0:13:10 tlr: 0.00018 tnm: 0.23 Lm: 6.563 (6.521) Lt: 5.831 (5.751) Accm: 3.30 (3.25) Acct: 4.75 (4.98) proj_loss: -0.6013 (-0.6005) time: 0.9415 data: 0.0003 [11-24 15:29:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [ 834/1669] eta: 0:13:08 tlr: 0.00018 tnm: 0.23 Lm: 6.506 (6.433) Lt: 5.648 (5.652) Accm: 3.38 (3.52) Acct: 4.98 (5.48) proj_loss: -0.6023 (-0.6032) time: 0.9415 data: 0.0003 [11-24 15:29:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.23 Lm: 6.598 (6.573) Lt: 5.815 (5.822) Accm: 3.04 (3.22) Acct: 5.09 (5.16) proj_loss: -0.6056 (-0.6033) time: 0.9415 data: 0.0003 [11-24 15:36:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [1251/1669] eta: 0:06:33 tlr: 0.00018 tnm: 0.23 Lm: 6.447 (6.451) Lt: 5.689 (5.687) Accm: 3.56 (3.61) Acct: 5.68 (5.69) proj_loss: -0.5976 (-0.5986) time: 0.9428 data: 0.0003 [11-24 15:36:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [1251/1669] eta: 0:06:35 tlr: 0.00018 tnm: 0.23 Lm: 6.563 (6.500) Lt: 5.819 (5.749) Accm: 3.33 (3.30) Acct: 5.32 (5.17) proj_loss: -0.6003 (-0.6002) time: 0.9428 data: 0.0004 [11-24 15:36:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [1251/1669] eta: 0:06:33 tlr: 0.00018 tnm: 0.23 Lm: 6.381 (6.446) Lt: 5.602 (5.673) Accm: 3.51 (3.41) Acct: 5.75 (5.55) proj_loss: -0.5973 (-0.5954) time: 0.9428 data: 0.0003 [11-24 15:36:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [1251/1669] eta: 0:06:33 tlr: 0.00018 tnm: 0.23 Lm: 6.554 (6.557) Lt: 5.792 (5.797) Accm: 3.11 (3.21) Acct: 5.01 (5.04) proj_loss: -0.6048 (-0.6035) time: 0.9428 data: 0.0002 [11-24 15:36:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.23 Lm: 6.583 (6.542) Lt: 5.865 (5.788) Accm: 3.17 (3.19) Acct: 4.64 (4.86) proj_loss: -0.6023 (-0.6013) time: 0.9428 data: 0.0003 [11-24 15:36:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.23 Lm: 6.516 (6.465) Lt: 5.724 (5.689) Accm: 3.31 (3.45) Acct: 5.20 (5.47) proj_loss: -0.6065 (-0.6083) time: 0.9428 data: 0.0003 [11-24 15:42:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.526 (6.516) Lt: 5.800 (5.740) Accm: 3.23 (3.33) Acct: 4.98 (5.28) proj_loss: -0.6107 (-0.6090) time: 0.9452 data: 0.0017 [11-24 15:42:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 100/350] Total time: 0:32:00 (1.150 s / it) [11-24 15:42:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.439 (6.449) Lt: 5.668 (5.679) Accm: 3.52 (3.59) Acct: 5.63 (5.64) proj_loss: -0.6099 (-0.6009) time: 0.9452 data: 0.0018 [11-24 15:42:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.563 (6.502) Lt: 5.831 (5.738) Accm: 3.30 (3.30) Acct: 4.75 (5.17) proj_loss: -0.6013 (-0.5931) time: 0.9452 data: 0.0021 [11-24 15:42:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.581 (6.528) Lt: 5.860 (5.779) Accm: 3.29 (3.20) Acct: 5.29 (5.03) proj_loss: -0.5935 (-0.5932) time: 0.9452 data: 0.0017 [11-24 15:42:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.382 (6.475) Lt: 5.615 (5.699) Accm: 3.43 (3.38) Acct: 5.63 (5.45) proj_loss: -0.5988 (-0.5970) time: 0.9452 data: 0.0020 [11-24 15:42:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 100/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.509 (6.546) Lt: 5.769 (5.777) Accm: 3.07 (3.18) Acct: 5.09 (5.07) proj_loss: -0.6056 (-0.6061) time: 0.9452 data: 0.0018 [11-24 15:42:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 100/350] Total time: 0:32:00 (1.150 s / it) [11-24 15:42:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 100/350] Total time: 0:32:00 (1.150 s / it) [11-24 15:42:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 100/350] Total time: 0:32:00 (1.150 s / it) [11-24 15:42:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 100/350] Total time: 0:32:00 (1.150 s / it) [11-24 15:42:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 100/350] Total time: 0:32:00 (1.150 s / it) [11-24 15:42:47] (/home/user/VAR/train.py , line 276)=> [ep100] (training ) Lm: 6.496 (6.517), Lt: 5.738 (5.760), Acc m&t: 3.38 5.31, Remain: 4 days, 13:56:12, Finish: 2024-11-28 13:38 [11-24 15:42:47] (/home/user/VAR/train.py , line 276)=> [ep100] (training ) Lm: 6.496 (6.517), Lt: 5.738 (5.760), Acc m&t: 3.38 5.31, Remain: 4 days, 13:59:13, Finish: 2024-11-28 13:42 [11-24 15:42:47] (/home/user/VAR/train.py , line 276)=> [ep100] (training ) Lm: 6.496 (6.517), Lt: 5.738 (5.760), Acc m&t: 3.38 5.31, Remain: 4 days, 13:55:46, Finish: 2024-11-28 13:38 [11-24 15:42:47] (/home/user/VAR/train.py , line 276)=> [ep100] (training ) Lm: 6.496 (6.517), Lt: 5.738 (5.760), Acc m&t: 3.38 5.31, Remain: 4 days, 13:58:22, Finish: 2024-11-28 13:41 [11-24 15:42:47] (/home/user/VAR/train.py , line 276)=> [ep100] (training ) Lm: 6.496 (6.517), Lt: 5.738 (5.760), Acc m&t: 3.38 5.31, Remain: 4 days, 13:56:28, Finish: 2024-11-28 13:39 [11-24 15:42:47] (/home/user/VAR/train.py , line 276)=> [ep100] (training ) Lm: 6.496 (6.517), Lt: 5.738 (5.760), Acc m&t: 3.38 5.31, Remain: 4 days, 13:58:19, Finish: 2024-11-28 13:41 [11-24 15:42:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [ 0/1669] eta: 0:25:01 tlr: 0.00018 tnm: 0.22 Lm: 6.548 (6.548) Lt: 5.843 (5.843) Accm: 3.26 (3.26) Acct: 4.98 (4.98) proj_loss: -0.6032 (-0.6032) time: 0.8999 data: 0.0004 [11-24 15:42:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [ 0/1669] eta: 0:25:02 tlr: 0.00018 tnm: 0.22 Lm: 6.421 (6.421) Lt: 5.629 (5.629) Accm: 3.61 (3.61) Acct: 5.27 (5.27) proj_loss: -0.6016 (-0.6016) time: 0.9000 data: 0.0004 [11-24 15:42:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [ 0/1669] eta: 0:25:02 tlr: 0.00018 tnm: 0.22 Lm: 6.467 (6.467) Lt: 5.733 (5.733) Accm: 3.91 (3.91) Acct: 6.25 (6.25) proj_loss: -0.6141 (-0.6141) time: 0.9001 data: 0.0004 [11-24 15:42:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [ 0/1669] eta: 0:25:02 tlr: 0.00018 tnm: 0.22 Lm: 6.484 (6.484) Lt: 5.682 (5.682) Accm: 3.34 (3.34) Acct: 5.22 (5.22) proj_loss: -0.5808 (-0.5808) time: 0.9003 data: 0.0003 [11-24 15:42:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [ 0/1669] eta: 0:25:03 tlr: 0.00018 tnm: 0.22 Lm: 6.523 (6.523) Lt: 5.792 (5.792) Accm: 3.23 (3.23) Acct: 5.24 (5.24) proj_loss: -0.6113 (-0.6113) time: 0.9007 data: 0.0003 [11-24 15:42:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [ 0/1669] eta: 0:25:12 tlr: 0.00018 tnm: 0.22 Lm: 6.584 (6.584) Lt: 5.892 (5.892) Accm: 3.57 (3.57) Acct: 5.60 (5.60) proj_loss: -0.6105 (-0.6105) time: 0.9065 data: 0.0004 [11-24 15:49:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.23 Lm: 6.542 (6.542) Lt: 5.821 (5.821) Accm: 3.38 (3.38) Acct: 5.40 (5.40) proj_loss: -0.6132 (-0.6132) time: 0.9413 data: 0.0003 [11-24 15:49:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.23 Lm: 6.576 (6.576) Lt: 5.843 (5.843) Accm: 3.10 (3.10) Acct: 4.84 (4.84) proj_loss: -0.6029 (-0.6029) time: 0.9413 data: 0.0003 [11-24 15:49:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.23 Lm: 6.423 (6.423) Lt: 5.687 (5.687) Accm: 3.90 (3.90) Acct: 5.95 (5.95) proj_loss: -0.6172 (-0.6172) time: 0.9413 data: 0.0003 [11-24 15:49:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.23 Lm: 6.391 (6.391) Lt: 5.618 (5.618) Accm: 3.74 (3.74) Acct: 5.68 (5.68) proj_loss: -0.6039 (-0.6039) time: 0.9413 data: 0.0002 [11-24 15:49:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.23 Lm: 6.439 (6.439) Lt: 5.710 (5.710) Accm: 3.44 (3.44) Acct: 5.27 (5.27) proj_loss: -0.5895 (-0.5895) time: 0.9414 data: 0.0002 [11-24 15:49:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.23 Lm: 6.548 (6.548) Lt: 5.805 (5.805) Accm: 3.19 (3.19) Acct: 5.04 (5.04) proj_loss: -0.5943 (-0.5943) time: 0.9414 data: 0.0003 [11-24 15:56:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [ 834/1669] eta: 0:13:13 tlr: 0.00018 tnm: 0.23 Lm: 6.523 (6.491) Lt: 5.792 (5.749) Accm: 3.23 (3.35) Acct: 5.24 (5.39) proj_loss: -0.6065 (-0.5983) time: 0.9438 data: 0.0003 [11-24 15:56:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [ 834/1669] eta: 0:13:13 tlr: 0.00018 tnm: 0.23 Lm: 6.548 (6.518) Lt: 5.843 (5.751) Accm: 3.26 (3.33) Acct: 4.98 (5.34) proj_loss: -0.6026 (-0.5988) time: 0.9437 data: 0.0003 [11-24 15:56:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [ 834/1669] eta: 0:13:13 tlr: 0.00018 tnm: 0.23 Lm: 6.467 (6.458) Lt: 5.733 (5.702) Accm: 3.88 (3.58) Acct: 5.66 (5.59) proj_loss: -0.6141 (-0.6032) time: 0.9437 data: 0.0003 [11-24 15:56:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [ 834/1669] eta: 0:13:13 tlr: 0.00018 tnm: 0.23 Lm: 6.421 (6.417) Lt: 5.629 (5.652) Accm: 3.61 (3.57) Acct: 5.27 (5.37) proj_loss: -0.6058 (-0.6045) time: 0.9437 data: 0.0003 [11-24 15:56:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [ 834/1669] eta: 0:13:13 tlr: 0.00018 tnm: 0.23 Lm: 6.393 (6.410) Lt: 5.682 (5.675) Accm: 3.54 (3.73) Acct: 5.32 (5.60) proj_loss: -0.5982 (-0.6004) time: 0.9437 data: 0.0003 [11-24 15:56:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [ 834/1669] eta: 0:13:13 tlr: 0.00018 tnm: 0.23 Lm: 6.584 (6.592) Lt: 5.892 (5.866) Accm: 3.18 (3.15) Acct: 5.19 (5.05) proj_loss: -0.6105 (-0.6077) time: 0.9438 data: 0.0003 [11-24 16:02:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [1251/1669] eta: 0:06:38 tlr: 0.00018 tnm: 0.23 Lm: 6.497 (6.518) Lt: 5.734 (5.752) Accm: 3.42 (3.35) Acct: 5.26 (5.29) proj_loss: -0.5997 (-0.5987) time: 1.1365 data: 0.0003 [11-24 16:02:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [1251/1669] eta: 0:06:38 tlr: 0.00018 tnm: 0.23 Lm: 6.576 (6.586) Lt: 5.858 (5.856) Accm: 3.26 (3.20) Acct: 5.00 (4.99) proj_loss: -0.6035 (-0.5991) time: 1.1365 data: 0.0003 [11-24 16:02:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [1251/1669] eta: 0:06:38 tlr: 0.00018 tnm: 0.23 Lm: 6.445 (6.461) Lt: 5.674 (5.716) Accm: 3.42 (3.40) Acct: 5.01 (5.15) proj_loss: -0.6060 (-0.6058) time: 1.1365 data: 0.0003 [11-24 16:02:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [1251/1669] eta: 0:06:38 tlr: 0.00018 tnm: 0.23 Lm: 6.439 (6.501) Lt: 5.710 (5.777) Accm: 3.44 (3.52) Acct: 5.27 (5.37) proj_loss: -0.6097 (-0.6056) time: 1.1365 data: 0.0002 [11-24 16:02:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [1251/1669] eta: 0:06:38 tlr: 0.00018 tnm: 0.23 Lm: 6.474 (6.483) Lt: 5.730 (5.718) Accm: 3.49 (3.43) Acct: 5.42 (5.47) proj_loss: -0.5966 (-0.5955) time: 1.1365 data: 0.0003 [11-24 16:02:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [1251/1669] eta: 0:06:38 tlr: 0.00018 tnm: 0.23 Lm: 6.450 (6.463) Lt: 5.715 (5.710) Accm: 3.39 (3.40) Acct: 5.51 (5.49) proj_loss: -0.6089 (-0.6039) time: 1.1365 data: 0.0003 [11-24 16:09:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.523 (6.512) Lt: 5.792 (5.762) Accm: 3.23 (3.30) Acct: 5.24 (5.32) proj_loss: -0.6065 (-0.5976) time: 0.9472 data: 0.0016 [11-24 16:09:14] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 101/350] Total time: 0:26:26 (0.951 s / it) [11-24 16:09:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.467 (6.500) Lt: 5.733 (5.741) Accm: 3.46 (3.37) Acct: 5.04 (5.24) proj_loss: -0.6141 (-0.6060) time: 0.9472 data: 0.0016 [11-24 16:09:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.510 (6.489) Lt: 5.688 (5.712) Accm: 3.58 (3.46) Acct: 5.86 (5.57) proj_loss: -0.5994 (-0.5963) time: 0.9472 data: 0.0014 [11-24 16:09:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.568 (6.569) Lt: 5.838 (5.852) Accm: 3.34 (3.26) Acct: 5.19 (5.05) proj_loss: -0.6105 (-0.6038) time: 0.9472 data: 0.0018 [11-24 16:09:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.455 (6.492) Lt: 5.738 (5.771) Accm: 3.54 (3.53) Acct: 5.22 (5.34) proj_loss: -0.6211 (-0.6105) time: 0.9472 data: 0.0017 [11-24 16:09:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 101/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.448 (6.459) Lt: 5.663 (5.705) Accm: 3.52 (3.42) Acct: 5.27 (5.23) proj_loss: -0.6058 (-0.5991) time: 0.9472 data: 0.0019 [11-24 16:09:14] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 101/350] Total time: 0:26:26 (0.951 s / it) [11-24 16:09:14] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 101/350] Total time: 0:26:26 (0.951 s / it) [11-24 16:09:14] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 101/350] Total time: 0:26:26 (0.951 s / it) [11-24 16:09:14] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 101/350] Total time: 0:26:26 (0.951 s / it) [11-24 16:09:14] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 101/350] Total time: 0:26:26 (0.951 s / it) [11-24 16:09:14] (/home/user/VAR/train.py , line 276)=> [ep101] (training ) Lm: 6.496 (6.505), Lt: 5.738 (5.752), Acc m&t: 3.40 5.34, Remain: 4 days, 13:37:04, Finish: 2024-11-28 13:46 [11-24 16:09:14] (/home/user/VAR/train.py , line 276)=> [ep101] (training ) Lm: 6.496 (6.505), Lt: 5.738 (5.752), Acc m&t: 3.40 5.34, Remain: 4 days, 13:34:51, Finish: 2024-11-28 13:44 [11-24 16:09:14] (/home/user/VAR/train.py , line 276)=> [ep101] (training ) Lm: 6.496 (6.505), Lt: 5.738 (5.752), Acc m&t: 3.40 5.34, Remain: 4 days, 13:36:37, Finish: 2024-11-28 13:45 [11-24 16:09:14] (/home/user/VAR/train.py , line 276)=> [ep101] (training ) Lm: 6.496 (6.505), Lt: 5.738 (5.752), Acc m&t: 3.40 5.34, Remain: 4 days, 13:35:41, Finish: 2024-11-28 13:44 [11-24 16:09:14] (/home/user/VAR/train.py , line 276)=> [ep101] (training ) Lm: 6.496 (6.505), Lt: 5.738 (5.752), Acc m&t: 3.40 5.34, Remain: 4 days, 13:34:33, Finish: 2024-11-28 13:43 [11-24 16:09:14] (/home/user/VAR/train.py , line 276)=> [ep101] (training ) Lm: 6.496 (6.505), Lt: 5.738 (5.752), Acc m&t: 3.40 5.34, Remain: 4 days, 13:34:33, Finish: 2024-11-28 13:43 [11-24 16:09:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [ 0/1669] eta: 0:25:44 tlr: 0.00018 tnm: 0.23 Lm: 6.570 (6.570) Lt: 5.792 (5.792) Accm: 3.16 (3.16) Acct: 5.11 (5.11) proj_loss: -0.5820 (-0.5820) time: 0.9255 data: 0.0004 [11-24 16:09:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [ 0/1669] eta: 0:25:46 tlr: 0.00018 tnm: 0.23 Lm: 6.471 (6.471) Lt: 5.605 (5.605) Accm: 3.79 (3.79) Acct: 6.22 (6.22) proj_loss: -0.5911 (-0.5911) time: 0.9264 data: 0.0003 [11-24 16:09:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [ 0/1669] eta: 0:25:37 tlr: 0.00018 tnm: 0.23 Lm: 6.641 (6.641) Lt: 5.903 (5.903) Accm: 2.80 (2.80) Acct: 4.52 (4.52) proj_loss: -0.5914 (-0.5914) time: 0.9213 data: 0.0004 [11-24 16:09:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [ 0/1669] eta: 0:25:46 tlr: 0.00018 tnm: 0.23 Lm: 6.598 (6.598) Lt: 5.877 (5.877) Accm: 2.94 (2.94) Acct: 4.47 (4.47) proj_loss: -0.6001 (-0.6001) time: 0.9269 data: 0.0004 [11-24 16:09:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [ 0/1669] eta: 0:25:38 tlr: 0.00018 tnm: 0.23 Lm: 6.768 (6.768) Lt: 6.043 (6.043) Accm: 2.56 (2.56) Acct: 3.64 (3.64) proj_loss: -0.6039 (-0.6039) time: 0.9218 data: 0.0004 [11-24 16:09:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [ 0/1669] eta: 0:25:47 tlr: 0.00018 tnm: 0.23 Lm: 6.472 (6.472) Lt: 5.749 (5.749) Accm: 2.68 (2.68) Acct: 4.26 (4.26) proj_loss: -0.5976 (-0.5976) time: 0.9272 data: 0.0003 [11-24 16:15:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.23 Lm: 6.439 (6.439) Lt: 5.677 (5.677) Accm: 3.35 (3.35) Acct: 5.38 (5.38) proj_loss: -0.6029 (-0.6029) time: 0.9436 data: 0.0003 [11-24 16:15:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.23 Lm: 6.507 (6.507) Lt: 5.766 (5.766) Accm: 3.43 (3.43) Acct: 5.44 (5.44) proj_loss: -0.5995 (-0.5995) time: 0.9437 data: 0.0002 [11-24 16:15:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.23 Lm: 6.495 (6.495) Lt: 5.638 (5.638) Accm: 3.45 (3.45) Acct: 5.81 (5.81) proj_loss: -0.5890 (-0.5890) time: 0.9437 data: 0.0003 [11-24 16:15:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.23 Lm: 6.616 (6.616) Lt: 5.879 (5.879) Accm: 3.10 (3.10) Acct: 4.61 (4.61) proj_loss: -0.5955 (-0.5955) time: 0.9436 data: 0.0003 [11-24 16:15:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.23 Lm: 6.528 (6.528) Lt: 5.775 (5.775) Accm: 3.22 (3.22) Acct: 4.88 (4.88) proj_loss: -0.5820 (-0.5820) time: 0.9437 data: 0.0003 [11-24 16:15:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.23 Lm: 6.520 (6.520) Lt: 5.786 (5.786) Accm: 3.14 (3.14) Acct: 5.07 (5.07) proj_loss: -0.6005 (-0.6005) time: 0.9437 data: 0.0003 [11-24 16:22:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.23 Lm: 6.509 (6.508) Lt: 5.740 (5.739) Accm: 3.16 (3.30) Acct: 5.11 (5.16) proj_loss: -0.5869 (-0.5953) time: 0.9454 data: 0.0002 [11-24 16:22:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.23 Lm: 6.465 (6.550) Lt: 5.715 (5.793) Accm: 3.64 (3.29) Acct: 5.58 (5.08) proj_loss: -0.6039 (-0.6042) time: 0.9453 data: 0.0003 [11-24 16:22:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.23 Lm: 6.472 (6.500) Lt: 5.749 (5.756) Accm: 3.19 (3.30) Acct: 5.09 (5.29) proj_loss: -0.5976 (-0.5983) time: 0.9453 data: 0.0004 [11-24 16:22:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.23 Lm: 6.519 (6.516) Lt: 5.671 (5.679) Accm: 3.25 (3.38) Acct: 5.40 (5.62) proj_loss: -0.5887 (-0.5889) time: 0.9453 data: 0.0003 [11-24 16:22:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.23 Lm: 6.539 (6.532) Lt: 5.808 (5.786) Accm: 3.34 (3.26) Acct: 5.29 (5.06) proj_loss: -0.5742 (-0.5794) time: 0.9454 data: 0.0003 [11-24 16:22:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.23 Lm: 6.442 (6.494) Lt: 5.675 (5.749) Accm: 3.32 (3.20) Acct: 5.14 (5.10) proj_loss: -0.6096 (-0.6047) time: 0.9455 data: 0.0003 [11-24 16:28:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.22 Lm: 6.458 (6.489) Lt: 5.674 (5.730) Accm: 3.40 (3.28) Acct: 5.38 (5.26) proj_loss: -0.6073 (-0.6047) time: 0.9449 data: 0.0003 [11-24 16:28:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.22 Lm: 6.461 (6.488) Lt: 5.681 (5.720) Accm: 3.35 (3.35) Acct: 5.51 (5.45) proj_loss: -0.6029 (-0.6025) time: 0.9449 data: 0.0003 [11-24 16:28:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.22 Lm: 6.476 (6.447) Lt: 5.713 (5.682) Accm: 3.43 (3.46) Acct: 5.44 (5.40) proj_loss: -0.5985 (-0.5990) time: 0.9449 data: 0.0002 [11-24 16:28:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.22 Lm: 6.499 (6.546) Lt: 5.750 (5.791) Accm: 3.42 (3.27) Acct: 5.45 (5.14) proj_loss: -0.5955 (-0.5965) time: 0.9449 data: 0.0003 [11-24 16:28:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.22 Lm: 6.538 (6.560) Lt: 5.716 (5.762) Accm: 3.17 (3.26) Acct: 5.32 (5.35) proj_loss: -0.5899 (-0.5897) time: 0.9449 data: 0.0003 [11-24 16:28:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.22 Lm: 6.499 (6.488) Lt: 5.741 (5.734) Accm: 3.43 (3.42) Acct: 5.36 (5.33) proj_loss: -0.5871 (-0.5899) time: 0.9449 data: 0.0003 [11-24 16:35:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.519 (6.547) Lt: 5.754 (5.760) Accm: 3.16 (3.24) Acct: 5.24 (5.26) proj_loss: -0.5911 (-0.5945) time: 0.9445 data: 0.0016 [11-24 16:35:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.534 (6.563) Lt: 5.784 (5.804) Accm: 3.20 (3.22) Acct: 5.32 (5.01) proj_loss: -0.6039 (-0.5995) time: 0.9445 data: 0.0016 [11-24 16:35:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.509 (6.463) Lt: 5.740 (5.724) Accm: 3.16 (3.37) Acct: 5.11 (5.19) proj_loss: -0.6102 (-0.6081) time: 0.9445 data: 0.0016 [11-24 16:35:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.450 (6.461) Lt: 5.614 (5.668) Accm: 3.45 (3.37) Acct: 5.63 (5.49) proj_loss: -0.5976 (-0.6000) time: 0.9445 data: 0.0015 [11-24 16:35:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.539 (6.520) Lt: 5.808 (5.772) Accm: 3.34 (3.36) Acct: 5.29 (5.22) proj_loss: -0.5946 (-0.5908) time: 0.9445 data: 0.0018 [11-24 16:35:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 102/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.442 (6.472) Lt: 5.675 (5.724) Accm: 3.49 (3.41) Acct: 5.63 (5.38) proj_loss: -0.6096 (-0.6071) time: 0.9445 data: 0.0018 [11-24 16:35:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 102/350] Total time: 0:26:14 (0.943 s / it) [11-24 16:35:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 102/350] Total time: 0:26:14 (0.943 s / it) [11-24 16:35:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 102/350] Total time: 0:26:14 (0.943 s / it) [11-24 16:35:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 102/350] Total time: 0:26:14 (0.943 s / it) [11-24 16:35:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 102/350] Total time: 0:26:14 (0.943 s / it) [11-24 16:35:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 102/350] Total time: 0:26:14 (0.943 s / it) [11-24 16:35:29] (/home/user/VAR/train.py , line 276)=> [ep102] (training ) Lm: 6.496 (6.503), Lt: 5.738 (5.745), Acc m&t: 3.40 5.34, Remain: 4 days, 12:59:35, Finish: 2024-11-28 13:35 [11-24 16:35:29] (/home/user/VAR/train.py , line 276)=> [ep102] (training ) Lm: 6.496 (6.503), Lt: 5.738 (5.745), Acc m&t: 3.40 5.34, Remain: 4 days, 12:58:32, Finish: 2024-11-28 13:34 [11-24 16:35:29] (/home/user/VAR/train.py , line 276)=> [ep102] (training ) Lm: 6.496 (6.503), Lt: 5.738 (5.745), Acc m&t: 3.40 5.34, Remain: 4 days, 12:58:10, Finish: 2024-11-28 13:33 [11-24 16:35:29] (/home/user/VAR/train.py , line 276)=> [ep102] (training ) Lm: 6.496 (6.503), Lt: 5.738 (5.745), Acc m&t: 3.40 5.34, Remain: 4 days, 12:58:45, Finish: 2024-11-28 13:34 [11-24 16:35:29] (/home/user/VAR/train.py , line 276)=> [ep102] (training ) Lm: 6.496 (6.503), Lt: 5.738 (5.745), Acc m&t: 3.40 5.34, Remain: 4 days, 12:58:28, Finish: 2024-11-28 13:33 [11-24 16:35:29] (/home/user/VAR/train.py , line 276)=> [ep102] (training ) Lm: 6.496 (6.503), Lt: 5.738 (5.745), Acc m&t: 3.40 5.34, Remain: 4 days, 12:58:42, Finish: 2024-11-28 13:34 [11-24 16:35:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [ 0/1669] eta: 0:25:31 tlr: 0.00018 tnm: 0.22 Lm: 6.589 (6.589) Lt: 5.845 (5.845) Accm: 3.39 (3.39) Acct: 5.29 (5.29) proj_loss: -0.6178 (-0.6178) time: 0.9177 data: 0.0004 [11-24 16:35:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [ 0/1669] eta: 0:25:33 tlr: 0.00018 tnm: 0.22 Lm: 6.490 (6.490) Lt: 5.727 (5.727) Accm: 3.49 (3.49) Acct: 5.45 (5.45) proj_loss: -0.6163 (-0.6163) time: 0.9190 data: 0.0004 [11-24 16:35:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [ 0/1669] eta: 0:25:33 tlr: 0.00018 tnm: 0.22 Lm: 6.427 (6.427) Lt: 5.621 (5.621) Accm: 3.59 (3.59) Acct: 5.73 (5.73) proj_loss: -0.5971 (-0.5971) time: 0.9188 data: 0.0003 [11-24 16:35:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [ 0/1669] eta: 0:25:33 tlr: 0.00018 tnm: 0.22 Lm: 6.613 (6.613) Lt: 5.870 (5.870) Accm: 3.08 (3.08) Acct: 4.73 (4.73) proj_loss: -0.5971 (-0.5971) time: 0.9191 data: 0.0004 [11-24 16:35:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [ 0/1669] eta: 0:25:34 tlr: 0.00018 tnm: 0.22 Lm: 6.508 (6.508) Lt: 5.831 (5.831) Accm: 3.35 (3.35) Acct: 4.93 (4.93) proj_loss: -0.5885 (-0.5885) time: 0.9191 data: 0.0004 [11-24 16:35:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [ 0/1669] eta: 0:25:34 tlr: 0.00018 tnm: 0.22 Lm: 6.671 (6.671) Lt: 5.971 (5.971) Accm: 2.99 (2.99) Acct: 4.73 (4.73) proj_loss: -0.6020 (-0.6020) time: 0.9193 data: 0.0003 [11-24 16:42:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [ 417/1669] eta: 0:20:18 tlr: 0.00018 tnm: 0.23 Lm: 6.568 (6.568) Lt: 5.828 (5.828) Accm: 3.50 (3.50) Acct: 5.54 (5.54) proj_loss: -0.6184 (-0.6184) time: 0.9433 data: 0.0002 [11-24 16:42:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [ 417/1669] eta: 0:20:18 tlr: 0.00018 tnm: 0.23 Lm: 6.479 (6.479) Lt: 5.698 (5.698) Accm: 3.23 (3.23) Acct: 5.18 (5.18) proj_loss: -0.5945 (-0.5945) time: 0.9434 data: 0.0003 [11-24 16:42:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [ 417/1669] eta: 0:20:18 tlr: 0.00018 tnm: 0.23 Lm: 6.508 (6.508) Lt: 5.761 (5.761) Accm: 3.29 (3.29) Acct: 5.24 (5.24) proj_loss: -0.6003 (-0.6003) time: 0.9434 data: 0.0003 [11-24 16:42:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [ 417/1669] eta: 0:20:18 tlr: 0.00018 tnm: 0.23 Lm: 6.594 (6.594) Lt: 5.859 (5.859) Accm: 3.32 (3.32) Acct: 5.26 (5.26) proj_loss: -0.6068 (-0.6068) time: 0.9434 data: 0.0003 [11-24 16:42:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [ 417/1669] eta: 0:20:18 tlr: 0.00018 tnm: 0.23 Lm: 6.471 (6.471) Lt: 5.689 (5.689) Accm: 3.48 (3.48) Acct: 5.58 (5.58) proj_loss: -0.5992 (-0.5992) time: 0.9434 data: 0.0003 [11-24 16:42:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [ 417/1669] eta: 0:20:18 tlr: 0.00018 tnm: 0.23 Lm: 6.505 (6.505) Lt: 5.805 (5.805) Accm: 3.30 (3.30) Acct: 5.04 (5.04) proj_loss: -0.5842 (-0.5842) time: 0.9434 data: 0.0003 [11-24 16:48:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [ 834/1669] eta: 0:13:20 tlr: 0.00018 tnm: 0.21 Lm: 6.508 (6.509) Lt: 5.780 (5.797) Accm: 3.28 (3.29) Acct: 4.93 (4.99) proj_loss: -0.5885 (-0.5889) time: 0.9421 data: 0.0003 [11-24 16:48:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [ 834/1669] eta: 0:13:20 tlr: 0.00018 tnm: 0.21 Lm: 6.546 (6.504) Lt: 5.812 (5.770) Accm: 3.42 (3.47) Acct: 5.29 (5.41) proj_loss: -0.6191 (-0.6239) time: 0.9421 data: 0.0002 [11-24 16:48:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [ 834/1669] eta: 0:13:20 tlr: 0.00018 tnm: 0.21 Lm: 6.488 (6.502) Lt: 5.697 (5.740) Accm: 3.16 (3.25) Acct: 4.73 (5.07) proj_loss: -0.6034 (-0.6067) time: 0.9421 data: 0.0003 [11-24 16:48:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [ 834/1669] eta: 0:13:20 tlr: 0.00018 tnm: 0.21 Lm: 6.532 (6.548) Lt: 5.776 (5.788) Accm: 2.86 (3.10) Acct: 4.62 (4.82) proj_loss: -0.5919 (-0.5908) time: 0.9421 data: 0.0003 [11-24 16:48:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [ 834/1669] eta: 0:13:20 tlr: 0.00018 tnm: 0.21 Lm: 6.490 (6.560) Lt: 5.727 (5.780) Accm: 3.47 (3.23) Acct: 5.45 (5.31) proj_loss: -0.5897 (-0.5961) time: 0.9421 data: 0.0003 [11-24 16:48:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [ 834/1669] eta: 0:13:20 tlr: 0.00018 tnm: 0.21 Lm: 6.518 (6.488) Lt: 5.748 (5.720) Accm: 3.64 (3.42) Acct: 5.79 (5.50) proj_loss: -0.6020 (-0.5985) time: 0.9421 data: 0.0003 [11-24 16:55:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [1251/1669] eta: 0:06:38 tlr: 0.00018 tnm: 0.23 Lm: 6.594 (6.560) Lt: 5.859 (5.803) Accm: 3.32 (3.22) Acct: 5.26 (5.12) proj_loss: -0.5920 (-0.5942) time: 0.9437 data: 0.0003 [11-24 16:55:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [1251/1669] eta: 0:06:38 tlr: 0.00018 tnm: 0.23 Lm: 6.462 (6.472) Lt: 5.737 (5.743) Accm: 3.51 (3.58) Acct: 5.54 (5.52) proj_loss: -0.6184 (-0.6195) time: 0.9437 data: 0.0003 [11-24 16:55:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [1251/1669] eta: 0:06:38 tlr: 0.00018 tnm: 0.23 Lm: 6.597 (6.576) Lt: 5.843 (5.819) Accm: 2.89 (3.05) Acct: 4.60 (4.76) proj_loss: -0.5900 (-0.5901) time: 0.9438 data: 0.0003 [11-24 16:55:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [1251/1669] eta: 0:06:38 tlr: 0.00018 tnm: 0.23 Lm: 6.505 (6.499) Lt: 5.779 (5.757) Accm: 3.26 (3.25) Acct: 5.02 (5.02) proj_loss: -0.5904 (-0.5897) time: 0.9438 data: 0.0002 [11-24 16:55:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [1251/1669] eta: 0:06:38 tlr: 0.00018 tnm: 0.23 Lm: 6.540 (6.524) Lt: 5.757 (5.759) Accm: 3.12 (3.16) Acct: 4.73 (4.93) proj_loss: -0.6003 (-0.6022) time: 0.9438 data: 0.0002 [11-24 16:55:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [1251/1669] eta: 0:06:38 tlr: 0.00018 tnm: 0.23 Lm: 6.523 (6.559) Lt: 5.732 (5.769) Accm: 3.34 (3.22) Acct: 5.23 (5.24) proj_loss: -0.5989 (-0.5990) time: 0.9437 data: 0.0003 [11-24 17:01:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.556 (6.565) Lt: 5.736 (5.786) Accm: 3.20 (3.18) Acct: 5.01 (5.16) proj_loss: -0.6080 (-0.6034) time: 0.9416 data: 0.0016 [11-24 17:01:55] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 103/350] Total time: 0:26:26 (0.951 s / it) [11-24 17:01:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.532 (6.525) Lt: 5.776 (5.753) Accm: 2.92 (3.28) Acct: 4.62 (5.10) proj_loss: -0.5919 (-0.5922) time: 0.9416 data: 0.0016 [11-24 17:01:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.546 (6.507) Lt: 5.812 (5.770) Accm: 3.42 (3.44) Acct: 5.29 (5.38) proj_loss: -0.6178 (-0.6170) time: 0.9416 data: 0.0014 [11-24 17:01:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.488 (6.513) Lt: 5.697 (5.746) Accm: 3.16 (3.26) Acct: 4.73 (5.08) proj_loss: -0.6034 (-0.6030) time: 0.9416 data: 0.0019 [11-24 17:01:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.658 (6.580) Lt: 5.894 (5.822) Accm: 2.99 (3.04) Acct: 4.73 (4.86) proj_loss: -0.5920 (-0.5938) time: 0.9416 data: 0.0017 [11-24 17:01:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 103/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.502 (6.481) Lt: 5.779 (5.731) Accm: 3.28 (3.37) Acct: 5.11 (5.24) proj_loss: -0.5923 (-0.5962) time: 0.9416 data: 0.0018 [11-24 17:01:55] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 103/350] Total time: 0:26:26 (0.951 s / it) [11-24 17:01:55] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 103/350] Total time: 0:26:26 (0.951 s / it) [11-24 17:01:55] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 103/350] Total time: 0:26:26 (0.951 s / it) [11-24 17:01:55] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 103/350] Total time: 0:26:26 (0.951 s / it) [11-24 17:01:55] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 103/350] Total time: 0:26:26 (0.951 s / it) [11-24 17:01:55] (/home/user/VAR/train.py , line 276)=> [ep103] (training ) Lm: 6.492 (6.492), Lt: 5.738 (5.738), Acc m&t: 3.40 5.35, Remain: 4 days, 12:29:05, Finish: 2024-11-28 13:31 [11-24 17:01:55] (/home/user/VAR/train.py , line 276)=> [ep103] (training ) Lm: 6.492 (6.492), Lt: 5.738 (5.738), Acc m&t: 3.40 5.35, Remain: 4 days, 12:30:59, Finish: 2024-11-28 13:32 [11-24 17:01:55] (/home/user/VAR/train.py , line 276)=> [ep103] (training ) Lm: 6.492 (6.492), Lt: 5.738 (5.738), Acc m&t: 3.40 5.35, Remain: 4 days, 12:31:33, Finish: 2024-11-28 13:33 [11-24 17:01:55] (/home/user/VAR/train.py , line 276)=> [ep103] (training ) Lm: 6.492 (6.492), Lt: 5.738 (5.738), Acc m&t: 3.40 5.35, Remain: 4 days, 12:30:56, Finish: 2024-11-28 13:32 [11-24 17:01:55] (/home/user/VAR/train.py , line 276)=> [ep103] (training ) Lm: 6.492 (6.492), Lt: 5.738 (5.738), Acc m&t: 3.40 5.35, Remain: 4 days, 12:30:05, Finish: 2024-11-28 13:32 [11-24 17:01:55] (/home/user/VAR/train.py , line 276)=> [ep103] (training ) Lm: 6.492 (6.492), Lt: 5.738 (5.738), Acc m&t: 3.40 5.35, Remain: 4 days, 12:31:45, Finish: 2024-11-28 13:33 [11-24 17:01:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [ 0/1669] eta: 0:25:25 tlr: 0.00018 tnm: 0.22 Lm: 6.442 (6.442) Lt: 5.666 (5.666) Accm: 3.06 (3.06) Acct: 4.86 (4.86) proj_loss: -0.6008 (-0.6008) time: 0.9142 data: 0.0004 [11-24 17:01:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [ 0/1669] eta: 0:25:26 tlr: 0.00018 tnm: 0.22 Lm: 6.351 (6.351) Lt: 5.537 (5.537) Accm: 3.79 (3.79) Acct: 5.81 (5.81) proj_loss: -0.6179 (-0.6179) time: 0.9144 data: 0.0003 [11-24 17:01:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [ 0/1669] eta: 0:25:26 tlr: 0.00018 tnm: 0.22 Lm: 6.356 (6.356) Lt: 5.585 (5.585) Accm: 3.89 (3.89) Acct: 6.12 (6.12) proj_loss: -0.6026 (-0.6026) time: 0.9148 data: 0.0004 [11-24 17:01:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [ 0/1669] eta: 0:25:27 tlr: 0.00018 tnm: 0.22 Lm: 6.544 (6.544) Lt: 5.774 (5.774) Accm: 3.21 (3.21) Acct: 4.96 (4.96) proj_loss: -0.5890 (-0.5890) time: 0.9152 data: 0.0004 [11-24 17:01:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [ 0/1669] eta: 0:25:26 tlr: 0.00018 tnm: 0.22 Lm: 6.531 (6.531) Lt: 5.793 (5.793) Accm: 3.29 (3.29) Acct: 5.37 (5.37) proj_loss: -0.6339 (-0.6339) time: 0.9148 data: 0.0003 [11-24 17:01:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [ 0/1669] eta: 0:25:28 tlr: 0.00018 tnm: 0.22 Lm: 6.271 (6.271) Lt: 5.481 (5.481) Accm: 4.02 (4.02) Acct: 6.59 (6.59) proj_loss: -0.6422 (-0.6422) time: 0.9157 data: 0.0004 [11-24 17:08:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.22 Lm: 6.546 (6.546) Lt: 5.829 (5.829) Accm: 3.06 (3.06) Acct: 4.83 (4.83) proj_loss: -0.6116 (-0.6116) time: 0.9434 data: 0.0002 [11-24 17:08:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.22 Lm: 6.410 (6.410) Lt: 5.618 (5.618) Accm: 3.70 (3.70) Acct: 5.81 (5.81) proj_loss: -0.6165 (-0.6165) time: 0.9434 data: 0.0003 [11-24 17:08:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.22 Lm: 6.417 (6.417) Lt: 5.648 (5.648) Accm: 3.67 (3.67) Acct: 5.67 (5.67) proj_loss: -0.5979 (-0.5979) time: 0.9434 data: 0.0003 [11-24 17:08:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.22 Lm: 6.307 (6.307) Lt: 5.537 (5.537) Accm: 3.78 (3.78) Acct: 5.99 (5.99) proj_loss: -0.6170 (-0.6170) time: 0.9434 data: 0.0003 [11-24 17:08:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.22 Lm: 6.410 (6.410) Lt: 5.638 (5.638) Accm: 3.69 (3.69) Acct: 5.75 (5.75) proj_loss: -0.5917 (-0.5917) time: 0.9434 data: 0.0003 [11-24 17:08:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.22 Lm: 6.561 (6.561) Lt: 5.833 (5.833) Accm: 3.21 (3.21) Acct: 5.02 (5.02) proj_loss: -0.6301 (-0.6301) time: 0.9434 data: 0.0003 [11-24 17:15:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [ 834/1669] eta: 0:13:20 tlr: 0.00018 tnm: 0.21 Lm: 6.531 (6.520) Lt: 5.793 (5.775) Accm: 3.29 (3.30) Acct: 5.37 (5.23) proj_loss: -0.6263 (-0.6260) time: 0.9450 data: 0.0003 [11-24 17:15:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [ 834/1669] eta: 0:13:20 tlr: 0.00018 tnm: 0.21 Lm: 6.351 (6.370) Lt: 5.583 (5.607) Accm: 3.79 (3.81) Acct: 5.81 (5.91) proj_loss: -0.6152 (-0.6139) time: 0.9450 data: 0.0003 [11-24 17:15:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [ 834/1669] eta: 0:13:20 tlr: 0.00018 tnm: 0.21 Lm: 6.544 (6.455) Lt: 5.774 (5.706) Accm: 3.34 (3.58) Acct: 5.40 (5.63) proj_loss: -0.5890 (-0.5886) time: 0.9450 data: 0.0003 [11-24 17:15:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [ 834/1669] eta: 0:13:20 tlr: 0.00018 tnm: 0.21 Lm: 6.343 (6.376) Lt: 5.593 (5.624) Accm: 3.54 (3.70) Acct: 5.48 (5.82) proj_loss: -0.6130 (-0.6157) time: 0.9450 data: 0.0003 [11-24 17:15:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [ 834/1669] eta: 0:13:20 tlr: 0.00018 tnm: 0.21 Lm: 6.478 (6.442) Lt: 5.711 (5.690) Accm: 3.44 (3.54) Acct: 5.32 (5.55) proj_loss: -0.6026 (-0.6038) time: 0.9451 data: 0.0003 [11-24 17:15:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [ 834/1669] eta: 0:13:20 tlr: 0.00018 tnm: 0.21 Lm: 6.650 (6.599) Lt: 5.991 (5.888) Accm: 3.06 (2.91) Acct: 4.80 (4.68) proj_loss: -0.6008 (-0.6055) time: 0.9451 data: 0.0002 [11-24 17:21:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [1251/1669] eta: 0:06:38 tlr: 0.00018 tnm: 0.23 Lm: 6.546 (6.554) Lt: 5.851 (5.843) Accm: 3.06 (3.12) Acct: 4.83 (5.03) proj_loss: -0.5970 (-0.6024) time: 0.9444 data: 0.0002 [11-24 17:21:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [1251/1669] eta: 0:06:38 tlr: 0.00018 tnm: 0.23 Lm: 6.486 (6.495) Lt: 5.742 (5.764) Accm: 3.37 (3.34) Acct: 5.27 (5.20) proj_loss: -0.6062 (-0.6053) time: 0.9444 data: 0.0002 [11-24 17:21:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [1251/1669] eta: 0:06:38 tlr: 0.00018 tnm: 0.23 Lm: 6.451 (6.431) Lt: 5.719 (5.695) Accm: 3.68 (3.69) Acct: 5.66 (5.70) proj_loss: -0.5917 (-0.5949) time: 0.9444 data: 0.0003 [11-24 17:21:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [1251/1669] eta: 0:06:38 tlr: 0.00018 tnm: 0.23 Lm: 6.410 (6.434) Lt: 5.642 (5.674) Accm: 3.70 (3.72) Acct: 5.91 (5.93) proj_loss: -0.6119 (-0.6123) time: 0.9444 data: 0.0003 [11-24 17:21:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [1251/1669] eta: 0:06:38 tlr: 0.00018 tnm: 0.23 Lm: 6.484 (6.482) Lt: 5.726 (5.733) Accm: 3.39 (3.41) Acct: 5.27 (5.21) proj_loss: -0.6221 (-0.6210) time: 0.9444 data: 0.0003 [11-24 17:21:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [1251/1669] eta: 0:06:38 tlr: 0.00018 tnm: 0.23 Lm: 6.429 (6.413) Lt: 5.693 (5.666) Accm: 3.54 (3.52) Acct: 5.44 (5.57) proj_loss: -0.6146 (-0.6158) time: 0.9444 data: 0.0003 [11-24 17:28:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.21 Lm: 6.515 (6.458) Lt: 5.793 (5.722) Accm: 3.54 (3.45) Acct: 5.40 (5.46) proj_loss: -0.6130 (-0.6136) time: 0.9441 data: 0.0017 [11-24 17:28:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 104/350] Total time: 0:26:38 (0.958 s / it) [11-24 17:28:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.21 Lm: 6.484 (6.492) Lt: 5.773 (5.766) Accm: 3.30 (3.32) Acct: 5.22 (5.20) proj_loss: -0.6099 (-0.6084) time: 0.9441 data: 0.0015 [11-24 17:28:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.21 Lm: 6.544 (6.484) Lt: 5.774 (5.731) Accm: 3.34 (3.52) Acct: 5.40 (5.57) proj_loss: -0.5900 (-0.5939) time: 0.9441 data: 0.0019 [11-24 17:28:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.21 Lm: 6.469 (6.473) Lt: 5.700 (5.716) Accm: 3.61 (3.56) Acct: 5.81 (5.68) proj_loss: -0.6087 (-0.6082) time: 0.9441 data: 0.0016 [11-24 17:28:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.21 Lm: 6.650 (6.583) Lt: 5.991 (5.885) Accm: 3.06 (3.10) Acct: 4.80 (4.97) proj_loss: -0.5933 (-0.5988) time: 0.9441 data: 0.0020 [11-24 17:28:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 104/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.21 Lm: 6.442 (6.474) Lt: 5.707 (5.728) Accm: 3.49 (3.44) Acct: 5.37 (5.32) proj_loss: -0.6179 (-0.6134) time: 0.9441 data: 0.0018 [11-24 17:28:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 104/350] Total time: 0:26:38 (0.958 s / it) [11-24 17:28:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 104/350] Total time: 0:26:38 (0.958 s / it) [11-24 17:28:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 104/350] Total time: 0:26:38 (0.958 s / it) [11-24 17:28:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 104/350] Total time: 0:26:38 (0.958 s / it) [11-24 17:28:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 104/350] Total time: 0:26:38 (0.958 s / it) [11-24 17:28:33] (/home/user/VAR/train.py , line 276)=> [ep104] (training ) Lm: 6.492 (6.507), Lt: 5.738 (5.756), Acc m&t: 3.40 5.35, Remain: 4 days, 12:10:08, Finish: 2024-11-28 13:38 [11-24 17:28:33] (/home/user/VAR/train.py , line 276)=> [ep104] (training ) Lm: 6.492 (6.507), Lt: 5.738 (5.756), Acc m&t: 3.40 5.35, Remain: 4 days, 12:09:15, Finish: 2024-11-28 13:37 [11-24 17:28:33] (/home/user/VAR/train.py , line 276)=> [ep104] (training ) Lm: 6.492 (6.507), Lt: 5.738 (5.756), Acc m&t: 3.40 5.35, Remain: 4 days, 12:11:57, Finish: 2024-11-28 13:40 [11-24 17:28:33] (/home/user/VAR/train.py , line 276)=> [ep104] (training ) Lm: 6.492 (6.507), Lt: 5.738 (5.756), Acc m&t: 3.40 5.35, Remain: 4 days, 12:12:47, Finish: 2024-11-28 13:41 [11-24 17:28:33] (/home/user/VAR/train.py , line 276)=> [ep104] (training ) Lm: 6.492 (6.507), Lt: 5.738 (5.756), Acc m&t: 3.40 5.35, Remain: 4 days, 12:14:20, Finish: 2024-11-28 13:42 [11-24 17:28:33] (/home/user/VAR/train.py , line 276)=> [ep104] (training ) Lm: 6.492 (6.507), Lt: 5.738 (5.756), Acc m&t: 3.40 5.35, Remain: 4 days, 12:09:47, Finish: 2024-11-28 13:38 [11-24 17:28:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [ 0/1669] eta: 0:25:34 tlr: 0.00018 tnm: 0.22 Lm: 6.416 (6.416) Lt: 5.716 (5.716) Accm: 3.80 (3.80) Acct: 5.73 (5.73) proj_loss: -0.6291 (-0.6291) time: 0.9193 data: 0.0003 [11-24 17:28:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [ 0/1669] eta: 0:25:35 tlr: 0.00018 tnm: 0.22 Lm: 6.616 (6.616) Lt: 5.773 (5.773) Accm: 3.03 (3.03) Acct: 5.19 (5.19) proj_loss: -0.5875 (-0.5875) time: 0.9202 data: 0.0004 [11-24 17:28:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [ 0/1669] eta: 0:25:36 tlr: 0.00018 tnm: 0.22 Lm: 6.224 (6.224) Lt: 5.449 (5.449) Accm: 4.15 (4.15) Acct: 6.64 (6.64) proj_loss: -0.6017 (-0.6017) time: 0.9206 data: 0.0004 [11-24 17:28:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [ 0/1669] eta: 0:25:36 tlr: 0.00018 tnm: 0.22 Lm: 6.639 (6.639) Lt: 5.921 (5.921) Accm: 3.27 (3.27) Acct: 5.22 (5.22) proj_loss: -0.6203 (-0.6203) time: 0.9206 data: 0.0003 [11-24 17:28:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [ 0/1669] eta: 0:25:37 tlr: 0.00018 tnm: 0.22 Lm: 6.511 (6.511) Lt: 5.751 (5.751) Accm: 3.34 (3.34) Acct: 5.19 (5.19) proj_loss: -0.5807 (-0.5807) time: 0.9210 data: 0.0004 [11-24 17:28:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [ 0/1669] eta: 0:25:37 tlr: 0.00018 tnm: 0.22 Lm: 6.703 (6.703) Lt: 6.046 (6.046) Accm: 3.06 (3.06) Acct: 4.47 (4.47) proj_loss: -0.6417 (-0.6417) time: 0.9213 data: 0.0004 [11-24 17:35:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.22 Lm: 6.575 (6.575) Lt: 5.873 (5.873) Accm: 3.34 (3.34) Acct: 5.07 (5.07) proj_loss: -0.6231 (-0.6231) time: 0.9407 data: 0.0003 [11-24 17:35:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.22 Lm: 6.528 (6.528) Lt: 5.808 (5.808) Accm: 3.52 (3.52) Acct: 5.46 (5.46) proj_loss: -0.6140 (-0.6140) time: 0.9407 data: 0.0003 [11-24 17:35:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.22 Lm: 6.633 (6.633) Lt: 5.913 (5.913) Accm: 3.07 (3.07) Acct: 4.93 (4.93) proj_loss: -0.6198 (-0.6198) time: 0.9407 data: 0.0002 [11-24 17:35:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.22 Lm: 6.519 (6.519) Lt: 5.728 (5.728) Accm: 3.35 (3.35) Acct: 5.62 (5.62) proj_loss: -0.6018 (-0.6018) time: 0.9407 data: 0.0003 [11-24 17:35:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.22 Lm: 6.392 (6.392) Lt: 5.670 (5.670) Accm: 3.70 (3.70) Acct: 5.85 (5.85) proj_loss: -0.6108 (-0.6108) time: 0.9407 data: 0.0003 [11-24 17:35:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.22 Lm: 6.565 (6.565) Lt: 5.818 (5.818) Accm: 3.19 (3.19) Acct: 4.91 (4.91) proj_loss: -0.6008 (-0.6008) time: 0.9407 data: 0.0003 [11-24 17:41:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.23 Lm: 6.528 (6.553) Lt: 5.751 (5.788) Accm: 3.34 (3.32) Acct: 5.19 (5.14) proj_loss: -0.5935 (-0.5984) time: 0.9435 data: 0.0003 [11-24 17:41:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.23 Lm: 6.469 (6.508) Lt: 5.716 (5.763) Accm: 3.42 (3.49) Acct: 5.35 (5.42) proj_loss: -0.5988 (-0.6087) time: 0.9435 data: 0.0002 [11-24 17:41:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.23 Lm: 6.559 (6.466) Lt: 5.820 (5.720) Accm: 3.25 (3.50) Acct: 5.06 (5.46) proj_loss: -0.6017 (-0.6072) time: 0.9435 data: 0.0003 [11-24 17:41:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.23 Lm: 6.628 (6.570) Lt: 5.906 (5.836) Accm: 3.27 (3.23) Acct: 5.22 (5.23) proj_loss: -0.6193 (-0.6178) time: 0.9435 data: 0.0002 [11-24 17:41:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.23 Lm: 6.464 (6.538) Lt: 5.709 (5.818) Accm: 3.55 (3.41) Acct: 5.68 (5.31) proj_loss: -0.6281 (-0.6248) time: 0.9435 data: 0.0003 [11-24 17:41:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.23 Lm: 6.423 (6.462) Lt: 5.683 (5.663) Accm: 3.68 (3.58) Acct: 6.04 (5.83) proj_loss: -0.6162 (-0.6067) time: 0.9435 data: 0.0003 [11-24 17:48:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.22 Lm: 6.468 (6.475) Lt: 5.704 (5.679) Accm: 3.64 (3.59) Acct: 6.02 (5.87) proj_loss: -0.6155 (-0.6087) time: 0.9421 data: 0.0003 [11-24 17:48:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.22 Lm: 6.442 (6.482) Lt: 5.700 (5.744) Accm: 3.59 (3.56) Acct: 5.50 (5.48) proj_loss: -0.5984 (-0.6033) time: 0.9422 data: 0.0002 [11-24 17:48:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.22 Lm: 6.577 (6.498) Lt: 5.813 (5.741) Accm: 3.25 (3.44) Acct: 5.10 (5.38) proj_loss: -0.6008 (-0.6047) time: 0.9421 data: 0.0003 [11-24 17:48:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.22 Lm: 6.536 (6.528) Lt: 5.794 (5.777) Accm: 3.38 (3.30) Acct: 5.33 (5.28) proj_loss: -0.6166 (-0.6135) time: 0.9421 data: 0.0003 [11-24 17:48:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.22 Lm: 6.538 (6.551) Lt: 5.778 (5.792) Accm: 3.45 (3.38) Acct: 5.40 (5.28) proj_loss: -0.5871 (-0.5939) time: 0.9421 data: 0.0003 [11-24 17:48:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.22 Lm: 6.569 (6.572) Lt: 5.824 (5.849) Accm: 3.31 (3.23) Acct: 5.07 (5.04) proj_loss: -0.6163 (-0.6169) time: 0.9422 data: 0.0003 [11-24 17:54:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.464 (6.540) Lt: 5.709 (5.801) Accm: 3.55 (3.33) Acct: 5.68 (5.27) proj_loss: -0.6050 (-0.6145) time: 0.9457 data: 0.0018 [11-24 17:54:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 105/350] Total time: 0:26:14 (0.943 s / it) [11-24 17:54:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.559 (6.494) Lt: 5.805 (5.742) Accm: 3.26 (3.53) Acct: 5.14 (5.45) proj_loss: -0.5999 (-0.6025) time: 0.9456 data: 0.0016 [11-24 17:54:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.423 (6.463) Lt: 5.683 (5.647) Accm: 3.59 (3.51) Acct: 5.99 (5.74) proj_loss: -0.6149 (-0.6060) time: 0.9456 data: 0.0018 [11-24 17:54:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.444 (6.508) Lt: 5.693 (5.760) Accm: 3.27 (3.29) Acct: 5.24 (5.27) proj_loss: -0.6139 (-0.6112) time: 0.9456 data: 0.0019 [11-24 17:54:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.418 (6.469) Lt: 5.716 (5.741) Accm: 3.42 (3.53) Acct: 5.35 (5.41) proj_loss: -0.5988 (-0.6082) time: 0.9457 data: 0.0016 [11-24 17:54:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 105/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.528 (6.495) Lt: 5.751 (5.734) Accm: 3.56 (3.51) Acct: 5.60 (5.49) proj_loss: -0.5935 (-0.6012) time: 0.9457 data: 0.0019 [11-24 17:54:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 105/350] Total time: 0:26:14 (0.943 s / it) [11-24 17:54:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 105/350] Total time: 0:26:14 (0.943 s / it) [11-24 17:54:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 105/350] Total time: 0:26:14 (0.943 s / it) [11-24 17:54:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 105/350] Total time: 0:26:14 (0.943 s / it) [11-24 17:54:48] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 105/350] Total time: 0:26:14 (0.943 s / it) [11-24 17:54:48] (/home/user/VAR/train.py , line 276)=> [ep105] (training ) Lm: 6.492 (6.498), Lt: 5.738 (5.740), Acc m&t: 3.40 5.35, Remain: 4 days, 11:46:26, Finish: 2024-11-28 13:41 [11-24 17:54:48] (/home/user/VAR/train.py , line 276)=> [ep105] (training ) Lm: 6.492 (6.498), Lt: 5.738 (5.740), Acc m&t: 3.40 5.35, Remain: 4 days, 11:45:46, Finish: 2024-11-28 13:40 [11-24 17:54:48] (/home/user/VAR/train.py , line 276)=> [ep105] (training ) Lm: 6.492 (6.498), Lt: 5.738 (5.740), Acc m&t: 3.40 5.35, Remain: 4 days, 11:46:00, Finish: 2024-11-28 13:40 [11-24 17:54:48] (/home/user/VAR/train.py , line 276)=> [ep105] (training ) Lm: 6.492 (6.498), Lt: 5.738 (5.740), Acc m&t: 3.40 5.35, Remain: 4 days, 11:45:37, Finish: 2024-11-28 13:40 [11-24 17:54:48] (/home/user/VAR/train.py , line 276)=> [ep105] (training ) Lm: 6.492 (6.498), Lt: 5.738 (5.740), Acc m&t: 3.40 5.35, Remain: 4 days, 11:45:37, Finish: 2024-11-28 13:40 [11-24 17:54:48] (/home/user/VAR/train.py , line 276)=> [ep105] (training ) Lm: 6.492 (6.498), Lt: 5.738 (5.740), Acc m&t: 3.40 5.35, Remain: 4 days, 11:45:48, Finish: 2024-11-28 13:40 [11-24 17:54:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [ 0/1669] eta: 0:25:25 tlr: 0.00018 tnm: 0.22 Lm: 6.490 (6.490) Lt: 5.791 (5.791) Accm: 3.29 (3.29) Acct: 5.22 (5.22) proj_loss: -0.6003 (-0.6003) time: 0.9143 data: 0.0003 [11-24 17:54:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [ 0/1669] eta: 0:25:26 tlr: 0.00018 tnm: 0.22 Lm: 6.613 (6.613) Lt: 5.804 (5.804) Accm: 3.21 (3.21) Acct: 5.37 (5.37) proj_loss: -0.5999 (-0.5999) time: 0.9146 data: 0.0004 [11-24 17:54:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [ 0/1669] eta: 0:25:27 tlr: 0.00018 tnm: 0.22 Lm: 6.521 (6.521) Lt: 5.733 (5.733) Accm: 3.32 (3.32) Acct: 5.37 (5.37) proj_loss: -0.6112 (-0.6112) time: 0.9152 data: 0.0004 [11-24 17:54:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [ 0/1669] eta: 0:25:27 tlr: 0.00018 tnm: 0.22 Lm: 6.501 (6.501) Lt: 5.768 (5.768) Accm: 3.40 (3.40) Acct: 5.24 (5.24) proj_loss: -0.6017 (-0.6017) time: 0.9153 data: 0.0004 [11-24 17:54:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [ 0/1669] eta: 0:25:20 tlr: 0.00018 tnm: 0.22 Lm: 6.396 (6.396) Lt: 5.598 (5.598) Accm: 4.17 (4.17) Acct: 6.64 (6.64) proj_loss: -0.5875 (-0.5875) time: 0.9110 data: 0.0004 [11-24 17:54:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [ 0/1669] eta: 0:25:28 tlr: 0.00018 tnm: 0.22 Lm: 6.575 (6.575) Lt: 5.883 (5.883) Accm: 3.00 (3.00) Acct: 4.36 (4.36) proj_loss: -0.5932 (-0.5932) time: 0.9158 data: 0.0004 [11-24 18:01:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [ 417/1669] eta: 0:20:37 tlr: 0.00018 tnm: 0.23 Lm: 6.426 (6.426) Lt: 5.668 (5.668) Accm: 3.52 (3.52) Acct: 5.66 (5.66) proj_loss: -0.5994 (-0.5994) time: 0.9440 data: 0.0003 [11-24 18:01:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [ 417/1669] eta: 0:20:37 tlr: 0.00018 tnm: 0.23 Lm: 6.513 (6.513) Lt: 5.739 (5.739) Accm: 3.33 (3.33) Acct: 5.28 (5.28) proj_loss: -0.6248 (-0.6248) time: 0.9440 data: 0.0003 [11-24 18:01:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [ 417/1669] eta: 0:20:37 tlr: 0.00018 tnm: 0.23 Lm: 6.634 (6.634) Lt: 5.937 (5.937) Accm: 2.86 (2.86) Acct: 4.39 (4.39) proj_loss: -0.5986 (-0.5986) time: 0.9440 data: 0.0003 [11-24 18:01:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [ 417/1669] eta: 0:20:37 tlr: 0.00018 tnm: 0.23 Lm: 6.403 (6.403) Lt: 5.624 (5.624) Accm: 3.73 (3.73) Acct: 5.76 (5.76) proj_loss: -0.6128 (-0.6128) time: 0.9440 data: 0.0003 [11-24 18:01:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [ 417/1669] eta: 0:20:37 tlr: 0.00018 tnm: 0.23 Lm: 6.380 (6.380) Lt: 5.587 (5.587) Accm: 4.07 (4.07) Acct: 6.35 (6.35) proj_loss: -0.5982 (-0.5982) time: 0.9440 data: 0.0003 [11-24 18:01:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [ 417/1669] eta: 0:20:37 tlr: 0.00018 tnm: 0.23 Lm: 6.618 (6.618) Lt: 5.806 (5.806) Accm: 3.17 (3.17) Acct: 5.15 (5.15) proj_loss: -0.6009 (-0.6009) time: 0.9440 data: 0.0003 [11-24 18:08:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [ 834/1669] eta: 0:13:26 tlr: 0.00018 tnm: 0.22 Lm: 6.613 (6.608) Lt: 5.808 (5.842) Accm: 3.12 (3.07) Acct: 4.93 (4.79) proj_loss: -0.6020 (-0.6023) time: 0.9438 data: 0.0003 [11-24 18:08:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [ 834/1669] eta: 0:13:26 tlr: 0.00018 tnm: 0.22 Lm: 6.386 (6.413) Lt: 5.586 (5.641) Accm: 3.73 (3.59) Acct: 5.89 (5.73) proj_loss: -0.6003 (-0.6031) time: 0.9438 data: 0.0002 [11-24 18:08:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [ 834/1669] eta: 0:13:26 tlr: 0.00018 tnm: 0.22 Lm: 6.501 (6.510) Lt: 5.768 (5.771) Accm: 3.40 (3.42) Acct: 5.24 (5.11) proj_loss: -0.6090 (-0.6115) time: 0.9438 data: 0.0003 [11-24 18:08:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [ 834/1669] eta: 0:13:26 tlr: 0.00018 tnm: 0.22 Lm: 6.521 (6.546) Lt: 5.746 (5.784) Accm: 3.32 (3.24) Acct: 5.19 (4.99) proj_loss: -0.6112 (-0.6071) time: 0.9438 data: 0.0003 [11-24 18:08:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [ 834/1669] eta: 0:13:26 tlr: 0.00018 tnm: 0.22 Lm: 6.647 (6.638) Lt: 5.919 (5.931) Accm: 2.93 (2.88) Acct: 4.42 (4.46) proj_loss: -0.5932 (-0.5935) time: 0.9438 data: 0.0003 [11-24 18:08:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [ 834/1669] eta: 0:13:26 tlr: 0.00018 tnm: 0.22 Lm: 6.396 (6.489) Lt: 5.598 (5.686) Accm: 3.97 (3.70) Acct: 6.07 (5.83) proj_loss: -0.5875 (-0.5906) time: 0.9438 data: 0.0003 [11-24 18:14:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [1251/1669] eta: 0:06:40 tlr: 0.00018 tnm: 0.24 Lm: 6.536 (6.525) Lt: 5.792 (5.782) Accm: 3.25 (3.34) Acct: 5.05 (5.04) proj_loss: -0.6066 (-0.6097) time: 0.9474 data: 0.0003 [11-24 18:14:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [1251/1669] eta: 0:06:40 tlr: 0.00018 tnm: 0.24 Lm: 6.524 (6.541) Lt: 5.782 (5.793) Accm: 3.23 (3.22) Acct: 4.95 (4.92) proj_loss: -0.6138 (-0.6094) time: 0.9475 data: 0.0003 [11-24 18:14:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [1251/1669] eta: 0:06:40 tlr: 0.00018 tnm: 0.24 Lm: 6.601 (6.578) Lt: 5.806 (5.813) Accm: 3.17 (3.14) Acct: 5.15 (4.93) proj_loss: -0.6009 (-0.6014) time: 0.9475 data: 0.0003 [11-24 18:14:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [1251/1669] eta: 0:06:40 tlr: 0.00018 tnm: 0.24 Lm: 6.484 (6.510) Lt: 5.724 (5.727) Accm: 3.51 (3.54) Acct: 5.42 (5.54) proj_loss: -0.5946 (-0.5934) time: 0.9475 data: 0.0003 [11-24 18:14:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [1251/1669] eta: 0:06:40 tlr: 0.00018 tnm: 0.24 Lm: 6.432 (6.429) Lt: 5.629 (5.649) Accm: 3.56 (3.54) Acct: 5.88 (5.77) proj_loss: -0.5994 (-0.5988) time: 0.9475 data: 0.0002 [11-24 18:14:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [1251/1669] eta: 0:06:40 tlr: 0.00018 tnm: 0.24 Lm: 6.611 (6.619) Lt: 5.901 (5.896) Accm: 2.97 (3.02) Acct: 4.51 (4.73) proj_loss: -0.5950 (-0.5943) time: 0.9475 data: 0.0003 [11-24 18:21:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.478 (6.464) Lt: 5.672 (5.699) Accm: 3.40 (3.43) Acct: 5.86 (5.55) proj_loss: -0.6003 (-0.6005) time: 0.9477 data: 0.0018 [11-24 18:21:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.575 (6.579) Lt: 5.883 (5.855) Accm: 3.00 (3.20) Acct: 4.60 (4.98) proj_loss: -0.5932 (-0.5928) time: 0.9477 data: 0.0019 [11-24 18:21:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.501 (6.520) Lt: 5.768 (5.769) Accm: 3.40 (3.42) Acct: 5.24 (5.13) proj_loss: -0.6090 (-0.6118) time: 0.9477 data: 0.0016 [11-24 18:21:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.526 (6.594) Lt: 5.819 (5.830) Accm: 3.15 (3.09) Acct: 4.70 (4.78) proj_loss: -0.6112 (-0.6059) time: 0.9477 data: 0.0018 [11-24 18:21:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.589 (6.524) Lt: 5.804 (5.747) Accm: 3.21 (3.29) Acct: 5.37 (5.24) proj_loss: -0.6020 (-0.6021) time: 0.9477 data: 0.0019 [11-24 18:21:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 106/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.571 (6.556) Lt: 5.850 (5.786) Accm: 3.06 (3.41) Acct: 4.91 (5.41) proj_loss: -0.6006 (-0.5948) time: 0.9477 data: 0.0016 [11-24 18:21:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 106/350] Total time: 0:26:34 (0.955 s / it) [11-24 18:21:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 106/350] Total time: 0:26:34 (0.955 s / it) [11-24 18:21:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 106/350] Total time: 0:26:34 (0.955 s / it) [11-24 18:21:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 106/350] Total time: 0:26:34 (0.955 s / it) [11-24 18:21:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 106/350] Total time: 0:26:34 (0.955 s / it) [11-24 18:21:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 106/350] Total time: 0:26:34 (0.955 s / it) [11-24 18:21:22] (/home/user/VAR/train.py , line 276)=> [ep106] (training ) Lm: 6.492 (6.498), Lt: 5.738 (5.744), Acc m&t: 3.40 5.35, Remain: 4 days, 11:25:12, Finish: 2024-11-28 13:46 [11-24 18:21:22] (/home/user/VAR/train.py , line 276)=> [ep106] (training ) Lm: 6.492 (6.498), Lt: 5.738 (5.744), Acc m&t: 3.40 5.35, Remain: 4 days, 11:27:48, Finish: 2024-11-28 13:49 [11-24 18:21:22] (/home/user/VAR/train.py , line 276)=> [ep106] (training ) Lm: 6.492 (6.498), Lt: 5.738 (5.744), Acc m&t: 3.40 5.35, Remain: 4 days, 11:26:53, Finish: 2024-11-28 13:48 [11-24 18:21:22] (/home/user/VAR/train.py , line 276)=> [ep106] (training ) Lm: 6.492 (6.498), Lt: 5.738 (5.744), Acc m&t: 3.40 5.35, Remain: 4 days, 11:27:58, Finish: 2024-11-28 13:49 [11-24 18:21:22] (/home/user/VAR/train.py , line 276)=> [ep106] (training ) Lm: 6.492 (6.498), Lt: 5.738 (5.744), Acc m&t: 3.40 5.35, Remain: 4 days, 11:28:41, Finish: 2024-11-28 13:50 [11-24 18:21:22] (/home/user/VAR/train.py , line 276)=> [ep106] (training ) Lm: 6.492 (6.498), Lt: 5.738 (5.744), Acc m&t: 3.40 5.35, Remain: 4 days, 11:25:41, Finish: 2024-11-28 13:47 [11-24 18:21:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [ 0/1669] eta: 0:25:16 tlr: 0.00018 tnm: 0.21 Lm: 6.357 (6.357) Lt: 5.568 (5.568) Accm: 3.82 (3.82) Acct: 6.04 (6.04) proj_loss: -0.5732 (-0.5732) time: 0.9085 data: 0.0004 [11-24 18:21:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [ 0/1669] eta: 0:25:18 tlr: 0.00018 tnm: 0.21 Lm: 6.240 (6.240) Lt: 5.483 (5.483) Accm: 4.20 (4.20) Acct: 6.71 (6.71) proj_loss: -0.6060 (-0.6060) time: 0.9096 data: 0.0004 [11-24 18:21:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [ 0/1669] eta: 0:25:18 tlr: 0.00018 tnm: 0.21 Lm: 6.617 (6.617) Lt: 5.896 (5.896) Accm: 2.99 (2.99) Acct: 4.78 (4.78) proj_loss: -0.6054 (-0.6054) time: 0.9100 data: 0.0004 [11-24 18:21:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [ 0/1669] eta: 0:25:18 tlr: 0.00018 tnm: 0.21 Lm: 6.213 (6.213) Lt: 5.389 (5.389) Accm: 4.65 (4.65) Acct: 7.28 (7.28) proj_loss: -0.6112 (-0.6112) time: 0.9101 data: 0.0004 [11-24 18:21:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [ 0/1669] eta: 0:25:18 tlr: 0.00018 tnm: 0.21 Lm: 6.287 (6.287) Lt: 5.506 (5.506) Accm: 4.18 (4.18) Acct: 7.21 (7.21) proj_loss: -0.6205 (-0.6205) time: 0.9101 data: 0.0003 [11-24 18:21:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [ 0/1669] eta: 0:25:19 tlr: 0.00018 tnm: 0.21 Lm: 6.598 (6.598) Lt: 5.863 (5.863) Accm: 2.95 (2.95) Acct: 4.44 (4.44) proj_loss: -0.6231 (-0.6231) time: 0.9102 data: 0.0004 [11-24 18:27:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [ 417/1669] eta: 0:19:42 tlr: 0.00018 tnm: 0.22 Lm: 6.429 (6.429) Lt: 5.646 (5.646) Accm: 3.53 (3.53) Acct: 5.51 (5.51) proj_loss: -0.5989 (-0.5989) time: 0.9453 data: 0.0003 [11-24 18:27:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [ 417/1669] eta: 0:19:42 tlr: 0.00018 tnm: 0.22 Lm: 6.531 (6.531) Lt: 5.769 (5.769) Accm: 3.19 (3.19) Acct: 5.18 (5.18) proj_loss: -0.6130 (-0.6130) time: 0.9453 data: 0.0003 [11-24 18:27:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [ 417/1669] eta: 0:19:42 tlr: 0.00018 tnm: 0.22 Lm: 6.456 (6.456) Lt: 5.739 (5.739) Accm: 3.40 (3.40) Acct: 5.18 (5.18) proj_loss: -0.6024 (-0.6024) time: 0.9453 data: 0.0003 [11-24 18:27:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [ 417/1669] eta: 0:19:42 tlr: 0.00018 tnm: 0.22 Lm: 6.483 (6.483) Lt: 5.710 (5.710) Accm: 3.21 (3.21) Acct: 5.17 (5.17) proj_loss: -0.6085 (-0.6085) time: 0.9453 data: 0.0003 [11-24 18:27:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [ 417/1669] eta: 0:19:42 tlr: 0.00018 tnm: 0.22 Lm: 6.432 (6.432) Lt: 5.663 (5.663) Accm: 3.74 (3.74) Acct: 6.29 (6.29) proj_loss: -0.6132 (-0.6132) time: 0.9453 data: 0.0003 [11-24 18:27:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [ 417/1669] eta: 0:19:42 tlr: 0.00018 tnm: 0.22 Lm: 6.324 (6.324) Lt: 5.520 (5.520) Accm: 4.13 (4.13) Acct: 6.46 (6.46) proj_loss: -0.6132 (-0.6132) time: 0.9453 data: 0.0003 [11-24 18:34:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [ 834/1669] eta: 0:13:10 tlr: 0.00018 tnm: 0.22 Lm: 6.429 (6.429) Lt: 5.601 (5.631) Accm: 3.73 (3.60) Acct: 6.04 (5.70) proj_loss: -0.5983 (-0.5987) time: 0.9427 data: 0.0002 [11-24 18:34:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [ 834/1669] eta: 0:13:10 tlr: 0.00018 tnm: 0.22 Lm: 6.562 (6.510) Lt: 5.838 (5.753) Accm: 3.00 (3.14) Acct: 4.78 (4.98) proj_loss: -0.6054 (-0.6072) time: 0.9427 data: 0.0003 [11-24 18:34:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [ 834/1669] eta: 0:13:10 tlr: 0.00018 tnm: 0.22 Lm: 6.340 (6.401) Lt: 5.553 (5.626) Accm: 3.87 (3.78) Acct: 6.15 (6.24) proj_loss: -0.6058 (-0.6054) time: 0.9427 data: 0.0003 [11-24 18:34:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [ 834/1669] eta: 0:13:10 tlr: 0.00018 tnm: 0.22 Lm: 6.358 (6.423) Lt: 5.649 (5.709) Accm: 3.64 (3.48) Acct: 5.40 (5.25) proj_loss: -0.6060 (-0.6077) time: 0.9427 data: 0.0003 [11-24 18:34:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [ 834/1669] eta: 0:13:10 tlr: 0.00018 tnm: 0.22 Lm: 6.435 (6.412) Lt: 5.652 (5.638) Accm: 3.61 (3.82) Acct: 5.63 (6.06) proj_loss: -0.6153 (-0.6157) time: 0.9427 data: 0.0003 [11-24 18:34:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [ 834/1669] eta: 0:13:10 tlr: 0.00018 tnm: 0.22 Lm: 6.551 (6.538) Lt: 5.761 (5.766) Accm: 3.22 (3.20) Acct: 5.24 (5.20) proj_loss: -0.6030 (-0.6057) time: 0.9427 data: 0.0003 [11-24 18:41:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [1251/1669] eta: 0:06:39 tlr: 0.00018 tnm: 0.24 Lm: 6.566 (6.525) Lt: 5.859 (5.785) Accm: 3.00 (3.08) Acct: 4.69 (4.84) proj_loss: -0.6085 (-0.6101) time: 0.9471 data: 0.0003 [11-24 18:41:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [1251/1669] eta: 0:06:39 tlr: 0.00018 tnm: 0.24 Lm: 6.371 (6.401) Lt: 5.635 (5.649) Accm: 3.62 (3.68) Acct: 5.76 (6.00) proj_loss: -0.6132 (-0.6098) time: 0.9471 data: 0.0003 [11-24 18:41:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [1251/1669] eta: 0:06:39 tlr: 0.00018 tnm: 0.24 Lm: 6.465 (6.450) Lt: 5.662 (5.671) Accm: 3.49 (3.40) Acct: 5.51 (5.38) proj_loss: -0.6063 (-0.6026) time: 0.9472 data: 0.0002 [11-24 18:41:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [1251/1669] eta: 0:06:39 tlr: 0.00018 tnm: 0.24 Lm: 6.508 (6.455) Lt: 5.718 (5.684) Accm: 3.32 (3.45) Acct: 5.58 (5.62) proj_loss: -0.6114 (-0.6092) time: 0.9472 data: 0.0003 [11-24 18:41:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [1251/1669] eta: 0:06:39 tlr: 0.00018 tnm: 0.24 Lm: 6.512 (6.482) Lt: 5.763 (5.705) Accm: 3.41 (3.59) Acct: 5.45 (5.72) proj_loss: -0.6132 (-0.6095) time: 0.9472 data: 0.0003 [11-24 18:41:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [1251/1669] eta: 0:06:39 tlr: 0.00018 tnm: 0.24 Lm: 6.484 (6.470) Lt: 5.750 (5.745) Accm: 3.35 (3.38) Acct: 5.11 (5.15) proj_loss: -0.6112 (-0.6098) time: 0.9471 data: 0.0003 [11-24 18:48:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.374 (6.451) Lt: 5.649 (5.712) Accm: 3.64 (3.45) Acct: 5.40 (5.29) proj_loss: -0.6128 (-0.6104) time: 1.0105 data: 0.0016 [11-24 18:48:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 107/350] Total time: 0:26:44 (0.962 s / it) [11-24 18:48:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.429 (6.430) Lt: 5.601 (5.657) Accm: 3.58 (3.44) Acct: 5.11 (5.33) proj_loss: -0.6142 (-0.6061) time: 1.0104 data: 0.0017 [11-24 18:48:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.562 (6.522) Lt: 5.838 (5.775) Accm: 3.00 (3.14) Acct: 4.78 (4.98) proj_loss: -0.6072 (-0.6095) time: 1.0105 data: 0.0015 [11-24 18:48:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.588 (6.506) Lt: 5.818 (5.727) Accm: 3.21 (3.45) Acct: 5.27 (5.50) proj_loss: -0.6112 (-0.6093) time: 1.0105 data: 0.0016 [11-24 18:48:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.402 (6.469) Lt: 5.718 (5.714) Accm: 3.37 (3.48) Acct: 5.37 (5.69) proj_loss: -0.6058 (-0.6037) time: 1.0105 data: 0.0019 [11-24 18:48:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 107/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.22 Lm: 6.465 (6.437) Lt: 5.675 (5.641) Accm: 3.42 (3.48) Acct: 5.91 (5.70) proj_loss: -0.6030 (-0.6015) time: 1.0105 data: 0.0020 [11-24 18:48:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 107/350] Total time: 0:26:44 (0.962 s / it) [11-24 18:48:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 107/350] Total time: 0:26:44 (0.962 s / it) [11-24 18:48:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 107/350] Total time: 0:26:44 (0.962 s / it) [11-24 18:48:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 107/350] Total time: 0:26:44 (0.962 s / it) [11-24 18:48:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 107/350] Total time: 0:26:44 (0.962 s / it) [11-24 18:48:07] (/home/user/VAR/train.py , line 276)=> [ep107] (training ) Lm: 6.492 (6.496), Lt: 5.738 (5.741), Acc m&t: 3.40 5.35, Remain: 4 days, 10:59:40, Finish: 2024-11-28 13:47 [11-24 18:48:07] (/home/user/VAR/train.py , line 276)=> [ep107] (training ) Lm: 6.492 (6.496), Lt: 5.738 (5.741), Acc m&t: 3.40 5.35, Remain: 4 days, 11:01:32, Finish: 2024-11-28 13:49 [11-24 18:48:07] (/home/user/VAR/train.py , line 276)=> [ep107] (training ) Lm: 6.492 (6.496), Lt: 5.738 (5.741), Acc m&t: 3.40 5.35, Remain: 4 days, 11:01:52, Finish: 2024-11-28 13:49 [11-24 18:48:07] (/home/user/VAR/train.py , line 276)=> [ep107] (training ) Lm: 6.492 (6.496), Lt: 5.738 (5.741), Acc m&t: 3.40 5.35, Remain: 4 days, 11:02:00, Finish: 2024-11-28 13:50 [11-24 18:48:07] (/home/user/VAR/train.py , line 276)=> [ep107] (training ) Lm: 6.492 (6.496), Lt: 5.738 (5.741), Acc m&t: 3.40 5.35, Remain: 4 days, 11:02:17, Finish: 2024-11-28 13:50 [11-24 18:48:07] (/home/user/VAR/train.py , line 276)=> [ep107] (training ) Lm: 6.492 (6.496), Lt: 5.738 (5.741), Acc m&t: 3.40 5.35, Remain: 4 days, 10:58:35, Finish: 2024-11-28 13:46 [11-24 18:48:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [ 0/1669] eta: 0:25:47 tlr: 0.00018 tnm: 0.22 Lm: 6.471 (6.471) Lt: 5.725 (5.725) Accm: 3.50 (3.50) Acct: 5.19 (5.19) proj_loss: -0.6041 (-0.6041) time: 0.9275 data: 0.0003 [11-24 18:48:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [ 0/1669] eta: 0:25:49 tlr: 0.00018 tnm: 0.22 Lm: 6.553 (6.553) Lt: 5.792 (5.792) Accm: 3.30 (3.30) Acct: 5.22 (5.22) proj_loss: -0.6076 (-0.6076) time: 0.9284 data: 0.0004 [11-24 18:48:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [ 0/1669] eta: 0:25:50 tlr: 0.00018 tnm: 0.22 Lm: 6.367 (6.367) Lt: 5.588 (5.588) Accm: 3.59 (3.59) Acct: 5.86 (5.86) proj_loss: -0.6259 (-0.6259) time: 0.9288 data: 0.0003 [11-24 18:48:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [ 0/1669] eta: 0:25:50 tlr: 0.00018 tnm: 0.22 Lm: 6.459 (6.459) Lt: 5.713 (5.713) Accm: 3.68 (3.68) Acct: 5.17 (5.17) proj_loss: -0.6171 (-0.6171) time: 0.9288 data: 0.0004 [11-24 18:48:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [ 0/1669] eta: 0:25:50 tlr: 0.00018 tnm: 0.22 Lm: 6.480 (6.480) Lt: 5.737 (5.737) Accm: 3.39 (3.39) Acct: 5.24 (5.24) proj_loss: -0.5968 (-0.5968) time: 0.9289 data: 0.0003 [11-24 18:48:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [ 0/1669] eta: 0:25:50 tlr: 0.00018 tnm: 0.22 Lm: 6.359 (6.359) Lt: 5.564 (5.564) Accm: 3.65 (3.65) Acct: 5.68 (5.68) proj_loss: -0.6049 (-0.6049) time: 0.9292 data: 0.0005 [11-24 18:54:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.22 Lm: 6.460 (6.460) Lt: 5.752 (5.752) Accm: 3.45 (3.45) Acct: 5.17 (5.17) proj_loss: -0.6204 (-0.6204) time: 0.9460 data: 0.0002 [11-24 18:54:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.22 Lm: 6.472 (6.472) Lt: 5.701 (5.701) Accm: 3.44 (3.44) Acct: 5.53 (5.53) proj_loss: -0.6216 (-0.6216) time: 0.9460 data: 0.0003 [11-24 18:54:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.22 Lm: 6.428 (6.428) Lt: 5.643 (5.643) Accm: 3.70 (3.70) Acct: 5.72 (5.72) proj_loss: -0.6030 (-0.6030) time: 0.9460 data: 0.0003 [11-24 18:54:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.22 Lm: 6.559 (6.559) Lt: 5.780 (5.780) Accm: 3.29 (3.29) Acct: 5.01 (5.01) proj_loss: -0.6054 (-0.6054) time: 0.9460 data: 0.0003 [11-24 18:54:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.22 Lm: 6.503 (6.503) Lt: 5.741 (5.741) Accm: 3.47 (3.47) Acct: 5.48 (5.48) proj_loss: -0.6109 (-0.6109) time: 0.9460 data: 0.0003 [11-24 18:54:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.22 Lm: 6.504 (6.504) Lt: 5.762 (5.762) Accm: 3.26 (3.26) Acct: 4.78 (4.78) proj_loss: -0.6037 (-0.6037) time: 0.9460 data: 0.0003 [11-24 19:01:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.22 Lm: 6.548 (6.519) Lt: 5.811 (5.781) Accm: 3.57 (3.36) Acct: 5.17 (5.09) proj_loss: -0.6171 (-0.6100) time: 0.9409 data: 0.0003 [11-24 19:01:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.22 Lm: 6.436 (6.460) Lt: 5.639 (5.681) Accm: 3.58 (3.49) Acct: 5.86 (5.69) proj_loss: -0.6174 (-0.6195) time: 0.9409 data: 0.0003 [11-24 19:01:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.22 Lm: 6.453 (6.469) Lt: 5.690 (5.702) Accm: 3.64 (3.69) Acct: 5.73 (5.84) proj_loss: -0.6143 (-0.6132) time: 0.9409 data: 0.0003 [11-24 19:01:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.22 Lm: 6.471 (6.465) Lt: 5.725 (5.742) Accm: 3.40 (3.34) Acct: 5.14 (5.05) proj_loss: -0.6141 (-0.6183) time: 0.9409 data: 0.0002 [11-24 19:01:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.22 Lm: 6.637 (6.591) Lt: 5.823 (5.815) Accm: 3.19 (3.10) Acct: 4.78 (4.82) proj_loss: -0.5978 (-0.6029) time: 0.9409 data: 0.0003 [11-24 19:01:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.22 Lm: 6.496 (6.474) Lt: 5.722 (5.702) Accm: 3.75 (3.73) Acct: 5.71 (5.72) proj_loss: -0.6049 (-0.6038) time: 0.9409 data: 0.0003 [11-24 19:07:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.23 Lm: 6.507 (6.508) Lt: 5.727 (5.728) Accm: 3.44 (3.29) Acct: 5.53 (5.31) proj_loss: -0.6163 (-0.6142) time: 0.9400 data: 0.0003 [11-24 19:07:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.23 Lm: 6.473 (6.474) Lt: 5.752 (5.757) Accm: 3.45 (3.42) Acct: 5.17 (5.22) proj_loss: -0.6091 (-0.6092) time: 0.9400 data: 0.0003 [11-24 19:07:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.23 Lm: 6.503 (6.503) Lt: 5.741 (5.746) Accm: 3.47 (3.54) Acct: 5.48 (5.55) proj_loss: -0.6109 (-0.6105) time: 0.9400 data: 0.0003 [11-24 19:07:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.23 Lm: 6.559 (6.562) Lt: 5.780 (5.786) Accm: 3.27 (3.16) Acct: 5.01 (4.95) proj_loss: -0.5973 (-0.5990) time: 0.9400 data: 0.0003 [11-24 19:07:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.23 Lm: 6.529 (6.496) Lt: 5.744 (5.718) Accm: 3.70 (3.58) Acct: 5.69 (5.49) proj_loss: -0.6030 (-0.6005) time: 0.9400 data: 0.0003 [11-24 19:07:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.23 Lm: 6.545 (6.525) Lt: 5.791 (5.778) Accm: 3.46 (3.36) Acct: 5.13 (5.09) proj_loss: -0.6037 (-0.6022) time: 0.9400 data: 0.0003 [11-24 19:14:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.475 (6.509) Lt: 5.779 (5.793) Accm: 3.40 (3.28) Acct: 5.14 (5.08) proj_loss: -0.6041 (-0.6071) time: 0.9449 data: 0.0022 [11-24 19:14:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.545 (6.515) Lt: 5.814 (5.759) Accm: 3.29 (3.25) Acct: 5.19 (5.15) proj_loss: -0.6152 (-0.6142) time: 0.9449 data: 0.0019 [11-24 19:14:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.480 (6.513) Lt: 5.737 (5.735) Accm: 3.34 (3.35) Acct: 5.24 (5.27) proj_loss: -0.5978 (-0.6014) time: 0.9449 data: 0.0017 [11-24 19:14:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.484 (6.500) Lt: 5.762 (5.749) Accm: 3.30 (3.47) Acct: 5.22 (5.42) proj_loss: -0.6076 (-0.6073) time: 0.9449 data: 0.0015 [11-24 19:14:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.542 (6.521) Lt: 5.786 (5.780) Accm: 3.35 (3.34) Acct: 5.09 (5.06) proj_loss: -0.6082 (-0.6034) time: 0.9449 data: 0.0021 [11-24 19:14:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 108/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.496 (6.474) Lt: 5.722 (5.709) Accm: 3.65 (3.56) Acct: 5.68 (5.51) proj_loss: -0.6049 (-0.6029) time: 0.9449 data: 0.0020 [11-24 19:14:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 108/350] Total time: 0:26:13 (0.943 s / it) [11-24 19:14:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 108/350] Total time: 0:26:13 (0.943 s / it) [11-24 19:14:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 108/350] Total time: 0:26:13 (0.943 s / it) [11-24 19:14:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 108/350] Total time: 0:26:13 (0.943 s / it) [11-24 19:14:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 108/350] Total time: 0:26:13 (0.943 s / it) [11-24 19:14:21] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 108/350] Total time: 0:26:13 (0.943 s / it) [11-24 19:14:21] (/home/user/VAR/train.py , line 276)=> [ep108] (training ) Lm: 6.492 (6.492), Lt: 5.738 (5.742), Acc m&t: 3.42 5.35, Remain: 4 days, 10:17:57, Finish: 2024-11-28 13:32 [11-24 19:14:21] (/home/user/VAR/train.py , line 276)=> [ep108] (training ) Lm: 6.492 (6.492), Lt: 5.738 (5.742), Acc m&t: 3.42 5.35, Remain: 4 days, 10:17:50, Finish: 2024-11-28 13:32 [11-24 19:14:21] (/home/user/VAR/train.py , line 276)=> [ep108] (training ) Lm: 6.492 (6.492), Lt: 5.738 (5.742), Acc m&t: 3.42 5.35, Remain: 4 days, 10:20:04, Finish: 2024-11-28 13:34 [11-24 19:14:21] (/home/user/VAR/train.py , line 276)=> [ep108] (training ) Lm: 6.492 (6.492), Lt: 5.738 (5.742), Acc m&t: 3.42 5.35, Remain: 4 days, 10:20:30, Finish: 2024-11-28 13:34 [11-24 19:14:21] (/home/user/VAR/train.py , line 276)=> [ep108] (training ) Lm: 6.492 (6.492), Lt: 5.738 (5.742), Acc m&t: 3.42 5.35, Remain: 4 days, 10:20:06, Finish: 2024-11-28 13:34 [11-24 19:14:21] (/home/user/VAR/train.py , line 276)=> [ep108] (training ) Lm: 6.492 (6.492), Lt: 5.738 (5.742), Acc m&t: 3.42 5.35, Remain: 4 days, 10:16:11, Finish: 2024-11-28 13:30 [11-24 19:14:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [ 0/1669] eta: 0:25:18 tlr: 0.00018 tnm: 0.23 Lm: 6.407 (6.407) Lt: 5.706 (5.706) Accm: 3.50 (3.50) Acct: 5.40 (5.40) proj_loss: -0.6100 (-0.6100) time: 0.9100 data: 0.0003 [11-24 19:14:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [ 0/1669] eta: 0:25:20 tlr: 0.00018 tnm: 0.23 Lm: 6.641 (6.641) Lt: 5.892 (5.892) Accm: 2.93 (2.93) Acct: 5.06 (5.06) proj_loss: -0.6194 (-0.6194) time: 0.9108 data: 0.0004 [11-24 19:14:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [ 0/1669] eta: 0:25:21 tlr: 0.00018 tnm: 0.23 Lm: 6.480 (6.480) Lt: 5.682 (5.682) Accm: 3.49 (3.49) Acct: 5.63 (5.63) proj_loss: -0.5810 (-0.5810) time: 0.9114 data: 0.0004 [11-24 19:14:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [ 0/1669] eta: 0:25:21 tlr: 0.00018 tnm: 0.23 Lm: 6.382 (6.382) Lt: 5.701 (5.701) Accm: 3.57 (3.57) Acct: 5.35 (5.35) proj_loss: -0.6098 (-0.6098) time: 0.9117 data: 0.0004 [11-24 19:14:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [ 0/1669] eta: 0:25:22 tlr: 0.00018 tnm: 0.23 Lm: 6.452 (6.452) Lt: 5.720 (5.720) Accm: 3.38 (3.38) Acct: 5.27 (5.27) proj_loss: -0.6098 (-0.6098) time: 0.9120 data: 0.0004 [11-24 19:14:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [ 0/1669] eta: 0:25:23 tlr: 0.00018 tnm: 0.23 Lm: 6.536 (6.536) Lt: 5.798 (5.798) Accm: 3.21 (3.21) Acct: 4.93 (4.93) proj_loss: -0.5862 (-0.5862) time: 0.9129 data: 0.0004 [11-24 19:20:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [ 417/1669] eta: 0:19:46 tlr: 0.00018 tnm: 0.23 Lm: 6.377 (6.377) Lt: 5.630 (5.630) Accm: 3.76 (3.76) Acct: 5.79 (5.79) proj_loss: -0.5937 (-0.5937) time: 1.0025 data: 0.0002 [11-24 19:20:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [ 417/1669] eta: 0:19:46 tlr: 0.00018 tnm: 0.23 Lm: 6.390 (6.390) Lt: 5.651 (5.651) Accm: 3.73 (3.73) Acct: 5.67 (5.67) proj_loss: -0.5977 (-0.5977) time: 1.0025 data: 0.0003 [11-24 19:20:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [ 417/1669] eta: 0:19:46 tlr: 0.00018 tnm: 0.23 Lm: 6.449 (6.449) Lt: 5.701 (5.701) Accm: 3.44 (3.44) Acct: 5.46 (5.46) proj_loss: -0.6028 (-0.6028) time: 1.0025 data: 0.0003 [11-24 19:20:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [ 417/1669] eta: 0:19:46 tlr: 0.00018 tnm: 0.23 Lm: 6.563 (6.563) Lt: 5.831 (5.831) Accm: 3.16 (3.16) Acct: 4.92 (4.92) proj_loss: -0.6059 (-0.6059) time: 1.0025 data: 0.0003 [11-24 19:20:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [ 417/1669] eta: 0:19:46 tlr: 0.00018 tnm: 0.23 Lm: 6.487 (6.487) Lt: 5.712 (5.712) Accm: 3.38 (3.38) Acct: 5.22 (5.22) proj_loss: -0.5948 (-0.5948) time: 1.0025 data: 0.0003 [11-24 19:20:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [ 417/1669] eta: 0:19:46 tlr: 0.00018 tnm: 0.23 Lm: 6.570 (6.570) Lt: 5.830 (5.830) Accm: 3.45 (3.45) Acct: 5.54 (5.54) proj_loss: -0.6075 (-0.6075) time: 1.0025 data: 0.0003 [11-24 19:27:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [ 834/1669] eta: 0:13:33 tlr: 0.00018 tnm: 0.22 Lm: 6.512 (6.551) Lt: 5.768 (5.785) Accm: 3.50 (3.47) Acct: 5.66 (5.58) proj_loss: -0.6008 (-0.6052) time: 0.9435 data: 0.0003 [11-24 19:27:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [ 834/1669] eta: 0:13:33 tlr: 0.00018 tnm: 0.22 Lm: 6.407 (6.394) Lt: 5.663 (5.641) Accm: 3.54 (3.69) Acct: 5.40 (5.62) proj_loss: -0.5848 (-0.5907) time: 0.9435 data: 0.0002 [11-24 19:27:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [ 834/1669] eta: 0:13:33 tlr: 0.00018 tnm: 0.22 Lm: 6.536 (6.506) Lt: 5.798 (5.730) Accm: 3.21 (3.30) Acct: 4.93 (5.28) proj_loss: -0.6154 (-0.6090) time: 0.9435 data: 0.0002 [11-24 19:27:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [ 834/1669] eta: 0:13:33 tlr: 0.00018 tnm: 0.22 Lm: 6.480 (6.425) Lt: 5.682 (5.667) Accm: 3.49 (3.59) Acct: 5.63 (5.57) proj_loss: -0.6086 (-0.6034) time: 0.9435 data: 0.0003 [11-24 19:27:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [ 834/1669] eta: 0:13:33 tlr: 0.00018 tnm: 0.22 Lm: 6.382 (6.379) Lt: 5.600 (5.628) Accm: 3.89 (3.85) Acct: 5.99 (5.87) proj_loss: -0.6098 (-0.6045) time: 0.9434 data: 0.0004 [11-24 19:27:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [ 834/1669] eta: 0:13:33 tlr: 0.00018 tnm: 0.22 Lm: 6.446 (6.430) Lt: 5.720 (5.711) Accm: 3.50 (3.50) Acct: 5.37 (5.43) proj_loss: -0.5958 (-0.5995) time: 0.9434 data: 0.0003 [11-24 19:34:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [1251/1669] eta: 0:06:42 tlr: 0.00018 tnm: 0.22 Lm: 6.449 (6.493) Lt: 5.726 (5.757) Accm: 3.44 (3.30) Acct: 5.32 (5.18) proj_loss: -0.5944 (-0.5965) time: 0.9446 data: 0.0003 [11-24 19:34:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [1251/1669] eta: 0:06:42 tlr: 0.00018 tnm: 0.22 Lm: 6.418 (6.419) Lt: 5.684 (5.662) Accm: 3.53 (3.65) Acct: 5.51 (5.62) proj_loss: -0.5969 (-0.5953) time: 0.9446 data: 0.0002 [11-24 19:34:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [1251/1669] eta: 0:06:42 tlr: 0.00018 tnm: 0.22 Lm: 6.558 (6.564) Lt: 5.830 (5.814) Accm: 3.21 (3.29) Acct: 5.36 (5.29) proj_loss: -0.6100 (-0.6087) time: 0.9445 data: 0.0003 [11-24 19:34:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [1251/1669] eta: 0:06:42 tlr: 0.00018 tnm: 0.22 Lm: 6.464 (6.411) Lt: 5.662 (5.634) Accm: 3.40 (3.64) Acct: 5.46 (5.83) proj_loss: -0.6161 (-0.6110) time: 0.9446 data: 0.0003 [11-24 19:34:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [1251/1669] eta: 0:06:42 tlr: 0.00018 tnm: 0.22 Lm: 6.390 (6.432) Lt: 5.651 (5.670) Accm: 3.73 (3.71) Acct: 5.73 (5.77) proj_loss: -0.5977 (-0.5965) time: 0.9446 data: 0.0003 [11-24 19:34:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [1251/1669] eta: 0:06:42 tlr: 0.00018 tnm: 0.22 Lm: 6.425 (6.412) Lt: 5.631 (5.646) Accm: 3.75 (3.69) Acct: 5.93 (5.73) proj_loss: -0.5948 (-0.5925) time: 0.9446 data: 0.0003 [11-24 19:41:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.512 (6.525) Lt: 5.768 (5.765) Accm: 3.50 (3.42) Acct: 5.66 (5.43) proj_loss: -0.6147 (-0.6099) time: 0.9431 data: 0.0016 [11-24 19:41:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.480 (6.453) Lt: 5.682 (5.700) Accm: 3.49 (3.52) Acct: 5.63 (5.34) proj_loss: -0.6086 (-0.5964) time: 0.9432 data: 0.0016 [11-24 19:41:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.391 (6.374) Lt: 5.527 (5.589) Accm: 3.59 (3.80) Acct: 5.99 (6.02) proj_loss: -0.6154 (-0.6057) time: 0.9432 data: 0.0015 [11-24 19:41:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.407 (6.413) Lt: 5.663 (5.658) Accm: 3.54 (3.65) Acct: 5.63 (5.64) proj_loss: -0.6030 (-0.5968) time: 0.9431 data: 0.0016 [11-24 19:41:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.446 (6.466) Lt: 5.720 (5.706) Accm: 3.50 (3.38) Acct: 5.37 (5.29) proj_loss: -0.5929 (-0.5955) time: 0.9431 data: 0.0016 [11-24 19:41:01] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 109/350] Total time: 0:26:39 (0.958 s / it) [11-24 19:41:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 109/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.399 (6.427) Lt: 5.670 (5.670) Accm: 3.57 (3.68) Acct: 5.73 (5.76) proj_loss: -0.6058 (-0.5984) time: 0.9431 data: 0.0019 [11-24 19:41:01] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 109/350] Total time: 0:26:39 (0.958 s / it) [11-24 19:41:01] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 109/350] Total time: 0:26:39 (0.958 s / it) [11-24 19:41:01] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 109/350] Total time: 0:26:39 (0.958 s / it) [11-24 19:41:01] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 109/350] Total time: 0:26:39 (0.958 s / it) [11-24 19:41:01] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 109/350] Total time: 0:26:39 (0.958 s / it) [11-24 19:43:24] (home/user/VAR/trainer.py, line 114)=> FID: 3.7915524739764237 [11-24 19:43:24] (/home/user/VAR/train.py , line 259)=> [*] [ep109] (val 50000) Lm: 6.4940, Lt: 5.7371, Acc m&t: 3.40 5.33, Val cost: 143.29s [11-24 19:43:24] (/home/user/VAR/train.py , line 264)=> [saving ckpt] ... [saving ckpt](*) finished! @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth [11-24 19:43:59] (/home/user/VAR/train.py , line 276)=> [ep109] (training ) Lm: 6.492 (6.494), Lt: 5.737 (5.737), Acc m&t: 3.42 5.35, Remain: 4 days, 9:41:56, Finish: 2024-11-28 13:22 [11-24 19:43:59] (/home/user/VAR/train.py , line 276)=> [ep109] (training ) Lm: 6.492 (6.494), Lt: 5.737 (5.737), Acc m&t: 3.42 5.35, Remain: 4 days, 9:43:04, Finish: 2024-11-28 13:24 [11-24 19:43:59] (/home/user/VAR/train.py , line 276)=> [ep109] (training ) Lm: 6.492 (6.494), Lt: 5.737 (5.737), Acc m&t: 3.42 5.35, Remain: 4 days, 9:44:00, Finish: 2024-11-28 13:25 [11-24 19:43:59] (/home/user/VAR/train.py , line 276)=> [ep109] (training ) Lm: 6.492 (6.494), Lt: 5.737 (5.737), Acc m&t: 3.42 5.35, Remain: 4 days, 9:43:32, Finish: 2024-11-28 13:24 [11-24 19:43:59] (/home/user/VAR/train.py , line 276)=> [ep109] (training ) Lm: 6.492 (6.494), Lt: 5.737 (5.737), Acc m&t: 3.42 5.35, Remain: 4 days, 9:44:21, Finish: 2024-11-28 13:25 [11-24 19:43:59] (/home/user/VAR/train.py , line 276)=> [ep109] (training ) Lm: 6.492 (6.494), Lt: 5.737 (5.737), Acc m&t: 3.42 5.35, Remain: 4 days, 9:43:37, Finish: 2024-11-28 13:24 [11-24 19:44:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 0/1669] eta: 0:25:29 tlr: 0.00018 tnm: 0.23 Lm: 6.468 (6.468) Lt: 5.705 (5.705) Accm: 3.30 (3.30) Acct: 5.04 (5.04) proj_loss: -0.6006 (-0.6006) time: 0.9161 data: 0.0004 [11-24 19:44:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 0/1669] eta: 0:25:35 tlr: 0.00018 tnm: 0.23 Lm: 6.452 (6.452) Lt: 5.717 (5.717) Accm: 3.73 (3.73) Acct: 5.71 (5.71) proj_loss: -0.6307 (-0.6307) time: 0.9201 data: 0.0004 [11-24 19:44:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 0/1669] eta: 0:25:30 tlr: 0.00018 tnm: 0.23 Lm: 6.554 (6.554) Lt: 5.842 (5.842) Accm: 3.26 (3.26) Acct: 5.14 (5.14) proj_loss: -0.6123 (-0.6123) time: 0.9172 data: 0.0004 [11-24 19:44:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 0/1669] eta: 0:25:30 tlr: 0.00018 tnm: 0.23 Lm: 6.604 (6.604) Lt: 5.888 (5.888) Accm: 3.12 (3.12) Acct: 4.88 (4.88) proj_loss: -0.6028 (-0.6028) time: 0.9170 data: 0.0004 [11-24 19:44:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 0/1669] eta: 0:25:31 tlr: 0.00018 tnm: 0.23 Lm: 6.581 (6.581) Lt: 5.834 (5.834) Accm: 2.95 (2.95) Acct: 4.62 (4.62) proj_loss: -0.6217 (-0.6217) time: 0.9174 data: 0.0003 [11-24 19:44:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 0/1669] eta: 0:25:31 tlr: 0.00018 tnm: 0.23 Lm: 6.308 (6.308) Lt: 5.554 (5.554) Accm: 3.84 (3.84) Acct: 5.76 (5.76) proj_loss: -0.6188 (-0.6188) time: 0.9176 data: 0.0004 [11-24 19:50:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 417/1669] eta: 0:19:41 tlr: 0.00018 tnm: 0.23 Lm: 6.392 (6.392) Lt: 5.640 (5.640) Accm: 3.64 (3.64) Acct: 5.54 (5.54) proj_loss: -0.6018 (-0.6018) time: 0.9459 data: 0.0003 [11-24 19:50:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 417/1669] eta: 0:19:41 tlr: 0.00018 tnm: 0.23 Lm: 6.507 (6.507) Lt: 5.779 (5.779) Accm: 3.33 (3.33) Acct: 5.07 (5.07) proj_loss: -0.6200 (-0.6200) time: 0.9459 data: 0.0002 [11-24 19:50:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 417/1669] eta: 0:19:41 tlr: 0.00018 tnm: 0.23 Lm: 6.484 (6.484) Lt: 5.742 (5.742) Accm: 3.50 (3.50) Acct: 5.53 (5.53) proj_loss: -0.6010 (-0.6010) time: 0.9459 data: 0.0003 [11-24 19:50:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 417/1669] eta: 0:19:41 tlr: 0.00018 tnm: 0.23 Lm: 6.584 (6.584) Lt: 5.799 (5.799) Accm: 3.08 (3.08) Acct: 4.91 (4.91) proj_loss: -0.6040 (-0.6040) time: 0.9459 data: 0.0002 [11-24 19:50:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 417/1669] eta: 0:19:41 tlr: 0.00018 tnm: 0.23 Lm: 6.572 (6.572) Lt: 5.871 (5.871) Accm: 3.04 (3.04) Acct: 4.62 (4.62) proj_loss: -0.6107 (-0.6107) time: 0.9459 data: 0.0003 [11-24 19:50:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 417/1669] eta: 0:19:41 tlr: 0.00018 tnm: 0.23 Lm: 6.581 (6.581) Lt: 5.827 (5.827) Accm: 3.22 (3.22) Acct: 4.98 (4.98) proj_loss: -0.5990 (-0.5990) time: 0.9459 data: 0.0003 [11-24 19:57:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.23 Lm: 6.604 (6.595) Lt: 5.825 (5.826) Accm: 3.12 (3.19) Acct: 5.09 (5.04) proj_loss: -0.6028 (-0.6009) time: 0.9416 data: 0.0003 [11-24 19:57:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.23 Lm: 6.500 (6.578) Lt: 5.779 (5.845) Accm: 3.30 (3.11) Acct: 5.04 (4.92) proj_loss: -0.6014 (-0.6029) time: 0.9416 data: 0.0003 [11-24 19:57:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.23 Lm: 6.477 (6.424) Lt: 5.726 (5.688) Accm: 3.44 (3.42) Acct: 5.32 (5.22) proj_loss: -0.6188 (-0.6105) time: 0.9415 data: 0.0003 [11-24 19:57:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.23 Lm: 6.554 (6.561) Lt: 5.842 (5.860) Accm: 3.26 (3.12) Acct: 5.11 (4.79) proj_loss: -0.6123 (-0.6155) time: 0.9415 data: 0.0003 [11-24 19:57:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.23 Lm: 6.452 (6.472) Lt: 5.717 (5.733) Accm: 3.73 (3.50) Acct: 5.71 (5.44) proj_loss: -0.6307 (-0.6292) time: 0.9416 data: 0.0002 [11-24 19:57:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 834/1669] eta: 0:13:07 tlr: 0.00018 tnm: 0.23 Lm: 6.587 (6.592) Lt: 5.825 (5.808) Accm: 2.95 (3.04) Acct: 4.65 (4.82) proj_loss: -0.5940 (-0.6007) time: 0.9416 data: 0.0003 [11-24 20:03:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.23 Lm: 6.584 (6.582) Lt: 5.817 (5.808) Accm: 3.08 (3.16) Acct: 4.92 (5.06) proj_loss: -0.6058 (-0.6049) time: 0.9440 data: 0.0003 [11-24 20:03:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.23 Lm: 6.471 (6.477) Lt: 5.723 (5.732) Accm: 3.58 (3.48) Acct: 5.72 (5.51) proj_loss: -0.6200 (-0.6239) time: 0.9440 data: 0.0002 [11-24 20:03:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.23 Lm: 6.483 (6.444) Lt: 5.727 (5.698) Accm: 3.28 (3.35) Acct: 5.06 (5.11) proj_loss: -0.6198 (-0.6131) time: 0.9440 data: 0.0003 [11-24 20:03:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.23 Lm: 6.491 (6.554) Lt: 5.743 (5.810) Accm: 3.28 (3.14) Acct: 4.98 (4.92) proj_loss: -0.6041 (-0.6042) time: 0.9440 data: 0.0003 [11-24 20:03:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.23 Lm: 6.547 (6.532) Lt: 5.841 (5.807) Accm: 3.26 (3.17) Acct: 5.11 (4.87) proj_loss: -0.6175 (-0.6173) time: 0.9440 data: 0.0003 [11-24 20:03:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [1251/1669] eta: 0:06:34 tlr: 0.00018 tnm: 0.23 Lm: 6.581 (6.582) Lt: 5.814 (5.821) Accm: 3.12 (3.12) Acct: 4.98 (4.90) proj_loss: -0.6037 (-0.6090) time: 0.9440 data: 0.0003 ======================================================= RESTART [11-25 01:24:25] ======================================================= ======================================================= RESTART [11-25 01:24:25] ======================================================= ======================================================= RESTART [11-25 01:24:25] ======================================================= ======================================================= RESTART [11-25 01:24:25] ======================================================= ======================================================= RESTART [11-25 01:24:25] ======================================================= ======================================================= RESTART [11-25 01:24:25] ======================================================= ======================================================= RESTART [11-25 01:24:25] ======================================================= ======================================================= RESTART [11-25 01:24:25] ======================================================= [11-25 01:24:25] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 01:24:25] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 01:24:25] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 01:26:06] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 01:26:06] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main commit_msg : add } [11-25 01:26:06] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 01:26:09] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 01:26:09] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> [11-25 01:26:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 01:26:09] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> [11-25 01:26:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 01:26:09] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-25 01:26:09] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep110, it0 [11-25 01:26:09] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-25 01:24:25] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 01:24:25] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 01:24:25] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 01:26:06] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 01:26:06] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main commit_msg : add } [11-25 01:26:06] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 01:26:09] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 01:26:09] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> [11-25 01:26:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 01:26:09] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> [11-25 01:26:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 01:26:09] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-25 01:26:09] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep110, it0 [11-25 01:26:09] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-25 01:24:25] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 01:24:25] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 01:24:25] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 01:26:06] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 01:26:06] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add } [11-25 01:26:06] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 01:26:09] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 01:26:09] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> [11-25 01:26:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 01:26:09] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> [11-25 01:26:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 01:26:09] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-25 01:26:09] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep110, it0 [11-25 01:26:09] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-25 01:24:25] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 01:24:25] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 01:24:25] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 01:26:06] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 01:26:06] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main } [11-25 01:26:06] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 01:26:09] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 01:26:09] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> [11-25 01:26:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 01:26:09] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> [11-25 01:26:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 01:26:09] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-25 01:26:09] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep110, it0 [11-25 01:26:09] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-25 01:24:25] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 01:24:25] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 01:24:25] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 01:26:06] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 01:26:06] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main } [11-25 01:26:06] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 01:26:09] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 01:26:09] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> [11-25 01:26:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 01:26:09] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> [11-25 01:26:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 01:26:09] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-25 01:26:09] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep110, it0 [11-25 01:26:09] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-25 01:24:25] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 01:24:25] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 01:24:25] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 01:26:06] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 01:26:06] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main commit_msg : add } [11-25 01:26:06] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 01:26:09] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 01:26:09] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> [11-25 01:26:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 01:26:09] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> [11-25 01:26:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 01:26:09] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-25 01:26:09] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep110, it0 [11-25 01:26:09] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-25 01:24:25] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 01:24:25] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 01:24:25] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 01:26:06] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 01:26:06] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main commit_msg : add } [11-25 01:26:06] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 01:26:09] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 01:26:09] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> [11-25 01:26:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 01:26:09] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> [11-25 01:26:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 01:26:09] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-25 01:26:09] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep110, it0 [11-25 01:26:09] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-25 01:24:25] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 01:24:25] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 01:24:25] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 01:26:06] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 01:26:06] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main } [11-25 01:26:06] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 01:26:09] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 01:26:09] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> [11-25 01:26:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 01:26:09] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 01:26:09] (e/user/VAR/utils/data.py, line 51)=> [11-25 01:26:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 01:26:09] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-25 01:26:09] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep110, it0 [11-25 01:26:09] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ... [dataloader multi processing](*) finished! (46.94s) [dataloader multi processing](*) finished! (47.04s) [dataloader multi processing](*) finished! (47.08s) [dataloader multi processing](*) finished! (48.13s) [dataloader multi processing](*) finished! (48.92s) [dataloader multi processing](*) finished! (49.42s) [dataloader multi processing](*) finished! (50.03s) [dataloader multi processing](*) finished! (50.36s) [11-25 01:26:56] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 01:26:59] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 01:26:59] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 01:27:00] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-25 01:26:56] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 01:27:01] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 01:27:01] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 01:27:02] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-25 01:26:56] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 01:27:01] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 01:27:01] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 01:27:02] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-25 01:26:57] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 01:27:02] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 01:27:02] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 01:27:03] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-25 01:26:58] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 01:27:03] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 01:27:03] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 01:27:04] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-25 01:26:59] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 01:27:03] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 01:27:03] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 01:27:05] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-25 01:26:59] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 01:27:04] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 01:27:04] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 01:27:05] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-25 01:27:00] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 01:27:04] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 01:27:04] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 01:27:05] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-25 01:27:04] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 01:27:30] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 01:27:30] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 01:27:30] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 01:27:30] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 01:27:31] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank0] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 01:27:06] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 01:27:30] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 01:27:30] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 01:27:30] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 01:27:30] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 01:27:31] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank8] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 01:27:05] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 01:27:30] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 01:27:30] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 01:27:30] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 01:27:30] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 01:27:31] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank16] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 01:27:08] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 01:27:30] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 01:27:30] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 01:27:30] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 01:27:30] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 01:27:31] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank24] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 01:27:08] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 01:27:30] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 01:27:30] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 01:27:30] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 01:27:30] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 01:27:31] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank32] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 01:27:07] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 01:27:31] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 01:27:31] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 01:27:31] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 01:27:31] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 01:27:31] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank40] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 01:27:06] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 01:27:30] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 01:27:30] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 01:27:30] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 01:27:30] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 01:27:31] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank48] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 01:27:09] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 01:27:30] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 01:27:30] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 01:27:30] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 01:27:30] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 01:27:32] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank56] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 01:27:32] (/VAR/utils/lr_control.py, line 105)=> [11-25 01:27:32] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 01:27:34] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 01:27:34] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 01:27:34] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 01:27:34] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 01:33:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 0/1669] eta: 7 days, 4:23:45 tlr: 0.00018 tnm: 0.22 Lm: 6.137 (6.137) Lt: 5.257 (5.257) Accm: 4.60 (4.60) Acct: 7.47 (7.47) proj_loss: -0.5740 (-0.5740) time: 371.8549 data: 0.0006 [11-25 01:27:32] (/VAR/utils/lr_control.py, line 105)=> [11-25 01:27:32] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 01:27:34] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 01:27:34] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 01:27:34] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 01:27:34] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 01:33:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 0/1669] eta: 7 days, 4:38:56 tlr: 0.00018 tnm: 0.22 Lm: 6.535 (6.535) Lt: 5.790 (5.790) Accm: 3.07 (3.07) Acct: 4.79 (4.79) proj_loss: -0.6252 (-0.6252) time: 372.4006 data: 0.0006 [11-25 01:27:32] (/VAR/utils/lr_control.py, line 105)=> [11-25 01:27:32] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 01:27:34] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 01:27:34] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 01:27:34] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 01:27:34] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 01:33:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 0/1669] eta: 7 days, 4:34:09 tlr: 0.00018 tnm: 0.22 Lm: 6.444 (6.444) Lt: 5.687 (5.687) Accm: 3.55 (3.55) Acct: 5.85 (5.85) proj_loss: -0.5936 (-0.5936) time: 372.2289 data: 0.0007 [11-25 01:27:32] (/VAR/utils/lr_control.py, line 105)=> [11-25 01:27:32] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 01:27:35] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 01:27:35] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 01:27:36] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 01:27:36] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 01:33:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 0/1669] eta: 7 days, 4:47:05 tlr: 0.00018 tnm: 0.22 Lm: 6.356 (6.356) Lt: 5.493 (5.493) Accm: 3.61 (3.61) Acct: 5.92 (5.92) proj_loss: -0.6107 (-0.6107) time: 372.6935 data: 0.0006 [11-25 01:27:32] (/VAR/utils/lr_control.py, line 105)=> [11-25 01:27:32] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 01:27:35] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 01:27:35] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 01:27:35] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 01:27:35] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 01:33:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 0/1669] eta: 7 days, 4:02:16 tlr: 0.00018 tnm: 0.22 Lm: 6.523 (6.523) Lt: 5.843 (5.843) Accm: 3.53 (3.53) Acct: 5.44 (5.44) proj_loss: -0.6261 (-0.6261) time: 371.0821 data: 0.0005 [11-25 01:27:32] (/VAR/utils/lr_control.py, line 105)=> [11-25 01:27:32] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 01:27:34] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 01:27:34] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 01:27:34] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 01:27:34] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 01:33:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 0/1669] eta: 7 days, 4:34:56 tlr: 0.00018 tnm: 0.22 Lm: 6.444 (6.444) Lt: 5.727 (5.727) Accm: 3.31 (3.31) Acct: 5.06 (5.06) proj_loss: -0.5952 (-0.5952) time: 372.2568 data: 0.0005 [11-25 01:27:32] (/VAR/utils/lr_control.py, line 105)=> [11-25 01:27:32] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 01:27:33] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 01:27:33] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 01:27:33] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 01:27:33] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 01:33:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 0/1669] eta: 7 days, 4:39:25 tlr: 0.00018 tnm: 0.22 Lm: 6.647 (6.647) Lt: 5.913 (5.913) Accm: 2.90 (2.90) Acct: 4.61 (4.61) proj_loss: -0.6256 (-0.6256) time: 372.4178 data: 0.0007 [11-25 01:27:32] (/VAR/utils/lr_control.py, line 105)=> [11-25 01:27:32] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 01:27:34] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 01:27:34] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 01:27:34] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 01:27:34] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 01:33:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 0/1669] eta: 7 days, 4:42:35 tlr: 0.00018 tnm: 0.22 Lm: 6.499 (6.499) Lt: 5.790 (5.790) Accm: 3.19 (3.19) Acct: 4.79 (4.79) proj_loss: -0.6283 (-0.6283) time: 372.5319 data: 0.0006 [11-25 01:48:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 417/1669] eta: 1:03:34 tlr: 0.00018 tnm: 0.23 Lm: 6.402 (6.402) Lt: 5.648 (5.648) Accm: 3.75 (3.75) Acct: 5.92 (5.92) proj_loss: -0.6121 (-0.6121) time: 0.9247 data: 0.0003 [11-25 01:48:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 417/1669] eta: 1:03:30 tlr: 0.00018 tnm: 0.23 Lm: 6.610 (6.610) Lt: 5.940 (5.940) Accm: 3.06 (3.06) Acct: 4.58 (4.58) proj_loss: -0.6195 (-0.6195) time: 0.9247 data: 0.0002 [11-25 01:48:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 417/1669] eta: 1:03:34 tlr: 0.00018 tnm: 0.23 Lm: 6.637 (6.637) Lt: 5.910 (5.910) Accm: 2.88 (2.88) Acct: 4.70 (4.70) proj_loss: -0.6066 (-0.6066) time: 0.9247 data: 0.0003 [11-25 01:48:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 417/1669] eta: 1:03:34 tlr: 0.00018 tnm: 0.23 Lm: 6.480 (6.480) Lt: 5.704 (5.704) Accm: 3.38 (3.38) Acct: 5.54 (5.54) proj_loss: -0.5965 (-0.5965) time: 0.9247 data: 0.0003 [11-25 01:48:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 417/1669] eta: 1:03:35 tlr: 0.00018 tnm: 0.23 Lm: 6.543 (6.543) Lt: 5.744 (5.744) Accm: 3.26 (3.26) Acct: 5.17 (5.17) proj_loss: -0.5871 (-0.5871) time: 0.9247 data: 0.0002 [11-25 01:48:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 417/1669] eta: 1:03:34 tlr: 0.00018 tnm: 0.23 Lm: 6.470 (6.470) Lt: 5.652 (5.652) Accm: 3.57 (3.57) Acct: 5.91 (5.91) proj_loss: -0.6032 (-0.6032) time: 0.9248 data: 0.0002 [11-25 01:48:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 417/1669] eta: 1:03:35 tlr: 0.00018 tnm: 0.23 Lm: 6.390 (6.390) Lt: 5.644 (5.644) Accm: 3.61 (3.61) Acct: 5.56 (5.56) proj_loss: -0.6155 (-0.6155) time: 0.9247 data: 0.0003 [11-25 01:48:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 417/1669] eta: 1:03:33 tlr: 0.00018 tnm: 0.23 Lm: 6.275 (6.275) Lt: 5.439 (5.439) Accm: 4.15 (4.15) Acct: 6.75 (6.75) proj_loss: -0.5810 (-0.5810) time: 0.9248 data: 0.0003 [11-25 01:55:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 834/1669] eta: 0:27:38 tlr: 0.00018 tnm: 0.23 Lm: 6.412 (6.343) Lt: 5.620 (5.516) Accm: 3.70 (3.90) Acct: 6.03 (6.26) proj_loss: -0.5880 (-0.5876) time: 0.9240 data: 0.0003 [11-25 01:55:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 834/1669] eta: 0:27:39 tlr: 0.00018 tnm: 0.23 Lm: 6.647 (6.661) Lt: 5.910 (5.910) Accm: 2.90 (2.97) Acct: 4.79 (4.88) proj_loss: -0.6161 (-0.6098) time: 0.9240 data: 0.0003 [11-25 01:55:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 834/1669] eta: 0:27:39 tlr: 0.00018 tnm: 0.23 Lm: 6.405 (6.446) Lt: 5.690 (5.665) Accm: 3.85 (3.66) Acct: 5.82 (5.88) proj_loss: -0.6252 (-0.6193) time: 0.9240 data: 0.0002 [11-25 01:55:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 834/1669] eta: 0:27:39 tlr: 0.00018 tnm: 0.23 Lm: 6.499 (6.451) Lt: 5.790 (5.696) Accm: 3.45 (3.56) Acct: 5.41 (5.51) proj_loss: -0.6027 (-0.6101) time: 0.9240 data: 0.0003 [11-25 01:55:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 834/1669] eta: 0:27:39 tlr: 0.00018 tnm: 0.23 Lm: 6.515 (6.534) Lt: 5.784 (5.757) Accm: 3.23 (3.25) Acct: 4.96 (5.10) proj_loss: -0.5877 (-0.5873) time: 0.9240 data: 0.0003 [11-25 01:55:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 834/1669] eta: 0:27:38 tlr: 0.00018 tnm: 0.23 Lm: 6.444 (6.461) Lt: 5.727 (5.737) Accm: 3.31 (3.45) Acct: 5.06 (5.49) proj_loss: -0.5952 (-0.6062) time: 0.9240 data: 0.0003 [11-25 01:55:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 834/1669] eta: 0:27:37 tlr: 0.00018 tnm: 0.23 Lm: 6.640 (6.620) Lt: 5.978 (5.953) Accm: 2.77 (2.96) Acct: 3.99 (4.38) proj_loss: -0.6260 (-0.6217) time: 0.9240 data: 0.0002 [11-25 01:55:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 834/1669] eta: 0:27:38 tlr: 0.00018 tnm: 0.23 Lm: 6.444 (6.424) Lt: 5.687 (5.661) Accm: 3.55 (3.61) Acct: 5.85 (5.87) proj_loss: -0.5936 (-0.5939) time: 0.9240 data: 0.0003 ======================================================= RESTART [11-25 02:36:22] ======================================================= ======================================================= RESTART [11-25 02:36:22] ======================================================= ======================================================= RESTART [11-25 02:36:22] ======================================================= ======================================================= RESTART [11-25 02:36:22] ======================================================= ======================================================= RESTART [11-25 02:36:22] ======================================================= ======================================================= RESTART [11-25 02:36:22] ======================================================= ======================================================= RESTART [11-25 02:36:22] ======================================================= ======================================================= RESTART [11-25 02:36:22] ======================================================= [11-25 02:36:22] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 02:36:22] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 02:36:22] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 02:38:00] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 02:38:00] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-25 02:38:00] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 02:38:03] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 02:38:03] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> [11-25 02:38:03] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 02:38:03] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> [11-25 02:38:03] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 02:38:03] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-25 02:38:03] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep110, it0 [11-25 02:38:03] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-25 02:36:22] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 02:36:22] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 02:36:22] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 02:38:00] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 02:38:00] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add } [11-25 02:38:00] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 02:38:03] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 02:38:03] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> [11-25 02:38:03] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 02:38:03] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> [11-25 02:38:03] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 02:38:03] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-25 02:38:03] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep110, it0 [11-25 02:38:03] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-25 02:36:22] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 02:36:22] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 02:36:22] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 02:38:00] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 02:38:00] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main } [11-25 02:38:00] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 02:38:03] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 02:38:03] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> [11-25 02:38:03] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 02:38:03] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> [11-25 02:38:03] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 02:38:03] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-25 02:38:03] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep110, it0 [11-25 02:38:03] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-25 02:36:22] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 02:36:22] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 02:36:22] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 02:38:00] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 02:38:00] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main } [11-25 02:38:00] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 02:38:03] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 02:38:03] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> [11-25 02:38:03] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 02:38:03] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> [11-25 02:38:03] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 02:38:03] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-25 02:38:03] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep110, it0 [11-25 02:38:03] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-25 02:36:22] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 02:36:22] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 02:36:22] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 02:38:00] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 02:38:00] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main commit_msg : add } [11-25 02:38:00] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 02:38:03] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 02:38:03] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> [11-25 02:38:03] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 02:38:03] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> [11-25 02:38:03] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 02:38:03] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-25 02:38:03] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep110, it0 [11-25 02:38:03] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-25 02:36:22] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 02:36:22] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 02:36:22] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 02:38:00] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 02:38:00] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add branch : main } [11-25 02:38:00] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 02:38:03] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 02:38:03] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> [11-25 02:38:03] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 02:38:03] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> [11-25 02:38:03] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 02:38:03] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-25 02:38:03] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep110, it0 [11-25 02:38:03] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-25 02:36:22] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 02:36:22] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 02:36:22] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 02:38:00] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 02:38:00] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add branch : main } [11-25 02:38:00] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 02:38:03] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 02:38:03] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> [11-25 02:38:03] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 02:38:03] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 02:38:03] (e/user/VAR/utils/data.py, line 51)=> [11-25 02:38:03] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 02:38:03] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-25 02:38:03] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep110, it0 [11-25 02:38:03] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-25 02:36:22] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 02:36:22] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 02:36:22] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 02:38:00] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 02:38:00] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main } [11-25 02:38:00] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 02:38:05] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 02:38:05] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 02:38:05] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 02:38:05] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 02:38:05] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 02:38:05] (e/user/VAR/utils/data.py, line 51)=> [11-25 02:38:05] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 02:38:05] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 02:38:05] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 02:38:05] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 02:38:05] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 02:38:05] (e/user/VAR/utils/data.py, line 51)=> [11-25 02:38:05] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 02:38:05] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-25 02:38:05] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep110, it0 [11-25 02:38:05] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ... [dataloader multi processing](*) finished! (46.43s) [dataloader multi processing](*) finished! (47.16s) [dataloader multi processing](*) finished! (47.65s) [dataloader multi processing](*) finished! (48.78s) [dataloader multi processing](*) finished! (49.19s) [dataloader multi processing](*) finished! (50.49s) [11-25 02:38:49] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 02:38:53] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 02:38:53] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 02:38:54] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [dataloader multi processing](*) finished! (52.31s) [11-25 02:38:50] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 02:38:55] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 02:38:55] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 02:38:56] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [dataloader multi processing](*) finished! (51.24s) [11-25 02:38:51] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 02:38:55] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 02:38:55] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 02:38:57] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-25 02:38:52] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 02:38:57] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 02:38:57] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 02:38:58] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-25 02:38:52] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 02:38:57] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 02:38:57] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 02:38:58] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-25 02:38:54] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 02:38:58] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 02:38:58] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 02:39:00] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-25 02:38:55] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 02:39:00] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 02:39:00] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 02:39:01] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-25 02:38:56] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 02:39:01] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 02:39:01] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 02:39:02] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-25 02:38:57] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 02:39:29] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 02:39:29] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 02:39:29] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 02:39:29] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 02:39:30] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank0] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 02:39:03] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 02:39:29] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 02:39:29] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 02:39:29] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 02:39:29] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 02:39:30] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank8] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 02:39:05] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 02:39:29] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 02:39:29] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 02:39:29] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 02:39:29] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 02:39:30] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank16] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 02:39:05] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 02:39:29] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 02:39:29] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 02:39:29] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 02:39:29] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 02:39:30] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank24] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 02:39:00] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 02:39:29] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 02:39:29] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 02:39:29] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 02:39:29] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 02:39:30] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank32] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 02:39:00] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 02:39:30] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 02:39:30] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 02:39:30] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 02:39:30] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 02:39:30] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank40] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 02:39:01] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 02:39:29] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 02:39:29] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 02:39:29] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 02:39:29] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 02:39:30] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank48] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 02:39:01] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 02:39:29] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 02:39:29] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 02:39:29] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 02:39:29] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 02:39:31] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank56] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 02:39:31] (/VAR/utils/lr_control.py, line 105)=> [11-25 02:39:31] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 02:39:33] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 02:39:33] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 02:39:33] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 02:39:33] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 02:46:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 0/1669] eta: 7 days, 9:24:56 tlr: 0.00018 tnm: 0.23 Lm: 6.396 (6.396) Lt: 5.692 (5.692) Accm: 3.61 (3.61) Acct: 5.92 (5.92) proj_loss: -0.6170 (-0.6170) time: 382.6821 data: 0.0006 [11-25 02:39:31] (/VAR/utils/lr_control.py, line 105)=> [11-25 02:39:31] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 02:39:33] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 02:39:33] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 02:39:34] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 02:39:34] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 02:46:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 0/1669] eta: 7 days, 9:16:48 tlr: 0.00018 tnm: 0.23 Lm: 6.172 (6.172) Lt: 5.352 (5.352) Accm: 4.40 (4.40) Acct: 6.96 (6.96) proj_loss: -0.5862 (-0.5862) time: 382.3897 data: 0.0007 [11-25 02:39:31] (/VAR/utils/lr_control.py, line 105)=> [11-25 02:39:31] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 02:39:33] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 02:39:33] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 02:39:33] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 02:39:33] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 02:46:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 0/1669] eta: 7 days, 9:22:28 tlr: 0.00018 tnm: 0.23 Lm: 6.665 (6.665) Lt: 5.992 (5.992) Accm: 2.93 (2.93) Acct: 4.68 (4.68) proj_loss: -0.6306 (-0.6306) time: 382.5934 data: 0.0006 [11-25 02:39:31] (/VAR/utils/lr_control.py, line 105)=> [11-25 02:39:31] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 02:39:33] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 02:39:33] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 02:39:33] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 02:39:33] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 02:46:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 0/1669] eta: 7 days, 9:07:44 tlr: 0.00018 tnm: 0.23 Lm: 6.402 (6.402) Lt: 5.614 (5.614) Accm: 3.47 (3.47) Acct: 5.72 (5.72) proj_loss: -0.5828 (-0.5828) time: 382.0639 data: 0.0006 [11-25 02:39:31] (/VAR/utils/lr_control.py, line 105)=> [11-25 02:39:31] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 02:39:33] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 02:39:33] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 02:39:34] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 02:39:34] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 02:46:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 0/1669] eta: 7 days, 9:11:04 tlr: 0.00018 tnm: 0.23 Lm: 6.510 (6.510) Lt: 5.732 (5.732) Accm: 3.53 (3.53) Acct: 5.23 (5.23) proj_loss: -0.6280 (-0.6280) time: 382.1834 data: 0.0007 [11-25 02:39:31] (/VAR/utils/lr_control.py, line 105)=> [11-25 02:39:31] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 02:39:33] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 02:39:33] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 02:39:33] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 02:39:33] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 02:46:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 0/1669] eta: 7 days, 9:33:29 tlr: 0.00018 tnm: 0.23 Lm: 6.364 (6.364) Lt: 5.548 (5.548) Accm: 3.70 (3.70) Acct: 5.82 (5.82) proj_loss: -0.6097 (-0.6097) time: 382.9894 data: 0.0006 [11-25 02:39:31] (/VAR/utils/lr_control.py, line 105)=> [11-25 02:39:31] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 02:39:33] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 02:39:33] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 02:39:34] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 02:39:34] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 02:46:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 0/1669] eta: 7 days, 9:38:47 tlr: 0.00018 tnm: 0.23 Lm: 6.679 (6.679) Lt: 5.893 (5.893) Accm: 3.03 (3.03) Acct: 5.34 (5.34) proj_loss: -0.6358 (-0.6358) time: 383.1801 data: 0.0007 [11-25 02:39:31] (/VAR/utils/lr_control.py, line 105)=> [11-25 02:39:31] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 02:39:32] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 02:39:32] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 02:39:33] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 02:39:33] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 02:46:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 0/1669] eta: 7 days, 9:01:10 tlr: 0.00018 tnm: 0.23 Lm: 6.470 (6.470) Lt: 5.755 (5.755) Accm: 3.39 (3.39) Acct: 5.20 (5.20) proj_loss: -0.6246 (-0.6246) time: 381.8280 data: 0.0005 [11-25 03:01:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 417/1669] eta: 1:04:06 tlr: 0.00018 tnm: 0.23 Lm: 6.558 (6.558) Lt: 5.777 (5.777) Accm: 3.34 (3.34) Acct: 5.46 (5.46) proj_loss: -0.6112 (-0.6112) time: 0.9226 data: 0.0003 [11-25 03:01:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 417/1669] eta: 1:04:05 tlr: 0.00018 tnm: 0.23 Lm: 6.392 (6.392) Lt: 5.607 (5.607) Accm: 3.77 (3.77) Acct: 5.79 (5.79) proj_loss: -0.6132 (-0.6132) time: 0.9226 data: 0.0003 [11-25 03:01:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 417/1669] eta: 1:04:06 tlr: 0.00018 tnm: 0.23 Lm: 6.455 (6.455) Lt: 5.722 (5.722) Accm: 3.74 (3.74) Acct: 5.87 (5.87) proj_loss: -0.6100 (-0.6100) time: 0.9226 data: 0.0003 [11-25 03:01:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 417/1669] eta: 1:04:05 tlr: 0.00018 tnm: 0.23 Lm: 6.348 (6.348) Lt: 5.493 (5.493) Accm: 4.03 (4.03) Acct: 6.46 (6.46) proj_loss: -0.5779 (-0.5779) time: 0.9226 data: 0.0003 [11-25 03:01:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 417/1669] eta: 1:04:07 tlr: 0.00018 tnm: 0.23 Lm: 6.545 (6.545) Lt: 5.769 (5.769) Accm: 3.19 (3.19) Acct: 5.01 (5.01) proj_loss: -0.5841 (-0.5841) time: 0.9226 data: 0.0003 [11-25 03:01:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 417/1669] eta: 1:04:03 tlr: 0.00018 tnm: 0.23 Lm: 6.584 (6.584) Lt: 5.871 (5.871) Accm: 2.97 (2.97) Acct: 4.58 (4.58) proj_loss: -0.6183 (-0.6183) time: 0.9226 data: 0.0002 [11-25 03:01:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 417/1669] eta: 1:04:08 tlr: 0.00018 tnm: 0.23 Lm: 6.646 (6.646) Lt: 5.861 (5.861) Accm: 3.09 (3.09) Acct: 5.37 (5.37) proj_loss: -0.6104 (-0.6104) time: 0.9226 data: 0.0003 [11-25 03:01:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 417/1669] eta: 1:04:04 tlr: 0.00018 tnm: 0.23 Lm: 6.402 (6.402) Lt: 5.644 (5.644) Accm: 3.63 (3.63) Acct: 5.73 (5.73) proj_loss: -0.6014 (-0.6014) time: 0.9226 data: 0.0003 [11-25 03:07:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 834/1669] eta: 0:27:49 tlr: 0.00018 tnm: 0.23 Lm: 6.403 (6.450) Lt: 5.674 (5.701) Accm: 3.48 (3.58) Acct: 5.72 (5.58) proj_loss: -0.6103 (-0.6044) time: 0.9236 data: 0.0003 [11-25 03:07:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 834/1669] eta: 0:27:49 tlr: 0.00018 tnm: 0.23 Lm: 6.451 (6.492) Lt: 5.603 (5.719) Accm: 3.67 (3.45) Acct: 5.61 (5.51) proj_loss: -0.6306 (-0.6229) time: 0.9235 data: 0.0002 [11-25 03:07:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 834/1669] eta: 0:27:50 tlr: 0.00018 tnm: 0.23 Lm: 6.679 (6.657) Lt: 5.829 (5.846) Accm: 3.12 (3.10) Acct: 5.41 (5.38) proj_loss: -0.6154 (-0.6121) time: 0.9235 data: 0.0003 [11-25 03:07:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 834/1669] eta: 0:27:49 tlr: 0.00018 tnm: 0.23 Lm: 6.510 (6.473) Lt: 5.732 (5.699) Accm: 3.53 (3.48) Acct: 5.23 (5.33) proj_loss: -0.5984 (-0.6061) time: 0.9235 data: 0.0003 [11-25 03:07:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 834/1669] eta: 0:27:49 tlr: 0.00018 tnm: 0.23 Lm: 6.396 (6.398) Lt: 5.692 (5.644) Accm: 3.83 (3.77) Acct: 5.89 (5.88) proj_loss: -0.6030 (-0.6061) time: 0.9235 data: 0.0003 [11-25 03:07:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 834/1669] eta: 0:27:50 tlr: 0.00018 tnm: 0.23 Lm: 6.478 (6.523) Lt: 5.711 (5.750) Accm: 3.26 (3.21) Acct: 5.41 (5.14) proj_loss: -0.5921 (-0.5868) time: 0.9235 data: 0.0003 [11-25 03:07:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 834/1669] eta: 0:27:49 tlr: 0.00018 tnm: 0.23 Lm: 6.467 (6.388) Lt: 5.633 (5.540) Accm: 3.66 (3.82) Acct: 5.96 (6.08) proj_loss: -0.5862 (-0.5877) time: 0.9235 data: 0.0003 [11-25 03:07:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [ 834/1669] eta: 0:27:48 tlr: 0.00018 tnm: 0.23 Lm: 6.622 (6.597) Lt: 5.959 (5.900) Accm: 3.22 (3.05) Acct: 5.20 (4.80) proj_loss: -0.6246 (-0.6215) time: 0.9235 data: 0.0003 [11-25 03:13:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [1251/1669] eta: 0:11:26 tlr: 0.00018 tnm: 0.22 Lm: 6.392 (6.414) Lt: 5.607 (5.643) Accm: 3.77 (3.69) Acct: 5.79 (5.60) proj_loss: -0.6022 (-0.6060) time: 0.9263 data: 0.0003 [11-25 03:13:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [1251/1669] eta: 0:11:26 tlr: 0.00018 tnm: 0.22 Lm: 6.646 (6.612) Lt: 5.823 (5.816) Accm: 3.13 (3.17) Acct: 5.41 (5.41) proj_loss: -0.6145 (-0.6125) time: 0.9263 data: 0.0002 [11-25 03:13:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [1251/1669] eta: 0:11:26 tlr: 0.00018 tnm: 0.22 Lm: 6.503 (6.524) Lt: 5.776 (5.773) Accm: 3.10 (3.14) Acct: 4.91 (4.96) proj_loss: -0.5966 (-0.5904) time: 0.9263 data: 0.0003 [11-25 03:13:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [1251/1669] eta: 0:11:26 tlr: 0.00018 tnm: 0.22 Lm: 6.455 (6.445) Lt: 5.722 (5.695) Accm: 3.72 (3.55) Acct: 5.85 (5.60) proj_loss: -0.6007 (-0.6009) time: 0.9263 data: 0.0003 [11-25 03:13:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [1251/1669] eta: 0:11:26 tlr: 0.00018 tnm: 0.22 Lm: 6.495 (6.424) Lt: 5.634 (5.607) Accm: 3.53 (3.65) Acct: 5.65 (5.78) proj_loss: -0.5856 (-0.5870) time: 0.9263 data: 0.0003 [11-25 03:13:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [1251/1669] eta: 0:11:26 tlr: 0.00018 tnm: 0.22 Lm: 6.402 (6.396) Lt: 5.644 (5.624) Accm: 3.63 (3.74) Acct: 5.73 (5.89) proj_loss: -0.6152 (-0.6083) time: 0.9263 data: 0.0003 [11-25 03:13:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [1251/1669] eta: 0:11:26 tlr: 0.00018 tnm: 0.22 Lm: 6.538 (6.525) Lt: 5.765 (5.771) Accm: 3.30 (3.20) Acct: 5.15 (5.18) proj_loss: -0.6333 (-0.6262) time: 0.9263 data: 0.0003 [11-25 03:13:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [1251/1669] eta: 0:11:26 tlr: 0.00018 tnm: 0.22 Lm: 6.551 (6.567) Lt: 5.857 (5.862) Accm: 3.31 (3.21) Acct: 5.22 (4.92) proj_loss: -0.6183 (-0.6184) time: 0.9264 data: 0.0002 [11-25 03:20:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [1668/1669] eta: 0:00:01 tlr: 0.00018 tnm: 0.23 Lm: 6.510 (6.556) Lt: 5.787 (5.847) Accm: 3.39 (3.25) Acct: 5.20 (4.95) proj_loss: -0.6120 (-0.6129) time: 0.9274 data: 0.0015 [11-25 03:20:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 110/350] Total time: 0:40:40 (1.462 s / it) [11-25 03:20:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [1668/1669] eta: 0:00:01 tlr: 0.00018 tnm: 0.23 Lm: 6.613 (6.587) Lt: 5.816 (5.796) Accm: 3.15 (3.22) Acct: 5.41 (5.47) proj_loss: -0.6136 (-0.6104) time: 0.9274 data: 0.0019 [11-25 03:20:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [1668/1669] eta: 0:00:01 tlr: 0.00018 tnm: 0.23 Lm: 6.529 (6.544) Lt: 5.841 (5.793) Accm: 2.93 (3.09) Acct: 4.41 (4.84) proj_loss: -0.5931 (-0.5909) time: 0.9274 data: 0.0016 [11-25 03:20:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [1668/1669] eta: 0:00:01 tlr: 0.00018 tnm: 0.23 Lm: 6.510 (6.519) Lt: 5.732 (5.768) Accm: 3.53 (3.39) Acct: 5.23 (5.13) proj_loss: -0.6020 (-0.6052) time: 0.9274 data: 0.0016 [11-25 03:20:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [1668/1669] eta: 0:00:01 tlr: 0.00018 tnm: 0.23 Lm: 6.451 (6.492) Lt: 5.603 (5.719) Accm: 3.67 (3.37) Acct: 5.61 (5.45) proj_loss: -0.6306 (-0.6213) time: 0.9274 data: 0.0020 [11-25 03:20:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [1668/1669] eta: 0:00:01 tlr: 0.00018 tnm: 0.23 Lm: 6.512 (6.458) Lt: 5.752 (5.710) Accm: 3.61 (3.50) Acct: 5.82 (5.47) proj_loss: -0.5984 (-0.5988) time: 0.9274 data: 0.0020 [11-25 03:20:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [1668/1669] eta: 0:00:01 tlr: 0.00018 tnm: 0.23 Lm: 6.403 (6.413) Lt: 5.674 (5.639) Accm: 3.79 (3.76) Acct: 5.72 (5.83) proj_loss: -0.6103 (-0.6007) time: 0.9274 data: 0.0016 [11-25 03:20:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 110/350] Total time: 0:40:42 (1.463 s / it) [11-25 03:20:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 110/350] [1668/1669] eta: 0:00:01 tlr: 0.00018 tnm: 0.23 Lm: 6.523 (6.448) Lt: 5.635 (5.650) Accm: 3.50 (3.62) Acct: 5.61 (5.74) proj_loss: -0.5862 (-0.5880) time: 0.9275 data: 0.0018 [11-25 03:20:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 110/350] Total time: 0:40:42 (1.463 s / it) [11-25 03:20:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 110/350] Total time: 0:40:41 (1.463 s / it) [11-25 03:20:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 110/350] Total time: 0:40:41 (1.463 s / it) [11-25 03:20:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 110/350] Total time: 0:40:41 (1.463 s / it) [11-25 03:20:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 110/350] Total time: 0:40:41 (1.463 s / it) [11-25 03:20:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 110/350] Total time: 0:40:41 (1.463 s / it) [11-25 03:20:25] (/home/user/VAR/train.py , line 276)=> [ep110] (training ) Lm: 6.494 (6.494), Lt: 5.737 (5.737), Acc m&t: 3.40 5.36, Remain: 4 days, 7:32:00, Finish: 2024-11-28 18:52 [11-25 03:20:25] (/home/user/VAR/train.py , line 276)=> [ep110] (training ) Lm: 6.494 (6.494), Lt: 5.737 (5.737), Acc m&t: 3.40 5.36, Remain: 4 days, 7:32:04, Finish: 2024-11-28 18:52 [11-25 03:20:25] (/home/user/VAR/train.py , line 276)=> [ep110] (training ) Lm: 6.494 (6.494), Lt: 5.737 (5.737), Acc m&t: 3.40 5.36, Remain: 4 days, 7:31:12, Finish: 2024-11-28 18:51 [11-25 03:20:25] (/home/user/VAR/train.py , line 276)=> [ep110] (training ) Lm: 6.494 (6.494), Lt: 5.737 (5.737), Acc m&t: 3.40 5.36, Remain: 4 days, 7:32:33, Finish: 2024-11-28 18:52 [11-25 03:20:25] (/home/user/VAR/train.py , line 276)=> [ep110] (training ) Lm: 6.494 (6.494), Lt: 5.737 (5.737), Acc m&t: 3.40 5.36, Remain: 4 days, 7:34:05, Finish: 2024-11-28 18:54 [11-25 03:20:25] (/home/user/VAR/train.py , line 276)=> [ep110] (training ) Lm: 6.494 (6.494), Lt: 5.737 (5.737), Acc m&t: 3.40 5.36, Remain: 4 days, 7:33:37, Finish: 2024-11-28 18:54 [11-25 03:20:25] (/home/user/VAR/train.py , line 276)=> [ep110] (training ) Lm: 6.494 (6.494), Lt: 5.737 (5.737), Acc m&t: 3.40 5.36, Remain: 4 days, 7:32:04, Finish: 2024-11-28 18:52 [11-25 03:20:25] (/home/user/VAR/train.py , line 276)=> [ep110] (training ) Lm: 6.494 (6.494), Lt: 5.737 (5.737), Acc m&t: 3.40 5.36, Remain: 4 days, 7:30:01, Finish: 2024-11-28 18:50 [11-25 03:20:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 0/1669] eta: 0:24:44 tlr: 0.00018 tnm: 0.21 Lm: 6.363 (6.363) Lt: 5.603 (5.603) Accm: 3.42 (3.42) Acct: 5.17 (5.17) proj_loss: -0.6229 (-0.6229) time: 0.8897 data: 0.0003 [11-25 03:20:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 0/1669] eta: 0:24:45 tlr: 0.00018 tnm: 0.21 Lm: 6.655 (6.655) Lt: 5.954 (5.954) Accm: 2.97 (2.97) Acct: 4.37 (4.37) proj_loss: -0.5966 (-0.5966) time: 0.8899 data: 0.0004 [11-25 03:20:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 0/1669] eta: 0:24:45 tlr: 0.00018 tnm: 0.21 Lm: 6.369 (6.369) Lt: 5.576 (5.576) Accm: 3.66 (3.66) Acct: 5.61 (5.61) proj_loss: -0.5867 (-0.5867) time: 0.8898 data: 0.0004 [11-25 03:20:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 0/1669] eta: 0:24:45 tlr: 0.00018 tnm: 0.21 Lm: 6.455 (6.455) Lt: 5.603 (5.603) Accm: 3.55 (3.55) Acct: 5.48 (5.48) proj_loss: -0.5894 (-0.5894) time: 0.8902 data: 0.0004 [11-25 03:20:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 0/1669] eta: 0:24:45 tlr: 0.00018 tnm: 0.21 Lm: 6.801 (6.801) Lt: 6.162 (6.162) Accm: 2.48 (2.48) Acct: 3.99 (3.99) proj_loss: -0.6313 (-0.6313) time: 0.8899 data: 0.0003 [11-25 03:20:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 0/1669] eta: 0:24:45 tlr: 0.00018 tnm: 0.21 Lm: 6.189 (6.189) Lt: 5.265 (5.265) Accm: 4.27 (4.27) Acct: 6.61 (6.61) proj_loss: -0.5719 (-0.5719) time: 0.8903 data: 0.0004 [11-25 03:20:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 0/1669] eta: 0:25:46 tlr: 0.00018 tnm: 0.21 Lm: 6.579 (6.579) Lt: 5.831 (5.831) Accm: 3.12 (3.12) Acct: 4.89 (4.89) proj_loss: -0.6186 (-0.6186) time: 0.9264 data: 0.0004 [11-25 03:20:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 0/1669] eta: 0:24:47 tlr: 0.00018 tnm: 0.21 Lm: 6.252 (6.252) Lt: 5.484 (5.484) Accm: 4.28 (4.28) Acct: 6.51 (6.51) proj_loss: -0.6290 (-0.6290) time: 0.8910 data: 0.0004 [11-25 03:26:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 417/1669] eta: 0:19:39 tlr: 0.00018 tnm: 0.22 Lm: 6.472 (6.472) Lt: 5.719 (5.719) Accm: 3.57 (3.57) Acct: 5.53 (5.53) proj_loss: -0.6252 (-0.6252) time: 0.9244 data: 0.0003 [11-25 03:26:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 417/1669] eta: 0:19:40 tlr: 0.00018 tnm: 0.22 Lm: 6.436 (6.436) Lt: 5.701 (5.701) Accm: 3.52 (3.52) Acct: 5.46 (5.46) proj_loss: -0.6152 (-0.6152) time: 0.9244 data: 0.0003 [11-25 03:26:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 417/1669] eta: 0:19:39 tlr: 0.00018 tnm: 0.22 Lm: 6.597 (6.597) Lt: 5.924 (5.924) Accm: 3.10 (3.10) Acct: 4.58 (4.58) proj_loss: -0.6032 (-0.6032) time: 0.9245 data: 0.0002 [11-25 03:26:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 417/1669] eta: 0:19:39 tlr: 0.00018 tnm: 0.22 Lm: 6.470 (6.470) Lt: 5.710 (5.710) Accm: 3.33 (3.33) Acct: 5.41 (5.41) proj_loss: -0.6029 (-0.6029) time: 0.9245 data: 0.0002 [11-25 03:26:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 417/1669] eta: 0:19:39 tlr: 0.00018 tnm: 0.22 Lm: 6.553 (6.553) Lt: 5.787 (5.787) Accm: 3.15 (3.15) Acct: 4.56 (4.56) proj_loss: -0.5943 (-0.5943) time: 0.9244 data: 0.0002 [11-25 03:26:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 417/1669] eta: 0:19:39 tlr: 0.00018 tnm: 0.22 Lm: 6.522 (6.522) Lt: 5.809 (5.809) Accm: 3.23 (3.23) Acct: 5.06 (5.06) proj_loss: -0.6032 (-0.6032) time: 0.9245 data: 0.0002 [11-25 03:26:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 417/1669] eta: 0:19:39 tlr: 0.00018 tnm: 0.22 Lm: 6.346 (6.346) Lt: 5.511 (5.511) Accm: 3.90 (3.90) Acct: 6.15 (6.15) proj_loss: -0.5893 (-0.5893) time: 0.9245 data: 0.0003 [11-25 03:26:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 417/1669] eta: 0:19:39 tlr: 0.00018 tnm: 0.22 Lm: 6.696 (6.696) Lt: 6.002 (6.002) Accm: 2.56 (2.56) Acct: 4.08 (4.08) proj_loss: -0.6129 (-0.6129) time: 0.9245 data: 0.0003 [11-25 03:33:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 834/1669] eta: 0:13:01 tlr: 0.00018 tnm: 0.23 Lm: 6.591 (6.637) Lt: 5.842 (5.934) Accm: 2.64 (2.91) Acct: 4.17 (4.57) proj_loss: -0.5944 (-0.6052) time: 0.9256 data: 0.0002 [11-25 03:33:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 834/1669] eta: 0:13:01 tlr: 0.00018 tnm: 0.23 Lm: 6.578 (6.483) Lt: 5.831 (5.764) Accm: 3.37 (3.47) Acct: 5.03 (5.31) proj_loss: -0.6119 (-0.6088) time: 0.9256 data: 0.0002 [11-25 03:33:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 834/1669] eta: 0:13:01 tlr: 0.00018 tnm: 0.23 Lm: 6.514 (6.485) Lt: 5.695 (5.705) Accm: 3.38 (3.35) Acct: 5.51 (5.44) proj_loss: -0.5829 (-0.5960) time: 0.9256 data: 0.0002 [11-25 03:33:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 834/1669] eta: 0:13:01 tlr: 0.00018 tnm: 0.23 Lm: 6.615 (6.574) Lt: 5.914 (5.830) Accm: 3.15 (3.15) Acct: 4.96 (4.69) proj_loss: -0.5992 (-0.5985) time: 0.9256 data: 0.0003 [11-25 03:33:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 834/1669] eta: 0:13:01 tlr: 0.00018 tnm: 0.23 Lm: 6.369 (6.457) Lt: 5.596 (5.738) Accm: 3.66 (3.76) Acct: 5.61 (5.80) proj_loss: -0.6132 (-0.6066) time: 0.9257 data: 0.0003 [11-25 03:33:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 834/1669] eta: 0:13:01 tlr: 0.00018 tnm: 0.23 Lm: 6.540 (6.566) Lt: 5.895 (5.891) Accm: 3.23 (3.27) Acct: 4.79 (4.98) proj_loss: -0.6097 (-0.6088) time: 0.9257 data: 0.0003 [11-25 03:33:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 834/1669] eta: 0:13:01 tlr: 0.00018 tnm: 0.23 Lm: 6.502 (6.439) Lt: 5.758 (5.649) Accm: 3.54 (3.68) Acct: 5.68 (5.69) proj_loss: -0.6067 (-0.6080) time: 0.9257 data: 0.0003 [11-25 03:33:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [ 834/1669] eta: 0:13:01 tlr: 0.00018 tnm: 0.23 Lm: 6.518 (6.487) Lt: 5.734 (5.724) Accm: 3.29 (3.48) Acct: 5.03 (5.36) proj_loss: -0.6214 (-0.6204) time: 0.9256 data: 0.0003 [11-25 03:39:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [1251/1669] eta: 0:06:29 tlr: 0.00018 tnm: 0.22 Lm: 6.579 (6.572) Lt: 5.861 (5.860) Accm: 3.24 (3.21) Acct: 4.96 (4.92) proj_loss: -0.6072 (-0.6072) time: 0.9237 data: 0.0002 [11-25 03:39:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [1251/1669] eta: 0:06:29 tlr: 0.00018 tnm: 0.22 Lm: 6.552 (6.553) Lt: 5.823 (5.805) Accm: 3.19 (3.17) Acct: 5.20 (4.88) proj_loss: -0.5980 (-0.5981) time: 0.9238 data: 0.0002 [11-25 03:39:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [1251/1669] eta: 0:06:29 tlr: 0.00018 tnm: 0.22 Lm: 6.687 (6.673) Lt: 5.986 (5.983) Accm: 2.77 (2.91) Acct: 4.29 (4.53) proj_loss: -0.6129 (-0.6148) time: 0.9237 data: 0.0002 [11-25 03:39:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [1251/1669] eta: 0:06:29 tlr: 0.00018 tnm: 0.22 Lm: 6.438 (6.446) Lt: 5.661 (5.686) Accm: 3.40 (3.45) Acct: 5.58 (5.56) proj_loss: -0.5921 (-0.5973) time: 0.9238 data: 0.0002 [11-25 03:39:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [1251/1669] eta: 0:06:29 tlr: 0.00018 tnm: 0.22 Lm: 6.522 (6.523) Lt: 5.819 (5.830) Accm: 3.23 (3.49) Acct: 5.06 (5.28) proj_loss: -0.6165 (-0.6114) time: 0.9238 data: 0.0002 [11-25 03:39:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [1251/1669] eta: 0:06:29 tlr: 0.00018 tnm: 0.22 Lm: 6.430 (6.418) Lt: 5.663 (5.629) Accm: 3.62 (3.69) Acct: 5.61 (5.66) proj_loss: -0.6074 (-0.6081) time: 0.9237 data: 0.0003 [11-25 03:39:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [1251/1669] eta: 0:06:29 tlr: 0.00018 tnm: 0.22 Lm: 6.532 (6.502) Lt: 5.753 (5.736) Accm: 3.07 (3.32) Acct: 4.79 (5.16) proj_loss: -0.6161 (-0.6171) time: 0.9238 data: 0.0003 [11-25 03:39:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [1251/1669] eta: 0:06:29 tlr: 0.00018 tnm: 0.22 Lm: 6.521 (6.514) Lt: 5.859 (5.789) Accm: 3.42 (3.37) Acct: 5.29 (5.29) proj_loss: -0.6032 (-0.6046) time: 0.9238 data: 0.0003 [11-25 03:46:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.540 (6.523) Lt: 5.824 (5.783) Accm: 3.38 (3.37) Acct: 5.68 (5.37) proj_loss: -0.5966 (-0.5976) time: 0.9282 data: 0.0016 [11-25 03:46:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 111/350] Total time: 0:25:53 (0.931 s / it) [11-25 03:46:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.490 (6.515) Lt: 5.731 (5.774) Accm: 3.23 (3.28) Acct: 5.37 (4.98) proj_loss: -0.5992 (-0.6035) time: 0.9282 data: 0.0016 [11-25 03:46:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.630 (6.544) Lt: 5.834 (5.831) Accm: 2.97 (3.39) Acct: 5.10 (5.24) proj_loss: -0.6132 (-0.6078) time: 0.9282 data: 0.0015 [11-25 03:46:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.591 (6.619) Lt: 5.842 (5.942) Accm: 2.90 (3.00) Acct: 4.41 (4.56) proj_loss: -0.6313 (-0.6187) time: 0.9282 data: 0.0014 [11-25 03:46:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.578 (6.565) Lt: 5.852 (5.859) Accm: 3.37 (3.26) Acct: 5.03 (5.04) proj_loss: -0.6119 (-0.6090) time: 0.9282 data: 0.0016 [11-25 03:46:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.514 (6.479) Lt: 5.695 (5.718) Accm: 3.38 (3.39) Acct: 5.51 (5.45) proj_loss: -0.5995 (-0.5977) time: 0.9282 data: 0.0016 [11-25 03:46:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.547 (6.554) Lt: 5.773 (5.804) Accm: 2.86 (3.19) Acct: 4.55 (4.97) proj_loss: -0.6214 (-0.6181) time: 0.9282 data: 0.0015 [11-25 03:46:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 111/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.502 (6.493) Lt: 5.758 (5.721) Accm: 3.54 (3.48) Acct: 5.54 (5.37) proj_loss: -0.6081 (-0.6101) time: 0.9283 data: 0.0018 [11-25 03:46:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 111/350] Total time: 0:25:53 (0.931 s / it) [11-25 03:46:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 111/350] Total time: 0:25:53 (0.931 s / it) [11-25 03:46:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 111/350] Total time: 0:25:53 (0.931 s / it) [11-25 03:46:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 111/350] Total time: 0:25:53 (0.931 s / it) [11-25 03:46:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 111/350] Total time: 0:25:53 (0.931 s / it) [11-25 03:46:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 111/350] Total time: 0:25:53 (0.931 s / it) [11-25 03:46:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 111/350] Total time: 0:25:53 (0.931 s / it) [11-25 03:46:19] (/home/user/VAR/train.py , line 276)=> [ep111] (training ) Lm: 6.494 (6.497), Lt: 5.737 (5.746), Acc m&t: 3.40 5.36, Remain: 4 days, 7:13:49, Finish: 2024-11-28 19:00 [11-25 03:46:19] (/home/user/VAR/train.py , line 276)=> [ep111] (training ) Lm: 6.494 (6.497), Lt: 5.737 (5.746), Acc m&t: 3.40 5.36, Remain: 4 days, 7:10:06, Finish: 2024-11-28 18:56 [11-25 03:46:19] (/home/user/VAR/train.py , line 276)=> [ep111] (training ) Lm: 6.494 (6.497), Lt: 5.737 (5.746), Acc m&t: 3.40 5.36, Remain: 4 days, 7:09:17, Finish: 2024-11-28 18:55 [11-25 03:46:19] (/home/user/VAR/train.py , line 276)=> [ep111] (training ) Lm: 6.494 (6.497), Lt: 5.737 (5.746), Acc m&t: 3.40 5.36, Remain: 4 days, 7:07:44, Finish: 2024-11-28 18:54 [11-25 03:46:19] (/home/user/VAR/train.py , line 276)=> [ep111] (training ) Lm: 6.494 (6.497), Lt: 5.737 (5.746), Acc m&t: 3.40 5.36, Remain: 4 days, 7:08:33, Finish: 2024-11-28 18:54 [11-25 03:46:19] (/home/user/VAR/train.py , line 276)=> [ep111] (training ) Lm: 6.494 (6.497), Lt: 5.737 (5.746), Acc m&t: 3.40 5.36, Remain: 4 days, 7:08:51, Finish: 2024-11-28 18:55 [11-25 03:46:19] (/home/user/VAR/train.py , line 276)=> [ep111] (training ) Lm: 6.494 (6.497), Lt: 5.737 (5.746), Acc m&t: 3.40 5.36, Remain: 4 days, 7:08:16, Finish: 2024-11-28 18:54 [11-25 03:46:19] (/home/user/VAR/train.py , line 276)=> [ep111] (training ) Lm: 6.494 (6.497), Lt: 5.737 (5.746), Acc m&t: 3.40 5.36, Remain: 4 days, 7:10:54, Finish: 2024-11-28 18:57 [11-25 03:46:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 0/1669] eta: 0:24:58 tlr: 0.00018 tnm: 0.24 Lm: 6.307 (6.307) Lt: 5.556 (5.556) Accm: 3.74 (3.74) Acct: 5.72 (5.72) proj_loss: -0.6028 (-0.6028) time: 0.8977 data: 0.0003 [11-25 03:46:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 0/1669] eta: 0:24:59 tlr: 0.00018 tnm: 0.24 Lm: 6.666 (6.666) Lt: 5.976 (5.976) Accm: 3.19 (3.19) Acct: 4.92 (4.92) proj_loss: -0.6134 (-0.6134) time: 0.8986 data: 0.0004 [11-25 03:46:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 0/1669] eta: 0:24:58 tlr: 0.00018 tnm: 0.24 Lm: 6.489 (6.489) Lt: 5.780 (5.780) Accm: 3.34 (3.34) Acct: 5.37 (5.37) proj_loss: -0.6024 (-0.6024) time: 0.8980 data: 0.0003 [11-25 03:46:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 0/1669] eta: 0:24:58 tlr: 0.00018 tnm: 0.24 Lm: 6.665 (6.665) Lt: 5.915 (5.915) Accm: 2.86 (2.86) Acct: 4.51 (4.51) proj_loss: -0.6193 (-0.6193) time: 0.8978 data: 0.0003 [11-25 03:46:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 0/1669] eta: 0:24:59 tlr: 0.00018 tnm: 0.24 Lm: 6.703 (6.703) Lt: 5.979 (5.979) Accm: 2.83 (2.83) Acct: 4.41 (4.41) proj_loss: -0.6201 (-0.6201) time: 0.8987 data: 0.0004 [11-25 03:46:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 0/1669] eta: 0:25:00 tlr: 0.00018 tnm: 0.24 Lm: 6.568 (6.568) Lt: 5.824 (5.824) Accm: 2.99 (2.99) Acct: 4.68 (4.68) proj_loss: -0.5671 (-0.5671) time: 0.8991 data: 0.0004 [11-25 03:46:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 0/1669] eta: 0:25:00 tlr: 0.00018 tnm: 0.24 Lm: 6.694 (6.694) Lt: 5.963 (5.963) Accm: 2.80 (2.80) Acct: 4.61 (4.61) proj_loss: -0.5960 (-0.5960) time: 0.8992 data: 0.0004 [11-25 03:46:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 0/1669] eta: 0:25:02 tlr: 0.00018 tnm: 0.24 Lm: 6.600 (6.600) Lt: 5.764 (5.764) Accm: 3.23 (3.23) Acct: 5.58 (5.58) proj_loss: -0.6386 (-0.6386) time: 0.9003 data: 0.0003 [11-25 03:52:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 417/1669] eta: 0:19:18 tlr: 0.00018 tnm: 0.22 Lm: 6.489 (6.489) Lt: 5.699 (5.699) Accm: 3.55 (3.55) Acct: 5.82 (5.82) proj_loss: -0.6312 (-0.6312) time: 0.9270 data: 0.0003 [11-25 03:52:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 417/1669] eta: 0:19:18 tlr: 0.00018 tnm: 0.22 Lm: 6.495 (6.495) Lt: 5.760 (5.760) Accm: 3.28 (3.28) Acct: 5.25 (5.25) proj_loss: -0.5861 (-0.5861) time: 0.9270 data: 0.0002 [11-25 03:52:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 417/1669] eta: 0:19:18 tlr: 0.00018 tnm: 0.22 Lm: 6.610 (6.610) Lt: 5.891 (5.891) Accm: 3.29 (3.29) Acct: 5.01 (5.01) proj_loss: -0.6134 (-0.6134) time: 0.9270 data: 0.0002 [11-25 03:52:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 417/1669] eta: 0:19:18 tlr: 0.00018 tnm: 0.22 Lm: 6.636 (6.636) Lt: 5.934 (5.934) Accm: 2.76 (2.76) Acct: 4.29 (4.29) proj_loss: -0.6170 (-0.6170) time: 0.9270 data: 0.0002 [11-25 03:52:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 417/1669] eta: 0:19:18 tlr: 0.00018 tnm: 0.22 Lm: 6.436 (6.436) Lt: 5.688 (5.688) Accm: 3.68 (3.68) Acct: 5.70 (5.70) proj_loss: -0.5958 (-0.5958) time: 0.9270 data: 0.0002 [11-25 03:52:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 417/1669] eta: 0:19:18 tlr: 0.00018 tnm: 0.22 Lm: 6.651 (6.651) Lt: 5.918 (5.918) Accm: 2.99 (2.99) Acct: 4.86 (4.86) proj_loss: -0.6004 (-0.6004) time: 0.9270 data: 0.0003 [11-25 03:52:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 417/1669] eta: 0:19:18 tlr: 0.00018 tnm: 0.22 Lm: 6.508 (6.508) Lt: 5.746 (5.746) Accm: 3.21 (3.21) Acct: 4.96 (4.96) proj_loss: -0.5832 (-0.5832) time: 0.9270 data: 0.0003 [11-25 03:52:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 417/1669] eta: 0:19:18 tlr: 0.00018 tnm: 0.22 Lm: 6.688 (6.688) Lt: 5.954 (5.954) Accm: 2.91 (2.91) Acct: 4.48 (4.48) proj_loss: -0.6152 (-0.6152) time: 0.9270 data: 0.0003 [11-25 03:59:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 834/1669] eta: 0:12:52 tlr: 0.00018 tnm: 0.22 Lm: 6.673 (6.596) Lt: 5.928 (5.835) Accm: 3.00 (3.20) Acct: 4.55 (5.07) proj_loss: -0.6102 (-0.6130) time: 0.9238 data: 0.0003 [11-25 03:59:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 834/1669] eta: 0:12:52 tlr: 0.00018 tnm: 0.22 Lm: 6.502 (6.573) Lt: 5.780 (5.830) Accm: 3.22 (3.06) Acct: 5.13 (4.86) proj_loss: -0.6024 (-0.5950) time: 0.9238 data: 0.0002 [11-25 03:59:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 834/1669] eta: 0:12:52 tlr: 0.00018 tnm: 0.22 Lm: 6.554 (6.584) Lt: 5.807 (5.831) Accm: 3.19 (3.25) Acct: 5.10 (5.06) proj_loss: -0.6135 (-0.6174) time: 0.9238 data: 0.0002 [11-25 03:59:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 834/1669] eta: 0:12:52 tlr: 0.00018 tnm: 0.22 Lm: 6.558 (6.512) Lt: 5.764 (5.760) Accm: 3.23 (3.44) Acct: 5.58 (5.44) proj_loss: -0.6336 (-0.6320) time: 0.9238 data: 0.0003 [11-25 03:59:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 834/1669] eta: 0:12:52 tlr: 0.00018 tnm: 0.22 Lm: 6.531 (6.468) Lt: 5.791 (5.723) Accm: 3.64 (3.67) Acct: 5.68 (5.66) proj_loss: -0.6028 (-0.5996) time: 0.9238 data: 0.0002 [11-25 03:59:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 834/1669] eta: 0:12:52 tlr: 0.00018 tnm: 0.22 Lm: 6.568 (6.530) Lt: 5.792 (5.761) Accm: 3.07 (3.16) Acct: 5.06 (4.99) proj_loss: -0.5925 (-0.5863) time: 0.9238 data: 0.0003 [11-25 03:59:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 834/1669] eta: 0:12:52 tlr: 0.00018 tnm: 0.22 Lm: 6.606 (6.623) Lt: 5.915 (5.912) Accm: 2.86 (2.88) Acct: 4.51 (4.40) proj_loss: -0.6193 (-0.6185) time: 0.9238 data: 0.0002 [11-25 03:59:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [ 834/1669] eta: 0:12:52 tlr: 0.00018 tnm: 0.22 Lm: 6.666 (6.656) Lt: 5.894 (5.910) Accm: 3.15 (3.04) Acct: 4.82 (4.84) proj_loss: -0.6048 (-0.6074) time: 0.9238 data: 0.0003 [11-25 04:05:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [1251/1669] eta: 0:06:29 tlr: 0.00018 tnm: 0.23 Lm: 6.524 (6.566) Lt: 5.760 (5.802) Accm: 3.12 (3.06) Acct: 5.06 (4.89) proj_loss: -0.5988 (-0.5950) time: 0.9253 data: 0.0002 [11-25 04:05:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [1251/1669] eta: 0:06:29 tlr: 0.00018 tnm: 0.23 Lm: 6.598 (6.599) Lt: 5.849 (5.846) Accm: 3.18 (3.13) Acct: 5.01 (4.93) proj_loss: -0.6194 (-0.6204) time: 0.9253 data: 0.0003 [11-25 04:05:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [1251/1669] eta: 0:06:29 tlr: 0.00018 tnm: 0.23 Lm: 6.601 (6.529) Lt: 5.892 (5.801) Accm: 2.99 (3.25) Acct: 4.56 (4.94) proj_loss: -0.6203 (-0.6242) time: 0.9253 data: 0.0003 [11-25 04:05:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [1251/1669] eta: 0:06:29 tlr: 0.00018 tnm: 0.23 Lm: 6.579 (6.539) Lt: 5.824 (5.798) Accm: 3.23 (3.37) Acct: 5.18 (5.28) proj_loss: -0.6287 (-0.6290) time: 0.9253 data: 0.0003 [11-25 04:05:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [1251/1669] eta: 0:06:29 tlr: 0.00018 tnm: 0.23 Lm: 6.524 (6.518) Lt: 5.765 (5.755) Accm: 3.25 (3.38) Acct: 5.15 (5.32) proj_loss: -0.5942 (-0.5887) time: 0.9253 data: 0.0002 [11-25 04:05:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [1251/1669] eta: 0:06:29 tlr: 0.00018 tnm: 0.23 Lm: 6.419 (6.426) Lt: 5.707 (5.698) Accm: 3.69 (3.73) Acct: 5.70 (5.72) proj_loss: -0.6050 (-0.6085) time: 0.9253 data: 0.0002 [11-25 04:05:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [1251/1669] eta: 0:06:29 tlr: 0.00018 tnm: 0.23 Lm: 6.637 (6.573) Lt: 5.883 (5.810) Accm: 3.16 (3.27) Acct: 4.96 (5.26) proj_loss: -0.6088 (-0.6087) time: 0.9253 data: 0.0003 [11-25 04:05:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [1251/1669] eta: 0:06:29 tlr: 0.00018 tnm: 0.23 Lm: 6.687 (6.622) Lt: 5.954 (5.878) Accm: 2.91 (3.09) Acct: 4.48 (4.86) proj_loss: -0.6152 (-0.6156) time: 0.9253 data: 0.0003 [11-25 04:12:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.673 (6.590) Lt: 5.928 (5.858) Accm: 3.00 (3.18) Acct: 4.55 (5.01) proj_loss: -0.6102 (-0.6073) time: 0.9294 data: 0.0017 [11-25 04:12:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 112/350] Total time: 0:25:54 (0.931 s / it) [11-25 04:12:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.481 (6.504) Lt: 5.738 (5.746) Accm: 3.42 (3.50) Acct: 5.23 (5.54) proj_loss: -0.5960 (-0.5987) time: 0.9294 data: 0.0022 [11-25 04:12:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.531 (6.458) Lt: 5.791 (5.743) Accm: 3.64 (3.57) Acct: 5.68 (5.52) proj_loss: -0.6028 (-0.6043) time: 0.9294 data: 0.0018 [11-25 04:12:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.502 (6.530) Lt: 5.741 (5.767) Accm: 3.22 (3.15) Acct: 5.13 (4.94) proj_loss: -0.5952 (-0.5937) time: 0.9294 data: 0.0017 [11-25 04:12:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.597 (6.479) Lt: 5.868 (5.740) Accm: 3.12 (3.45) Acct: 4.61 (5.32) proj_loss: -0.6193 (-0.6185) time: 0.9294 data: 0.0017 [11-25 04:12:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.642 (6.611) Lt: 5.892 (5.875) Accm: 3.18 (3.10) Acct: 4.92 (4.89) proj_loss: -0.6135 (-0.6167) time: 0.9294 data: 0.0019 [11-25 04:12:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.558 (6.516) Lt: 5.764 (5.775) Accm: 3.23 (3.40) Acct: 5.58 (5.37) proj_loss: -0.6242 (-0.6280) time: 0.9294 data: 0.0018 [11-25 04:12:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 112/350] [1668/1669] eta: 0:00:00 tlr: 0.00018 tnm: 0.23 Lm: 6.608 (6.495) Lt: 5.873 (5.718) Accm: 3.18 (3.61) Acct: 5.10 (5.80) proj_loss: -0.6128 (-0.6129) time: 0.9294 data: 0.0021 [11-25 04:12:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 112/350] Total time: 0:25:54 (0.931 s / it) [11-25 04:12:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 112/350] Total time: 0:25:54 (0.931 s / it) [11-25 04:12:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 112/350] Total time: 0:25:54 (0.931 s / it) [11-25 04:12:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 112/350] Total time: 0:25:54 (0.931 s / it) [11-25 04:12:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 112/350] Total time: 0:25:54 (0.931 s / it) [11-25 04:12:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 112/350] Total time: 0:25:54 (0.931 s / it) [11-25 04:12:13] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 112/350] Total time: 0:25:54 (0.931 s / it) [11-25 04:12:13] (/home/user/VAR/train.py , line 276)=> [ep112] (training ) Lm: 6.489 (6.489), Lt: 5.731 (5.731), Acc m&t: 3.42 5.38, Remain: 4 days, 6:48:17, Finish: 2024-11-28 19:00 [11-25 04:12:13] (/home/user/VAR/train.py , line 276)=> [ep112] (training ) Lm: 6.489 (6.489), Lt: 5.731 (5.731), Acc m&t: 3.42 5.38, Remain: 4 days, 6:47:51, Finish: 2024-11-28 19:00 [11-25 04:12:13] (/home/user/VAR/train.py , line 276)=> [ep112] (training ) Lm: 6.489 (6.489), Lt: 5.731 (5.731), Acc m&t: 3.42 5.38, Remain: 4 days, 6:48:32, Finish: 2024-11-28 19:00 [11-25 04:12:13] (/home/user/VAR/train.py , line 276)=> [ep112] (training ) Lm: 6.489 (6.489), Lt: 5.731 (5.731), Acc m&t: 3.42 5.38, Remain: 4 days, 6:50:36, Finish: 2024-11-28 19:02 [11-25 04:12:13] (/home/user/VAR/train.py , line 276)=> [ep112] (training ) Lm: 6.489 (6.489), Lt: 5.731 (5.731), Acc m&t: 3.42 5.38, Remain: 4 days, 6:53:44, Finish: 2024-11-28 19:05 [11-25 04:12:13] (/home/user/VAR/train.py , line 276)=> [ep112] (training ) Lm: 6.489 (6.489), Lt: 5.731 (5.731), Acc m&t: 3.42 5.38, Remain: 4 days, 6:49:19, Finish: 2024-11-28 19:01 [11-25 04:12:13] (/home/user/VAR/train.py , line 276)=> [ep112] (training ) Lm: 6.489 (6.489), Lt: 5.731 (5.731), Acc m&t: 3.42 5.38, Remain: 4 days, 6:48:57, Finish: 2024-11-28 19:01 [11-25 04:12:13] (/home/user/VAR/train.py , line 276)=> [ep112] (training ) Lm: 6.489 (6.489), Lt: 5.731 (5.731), Acc m&t: 3.42 5.38, Remain: 4 days, 6:43:48, Finish: 2024-11-28 18:56 [11-25 04:12:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 0/1669] eta: 0:25:16 tlr: 0.00018 tnm: 0.22 Lm: 6.513 (6.513) Lt: 5.795 (5.795) Accm: 3.51 (3.51) Acct: 5.85 (5.85) proj_loss: -0.6279 (-0.6279) time: 0.9086 data: 0.0003 [11-25 04:12:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 0/1669] eta: 0:25:16 tlr: 0.00018 tnm: 0.22 Lm: 6.404 (6.404) Lt: 5.694 (5.694) Accm: 3.80 (3.80) Acct: 5.41 (5.41) proj_loss: -0.5995 (-0.5995) time: 0.9088 data: 0.0003 [11-25 04:12:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 0/1669] eta: 0:25:15 tlr: 0.00018 tnm: 0.22 Lm: 6.479 (6.479) Lt: 5.672 (5.672) Accm: 3.53 (3.53) Acct: 5.41 (5.41) proj_loss: -0.6233 (-0.6233) time: 0.9079 data: 0.0004 [11-25 04:12:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 0/1669] eta: 0:25:17 tlr: 0.00018 tnm: 0.22 Lm: 6.614 (6.614) Lt: 5.882 (5.882) Accm: 2.84 (2.84) Acct: 4.96 (4.96) proj_loss: -0.6154 (-0.6154) time: 0.9091 data: 0.0003 [11-25 04:12:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 0/1669] eta: 0:25:17 tlr: 0.00018 tnm: 0.22 Lm: 6.608 (6.608) Lt: 5.870 (5.870) Accm: 3.21 (3.21) Acct: 5.13 (5.13) proj_loss: -0.5963 (-0.5963) time: 0.9092 data: 0.0003 [11-25 04:12:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 0/1669] eta: 0:25:17 tlr: 0.00018 tnm: 0.22 Lm: 6.396 (6.396) Lt: 5.704 (5.704) Accm: 3.89 (3.89) Acct: 6.06 (6.06) proj_loss: -0.6188 (-0.6188) time: 0.9091 data: 0.0004 [11-25 04:12:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 0/1669] eta: 0:25:17 tlr: 0.00018 tnm: 0.22 Lm: 6.454 (6.454) Lt: 5.715 (5.715) Accm: 3.50 (3.50) Acct: 5.58 (5.58) proj_loss: -0.5922 (-0.5922) time: 0.9091 data: 0.0004 [11-25 04:12:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 0/1669] eta: 0:25:17 tlr: 0.00018 tnm: 0.22 Lm: 6.468 (6.468) Lt: 5.796 (5.796) Accm: 3.26 (3.26) Acct: 4.68 (4.68) proj_loss: -0.5815 (-0.5815) time: 0.9093 data: 0.0004 [11-25 04:18:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 417/1669] eta: 0:19:18 tlr: 0.00018 tnm: 0.23 Lm: 6.551 (6.551) Lt: 5.833 (5.833) Accm: 3.19 (3.19) Acct: 4.98 (4.98) proj_loss: -0.5863 (-0.5863) time: 0.9227 data: 0.0003 [11-25 04:18:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 417/1669] eta: 0:19:18 tlr: 0.00018 tnm: 0.23 Lm: 6.550 (6.550) Lt: 5.865 (5.865) Accm: 3.16 (3.16) Acct: 4.53 (4.53) proj_loss: -0.5968 (-0.5968) time: 0.9227 data: 0.0002 [11-25 04:18:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 417/1669] eta: 0:19:18 tlr: 0.00018 tnm: 0.23 Lm: 6.568 (6.568) Lt: 5.801 (5.801) Accm: 3.15 (3.15) Acct: 5.08 (5.08) proj_loss: -0.5927 (-0.5927) time: 0.9227 data: 0.0003 [11-25 04:18:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 417/1669] eta: 0:19:18 tlr: 0.00018 tnm: 0.23 Lm: 6.426 (6.426) Lt: 5.663 (5.663) Accm: 3.53 (3.53) Acct: 5.66 (5.66) proj_loss: -0.5977 (-0.5977) time: 0.9227 data: 0.0003 [11-25 04:18:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 417/1669] eta: 0:19:18 tlr: 0.00018 tnm: 0.23 Lm: 6.521 (6.521) Lt: 5.766 (5.766) Accm: 3.40 (3.40) Acct: 5.37 (5.37) proj_loss: -0.6052 (-0.6052) time: 0.9227 data: 0.0003 [11-25 04:18:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 417/1669] eta: 0:19:18 tlr: 0.00018 tnm: 0.23 Lm: 6.599 (6.599) Lt: 5.914 (5.914) Accm: 3.14 (3.14) Acct: 5.04 (5.04) proj_loss: -0.6136 (-0.6136) time: 0.9227 data: 0.0003 [11-25 04:18:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 417/1669] eta: 0:19:18 tlr: 0.00018 tnm: 0.23 Lm: 6.483 (6.483) Lt: 5.747 (5.747) Accm: 3.23 (3.23) Acct: 5.10 (5.10) proj_loss: -0.6047 (-0.6047) time: 0.9227 data: 0.0003 [11-25 04:18:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 417/1669] eta: 0:19:18 tlr: 0.00018 tnm: 0.23 Lm: 6.463 (6.463) Lt: 5.717 (5.717) Accm: 3.40 (3.40) Acct: 5.72 (5.72) proj_loss: -0.6171 (-0.6171) time: 0.9227 data: 0.0003 [11-25 04:25:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 834/1669] eta: 0:12:52 tlr: 0.00017 tnm: 0.24 Lm: 6.522 (6.483) Lt: 5.804 (5.746) Accm: 3.41 (3.40) Acct: 5.30 (5.58) proj_loss: -0.6154 (-0.6097) time: 0.9250 data: 0.0002 [11-25 04:25:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 834/1669] eta: 0:12:52 tlr: 0.00017 tnm: 0.24 Lm: 6.529 (6.483) Lt: 5.731 (5.707) Accm: 3.21 (3.26) Acct: 5.13 (5.29) proj_loss: -0.5890 (-0.5911) time: 0.9250 data: 0.0002 [11-25 04:25:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 834/1669] eta: 0:12:52 tlr: 0.00017 tnm: 0.24 Lm: 6.479 (6.415) Lt: 5.672 (5.628) Accm: 3.53 (3.74) Acct: 5.41 (6.13) proj_loss: -0.6000 (-0.6034) time: 0.9250 data: 0.0003 [11-25 04:25:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 834/1669] eta: 0:12:52 tlr: 0.00017 tnm: 0.24 Lm: 6.614 (6.604) Lt: 5.852 (5.894) Accm: 2.88 (3.05) Acct: 5.17 (5.08) proj_loss: -0.6071 (-0.6114) time: 0.9250 data: 0.0002 [11-25 04:25:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 834/1669] eta: 0:12:52 tlr: 0.00017 tnm: 0.24 Lm: 6.454 (6.453) Lt: 5.715 (5.698) Accm: 3.50 (3.43) Acct: 5.58 (5.43) proj_loss: -0.5931 (-0.6008) time: 0.9250 data: 0.0003 [11-25 04:25:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 834/1669] eta: 0:12:52 tlr: 0.00017 tnm: 0.24 Lm: 6.563 (6.555) Lt: 5.912 (5.881) Accm: 2.75 (3.03) Acct: 4.34 (4.47) proj_loss: -0.5990 (-0.5975) time: 0.9251 data: 0.0003 [11-25 04:25:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 834/1669] eta: 0:12:52 tlr: 0.00017 tnm: 0.24 Lm: 6.456 (6.481) Lt: 5.704 (5.746) Accm: 3.18 (3.30) Acct: 5.27 (5.26) proj_loss: -0.6188 (-0.6057) time: 0.9250 data: 0.0003 [11-25 04:25:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [ 834/1669] eta: 0:12:52 tlr: 0.00017 tnm: 0.24 Lm: 6.468 (6.509) Lt: 5.796 (5.760) Accm: 3.26 (3.30) Acct: 5.27 (5.31) proj_loss: -0.5815 (-0.5795) time: 0.9250 data: 0.0003 [11-25 04:31:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [1251/1669] eta: 0:06:31 tlr: 0.00017 tnm: 0.24 Lm: 6.551 (6.578) Lt: 5.833 (5.824) Accm: 3.19 (3.17) Acct: 5.06 (5.20) proj_loss: -0.5863 (-0.5854) time: 0.9266 data: 0.0003 [11-25 04:31:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [1251/1669] eta: 0:06:31 tlr: 0.00017 tnm: 0.24 Lm: 6.531 (6.497) Lt: 5.790 (5.754) Accm: 3.25 (3.33) Acct: 5.13 (5.38) proj_loss: -0.6105 (-0.6087) time: 0.9265 data: 0.0003 [11-25 04:31:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [1251/1669] eta: 0:06:31 tlr: 0.00017 tnm: 0.24 Lm: 6.494 (6.477) Lt: 5.670 (5.682) Accm: 3.29 (3.29) Acct: 5.42 (5.41) proj_loss: -0.5927 (-0.5931) time: 0.9265 data: 0.0003 [11-25 04:31:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [1251/1669] eta: 0:06:31 tlr: 0.00017 tnm: 0.24 Lm: 6.563 (6.557) Lt: 5.824 (5.820) Accm: 3.20 (3.18) Acct: 5.25 (5.15) proj_loss: -0.6130 (-0.6133) time: 0.9265 data: 0.0003 [11-25 04:31:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [1251/1669] eta: 0:06:31 tlr: 0.00017 tnm: 0.24 Lm: 6.485 (6.489) Lt: 5.757 (5.762) Accm: 3.25 (3.30) Acct: 5.13 (5.19) proj_loss: -0.6203 (-0.6152) time: 0.9265 data: 0.0002 [11-25 04:31:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [1251/1669] eta: 0:06:31 tlr: 0.00017 tnm: 0.24 Lm: 6.568 (6.559) Lt: 5.884 (5.875) Accm: 3.04 (3.10) Acct: 4.65 (4.59) proj_loss: -0.5971 (-0.5970) time: 0.9266 data: 0.0002 [11-25 04:31:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [1251/1669] eta: 0:06:31 tlr: 0.00017 tnm: 0.24 Lm: 6.518 (6.451) Lt: 5.718 (5.662) Accm: 3.41 (3.63) Acct: 5.37 (5.89) proj_loss: -0.6066 (-0.6059) time: 0.9265 data: 0.0003 [11-25 04:31:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [1251/1669] eta: 0:06:31 tlr: 0.00017 tnm: 0.24 Lm: 6.423 (6.412) Lt: 5.658 (5.643) Accm: 3.66 (3.63) Acct: 5.84 (5.72) proj_loss: -0.5966 (-0.6006) time: 0.9266 data: 0.0003 [11-25 04:38:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.454 (6.422) Lt: 5.715 (5.662) Accm: 3.50 (3.55) Acct: 5.58 (5.59) proj_loss: -0.6000 (-0.6018) time: 0.9282 data: 0.0019 [11-25 04:38:12] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 113/350] Total time: 0:25:58 (0.934 s / it) [11-25 04:38:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.614 (6.592) Lt: 5.852 (5.860) Accm: 2.88 (3.09) Acct: 5.17 (4.99) proj_loss: -0.6170 (-0.6140) time: 0.9282 data: 0.0015 [11-25 04:38:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.573 (6.579) Lt: 5.912 (5.889) Accm: 3.19 (3.12) Acct: 4.96 (4.68) proj_loss: -0.5990 (-0.6023) time: 0.9282 data: 0.0016 [11-25 04:38:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.522 (6.448) Lt: 5.777 (5.710) Accm: 3.41 (3.52) Acct: 5.30 (5.63) proj_loss: -0.6154 (-0.6142) time: 0.9282 data: 0.0014 [11-25 04:38:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.556 (6.489) Lt: 5.764 (5.722) Accm: 3.32 (3.57) Acct: 5.34 (5.74) proj_loss: -0.6107 (-0.6068) time: 0.9283 data: 0.0019 [11-25 04:38:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.493 (6.490) Lt: 5.749 (5.759) Accm: 3.29 (3.30) Acct: 5.17 (5.19) proj_loss: -0.6219 (-0.6171) time: 0.9283 data: 0.0016 [11-25 04:38:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.460 (6.473) Lt: 5.731 (5.706) Accm: 3.21 (3.24) Acct: 5.13 (5.26) proj_loss: -0.5963 (-0.5989) time: 0.9283 data: 0.0016 [11-25 04:38:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 113/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.508 (6.564) Lt: 5.796 (5.805) Accm: 3.26 (3.21) Acct: 5.13 (5.19) proj_loss: -0.5910 (-0.5949) time: 0.9283 data: 0.0017 [11-25 04:38:12] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 113/350] Total time: 0:25:58 (0.934 s / it) [11-25 04:38:12] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 113/350] Total time: 0:25:58 (0.934 s / it) [11-25 04:38:12] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 113/350] Total time: 0:25:58 (0.934 s / it) [11-25 04:38:12] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 113/350] Total time: 0:25:58 (0.934 s / it) [11-25 04:38:12] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 113/350] Total time: 0:25:58 (0.934 s / it) [11-25 04:38:12] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 113/350] Total time: 0:25:58 (0.934 s / it) [11-25 04:38:12] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 113/350] Total time: 0:25:58 (0.934 s / it) [11-25 04:38:12] (/home/user/VAR/train.py , line 276)=> [ep113] (training ) Lm: 6.488 (6.488), Lt: 5.731 (5.734), Acc m&t: 3.42 5.38, Remain: 4 days, 6:23:39, Finish: 2024-11-28 19:01 [11-25 04:38:12] (/home/user/VAR/train.py , line 276)=> [ep113] (training ) Lm: 6.488 (6.488), Lt: 5.731 (5.734), Acc m&t: 3.42 5.38, Remain: 4 days, 6:24:04, Finish: 2024-11-28 19:02 [11-25 04:38:12] (/home/user/VAR/train.py , line 276)=> [ep113] (training ) Lm: 6.488 (6.488), Lt: 5.731 (5.734), Acc m&t: 3.42 5.38, Remain: 4 days, 6:22:26, Finish: 2024-11-28 19:00 [11-25 04:38:12] (/home/user/VAR/train.py , line 276)=> [ep113] (training ) Lm: 6.488 (6.488), Lt: 5.731 (5.734), Acc m&t: 3.42 5.38, Remain: 4 days, 6:22:48, Finish: 2024-11-28 19:01 [11-25 04:38:12] (/home/user/VAR/train.py , line 276)=> [ep113] (training ) Lm: 6.488 (6.488), Lt: 5.731 (5.734), Acc m&t: 3.42 5.38, Remain: 4 days, 6:22:43, Finish: 2024-11-28 19:00 [11-25 04:38:12] (/home/user/VAR/train.py , line 276)=> [ep113] (training ) Lm: 6.488 (6.488), Lt: 5.731 (5.734), Acc m&t: 3.42 5.38, Remain: 4 days, 6:23:39, Finish: 2024-11-28 19:01 [11-25 04:38:12] (/home/user/VAR/train.py , line 276)=> [ep113] (training ) Lm: 6.488 (6.488), Lt: 5.731 (5.734), Acc m&t: 3.42 5.38, Remain: 4 days, 6:24:22, Finish: 2024-11-28 19:02 [11-25 04:38:12] (/home/user/VAR/train.py , line 276)=> [ep113] (training ) Lm: 6.488 (6.488), Lt: 5.731 (5.734), Acc m&t: 3.42 5.38, Remain: 4 days, 6:22:49, Finish: 2024-11-28 19:01 [11-25 04:38:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 0/1669] eta: 0:24:37 tlr: 0.00017 tnm: 0.22 Lm: 6.410 (6.410) Lt: 5.575 (5.575) Accm: 3.86 (3.86) Acct: 6.47 (6.47) proj_loss: -0.5811 (-0.5811) time: 0.8850 data: 0.0004 [11-25 04:38:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 0/1669] eta: 0:24:37 tlr: 0.00017 tnm: 0.22 Lm: 6.655 (6.655) Lt: 5.862 (5.862) Accm: 3.19 (3.19) Acct: 5.30 (5.30) proj_loss: -0.5823 (-0.5823) time: 0.8850 data: 0.0003 [11-25 04:38:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 0/1669] eta: 0:24:36 tlr: 0.00017 tnm: 0.22 Lm: 6.755 (6.755) Lt: 6.067 (6.067) Accm: 2.81 (2.81) Acct: 4.55 (4.55) proj_loss: -0.6216 (-0.6216) time: 0.8847 data: 0.0004 [11-25 04:38:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 0/1669] eta: 0:24:36 tlr: 0.00017 tnm: 0.22 Lm: 6.392 (6.392) Lt: 5.641 (5.641) Accm: 3.61 (3.61) Acct: 5.44 (5.44) proj_loss: -0.5910 (-0.5910) time: 0.8849 data: 0.0004 [11-25 04:38:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 0/1669] eta: 0:24:36 tlr: 0.00017 tnm: 0.22 Lm: 6.446 (6.446) Lt: 5.635 (5.635) Accm: 3.73 (3.73) Acct: 6.20 (6.20) proj_loss: -0.6111 (-0.6111) time: 0.8849 data: 0.0003 [11-25 04:38:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 0/1669] eta: 0:24:36 tlr: 0.00017 tnm: 0.22 Lm: 6.497 (6.497) Lt: 5.770 (5.770) Accm: 3.57 (3.57) Acct: 5.79 (5.79) proj_loss: -0.6160 (-0.6160) time: 0.8846 data: 0.0004 [11-25 04:38:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 0/1669] eta: 0:24:37 tlr: 0.00017 tnm: 0.22 Lm: 6.553 (6.553) Lt: 5.792 (5.792) Accm: 3.19 (3.19) Acct: 5.03 (5.03) proj_loss: -0.6020 (-0.6020) time: 0.8851 data: 0.0004 [11-25 04:38:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 0/1669] eta: 0:24:37 tlr: 0.00017 tnm: 0.22 Lm: 6.678 (6.678) Lt: 5.902 (5.902) Accm: 2.96 (2.96) Acct: 4.82 (4.82) proj_loss: -0.5983 (-0.5983) time: 0.8854 data: 0.0004 [11-25 04:44:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 417/1669] eta: 0:19:22 tlr: 0.00017 tnm: 0.24 Lm: 6.663 (6.663) Lt: 5.949 (5.949) Accm: 2.84 (2.84) Acct: 4.56 (4.56) proj_loss: -0.6056 (-0.6056) time: 0.9272 data: 0.0003 [11-25 04:44:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 417/1669] eta: 0:19:22 tlr: 0.00017 tnm: 0.24 Lm: 6.456 (6.456) Lt: 5.687 (5.687) Accm: 3.53 (3.53) Acct: 5.60 (5.60) proj_loss: -0.6141 (-0.6141) time: 0.9272 data: 0.0002 [11-25 04:44:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 417/1669] eta: 0:19:22 tlr: 0.00017 tnm: 0.24 Lm: 6.528 (6.528) Lt: 5.830 (5.830) Accm: 3.26 (3.26) Acct: 4.91 (4.91) proj_loss: -0.6299 (-0.6299) time: 0.9272 data: 0.0002 [11-25 04:44:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 417/1669] eta: 0:19:22 tlr: 0.00017 tnm: 0.24 Lm: 6.485 (6.485) Lt: 5.748 (5.748) Accm: 3.47 (3.47) Acct: 5.56 (5.56) proj_loss: -0.6112 (-0.6112) time: 0.9272 data: 0.0003 [11-25 04:44:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 417/1669] eta: 0:19:22 tlr: 0.00017 tnm: 0.24 Lm: 6.536 (6.536) Lt: 5.712 (5.712) Accm: 3.43 (3.43) Acct: 5.48 (5.48) proj_loss: -0.5931 (-0.5931) time: 0.9272 data: 0.0003 [11-25 04:44:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 417/1669] eta: 0:19:22 tlr: 0.00017 tnm: 0.24 Lm: 6.461 (6.461) Lt: 5.678 (5.678) Accm: 3.61 (3.61) Acct: 5.68 (5.68) proj_loss: -0.5924 (-0.5924) time: 0.9272 data: 0.0003 [11-25 04:44:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 417/1669] eta: 0:19:22 tlr: 0.00017 tnm: 0.24 Lm: 6.584 (6.584) Lt: 5.798 (5.798) Accm: 3.32 (3.32) Acct: 5.34 (5.34) proj_loss: -0.5973 (-0.5973) time: 0.9272 data: 0.0003 [11-25 04:44:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 417/1669] eta: 0:19:22 tlr: 0.00017 tnm: 0.24 Lm: 6.469 (6.469) Lt: 5.656 (5.656) Accm: 3.70 (3.70) Acct: 6.20 (6.20) proj_loss: -0.5777 (-0.5777) time: 0.9272 data: 0.0003 [11-25 04:51:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.423 (6.454) Lt: 5.663 (5.658) Accm: 3.54 (3.55) Acct: 5.92 (5.97) proj_loss: -0.5811 (-0.5830) time: 0.9273 data: 0.0003 [11-25 04:51:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.466 (6.506) Lt: 5.740 (5.757) Accm: 3.50 (3.52) Acct: 4.99 (5.33) proj_loss: -0.6172 (-0.6197) time: 0.9272 data: 0.0002 [11-25 04:51:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.529 (6.484) Lt: 5.715 (5.705) Accm: 3.60 (3.39) Acct: 5.44 (5.36) proj_loss: -0.5939 (-0.6037) time: 0.9273 data: 0.0002 [11-25 04:51:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.449 (6.502) Lt: 5.727 (5.796) Accm: 3.70 (3.42) Acct: 5.27 (5.29) proj_loss: -0.6343 (-0.6314) time: 0.9272 data: 0.0002 [11-25 04:51:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.553 (6.551) Lt: 5.804 (5.801) Accm: 3.45 (3.46) Acct: 5.65 (5.44) proj_loss: -0.6020 (-0.6088) time: 0.9273 data: 0.0003 [11-25 04:51:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.417 (6.495) Lt: 5.709 (5.711) Accm: 3.54 (3.47) Acct: 5.30 (5.37) proj_loss: -0.6038 (-0.5980) time: 0.9273 data: 0.0002 [11-25 04:51:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.497 (6.522) Lt: 5.770 (5.785) Accm: 3.37 (3.30) Acct: 5.34 (5.21) proj_loss: -0.6160 (-0.6148) time: 0.9273 data: 0.0002 [11-25 04:51:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.678 (6.693) Lt: 5.995 (5.966) Accm: 2.72 (2.78) Acct: 4.30 (4.42) proj_loss: -0.5983 (-0.5994) time: 0.9273 data: 0.0003 [11-25 04:57:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.663 (6.582) Lt: 5.949 (5.837) Accm: 2.84 (3.19) Acct: 4.56 (5.03) proj_loss: -0.6017 (-0.6008) time: 0.9233 data: 0.0003 [11-25 04:57:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.456 (6.444) Lt: 5.687 (5.682) Accm: 3.57 (3.55) Acct: 5.60 (5.57) proj_loss: -0.6240 (-0.6248) time: 0.9233 data: 0.0002 [11-25 04:57:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.393 (6.460) Lt: 5.660 (5.723) Accm: 3.72 (3.62) Acct: 5.66 (5.66) proj_loss: -0.6280 (-0.6167) time: 0.9233 data: 0.0003 [11-25 04:57:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.527 (6.494) Lt: 5.737 (5.724) Accm: 3.52 (3.40) Acct: 5.42 (5.37) proj_loss: -0.6101 (-0.6102) time: 0.9233 data: 0.0002 [11-25 04:57:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.501 (6.517) Lt: 5.786 (5.757) Accm: 3.37 (3.35) Acct: 5.23 (5.15) proj_loss: -0.6059 (-0.6035) time: 0.9233 data: 0.0002 [11-25 04:57:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.445 (6.457) Lt: 5.650 (5.653) Accm: 3.58 (3.57) Acct: 5.97 (5.98) proj_loss: -0.5788 (-0.5814) time: 0.9233 data: 0.0003 [11-25 04:57:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.547 (6.608) Lt: 5.814 (5.875) Accm: 3.16 (3.12) Acct: 4.92 (4.98) proj_loss: -0.6112 (-0.6091) time: 0.9233 data: 0.0002 [11-25 04:57:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.519 (6.470) Lt: 5.798 (5.746) Accm: 3.59 (3.61) Acct: 5.65 (5.64) proj_loss: -0.6148 (-0.6135) time: 0.9233 data: 0.0003 [11-25 05:03:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.520 (6.480) Lt: 5.804 (5.760) Accm: 3.50 (3.59) Acct: 5.65 (5.54) proj_loss: -0.6020 (-0.6067) time: 0.9265 data: 0.0017 [11-25 05:03:59] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 114/350] Total time: 0:25:46 (0.927 s / it) [11-25 05:03:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.423 (6.436) Lt: 5.638 (5.637) Accm: 3.54 (3.55) Acct: 5.92 (5.83) proj_loss: -0.5811 (-0.5867) time: 0.9265 data: 0.0019 [11-25 05:03:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.537 (6.521) Lt: 5.842 (5.774) Accm: 3.28 (3.34) Acct: 5.17 (5.15) proj_loss: -0.6080 (-0.6057) time: 0.9265 data: 0.0018 [11-25 05:03:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.466 (6.452) Lt: 5.711 (5.688) Accm: 3.50 (3.49) Acct: 5.27 (5.51) proj_loss: -0.6172 (-0.6206) time: 0.9265 data: 0.0017 [11-25 05:03:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.497 (6.569) Lt: 5.770 (5.843) Accm: 3.37 (3.21) Acct: 5.34 (5.10) proj_loss: -0.6160 (-0.6171) time: 0.9265 data: 0.0016 [11-25 05:03:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.526 (6.490) Lt: 5.720 (5.723) Accm: 3.44 (3.36) Acct: 5.41 (5.32) proj_loss: -0.6058 (-0.6094) time: 0.9265 data: 0.0014 [11-25 05:03:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.449 (6.490) Lt: 5.727 (5.759) Accm: 3.70 (3.47) Acct: 5.27 (5.41) proj_loss: -0.6216 (-0.6141) time: 0.9266 data: 0.0017 [11-25 05:03:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 114/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.649 (6.527) Lt: 5.902 (5.778) Accm: 2.96 (3.40) Acct: 4.82 (5.45) proj_loss: -0.6052 (-0.6056) time: 0.9266 data: 0.0019 [11-25 05:03:59] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 114/350] Total time: 0:25:46 (0.927 s / it) [11-25 05:03:59] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 114/350] Total time: 0:25:46 (0.927 s / it) [11-25 05:03:59] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 114/350] Total time: 0:25:46 (0.927 s / it) [11-25 05:03:59] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 114/350] Total time: 0:25:46 (0.927 s / it) [11-25 05:03:59] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 114/350] Total time: 0:25:46 (0.927 s / it) [11-25 05:03:59] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 114/350] Total time: 0:25:46 (0.927 s / it) [11-25 05:03:59] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 114/350] Total time: 0:25:46 (0.927 s / it) [11-25 05:03:59] (/home/user/VAR/train.py , line 276)=> [ep114] (training ) Lm: 6.485 (6.485), Lt: 5.728 (5.728), Acc m&t: 3.42 5.38, Remain: 4 days, 5:39:24, Finish: 2024-11-28 18:43 [11-25 05:03:59] (/home/user/VAR/train.py , line 276)=> [ep114] (training ) Lm: 6.485 (6.485), Lt: 5.728 (5.728), Acc m&t: 3.42 5.38, Remain: 4 days, 5:38:42, Finish: 2024-11-28 18:42 [11-25 05:03:59] (/home/user/VAR/train.py , line 276)=> [ep114] (training ) Lm: 6.485 (6.485), Lt: 5.728 (5.728), Acc m&t: 3.42 5.38, Remain: 4 days, 5:38:39, Finish: 2024-11-28 18:42 [11-25 05:03:59] (/home/user/VAR/train.py , line 276)=> [ep114] (training ) Lm: 6.485 (6.485), Lt: 5.728 (5.728), Acc m&t: 3.42 5.38, Remain: 4 days, 5:41:22, Finish: 2024-11-28 18:45 [11-25 05:03:59] (/home/user/VAR/train.py , line 276)=> [ep114] (training ) Lm: 6.485 (6.485), Lt: 5.728 (5.728), Acc m&t: 3.42 5.38, Remain: 4 days, 5:41:15, Finish: 2024-11-28 18:45 [11-25 05:03:59] (/home/user/VAR/train.py , line 276)=> [ep114] (training ) Lm: 6.485 (6.485), Lt: 5.728 (5.728), Acc m&t: 3.42 5.38, Remain: 4 days, 5:40:36, Finish: 2024-11-28 18:44 [11-25 05:03:59] (/home/user/VAR/train.py , line 276)=> [ep114] (training ) Lm: 6.485 (6.485), Lt: 5.728 (5.728), Acc m&t: 3.42 5.38, Remain: 4 days, 5:41:25, Finish: 2024-11-28 18:45 [11-25 05:03:59] (/home/user/VAR/train.py , line 276)=> [ep114] (training ) Lm: 6.485 (6.485), Lt: 5.728 (5.728), Acc m&t: 3.42 5.38, Remain: 4 days, 5:39:18, Finish: 2024-11-28 18:43 [11-25 05:04:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 0/1669] eta: 0:25:50 tlr: 0.00017 tnm: 0.22 Lm: 6.642 (6.642) Lt: 5.866 (5.866) Accm: 2.78 (2.78) Acct: 4.99 (4.99) proj_loss: -0.6043 (-0.6043) time: 0.9288 data: 0.0003 [11-25 05:04:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 0/1669] eta: 0:25:50 tlr: 0.00017 tnm: 0.22 Lm: 5.997 (5.997) Lt: 5.094 (5.094) Accm: 5.64 (5.64) Acct: 8.75 (8.75) proj_loss: -0.6187 (-0.6187) time: 0.9291 data: 0.0003 [11-25 05:04:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 0/1669] eta: 0:25:50 tlr: 0.00017 tnm: 0.22 Lm: 6.448 (6.448) Lt: 5.639 (5.639) Accm: 3.92 (3.92) Acct: 6.44 (6.44) proj_loss: -0.5880 (-0.5880) time: 0.9293 data: 0.0004 [11-25 05:04:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 0/1669] eta: 0:25:51 tlr: 0.00017 tnm: 0.22 Lm: 6.561 (6.561) Lt: 5.771 (5.771) Accm: 3.54 (3.54) Acct: 5.65 (5.65) proj_loss: -0.6006 (-0.6006) time: 0.9294 data: 0.0004 [11-25 05:04:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 0/1669] eta: 0:25:51 tlr: 0.00017 tnm: 0.22 Lm: 6.547 (6.547) Lt: 5.791 (5.791) Accm: 3.44 (3.44) Acct: 5.34 (5.34) proj_loss: -0.5955 (-0.5955) time: 0.9295 data: 0.0003 [11-25 05:04:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 0/1669] eta: 0:25:51 tlr: 0.00017 tnm: 0.22 Lm: 6.525 (6.525) Lt: 5.824 (5.824) Accm: 3.15 (3.15) Acct: 4.68 (4.68) proj_loss: -0.6077 (-0.6077) time: 0.9295 data: 0.0003 [11-25 05:04:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 0/1669] eta: 0:25:51 tlr: 0.00017 tnm: 0.22 Lm: 6.531 (6.531) Lt: 5.761 (5.761) Accm: 3.16 (3.16) Acct: 5.17 (5.17) proj_loss: -0.6185 (-0.6185) time: 0.9295 data: 0.0004 [11-25 05:04:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 0/1669] eta: 0:25:51 tlr: 0.00017 tnm: 0.22 Lm: 6.637 (6.637) Lt: 5.815 (5.815) Accm: 3.07 (3.07) Acct: 5.10 (5.10) proj_loss: -0.6045 (-0.6045) time: 0.9294 data: 0.0004 [11-25 05:10:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 417/1669] eta: 0:19:57 tlr: 0.00017 tnm: 0.23 Lm: 6.684 (6.684) Lt: 5.953 (5.953) Accm: 2.88 (2.88) Acct: 4.44 (4.44) proj_loss: -0.6039 (-0.6039) time: 0.9253 data: 0.0003 [11-25 05:10:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 417/1669] eta: 0:19:57 tlr: 0.00017 tnm: 0.23 Lm: 6.526 (6.526) Lt: 5.721 (5.721) Accm: 3.79 (3.79) Acct: 6.10 (6.10) proj_loss: -0.5912 (-0.5912) time: 0.9253 data: 0.0003 [11-25 05:10:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 417/1669] eta: 0:19:57 tlr: 0.00017 tnm: 0.23 Lm: 6.475 (6.475) Lt: 5.701 (5.701) Accm: 3.62 (3.62) Acct: 5.72 (5.72) proj_loss: -0.6005 (-0.6005) time: 0.9253 data: 0.0002 [11-25 05:10:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 417/1669] eta: 0:19:57 tlr: 0.00017 tnm: 0.23 Lm: 6.395 (6.395) Lt: 5.628 (5.628) Accm: 4.04 (4.04) Acct: 6.39 (6.39) proj_loss: -0.5905 (-0.5905) time: 0.9253 data: 0.0003 [11-25 05:10:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 417/1669] eta: 0:19:57 tlr: 0.00017 tnm: 0.23 Lm: 6.337 (6.337) Lt: 5.538 (5.538) Accm: 4.24 (4.24) Acct: 6.54 (6.54) proj_loss: -0.6085 (-0.6085) time: 0.9253 data: 0.0002 [11-25 05:10:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 417/1669] eta: 0:19:57 tlr: 0.00017 tnm: 0.23 Lm: 6.575 (6.575) Lt: 5.908 (5.908) Accm: 2.96 (2.96) Acct: 4.46 (4.46) proj_loss: -0.6112 (-0.6112) time: 0.9253 data: 0.0003 [11-25 05:10:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 417/1669] eta: 0:19:57 tlr: 0.00017 tnm: 0.23 Lm: 6.600 (6.600) Lt: 5.841 (5.841) Accm: 2.95 (2.95) Acct: 4.77 (4.77) proj_loss: -0.6022 (-0.6022) time: 0.9253 data: 0.0002 [11-25 05:10:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 417/1669] eta: 0:19:57 tlr: 0.00017 tnm: 0.23 Lm: 6.462 (6.462) Lt: 5.661 (5.661) Accm: 3.37 (3.37) Acct: 5.46 (5.46) proj_loss: -0.6217 (-0.6217) time: 0.9253 data: 0.0003 [11-25 05:17:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 834/1669] eta: 0:13:05 tlr: 0.00017 tnm: 0.23 Lm: 6.531 (6.586) Lt: 5.761 (5.820) Accm: 3.16 (3.09) Acct: 5.17 (4.87) proj_loss: -0.6185 (-0.6176) time: 0.9239 data: 0.0003 [11-25 05:17:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 834/1669] eta: 0:13:05 tlr: 0.00017 tnm: 0.23 Lm: 6.429 (6.368) Lt: 5.683 (5.586) Accm: 3.44 (3.97) Acct: 5.58 (6.22) proj_loss: -0.6187 (-0.6157) time: 0.9238 data: 0.0003 [11-25 05:17:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 834/1669] eta: 0:13:05 tlr: 0.00017 tnm: 0.23 Lm: 6.547 (6.570) Lt: 5.791 (5.832) Accm: 3.44 (3.16) Acct: 5.34 (5.05) proj_loss: -0.5955 (-0.5940) time: 0.9239 data: 0.0002 [11-25 05:17:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 834/1669] eta: 0:13:05 tlr: 0.00017 tnm: 0.23 Lm: 6.342 (6.376) Lt: 5.617 (5.614) Accm: 3.93 (4.00) Acct: 6.34 (6.27) proj_loss: -0.5930 (-0.6028) time: 0.9239 data: 0.0002 [11-25 05:17:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 834/1669] eta: 0:13:05 tlr: 0.00017 tnm: 0.23 Lm: 6.491 (6.497) Lt: 5.711 (5.717) Accm: 3.58 (3.72) Acct: 5.65 (5.89) proj_loss: -0.6006 (-0.5991) time: 0.9239 data: 0.0003 [11-25 05:17:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 834/1669] eta: 0:13:05 tlr: 0.00017 tnm: 0.23 Lm: 6.557 (6.530) Lt: 5.816 (5.756) Accm: 3.12 (3.19) Acct: 4.99 (4.96) proj_loss: -0.6018 (-0.6020) time: 0.9238 data: 0.0002 [11-25 05:17:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 834/1669] eta: 0:13:05 tlr: 0.00017 tnm: 0.23 Lm: 6.637 (6.571) Lt: 5.815 (5.816) Accm: 3.07 (3.24) Acct: 5.10 (5.10) proj_loss: -0.6045 (-0.6087) time: 0.9239 data: 0.0002 [11-25 05:17:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [ 834/1669] eta: 0:13:05 tlr: 0.00017 tnm: 0.23 Lm: 6.525 (6.501) Lt: 5.824 (5.822) Accm: 3.15 (3.21) Acct: 4.68 (4.97) proj_loss: -0.6147 (-0.6137) time: 0.9239 data: 0.0002 [11-25 05:23:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [1251/1669] eta: 0:06:31 tlr: 0.00017 tnm: 0.22 Lm: 6.564 (6.526) Lt: 5.826 (5.823) Accm: 3.04 (3.15) Acct: 4.70 (4.91) proj_loss: -0.6112 (-0.6051) time: 0.9247 data: 0.0003 [11-25 05:23:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [1251/1669] eta: 0:06:31 tlr: 0.00017 tnm: 0.22 Lm: 6.395 (6.444) Lt: 5.628 (5.698) Accm: 3.93 (3.73) Acct: 6.18 (5.80) proj_loss: -0.5905 (-0.5933) time: 0.9247 data: 0.0002 [11-25 05:23:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [1251/1669] eta: 0:06:31 tlr: 0.00017 tnm: 0.22 Lm: 6.684 (6.652) Lt: 5.953 (5.903) Accm: 2.88 (2.96) Acct: 4.44 (4.73) proj_loss: -0.6039 (-0.6030) time: 0.9247 data: 0.0002 [11-25 05:23:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [1251/1669] eta: 0:06:31 tlr: 0.00017 tnm: 0.22 Lm: 6.493 (6.415) Lt: 5.729 (5.633) Accm: 3.63 (3.93) Acct: 5.82 (6.18) proj_loss: -0.6085 (-0.6113) time: 0.9247 data: 0.0003 [11-25 05:23:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [1251/1669] eta: 0:06:31 tlr: 0.00017 tnm: 0.22 Lm: 6.507 (6.512) Lt: 5.751 (5.738) Accm: 3.21 (3.22) Acct: 5.13 (5.04) proj_loss: -0.6030 (-0.6041) time: 0.9247 data: 0.0002 [11-25 05:23:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [1251/1669] eta: 0:06:31 tlr: 0.00017 tnm: 0.22 Lm: 6.518 (6.550) Lt: 5.746 (5.799) Accm: 3.26 (3.14) Acct: 5.06 (4.98) proj_loss: -0.5882 (-0.5890) time: 0.9247 data: 0.0002 [11-25 05:23:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [1251/1669] eta: 0:06:31 tlr: 0.00017 tnm: 0.22 Lm: 6.528 (6.570) Lt: 5.794 (5.822) Accm: 3.08 (3.07) Acct: 4.84 (4.78) proj_loss: -0.6142 (-0.6157) time: 0.9247 data: 0.0003 [11-25 05:23:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [1251/1669] eta: 0:06:31 tlr: 0.00017 tnm: 0.22 Lm: 6.526 (6.573) Lt: 5.741 (5.788) Accm: 3.56 (3.47) Acct: 5.56 (5.48) proj_loss: -0.5912 (-0.5922) time: 0.9247 data: 0.0003 [11-25 05:29:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.491 (6.539) Lt: 5.711 (5.755) Accm: 3.58 (3.51) Acct: 5.65 (5.52) proj_loss: -0.6006 (-0.5997) time: 0.9274 data: 0.0020 [11-25 05:29:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 115/350] Total time: 0:25:57 (0.933 s / it) [11-25 05:29:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.448 (6.467) Lt: 5.639 (5.740) Accm: 3.92 (3.60) Acct: 6.03 (5.62) proj_loss: -0.5930 (-0.5988) time: 0.9274 data: 0.0014 [11-25 05:29:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.529 (6.438) Lt: 5.774 (5.681) Accm: 3.44 (3.73) Acct: 5.58 (5.79) proj_loss: -0.6120 (-0.6114) time: 0.9274 data: 0.0016 [11-25 05:29:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.547 (6.603) Lt: 5.791 (5.869) Accm: 3.09 (3.03) Acct: 4.79 (4.82) proj_loss: -0.5955 (-0.5904) time: 0.9274 data: 0.0015 [11-25 05:29:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.525 (6.493) Lt: 5.824 (5.762) Accm: 3.15 (3.37) Acct: 4.72 (5.30) proj_loss: -0.6147 (-0.6094) time: 0.9274 data: 0.0018 [11-25 05:29:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.485 (6.507) Lt: 5.786 (5.748) Accm: 3.12 (3.20) Acct: 4.99 (4.99) proj_loss: -0.6018 (-0.6020) time: 0.9274 data: 0.0015 [11-25 05:29:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.710 (6.663) Lt: 5.955 (5.913) Accm: 2.71 (2.91) Acct: 4.65 (4.72) proj_loss: -0.6032 (-0.6013) time: 0.9274 data: 0.0016 [11-25 05:29:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 115/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.531 (6.579) Lt: 5.828 (5.847) Accm: 3.00 (3.01) Acct: 4.51 (4.66) proj_loss: -0.6185 (-0.6208) time: 0.9274 data: 0.0022 [11-25 05:29:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 115/350] Total time: 0:25:57 (0.933 s / it) [11-25 05:29:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 115/350] Total time: 0:25:57 (0.933 s / it) [11-25 05:29:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 115/350] Total time: 0:25:57 (0.933 s / it) [11-25 05:29:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 115/350] Total time: 0:25:57 (0.933 s / it) [11-25 05:29:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 115/350] Total time: 0:25:57 (0.933 s / it) [11-25 05:29:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 115/350] Total time: 0:25:57 (0.933 s / it) [11-25 05:29:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 115/350] Total time: 0:25:57 (0.933 s / it) [11-25 05:29:57] (/home/user/VAR/train.py , line 276)=> [ep115] (training ) Lm: 6.485 (6.489), Lt: 5.728 (5.733), Acc m&t: 3.42 5.38, Remain: 4 days, 5:23:52, Finish: 2024-11-28 18:53 [11-25 05:29:57] (/home/user/VAR/train.py , line 276)=> [ep115] (training ) Lm: 6.485 (6.489), Lt: 5.728 (5.733), Acc m&t: 3.42 5.38, Remain: 4 days, 5:22:46, Finish: 2024-11-28 18:52 [11-25 05:29:57] (/home/user/VAR/train.py , line 276)=> [ep115] (training ) Lm: 6.485 (6.489), Lt: 5.728 (5.733), Acc m&t: 3.42 5.38, Remain: 4 days, 5:24:19, Finish: 2024-11-28 18:54 [11-25 05:29:57] (/home/user/VAR/train.py , line 276)=> [ep115] (training ) Lm: 6.485 (6.489), Lt: 5.728 (5.733), Acc m&t: 3.42 5.38, Remain: 4 days, 5:21:53, Finish: 2024-11-28 18:51 [11-25 05:29:57] (/home/user/VAR/train.py , line 276)=> [ep115] (training ) Lm: 6.485 (6.489), Lt: 5.728 (5.733), Acc m&t: 3.42 5.38, Remain: 4 days, 5:22:44, Finish: 2024-11-28 18:52 [11-25 05:29:57] (/home/user/VAR/train.py , line 276)=> [ep115] (training ) Lm: 6.485 (6.489), Lt: 5.728 (5.733), Acc m&t: 3.42 5.38, Remain: 4 days, 5:21:50, Finish: 2024-11-28 18:51 [11-25 05:29:57] (/home/user/VAR/train.py , line 276)=> [ep115] (training ) Lm: 6.485 (6.489), Lt: 5.728 (5.733), Acc m&t: 3.42 5.38, Remain: 4 days, 5:21:52, Finish: 2024-11-28 18:51 [11-25 05:29:57] (/home/user/VAR/train.py , line 276)=> [ep115] (training ) Lm: 6.485 (6.489), Lt: 5.728 (5.733), Acc m&t: 3.42 5.38, Remain: 4 days, 5:23:11, Finish: 2024-11-28 18:53 [11-25 05:29:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 0/1669] eta: 0:24:42 tlr: 0.00017 tnm: 0.24 Lm: 6.576 (6.576) Lt: 5.848 (5.848) Accm: 3.18 (3.18) Acct: 4.99 (4.99) proj_loss: -0.6032 (-0.6032) time: 0.8884 data: 0.0003 [11-25 05:29:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 0/1669] eta: 0:24:34 tlr: 0.00017 tnm: 0.24 Lm: 6.372 (6.372) Lt: 5.549 (5.549) Accm: 3.77 (3.77) Acct: 6.06 (6.06) proj_loss: -0.6228 (-0.6228) time: 0.8834 data: 0.0004 [11-25 05:29:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 0/1669] eta: 0:24:42 tlr: 0.00017 tnm: 0.24 Lm: 6.451 (6.451) Lt: 5.634 (5.634) Accm: 3.29 (3.29) Acct: 5.61 (5.61) proj_loss: -0.5928 (-0.5928) time: 0.8884 data: 0.0004 [11-25 05:29:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 0/1669] eta: 0:24:34 tlr: 0.00017 tnm: 0.24 Lm: 6.452 (6.452) Lt: 5.778 (5.778) Accm: 3.55 (3.55) Acct: 5.44 (5.44) proj_loss: -0.6345 (-0.6345) time: 0.8837 data: 0.0004 [11-25 05:29:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 0/1669] eta: 0:24:43 tlr: 0.00017 tnm: 0.24 Lm: 6.643 (6.643) Lt: 5.826 (5.826) Accm: 3.04 (3.04) Acct: 4.79 (4.79) proj_loss: -0.6207 (-0.6207) time: 0.8887 data: 0.0003 [11-25 05:29:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 0/1669] eta: 0:24:34 tlr: 0.00017 tnm: 0.24 Lm: 6.334 (6.334) Lt: 5.582 (5.582) Accm: 3.96 (3.96) Acct: 5.92 (5.92) proj_loss: -0.6139 (-0.6139) time: 0.8835 data: 0.0004 [11-25 05:29:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 0/1669] eta: 0:24:35 tlr: 0.00017 tnm: 0.24 Lm: 6.515 (6.515) Lt: 5.733 (5.733) Accm: 3.22 (3.22) Acct: 5.20 (5.20) proj_loss: -0.6202 (-0.6202) time: 0.8839 data: 0.0004 [11-25 05:29:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 0/1669] eta: 0:24:43 tlr: 0.00017 tnm: 0.24 Lm: 6.496 (6.496) Lt: 5.714 (5.714) Accm: 3.53 (3.53) Acct: 5.41 (5.41) proj_loss: -0.5901 (-0.5901) time: 0.8890 data: 0.0004 [11-25 05:36:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 417/1669] eta: 0:19:19 tlr: 0.00017 tnm: 0.23 Lm: 6.463 (6.463) Lt: 5.672 (5.672) Accm: 3.70 (3.70) Acct: 5.51 (5.51) proj_loss: -0.6041 (-0.6041) time: 0.9249 data: 0.0003 [11-25 05:36:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 417/1669] eta: 0:19:19 tlr: 0.00017 tnm: 0.23 Lm: 6.537 (6.537) Lt: 5.745 (5.745) Accm: 3.15 (3.15) Acct: 5.32 (5.32) proj_loss: -0.5839 (-0.5839) time: 0.9248 data: 0.0003 [11-25 05:36:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 417/1669] eta: 0:19:19 tlr: 0.00017 tnm: 0.23 Lm: 6.523 (6.523) Lt: 5.801 (5.801) Accm: 3.29 (3.29) Acct: 5.34 (5.34) proj_loss: -0.6139 (-0.6139) time: 0.9248 data: 0.0002 [11-25 05:36:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 417/1669] eta: 0:19:19 tlr: 0.00017 tnm: 0.23 Lm: 6.410 (6.410) Lt: 5.698 (5.698) Accm: 3.57 (3.57) Acct: 5.56 (5.56) proj_loss: -0.6204 (-0.6204) time: 0.9248 data: 0.0002 [11-25 05:36:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 417/1669] eta: 0:19:19 tlr: 0.00017 tnm: 0.23 Lm: 6.601 (6.601) Lt: 5.769 (5.769) Accm: 3.15 (3.15) Acct: 5.10 (5.10) proj_loss: -0.6072 (-0.6072) time: 0.9249 data: 0.0002 [11-25 05:36:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 417/1669] eta: 0:19:19 tlr: 0.00017 tnm: 0.23 Lm: 6.328 (6.328) Lt: 5.570 (5.570) Accm: 3.63 (3.63) Acct: 5.70 (5.70) proj_loss: -0.6222 (-0.6222) time: 0.9249 data: 0.0002 [11-25 05:36:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 417/1669] eta: 0:19:19 tlr: 0.00017 tnm: 0.23 Lm: 6.426 (6.426) Lt: 5.662 (5.662) Accm: 3.61 (3.61) Acct: 5.49 (5.49) proj_loss: -0.6060 (-0.6060) time: 0.9249 data: 0.0003 [11-25 05:36:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 417/1669] eta: 0:19:19 tlr: 0.00017 tnm: 0.23 Lm: 6.574 (6.574) Lt: 5.869 (5.869) Accm: 3.13 (3.13) Acct: 4.73 (4.73) proj_loss: -0.6242 (-0.6242) time: 0.9249 data: 0.0003 [11-25 05:43:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 834/1669] eta: 0:13:12 tlr: 0.00017 tnm: 0.22 Lm: 6.515 (6.522) Lt: 5.733 (5.765) Accm: 3.22 (3.26) Acct: 5.20 (5.07) proj_loss: -0.6202 (-0.6180) time: 0.9275 data: 0.0002 [11-25 05:43:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 834/1669] eta: 0:13:12 tlr: 0.00017 tnm: 0.22 Lm: 6.315 (6.324) Lt: 5.549 (5.557) Accm: 3.61 (3.62) Acct: 5.34 (5.58) proj_loss: -0.6215 (-0.6173) time: 0.9275 data: 0.0002 [11-25 05:43:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 834/1669] eta: 0:13:12 tlr: 0.00017 tnm: 0.22 Lm: 6.368 (6.361) Lt: 5.619 (5.615) Accm: 3.58 (3.69) Acct: 5.68 (5.85) proj_loss: -0.6063 (-0.6145) time: 0.9275 data: 0.0003 [11-25 05:43:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 834/1669] eta: 0:13:12 tlr: 0.00017 tnm: 0.22 Lm: 6.469 (6.476) Lt: 5.755 (5.766) Accm: 3.39 (3.41) Acct: 5.54 (5.41) proj_loss: -0.6032 (-0.6101) time: 0.9275 data: 0.0002 [11-25 05:43:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 834/1669] eta: 0:13:12 tlr: 0.00017 tnm: 0.22 Lm: 6.451 (6.503) Lt: 5.777 (5.756) Accm: 3.29 (3.29) Acct: 5.37 (5.34) proj_loss: -0.5928 (-0.5989) time: 0.9275 data: 0.0003 [11-25 05:43:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 834/1669] eta: 0:13:12 tlr: 0.00017 tnm: 0.22 Lm: 6.567 (6.589) Lt: 5.745 (5.761) Accm: 3.25 (3.31) Acct: 5.41 (5.37) proj_loss: -0.5992 (-0.6045) time: 0.9275 data: 0.0003 [11-25 05:43:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 834/1669] eta: 0:13:12 tlr: 0.00017 tnm: 0.22 Lm: 6.470 (6.441) Lt: 5.742 (5.693) Accm: 3.25 (3.44) Acct: 5.06 (5.30) proj_loss: -0.6139 (-0.6089) time: 0.9275 data: 0.0003 [11-25 05:43:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [ 834/1669] eta: 0:13:12 tlr: 0.00017 tnm: 0.22 Lm: 6.496 (6.518) Lt: 5.714 (5.775) Accm: 3.53 (3.46) Acct: 5.41 (5.21) proj_loss: -0.6109 (-0.6063) time: 0.9276 data: 0.0003 [11-25 05:49:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [1251/1669] eta: 0:06:33 tlr: 0.00017 tnm: 0.24 Lm: 6.410 (6.453) Lt: 5.698 (5.723) Accm: 3.57 (3.45) Acct: 5.56 (5.48) proj_loss: -0.6045 (-0.6056) time: 0.9246 data: 0.0002 [11-25 05:49:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [1251/1669] eta: 0:06:33 tlr: 0.00017 tnm: 0.24 Lm: 6.535 (6.532) Lt: 5.817 (5.784) Accm: 3.15 (3.20) Acct: 5.20 (5.26) proj_loss: -0.6050 (-0.6035) time: 0.9246 data: 0.0002 [11-25 05:49:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [1251/1669] eta: 0:06:33 tlr: 0.00017 tnm: 0.24 Lm: 6.300 (6.314) Lt: 5.540 (5.535) Accm: 3.69 (3.67) Acct: 5.70 (5.72) proj_loss: -0.6175 (-0.6163) time: 0.9246 data: 0.0002 [11-25 05:49:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [1251/1669] eta: 0:06:33 tlr: 0.00017 tnm: 0.24 Lm: 6.493 (6.459) Lt: 5.701 (5.685) Accm: 3.18 (3.32) Acct: 4.99 (5.19) proj_loss: -0.6077 (-0.6070) time: 0.9246 data: 0.0003 [11-25 05:49:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [1251/1669] eta: 0:06:33 tlr: 0.00017 tnm: 0.24 Lm: 6.563 (6.567) Lt: 5.729 (5.722) Accm: 3.31 (3.33) Acct: 5.61 (5.48) proj_loss: -0.5964 (-0.6010) time: 0.9246 data: 0.0003 [11-25 05:49:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [1251/1669] eta: 0:06:33 tlr: 0.00017 tnm: 0.24 Lm: 6.425 (6.428) Lt: 5.725 (5.683) Accm: 3.53 (3.69) Acct: 5.61 (5.95) proj_loss: -0.6051 (-0.6094) time: 0.9246 data: 0.0002 [11-25 05:49:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [1251/1669] eta: 0:06:33 tlr: 0.00017 tnm: 0.24 Lm: 6.574 (6.550) Lt: 5.783 (5.782) Accm: 3.19 (3.23) Acct: 5.20 (5.11) proj_loss: -0.6146 (-0.6158) time: 0.9246 data: 0.0003 [11-25 05:49:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [1251/1669] eta: 0:06:33 tlr: 0.00017 tnm: 0.24 Lm: 6.473 (6.501) Lt: 5.694 (5.750) Accm: 3.43 (3.43) Acct: 5.35 (5.23) proj_loss: -0.6028 (-0.6035) time: 0.9246 data: 0.0003 [11-25 05:56:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.496 (6.546) Lt: 5.714 (5.801) Accm: 3.34 (3.26) Acct: 5.30 (4.99) proj_loss: -0.5948 (-0.6015) time: 0.9262 data: 0.0015 [11-25 05:56:02] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 116/350] Total time: 0:26:05 (0.938 s / it) [11-25 05:56:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.559 (6.534) Lt: 5.745 (5.732) Accm: 3.37 (3.36) Acct: 5.41 (5.41) proj_loss: -0.5980 (-0.6004) time: 0.9262 data: 0.0022 [11-25 05:56:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.315 (6.360) Lt: 5.549 (5.573) Accm: 3.61 (3.47) Acct: 5.34 (5.41) proj_loss: -0.6135 (-0.6139) time: 0.9262 data: 0.0017 [11-25 05:56:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.368 (6.425) Lt: 5.619 (5.673) Accm: 3.55 (3.42) Acct: 5.44 (5.41) proj_loss: -0.6028 (-0.6029) time: 0.9262 data: 0.0019 [11-25 05:56:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.451 (6.439) Lt: 5.777 (5.669) Accm: 3.29 (3.62) Acct: 5.37 (5.84) proj_loss: -0.6018 (-0.6032) time: 0.9262 data: 0.0014 [11-25 05:56:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.469 (6.472) Lt: 5.755 (5.726) Accm: 3.39 (3.47) Acct: 5.54 (5.61) proj_loss: -0.6032 (-0.6069) time: 0.9262 data: 0.0018 [11-25 05:56:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.470 (6.453) Lt: 5.661 (5.663) Accm: 3.25 (3.38) Acct: 5.06 (5.39) proj_loss: -0.6014 (-0.6013) time: 0.9262 data: 0.0018 [11-25 05:56:02] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 116/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.515 (6.500) Lt: 5.733 (5.733) Accm: 3.22 (3.35) Acct: 5.20 (5.23) proj_loss: -0.6152 (-0.6156) time: 0.9262 data: 0.0020 [11-25 05:56:02] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 116/350] Total time: 0:26:05 (0.938 s / it) [11-25 05:56:02] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 116/350] Total time: 0:26:05 (0.938 s / it) [11-25 05:56:02] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 116/350] Total time: 0:26:05 (0.938 s / it) [11-25 05:56:02] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 116/350] Total time: 0:26:05 (0.938 s / it) [11-25 05:56:02] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 116/350] Total time: 0:26:05 (0.938 s / it) [11-25 05:56:02] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 116/350] Total time: 0:26:05 (0.938 s / it) [11-25 05:56:02] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 116/350] Total time: 0:26:05 (0.938 s / it) [11-25 05:56:02] (/home/user/VAR/train.py , line 276)=> [ep116] (training ) Lm: 6.485 (6.487), Lt: 5.728 (5.730), Acc m&t: 3.42 5.38, Remain: 4 days, 4:32:02, Finish: 2024-11-28 18:28 [11-25 05:56:02] (/home/user/VAR/train.py , line 276)=> [ep116] (training ) Lm: 6.485 (6.487), Lt: 5.728 (5.730), Acc m&t: 3.42 5.38, Remain: 4 days, 4:35:12, Finish: 2024-11-28 18:31 [11-25 05:56:02] (/home/user/VAR/train.py , line 276)=> [ep116] (training ) Lm: 6.485 (6.487), Lt: 5.728 (5.730), Acc m&t: 3.42 5.38, Remain: 4 days, 4:35:00, Finish: 2024-11-28 18:31 [11-25 05:56:02] (/home/user/VAR/train.py , line 276)=> [ep116] (training ) Lm: 6.485 (6.487), Lt: 5.728 (5.730), Acc m&t: 3.42 5.38, Remain: 4 days, 4:32:30, Finish: 2024-11-28 18:28 [11-25 05:56:02] (/home/user/VAR/train.py , line 276)=> [ep116] (training ) Lm: 6.485 (6.487), Lt: 5.728 (5.730), Acc m&t: 3.42 5.38, Remain: 4 days, 4:37:51, Finish: 2024-11-28 18:33 [11-25 05:56:02] (/home/user/VAR/train.py , line 276)=> [ep116] (training ) Lm: 6.485 (6.487), Lt: 5.728 (5.730), Acc m&t: 3.42 5.38, Remain: 4 days, 4:33:24, Finish: 2024-11-28 18:29 [11-25 05:56:02] (/home/user/VAR/train.py , line 276)=> [ep116] (training ) Lm: 6.485 (6.487), Lt: 5.728 (5.730), Acc m&t: 3.42 5.38, Remain: 4 days, 4:32:33, Finish: 2024-11-28 18:28 [11-25 05:56:02] (/home/user/VAR/train.py , line 276)=> [ep116] (training ) Lm: 6.485 (6.487), Lt: 5.728 (5.730), Acc m&t: 3.42 5.38, Remain: 4 days, 4:36:24, Finish: 2024-11-28 18:32 [11-25 05:56:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 0/1669] eta: 0:25:08 tlr: 0.00017 tnm: 0.24 Lm: 6.517 (6.517) Lt: 5.848 (5.848) Accm: 3.16 (3.16) Acct: 4.86 (4.86) proj_loss: -0.6032 (-0.6032) time: 0.9039 data: 0.0004 [11-25 05:56:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 0/1669] eta: 0:25:08 tlr: 0.00017 tnm: 0.24 Lm: 6.670 (6.670) Lt: 5.958 (5.958) Accm: 3.21 (3.21) Acct: 4.61 (4.61) proj_loss: -0.6050 (-0.6050) time: 0.9038 data: 0.0003 [11-25 05:56:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 0/1669] eta: 0:25:09 tlr: 0.00017 tnm: 0.24 Lm: 6.410 (6.410) Lt: 5.636 (5.636) Accm: 3.69 (3.69) Acct: 5.85 (5.85) proj_loss: -0.6033 (-0.6033) time: 0.9041 data: 0.0004 [11-25 05:56:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 0/1669] eta: 0:25:09 tlr: 0.00017 tnm: 0.24 Lm: 6.637 (6.637) Lt: 6.003 (6.003) Accm: 2.84 (2.84) Acct: 4.13 (4.13) proj_loss: -0.6235 (-0.6235) time: 0.9045 data: 0.0003 [11-25 05:56:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 0/1669] eta: 0:25:08 tlr: 0.00017 tnm: 0.24 Lm: 6.569 (6.569) Lt: 5.843 (5.843) Accm: 2.68 (2.68) Acct: 4.24 (4.24) proj_loss: -0.6333 (-0.6333) time: 0.9041 data: 0.0004 [11-25 05:56:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 0/1669] eta: 0:25:14 tlr: 0.00017 tnm: 0.24 Lm: 6.457 (6.457) Lt: 5.707 (5.707) Accm: 3.39 (3.39) Acct: 5.03 (5.03) proj_loss: -0.6183 (-0.6183) time: 0.9077 data: 0.0004 [11-25 05:56:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 0/1669] eta: 0:25:14 tlr: 0.00017 tnm: 0.24 Lm: 6.378 (6.378) Lt: 5.664 (5.664) Accm: 3.55 (3.55) Acct: 5.30 (5.30) proj_loss: -0.6409 (-0.6409) time: 0.9075 data: 0.0004 [11-25 05:56:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 0/1669] eta: 0:25:17 tlr: 0.00017 tnm: 0.24 Lm: 6.607 (6.607) Lt: 5.843 (5.843) Accm: 3.31 (3.31) Acct: 5.20 (5.20) proj_loss: -0.5806 (-0.5806) time: 0.9091 data: 0.0004 [11-25 06:02:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 417/1669] eta: 0:19:19 tlr: 0.00017 tnm: 0.24 Lm: 6.531 (6.531) Lt: 5.787 (5.787) Accm: 3.18 (3.18) Acct: 4.80 (4.80) proj_loss: -0.6085 (-0.6085) time: 0.9238 data: 0.0002 [11-25 06:02:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 417/1669] eta: 0:19:19 tlr: 0.00017 tnm: 0.24 Lm: 6.410 (6.410) Lt: 5.690 (5.690) Accm: 3.51 (3.51) Acct: 5.42 (5.42) proj_loss: -0.6328 (-0.6328) time: 0.9238 data: 0.0003 [11-25 06:02:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 417/1669] eta: 0:19:19 tlr: 0.00017 tnm: 0.24 Lm: 6.394 (6.394) Lt: 5.620 (5.620) Accm: 3.72 (3.72) Acct: 5.96 (5.96) proj_loss: -0.5959 (-0.5959) time: 0.9238 data: 0.0002 [11-25 06:02:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 417/1669] eta: 0:19:19 tlr: 0.00017 tnm: 0.24 Lm: 6.517 (6.517) Lt: 5.776 (5.776) Accm: 3.16 (3.16) Acct: 5.10 (5.10) proj_loss: -0.6144 (-0.6144) time: 0.9238 data: 0.0003 [11-25 06:02:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 417/1669] eta: 0:19:19 tlr: 0.00017 tnm: 0.24 Lm: 6.560 (6.560) Lt: 5.858 (5.858) Accm: 2.92 (2.92) Acct: 4.51 (4.51) proj_loss: -0.6232 (-0.6232) time: 0.9238 data: 0.0002 [11-25 06:02:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 417/1669] eta: 0:19:19 tlr: 0.00017 tnm: 0.24 Lm: 6.503 (6.503) Lt: 5.770 (5.770) Accm: 2.99 (2.99) Acct: 4.77 (4.77) proj_loss: -0.6263 (-0.6263) time: 0.9239 data: 0.0002 [11-25 06:02:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 417/1669] eta: 0:19:19 tlr: 0.00017 tnm: 0.24 Lm: 6.489 (6.489) Lt: 5.742 (5.742) Accm: 3.29 (3.29) Acct: 4.94 (4.94) proj_loss: -0.6174 (-0.6174) time: 0.9238 data: 0.0003 [11-25 06:02:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 417/1669] eta: 0:19:19 tlr: 0.00017 tnm: 0.24 Lm: 6.528 (6.528) Lt: 5.780 (5.780) Accm: 3.32 (3.32) Acct: 5.23 (5.23) proj_loss: -0.6063 (-0.6063) time: 0.9238 data: 0.0003 [11-25 06:08:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 834/1669] eta: 0:12:53 tlr: 0.00017 tnm: 0.23 Lm: 6.564 (6.540) Lt: 5.843 (5.848) Accm: 3.31 (3.32) Acct: 5.20 (5.14) proj_loss: -0.6185 (-0.6104) time: 0.9246 data: 0.0003 [11-25 06:08:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 834/1669] eta: 0:12:53 tlr: 0.00017 tnm: 0.23 Lm: 6.442 (6.492) Lt: 5.715 (5.760) Accm: 3.47 (3.33) Acct: 5.30 (5.14) proj_loss: -0.6247 (-0.6171) time: 0.9246 data: 0.0003 [11-25 06:08:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 834/1669] eta: 0:12:53 tlr: 0.00017 tnm: 0.23 Lm: 6.549 (6.557) Lt: 5.813 (5.843) Accm: 2.97 (2.94) Acct: 4.89 (4.66) proj_loss: -0.6228 (-0.6216) time: 0.9246 data: 0.0002 [11-25 06:08:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 834/1669] eta: 0:12:53 tlr: 0.00017 tnm: 0.23 Lm: 6.391 (6.478) Lt: 5.615 (5.696) Accm: 3.21 (3.33) Acct: 4.99 (5.23) proj_loss: -0.6050 (-0.5948) time: 0.9246 data: 0.0003 [11-25 06:08:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 834/1669] eta: 0:12:53 tlr: 0.00017 tnm: 0.23 Lm: 6.516 (6.508) Lt: 5.722 (5.754) Accm: 3.13 (3.04) Acct: 4.99 (4.84) proj_loss: -0.6192 (-0.6150) time: 0.9246 data: 0.0003 [11-25 06:08:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 834/1669] eta: 0:12:53 tlr: 0.00017 tnm: 0.23 Lm: 6.517 (6.438) Lt: 5.848 (5.701) Accm: 3.63 (3.69) Acct: 5.61 (5.84) proj_loss: -0.5971 (-0.5963) time: 0.9246 data: 0.0002 [11-25 06:08:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 834/1669] eta: 0:12:53 tlr: 0.00017 tnm: 0.23 Lm: 6.416 (6.483) Lt: 5.636 (5.724) Accm: 3.69 (3.34) Acct: 5.68 (5.29) proj_loss: -0.6033 (-0.6031) time: 0.9246 data: 0.0002 [11-25 06:08:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [ 834/1669] eta: 0:12:53 tlr: 0.00017 tnm: 0.23 Lm: 6.521 (6.523) Lt: 5.777 (5.772) Accm: 3.18 (3.19) Acct: 4.86 (4.88) proj_loss: -0.6183 (-0.6249) time: 0.9246 data: 0.0002 [11-25 06:15:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.489 (6.493) Lt: 5.742 (5.741) Accm: 3.21 (3.21) Acct: 4.94 (4.98) proj_loss: -0.6185 (-0.6233) time: 0.9636 data: 0.0003 [11-25 06:15:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.381 (6.446) Lt: 5.616 (5.676) Accm: 3.42 (3.62) Acct: 5.54 (5.66) proj_loss: -0.6085 (-0.6014) time: 0.9635 data: 0.0002 [11-25 06:15:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.522 (6.462) Lt: 5.790 (5.708) Accm: 3.42 (3.57) Acct: 5.39 (5.67) proj_loss: -0.5930 (-0.5944) time: 0.9635 data: 0.0002 [11-25 06:15:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.410 (6.453) Lt: 5.690 (5.701) Accm: 3.51 (3.39) Acct: 5.42 (5.31) proj_loss: -0.6224 (-0.6178) time: 0.9635 data: 0.0003 [11-25 06:15:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.413 (6.451) Lt: 5.649 (5.708) Accm: 3.63 (3.40) Acct: 5.61 (5.35) proj_loss: -0.6144 (-0.6121) time: 0.9635 data: 0.0003 [11-25 06:15:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.506 (6.495) Lt: 5.780 (5.780) Accm: 3.32 (3.41) Acct: 5.23 (5.41) proj_loss: -0.5996 (-0.6017) time: 0.9636 data: 0.0003 [11-25 06:15:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.514 (6.509) Lt: 5.747 (5.758) Accm: 3.19 (3.09) Acct: 5.08 (4.92) proj_loss: -0.6202 (-0.6166) time: 0.9636 data: 0.0003 [11-25 06:15:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.593 (6.589) Lt: 5.867 (5.862) Accm: 2.99 (2.99) Acct: 4.73 (4.64) proj_loss: -0.6206 (-0.6127) time: 0.9636 data: 0.0003 [11-25 06:22:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.549 (6.557) Lt: 5.813 (5.832) Accm: 3.00 (3.09) Acct: 4.89 (4.76) proj_loss: -0.6184 (-0.6137) time: 0.9306 data: 0.0016 [11-25 06:22:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 117/350] Total time: 0:26:03 (0.937 s / it) [11-25 06:22:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.517 (6.437) Lt: 5.732 (5.673) Accm: 3.63 (3.67) Acct: 5.61 (5.76) proj_loss: -0.5971 (-0.5968) time: 0.9306 data: 0.0019 [11-25 06:22:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.391 (6.467) Lt: 5.617 (5.696) Accm: 3.21 (3.53) Acct: 4.99 (5.50) proj_loss: -0.6050 (-0.6007) time: 0.9306 data: 0.0018 [11-25 06:22:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.457 (6.473) Lt: 5.707 (5.712) Accm: 3.25 (3.28) Acct: 5.03 (5.18) proj_loss: -0.6183 (-0.6173) time: 0.9306 data: 0.0017 [11-25 06:22:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.481 (6.492) Lt: 5.717 (5.756) Accm: 3.34 (3.42) Acct: 5.27 (5.48) proj_loss: -0.6004 (-0.6015) time: 0.9306 data: 0.0020 [11-25 06:22:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.378 (6.371) Lt: 5.664 (5.618) Accm: 3.55 (3.70) Acct: 5.54 (5.82) proj_loss: -0.6200 (-0.6108) time: 0.9306 data: 0.0016 [11-25 06:22:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.516 (6.540) Lt: 5.772 (5.790) Accm: 3.13 (3.06) Acct: 4.99 (4.82) proj_loss: -0.6192 (-0.6129) time: 0.9306 data: 0.0018 [11-25 06:22:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 117/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.416 (6.487) Lt: 5.663 (5.756) Accm: 3.58 (3.33) Acct: 5.54 (5.10) proj_loss: -0.6035 (-0.6104) time: 0.9306 data: 0.0017 [11-25 06:22:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 117/350] Total time: 0:26:03 (0.937 s / it) [11-25 06:22:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 117/350] Total time: 0:26:03 (0.937 s / it) [11-25 06:22:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 117/350] Total time: 0:26:03 (0.937 s / it) [11-25 06:22:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 117/350] Total time: 0:26:03 (0.937 s / it) [11-25 06:22:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 117/350] Total time: 0:26:03 (0.937 s / it) [11-25 06:22:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 117/350] Total time: 0:26:03 (0.937 s / it) [11-25 06:22:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 117/350] Total time: 0:26:03 (0.937 s / it) [11-25 06:22:06] (/home/user/VAR/train.py , line 276)=> [ep117] (training ) Lm: 6.485 (6.488), Lt: 5.728 (5.735), Acc m&t: 3.42 5.38, Remain: 4 days, 4:35:24, Finish: 2024-11-28 18:57 [11-25 06:22:06] (/home/user/VAR/train.py , line 276)=> [ep117] (training ) Lm: 6.485 (6.488), Lt: 5.728 (5.735), Acc m&t: 3.42 5.38, Remain: 4 days, 4:35:39, Finish: 2024-11-28 18:57 [11-25 06:22:06] (/home/user/VAR/train.py , line 276)=> [ep117] (training ) Lm: 6.485 (6.488), Lt: 5.728 (5.735), Acc m&t: 3.42 5.38, Remain: 4 days, 4:36:14, Finish: 2024-11-28 18:58 [11-25 06:22:06] (/home/user/VAR/train.py , line 276)=> [ep117] (training ) Lm: 6.485 (6.488), Lt: 5.728 (5.735), Acc m&t: 3.42 5.38, Remain: 4 days, 4:37:08, Finish: 2024-11-28 18:59 [11-25 06:22:06] (/home/user/VAR/train.py , line 276)=> [ep117] (training ) Lm: 6.485 (6.488), Lt: 5.728 (5.735), Acc m&t: 3.42 5.38, Remain: 4 days, 4:35:06, Finish: 2024-11-28 18:57 [11-25 06:22:06] (/home/user/VAR/train.py , line 276)=> [ep117] (training ) Lm: 6.485 (6.488), Lt: 5.728 (5.735), Acc m&t: 3.42 5.38, Remain: 4 days, 4:36:07, Finish: 2024-11-28 18:58 [11-25 06:22:06] (/home/user/VAR/train.py , line 276)=> [ep117] (training ) Lm: 6.485 (6.488), Lt: 5.728 (5.735), Acc m&t: 3.42 5.38, Remain: 4 days, 4:37:03, Finish: 2024-11-28 18:59 [11-25 06:22:06] (/home/user/VAR/train.py , line 276)=> [ep117] (training ) Lm: 6.485 (6.488), Lt: 5.728 (5.735), Acc m&t: 3.42 5.38, Remain: 4 days, 4:36:56, Finish: 2024-11-28 18:59 [11-25 06:22:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 0/1669] eta: 0:24:39 tlr: 0.00017 tnm: 0.22 Lm: 6.429 (6.429) Lt: 5.615 (5.615) Accm: 3.29 (3.29) Acct: 5.13 (5.13) proj_loss: -0.5883 (-0.5883) time: 0.8863 data: 0.0003 [11-25 06:22:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 0/1669] eta: 0:24:39 tlr: 0.00017 tnm: 0.22 Lm: 6.366 (6.366) Lt: 5.564 (5.564) Accm: 4.21 (4.21) Acct: 6.44 (6.44) proj_loss: -0.6284 (-0.6284) time: 0.8864 data: 0.0003 [11-25 06:22:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 0/1669] eta: 0:24:39 tlr: 0.00017 tnm: 0.22 Lm: 6.290 (6.290) Lt: 5.545 (5.545) Accm: 3.74 (3.74) Acct: 5.85 (5.85) proj_loss: -0.6179 (-0.6179) time: 0.8866 data: 0.0004 [11-25 06:22:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 0/1669] eta: 0:24:40 tlr: 0.00017 tnm: 0.22 Lm: 6.645 (6.645) Lt: 5.933 (5.933) Accm: 3.06 (3.06) Acct: 5.13 (5.13) proj_loss: -0.6081 (-0.6081) time: 0.8868 data: 0.0004 [11-25 06:22:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 0/1669] eta: 0:24:40 tlr: 0.00017 tnm: 0.22 Lm: 6.455 (6.455) Lt: 5.705 (5.705) Accm: 3.34 (3.34) Acct: 4.55 (4.55) proj_loss: -0.6030 (-0.6030) time: 0.8868 data: 0.0003 [11-25 06:22:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 0/1669] eta: 0:24:40 tlr: 0.00017 tnm: 0.22 Lm: 6.466 (6.466) Lt: 5.751 (5.751) Accm: 3.21 (3.21) Acct: 5.06 (5.06) proj_loss: -0.6273 (-0.6273) time: 0.8871 data: 0.0003 [11-25 06:22:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 0/1669] eta: 0:24:40 tlr: 0.00017 tnm: 0.22 Lm: 6.666 (6.666) Lt: 5.921 (5.921) Accm: 2.62 (2.62) Acct: 4.27 (4.27) proj_loss: -0.6069 (-0.6069) time: 0.8871 data: 0.0004 [11-25 06:22:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 0/1669] eta: 0:24:39 tlr: 0.00017 tnm: 0.22 Lm: 6.278 (6.278) Lt: 5.494 (5.494) Accm: 4.31 (4.31) Acct: 6.40 (6.40) proj_loss: -0.6223 (-0.6223) time: 0.8863 data: 0.0003 [11-25 06:28:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 417/1669] eta: 0:19:20 tlr: 0.00017 tnm: 0.22 Lm: 6.454 (6.454) Lt: 5.702 (5.702) Accm: 3.92 (3.92) Acct: 6.01 (6.01) proj_loss: -0.6226 (-0.6226) time: 0.9269 data: 0.0003 [11-25 06:28:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 417/1669] eta: 0:19:20 tlr: 0.00017 tnm: 0.22 Lm: 6.509 (6.509) Lt: 5.828 (5.828) Accm: 3.28 (3.28) Acct: 5.10 (5.10) proj_loss: -0.6276 (-0.6276) time: 0.9269 data: 0.0002 [11-25 06:28:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 417/1669] eta: 0:19:20 tlr: 0.00017 tnm: 0.22 Lm: 6.507 (6.507) Lt: 5.747 (5.747) Accm: 3.26 (3.26) Acct: 5.04 (5.04) proj_loss: -0.6170 (-0.6170) time: 0.9269 data: 0.0002 [11-25 06:28:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 417/1669] eta: 0:19:20 tlr: 0.00017 tnm: 0.22 Lm: 6.438 (6.438) Lt: 5.658 (5.658) Accm: 3.74 (3.74) Acct: 5.85 (5.85) proj_loss: -0.6218 (-0.6218) time: 0.9269 data: 0.0002 [11-25 06:28:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 417/1669] eta: 0:19:20 tlr: 0.00017 tnm: 0.22 Lm: 6.449 (6.449) Lt: 5.679 (5.679) Accm: 3.47 (3.47) Acct: 5.37 (5.37) proj_loss: -0.6190 (-0.6190) time: 0.9269 data: 0.0003 [11-25 06:28:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 417/1669] eta: 0:19:20 tlr: 0.00017 tnm: 0.22 Lm: 6.529 (6.529) Lt: 5.796 (5.796) Accm: 3.04 (3.04) Acct: 5.01 (5.01) proj_loss: -0.6082 (-0.6082) time: 0.9269 data: 0.0003 [11-25 06:28:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 417/1669] eta: 0:19:20 tlr: 0.00017 tnm: 0.22 Lm: 6.549 (6.549) Lt: 5.837 (5.837) Accm: 3.34 (3.34) Acct: 5.30 (5.30) proj_loss: -0.6127 (-0.6127) time: 0.9269 data: 0.0003 [11-25 06:28:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 417/1669] eta: 0:19:20 tlr: 0.00017 tnm: 0.22 Lm: 6.389 (6.389) Lt: 5.599 (5.599) Accm: 3.50 (3.50) Acct: 5.11 (5.11) proj_loss: -0.5938 (-0.5938) time: 0.9269 data: 0.0002 [11-25 06:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 834/1669] eta: 0:12:53 tlr: 0.00017 tnm: 0.24 Lm: 6.455 (6.480) Lt: 5.705 (5.723) Accm: 3.34 (3.31) Acct: 4.79 (5.00) proj_loss: -0.6030 (-0.6009) time: 0.9253 data: 0.0002 [11-25 06:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 834/1669] eta: 0:12:53 tlr: 0.00017 tnm: 0.24 Lm: 6.466 (6.454) Lt: 5.751 (5.754) Accm: 3.35 (3.53) Acct: 5.13 (5.48) proj_loss: -0.6273 (-0.6188) time: 0.9253 data: 0.0002 [11-25 06:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 834/1669] eta: 0:12:53 tlr: 0.00017 tnm: 0.24 Lm: 6.511 (6.516) Lt: 5.752 (5.738) Accm: 3.26 (3.47) Acct: 5.27 (5.43) proj_loss: -0.6151 (-0.6189) time: 0.9253 data: 0.0002 [11-25 06:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 834/1669] eta: 0:12:53 tlr: 0.00017 tnm: 0.24 Lm: 6.586 (6.566) Lt: 5.880 (5.853) Accm: 3.23 (3.19) Acct: 4.96 (4.84) proj_loss: -0.6456 (-0.6294) time: 0.9253 data: 0.0002 [11-25 06:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 834/1669] eta: 0:12:53 tlr: 0.00017 tnm: 0.24 Lm: 6.607 (6.512) Lt: 5.812 (5.793) Accm: 3.19 (3.30) Acct: 4.89 (5.11) proj_loss: -0.6202 (-0.6206) time: 0.9253 data: 0.0003 [11-25 06:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 834/1669] eta: 0:12:53 tlr: 0.00017 tnm: 0.24 Lm: 6.648 (6.569) Lt: 5.879 (5.823) Accm: 3.28 (3.12) Acct: 5.20 (5.07) proj_loss: -0.6095 (-0.6128) time: 0.9253 data: 0.0003 [11-25 06:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 834/1669] eta: 0:12:53 tlr: 0.00017 tnm: 0.24 Lm: 6.611 (6.507) Lt: 5.817 (5.741) Accm: 3.53 (3.60) Acct: 5.61 (5.72) proj_loss: -0.6223 (-0.6215) time: 0.9253 data: 0.0003 [11-25 06:35:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [ 834/1669] eta: 0:12:53 tlr: 0.00017 tnm: 0.24 Lm: 6.454 (6.463) Lt: 5.742 (5.728) Accm: 3.61 (3.46) Acct: 5.48 (5.41) proj_loss: -0.6173 (-0.6169) time: 0.9253 data: 0.0003 [11-25 06:41:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.24 Lm: 6.514 (6.491) Lt: 5.808 (5.764) Accm: 3.45 (3.41) Acct: 5.30 (5.34) proj_loss: -0.6127 (-0.6143) time: 0.9269 data: 0.0003 [11-25 06:41:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.24 Lm: 6.496 (6.472) Lt: 5.819 (5.788) Accm: 3.28 (3.44) Acct: 5.10 (5.33) proj_loss: -0.6143 (-0.6136) time: 0.9269 data: 0.0002 [11-25 06:41:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.24 Lm: 6.438 (6.474) Lt: 5.658 (5.684) Accm: 3.47 (3.53) Acct: 5.49 (5.50) proj_loss: -0.6147 (-0.6177) time: 0.9269 data: 0.0002 [11-25 06:41:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.24 Lm: 6.507 (6.446) Lt: 5.747 (5.713) Accm: 3.26 (3.49) Acct: 5.04 (5.29) proj_loss: -0.6413 (-0.6313) time: 0.9269 data: 0.0002 [11-25 06:41:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.24 Lm: 6.518 (6.491) Lt: 5.688 (5.736) Accm: 3.47 (3.46) Acct: 5.37 (5.48) proj_loss: -0.6190 (-0.5999) time: 0.9269 data: 0.0003 [11-25 06:41:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.24 Lm: 6.520 (6.525) Lt: 5.774 (5.776) Accm: 3.37 (3.31) Acct: 5.48 (5.26) proj_loss: -0.6082 (-0.6113) time: 0.9269 data: 0.0003 [11-25 06:41:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.24 Lm: 6.481 (6.467) Lt: 5.712 (5.707) Accm: 3.66 (3.65) Acct: 5.48 (5.62) proj_loss: -0.6208 (-0.6179) time: 0.9269 data: 0.0003 [11-25 06:41:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.24 Lm: 6.420 (6.456) Lt: 5.656 (5.694) Accm: 3.50 (3.54) Acct: 5.23 (5.41) proj_loss: -0.6059 (-0.6028) time: 0.9269 data: 0.0003 [11-25 06:48:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.455 (6.485) Lt: 5.705 (5.720) Accm: 3.34 (3.39) Acct: 4.79 (5.27) proj_loss: -0.6088 (-0.6070) time: 0.9272 data: 0.0017 [11-25 06:48:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 118/350] Total time: 0:26:08 (0.940 s / it) [11-25 06:48:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.511 (6.490) Lt: 5.752 (5.712) Accm: 3.28 (3.48) Acct: 5.27 (5.37) proj_loss: -0.6142 (-0.6136) time: 0.9272 data: 0.0020 [11-25 06:48:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.429 (6.384) Lt: 5.615 (5.631) Accm: 3.29 (3.80) Acct: 5.13 (5.85) proj_loss: -0.6369 (-0.6261) time: 0.9272 data: 0.0018 [11-25 06:48:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.428 (6.473) Lt: 5.585 (5.706) Accm: 3.74 (3.53) Acct: 5.85 (5.59) proj_loss: -0.6200 (-0.6039) time: 0.9272 data: 0.0022 [11-25 06:48:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.526 (6.512) Lt: 5.887 (5.816) Accm: 3.21 (3.31) Acct: 5.06 (5.16) proj_loss: -0.6027 (-0.6114) time: 0.9272 data: 0.0020 [11-25 06:48:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.454 (6.404) Lt: 5.742 (5.673) Accm: 3.61 (3.70) Acct: 5.48 (5.83) proj_loss: -0.6173 (-0.6228) time: 0.9272 data: 0.0017 [11-25 06:48:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.600 (6.494) Lt: 5.817 (5.734) Accm: 3.53 (3.48) Acct: 5.34 (5.45) proj_loss: -0.6194 (-0.6090) time: 0.9272 data: 0.0021 [11-25 06:48:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 118/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.22 Lm: 6.648 (6.570) Lt: 5.879 (5.818) Accm: 3.28 (3.20) Acct: 5.20 (5.17) proj_loss: -0.6069 (-0.6075) time: 0.9272 data: 0.0021 [11-25 06:48:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 118/350] Total time: 0:26:08 (0.940 s / it) [11-25 06:48:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 118/350] Total time: 0:26:08 (0.940 s / it) [11-25 06:48:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 118/350] Total time: 0:26:08 (0.940 s / it) [11-25 06:48:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 118/350] Total time: 0:26:08 (0.940 s / it) [11-25 06:48:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 118/350] Total time: 0:26:08 (0.940 s / it) [11-25 06:48:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 118/350] Total time: 0:26:08 (0.940 s / it) [11-25 06:48:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 118/350] Total time: 0:26:08 (0.940 s / it) [11-25 06:48:15] (/home/user/VAR/train.py , line 276)=> [ep118] (training ) Lm: 6.476 (6.476), Lt: 5.720 (5.720), Acc m&t: 3.45 5.43, Remain: 4 days, 3:56:03, Finish: 2024-11-28 18:44 [11-25 06:48:15] (/home/user/VAR/train.py , line 276)=> [ep118] (training ) Lm: 6.476 (6.476), Lt: 5.720 (5.720), Acc m&t: 3.45 5.43, Remain: 4 days, 3:56:47, Finish: 2024-11-28 18:45 [11-25 06:48:15] (/home/user/VAR/train.py , line 276)=> [ep118] (training ) Lm: 6.476 (6.476), Lt: 5.720 (5.720), Acc m&t: 3.45 5.43, Remain: 4 days, 3:56:44, Finish: 2024-11-28 18:44 [11-25 06:48:15] (/home/user/VAR/train.py , line 276)=> [ep118] (training ) Lm: 6.476 (6.476), Lt: 5.720 (5.720), Acc m&t: 3.45 5.43, Remain: 4 days, 3:54:53, Finish: 2024-11-28 18:43 [11-25 06:48:15] (/home/user/VAR/train.py , line 276)=> [ep118] (training ) Lm: 6.476 (6.476), Lt: 5.720 (5.720), Acc m&t: 3.45 5.43, Remain: 4 days, 3:55:14, Finish: 2024-11-28 18:43 [11-25 06:48:15] (/home/user/VAR/train.py , line 276)=> [ep118] (training ) Lm: 6.476 (6.476), Lt: 5.720 (5.720), Acc m&t: 3.45 5.43, Remain: 4 days, 3:54:35, Finish: 2024-11-28 18:42 [11-25 06:48:15] (/home/user/VAR/train.py , line 276)=> [ep118] (training ) Lm: 6.476 (6.476), Lt: 5.720 (5.720), Acc m&t: 3.45 5.43, Remain: 4 days, 3:54:59, Finish: 2024-11-28 18:43 [11-25 06:48:15] (/home/user/VAR/train.py , line 276)=> [ep118] (training ) Lm: 6.476 (6.476), Lt: 5.720 (5.720), Acc m&t: 3.45 5.43, Remain: 4 days, 3:57:45, Finish: 2024-11-28 18:46 [11-25 06:48:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 0/1669] eta: 0:24:36 tlr: 0.00017 tnm: 0.23 Lm: 6.520 (6.520) Lt: 5.734 (5.734) Accm: 3.45 (3.45) Acct: 5.58 (5.58) proj_loss: -0.5447 (-0.5447) time: 0.8849 data: 0.0004 [11-25 06:48:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 0/1669] eta: 0:24:35 tlr: 0.00017 tnm: 0.23 Lm: 6.356 (6.356) Lt: 5.507 (5.507) Accm: 3.95 (3.95) Acct: 6.44 (6.44) proj_loss: -0.6145 (-0.6145) time: 0.8839 data: 0.0004 [11-25 06:48:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 0/1669] eta: 0:24:36 tlr: 0.00017 tnm: 0.23 Lm: 6.526 (6.526) Lt: 5.696 (5.696) Accm: 3.19 (3.19) Acct: 5.23 (5.23) proj_loss: -0.6082 (-0.6082) time: 0.8848 data: 0.0003 [11-25 06:48:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 0/1669] eta: 0:24:34 tlr: 0.00017 tnm: 0.23 Lm: 6.479 (6.479) Lt: 5.715 (5.715) Accm: 3.51 (3.51) Acct: 5.48 (5.48) proj_loss: -0.6252 (-0.6252) time: 0.8834 data: 0.0003 [11-25 06:48:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 0/1669] eta: 0:24:36 tlr: 0.00017 tnm: 0.23 Lm: 6.487 (6.487) Lt: 5.740 (5.740) Accm: 3.77 (3.77) Acct: 6.10 (6.10) proj_loss: -0.6206 (-0.6206) time: 0.8848 data: 0.0003 [11-25 06:48:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 0/1669] eta: 0:24:37 tlr: 0.00017 tnm: 0.23 Lm: 6.476 (6.476) Lt: 5.716 (5.716) Accm: 3.41 (3.41) Acct: 5.23 (5.23) proj_loss: -0.6109 (-0.6109) time: 0.8855 data: 0.0003 [11-25 06:48:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 0/1669] eta: 0:24:37 tlr: 0.00017 tnm: 0.23 Lm: 6.575 (6.575) Lt: 5.872 (5.872) Accm: 3.10 (3.10) Acct: 4.89 (4.89) proj_loss: -0.6445 (-0.6445) time: 0.8855 data: 0.0004 [11-25 06:48:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 0/1669] eta: 0:24:38 tlr: 0.00017 tnm: 0.23 Lm: 6.511 (6.511) Lt: 5.636 (5.636) Accm: 3.48 (3.48) Acct: 5.72 (5.72) proj_loss: -0.5884 (-0.5884) time: 0.8858 data: 0.0004 [11-25 06:54:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.23 Lm: 6.486 (6.486) Lt: 5.621 (5.621) Accm: 3.55 (3.55) Acct: 5.82 (5.82) proj_loss: -0.5888 (-0.5888) time: 0.9280 data: 0.0003 [11-25 06:54:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.23 Lm: 6.424 (6.424) Lt: 5.598 (5.598) Accm: 3.72 (3.72) Acct: 6.10 (6.10) proj_loss: -0.6072 (-0.6072) time: 0.9280 data: 0.0002 [11-25 06:54:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.23 Lm: 6.436 (6.436) Lt: 5.715 (5.715) Accm: 3.53 (3.53) Acct: 5.54 (5.54) proj_loss: -0.6308 (-0.6308) time: 0.9280 data: 0.0003 [11-25 06:54:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.23 Lm: 6.447 (6.447) Lt: 5.692 (5.692) Accm: 3.70 (3.70) Acct: 6.10 (6.10) proj_loss: -0.6080 (-0.6080) time: 0.9280 data: 0.0002 [11-25 06:54:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.23 Lm: 6.483 (6.483) Lt: 5.743 (5.743) Accm: 3.53 (3.53) Acct: 5.44 (5.44) proj_loss: -0.6302 (-0.6302) time: 0.9280 data: 0.0003 [11-25 06:54:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.23 Lm: 6.375 (6.375) Lt: 5.579 (5.579) Accm: 3.92 (3.92) Acct: 6.06 (6.06) proj_loss: -0.5861 (-0.5861) time: 0.9280 data: 0.0003 [11-25 06:54:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.23 Lm: 6.567 (6.567) Lt: 5.849 (5.849) Accm: 3.15 (3.15) Acct: 5.04 (5.04) proj_loss: -0.6252 (-0.6252) time: 0.9280 data: 0.0002 [11-25 06:54:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.23 Lm: 6.399 (6.399) Lt: 5.600 (5.600) Accm: 3.82 (3.82) Acct: 5.97 (5.97) proj_loss: -0.6026 (-0.6026) time: 0.9280 data: 0.0003 [11-25 07:01:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 834/1669] eta: 0:12:55 tlr: 0.00017 tnm: 0.23 Lm: 6.476 (6.530) Lt: 5.716 (5.753) Accm: 3.41 (3.43) Acct: 5.23 (5.27) proj_loss: -0.6085 (-0.6046) time: 0.9242 data: 0.0003 [11-25 07:01:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 834/1669] eta: 0:12:55 tlr: 0.00017 tnm: 0.23 Lm: 6.526 (6.502) Lt: 5.696 (5.703) Accm: 3.19 (3.40) Acct: 5.23 (5.60) proj_loss: -0.6062 (-0.6019) time: 0.9242 data: 0.0002 [11-25 07:01:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 834/1669] eta: 0:12:55 tlr: 0.00017 tnm: 0.23 Lm: 6.479 (6.471) Lt: 5.715 (5.758) Accm: 3.51 (3.45) Acct: 5.48 (5.28) proj_loss: -0.6252 (-0.6257) time: 0.9242 data: 0.0002 [11-25 07:01:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 834/1669] eta: 0:12:55 tlr: 0.00017 tnm: 0.23 Lm: 6.575 (6.577) Lt: 5.872 (5.858) Accm: 3.10 (3.10) Acct: 4.89 (4.83) proj_loss: -0.6058 (-0.6175) time: 0.9242 data: 0.0003 [11-25 07:01:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 834/1669] eta: 0:12:55 tlr: 0.00017 tnm: 0.23 Lm: 6.406 (6.389) Lt: 5.645 (5.649) Accm: 3.77 (3.89) Acct: 6.10 (6.22) proj_loss: -0.5954 (-0.6020) time: 0.9242 data: 0.0003 [11-25 07:01:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 834/1669] eta: 0:12:55 tlr: 0.00017 tnm: 0.23 Lm: 6.356 (6.418) Lt: 5.569 (5.685) Accm: 3.72 (3.59) Acct: 5.61 (5.50) proj_loss: -0.6350 (-0.6318) time: 0.9242 data: 0.0003 [11-25 07:01:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 834/1669] eta: 0:12:55 tlr: 0.00017 tnm: 0.23 Lm: 6.511 (6.577) Lt: 5.636 (5.790) Accm: 3.48 (3.20) Acct: 5.72 (5.15) proj_loss: -0.5893 (-0.6002) time: 0.9242 data: 0.0003 [11-25 07:01:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [ 834/1669] eta: 0:12:55 tlr: 0.00017 tnm: 0.23 Lm: 6.231 (6.281) Lt: 5.423 (5.500) Accm: 4.37 (4.07) Acct: 6.54 (6.44) proj_loss: -0.6274 (-0.6026) time: 0.9242 data: 0.0003 [11-25 07:07:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.375 (6.342) Lt: 5.563 (5.551) Accm: 3.98 (3.95) Acct: 6.23 (6.31) proj_loss: -0.6214 (-0.6058) time: 0.9285 data: 0.0003 [11-25 07:07:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.486 (6.476) Lt: 5.716 (5.748) Accm: 3.47 (3.45) Acct: 5.53 (5.35) proj_loss: -0.6203 (-0.6153) time: 0.9285 data: 0.0002 [11-25 07:07:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.486 (6.545) Lt: 5.693 (5.780) Accm: 3.38 (3.22) Acct: 5.39 (5.13) proj_loss: -0.5959 (-0.6007) time: 0.9285 data: 0.0003 [11-25 07:07:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.376 (6.412) Lt: 5.561 (5.652) Accm: 3.61 (3.57) Acct: 5.63 (5.54) proj_loss: -0.6247 (-0.6271) time: 0.9285 data: 0.0003 [11-25 07:07:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.567 (6.555) Lt: 5.849 (5.810) Accm: 3.04 (3.04) Acct: 4.99 (4.90) proj_loss: -0.6073 (-0.6153) time: 0.9285 data: 0.0003 [11-25 07:07:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.447 (6.444) Lt: 5.692 (5.704) Accm: 3.70 (3.60) Acct: 6.10 (5.79) proj_loss: -0.5995 (-0.6024) time: 0.9285 data: 0.0003 [11-25 07:07:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.551 (6.521) Lt: 5.747 (5.727) Accm: 3.15 (3.33) Acct: 5.25 (5.52) proj_loss: -0.5988 (-0.5943) time: 0.9285 data: 0.0003 [11-25 07:07:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.546 (6.552) Lt: 5.810 (5.791) Accm: 3.13 (3.29) Acct: 4.87 (5.08) proj_loss: -0.6014 (-0.6002) time: 0.9285 data: 0.0003 [11-25 07:14:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.586 (6.559) Lt: 5.884 (5.809) Accm: 2.87 (3.21) Acct: 4.51 (4.91) proj_loss: -0.6085 (-0.6022) time: 0.9285 data: 0.0015 [11-25 07:14:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 119/350] Total time: 0:25:48 (0.928 s / it) [11-25 07:14:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.526 (6.518) Lt: 5.708 (5.723) Accm: 3.12 (3.27) Acct: 5.23 (5.31) proj_loss: -0.5913 (-0.5917) time: 0.9284 data: 0.0016 [11-25 07:14:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.492 (6.511) Lt: 5.717 (5.789) Accm: 3.42 (3.30) Acct: 5.48 (5.10) proj_loss: -0.6155 (-0.6133) time: 0.9284 data: 0.0015 [11-25 07:14:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.395 (6.420) Lt: 5.569 (5.665) Accm: 3.50 (3.55) Acct: 5.61 (5.54) proj_loss: -0.6149 (-0.6246) time: 0.9285 data: 0.0018 [11-25 07:14:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.406 (6.429) Lt: 5.645 (5.687) Accm: 3.63 (3.57) Acct: 6.10 (5.65) proj_loss: -0.6036 (-0.6035) time: 0.9284 data: 0.0015 [11-25 07:14:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.460 (6.526) Lt: 5.650 (5.754) Accm: 3.48 (3.32) Acct: 5.72 (5.31) proj_loss: -0.5893 (-0.5982) time: 0.9284 data: 0.0017 [11-25 07:14:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.559 (6.507) Lt: 5.827 (5.759) Accm: 3.10 (3.24) Acct: 5.10 (5.11) proj_loss: -0.6058 (-0.6129) time: 0.9284 data: 0.0017 [11-25 07:14:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 119/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.285 (6.331) Lt: 5.452 (5.531) Accm: 4.02 (3.96) Acct: 6.54 (6.39) proj_loss: -0.6154 (-0.6047) time: 0.9284 data: 0.0018 [11-25 07:14:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 119/350] Total time: 0:25:48 (0.928 s / it) [11-25 07:14:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 119/350] Total time: 0:25:48 (0.928 s / it) [11-25 07:14:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 119/350] Total time: 0:25:48 (0.928 s / it) [11-25 07:14:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 119/350] Total time: 0:25:48 (0.928 s / it) [11-25 07:14:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 119/350] Total time: 0:25:48 (0.928 s / it) [11-25 07:14:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 119/350] Total time: 0:25:48 (0.928 s / it) [11-25 07:14:03] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 119/350] Total time: 0:25:48 (0.928 s / it) [11-25 07:18:47] (home/user/VAR/trainer.py, line 114)=> FID: 3.565091666292801 [11-25 07:18:48] (/home/user/VAR/train.py , line 259)=> [*] [ep119] (val 50000) Lm: 6.4723, Lt: 5.7169, Acc m&t: 3.46 5.45, Val cost: 284.23s [11-25 07:18:48] (/home/user/VAR/train.py , line 264)=> [saving ckpt] ... [saving ckpt](*) finished! @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth [11-25 07:19:58] (/home/user/VAR/train.py , line 276)=> [ep119] (training ) Lm: 6.472 (6.472), Lt: 5.717 (5.717), Acc m&t: 3.46 5.45, Remain: 4 days, 3:39:56, Finish: 2024-11-28 18:54 [11-25 07:19:58] (/home/user/VAR/train.py , line 276)=> [ep119] (training ) Lm: 6.472 (6.472), Lt: 5.717 (5.717), Acc m&t: 3.46 5.45, Remain: 4 days, 3:38:27, Finish: 2024-11-28 18:52 [11-25 07:19:58] (/home/user/VAR/train.py , line 276)=> [ep119] (training ) Lm: 6.472 (6.472), Lt: 5.717 (5.717), Acc m&t: 3.46 5.45, Remain: 4 days, 3:37:08, Finish: 2024-11-28 18:51 [11-25 07:19:58] (/home/user/VAR/train.py , line 276)=> [ep119] (training ) Lm: 6.472 (6.472), Lt: 5.717 (5.717), Acc m&t: 3.46 5.45, Remain: 4 days, 3:39:11, Finish: 2024-11-28 18:53 [11-25 07:19:58] (/home/user/VAR/train.py , line 276)=> [ep119] (training ) Lm: 6.472 (6.472), Lt: 5.717 (5.717), Acc m&t: 3.46 5.45, Remain: 4 days, 3:37:28, Finish: 2024-11-28 18:51 [11-25 07:19:58] (/home/user/VAR/train.py , line 276)=> [ep119] (training ) Lm: 6.472 (6.472), Lt: 5.717 (5.717), Acc m&t: 3.46 5.45, Remain: 4 days, 3:36:37, Finish: 2024-11-28 18:50 [11-25 07:19:58] (/home/user/VAR/train.py , line 276)=> [ep119] (training ) Lm: 6.472 (6.472), Lt: 5.717 (5.717), Acc m&t: 3.46 5.45, Remain: 4 days, 3:38:43, Finish: 2024-11-28 18:52 [11-25 07:19:58] (/home/user/VAR/train.py , line 276)=> [ep119] (training ) Lm: 6.472 (6.472), Lt: 5.717 (5.717), Acc m&t: 3.46 5.45, Remain: 4 days, 3:38:39, Finish: 2024-11-28 18:52 [11-25 07:19:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 0/1669] eta: 0:28:39 tlr: 0.00017 tnm: 0.23 Lm: 6.254 (6.254) Lt: 5.459 (5.459) Accm: 4.15 (4.15) Acct: 6.37 (6.37) proj_loss: -0.5984 (-0.5984) time: 1.0303 data: 0.0004 [11-25 07:19:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 0/1669] eta: 0:28:16 tlr: 0.00017 tnm: 0.23 Lm: 6.603 (6.603) Lt: 5.942 (5.942) Accm: 2.72 (2.72) Acct: 4.20 (4.20) proj_loss: -0.5832 (-0.5832) time: 1.0163 data: 0.0004 [11-25 07:19:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 0/1669] eta: 0:28:16 tlr: 0.00017 tnm: 0.23 Lm: 6.555 (6.555) Lt: 5.760 (5.760) Accm: 3.37 (3.37) Acct: 5.44 (5.44) proj_loss: -0.6245 (-0.6245) time: 1.0163 data: 0.0004 [11-25 07:19:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 0/1669] eta: 0:28:16 tlr: 0.00017 tnm: 0.23 Lm: 6.657 (6.657) Lt: 5.927 (5.927) Accm: 2.97 (2.97) Acct: 4.61 (4.61) proj_loss: -0.6056 (-0.6056) time: 1.0164 data: 0.0004 [11-25 07:19:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 0/1669] eta: 0:28:16 tlr: 0.00017 tnm: 0.23 Lm: 6.438 (6.438) Lt: 5.680 (5.680) Accm: 3.37 (3.37) Acct: 5.37 (5.37) proj_loss: -0.6209 (-0.6209) time: 1.0166 data: 0.0004 [11-25 07:19:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 0/1669] eta: 0:28:17 tlr: 0.00017 tnm: 0.23 Lm: 6.235 (6.235) Lt: 5.470 (5.470) Accm: 4.12 (4.12) Acct: 6.16 (6.16) proj_loss: -0.6017 (-0.6017) time: 1.0168 data: 0.0004 [11-25 07:19:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 0/1669] eta: 0:28:17 tlr: 0.00017 tnm: 0.23 Lm: 6.555 (6.555) Lt: 5.791 (5.791) Accm: 3.37 (3.37) Acct: 5.54 (5.54) proj_loss: -0.6045 (-0.6045) time: 1.0171 data: 0.0004 [11-25 07:19:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 0/1669] eta: 0:28:19 tlr: 0.00017 tnm: 0.23 Lm: 6.476 (6.476) Lt: 5.753 (5.753) Accm: 3.83 (3.83) Acct: 5.85 (5.85) proj_loss: -0.5814 (-0.5814) time: 1.0183 data: 0.0004 [11-25 07:26:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.25 Lm: 6.472 (6.472) Lt: 5.752 (5.752) Accm: 3.46 (3.46) Acct: 5.22 (5.22) proj_loss: -0.5870 (-0.5870) time: 0.9286 data: 0.0003 [11-25 07:26:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.25 Lm: 6.478 (6.478) Lt: 5.703 (5.703) Accm: 3.36 (3.36) Acct: 5.32 (5.32) proj_loss: -0.6236 (-0.6236) time: 0.9286 data: 0.0002 [11-25 07:26:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.25 Lm: 6.523 (6.523) Lt: 5.827 (5.827) Accm: 2.94 (2.94) Acct: 4.60 (4.60) proj_loss: -0.6035 (-0.6035) time: 0.9286 data: 0.0002 [11-25 07:26:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.25 Lm: 6.490 (6.490) Lt: 5.728 (5.728) Accm: 3.29 (3.29) Acct: 5.25 (5.25) proj_loss: -0.5892 (-0.5892) time: 0.9286 data: 0.0003 [11-25 07:26:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.25 Lm: 6.601 (6.601) Lt: 5.847 (5.847) Accm: 3.08 (3.08) Acct: 4.94 (4.94) proj_loss: -0.6064 (-0.6064) time: 0.9286 data: 0.0003 [11-25 07:26:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.25 Lm: 6.540 (6.540) Lt: 5.758 (5.758) Accm: 3.37 (3.37) Acct: 5.53 (5.53) proj_loss: -0.5956 (-0.5956) time: 0.9286 data: 0.0003 [11-25 07:26:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.25 Lm: 6.395 (6.395) Lt: 5.644 (5.644) Accm: 3.55 (3.55) Acct: 5.42 (5.42) proj_loss: -0.6009 (-0.6009) time: 0.9286 data: 0.0003 [11-25 07:26:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.25 Lm: 6.423 (6.423) Lt: 5.685 (5.685) Accm: 3.63 (3.63) Acct: 5.58 (5.58) proj_loss: -0.5995 (-0.5995) time: 0.9286 data: 0.0002 [11-25 07:32:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.24 Lm: 6.479 (6.442) Lt: 5.738 (5.703) Accm: 3.54 (3.60) Acct: 5.37 (5.51) proj_loss: -0.5974 (-0.5945) time: 0.9263 data: 0.0003 [11-25 07:32:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.24 Lm: 6.401 (6.446) Lt: 5.646 (5.676) Accm: 3.37 (3.50) Acct: 5.44 (5.60) proj_loss: -0.6227 (-0.6225) time: 0.9263 data: 0.0002 [11-25 07:32:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.24 Lm: 6.563 (6.514) Lt: 5.801 (5.752) Accm: 3.16 (3.25) Acct: 4.61 (5.04) proj_loss: -0.5990 (-0.5925) time: 0.9263 data: 0.0003 [11-25 07:32:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.24 Lm: 6.555 (6.558) Lt: 5.791 (5.781) Accm: 3.37 (3.22) Acct: 5.51 (5.19) proj_loss: -0.5866 (-0.5888) time: 0.9263 data: 0.0002 [11-25 07:32:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.24 Lm: 6.438 (6.481) Lt: 5.680 (5.719) Accm: 3.37 (3.49) Acct: 5.37 (5.70) proj_loss: -0.6093 (-0.6074) time: 0.9263 data: 0.0003 [11-25 07:32:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.24 Lm: 6.443 (6.472) Lt: 5.711 (5.724) Accm: 3.15 (3.13) Acct: 4.99 (4.89) proj_loss: -0.6131 (-0.6067) time: 0.9263 data: 0.0003 [11-25 07:32:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.24 Lm: 6.537 (6.448) Lt: 5.798 (5.695) Accm: 3.35 (3.48) Acct: 5.72 (5.52) proj_loss: -0.6035 (-0.6064) time: 0.9263 data: 0.0003 [11-25 07:32:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.24 Lm: 6.468 (6.455) Lt: 5.750 (5.715) Accm: 3.61 (3.51) Acct: 5.85 (5.45) proj_loss: -0.5927 (-0.5945) time: 0.9263 data: 0.0003 [11-25 07:39:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.24 Lm: 6.444 (6.424) Lt: 5.696 (5.690) Accm: 3.72 (3.69) Acct: 5.89 (5.61) proj_loss: -0.6011 (-0.6004) time: 0.9264 data: 0.0003 [11-25 07:39:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.24 Lm: 6.477 (6.482) Lt: 5.738 (5.734) Accm: 3.15 (3.13) Acct: 5.20 (5.02) proj_loss: -0.6022 (-0.6029) time: 0.9263 data: 0.0002 [11-25 07:39:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.24 Lm: 6.391 (6.422) Lt: 5.634 (5.630) Accm: 3.58 (3.70) Acct: 5.80 (5.90) proj_loss: -0.6215 (-0.6204) time: 0.9263 data: 0.0002 [11-25 07:39:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.24 Lm: 6.556 (6.523) Lt: 5.827 (5.778) Accm: 3.08 (3.19) Acct: 4.61 (4.93) proj_loss: -0.6023 (-0.5999) time: 0.9263 data: 0.0003 [11-25 07:39:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.24 Lm: 6.546 (6.480) Lt: 5.813 (5.746) Accm: 3.15 (3.31) Acct: 5.10 (5.22) proj_loss: -0.6070 (-0.6074) time: 0.9263 data: 0.0003 [11-25 07:39:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.24 Lm: 6.544 (6.523) Lt: 5.815 (5.777) Accm: 3.08 (3.31) Acct: 4.94 (5.35) proj_loss: -0.6006 (-0.6019) time: 0.9263 data: 0.0003 [11-25 07:39:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.24 Lm: 6.575 (6.580) Lt: 5.809 (5.813) Accm: 3.15 (3.11) Acct: 5.01 (4.88) proj_loss: -0.5956 (-0.5965) time: 0.9264 data: 0.0002 [11-25 07:39:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.24 Lm: 6.429 (6.426) Lt: 5.707 (5.696) Accm: 3.74 (3.68) Acct: 5.60 (5.59) proj_loss: -0.5995 (-0.6031) time: 0.9264 data: 0.0003 [11-25 07:45:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.443 (6.457) Lt: 5.711 (5.713) Accm: 3.15 (3.24) Acct: 5.41 (5.18) proj_loss: -0.6013 (-0.6025) time: 0.9307 data: 0.0021 [11-25 07:45:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.549 (6.504) Lt: 5.801 (5.767) Accm: 3.04 (3.16) Acct: 4.61 (4.91) proj_loss: -0.6056 (-0.6021) time: 0.9307 data: 0.0016 [11-25 07:45:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.555 (6.513) Lt: 5.791 (5.752) Accm: 3.37 (3.43) Acct: 5.51 (5.38) proj_loss: -0.6045 (-0.5997) time: 0.9307 data: 0.0013 [11-25 07:45:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.381 (6.407) Lt: 5.623 (5.626) Accm: 3.58 (3.67) Acct: 5.85 (5.89) proj_loss: -0.6212 (-0.6205) time: 0.9307 data: 0.0016 [11-25 07:45:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.479 (6.439) Lt: 5.738 (5.716) Accm: 3.54 (3.52) Acct: 5.37 (5.35) proj_loss: -0.6017 (-0.6093) time: 0.9307 data: 0.0021 [11-25 07:45:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.555 (6.520) Lt: 5.829 (5.787) Accm: 2.94 (3.23) Acct: 4.48 (5.07) proj_loss: -0.6105 (-0.6081) time: 0.9307 data: 0.0016 [11-25 07:45:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.468 (6.481) Lt: 5.750 (5.752) Accm: 3.61 (3.55) Acct: 5.85 (5.39) proj_loss: -0.5972 (-0.5998) time: 0.9307 data: 0.0023 [11-25 07:45:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 120/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.649 (6.548) Lt: 5.889 (5.799) Accm: 3.18 (3.28) Acct: 5.20 (5.32) proj_loss: -0.6065 (-0.6028) time: 0.9307 data: 0.0020 [11-25 07:45:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 120/350] Total time: 0:25:48 (0.928 s / it) [11-25 07:45:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 120/350] Total time: 0:25:48 (0.928 s / it) [11-25 07:45:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 120/350] Total time: 0:25:48 (0.928 s / it) [11-25 07:45:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 120/350] Total time: 0:25:48 (0.928 s / it) [11-25 07:45:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 120/350] Total time: 0:25:48 (0.928 s / it) [11-25 07:45:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 120/350] Total time: 0:25:48 (0.928 s / it) [11-25 07:45:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 120/350] Total time: 0:25:48 (0.928 s / it) [11-25 07:45:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 120/350] Total time: 0:25:48 (0.928 s / it) [11-25 07:45:47] (/home/user/VAR/train.py , line 276)=> [ep120] (training ) Lm: 6.462 (6.462), Lt: 5.704 (5.704), Acc m&t: 3.47 5.45, Remain: 4 days, 3:32:43, Finish: 2024-11-28 19:18 [11-25 07:45:47] (/home/user/VAR/train.py , line 276)=> [ep120] (training ) Lm: 6.462 (6.462), Lt: 5.704 (5.704), Acc m&t: 3.47 5.45, Remain: 4 days, 3:34:43, Finish: 2024-11-28 19:20 [11-25 07:45:47] (/home/user/VAR/train.py , line 276)=> [ep120] (training ) Lm: 6.462 (6.462), Lt: 5.704 (5.704), Acc m&t: 3.47 5.45, Remain: 4 days, 3:33:00, Finish: 2024-11-28 19:18 [11-25 07:45:47] (/home/user/VAR/train.py , line 276)=> [ep120] (training ) Lm: 6.462 (6.462), Lt: 5.704 (5.704), Acc m&t: 3.47 5.45, Remain: 4 days, 3:34:11, Finish: 2024-11-28 19:19 [11-25 07:45:47] (/home/user/VAR/train.py , line 276)=> [ep120] (training ) Lm: 6.462 (6.462), Lt: 5.704 (5.704), Acc m&t: 3.47 5.45, Remain: 4 days, 3:32:10, Finish: 2024-11-28 19:17 [11-25 07:45:47] (/home/user/VAR/train.py , line 276)=> [ep120] (training ) Lm: 6.462 (6.462), Lt: 5.704 (5.704), Acc m&t: 3.47 5.45, Remain: 4 days, 3:32:40, Finish: 2024-11-28 19:18 [11-25 07:45:47] (/home/user/VAR/train.py , line 276)=> [ep120] (training ) Lm: 6.462 (6.462), Lt: 5.704 (5.704), Acc m&t: 3.47 5.45, Remain: 4 days, 3:32:37, Finish: 2024-11-28 19:18 [11-25 07:45:47] (/home/user/VAR/train.py , line 276)=> [ep120] (training ) Lm: 6.462 (6.462), Lt: 5.704 (5.704), Acc m&t: 3.47 5.45, Remain: 4 days, 3:34:35, Finish: 2024-11-28 19:20 [11-25 07:45:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 0/1669] eta: 0:24:31 tlr: 0.00017 tnm: 0.24 Lm: 6.408 (6.408) Lt: 5.677 (5.677) Accm: 3.51 (3.51) Acct: 5.27 (5.27) proj_loss: -0.6315 (-0.6315) time: 0.8819 data: 0.0003 [11-25 07:45:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 0/1669] eta: 0:24:32 tlr: 0.00017 tnm: 0.24 Lm: 6.263 (6.263) Lt: 5.497 (5.497) Accm: 4.02 (4.02) Acct: 6.58 (6.58) proj_loss: -0.6198 (-0.6198) time: 0.8821 data: 0.0003 [11-25 07:45:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 0/1669] eta: 0:24:32 tlr: 0.00017 tnm: 0.24 Lm: 6.262 (6.262) Lt: 5.488 (5.488) Accm: 4.27 (4.27) Acct: 6.16 (6.16) proj_loss: -0.6241 (-0.6241) time: 0.8825 data: 0.0003 [11-25 07:45:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 0/1669] eta: 0:24:32 tlr: 0.00017 tnm: 0.24 Lm: 6.616 (6.616) Lt: 5.880 (5.880) Accm: 2.96 (2.96) Acct: 4.68 (4.68) proj_loss: -0.5831 (-0.5831) time: 0.8823 data: 0.0003 [11-25 07:45:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 0/1669] eta: 0:25:43 tlr: 0.00017 tnm: 0.24 Lm: 6.407 (6.407) Lt: 5.582 (5.582) Accm: 3.76 (3.76) Acct: 6.06 (6.06) proj_loss: -0.5857 (-0.5857) time: 0.9246 data: 0.0004 [11-25 07:45:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 0/1669] eta: 0:24:30 tlr: 0.00017 tnm: 0.24 Lm: 6.383 (6.383) Lt: 5.592 (5.592) Accm: 3.77 (3.77) Acct: 6.03 (6.03) proj_loss: -0.5895 (-0.5895) time: 0.8811 data: 0.0003 [11-25 07:45:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 0/1669] eta: 0:24:32 tlr: 0.00017 tnm: 0.24 Lm: 6.500 (6.500) Lt: 5.764 (5.764) Accm: 3.58 (3.58) Acct: 5.85 (5.85) proj_loss: -0.6268 (-0.6268) time: 0.8823 data: 0.0004 [11-25 07:45:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 0/1669] eta: 0:25:36 tlr: 0.00017 tnm: 0.24 Lm: 6.548 (6.548) Lt: 5.860 (5.860) Accm: 3.16 (3.16) Acct: 4.99 (4.99) proj_loss: -0.5745 (-0.5745) time: 0.9206 data: 0.0004 [11-25 07:52:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 417/1669] eta: 0:19:27 tlr: 0.00017 tnm: 0.23 Lm: 6.559 (6.559) Lt: 5.838 (5.838) Accm: 3.25 (3.25) Acct: 5.03 (5.03) proj_loss: -0.6095 (-0.6095) time: 0.9916 data: 0.0002 [11-25 07:52:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 417/1669] eta: 0:19:27 tlr: 0.00017 tnm: 0.23 Lm: 6.535 (6.535) Lt: 5.784 (5.784) Accm: 3.26 (3.26) Acct: 5.13 (5.13) proj_loss: -0.5899 (-0.5899) time: 0.9916 data: 0.0002 [11-25 07:52:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 417/1669] eta: 0:19:27 tlr: 0.00017 tnm: 0.23 Lm: 6.387 (6.387) Lt: 5.648 (5.648) Accm: 3.47 (3.47) Acct: 5.54 (5.54) proj_loss: -0.6148 (-0.6148) time: 0.9916 data: 0.0003 [11-25 07:52:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 417/1669] eta: 0:19:27 tlr: 0.00017 tnm: 0.23 Lm: 6.387 (6.387) Lt: 5.659 (5.659) Accm: 3.61 (3.61) Acct: 5.61 (5.61) proj_loss: -0.6138 (-0.6138) time: 0.9916 data: 0.0005 [11-25 07:52:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 417/1669] eta: 0:19:27 tlr: 0.00017 tnm: 0.23 Lm: 6.417 (6.417) Lt: 5.639 (5.639) Accm: 3.65 (3.65) Acct: 5.84 (5.84) proj_loss: -0.6087 (-0.6087) time: 0.9916 data: 0.0002 [11-25 07:52:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 417/1669] eta: 0:19:27 tlr: 0.00017 tnm: 0.23 Lm: 6.375 (6.375) Lt: 5.625 (5.625) Accm: 3.83 (3.83) Acct: 5.68 (5.68) proj_loss: -0.6252 (-0.6252) time: 0.9916 data: 0.0003 [11-25 07:52:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 417/1669] eta: 0:19:27 tlr: 0.00017 tnm: 0.23 Lm: 6.440 (6.440) Lt: 5.685 (5.685) Accm: 3.57 (3.57) Acct: 5.80 (5.80) proj_loss: -0.6185 (-0.6185) time: 0.9916 data: 0.0003 [11-25 07:52:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 417/1669] eta: 0:19:27 tlr: 0.00017 tnm: 0.23 Lm: 6.566 (6.566) Lt: 5.850 (5.850) Accm: 3.22 (3.22) Acct: 5.06 (5.06) proj_loss: -0.6082 (-0.6082) time: 0.9916 data: 0.0003 [11-25 07:58:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 834/1669] eta: 0:13:09 tlr: 0.00017 tnm: 0.22 Lm: 6.500 (6.459) Lt: 5.764 (5.725) Accm: 3.58 (3.57) Acct: 5.85 (5.56) proj_loss: -0.6245 (-0.6136) time: 0.9321 data: 0.0003 [11-25 07:58:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 834/1669] eta: 0:13:09 tlr: 0.00017 tnm: 0.22 Lm: 6.454 (6.438) Lt: 5.688 (5.690) Accm: 3.55 (3.66) Acct: 5.58 (5.73) proj_loss: -0.5966 (-0.5946) time: 0.9321 data: 0.0003 [11-25 07:58:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 834/1669] eta: 0:13:09 tlr: 0.00017 tnm: 0.22 Lm: 6.426 (6.535) Lt: 5.697 (5.772) Accm: 3.54 (3.34) Acct: 5.61 (5.41) proj_loss: -0.6082 (-0.6085) time: 0.9321 data: 0.0003 [11-25 07:58:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 834/1669] eta: 0:13:09 tlr: 0.00017 tnm: 0.22 Lm: 6.383 (6.412) Lt: 5.592 (5.637) Accm: 3.61 (3.58) Acct: 5.61 (5.74) proj_loss: -0.5895 (-0.5985) time: 0.9321 data: 0.0003 [11-25 07:58:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 834/1669] eta: 0:13:09 tlr: 0.00017 tnm: 0.22 Lm: 6.512 (6.443) Lt: 5.763 (5.686) Accm: 3.47 (3.47) Acct: 5.89 (5.66) proj_loss: -0.6192 (-0.6163) time: 0.9322 data: 0.0003 [11-25 07:58:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 834/1669] eta: 0:13:09 tlr: 0.00017 tnm: 0.22 Lm: 6.388 (6.379) Lt: 5.527 (5.593) Accm: 3.50 (3.72) Acct: 6.03 (5.80) proj_loss: -0.6241 (-0.6179) time: 0.9321 data: 0.0003 [11-25 07:58:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 834/1669] eta: 0:13:09 tlr: 0.00017 tnm: 0.22 Lm: 6.408 (6.418) Lt: 5.677 (5.694) Accm: 3.51 (3.55) Acct: 5.27 (5.49) proj_loss: -0.5961 (-0.6075) time: 0.9321 data: 0.0003 [11-25 07:58:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [ 834/1669] eta: 0:13:09 tlr: 0.00017 tnm: 0.22 Lm: 6.548 (6.550) Lt: 5.816 (5.798) Accm: 3.16 (3.21) Acct: 5.06 (5.07) proj_loss: -0.5957 (-0.6049) time: 0.9322 data: 0.0003 [11-25 08:05:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [1251/1669] eta: 0:06:32 tlr: 0.00017 tnm: 0.23 Lm: 6.539 (6.539) Lt: 5.776 (5.782) Accm: 3.15 (3.19) Acct: 5.04 (5.06) proj_loss: -0.6049 (-0.6072) time: 0.9279 data: 0.0003 [11-25 08:05:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [1251/1669] eta: 0:06:32 tlr: 0.00017 tnm: 0.23 Lm: 6.493 (6.541) Lt: 5.761 (5.786) Accm: 3.45 (3.34) Acct: 5.42 (5.36) proj_loss: -0.6082 (-0.6084) time: 0.9279 data: 0.0002 [11-25 08:05:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [1251/1669] eta: 0:06:32 tlr: 0.00017 tnm: 0.23 Lm: 6.518 (6.474) Lt: 5.770 (5.730) Accm: 3.35 (3.53) Acct: 5.22 (5.51) proj_loss: -0.6004 (-0.6013) time: 0.9279 data: 0.0003 [11-25 08:05:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [1251/1669] eta: 0:06:32 tlr: 0.00017 tnm: 0.23 Lm: 6.438 (6.412) Lt: 5.606 (5.615) Accm: 3.45 (3.60) Acct: 5.79 (5.73) proj_loss: -0.6137 (-0.6137) time: 0.9280 data: 0.0003 [11-25 08:05:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [1251/1669] eta: 0:06:32 tlr: 0.00017 tnm: 0.23 Lm: 6.533 (6.497) Lt: 5.780 (5.748) Accm: 3.19 (3.28) Acct: 5.20 (5.30) proj_loss: -0.6145 (-0.6142) time: 0.9280 data: 0.0003 [11-25 08:05:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [1251/1669] eta: 0:06:32 tlr: 0.00017 tnm: 0.23 Lm: 6.440 (6.476) Lt: 5.685 (5.707) Accm: 3.50 (3.54) Acct: 5.77 (5.79) proj_loss: -0.6082 (-0.6056) time: 0.9280 data: 0.0003 [11-25 08:05:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [1251/1669] eta: 0:06:32 tlr: 0.00017 tnm: 0.23 Lm: 6.456 (6.447) Lt: 5.730 (5.718) Accm: 3.80 (3.68) Acct: 5.87 (5.64) proj_loss: -0.6115 (-0.6099) time: 0.9280 data: 0.0003 [11-25 08:05:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [1251/1669] eta: 0:06:32 tlr: 0.00017 tnm: 0.23 Lm: 6.445 (6.446) Lt: 5.690 (5.696) Accm: 3.47 (3.50) Acct: 5.25 (5.34) proj_loss: -0.5991 (-0.6061) time: 0.9280 data: 0.0003 [11-25 08:11:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.408 (6.434) Lt: 5.677 (5.682) Accm: 3.51 (3.58) Acct: 5.27 (5.54) proj_loss: -0.6020 (-0.6131) time: 0.9327 data: 0.0019 [11-25 08:11:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 121/350] Total time: 0:26:02 (0.936 s / it) [11-25 08:11:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.512 (6.439) Lt: 5.763 (5.676) Accm: 3.47 (3.58) Acct: 5.89 (5.64) proj_loss: -0.6192 (-0.6176) time: 0.9327 data: 0.0020 [11-25 08:11:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.488 (6.436) Lt: 5.684 (5.657) Accm: 3.39 (3.49) Acct: 5.54 (5.54) proj_loss: -0.6135 (-0.6136) time: 0.9327 data: 0.0016 [11-25 08:11:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.454 (6.455) Lt: 5.688 (5.718) Accm: 3.55 (3.57) Acct: 5.58 (5.53) proj_loss: -0.6042 (-0.6089) time: 0.9327 data: 0.0019 [11-25 08:11:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.496 (6.485) Lt: 5.778 (5.729) Accm: 3.39 (3.37) Acct: 5.61 (5.46) proj_loss: -0.5980 (-0.6041) time: 0.9327 data: 0.0017 [11-25 08:11:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.514 (6.536) Lt: 5.764 (5.781) Accm: 3.38 (3.35) Acct: 5.27 (5.34) proj_loss: -0.6082 (-0.6033) time: 0.9327 data: 0.0014 [11-25 08:11:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.500 (6.469) Lt: 5.748 (5.724) Accm: 3.58 (3.62) Acct: 5.85 (5.63) proj_loss: -0.5986 (-0.6051) time: 0.9327 data: 0.0015 [11-25 08:11:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 121/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.531 (6.524) Lt: 5.736 (5.766) Accm: 3.16 (3.30) Acct: 5.06 (5.28) proj_loss: -0.6141 (-0.6095) time: 0.9327 data: 0.0020 [11-25 08:11:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 121/350] Total time: 0:26:02 (0.936 s / it) [11-25 08:11:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 121/350] Total time: 0:26:02 (0.936 s / it) [11-25 08:11:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 121/350] Total time: 0:26:02 (0.936 s / it) [11-25 08:11:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 121/350] Total time: 0:26:02 (0.936 s / it) [11-25 08:11:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 121/350] Total time: 0:26:02 (0.936 s / it) [11-25 08:11:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 121/350] Total time: 0:26:02 (0.936 s / it) [11-25 08:11:50] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 121/350] Total time: 0:26:02 (0.936 s / it) [11-25 08:11:50] (/home/user/VAR/train.py , line 276)=> [ep121] (training ) Lm: 6.462 (6.479), Lt: 5.704 (5.723), Acc m&t: 3.47 5.45, Remain: 4 days, 3:12:36, Finish: 2024-11-28 19:24 [11-25 08:11:50] (/home/user/VAR/train.py , line 276)=> [ep121] (training ) Lm: 6.462 (6.479), Lt: 5.704 (5.723), Acc m&t: 3.47 5.45, Remain: 4 days, 3:12:33, Finish: 2024-11-28 19:24 [11-25 08:11:50] (/home/user/VAR/train.py , line 276)=> [ep121] (training ) Lm: 6.462 (6.479), Lt: 5.704 (5.723), Acc m&t: 3.47 5.45, Remain: 4 days, 3:12:59, Finish: 2024-11-28 19:24 [11-25 08:11:50] (/home/user/VAR/train.py , line 276)=> [ep121] (training ) Lm: 6.462 (6.479), Lt: 5.704 (5.723), Acc m&t: 3.47 5.45, Remain: 4 days, 3:11:32, Finish: 2024-11-28 19:23 [11-25 08:11:50] (/home/user/VAR/train.py , line 276)=> [ep121] (training ) Lm: 6.462 (6.479), Lt: 5.704 (5.723), Acc m&t: 3.47 5.45, Remain: 4 days, 3:12:53, Finish: 2024-11-28 19:24 [11-25 08:11:50] (/home/user/VAR/train.py , line 276)=> [ep121] (training ) Lm: 6.462 (6.479), Lt: 5.704 (5.723), Acc m&t: 3.47 5.45, Remain: 4 days, 3:12:43, Finish: 2024-11-28 19:24 [11-25 08:11:50] (/home/user/VAR/train.py , line 276)=> [ep121] (training ) Lm: 6.462 (6.479), Lt: 5.704 (5.723), Acc m&t: 3.47 5.45, Remain: 4 days, 3:13:13, Finish: 2024-11-28 19:25 [11-25 08:11:50] (/home/user/VAR/train.py , line 276)=> [ep121] (training ) Lm: 6.462 (6.479), Lt: 5.704 (5.723), Acc m&t: 3.47 5.45, Remain: 4 days, 3:12:48, Finish: 2024-11-28 19:24 [11-25 08:11:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 0/1669] eta: 0:25:27 tlr: 0.00017 tnm: 0.23 Lm: 6.509 (6.509) Lt: 5.815 (5.815) Accm: 3.32 (3.32) Acct: 5.13 (5.13) proj_loss: -0.6311 (-0.6311) time: 0.9154 data: 0.0003 [11-25 08:11:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 0/1669] eta: 0:25:28 tlr: 0.00017 tnm: 0.23 Lm: 6.509 (6.509) Lt: 5.736 (5.736) Accm: 3.10 (3.10) Acct: 4.75 (4.75) proj_loss: -0.6220 (-0.6220) time: 0.9155 data: 0.0003 [11-25 08:11:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 0/1669] eta: 0:25:28 tlr: 0.00017 tnm: 0.23 Lm: 6.445 (6.445) Lt: 5.562 (5.562) Accm: 3.89 (3.89) Acct: 6.03 (6.03) proj_loss: -0.5804 (-0.5804) time: 0.9156 data: 0.0003 [11-25 08:11:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 0/1669] eta: 0:25:27 tlr: 0.00017 tnm: 0.23 Lm: 6.653 (6.653) Lt: 5.843 (5.843) Accm: 3.06 (3.06) Acct: 4.86 (4.86) proj_loss: -0.5958 (-0.5958) time: 0.9151 data: 0.0004 [11-25 08:11:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 0/1669] eta: 0:25:28 tlr: 0.00017 tnm: 0.23 Lm: 6.566 (6.566) Lt: 5.858 (5.858) Accm: 3.37 (3.37) Acct: 5.13 (5.13) proj_loss: -0.6181 (-0.6181) time: 0.9157 data: 0.0003 [11-25 08:11:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 0/1669] eta: 0:25:28 tlr: 0.00017 tnm: 0.23 Lm: 6.647 (6.647) Lt: 5.931 (5.931) Accm: 3.10 (3.10) Acct: 4.68 (4.68) proj_loss: -0.6241 (-0.6241) time: 0.9159 data: 0.0004 [11-25 08:11:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 0/1669] eta: 0:25:28 tlr: 0.00017 tnm: 0.23 Lm: 6.317 (6.317) Lt: 5.521 (5.521) Accm: 3.67 (3.67) Acct: 6.10 (6.10) proj_loss: -0.6168 (-0.6168) time: 0.9160 data: 0.0003 [11-25 08:11:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 0/1669] eta: 0:25:34 tlr: 0.00017 tnm: 0.23 Lm: 6.646 (6.646) Lt: 5.925 (5.925) Accm: 3.19 (3.19) Acct: 5.06 (5.06) proj_loss: -0.6250 (-0.6250) time: 0.9194 data: 0.0004 [11-25 08:18:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.24 Lm: 6.580 (6.580) Lt: 5.828 (5.828) Accm: 3.24 (3.24) Acct: 5.10 (5.10) proj_loss: -0.6195 (-0.6195) time: 0.9297 data: 0.0003 [11-25 08:18:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.24 Lm: 6.490 (6.490) Lt: 5.723 (5.723) Accm: 3.48 (3.48) Acct: 5.51 (5.51) proj_loss: -0.5891 (-0.5891) time: 0.9297 data: 0.0002 [11-25 08:18:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.24 Lm: 6.479 (6.479) Lt: 5.654 (5.654) Accm: 3.41 (3.41) Acct: 5.44 (5.44) proj_loss: -0.5970 (-0.5970) time: 0.9297 data: 0.0002 [11-25 08:18:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.24 Lm: 6.461 (6.461) Lt: 5.697 (5.697) Accm: 3.67 (3.67) Acct: 5.66 (5.66) proj_loss: -0.6162 (-0.6162) time: 0.9297 data: 0.0003 [11-25 08:18:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.24 Lm: 6.467 (6.467) Lt: 5.665 (5.665) Accm: 3.27 (3.27) Acct: 4.99 (4.99) proj_loss: -0.6072 (-0.6072) time: 0.9297 data: 0.0003 [11-25 08:18:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.24 Lm: 6.549 (6.549) Lt: 5.854 (5.854) Accm: 3.15 (3.15) Acct: 4.84 (4.84) proj_loss: -0.6204 (-0.6204) time: 0.9297 data: 0.0003 [11-25 08:18:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.24 Lm: 6.518 (6.518) Lt: 5.764 (5.764) Accm: 3.22 (3.22) Acct: 5.01 (5.01) proj_loss: -0.6267 (-0.6267) time: 0.9297 data: 0.0003 [11-25 08:18:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.24 Lm: 6.437 (6.437) Lt: 5.639 (5.639) Accm: 3.33 (3.33) Acct: 5.44 (5.44) proj_loss: -0.6191 (-0.6191) time: 0.9297 data: 0.0002 [11-25 08:24:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.455 (6.443) Lt: 5.724 (5.667) Accm: 3.48 (3.38) Acct: 5.30 (5.39) proj_loss: -0.6168 (-0.6111) time: 0.9275 data: 0.0003 [11-25 08:24:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.426 (6.385) Lt: 5.595 (5.576) Accm: 3.44 (3.73) Acct: 5.23 (5.70) proj_loss: -0.6063 (-0.6069) time: 0.9275 data: 0.0003 [11-25 08:24:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.576 (6.519) Lt: 5.842 (5.763) Accm: 3.13 (3.37) Acct: 4.96 (5.33) proj_loss: -0.5958 (-0.5950) time: 0.9275 data: 0.0002 [11-25 08:24:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.513 (6.566) Lt: 5.745 (5.761) Accm: 2.93 (3.22) Acct: 4.86 (5.03) proj_loss: -0.5956 (-0.5965) time: 0.9275 data: 0.0002 [11-25 08:24:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.522 (6.540) Lt: 5.815 (5.829) Accm: 3.32 (3.21) Acct: 5.13 (4.96) proj_loss: -0.6097 (-0.6120) time: 0.9275 data: 0.0003 [11-25 08:24:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.514 (6.524) Lt: 5.731 (5.795) Accm: 3.28 (3.25) Acct: 5.06 (5.04) proj_loss: -0.6172 (-0.6188) time: 0.9275 data: 0.0002 [11-25 08:24:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.390 (6.389) Lt: 5.596 (5.629) Accm: 3.34 (3.70) Acct: 5.34 (5.66) proj_loss: -0.6241 (-0.6196) time: 0.9275 data: 0.0003 [11-25 08:24:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.530 (6.484) Lt: 5.790 (5.728) Accm: 3.37 (3.38) Acct: 5.13 (5.25) proj_loss: -0.6143 (-0.6078) time: 0.9275 data: 0.0003 [11-25 08:31:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.548 (6.569) Lt: 5.824 (5.795) Accm: 3.09 (3.18) Acct: 4.77 (5.00) proj_loss: -0.6116 (-0.6081) time: 0.9291 data: 0.0003 [11-25 08:31:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.467 (6.477) Lt: 5.665 (5.675) Accm: 3.27 (3.44) Acct: 4.99 (5.46) proj_loss: -0.6131 (-0.6101) time: 0.9291 data: 0.0003 [11-25 08:31:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.507 (6.492) Lt: 5.741 (5.736) Accm: 3.23 (3.13) Acct: 5.04 (4.95) proj_loss: -0.6060 (-0.6062) time: 0.9291 data: 0.0003 [11-25 08:31:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.452 (6.465) Lt: 5.722 (5.701) Accm: 3.38 (3.43) Acct: 5.23 (5.37) proj_loss: -0.6013 (-0.5986) time: 0.9291 data: 0.0003 [11-25 08:31:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.606 (6.599) Lt: 5.860 (5.818) Accm: 2.89 (3.10) Acct: 4.58 (4.85) proj_loss: -0.5898 (-0.5934) time: 0.9291 data: 0.0002 [11-25 08:31:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.544 (6.546) Lt: 5.798 (5.817) Accm: 3.15 (3.15) Acct: 4.86 (4.86) proj_loss: -0.6076 (-0.6104) time: 0.9291 data: 0.0003 [11-25 08:31:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.504 (6.516) Lt: 5.730 (5.774) Accm: 3.29 (3.28) Acct: 5.10 (5.14) proj_loss: -0.6157 (-0.6133) time: 0.9291 data: 0.0003 [11-25 08:31:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.433 (6.411) Lt: 5.638 (5.642) Accm: 3.25 (3.57) Acct: 5.37 (5.60) proj_loss: -0.6147 (-0.6132) time: 0.9291 data: 0.0003 [11-25 08:37:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.476 (6.444) Lt: 5.679 (5.661) Accm: 3.16 (3.46) Acct: 5.34 (5.42) proj_loss: -0.6054 (-0.6105) time: 0.9893 data: 0.0020 [11-25 08:37:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 122/350] Total time: 0:25:50 (0.929 s / it) [11-25 08:37:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.530 (6.535) Lt: 5.790 (5.775) Accm: 3.37 (3.23) Acct: 5.13 (5.03) proj_loss: -0.6089 (-0.6049) time: 0.9893 data: 0.0018 [11-25 08:37:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.538 (6.587) Lt: 5.844 (5.823) Accm: 2.93 (3.15) Acct: 4.86 (4.86) proj_loss: -0.5956 (-0.6010) time: 0.9893 data: 0.0017 [11-25 08:37:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.508 (6.483) Lt: 5.736 (5.692) Accm: 3.19 (3.39) Acct: 5.03 (5.37) proj_loss: -0.6159 (-0.6113) time: 0.9893 data: 0.0017 [11-25 08:37:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.522 (6.514) Lt: 5.781 (5.751) Accm: 3.32 (3.29) Acct: 5.13 (5.25) proj_loss: -0.6055 (-0.6054) time: 0.9893 data: 0.0018 [11-25 08:37:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.549 (6.482) Lt: 5.792 (5.719) Accm: 3.31 (3.41) Acct: 5.41 (5.38) proj_loss: -0.6067 (-0.6017) time: 0.9893 data: 0.0019 [11-25 08:37:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.494 (6.487) Lt: 5.730 (5.737) Accm: 3.29 (3.48) Acct: 5.13 (5.45) proj_loss: -0.6141 (-0.6105) time: 0.9893 data: 0.0019 [11-25 08:37:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 122/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.523 (6.498) Lt: 5.757 (5.756) Accm: 3.16 (3.14) Acct: 4.99 (4.96) proj_loss: -0.6168 (-0.6084) time: 0.9894 data: 0.0017 [11-25 08:37:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 122/350] Total time: 0:25:50 (0.929 s / it) [11-25 08:37:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 122/350] Total time: 0:25:50 (0.929 s / it) [11-25 08:37:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 122/350] Total time: 0:25:50 (0.929 s / it) [11-25 08:37:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 122/350] Total time: 0:25:50 (0.929 s / it) [11-25 08:37:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 122/350] Total time: 0:25:50 (0.929 s / it) [11-25 08:37:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 122/350] Total time: 0:25:50 (0.929 s / it) [11-25 08:37:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 122/350] Total time: 0:25:50 (0.929 s / it) [11-25 08:37:40] (/home/user/VAR/train.py , line 276)=> [ep122] (training ) Lm: 6.462 (6.482), Lt: 5.704 (5.726), Acc m&t: 3.47 5.45, Remain: 4 days, 2:30:01, Finish: 2024-11-28 19:07 [11-25 08:37:40] (/home/user/VAR/train.py , line 276)=> [ep122] (training ) Lm: 6.462 (6.482), Lt: 5.704 (5.726), Acc m&t: 3.47 5.45, Remain: 4 days, 2:29:56, Finish: 2024-11-28 19:07 [11-25 08:37:40] (/home/user/VAR/train.py , line 276)=> [ep122] (training ) Lm: 6.462 (6.482), Lt: 5.704 (5.726), Acc m&t: 3.47 5.45, Remain: 4 days, 2:29:49, Finish: 2024-11-28 19:07 [11-25 08:37:40] (/home/user/VAR/train.py , line 276)=> [ep122] (training ) Lm: 6.462 (6.482), Lt: 5.704 (5.726), Acc m&t: 3.47 5.45, Remain: 4 days, 2:28:48, Finish: 2024-11-28 19:06 [11-25 08:37:40] (/home/user/VAR/train.py , line 276)=> [ep122] (training ) Lm: 6.462 (6.482), Lt: 5.704 (5.726), Acc m&t: 3.47 5.45, Remain: 4 days, 2:29:12, Finish: 2024-11-28 19:06 [11-25 08:37:40] (/home/user/VAR/train.py , line 276)=> [ep122] (training ) Lm: 6.462 (6.482), Lt: 5.704 (5.726), Acc m&t: 3.47 5.45, Remain: 4 days, 2:29:11, Finish: 2024-11-28 19:06 [11-25 08:37:40] (/home/user/VAR/train.py , line 276)=> [ep122] (training ) Lm: 6.462 (6.482), Lt: 5.704 (5.726), Acc m&t: 3.47 5.45, Remain: 4 days, 2:29:21, Finish: 2024-11-28 19:07 [11-25 08:37:40] (/home/user/VAR/train.py , line 276)=> [ep122] (training ) Lm: 6.462 (6.482), Lt: 5.704 (5.726), Acc m&t: 3.47 5.45, Remain: 4 days, 2:30:34, Finish: 2024-11-28 19:08 [11-25 08:37:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 0/1669] eta: 0:25:08 tlr: 0.00017 tnm: 0.23 Lm: 6.583 (6.583) Lt: 5.831 (5.831) Accm: 2.93 (2.93) Acct: 4.44 (4.44) proj_loss: -0.6104 (-0.6104) time: 0.9036 data: 0.0004 [11-25 08:37:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 0/1669] eta: 0:25:08 tlr: 0.00017 tnm: 0.23 Lm: 6.556 (6.556) Lt: 5.747 (5.747) Accm: 3.19 (3.19) Acct: 5.23 (5.23) proj_loss: -0.6045 (-0.6045) time: 0.9036 data: 0.0004 [11-25 08:37:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 0/1669] eta: 0:25:08 tlr: 0.00017 tnm: 0.23 Lm: 6.727 (6.727) Lt: 5.970 (5.970) Accm: 2.68 (2.68) Acct: 4.06 (4.06) proj_loss: -0.6010 (-0.6010) time: 0.9035 data: 0.0005 [11-25 08:37:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 0/1669] eta: 0:25:08 tlr: 0.00017 tnm: 0.23 Lm: 6.585 (6.585) Lt: 5.828 (5.828) Accm: 3.18 (3.18) Acct: 5.03 (5.03) proj_loss: -0.5765 (-0.5765) time: 0.9037 data: 0.0004 [11-25 08:37:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 0/1669] eta: 0:25:08 tlr: 0.00017 tnm: 0.23 Lm: 6.363 (6.363) Lt: 5.524 (5.524) Accm: 3.73 (3.73) Acct: 6.27 (6.27) proj_loss: -0.6033 (-0.6033) time: 0.9041 data: 0.0004 [11-25 08:37:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 0/1669] eta: 0:25:08 tlr: 0.00017 tnm: 0.23 Lm: 6.483 (6.483) Lt: 5.787 (5.787) Accm: 3.57 (3.57) Acct: 5.20 (5.20) proj_loss: -0.6187 (-0.6187) time: 0.9039 data: 0.0004 [11-25 08:37:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 0/1669] eta: 0:25:07 tlr: 0.00017 tnm: 0.23 Lm: 6.570 (6.570) Lt: 5.928 (5.928) Accm: 2.80 (2.80) Acct: 4.03 (4.03) proj_loss: -0.6442 (-0.6442) time: 0.9033 data: 0.0004 [11-25 08:37:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 0/1669] eta: 0:25:09 tlr: 0.00017 tnm: 0.23 Lm: 6.579 (6.579) Lt: 5.832 (5.832) Accm: 3.07 (3.07) Acct: 4.68 (4.68) proj_loss: -0.5713 (-0.5713) time: 0.9044 data: 0.0004 [11-25 08:44:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 417/1669] eta: 0:19:48 tlr: 0.00017 tnm: 0.23 Lm: 6.535 (6.535) Lt: 5.799 (5.799) Accm: 3.14 (3.14) Acct: 4.82 (4.82) proj_loss: -0.5989 (-0.5989) time: 0.9261 data: 0.0003 [11-25 08:44:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 417/1669] eta: 0:19:48 tlr: 0.00017 tnm: 0.23 Lm: 6.530 (6.530) Lt: 5.749 (5.749) Accm: 3.12 (3.12) Acct: 4.91 (4.91) proj_loss: -0.6103 (-0.6103) time: 0.9260 data: 0.0002 [11-25 08:44:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 417/1669] eta: 0:19:48 tlr: 0.00017 tnm: 0.23 Lm: 6.546 (6.546) Lt: 5.788 (5.788) Accm: 3.12 (3.12) Acct: 4.91 (4.91) proj_loss: -0.6126 (-0.6126) time: 0.9261 data: 0.0003 [11-25 08:44:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 417/1669] eta: 0:19:48 tlr: 0.00017 tnm: 0.23 Lm: 6.589 (6.589) Lt: 5.803 (5.803) Accm: 2.93 (2.93) Acct: 4.75 (4.75) proj_loss: -0.6173 (-0.6173) time: 0.9260 data: 0.0003 [11-25 08:44:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 417/1669] eta: 0:19:48 tlr: 0.00017 tnm: 0.23 Lm: 6.587 (6.587) Lt: 5.874 (5.874) Accm: 3.15 (3.15) Acct: 4.51 (4.51) proj_loss: -0.5989 (-0.5989) time: 0.9261 data: 0.0003 [11-25 08:44:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 417/1669] eta: 0:19:48 tlr: 0.00017 tnm: 0.23 Lm: 6.345 (6.345) Lt: 5.623 (5.623) Accm: 4.01 (4.01) Acct: 5.99 (5.99) proj_loss: -0.6132 (-0.6132) time: 0.9261 data: 0.0003 [11-25 08:44:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 417/1669] eta: 0:19:48 tlr: 0.00017 tnm: 0.23 Lm: 6.536 (6.536) Lt: 5.866 (5.866) Accm: 2.72 (2.72) Acct: 4.12 (4.12) proj_loss: -0.6286 (-0.6286) time: 0.9261 data: 0.0003 [11-25 08:44:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 417/1669] eta: 0:19:48 tlr: 0.00017 tnm: 0.23 Lm: 6.623 (6.623) Lt: 5.838 (5.838) Accm: 3.06 (3.06) Acct: 4.75 (4.75) proj_loss: -0.5859 (-0.5859) time: 0.9261 data: 0.0003 [11-25 08:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 834/1669] eta: 0:13:03 tlr: 0.00017 tnm: 0.23 Lm: 6.585 (6.586) Lt: 5.828 (5.814) Accm: 3.13 (3.08) Acct: 4.99 (4.83) proj_loss: -0.5953 (-0.5962) time: 0.9274 data: 0.0003 [11-25 08:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 834/1669] eta: 0:13:03 tlr: 0.00017 tnm: 0.23 Lm: 6.467 (6.520) Lt: 5.631 (5.736) Accm: 3.73 (3.33) Acct: 6.20 (5.34) proj_loss: -0.6033 (-0.6050) time: 0.9274 data: 0.0003 [11-25 08:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 834/1669] eta: 0:13:03 tlr: 0.00017 tnm: 0.23 Lm: 6.483 (6.396) Lt: 5.753 (5.666) Accm: 3.57 (3.74) Acct: 5.20 (5.64) proj_loss: -0.6115 (-0.6126) time: 0.9274 data: 0.0003 [11-25 08:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 834/1669] eta: 0:13:03 tlr: 0.00017 tnm: 0.23 Lm: 6.502 (6.483) Lt: 5.804 (5.773) Accm: 2.80 (3.07) Acct: 4.20 (4.51) proj_loss: -0.6336 (-0.6303) time: 0.9274 data: 0.0003 [11-25 08:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 834/1669] eta: 0:13:03 tlr: 0.00017 tnm: 0.23 Lm: 6.573 (6.584) Lt: 5.859 (5.829) Accm: 2.86 (2.90) Acct: 4.27 (4.55) proj_loss: -0.6236 (-0.6194) time: 0.9274 data: 0.0003 [11-25 08:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 834/1669] eta: 0:13:03 tlr: 0.00017 tnm: 0.23 Lm: 6.549 (6.574) Lt: 5.906 (5.884) Accm: 3.29 (3.20) Acct: 4.86 (4.63) proj_loss: -0.6010 (-0.6039) time: 0.9274 data: 0.0003 [11-25 08:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 834/1669] eta: 0:13:03 tlr: 0.00017 tnm: 0.23 Lm: 6.478 (6.464) Lt: 5.667 (5.691) Accm: 3.31 (3.35) Acct: 5.37 (5.26) proj_loss: -0.6102 (-0.6100) time: 0.9274 data: 0.0002 [11-25 08:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [ 834/1669] eta: 0:13:03 tlr: 0.00017 tnm: 0.23 Lm: 6.492 (6.350) Lt: 5.766 (5.584) Accm: 3.21 (3.87) Acct: 4.96 (6.01) proj_loss: -0.5790 (-0.5923) time: 0.9274 data: 0.0003 [11-25 08:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [1251/1669] eta: 0:06:30 tlr: 0.00017 tnm: 0.23 Lm: 6.534 (6.406) Lt: 5.776 (5.635) Accm: 3.18 (3.69) Acct: 4.99 (5.77) proj_loss: -0.5916 (-0.5952) time: 0.9286 data: 0.0003 [11-25 08:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [1251/1669] eta: 0:06:30 tlr: 0.00017 tnm: 0.23 Lm: 6.475 (6.511) Lt: 5.663 (5.725) Accm: 3.69 (3.41) Acct: 6.13 (5.52) proj_loss: -0.5966 (-0.6005) time: 0.9286 data: 0.0003 [11-25 08:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [1251/1669] eta: 0:06:30 tlr: 0.00017 tnm: 0.23 Lm: 6.530 (6.498) Lt: 5.735 (5.719) Accm: 3.23 (3.30) Acct: 5.11 (5.16) proj_loss: -0.6103 (-0.6110) time: 0.9286 data: 0.0002 [11-25 08:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [1251/1669] eta: 0:06:30 tlr: 0.00017 tnm: 0.23 Lm: 6.584 (6.586) Lt: 5.870 (5.847) Accm: 3.02 (3.00) Acct: 4.51 (4.60) proj_loss: -0.6140 (-0.6049) time: 0.9286 data: 0.0003 [11-25 08:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [1251/1669] eta: 0:06:30 tlr: 0.00017 tnm: 0.23 Lm: 6.498 (6.495) Lt: 5.842 (5.777) Accm: 3.45 (3.43) Acct: 4.91 (5.08) proj_loss: -0.6068 (-0.6061) time: 0.9286 data: 0.0002 [11-25 08:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [1251/1669] eta: 0:06:30 tlr: 0.00017 tnm: 0.23 Lm: 6.623 (6.626) Lt: 5.838 (5.873) Accm: 3.04 (2.94) Acct: 4.73 (4.57) proj_loss: -0.5936 (-0.5952) time: 0.9286 data: 0.0003 [11-25 08:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [1251/1669] eta: 0:06:30 tlr: 0.00017 tnm: 0.23 Lm: 6.470 (6.472) Lt: 5.771 (5.764) Accm: 3.25 (3.23) Acct: 4.75 (4.75) proj_loss: -0.6308 (-0.6297) time: 0.9286 data: 0.0003 [11-25 08:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [1251/1669] eta: 0:06:30 tlr: 0.00017 tnm: 0.23 Lm: 6.417 (6.385) Lt: 5.647 (5.635) Accm: 3.68 (3.76) Acct: 5.79 (5.82) proj_loss: -0.6151 (-0.6191) time: 0.9286 data: 0.0003 [11-25 09:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.483 (6.409) Lt: 5.673 (5.643) Accm: 3.57 (3.67) Acct: 5.30 (5.72) proj_loss: -0.6115 (-0.6168) time: 0.9291 data: 0.0018 [11-25 09:03:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 123/350] Total time: 0:25:57 (0.933 s / it) [11-25 09:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.478 (6.480) Lt: 5.764 (5.728) Accm: 3.31 (3.37) Acct: 5.37 (5.23) proj_loss: -0.6102 (-0.6094) time: 0.9291 data: 0.0015 [11-25 09:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.483 (6.527) Lt: 5.694 (5.750) Accm: 3.66 (3.33) Acct: 6.06 (5.32) proj_loss: -0.5919 (-0.5988) time: 0.9291 data: 0.0018 [11-25 09:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.573 (6.580) Lt: 5.859 (5.819) Accm: 3.19 (3.11) Acct: 4.75 (4.86) proj_loss: -0.6045 (-0.6023) time: 0.9291 data: 0.0018 [11-25 09:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.585 (6.605) Lt: 5.828 (5.850) Accm: 3.13 (3.11) Acct: 4.99 (4.92) proj_loss: -0.5953 (-0.5976) time: 0.9291 data: 0.0016 [11-25 09:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.549 (6.532) Lt: 5.906 (5.815) Accm: 3.29 (3.34) Acct: 4.86 (4.99) proj_loss: -0.6127 (-0.6088) time: 0.9291 data: 0.0018 [11-25 09:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.492 (6.406) Lt: 5.766 (5.643) Accm: 3.21 (3.66) Acct: 5.03 (5.71) proj_loss: -0.6042 (-0.5997) time: 0.9291 data: 0.0024 [11-25 09:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 123/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.494 (6.476) Lt: 5.738 (5.751) Accm: 3.13 (3.21) Acct: 4.68 (4.74) proj_loss: -0.6279 (-0.6262) time: 0.9292 data: 0.0016 [11-25 09:03:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 123/350] Total time: 0:25:57 (0.933 s / it) [11-25 09:03:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 123/350] Total time: 0:25:57 (0.933 s / it) [11-25 09:03:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 123/350] Total time: 0:25:57 (0.933 s / it) [11-25 09:03:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 123/350] Total time: 0:25:57 (0.933 s / it) [11-25 09:03:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 123/350] Total time: 0:25:57 (0.933 s / it) [11-25 09:03:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 123/350] Total time: 0:25:57 (0.933 s / it) [11-25 09:03:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 123/350] Total time: 0:25:57 (0.933 s / it) [11-25 09:03:38] (/home/user/VAR/train.py , line 276)=> [ep123] (training ) Lm: 6.462 (6.493), Lt: 5.704 (5.745), Acc m&t: 3.47 5.45, Remain: 4 days, 2:05:35, Finish: 2024-11-28 19:09 [11-25 09:03:38] (/home/user/VAR/train.py , line 276)=> [ep123] (training ) Lm: 6.462 (6.493), Lt: 5.704 (5.745), Acc m&t: 3.47 5.45, Remain: 4 days, 2:05:56, Finish: 2024-11-28 19:09 [11-25 09:03:38] (/home/user/VAR/train.py , line 276)=> [ep123] (training ) Lm: 6.462 (6.493), Lt: 5.704 (5.745), Acc m&t: 3.47 5.45, Remain: 4 days, 2:05:49, Finish: 2024-11-28 19:09 [11-25 09:03:38] (/home/user/VAR/train.py , line 276)=> [ep123] (training ) Lm: 6.462 (6.493), Lt: 5.704 (5.745), Acc m&t: 3.47 5.45, Remain: 4 days, 2:06:02, Finish: 2024-11-28 19:09 [11-25 09:03:38] (/home/user/VAR/train.py , line 276)=> [ep123] (training ) Lm: 6.462 (6.493), Lt: 5.704 (5.745), Acc m&t: 3.47 5.45, Remain: 4 days, 2:05:05, Finish: 2024-11-28 19:08 [11-25 09:03:38] (/home/user/VAR/train.py , line 276)=> [ep123] (training ) Lm: 6.462 (6.493), Lt: 5.704 (5.745), Acc m&t: 3.47 5.45, Remain: 4 days, 2:05:57, Finish: 2024-11-28 19:09 [11-25 09:03:38] (/home/user/VAR/train.py , line 276)=> [ep123] (training ) Lm: 6.462 (6.493), Lt: 5.704 (5.745), Acc m&t: 3.47 5.45, Remain: 4 days, 2:05:11, Finish: 2024-11-28 19:08 [11-25 09:03:38] (/home/user/VAR/train.py , line 276)=> [ep123] (training ) Lm: 6.462 (6.493), Lt: 5.704 (5.745), Acc m&t: 3.47 5.45, Remain: 4 days, 2:05:50, Finish: 2024-11-28 19:09 [11-25 09:03:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 0/1669] eta: 0:25:13 tlr: 0.00017 tnm: 0.22 Lm: 6.665 (6.665) Lt: 5.896 (5.896) Accm: 3.06 (3.06) Acct: 5.17 (5.17) proj_loss: -0.6197 (-0.6197) time: 0.9066 data: 0.0004 [11-25 09:03:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 0/1669] eta: 0:25:13 tlr: 0.00017 tnm: 0.22 Lm: 6.413 (6.413) Lt: 5.574 (5.574) Accm: 3.61 (3.61) Acct: 5.82 (5.82) proj_loss: -0.5904 (-0.5904) time: 0.9066 data: 0.0004 [11-25 09:03:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 0/1669] eta: 0:25:13 tlr: 0.00017 tnm: 0.22 Lm: 6.765 (6.765) Lt: 6.032 (6.032) Accm: 2.77 (2.77) Acct: 4.51 (4.51) proj_loss: -0.6256 (-0.6256) time: 0.9068 data: 0.0004 [11-25 09:03:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 0/1669] eta: 0:25:13 tlr: 0.00017 tnm: 0.22 Lm: 6.704 (6.704) Lt: 5.987 (5.987) Accm: 2.84 (2.84) Acct: 4.30 (4.30) proj_loss: -0.6113 (-0.6113) time: 0.9068 data: 0.0004 [11-25 09:03:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 0/1669] eta: 0:25:12 tlr: 0.00017 tnm: 0.22 Lm: 6.438 (6.438) Lt: 5.736 (5.736) Accm: 3.66 (3.66) Acct: 5.20 (5.20) proj_loss: -0.6253 (-0.6253) time: 0.9062 data: 0.0003 [11-25 09:03:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 0/1669] eta: 0:25:13 tlr: 0.00017 tnm: 0.22 Lm: 6.535 (6.535) Lt: 5.782 (5.782) Accm: 3.44 (3.44) Acct: 5.75 (5.75) proj_loss: -0.5997 (-0.5997) time: 0.9071 data: 0.0004 [11-25 09:03:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 0/1669] eta: 0:25:10 tlr: 0.00017 tnm: 0.22 Lm: 6.478 (6.478) Lt: 5.700 (5.700) Accm: 3.57 (3.57) Acct: 5.75 (5.75) proj_loss: -0.6261 (-0.6261) time: 0.9053 data: 0.0005 [11-25 09:03:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 0/1669] eta: 0:25:14 tlr: 0.00017 tnm: 0.22 Lm: 6.168 (6.168) Lt: 5.309 (5.309) Accm: 4.46 (4.46) Acct: 7.06 (7.06) proj_loss: -0.6189 (-0.6189) time: 0.9076 data: 0.0003 [11-25 09:10:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.24 Lm: 6.272 (6.272) Lt: 5.482 (5.482) Accm: 4.14 (4.14) Acct: 6.28 (6.28) proj_loss: -0.6092 (-0.6092) time: 0.9293 data: 0.0003 [11-25 09:10:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.24 Lm: 6.677 (6.677) Lt: 5.933 (5.933) Accm: 2.84 (2.84) Acct: 4.86 (4.86) proj_loss: -0.6098 (-0.6098) time: 0.9293 data: 0.0002 [11-25 09:10:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.24 Lm: 6.381 (6.381) Lt: 5.593 (5.593) Accm: 3.92 (3.92) Acct: 6.23 (6.23) proj_loss: -0.6096 (-0.6096) time: 0.9293 data: 0.0003 [11-25 09:10:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.24 Lm: 6.592 (6.592) Lt: 5.818 (5.818) Accm: 3.18 (3.18) Acct: 5.18 (5.18) proj_loss: -0.6306 (-0.6306) time: 0.9293 data: 0.0003 [11-25 09:10:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.24 Lm: 6.649 (6.649) Lt: 5.898 (5.898) Accm: 2.80 (2.80) Acct: 4.44 (4.44) proj_loss: -0.6150 (-0.6150) time: 0.9293 data: 0.0003 [11-25 09:10:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.24 Lm: 6.515 (6.515) Lt: 5.755 (5.755) Accm: 3.38 (3.38) Acct: 5.39 (5.39) proj_loss: -0.6268 (-0.6268) time: 0.9293 data: 0.0003 [11-25 09:10:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.24 Lm: 6.515 (6.515) Lt: 5.806 (5.806) Accm: 3.45 (3.45) Acct: 5.10 (5.10) proj_loss: -0.6219 (-0.6219) time: 0.9293 data: 0.0003 [11-25 09:10:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.24 Lm: 6.535 (6.535) Lt: 5.786 (5.786) Accm: 3.23 (3.23) Acct: 5.13 (5.13) proj_loss: -0.5852 (-0.5852) time: 0.9293 data: 0.0003 [11-25 09:17:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 834/1669] eta: 0:13:25 tlr: 0.00017 tnm: 0.23 Lm: 6.534 (6.500) Lt: 5.782 (5.754) Accm: 3.44 (3.38) Acct: 5.61 (5.29) proj_loss: -0.5990 (-0.5898) time: 0.9272 data: 0.0002 [11-25 09:17:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 834/1669] eta: 0:13:25 tlr: 0.00017 tnm: 0.23 Lm: 6.689 (6.685) Lt: 5.931 (5.933) Accm: 2.96 (2.88) Acct: 4.89 (4.87) proj_loss: -0.6019 (-0.6072) time: 0.9272 data: 0.0002 [11-25 09:17:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 834/1669] eta: 0:13:25 tlr: 0.00017 tnm: 0.23 Lm: 6.413 (6.518) Lt: 5.612 (5.780) Accm: 3.61 (3.56) Acct: 5.82 (5.52) proj_loss: -0.5954 (-0.6049) time: 0.9272 data: 0.0002 [11-25 09:17:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 834/1669] eta: 0:13:25 tlr: 0.00017 tnm: 0.23 Lm: 6.524 (6.518) Lt: 5.736 (5.768) Accm: 3.66 (3.56) Acct: 5.20 (5.41) proj_loss: -0.6184 (-0.6151) time: 0.9272 data: 0.0003 [11-25 09:17:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 834/1669] eta: 0:13:25 tlr: 0.00017 tnm: 0.23 Lm: 6.552 (6.572) Lt: 5.809 (5.827) Accm: 3.19 (3.28) Acct: 5.03 (5.21) proj_loss: -0.6261 (-0.6153) time: 0.9272 data: 0.0003 [11-25 09:17:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 834/1669] eta: 0:13:25 tlr: 0.00017 tnm: 0.23 Lm: 6.419 (6.505) Lt: 5.604 (5.727) Accm: 3.48 (3.28) Acct: 5.72 (5.36) proj_loss: -0.6256 (-0.6264) time: 0.9272 data: 0.0002 [11-25 09:17:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 834/1669] eta: 0:13:25 tlr: 0.00017 tnm: 0.23 Lm: 6.595 (6.519) Lt: 5.809 (5.767) Accm: 2.84 (3.11) Acct: 4.58 (5.00) proj_loss: -0.6188 (-0.6195) time: 0.9272 data: 0.0003 [11-25 09:17:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [ 834/1669] eta: 0:13:25 tlr: 0.00017 tnm: 0.23 Lm: 6.376 (6.311) Lt: 5.655 (5.540) Accm: 3.85 (4.04) Acct: 5.51 (6.03) proj_loss: -0.6189 (-0.6162) time: 0.9272 data: 0.0004 [11-25 09:23:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [1251/1669] eta: 0:06:37 tlr: 0.00017 tnm: 0.24 Lm: 6.382 (6.406) Lt: 5.656 (5.640) Accm: 3.83 (3.69) Acct: 5.51 (5.63) proj_loss: -0.6228 (-0.6188) time: 0.9268 data: 0.0003 [11-25 09:23:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [1251/1669] eta: 0:06:37 tlr: 0.00017 tnm: 0.24 Lm: 6.469 (6.520) Lt: 5.696 (5.780) Accm: 3.55 (3.54) Acct: 5.56 (5.47) proj_loss: -0.6034 (-0.6065) time: 0.9267 data: 0.0002 [11-25 09:23:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [1251/1669] eta: 0:06:37 tlr: 0.00017 tnm: 0.24 Lm: 6.515 (6.487) Lt: 5.755 (5.737) Accm: 3.38 (3.52) Acct: 5.39 (5.68) proj_loss: -0.6253 (-0.6176) time: 0.9267 data: 0.0003 [11-25 09:23:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [1251/1669] eta: 0:06:37 tlr: 0.00017 tnm: 0.24 Lm: 6.497 (6.522) Lt: 5.743 (5.766) Accm: 3.18 (3.18) Acct: 5.13 (5.16) proj_loss: -0.6306 (-0.6314) time: 0.9268 data: 0.0002 [11-25 09:23:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [1251/1669] eta: 0:06:37 tlr: 0.00017 tnm: 0.24 Lm: 6.677 (6.648) Lt: 5.914 (5.897) Accm: 3.01 (3.00) Acct: 5.03 (4.97) proj_loss: -0.6051 (-0.6074) time: 0.9267 data: 0.0002 [11-25 09:23:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [1251/1669] eta: 0:06:37 tlr: 0.00017 tnm: 0.24 Lm: 6.541 (6.528) Lt: 5.782 (5.783) Accm: 3.45 (3.47) Acct: 5.27 (5.39) proj_loss: -0.6172 (-0.6154) time: 0.9268 data: 0.0003 [11-25 09:23:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [1251/1669] eta: 0:06:37 tlr: 0.00017 tnm: 0.24 Lm: 6.426 (6.453) Lt: 5.657 (5.692) Accm: 3.29 (3.35) Acct: 5.34 (5.28) proj_loss: -0.6150 (-0.6142) time: 0.9268 data: 0.0003 [11-25 09:23:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [1251/1669] eta: 0:06:37 tlr: 0.00017 tnm: 0.24 Lm: 6.513 (6.498) Lt: 5.736 (5.730) Accm: 3.41 (3.38) Acct: 5.61 (5.37) proj_loss: -0.5993 (-0.5967) time: 0.9268 data: 0.0002 [11-25 09:29:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.491 (6.450) Lt: 5.690 (5.685) Accm: 3.44 (3.50) Acct: 5.61 (5.50) proj_loss: -0.5997 (-0.6040) time: 0.9297 data: 0.0019 [11-25 09:29:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 124/350] Total time: 0:26:18 (0.946 s / it) [11-25 09:29:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.419 (6.491) Lt: 5.648 (5.742) Accm: 3.48 (3.28) Acct: 5.17 (5.16) proj_loss: -0.6256 (-0.6271) time: 0.9297 data: 0.0015 [11-25 09:29:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.665 (6.593) Lt: 5.896 (5.843) Accm: 3.06 (3.10) Acct: 5.17 (5.09) proj_loss: -0.6019 (-0.6050) time: 0.9297 data: 0.0019 [11-25 09:29:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.486 (6.487) Lt: 5.730 (5.736) Accm: 3.19 (3.45) Acct: 5.03 (5.53) proj_loss: -0.6245 (-0.6141) time: 0.9297 data: 0.0017 [11-25 09:29:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.525 (6.556) Lt: 5.781 (5.827) Accm: 3.50 (3.44) Acct: 5.30 (5.41) proj_loss: -0.5954 (-0.6034) time: 0.9297 data: 0.0015 [11-25 09:29:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.387 (6.450) Lt: 5.657 (5.701) Accm: 3.82 (3.48) Acct: 5.51 (5.32) proj_loss: -0.6267 (-0.6217) time: 0.9297 data: 0.0016 [11-25 09:29:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.257 (6.394) Lt: 5.505 (5.621) Accm: 3.74 (3.61) Acct: 6.10 (5.62) proj_loss: -0.6188 (-0.6171) time: 0.9297 data: 0.0021 [11-25 09:29:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 124/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.23 Lm: 6.524 (6.516) Lt: 5.736 (5.748) Accm: 3.54 (3.48) Acct: 5.34 (5.40) proj_loss: -0.6160 (-0.6155) time: 0.9297 data: 0.0018 [11-25 09:29:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 124/350] Total time: 0:26:18 (0.946 s / it) [11-25 09:29:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 124/350] Total time: 0:26:18 (0.946 s / it) [11-25 09:29:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 124/350] Total time: 0:26:18 (0.946 s / it) [11-25 09:29:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 124/350] Total time: 0:26:18 (0.946 s / it) [11-25 09:29:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 124/350] Total time: 0:26:18 (0.946 s / it) [11-25 09:29:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 124/350] Total time: 0:26:18 (0.946 s / it) [11-25 09:29:57] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 124/350] Total time: 0:26:18 (0.946 s / it) [11-25 09:29:57] (/home/user/VAR/train.py , line 276)=> [ep124] (training ) Lm: 6.462 (6.473), Lt: 5.704 (5.716), Acc m&t: 3.47 5.45, Remain: 4 days, 1:40:19, Finish: 2024-11-28 19:10 [11-25 09:29:57] (/home/user/VAR/train.py , line 276)=> [ep124] (training ) Lm: 6.462 (6.473), Lt: 5.704 (5.716), Acc m&t: 3.47 5.45, Remain: 4 days, 1:41:38, Finish: 2024-11-28 19:11 [11-25 09:29:57] (/home/user/VAR/train.py , line 276)=> [ep124] (training ) Lm: 6.462 (6.473), Lt: 5.704 (5.716), Acc m&t: 3.47 5.45, Remain: 4 days, 1:41:24, Finish: 2024-11-28 19:11 [11-25 09:29:57] (/home/user/VAR/train.py , line 276)=> [ep124] (training ) Lm: 6.462 (6.473), Lt: 5.704 (5.716), Acc m&t: 3.47 5.45, Remain: 4 days, 1:39:33, Finish: 2024-11-28 19:09 [11-25 09:29:57] (/home/user/VAR/train.py , line 276)=> [ep124] (training ) Lm: 6.462 (6.473), Lt: 5.704 (5.716), Acc m&t: 3.47 5.45, Remain: 4 days, 1:39:45, Finish: 2024-11-28 19:09 [11-25 09:29:57] (/home/user/VAR/train.py , line 276)=> [ep124] (training ) Lm: 6.462 (6.473), Lt: 5.704 (5.716), Acc m&t: 3.47 5.45, Remain: 4 days, 1:40:40, Finish: 2024-11-28 19:10 [11-25 09:29:57] (/home/user/VAR/train.py , line 276)=> [ep124] (training ) Lm: 6.462 (6.473), Lt: 5.704 (5.716), Acc m&t: 3.47 5.45, Remain: 4 days, 1:40:39, Finish: 2024-11-28 19:10 [11-25 09:29:57] (/home/user/VAR/train.py , line 276)=> [ep124] (training ) Lm: 6.462 (6.473), Lt: 5.704 (5.716), Acc m&t: 3.47 5.45, Remain: 4 days, 1:39:52, Finish: 2024-11-28 19:09 [11-25 09:29:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 0/1669] eta: 0:24:43 tlr: 0.00017 tnm: 0.23 Lm: 6.583 (6.583) Lt: 5.764 (5.764) Accm: 2.93 (2.93) Acct: 4.99 (4.99) proj_loss: -0.5913 (-0.5913) time: 0.8888 data: 0.0003 [11-25 09:29:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 0/1669] eta: 0:24:38 tlr: 0.00017 tnm: 0.23 Lm: 6.480 (6.480) Lt: 5.801 (5.801) Accm: 2.97 (2.97) Acct: 4.89 (4.89) proj_loss: -0.6516 (-0.6516) time: 0.8860 data: 0.0004 [11-25 09:29:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 0/1669] eta: 0:24:44 tlr: 0.00017 tnm: 0.23 Lm: 6.540 (6.540) Lt: 5.809 (5.809) Accm: 3.42 (3.42) Acct: 5.20 (5.20) proj_loss: -0.6224 (-0.6224) time: 0.8893 data: 0.0004 [11-25 09:29:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 0/1669] eta: 0:24:43 tlr: 0.00017 tnm: 0.23 Lm: 6.453 (6.453) Lt: 5.753 (5.753) Accm: 2.99 (2.99) Acct: 4.51 (4.51) proj_loss: -0.6167 (-0.6167) time: 0.8886 data: 0.0003 [11-25 09:29:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 0/1669] eta: 0:24:44 tlr: 0.00017 tnm: 0.23 Lm: 6.455 (6.455) Lt: 5.750 (5.750) Accm: 3.07 (3.07) Acct: 5.20 (5.20) proj_loss: -0.6642 (-0.6642) time: 0.8894 data: 0.0003 [11-25 09:29:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 0/1669] eta: 0:24:45 tlr: 0.00017 tnm: 0.23 Lm: 6.402 (6.402) Lt: 5.737 (5.737) Accm: 3.44 (3.44) Acct: 5.10 (5.10) proj_loss: -0.6287 (-0.6287) time: 0.8901 data: 0.0004 [11-25 09:29:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 0/1669] eta: 0:24:43 tlr: 0.00017 tnm: 0.23 Lm: 6.614 (6.614) Lt: 5.850 (5.850) Accm: 3.06 (3.06) Acct: 4.96 (4.96) proj_loss: -0.6004 (-0.6004) time: 0.8886 data: 0.0004 [11-25 09:29:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 0/1669] eta: 0:24:44 tlr: 0.00017 tnm: 0.23 Lm: 6.611 (6.611) Lt: 5.789 (5.789) Accm: 3.02 (3.02) Acct: 4.79 (4.79) proj_loss: -0.6081 (-0.6081) time: 0.8894 data: 0.0004 [11-25 09:36:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.23 Lm: 6.607 (6.607) Lt: 5.851 (5.851) Accm: 3.22 (3.22) Acct: 4.98 (4.98) proj_loss: -0.6125 (-0.6125) time: 0.9287 data: 0.0002 [11-25 09:36:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.23 Lm: 6.438 (6.438) Lt: 5.754 (5.754) Accm: 3.46 (3.46) Acct: 5.32 (5.32) proj_loss: -0.6215 (-0.6215) time: 0.9287 data: 0.0002 [11-25 09:36:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.23 Lm: 6.432 (6.432) Lt: 5.677 (5.677) Accm: 3.71 (3.71) Acct: 5.96 (5.96) proj_loss: -0.6029 (-0.6029) time: 0.9287 data: 0.0003 [11-25 09:36:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.23 Lm: 6.569 (6.569) Lt: 5.816 (5.816) Accm: 3.05 (3.05) Acct: 4.73 (4.73) proj_loss: -0.6155 (-0.6155) time: 0.9287 data: 0.0003 [11-25 09:36:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.23 Lm: 6.572 (6.572) Lt: 5.821 (5.821) Accm: 3.32 (3.32) Acct: 5.10 (5.10) proj_loss: -0.6134 (-0.6134) time: 0.9287 data: 0.0003 [11-25 09:36:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.23 Lm: 6.499 (6.499) Lt: 5.790 (5.790) Accm: 3.10 (3.10) Acct: 4.87 (4.87) proj_loss: -0.6254 (-0.6254) time: 0.9287 data: 0.0003 [11-25 09:36:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.23 Lm: 6.364 (6.364) Lt: 5.612 (5.612) Accm: 3.43 (3.43) Acct: 5.27 (5.27) proj_loss: -0.6117 (-0.6117) time: 0.9287 data: 0.0003 [11-25 09:36:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 417/1669] eta: 0:19:21 tlr: 0.00017 tnm: 0.23 Lm: 6.394 (6.394) Lt: 5.673 (5.673) Accm: 3.39 (3.39) Acct: 5.32 (5.32) proj_loss: -0.6468 (-0.6468) time: 0.9287 data: 0.0003 [11-25 09:42:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.365 (6.384) Lt: 5.596 (5.635) Accm: 3.55 (3.44) Acct: 5.44 (5.44) proj_loss: -0.6339 (-0.6425) time: 0.9291 data: 0.0003 [11-25 09:42:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.453 (6.444) Lt: 5.753 (5.740) Accm: 3.51 (3.48) Acct: 5.30 (5.31) proj_loss: -0.6185 (-0.6205) time: 0.9291 data: 0.0002 [11-25 09:42:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.519 (6.461) Lt: 5.700 (5.685) Accm: 3.42 (3.52) Acct: 5.20 (5.69) proj_loss: -0.6033 (-0.6030) time: 0.9291 data: 0.0003 [11-25 09:42:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.555 (6.503) Lt: 5.764 (5.734) Accm: 3.18 (3.33) Acct: 4.99 (5.15) proj_loss: -0.6063 (-0.6124) time: 0.9291 data: 0.0003 [11-25 09:42:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.614 (6.643) Lt: 5.850 (5.905) Accm: 3.06 (3.23) Acct: 4.96 (5.05) proj_loss: -0.6198 (-0.6155) time: 0.9291 data: 0.0003 [11-25 09:42:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.402 (6.405) Lt: 5.737 (5.664) Accm: 3.42 (3.41) Acct: 5.44 (5.34) proj_loss: -0.5965 (-0.6067) time: 0.9291 data: 0.0003 [11-25 09:42:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.602 (6.580) Lt: 5.789 (5.827) Accm: 3.22 (3.22) Acct: 4.86 (4.94) proj_loss: -0.6081 (-0.6089) time: 0.9291 data: 0.0003 [11-25 09:42:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [ 834/1669] eta: 0:12:54 tlr: 0.00017 tnm: 0.23 Lm: 6.518 (6.543) Lt: 5.801 (5.823) Accm: 2.97 (2.99) Acct: 4.86 (4.76) proj_loss: -0.6158 (-0.6222) time: 0.9291 data: 0.0003 [11-25 09:49:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.574 (6.586) Lt: 5.846 (5.869) Accm: 2.97 (2.98) Acct: 4.77 (4.74) proj_loss: -0.6075 (-0.6160) time: 0.9292 data: 0.0003 [11-25 09:49:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.521 (6.499) Lt: 5.723 (5.721) Accm: 3.38 (3.39) Acct: 5.22 (5.23) proj_loss: -0.5988 (-0.6023) time: 0.9292 data: 0.0003 [11-25 09:49:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.441 (6.440) Lt: 5.732 (5.727) Accm: 3.49 (3.47) Acct: 5.39 (5.35) proj_loss: -0.6224 (-0.6232) time: 0.9292 data: 0.0003 [11-25 09:49:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.572 (6.595) Lt: 5.821 (5.857) Accm: 3.23 (3.27) Acct: 5.10 (5.13) proj_loss: -0.6132 (-0.6133) time: 0.9292 data: 0.0004 [11-25 09:49:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.529 (6.492) Lt: 5.754 (5.720) Accm: 3.29 (3.36) Acct: 5.18 (5.47) proj_loss: -0.6016 (-0.6022) time: 0.9292 data: 0.0002 [11-25 09:49:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.445 (6.444) Lt: 5.753 (5.693) Accm: 3.40 (3.30) Acct: 5.27 (5.20) proj_loss: -0.6069 (-0.6093) time: 0.9292 data: 0.0003 [11-25 09:49:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.410 (6.407) Lt: 5.648 (5.651) Accm: 3.42 (3.41) Acct: 5.32 (5.35) proj_loss: -0.6317 (-0.6344) time: 0.9292 data: 0.0003 [11-25 09:49:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [1251/1669] eta: 0:06:27 tlr: 0.00017 tnm: 0.23 Lm: 6.607 (6.590) Lt: 5.825 (5.836) Accm: 3.12 (3.12) Acct: 4.82 (4.82) proj_loss: -0.6049 (-0.6022) time: 0.9292 data: 0.0002 [11-25 09:55:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.602 (6.566) Lt: 5.789 (5.799) Accm: 3.22 (3.19) Acct: 4.86 (4.99) proj_loss: -0.6081 (-0.6041) time: 0.9305 data: 0.0018 [11-25 09:55:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 125/350] Total time: 0:25:49 (0.928 s / it) [11-25 09:55:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.429 (6.417) Lt: 5.712 (5.698) Accm: 3.51 (3.48) Acct: 5.48 (5.39) proj_loss: -0.6185 (-0.6179) time: 0.9305 data: 0.0018 [11-25 09:55:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.517 (6.502) Lt: 5.764 (5.736) Accm: 3.18 (3.31) Acct: 4.99 (5.06) proj_loss: -0.6063 (-0.6038) time: 0.9305 data: 0.0017 [11-25 09:55:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.519 (6.491) Lt: 5.731 (5.722) Accm: 3.42 (3.38) Acct: 5.20 (5.42) proj_loss: -0.6033 (-0.6049) time: 0.9305 data: 0.0019 [11-25 09:55:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.530 (6.507) Lt: 5.793 (5.777) Accm: 3.39 (3.52) Acct: 5.23 (5.37) proj_loss: -0.6198 (-0.6191) time: 0.9305 data: 0.0019 [11-25 09:55:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.483 (6.452) Lt: 5.737 (5.688) Accm: 3.42 (3.36) Acct: 5.44 (5.28) proj_loss: -0.6173 (-0.6147) time: 0.9305 data: 0.0017 [11-25 09:55:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.452 (6.416) Lt: 5.701 (5.680) Accm: 3.29 (3.34) Acct: 5.20 (5.19) proj_loss: -0.6295 (-0.6283) time: 0.9305 data: 0.0020 [11-25 09:55:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 125/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.533 (6.575) Lt: 5.801 (5.852) Accm: 2.97 (3.05) Acct: 4.86 (4.81) proj_loss: -0.6146 (-0.6157) time: 0.9305 data: 0.0023 [11-25 09:55:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 125/350] Total time: 0:25:49 (0.928 s / it) [11-25 09:55:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 125/350] Total time: 0:25:49 (0.928 s / it) [11-25 09:55:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 125/350] Total time: 0:25:49 (0.928 s / it) [11-25 09:55:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 125/350] Total time: 0:25:49 (0.928 s / it) [11-25 09:55:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 125/350] Total time: 0:25:49 (0.928 s / it) [11-25 09:55:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 125/350] Total time: 0:25:49 (0.928 s / it) [11-25 09:55:46] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 125/350] Total time: 0:25:49 (0.928 s / it) [11-25 09:55:46] (/home/user/VAR/train.py , line 276)=> [ep125] (training ) Lm: 6.462 (6.480), Lt: 5.704 (5.727), Acc m&t: 3.47 5.45, Remain: 4 days, 1:18:07, Finish: 2024-11-28 19:13 [11-25 09:55:46] (/home/user/VAR/train.py , line 276)=> [ep125] (training ) Lm: 6.462 (6.480), Lt: 5.704 (5.727), Acc m&t: 3.47 5.45, Remain: 4 days, 1:18:21, Finish: 2024-11-28 19:14 [11-25 09:55:46] (/home/user/VAR/train.py , line 276)=> [ep125] (training ) Lm: 6.462 (6.480), Lt: 5.704 (5.727), Acc m&t: 3.47 5.45, Remain: 4 days, 1:17:17, Finish: 2024-11-28 19:13 [11-25 09:55:46] (/home/user/VAR/train.py , line 276)=> [ep125] (training ) Lm: 6.462 (6.480), Lt: 5.704 (5.727), Acc m&t: 3.47 5.45, Remain: 4 days, 1:17:54, Finish: 2024-11-28 19:13 [11-25 09:55:46] (/home/user/VAR/train.py , line 276)=> [ep125] (training ) Lm: 6.462 (6.480), Lt: 5.704 (5.727), Acc m&t: 3.47 5.45, Remain: 4 days, 1:17:42, Finish: 2024-11-28 19:13 [11-25 09:55:46] (/home/user/VAR/train.py , line 276)=> [ep125] (training ) Lm: 6.462 (6.480), Lt: 5.704 (5.727), Acc m&t: 3.47 5.45, Remain: 4 days, 1:18:05, Finish: 2024-11-28 19:13 [11-25 09:55:46] (/home/user/VAR/train.py , line 276)=> [ep125] (training ) Lm: 6.462 (6.480), Lt: 5.704 (5.727), Acc m&t: 3.47 5.45, Remain: 4 days, 1:18:55, Finish: 2024-11-28 19:14 [11-25 09:55:46] (/home/user/VAR/train.py , line 276)=> [ep125] (training ) Lm: 6.462 (6.480), Lt: 5.704 (5.727), Acc m&t: 3.47 5.45, Remain: 4 days, 1:17:14, Finish: 2024-11-28 19:13 [11-25 09:55:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 0/1669] eta: 0:24:59 tlr: 0.00017 tnm: 0.24 Lm: 6.385 (6.385) Lt: 5.578 (5.578) Accm: 3.02 (3.02) Acct: 5.10 (5.10) proj_loss: -0.6312 (-0.6312) time: 0.8983 data: 0.0004 [11-25 09:55:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 0/1669] eta: 0:25:01 tlr: 0.00017 tnm: 0.24 Lm: 6.563 (6.563) Lt: 5.763 (5.763) Accm: 3.22 (3.22) Acct: 5.06 (5.06) proj_loss: -0.6003 (-0.6003) time: 0.8999 data: 0.0004 [11-25 09:55:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 0/1669] eta: 0:24:59 tlr: 0.00017 tnm: 0.24 Lm: 6.488 (6.488) Lt: 5.757 (5.757) Accm: 3.21 (3.21) Acct: 5.06 (5.06) proj_loss: -0.6196 (-0.6196) time: 0.8985 data: 0.0004 [11-25 09:55:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 0/1669] eta: 0:24:58 tlr: 0.00017 tnm: 0.24 Lm: 6.359 (6.359) Lt: 5.647 (5.647) Accm: 3.96 (3.96) Acct: 6.06 (6.06) proj_loss: -0.6247 (-0.6247) time: 0.8976 data: 0.0004 [11-25 09:55:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 0/1669] eta: 0:25:00 tlr: 0.00017 tnm: 0.24 Lm: 6.454 (6.454) Lt: 5.683 (5.683) Accm: 3.63 (3.63) Acct: 5.92 (5.92) proj_loss: -0.5999 (-0.5999) time: 0.8988 data: 0.0004 [11-25 09:55:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 0/1669] eta: 0:25:00 tlr: 0.00017 tnm: 0.24 Lm: 6.523 (6.523) Lt: 5.806 (5.806) Accm: 3.09 (3.09) Acct: 4.79 (4.79) proj_loss: -0.6341 (-0.6341) time: 0.8988 data: 0.0003 [11-25 09:55:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 0/1669] eta: 0:25:00 tlr: 0.00017 tnm: 0.24 Lm: 6.399 (6.399) Lt: 5.715 (5.715) Accm: 3.53 (3.53) Acct: 5.41 (5.41) proj_loss: -0.5931 (-0.5931) time: 0.8991 data: 0.0004 [11-25 09:55:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 0/1669] eta: 0:25:00 tlr: 0.00017 tnm: 0.24 Lm: 6.421 (6.421) Lt: 5.710 (5.710) Accm: 3.60 (3.60) Acct: 5.58 (5.58) proj_loss: -0.5958 (-0.5958) time: 0.8989 data: 0.0004 [11-25 10:02:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 417/1669] eta: 0:20:19 tlr: 0.00017 tnm: 0.24 Lm: 6.344 (6.344) Lt: 5.623 (5.623) Accm: 3.82 (3.82) Acct: 5.73 (5.73) proj_loss: -0.6031 (-0.6031) time: 0.9293 data: 0.0003 [11-25 10:02:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 417/1669] eta: 0:20:19 tlr: 0.00017 tnm: 0.24 Lm: 6.450 (6.450) Lt: 5.721 (5.721) Accm: 3.45 (3.45) Acct: 5.41 (5.41) proj_loss: -0.6190 (-0.6190) time: 0.9292 data: 0.0003 [11-25 10:02:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 417/1669] eta: 0:20:19 tlr: 0.00017 tnm: 0.24 Lm: 6.379 (6.379) Lt: 5.618 (5.618) Accm: 3.38 (3.38) Acct: 5.41 (5.41) proj_loss: -0.6357 (-0.6357) time: 0.9292 data: 0.0002 [11-25 10:02:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 417/1669] eta: 0:20:19 tlr: 0.00017 tnm: 0.24 Lm: 6.532 (6.532) Lt: 5.721 (5.721) Accm: 3.07 (3.07) Acct: 4.92 (4.92) proj_loss: -0.5989 (-0.5989) time: 0.9292 data: 0.0002 [11-25 10:02:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 417/1669] eta: 0:20:19 tlr: 0.00017 tnm: 0.24 Lm: 6.598 (6.598) Lt: 5.844 (5.844) Accm: 3.39 (3.39) Acct: 5.34 (5.34) proj_loss: -0.5898 (-0.5898) time: 0.9292 data: 0.0003 [11-25 10:02:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 417/1669] eta: 0:20:19 tlr: 0.00017 tnm: 0.24 Lm: 6.427 (6.427) Lt: 5.701 (5.701) Accm: 3.54 (3.54) Acct: 5.37 (5.37) proj_loss: -0.6146 (-0.6146) time: 0.9293 data: 0.0003 [11-25 10:02:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 417/1669] eta: 0:20:19 tlr: 0.00017 tnm: 0.24 Lm: 6.579 (6.579) Lt: 5.871 (5.871) Accm: 3.02 (3.02) Acct: 4.77 (4.77) proj_loss: -0.5973 (-0.5973) time: 0.9292 data: 0.0003 [11-25 10:02:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 417/1669] eta: 0:20:19 tlr: 0.00017 tnm: 0.24 Lm: 6.466 (6.466) Lt: 5.691 (5.691) Accm: 3.32 (3.32) Acct: 5.41 (5.41) proj_loss: -0.6134 (-0.6134) time: 0.9293 data: 0.0003 [11-25 10:09:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 834/1669] eta: 0:13:14 tlr: 0.00017 tnm: 0.23 Lm: 6.409 (6.397) Lt: 5.576 (5.603) Accm: 3.55 (3.62) Acct: 6.03 (5.85) proj_loss: -0.5927 (-0.6062) time: 0.9296 data: 0.0002 [11-25 10:09:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 834/1669] eta: 0:13:14 tlr: 0.00017 tnm: 0.23 Lm: 6.563 (6.616) Lt: 5.763 (5.825) Accm: 2.93 (2.79) Acct: 4.79 (4.53) proj_loss: -0.5976 (-0.5959) time: 0.9296 data: 0.0002 [11-25 10:09:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 834/1669] eta: 0:13:14 tlr: 0.00017 tnm: 0.23 Lm: 6.385 (6.424) Lt: 5.658 (5.710) Accm: 3.02 (3.23) Acct: 5.10 (5.12) proj_loss: -0.6316 (-0.6343) time: 0.9296 data: 0.0003 [11-25 10:09:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 834/1669] eta: 0:13:14 tlr: 0.00017 tnm: 0.23 Lm: 6.454 (6.549) Lt: 5.683 (5.781) Accm: 3.44 (3.40) Acct: 5.48 (5.38) proj_loss: -0.5995 (-0.5930) time: 0.9296 data: 0.0003 [11-25 10:09:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 834/1669] eta: 0:13:14 tlr: 0.00017 tnm: 0.23 Lm: 6.399 (6.447) Lt: 5.715 (5.755) Accm: 3.53 (3.46) Acct: 5.41 (5.21) proj_loss: -0.6016 (-0.6077) time: 0.9296 data: 0.0003 [11-25 10:09:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 834/1669] eta: 0:13:14 tlr: 0.00017 tnm: 0.23 Lm: 6.421 (6.385) Lt: 5.710 (5.664) Accm: 3.60 (3.71) Acct: 5.79 (5.75) proj_loss: -0.6103 (-0.6099) time: 0.9296 data: 0.0003 [11-25 10:09:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 834/1669] eta: 0:13:14 tlr: 0.00017 tnm: 0.23 Lm: 6.412 (6.426) Lt: 5.685 (5.662) Accm: 3.70 (3.66) Acct: 5.75 (5.79) proj_loss: -0.6185 (-0.6115) time: 0.9296 data: 0.0002 [11-25 10:09:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [ 834/1669] eta: 0:13:14 tlr: 0.00017 tnm: 0.23 Lm: 6.482 (6.445) Lt: 5.705 (5.702) Accm: 3.47 (3.52) Acct: 5.06 (5.27) proj_loss: -0.6044 (-0.6061) time: 0.9296 data: 0.0003 [11-25 10:15:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [1251/1669] eta: 0:06:34 tlr: 0.00017 tnm: 0.23 Lm: 6.488 (6.475) Lt: 5.730 (5.724) Accm: 3.29 (3.41) Acct: 4.92 (5.15) proj_loss: -0.6146 (-0.6110) time: 0.9292 data: 0.0003 [11-25 10:15:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [1251/1669] eta: 0:06:34 tlr: 0.00017 tnm: 0.23 Lm: 6.443 (6.443) Lt: 5.673 (5.705) Accm: 3.11 (3.23) Acct: 5.18 (5.16) proj_loss: -0.6314 (-0.6291) time: 0.9292 data: 0.0003 [11-25 10:15:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [1251/1669] eta: 0:06:34 tlr: 0.00017 tnm: 0.23 Lm: 6.527 (6.562) Lt: 5.772 (5.801) Accm: 3.29 (3.33) Acct: 5.11 (5.22) proj_loss: -0.5997 (-0.6027) time: 0.9292 data: 0.0003 [11-25 10:15:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [1251/1669] eta: 0:06:34 tlr: 0.00017 tnm: 0.23 Lm: 6.395 (6.385) Lt: 5.620 (5.635) Accm: 3.88 (3.78) Acct: 6.11 (5.96) proj_loss: -0.6190 (-0.6186) time: 0.9291 data: 0.0002 [11-25 10:15:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [1251/1669] eta: 0:06:34 tlr: 0.00017 tnm: 0.23 Lm: 6.467 (6.469) Lt: 5.771 (5.773) Accm: 3.37 (3.39) Acct: 5.44 (5.28) proj_loss: -0.6149 (-0.6166) time: 0.9292 data: 0.0003 [11-25 10:15:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [1251/1669] eta: 0:06:34 tlr: 0.00017 tnm: 0.23 Lm: 6.532 (6.569) Lt: 5.721 (5.789) Accm: 3.07 (2.98) Acct: 4.92 (4.82) proj_loss: -0.5989 (-0.5996) time: 0.9292 data: 0.0002 [11-25 10:15:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [1251/1669] eta: 0:06:34 tlr: 0.00017 tnm: 0.23 Lm: 6.466 (6.430) Lt: 5.662 (5.639) Accm: 3.55 (3.60) Acct: 5.82 (5.79) proj_loss: -0.5950 (-0.6040) time: 0.9292 data: 0.0003 [11-25 10:15:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [1251/1669] eta: 0:06:34 tlr: 0.00017 tnm: 0.23 Lm: 6.441 (6.404) Lt: 5.663 (5.652) Accm: 3.55 (3.61) Acct: 5.68 (5.60) proj_loss: -0.6068 (-0.6083) time: 0.9292 data: 0.0003 [11-25 10:21:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.421 (6.384) Lt: 5.617 (5.624) Accm: 3.50 (3.58) Acct: 5.65 (5.61) proj_loss: -0.6034 (-0.6065) time: 0.9300 data: 0.0015 [11-25 10:21:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 126/350] Total time: 0:26:08 (0.940 s / it) [11-25 10:21:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.563 (6.574) Lt: 5.763 (5.793) Accm: 2.97 (2.97) Acct: 4.96 (4.85) proj_loss: -0.6003 (-0.6011) time: 0.9299 data: 0.0021 [11-25 10:21:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.409 (6.407) Lt: 5.576 (5.621) Accm: 3.54 (3.58) Acct: 5.61 (5.70) proj_loss: -0.5973 (-0.6068) time: 0.9299 data: 0.0018 [11-25 10:21:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.500 (6.461) Lt: 5.687 (5.714) Accm: 3.02 (3.18) Acct: 5.10 (5.09) proj_loss: -0.6312 (-0.6270) time: 0.9300 data: 0.0018 [11-25 10:21:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.454 (6.532) Lt: 5.683 (5.758) Accm: 3.44 (3.41) Acct: 5.48 (5.38) proj_loss: -0.5995 (-0.5963) time: 0.9300 data: 0.0022 [11-25 10:21:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.399 (6.438) Lt: 5.715 (5.748) Accm: 3.53 (3.57) Acct: 5.48 (5.57) proj_loss: -0.6106 (-0.6154) time: 0.9300 data: 0.0017 [11-25 10:21:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.378 (6.352) Lt: 5.554 (5.585) Accm: 3.92 (3.81) Acct: 6.40 (6.05) proj_loss: -0.6185 (-0.6178) time: 0.9300 data: 0.0019 [11-25 10:21:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 126/350] [1668/1669] eta: 0:00:00 tlr: 0.00017 tnm: 0.24 Lm: 6.482 (6.460) Lt: 5.705 (5.706) Accm: 3.47 (3.45) Acct: 5.06 (5.32) proj_loss: -0.6247 (-0.6179) time: 0.9300 data: 0.0020 [11-25 10:21:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 126/350] Total time: 0:26:08 (0.940 s / it) [11-25 10:21:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 126/350] Total time: 0:26:08 (0.940 s / it) [11-25 10:21:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 126/350] Total time: 0:26:08 (0.940 s / it) [11-25 10:21:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 126/350] Total time: 0:26:08 (0.940 s / it) [11-25 10:21:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 126/350] Total time: 0:26:08 (0.940 s / it) [11-25 10:21:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 126/350] Total time: 0:26:08 (0.940 s / it) [11-25 10:21:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 126/350] Total time: 0:26:08 (0.940 s / it) [11-25 10:21:54] (/home/user/VAR/train.py , line 276)=> [ep126] (training ) Lm: 6.462 (6.472), Lt: 5.704 (5.715), Acc m&t: 3.47 5.45, Remain: 4 days, 0:37:15, Finish: 2024-11-28 18:59 [11-25 10:21:54] (/home/user/VAR/train.py , line 276)=> [ep126] (training ) Lm: 6.462 (6.472), Lt: 5.704 (5.715), Acc m&t: 3.47 5.45, Remain: 4 days, 0:38:08, Finish: 2024-11-28 19:00 [11-25 10:21:54] (/home/user/VAR/train.py , line 276)=> [ep126] (training ) Lm: 6.462 (6.472), Lt: 5.704 (5.715), Acc m&t: 3.47 5.45, Remain: 4 days, 0:35:50, Finish: 2024-11-28 18:57 [11-25 10:21:54] (/home/user/VAR/train.py , line 276)=> [ep126] (training ) Lm: 6.462 (6.472), Lt: 5.704 (5.715), Acc m&t: 3.47 5.45, Remain: 4 days, 0:34:43, Finish: 2024-11-28 18:56 [11-25 10:21:54] (/home/user/VAR/train.py , line 276)=> [ep126] (training ) Lm: 6.462 (6.472), Lt: 5.704 (5.715), Acc m&t: 3.47 5.45, Remain: 4 days, 0:38:06, Finish: 2024-11-28 19:00 [11-25 10:21:54] (/home/user/VAR/train.py , line 276)=> [ep126] (training ) Lm: 6.462 (6.472), Lt: 5.704 (5.715), Acc m&t: 3.47 5.45, Remain: 4 days, 0:36:51, Finish: 2024-11-28 18:58 [11-25 10:21:54] (/home/user/VAR/train.py , line 276)=> [ep126] (training ) Lm: 6.462 (6.472), Lt: 5.704 (5.715), Acc m&t: 3.47 5.45, Remain: 4 days, 0:36:15, Finish: 2024-11-28 18:58 [11-25 10:21:54] (/home/user/VAR/train.py , line 276)=> [ep126] (training ) Lm: 6.462 (6.472), Lt: 5.704 (5.715), Acc m&t: 3.47 5.45, Remain: 4 days, 0:37:30, Finish: 2024-11-28 18:59 [11-25 10:21:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 0/1669] eta: 0:25:26 tlr: 0.00017 tnm: 0.23 Lm: 6.491 (6.491) Lt: 5.755 (5.755) Accm: 3.55 (3.55) Acct: 5.79 (5.79) proj_loss: -0.6625 (-0.6625) time: 0.9145 data: 0.0004 [11-25 10:21:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 0/1669] eta: 0:25:26 tlr: 0.00017 tnm: 0.23 Lm: 6.384 (6.384) Lt: 5.730 (5.730) Accm: 3.80 (3.80) Acct: 5.20 (5.20) proj_loss: -0.6302 (-0.6302) time: 0.9145 data: 0.0003 [11-25 10:21:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 0/1669] eta: 0:25:25 tlr: 0.00017 tnm: 0.23 Lm: 6.321 (6.321) Lt: 5.532 (5.532) Accm: 3.96 (3.96) Acct: 6.03 (6.03) proj_loss: -0.5934 (-0.5934) time: 0.9138 data: 0.0004 [11-25 10:21:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 0/1669] eta: 0:25:27 tlr: 0.00017 tnm: 0.23 Lm: 6.579 (6.579) Lt: 5.869 (5.869) Accm: 2.97 (2.97) Acct: 4.58 (4.58) proj_loss: -0.5977 (-0.5977) time: 0.9150 data: 0.0003 [11-25 10:21:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 0/1669] eta: 0:25:25 tlr: 0.00017 tnm: 0.23 Lm: 6.594 (6.594) Lt: 5.802 (5.802) Accm: 2.58 (2.58) Acct: 4.06 (4.06) proj_loss: -0.5779 (-0.5779) time: 0.9138 data: 0.0003 [11-25 10:21:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 0/1669] eta: 0:25:24 tlr: 0.00017 tnm: 0.23 Lm: 6.219 (6.219) Lt: 5.407 (5.407) Accm: 3.83 (3.83) Acct: 5.75 (5.75) proj_loss: -0.6059 (-0.6059) time: 0.9137 data: 0.0004 [11-25 10:21:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 0/1669] eta: 0:25:27 tlr: 0.00017 tnm: 0.23 Lm: 6.420 (6.420) Lt: 5.628 (5.628) Accm: 3.60 (3.60) Acct: 5.85 (5.85) proj_loss: -0.6013 (-0.6013) time: 0.9152 data: 0.0004 [11-25 10:21:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 0/1669] eta: 0:25:26 tlr: 0.00017 tnm: 0.23 Lm: 6.510 (6.510) Lt: 5.825 (5.825) Accm: 3.45 (3.45) Acct: 5.61 (5.61) proj_loss: -0.6073 (-0.6073) time: 0.9148 data: 0.0004 [11-25 10:28:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 417/1669] eta: 0:19:20 tlr: 0.00016 tnm: 0.23 Lm: 6.346 (6.346) Lt: 5.587 (5.587) Accm: 3.75 (3.75) Acct: 6.10 (6.10) proj_loss: -0.6201 (-0.6201) time: 0.9257 data: 0.0003 [11-25 10:28:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 417/1669] eta: 0:19:20 tlr: 0.00016 tnm: 0.23 Lm: 6.494 (6.494) Lt: 5.795 (5.795) Accm: 3.44 (3.44) Acct: 5.08 (5.08) proj_loss: -0.6094 (-0.6094) time: 0.9257 data: 0.0002 [11-25 10:28:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 417/1669] eta: 0:19:20 tlr: 0.00016 tnm: 0.23 Lm: 6.465 (6.465) Lt: 5.752 (5.752) Accm: 3.66 (3.66) Acct: 5.49 (5.49) proj_loss: -0.6107 (-0.6107) time: 0.9257 data: 0.0003 [11-25 10:28:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 417/1669] eta: 0:19:20 tlr: 0.00016 tnm: 0.23 Lm: 6.528 (6.528) Lt: 5.765 (5.765) Accm: 3.28 (3.28) Acct: 5.29 (5.29) proj_loss: -0.6191 (-0.6191) time: 0.9257 data: 0.0003 [11-25 10:28:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 417/1669] eta: 0:19:20 tlr: 0.00016 tnm: 0.23 Lm: 6.351 (6.351) Lt: 5.579 (5.579) Accm: 3.74 (3.74) Acct: 5.65 (5.65) proj_loss: -0.6150 (-0.6150) time: 0.9257 data: 0.0003 [11-25 10:28:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 417/1669] eta: 0:19:20 tlr: 0.00016 tnm: 0.23 Lm: 6.344 (6.344) Lt: 5.559 (5.559) Accm: 3.88 (3.88) Acct: 6.03 (6.03) proj_loss: -0.6094 (-0.6094) time: 0.9257 data: 0.0003 [11-25 10:28:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 417/1669] eta: 0:19:20 tlr: 0.00016 tnm: 0.23 Lm: 6.568 (6.568) Lt: 5.808 (5.808) Accm: 3.04 (3.04) Acct: 4.73 (4.73) proj_loss: -0.5956 (-0.5956) time: 0.9257 data: 0.0003 [11-25 10:28:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 417/1669] eta: 0:19:20 tlr: 0.00016 tnm: 0.23 Lm: 6.392 (6.392) Lt: 5.586 (5.586) Accm: 3.65 (3.65) Acct: 5.89 (5.89) proj_loss: -0.6066 (-0.6066) time: 0.9257 data: 0.0003 [11-25 10:35:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 834/1669] eta: 0:13:33 tlr: 0.00016 tnm: 0.24 Lm: 6.420 (6.408) Lt: 5.628 (5.613) Accm: 3.60 (3.59) Acct: 5.85 (5.66) proj_loss: -0.6119 (-0.6109) time: 0.9295 data: 0.0003 [11-25 10:35:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 834/1669] eta: 0:13:33 tlr: 0.00016 tnm: 0.24 Lm: 6.558 (6.515) Lt: 5.765 (5.785) Accm: 3.13 (3.34) Acct: 5.13 (5.10) proj_loss: -0.6302 (-0.6227) time: 0.9295 data: 0.0003 [11-25 10:35:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 834/1669] eta: 0:13:33 tlr: 0.00016 tnm: 0.24 Lm: 6.491 (6.503) Lt: 5.755 (5.724) Accm: 3.55 (3.41) Acct: 5.79 (5.48) proj_loss: -0.5757 (-0.6030) time: 0.9295 data: 0.0003 [11-25 10:35:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 834/1669] eta: 0:13:33 tlr: 0.00016 tnm: 0.24 Lm: 6.423 (6.451) Lt: 5.647 (5.717) Accm: 3.63 (3.65) Acct: 5.75 (5.58) proj_loss: -0.5973 (-0.6062) time: 0.9295 data: 0.0003 [11-25 10:35:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 834/1669] eta: 0:13:33 tlr: 0.00016 tnm: 0.24 Lm: 6.420 (6.369) Lt: 5.709 (5.609) Accm: 3.83 (3.66) Acct: 5.75 (5.59) proj_loss: -0.6130 (-0.6153) time: 0.9295 data: 0.0003 [11-25 10:35:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 834/1669] eta: 0:13:33 tlr: 0.00016 tnm: 0.24 Lm: 6.542 (6.458) Lt: 5.802 (5.696) Accm: 3.51 (3.53) Acct: 5.41 (5.52) proj_loss: -0.5821 (-0.5911) time: 0.9295 data: 0.0003 [11-25 10:35:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 834/1669] eta: 0:13:33 tlr: 0.00016 tnm: 0.24 Lm: 6.434 (6.379) Lt: 5.740 (5.633) Accm: 3.42 (3.64) Acct: 5.27 (5.52) proj_loss: -0.6162 (-0.6154) time: 0.9295 data: 0.0003 [11-25 10:35:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [ 834/1669] eta: 0:13:33 tlr: 0.00016 tnm: 0.24 Lm: 6.425 (6.372) Lt: 5.689 (5.621) Accm: 3.73 (3.74) Acct: 5.82 (6.00) proj_loss: -0.6329 (-0.6246) time: 0.9295 data: 0.0003 [11-25 10:41:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [1251/1669] eta: 0:06:40 tlr: 0.00016 tnm: 0.23 Lm: 6.468 (6.418) Lt: 5.729 (5.658) Accm: 3.59 (3.63) Acct: 5.72 (5.78) proj_loss: -0.6240 (-0.6222) time: 0.9286 data: 0.0003 [11-25 10:41:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [1251/1669] eta: 0:06:40 tlr: 0.00016 tnm: 0.23 Lm: 6.471 (6.487) Lt: 5.699 (5.689) Accm: 3.62 (3.59) Acct: 5.82 (5.83) proj_loss: -0.6095 (-0.6131) time: 0.9286 data: 0.0002 [11-25 10:41:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [1251/1669] eta: 0:06:40 tlr: 0.00016 tnm: 0.23 Lm: 6.493 (6.494) Lt: 5.749 (5.772) Accm: 3.42 (3.43) Acct: 5.17 (5.14) proj_loss: -0.6295 (-0.6242) time: 0.9286 data: 0.0002 [11-25 10:41:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [1251/1669] eta: 0:06:40 tlr: 0.00016 tnm: 0.23 Lm: 6.430 (6.482) Lt: 5.647 (5.707) Accm: 3.54 (3.35) Acct: 5.53 (5.29) proj_loss: -0.6085 (-0.6095) time: 0.9286 data: 0.0003 [11-25 10:41:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [1251/1669] eta: 0:06:40 tlr: 0.00016 tnm: 0.23 Lm: 6.506 (6.439) Lt: 5.803 (5.691) Accm: 3.23 (3.49) Acct: 5.03 (5.34) proj_loss: -0.6201 (-0.6176) time: 0.9286 data: 0.0003 [11-25 10:41:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [1251/1669] eta: 0:06:40 tlr: 0.00016 tnm: 0.23 Lm: 6.408 (6.436) Lt: 5.658 (5.705) Accm: 3.57 (3.62) Acct: 5.39 (5.44) proj_loss: -0.6004 (-0.6056) time: 0.9286 data: 0.0002 [11-25 10:41:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [1251/1669] eta: 0:06:40 tlr: 0.00016 tnm: 0.23 Lm: 6.444 (6.402) Lt: 5.704 (5.631) Accm: 3.65 (3.61) Acct: 5.68 (5.60) proj_loss: -0.6200 (-0.6192) time: 0.9286 data: 0.0003 [11-25 10:41:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [1251/1669] eta: 0:06:40 tlr: 0.00016 tnm: 0.23 Lm: 6.568 (6.502) Lt: 5.808 (5.744) Accm: 3.10 (3.32) Acct: 4.73 (5.14) proj_loss: -0.5978 (-0.5982) time: 0.9286 data: 0.0003 [11-25 10:48:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.23 Lm: 6.542 (6.509) Lt: 5.802 (5.737) Accm: 3.34 (3.32) Acct: 5.30 (5.17) proj_loss: -0.6093 (-0.6004) time: 0.9286 data: 0.0018 [11-25 10:48:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 127/350] Total time: 0:26:27 (0.951 s / it) [11-25 10:48:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.23 Lm: 6.444 (6.484) Lt: 5.734 (5.737) Accm: 3.51 (3.44) Acct: 5.20 (5.29) proj_loss: -0.6288 (-0.6176) time: 0.9286 data: 0.0018 [11-25 10:48:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.23 Lm: 6.425 (6.374) Lt: 5.689 (5.641) Accm: 3.73 (3.76) Acct: 5.82 (5.88) proj_loss: -0.6329 (-0.6260) time: 0.9286 data: 0.0018 [11-25 10:48:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.23 Lm: 6.431 (6.472) Lt: 5.667 (5.705) Accm: 3.48 (3.34) Acct: 5.48 (5.32) proj_loss: -0.6119 (-0.6107) time: 0.9286 data: 0.0021 [11-25 10:48:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.23 Lm: 6.491 (6.488) Lt: 5.686 (5.689) Accm: 3.55 (3.53) Acct: 5.79 (5.72) proj_loss: -0.5987 (-0.6102) time: 0.9286 data: 0.0018 [11-25 10:48:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.23 Lm: 6.423 (6.463) Lt: 5.668 (5.753) Accm: 3.51 (3.51) Acct: 5.03 (5.25) proj_loss: -0.6036 (-0.6066) time: 0.9286 data: 0.0015 [11-25 10:48:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.23 Lm: 6.455 (6.413) Lt: 5.709 (5.647) Accm: 3.53 (3.60) Acct: 5.61 (5.60) proj_loss: -0.6130 (-0.6175) time: 0.9286 data: 0.0023 [11-25 10:48:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 127/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.23 Lm: 6.579 (6.468) Lt: 5.823 (5.717) Accm: 3.04 (3.39) Acct: 4.79 (5.19) proj_loss: -0.6162 (-0.6092) time: 0.9286 data: 0.0015 [11-25 10:48:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 127/350] Total time: 0:26:27 (0.951 s / it) [11-25 10:48:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 127/350] Total time: 0:26:27 (0.951 s / it) [11-25 10:48:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 127/350] Total time: 0:26:27 (0.951 s / it) [11-25 10:48:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 127/350] Total time: 0:26:27 (0.951 s / it) [11-25 10:48:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 127/350] Total time: 0:26:27 (0.951 s / it) [11-25 10:48:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 127/350] Total time: 0:26:27 (0.951 s / it) [11-25 10:48:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 127/350] Total time: 0:26:27 (0.951 s / it) [11-25 10:48:22] (/home/user/VAR/train.py , line 276)=> [ep127] (training ) Lm: 6.462 (6.472), Lt: 5.704 (5.713), Acc m&t: 3.47 5.45, Remain: 4 days, 0:12:53, Finish: 2024-11-28 19:01 [11-25 10:48:22] (/home/user/VAR/train.py , line 276)=> [ep127] (training ) Lm: 6.462 (6.472), Lt: 5.704 (5.713), Acc m&t: 3.47 5.45, Remain: 4 days, 0:13:30, Finish: 2024-11-28 19:01 [11-25 10:48:22] (/home/user/VAR/train.py , line 276)=> [ep127] (training ) Lm: 6.462 (6.472), Lt: 5.704 (5.713), Acc m&t: 3.47 5.45, Remain: 4 days, 0:14:00, Finish: 2024-11-28 19:02 [11-25 10:48:22] (/home/user/VAR/train.py , line 276)=> [ep127] (training ) Lm: 6.462 (6.472), Lt: 5.704 (5.713), Acc m&t: 3.47 5.45, Remain: 4 days, 0:13:42, Finish: 2024-11-28 19:02 [11-25 10:48:22] (/home/user/VAR/train.py , line 276)=> [ep127] (training ) Lm: 6.462 (6.472), Lt: 5.704 (5.713), Acc m&t: 3.47 5.45, Remain: 4 days, 0:12:59, Finish: 2024-11-28 19:01 [11-25 10:48:22] (/home/user/VAR/train.py , line 276)=> [ep127] (training ) Lm: 6.462 (6.472), Lt: 5.704 (5.713), Acc m&t: 3.47 5.45, Remain: 4 days, 0:12:24, Finish: 2024-11-28 19:00 [11-25 10:48:22] (/home/user/VAR/train.py , line 276)=> [ep127] (training ) Lm: 6.462 (6.472), Lt: 5.704 (5.713), Acc m&t: 3.47 5.45, Remain: 4 days, 0:13:03, Finish: 2024-11-28 19:01 [11-25 10:48:22] (/home/user/VAR/train.py , line 276)=> [ep127] (training ) Lm: 6.462 (6.472), Lt: 5.704 (5.713), Acc m&t: 3.47 5.45, Remain: 4 days, 0:15:05, Finish: 2024-11-28 19:03 [11-25 10:48:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 0/1669] eta: 0:24:43 tlr: 0.00016 tnm: 0.23 Lm: 6.385 (6.385) Lt: 5.589 (5.589) Accm: 3.51 (3.51) Acct: 5.92 (5.92) proj_loss: -0.6420 (-0.6420) time: 0.8886 data: 0.0004 [11-25 10:48:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 0/1669] eta: 0:24:43 tlr: 0.00016 tnm: 0.23 Lm: 6.508 (6.508) Lt: 5.732 (5.732) Accm: 3.70 (3.70) Acct: 5.61 (5.61) proj_loss: -0.5906 (-0.5906) time: 0.8889 data: 0.0003 [11-25 10:48:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 0/1669] eta: 0:24:42 tlr: 0.00016 tnm: 0.23 Lm: 6.429 (6.429) Lt: 5.594 (5.594) Accm: 4.01 (4.01) Acct: 6.85 (6.85) proj_loss: -0.5819 (-0.5819) time: 0.8885 data: 0.0004 [11-25 10:48:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 0/1669] eta: 0:24:43 tlr: 0.00016 tnm: 0.23 Lm: 6.496 (6.496) Lt: 5.759 (5.759) Accm: 3.00 (3.00) Acct: 4.82 (4.82) proj_loss: -0.6221 (-0.6221) time: 0.8891 data: 0.0004 [11-25 10:48:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 0/1669] eta: 0:24:43 tlr: 0.00016 tnm: 0.23 Lm: 6.383 (6.383) Lt: 5.572 (5.572) Accm: 4.04 (4.04) Acct: 6.54 (6.54) proj_loss: -0.5853 (-0.5853) time: 0.8891 data: 0.0004 [11-25 10:48:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 0/1669] eta: 0:24:43 tlr: 0.00016 tnm: 0.23 Lm: 6.227 (6.227) Lt: 5.476 (5.476) Accm: 3.89 (3.89) Acct: 6.10 (6.10) proj_loss: -0.6275 (-0.6275) time: 0.8886 data: 0.0004 [11-25 10:48:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 0/1669] eta: 0:24:35 tlr: 0.00016 tnm: 0.23 Lm: 6.455 (6.455) Lt: 5.665 (5.665) Accm: 3.50 (3.50) Acct: 5.44 (5.44) proj_loss: -0.5781 (-0.5781) time: 0.8839 data: 0.0004 [11-25 10:48:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 0/1669] eta: 0:24:44 tlr: 0.00016 tnm: 0.23 Lm: 6.409 (6.409) Lt: 5.677 (5.677) Accm: 3.61 (3.61) Acct: 5.41 (5.41) proj_loss: -0.6497 (-0.6497) time: 0.8893 data: 0.0003 [11-25 10:54:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 417/1669] eta: 0:19:21 tlr: 0.00016 tnm: 0.24 Lm: 6.472 (6.472) Lt: 5.716 (5.716) Accm: 3.39 (3.39) Acct: 5.42 (5.42) proj_loss: -0.6263 (-0.6263) time: 0.9271 data: 0.0003 [11-25 10:54:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 417/1669] eta: 0:19:21 tlr: 0.00016 tnm: 0.24 Lm: 6.311 (6.311) Lt: 5.545 (5.545) Accm: 4.18 (4.18) Acct: 6.49 (6.49) proj_loss: -0.6013 (-0.6013) time: 0.9270 data: 0.0002 [11-25 10:54:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 417/1669] eta: 0:19:21 tlr: 0.00016 tnm: 0.24 Lm: 6.441 (6.441) Lt: 5.703 (5.703) Accm: 3.72 (3.72) Acct: 5.70 (5.70) proj_loss: -0.6013 (-0.6013) time: 0.9271 data: 0.0002 [11-25 10:54:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 417/1669] eta: 0:19:21 tlr: 0.00016 tnm: 0.24 Lm: 6.353 (6.353) Lt: 5.607 (5.607) Accm: 3.58 (3.58) Acct: 5.75 (5.75) proj_loss: -0.6103 (-0.6103) time: 0.9270 data: 0.0003 [11-25 10:54:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 417/1669] eta: 0:19:21 tlr: 0.00016 tnm: 0.24 Lm: 6.480 (6.480) Lt: 5.669 (5.669) Accm: 3.34 (3.34) Acct: 5.63 (5.63) proj_loss: -0.6231 (-0.6231) time: 0.9270 data: 0.0002 [11-25 10:54:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 417/1669] eta: 0:19:21 tlr: 0.00016 tnm: 0.24 Lm: 6.420 (6.420) Lt: 5.633 (5.633) Accm: 3.56 (3.56) Acct: 5.73 (5.73) proj_loss: -0.5846 (-0.5846) time: 0.9271 data: 0.0003 [11-25 10:54:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 417/1669] eta: 0:19:21 tlr: 0.00016 tnm: 0.24 Lm: 6.457 (6.457) Lt: 5.649 (5.649) Accm: 3.65 (3.65) Acct: 5.97 (5.97) proj_loss: -0.5949 (-0.5949) time: 0.9271 data: 0.0003 [11-25 10:54:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 417/1669] eta: 0:19:21 tlr: 0.00016 tnm: 0.24 Lm: 6.419 (6.419) Lt: 5.703 (5.703) Accm: 3.39 (3.39) Acct: 5.44 (5.44) proj_loss: -0.6225 (-0.6225) time: 0.9271 data: 0.0003 [11-25 11:01:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 834/1669] eta: 0:12:54 tlr: 0.00016 tnm: 0.23 Lm: 6.496 (6.452) Lt: 5.759 (5.744) Accm: 3.15 (3.31) Acct: 4.82 (5.21) proj_loss: -0.6228 (-0.6241) time: 0.9299 data: 0.0003 [11-25 11:01:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 834/1669] eta: 0:12:54 tlr: 0.00016 tnm: 0.23 Lm: 6.441 (6.467) Lt: 5.736 (5.692) Accm: 3.28 (3.32) Acct: 5.34 (5.44) proj_loss: -0.6332 (-0.6265) time: 0.9299 data: 0.0002 [11-25 11:01:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 834/1669] eta: 0:12:54 tlr: 0.00016 tnm: 0.23 Lm: 6.480 (6.455) Lt: 5.737 (5.725) Accm: 3.26 (3.33) Acct: 5.41 (5.18) proj_loss: -0.6263 (-0.6156) time: 0.9299 data: 0.0003 [11-25 11:01:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 834/1669] eta: 0:12:54 tlr: 0.00016 tnm: 0.23 Lm: 6.483 (6.455) Lt: 5.674 (5.679) Accm: 3.70 (3.71) Acct: 5.79 (5.85) proj_loss: -0.5978 (-0.6001) time: 0.9299 data: 0.0003 [11-25 11:01:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 834/1669] eta: 0:12:54 tlr: 0.00016 tnm: 0.23 Lm: 6.429 (6.405) Lt: 5.594 (5.670) Accm: 4.01 (3.89) Acct: 6.13 (6.03) proj_loss: -0.6206 (-0.6141) time: 0.9299 data: 0.0003 [11-25 11:01:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 834/1669] eta: 0:12:54 tlr: 0.00016 tnm: 0.23 Lm: 6.385 (6.403) Lt: 5.601 (5.592) Accm: 3.63 (3.59) Acct: 6.03 (5.91) proj_loss: -0.5912 (-0.5914) time: 0.9299 data: 0.0003 [11-25 11:01:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 834/1669] eta: 0:12:54 tlr: 0.00016 tnm: 0.23 Lm: 6.535 (6.500) Lt: 5.756 (5.742) Accm: 3.18 (3.32) Acct: 5.41 (5.25) proj_loss: -0.6028 (-0.6078) time: 0.9299 data: 0.0003 [11-25 11:01:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [ 834/1669] eta: 0:12:54 tlr: 0.00016 tnm: 0.23 Lm: 6.402 (6.438) Lt: 5.637 (5.645) Accm: 3.53 (3.61) Acct: 6.06 (6.00) proj_loss: -0.5908 (-0.5935) time: 0.9299 data: 0.0004 [11-25 11:07:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [1251/1669] eta: 0:06:27 tlr: 0.00016 tnm: 0.23 Lm: 6.466 (6.483) Lt: 5.681 (5.689) Accm: 3.39 (3.50) Acct: 5.73 (5.79) proj_loss: -0.5962 (-0.5955) time: 0.9286 data: 0.0003 [11-25 11:07:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [1251/1669] eta: 0:06:27 tlr: 0.00016 tnm: 0.23 Lm: 6.495 (6.497) Lt: 5.703 (5.754) Accm: 3.69 (3.48) Acct: 5.70 (5.50) proj_loss: -0.5942 (-0.5961) time: 0.9286 data: 0.0003 [11-25 11:07:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [1251/1669] eta: 0:06:27 tlr: 0.00016 tnm: 0.23 Lm: 6.495 (6.444) Lt: 5.738 (5.723) Accm: 3.80 (3.82) Acct: 5.65 (5.81) proj_loss: -0.6186 (-0.6147) time: 0.9285 data: 0.0002 [11-25 11:07:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [1251/1669] eta: 0:06:27 tlr: 0.00016 tnm: 0.23 Lm: 6.455 (6.468) Lt: 5.743 (5.714) Accm: 3.36 (3.35) Acct: 5.34 (5.41) proj_loss: -0.6322 (-0.6276) time: 0.9286 data: 0.0003 [11-25 11:07:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [1251/1669] eta: 0:06:27 tlr: 0.00016 tnm: 0.23 Lm: 6.531 (6.506) Lt: 5.749 (5.742) Accm: 3.18 (3.26) Acct: 5.15 (5.05) proj_loss: -0.6102 (-0.6103) time: 0.9286 data: 0.0003 [11-25 11:07:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [1251/1669] eta: 0:06:27 tlr: 0.00016 tnm: 0.23 Lm: 6.420 (6.457) Lt: 5.633 (5.652) Accm: 3.56 (3.45) Acct: 5.73 (5.69) proj_loss: -0.5981 (-0.5956) time: 0.9286 data: 0.0003 [11-25 11:07:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [1251/1669] eta: 0:06:27 tlr: 0.00016 tnm: 0.23 Lm: 6.378 (6.410) Lt: 5.670 (5.694) Accm: 3.56 (3.46) Acct: 5.61 (5.34) proj_loss: -0.6269 (-0.6188) time: 0.9286 data: 0.0003 [11-25 11:07:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [1251/1669] eta: 0:06:27 tlr: 0.00016 tnm: 0.23 Lm: 6.494 (6.462) Lt: 5.738 (5.738) Accm: 3.40 (3.39) Acct: 5.41 (5.41) proj_loss: -0.6225 (-0.6173) time: 0.9286 data: 0.0003 [11-25 11:14:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.492 (6.453) Lt: 5.718 (5.708) Accm: 3.66 (3.47) Acct: 5.85 (5.50) proj_loss: -0.6221 (-0.6145) time: 0.9300 data: 0.0015 [11-25 11:14:10] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 128/350] Total time: 0:25:48 (0.928 s / it) [11-25 11:14:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.372 (6.402) Lt: 5.603 (5.669) Accm: 3.54 (3.48) Acct: 5.61 (5.39) proj_loss: -0.6263 (-0.6158) time: 0.9300 data: 0.0015 [11-25 11:14:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.508 (6.505) Lt: 5.732 (5.755) Accm: 3.69 (3.42) Acct: 5.61 (5.41) proj_loss: -0.5978 (-0.5999) time: 0.9300 data: 0.0017 [11-25 11:14:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.446 (6.445) Lt: 5.613 (5.701) Accm: 3.61 (3.78) Acct: 5.30 (5.71) proj_loss: -0.6206 (-0.6172) time: 0.9299 data: 0.0015 [11-25 11:14:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.468 (6.511) Lt: 5.749 (5.766) Accm: 3.28 (3.23) Acct: 5.34 (5.22) proj_loss: -0.6311 (-0.6264) time: 0.9300 data: 0.0021 [11-25 11:14:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.455 (6.471) Lt: 5.665 (5.663) Accm: 3.50 (3.43) Acct: 5.58 (5.67) proj_loss: -0.5912 (-0.5933) time: 0.9300 data: 0.0018 [11-25 11:14:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.527 (6.487) Lt: 5.742 (5.737) Accm: 3.18 (3.34) Acct: 5.41 (5.17) proj_loss: -0.6176 (-0.6178) time: 0.9300 data: 0.0020 [11-25 11:14:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 128/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.402 (6.447) Lt: 5.637 (5.634) Accm: 3.53 (3.52) Acct: 5.72 (5.77) proj_loss: -0.5908 (-0.5921) time: 0.9300 data: 0.0019 [11-25 11:14:10] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 128/350] Total time: 0:25:48 (0.928 s / it) [11-25 11:14:10] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 128/350] Total time: 0:25:48 (0.928 s / it) [11-25 11:14:10] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 128/350] Total time: 0:25:48 (0.928 s / it) [11-25 11:14:10] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 128/350] Total time: 0:25:48 (0.928 s / it) [11-25 11:14:10] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 128/350] Total time: 0:25:48 (0.928 s / it) [11-25 11:14:10] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 128/350] Total time: 0:25:48 (0.928 s / it) [11-25 11:14:10] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 128/350] Total time: 0:25:48 (0.928 s / it) [11-25 11:14:10] (/home/user/VAR/train.py , line 276)=> [ep128] (training ) Lm: 6.462 (6.462), Lt: 5.703 (5.703), Acc m&t: 3.49 5.46, Remain: 3 days, 23:58:35, Finish: 2024-11-28 19:12 [11-25 11:14:10] (/home/user/VAR/train.py , line 276)=> [ep128] (training ) Lm: 6.462 (6.462), Lt: 5.703 (5.703), Acc m&t: 3.49 5.46, Remain: 3 days, 23:56:37, Finish: 2024-11-28 19:10 [11-25 11:14:10] (/home/user/VAR/train.py , line 276)=> [ep128] (training ) Lm: 6.462 (6.462), Lt: 5.703 (5.703), Acc m&t: 3.49 5.46, Remain: 3 days, 23:56:37, Finish: 2024-11-28 19:10 [11-25 11:14:10] (/home/user/VAR/train.py , line 276)=> [ep128] (training ) Lm: 6.462 (6.462), Lt: 5.703 (5.703), Acc m&t: 3.49 5.46, Remain: 3 days, 23:58:34, Finish: 2024-11-28 19:12 [11-25 11:14:10] (/home/user/VAR/train.py , line 276)=> [ep128] (training ) Lm: 6.462 (6.462), Lt: 5.703 (5.703), Acc m&t: 3.49 5.46, Remain: 3 days, 23:56:30, Finish: 2024-11-28 19:10 [11-25 11:14:10] (/home/user/VAR/train.py , line 276)=> [ep128] (training ) Lm: 6.462 (6.462), Lt: 5.703 (5.703), Acc m&t: 3.49 5.46, Remain: 3 days, 23:57:39, Finish: 2024-11-28 19:11 [11-25 11:14:10] (/home/user/VAR/train.py , line 276)=> [ep128] (training ) Lm: 6.462 (6.462), Lt: 5.703 (5.703), Acc m&t: 3.49 5.46, Remain: 3 days, 23:57:13, Finish: 2024-11-28 19:11 [11-25 11:14:10] (/home/user/VAR/train.py , line 276)=> [ep128] (training ) Lm: 6.462 (6.462), Lt: 5.703 (5.703), Acc m&t: 3.49 5.46, Remain: 3 days, 23:57:08, Finish: 2024-11-28 19:11 [11-25 11:14:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 0/1669] eta: 0:25:15 tlr: 0.00016 tnm: 0.24 Lm: 6.751 (6.751) Lt: 6.057 (6.057) Accm: 2.91 (2.91) Acct: 4.30 (4.30) proj_loss: -0.6053 (-0.6053) time: 0.9083 data: 0.0003 [11-25 11:14:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 0/1669] eta: 0:25:17 tlr: 0.00016 tnm: 0.24 Lm: 6.393 (6.393) Lt: 5.603 (5.603) Accm: 3.74 (3.74) Acct: 6.16 (6.16) proj_loss: -0.5898 (-0.5898) time: 0.9094 data: 0.0003 [11-25 11:14:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 0/1669] eta: 0:25:18 tlr: 0.00016 tnm: 0.24 Lm: 5.970 (5.970) Lt: 5.209 (5.209) Accm: 5.49 (5.49) Acct: 8.09 (8.09) proj_loss: -0.6391 (-0.6391) time: 0.9096 data: 0.0004 [11-25 11:14:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 0/1669] eta: 0:25:18 tlr: 0.00016 tnm: 0.24 Lm: 6.573 (6.573) Lt: 5.762 (5.762) Accm: 3.23 (3.23) Acct: 5.23 (5.23) proj_loss: -0.6052 (-0.6052) time: 0.9100 data: 0.0004 [11-25 11:14:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 0/1669] eta: 0:25:12 tlr: 0.00016 tnm: 0.24 Lm: 6.587 (6.587) Lt: 5.897 (5.897) Accm: 3.31 (3.31) Acct: 5.17 (5.17) proj_loss: -0.6172 (-0.6172) time: 0.9062 data: 0.0004 [11-25 11:14:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 0/1669] eta: 0:25:18 tlr: 0.00016 tnm: 0.24 Lm: 6.312 (6.312) Lt: 5.510 (5.510) Accm: 4.08 (4.08) Acct: 6.16 (6.16) proj_loss: -0.5722 (-0.5722) time: 0.9101 data: 0.0004 [11-25 11:14:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 0/1669] eta: 0:25:19 tlr: 0.00016 tnm: 0.24 Lm: 6.313 (6.313) Lt: 5.553 (5.553) Accm: 4.17 (4.17) Acct: 6.54 (6.54) proj_loss: -0.6544 (-0.6544) time: 0.9102 data: 0.0004 [11-25 11:14:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 0/1669] eta: 0:25:19 tlr: 0.00016 tnm: 0.24 Lm: 6.719 (6.719) Lt: 6.058 (6.058) Accm: 2.78 (2.78) Acct: 4.03 (4.03) proj_loss: -0.5901 (-0.5901) time: 0.9102 data: 0.0003 [11-25 11:21:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 417/1669] eta: 0:20:34 tlr: 0.00016 tnm: 0.22 Lm: 6.598 (6.598) Lt: 5.872 (5.872) Accm: 3.10 (3.10) Acct: 4.55 (4.55) proj_loss: -0.5945 (-0.5945) time: 0.9275 data: 0.0003 [11-25 11:21:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 417/1669] eta: 0:20:34 tlr: 0.00016 tnm: 0.22 Lm: 6.497 (6.497) Lt: 5.729 (5.729) Accm: 3.33 (3.33) Acct: 5.49 (5.49) proj_loss: -0.6008 (-0.6008) time: 0.9275 data: 0.0002 [11-25 11:21:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 417/1669] eta: 0:20:34 tlr: 0.00016 tnm: 0.22 Lm: 6.201 (6.201) Lt: 5.452 (5.452) Accm: 4.51 (4.51) Acct: 6.63 (6.63) proj_loss: -0.6405 (-0.6405) time: 0.9275 data: 0.0003 [11-25 11:21:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 417/1669] eta: 0:20:34 tlr: 0.00016 tnm: 0.22 Lm: 6.339 (6.339) Lt: 5.543 (5.543) Accm: 3.93 (3.93) Acct: 6.25 (6.25) proj_loss: -0.5676 (-0.5676) time: 0.9275 data: 0.0003 [11-25 11:21:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 417/1669] eta: 0:20:34 tlr: 0.00016 tnm: 0.22 Lm: 6.712 (6.712) Lt: 6.015 (6.015) Accm: 2.78 (2.78) Acct: 3.96 (3.96) proj_loss: -0.6176 (-0.6176) time: 0.9275 data: 0.0003 [11-25 11:21:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 417/1669] eta: 0:20:34 tlr: 0.00016 tnm: 0.22 Lm: 6.532 (6.532) Lt: 5.829 (5.829) Accm: 3.45 (3.45) Acct: 5.53 (5.53) proj_loss: -0.6197 (-0.6197) time: 0.9275 data: 0.0003 [11-25 11:21:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 417/1669] eta: 0:20:34 tlr: 0.00016 tnm: 0.22 Lm: 6.567 (6.567) Lt: 5.787 (5.787) Accm: 3.23 (3.23) Acct: 5.20 (5.20) proj_loss: -0.6120 (-0.6120) time: 0.9275 data: 0.0002 [11-25 11:21:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 417/1669] eta: 0:20:34 tlr: 0.00016 tnm: 0.22 Lm: 6.271 (6.271) Lt: 5.477 (5.477) Accm: 4.21 (4.21) Acct: 6.85 (6.85) proj_loss: -0.6316 (-0.6316) time: 0.9275 data: 0.0003 [11-25 11:27:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 834/1669] eta: 0:13:19 tlr: 0.00016 tnm: 0.23 Lm: 6.313 (6.335) Lt: 5.553 (5.563) Accm: 4.17 (3.80) Acct: 6.54 (6.13) proj_loss: -0.6132 (-0.6255) time: 0.9268 data: 0.0003 [11-25 11:27:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 834/1669] eta: 0:13:19 tlr: 0.00016 tnm: 0.23 Lm: 6.432 (6.283) Lt: 5.604 (5.503) Accm: 3.53 (4.15) Acct: 5.58 (6.28) proj_loss: -0.6391 (-0.6262) time: 0.9268 data: 0.0003 [11-25 11:27:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 834/1669] eta: 0:13:19 tlr: 0.00016 tnm: 0.23 Lm: 6.562 (6.498) Lt: 5.762 (5.742) Accm: 3.23 (3.39) Acct: 5.20 (5.20) proj_loss: -0.6068 (-0.6103) time: 0.9268 data: 0.0002 [11-25 11:27:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 834/1669] eta: 0:13:19 tlr: 0.00016 tnm: 0.23 Lm: 6.365 (6.442) Lt: 5.576 (5.675) Accm: 3.79 (3.52) Acct: 6.16 (5.54) proj_loss: -0.5722 (-0.5784) time: 0.9268 data: 0.0003 [11-25 11:27:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 834/1669] eta: 0:13:19 tlr: 0.00016 tnm: 0.23 Lm: 6.477 (6.506) Lt: 5.687 (5.750) Accm: 3.42 (3.26) Acct: 5.06 (4.94) proj_loss: -0.5934 (-0.5941) time: 0.9268 data: 0.0003 [11-25 11:27:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 834/1669] eta: 0:13:19 tlr: 0.00016 tnm: 0.23 Lm: 6.527 (6.531) Lt: 5.792 (5.817) Accm: 3.31 (3.34) Acct: 5.17 (5.27) proj_loss: -0.6172 (-0.6120) time: 0.9268 data: 0.0003 [11-25 11:27:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 834/1669] eta: 0:13:19 tlr: 0.00016 tnm: 0.23 Lm: 6.417 (6.470) Lt: 5.701 (5.719) Accm: 3.31 (3.32) Acct: 5.13 (5.37) proj_loss: -0.6109 (-0.6041) time: 0.9269 data: 0.0003 [11-25 11:27:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [ 834/1669] eta: 0:13:19 tlr: 0.00016 tnm: 0.23 Lm: 6.672 (6.677) Lt: 5.973 (5.956) Accm: 2.91 (2.87) Acct: 4.30 (4.19) proj_loss: -0.6053 (-0.6084) time: 0.9268 data: 0.0004 [11-25 11:33:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [1251/1669] eta: 0:06:36 tlr: 0.00016 tnm: 0.23 Lm: 6.640 (6.625) Lt: 5.905 (5.891) Accm: 2.98 (3.04) Acct: 4.48 (4.67) proj_loss: -0.6054 (-0.6077) time: 0.9298 data: 0.0003 [11-25 11:33:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [1251/1669] eta: 0:06:36 tlr: 0.00016 tnm: 0.23 Lm: 6.301 (6.255) Lt: 5.491 (5.472) Accm: 3.71 (4.09) Acct: 5.72 (6.17) proj_loss: -0.6337 (-0.6267) time: 0.9298 data: 0.0003 [11-25 11:33:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [1251/1669] eta: 0:06:36 tlr: 0.00016 tnm: 0.23 Lm: 6.542 (6.504) Lt: 5.775 (5.754) Accm: 3.48 (3.51) Acct: 5.22 (5.43) proj_loss: -0.6128 (-0.6162) time: 0.9298 data: 0.0003 [11-25 11:33:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [1251/1669] eta: 0:06:36 tlr: 0.00016 tnm: 0.23 Lm: 6.388 (6.376) Lt: 5.644 (5.619) Accm: 3.98 (3.80) Acct: 6.27 (6.10) proj_loss: -0.6138 (-0.6227) time: 0.9298 data: 0.0003 [11-25 11:33:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [1251/1669] eta: 0:06:36 tlr: 0.00016 tnm: 0.23 Lm: 6.502 (6.483) Lt: 5.776 (5.745) Accm: 3.36 (3.35) Acct: 5.48 (5.40) proj_loss: -0.6069 (-0.6066) time: 0.9298 data: 0.0003 [11-25 11:33:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [1251/1669] eta: 0:06:36 tlr: 0.00016 tnm: 0.23 Lm: 6.405 (6.438) Lt: 5.652 (5.690) Accm: 3.47 (3.40) Acct: 5.34 (5.41) proj_loss: -0.6113 (-0.6095) time: 0.9298 data: 0.0005 [11-25 11:33:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [1251/1669] eta: 0:06:36 tlr: 0.00016 tnm: 0.23 Lm: 6.344 (6.412) Lt: 5.545 (5.635) Accm: 3.75 (3.57) Acct: 5.82 (5.53) proj_loss: -0.5860 (-0.5883) time: 0.9298 data: 0.0003 [11-25 11:33:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [1251/1669] eta: 0:06:36 tlr: 0.00016 tnm: 0.23 Lm: 6.436 (6.478) Lt: 5.647 (5.715) Accm: 3.50 (3.37) Acct: 5.37 (5.12) proj_loss: -0.5961 (-0.5994) time: 0.9298 data: 0.0003 [11-25 11:40:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.305 (6.265) Lt: 5.599 (5.497) Accm: 3.80 (4.03) Acct: 5.58 (6.05) proj_loss: -0.6283 (-0.6254) time: 0.9299 data: 0.0020 [11-25 11:40:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.562 (6.520) Lt: 5.788 (5.769) Accm: 3.23 (3.37) Acct: 5.20 (5.20) proj_loss: -0.6118 (-0.6154) time: 0.9299 data: 0.0022 [11-25 11:40:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.365 (6.406) Lt: 5.576 (5.631) Accm: 3.73 (3.60) Acct: 5.48 (5.46) proj_loss: -0.5776 (-0.5862) time: 0.9299 data: 0.0019 [11-25 11:40:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.395 (6.452) Lt: 5.607 (5.689) Accm: 3.58 (3.42) Acct: 5.58 (5.21) proj_loss: -0.5989 (-0.6070) time: 0.9299 data: 0.0018 [11-25 11:40:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.608 (6.591) Lt: 5.837 (5.851) Accm: 3.04 (3.17) Acct: 4.65 (4.88) proj_loss: -0.6055 (-0.6084) time: 0.9299 data: 0.0018 [11-25 11:40:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.462 (6.409) Lt: 5.735 (5.662) Accm: 3.79 (3.68) Acct: 5.99 (5.85) proj_loss: -0.6144 (-0.6230) time: 0.9299 data: 0.0018 [11-25 11:40:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.393 (6.420) Lt: 5.603 (5.642) Accm: 3.63 (3.45) Acct: 5.54 (5.55) proj_loss: -0.6109 (-0.6094) time: 0.9299 data: 0.0016 [11-25 11:40:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 129/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.478 (6.471) Lt: 5.760 (5.714) Accm: 3.41 (3.46) Acct: 5.75 (5.47) proj_loss: -0.6172 (-0.6111) time: 0.9299 data: 0.0016 [11-25 11:40:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 129/350] Total time: 0:26:13 (0.943 s / it) [11-25 11:40:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 129/350] Total time: 0:26:13 (0.943 s / it) [11-25 11:40:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 129/350] Total time: 0:26:13 (0.943 s / it) [11-25 11:40:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 129/350] Total time: 0:26:13 (0.943 s / it) [11-25 11:40:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 129/350] Total time: 0:26:13 (0.943 s / it) [11-25 11:40:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 129/350] Total time: 0:26:13 (0.943 s / it) [11-25 11:40:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 129/350] Total time: 0:26:13 (0.943 s / it) [11-25 11:40:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 129/350] Total time: 0:26:13 (0.943 s / it) [11-25 11:42:32] (home/user/VAR/trainer.py, line 114)=> FID: 3.414891966449659 [11-25 11:42:33] (/home/user/VAR/train.py , line 259)=> [*] [ep129] (val 50000) Lm: 6.4741, Lt: 5.7237, Acc m&t: 3.43 5.33, Val cost: 128.44s [11-25 11:42:33] (/home/user/VAR/train.py , line 264)=> [saving ckpt] ... [saving ckpt](*) finished! @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth [11-25 11:43:35] (/home/user/VAR/train.py , line 276)=> [ep129] (training ) Lm: 6.462 (6.474), Lt: 5.703 (5.724), Acc m&t: 3.49 5.46, Remain: 3 days, 23:28:29, Finish: 2024-11-28 19:08 [11-25 11:43:35] (/home/user/VAR/train.py , line 276)=> [ep129] (training ) Lm: 6.462 (6.474), Lt: 5.703 (5.724), Acc m&t: 3.49 5.46, Remain: 3 days, 23:28:30, Finish: 2024-11-28 19:08 [11-25 11:43:35] (/home/user/VAR/train.py , line 276)=> [ep129] (training ) Lm: 6.462 (6.474), Lt: 5.703 (5.724), Acc m&t: 3.49 5.46, Remain: 3 days, 23:29:05, Finish: 2024-11-28 19:09 [11-25 11:43:35] (/home/user/VAR/train.py , line 276)=> [ep129] (training ) Lm: 6.462 (6.474), Lt: 5.703 (5.724), Acc m&t: 3.49 5.46, Remain: 3 days, 23:29:27, Finish: 2024-11-28 19:09 [11-25 11:43:35] (/home/user/VAR/train.py , line 276)=> [ep129] (training ) Lm: 6.462 (6.474), Lt: 5.703 (5.724), Acc m&t: 3.49 5.46, Remain: 3 days, 23:28:21, Finish: 2024-11-28 19:08 [11-25 11:43:35] (/home/user/VAR/train.py , line 276)=> [ep129] (training ) Lm: 6.462 (6.474), Lt: 5.703 (5.724), Acc m&t: 3.49 5.46, Remain: 3 days, 23:28:08, Finish: 2024-11-28 19:08 [11-25 11:43:35] (/home/user/VAR/train.py , line 276)=> [ep129] (training ) Lm: 6.462 (6.474), Lt: 5.703 (5.724), Acc m&t: 3.49 5.46, Remain: 3 days, 23:28:26, Finish: 2024-11-28 19:08 [11-25 11:43:35] (/home/user/VAR/train.py , line 276)=> [ep129] (training ) Lm: 6.462 (6.474), Lt: 5.703 (5.724), Acc m&t: 3.49 5.46, Remain: 3 days, 23:28:56, Finish: 2024-11-28 19:09 [11-25 11:43:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 0/1669] eta: 0:24:45 tlr: 0.00016 tnm: 0.23 Lm: 6.534 (6.534) Lt: 5.806 (5.806) Accm: 2.83 (2.83) Acct: 4.61 (4.61) proj_loss: -0.6391 (-0.6391) time: 0.8902 data: 0.0005 [11-25 11:43:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 0/1669] eta: 0:24:45 tlr: 0.00016 tnm: 0.23 Lm: 6.611 (6.611) Lt: 5.831 (5.831) Accm: 2.70 (2.70) Acct: 4.27 (4.27) proj_loss: -0.6206 (-0.6206) time: 0.8902 data: 0.0004 [11-25 11:43:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 0/1669] eta: 0:24:46 tlr: 0.00016 tnm: 0.23 Lm: 6.240 (6.240) Lt: 5.455 (5.455) Accm: 4.14 (4.14) Acct: 6.68 (6.68) proj_loss: -0.6007 (-0.6007) time: 0.8905 data: 0.0004 [11-25 11:43:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 0/1669] eta: 0:24:45 tlr: 0.00016 tnm: 0.23 Lm: 6.400 (6.400) Lt: 5.693 (5.693) Accm: 3.58 (3.58) Acct: 5.82 (5.82) proj_loss: -0.6187 (-0.6187) time: 0.8900 data: 0.0004 [11-25 11:43:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 0/1669] eta: 0:24:46 tlr: 0.00016 tnm: 0.23 Lm: 6.644 (6.644) Lt: 5.940 (5.940) Accm: 2.81 (2.81) Acct: 4.51 (4.51) proj_loss: -0.6356 (-0.6356) time: 0.8905 data: 0.0004 [11-25 11:43:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 0/1669] eta: 0:24:46 tlr: 0.00016 tnm: 0.23 Lm: 6.496 (6.496) Lt: 5.755 (5.755) Accm: 3.18 (3.18) Acct: 4.72 (4.72) proj_loss: -0.6198 (-0.6198) time: 0.8904 data: 0.0004 [11-25 11:43:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 0/1669] eta: 0:26:06 tlr: 0.00016 tnm: 0.23 Lm: 6.262 (6.262) Lt: 5.455 (5.455) Accm: 4.17 (4.17) Acct: 6.47 (6.47) proj_loss: -0.6373 (-0.6373) time: 0.9385 data: 0.0003 [11-25 11:43:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 0/1669] eta: 0:25:51 tlr: 0.00016 tnm: 0.23 Lm: 6.486 (6.486) Lt: 5.715 (5.715) Accm: 3.54 (3.54) Acct: 6.10 (6.10) proj_loss: -0.6490 (-0.6490) time: 0.9296 data: 0.0004 [11-25 11:50:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 417/1669] eta: 0:19:21 tlr: 0.00016 tnm: 0.23 Lm: 6.258 (6.258) Lt: 5.467 (5.467) Accm: 4.61 (4.61) Acct: 7.56 (7.56) proj_loss: -0.6355 (-0.6355) time: 0.9294 data: 0.0003 [11-25 11:50:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 417/1669] eta: 0:19:21 tlr: 0.00016 tnm: 0.23 Lm: 6.460 (6.460) Lt: 5.698 (5.698) Accm: 3.40 (3.40) Acct: 5.11 (5.11) proj_loss: -0.6318 (-0.6318) time: 0.9294 data: 0.0003 [11-25 11:50:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 417/1669] eta: 0:19:21 tlr: 0.00016 tnm: 0.23 Lm: 6.393 (6.393) Lt: 5.634 (5.634) Accm: 3.82 (3.82) Acct: 6.08 (6.08) proj_loss: -0.6342 (-0.6342) time: 0.9294 data: 0.0003 [11-25 11:50:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 417/1669] eta: 0:19:21 tlr: 0.00016 tnm: 0.23 Lm: 6.559 (6.559) Lt: 5.808 (5.808) Accm: 2.90 (2.90) Acct: 4.53 (4.53) proj_loss: -0.6097 (-0.6097) time: 0.9295 data: 0.0003 [11-25 11:50:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 417/1669] eta: 0:19:21 tlr: 0.00016 tnm: 0.23 Lm: 6.546 (6.546) Lt: 5.838 (5.838) Accm: 3.02 (3.02) Acct: 4.73 (4.73) proj_loss: -0.6202 (-0.6202) time: 0.9294 data: 0.0003 [11-25 11:50:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 417/1669] eta: 0:19:21 tlr: 0.00016 tnm: 0.23 Lm: 6.518 (6.518) Lt: 5.820 (5.820) Accm: 3.18 (3.18) Acct: 4.96 (4.96) proj_loss: -0.6279 (-0.6279) time: 0.9295 data: 0.0003 [11-25 11:50:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 417/1669] eta: 0:19:21 tlr: 0.00016 tnm: 0.23 Lm: 6.333 (6.333) Lt: 5.570 (5.570) Accm: 3.77 (3.77) Acct: 5.89 (5.89) proj_loss: -0.6029 (-0.6029) time: 0.9295 data: 0.0003 [11-25 11:50:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 417/1669] eta: 0:19:21 tlr: 0.00016 tnm: 0.23 Lm: 6.552 (6.552) Lt: 5.779 (5.779) Accm: 3.16 (3.16) Acct: 5.15 (5.15) proj_loss: -0.6178 (-0.6178) time: 0.9294 data: 0.0002 [11-25 11:56:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.24 Lm: 6.400 (6.498) Lt: 5.693 (5.733) Accm: 3.29 (3.21) Acct: 4.89 (5.06) proj_loss: -0.6187 (-0.6213) time: 0.9279 data: 0.0003 [11-25 11:56:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.24 Lm: 6.424 (6.424) Lt: 5.641 (5.643) Accm: 3.63 (3.52) Acct: 5.51 (5.52) proj_loss: -0.6198 (-0.6239) time: 0.9279 data: 0.0002 [11-25 11:56:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.24 Lm: 6.499 (6.428) Lt: 5.760 (5.676) Accm: 3.47 (3.58) Acct: 5.68 (5.68) proj_loss: -0.6373 (-0.6382) time: 0.9278 data: 0.0003 [11-25 11:56:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.24 Lm: 6.508 (6.446) Lt: 5.785 (5.701) Accm: 3.10 (3.25) Acct: 4.79 (5.08) proj_loss: -0.5987 (-0.6041) time: 0.9278 data: 0.0002 [11-25 11:56:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.24 Lm: 6.465 (6.327) Lt: 5.672 (5.535) Accm: 3.54 (4.14) Acct: 6.10 (6.76) proj_loss: -0.6221 (-0.6259) time: 0.9279 data: 0.0003 [11-25 11:56:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.24 Lm: 6.534 (6.483) Lt: 5.806 (5.755) Accm: 3.22 (3.31) Acct: 4.86 (5.22) proj_loss: -0.6014 (-0.6125) time: 0.9279 data: 0.0003 [11-25 11:56:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.24 Lm: 6.413 (6.359) Lt: 5.597 (5.579) Accm: 3.85 (3.80) Acct: 6.13 (5.97) proj_loss: -0.6007 (-0.6000) time: 0.9279 data: 0.0003 [11-25 11:56:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.24 Lm: 6.643 (6.560) Lt: 5.870 (5.837) Accm: 3.04 (3.13) Acct: 4.75 (4.89) proj_loss: -0.6202 (-0.6234) time: 0.9279 data: 0.0003 [11-25 12:02:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.23 Lm: 6.521 (6.520) Lt: 5.790 (5.805) Accm: 3.29 (3.27) Acct: 5.08 (5.10) proj_loss: -0.6255 (-0.6253) time: 0.9302 data: 0.0003 [11-25 12:02:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.23 Lm: 6.387 (6.389) Lt: 5.593 (5.618) Accm: 3.63 (3.55) Acct: 5.60 (5.56) proj_loss: -0.6318 (-0.6308) time: 0.9302 data: 0.0002 [11-25 12:02:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.23 Lm: 6.511 (6.455) Lt: 5.733 (5.684) Accm: 3.32 (3.48) Acct: 5.66 (5.67) proj_loss: -0.6342 (-0.6324) time: 0.9302 data: 0.0003 [11-25 12:02:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.23 Lm: 6.406 (6.332) Lt: 5.643 (5.555) Accm: 3.43 (3.94) Acct: 5.63 (6.36) proj_loss: -0.6258 (-0.6268) time: 0.9302 data: 0.0004 [11-25 12:02:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.23 Lm: 6.522 (6.490) Lt: 5.804 (5.766) Accm: 3.46 (3.41) Acct: 5.35 (5.38) proj_loss: -0.6168 (-0.6174) time: 0.9302 data: 0.0003 [11-25 12:02:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.23 Lm: 6.419 (6.404) Lt: 5.641 (5.622) Accm: 3.63 (3.65) Acct: 5.61 (5.72) proj_loss: -0.5975 (-0.5966) time: 0.9302 data: 0.0003 [11-25 12:02:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.23 Lm: 6.451 (6.433) Lt: 5.734 (5.696) Accm: 3.46 (3.39) Acct: 5.17 (5.20) proj_loss: -0.6097 (-0.6128) time: 0.9302 data: 0.0002 [11-25 12:02:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.23 Lm: 6.418 (6.483) Lt: 5.689 (5.721) Accm: 3.44 (3.31) Acct: 5.34 (5.24) proj_loss: -0.6178 (-0.6174) time: 0.9302 data: 0.0002 [11-25 12:09:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.23 Lm: 6.381 (6.387) Lt: 5.596 (5.614) Accm: 3.64 (3.65) Acct: 5.68 (5.71) proj_loss: -0.6198 (-0.6245) time: 0.9287 data: 0.0019 [11-25 12:09:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.23 Lm: 6.400 (6.453) Lt: 5.685 (5.692) Accm: 3.58 (3.45) Acct: 5.79 (5.45) proj_loss: -0.6187 (-0.6205) time: 0.9287 data: 0.0020 [11-25 12:09:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.23 Lm: 6.621 (6.540) Lt: 5.857 (5.816) Accm: 3.25 (3.26) Acct: 5.10 (5.10) proj_loss: -0.6216 (-0.6245) time: 0.9287 data: 0.0022 [11-25 12:09:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.23 Lm: 6.510 (6.486) Lt: 5.802 (5.752) Accm: 3.54 (3.43) Acct: 5.13 (5.33) proj_loss: -0.6133 (-0.6166) time: 0.9287 data: 0.0017 [11-25 12:09:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.23 Lm: 6.508 (6.456) Lt: 5.785 (5.716) Accm: 3.21 (3.36) Acct: 4.79 (5.10) proj_loss: -0.5987 (-0.6075) time: 0.9287 data: 0.0016 [11-25 12:09:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.23 Lm: 6.465 (6.401) Lt: 5.672 (5.640) Accm: 3.32 (3.75) Acct: 5.17 (6.05) proj_loss: -0.6294 (-0.6282) time: 0.9287 data: 0.0017 [11-25 12:09:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.23 Lm: 6.426 (6.439) Lt: 5.685 (5.678) Accm: 3.41 (3.49) Acct: 5.10 (5.45) proj_loss: -0.6007 (-0.5997) time: 0.9287 data: 0.0016 [11-25 12:09:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 130/350] Total time: 0:25:50 (0.929 s / it) [11-25 12:09:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.23 Lm: 6.499 (6.452) Lt: 5.706 (5.684) Accm: 3.47 (3.56) Acct: 5.68 (5.83) proj_loss: -0.6311 (-0.6274) time: 0.9288 data: 0.0015 [11-25 12:09:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 130/350] Total time: 0:25:50 (0.929 s / it) [11-25 12:09:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 130/350] Total time: 0:25:50 (0.929 s / it) [11-25 12:09:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 130/350] Total time: 0:25:50 (0.929 s / it) [11-25 12:09:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 130/350] Total time: 0:25:50 (0.929 s / it) [11-25 12:09:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 130/350] Total time: 0:25:50 (0.929 s / it) [11-25 12:09:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 130/350] Total time: 0:25:50 (0.929 s / it) [11-25 12:09:25] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 130/350] Total time: 0:25:50 (0.929 s / it) [11-25 12:09:25] (/home/user/VAR/train.py , line 276)=> [ep130] (training ) Lm: 6.462 (6.463), Lt: 5.703 (5.708), Acc m&t: 3.49 5.51, Remain: 3 days, 22:58:05, Finish: 2024-11-28 19:07 [11-25 12:09:25] (/home/user/VAR/train.py , line 276)=> [ep130] (training ) Lm: 6.462 (6.463), Lt: 5.703 (5.708), Acc m&t: 3.49 5.51, Remain: 3 days, 22:57:22, Finish: 2024-11-28 19:06 [11-25 12:09:25] (/home/user/VAR/train.py , line 276)=> [ep130] (training ) Lm: 6.462 (6.463), Lt: 5.703 (5.708), Acc m&t: 3.49 5.51, Remain: 3 days, 22:57:50, Finish: 2024-11-28 19:07 [11-25 12:09:25] (/home/user/VAR/train.py , line 276)=> [ep130] (training ) Lm: 6.462 (6.463), Lt: 5.703 (5.708), Acc m&t: 3.49 5.51, Remain: 3 days, 22:57:03, Finish: 2024-11-28 19:06 [11-25 12:09:25] (/home/user/VAR/train.py , line 276)=> [ep130] (training ) Lm: 6.462 (6.463), Lt: 5.703 (5.708), Acc m&t: 3.49 5.51, Remain: 3 days, 22:58:35, Finish: 2024-11-28 19:08 [11-25 12:09:25] (/home/user/VAR/train.py , line 276)=> [ep130] (training ) Lm: 6.462 (6.463), Lt: 5.703 (5.708), Acc m&t: 3.49 5.51, Remain: 3 days, 22:57:55, Finish: 2024-11-28 19:07 [11-25 12:09:25] (/home/user/VAR/train.py , line 276)=> [ep130] (training ) Lm: 6.462 (6.463), Lt: 5.703 (5.708), Acc m&t: 3.49 5.51, Remain: 3 days, 22:58:53, Finish: 2024-11-28 19:08 [11-25 12:09:25] (/home/user/VAR/train.py , line 276)=> [ep130] (training ) Lm: 6.462 (6.463), Lt: 5.703 (5.708), Acc m&t: 3.49 5.51, Remain: 3 days, 22:58:00, Finish: 2024-11-28 19:07 [11-25 12:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 0/1669] eta: 0:24:41 tlr: 0.00016 tnm: 0.23 Lm: 6.308 (6.308) Lt: 5.432 (5.432) Accm: 3.76 (3.76) Acct: 6.10 (6.10) proj_loss: -0.6028 (-0.6028) time: 0.8878 data: 0.0004 [11-25 12:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 0/1669] eta: 0:24:41 tlr: 0.00016 tnm: 0.23 Lm: 6.104 (6.104) Lt: 5.361 (5.361) Accm: 4.82 (4.82) Acct: 7.47 (7.47) proj_loss: -0.6351 (-0.6351) time: 0.8876 data: 0.0005 [11-25 12:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 0/1669] eta: 0:25:46 tlr: 0.00016 tnm: 0.23 Lm: 6.480 (6.480) Lt: 5.724 (5.724) Accm: 3.21 (3.21) Acct: 5.30 (5.30) proj_loss: -0.6268 (-0.6268) time: 0.9263 data: 0.0004 [11-25 12:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 0/1669] eta: 0:24:41 tlr: 0.00016 tnm: 0.23 Lm: 6.540 (6.540) Lt: 5.738 (5.738) Accm: 3.26 (3.26) Acct: 4.96 (4.96) proj_loss: -0.5950 (-0.5950) time: 0.8879 data: 0.0004 [11-25 12:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 0/1669] eta: 0:24:42 tlr: 0.00016 tnm: 0.23 Lm: 6.510 (6.510) Lt: 5.673 (5.673) Accm: 3.35 (3.35) Acct: 5.44 (5.44) proj_loss: -0.5944 (-0.5944) time: 0.8880 data: 0.0003 [11-25 12:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 0/1669] eta: 0:24:40 tlr: 0.00016 tnm: 0.23 Lm: 6.537 (6.537) Lt: 5.779 (5.779) Accm: 3.23 (3.23) Acct: 5.10 (5.10) proj_loss: -0.5901 (-0.5901) time: 0.8871 data: 0.0003 [11-25 12:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 0/1669] eta: 0:24:53 tlr: 0.00016 tnm: 0.23 Lm: 6.620 (6.620) Lt: 5.884 (5.884) Accm: 2.87 (2.87) Acct: 4.89 (4.89) proj_loss: -0.6088 (-0.6088) time: 0.8947 data: 0.0004 [11-25 12:09:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 0/1669] eta: 0:24:41 tlr: 0.00016 tnm: 0.23 Lm: 6.234 (6.234) Lt: 5.416 (5.416) Accm: 4.08 (4.08) Acct: 6.40 (6.40) proj_loss: -0.6284 (-0.6284) time: 0.8879 data: 0.0004 [11-25 12:15:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.24 Lm: 6.374 (6.374) Lt: 5.549 (5.549) Accm: 3.80 (3.80) Acct: 5.77 (5.77) proj_loss: -0.6046 (-0.6046) time: 0.9300 data: 0.0003 [11-25 12:15:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.24 Lm: 6.488 (6.488) Lt: 5.695 (5.695) Accm: 3.25 (3.25) Acct: 5.10 (5.10) proj_loss: -0.6145 (-0.6145) time: 0.9300 data: 0.0003 [11-25 12:15:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.24 Lm: 6.596 (6.596) Lt: 5.850 (5.850) Accm: 2.98 (2.98) Acct: 4.77 (4.77) proj_loss: -0.5954 (-0.5954) time: 0.9300 data: 0.0002 [11-25 12:15:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.24 Lm: 6.504 (6.504) Lt: 5.743 (5.743) Accm: 3.31 (3.31) Acct: 5.51 (5.51) proj_loss: -0.6101 (-0.6101) time: 0.9300 data: 0.0003 [11-25 12:15:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.24 Lm: 6.477 (6.477) Lt: 5.733 (5.733) Accm: 3.31 (3.31) Acct: 5.34 (5.34) proj_loss: -0.6038 (-0.6038) time: 0.9301 data: 0.0003 [11-25 12:15:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.24 Lm: 6.454 (6.454) Lt: 5.690 (5.690) Accm: 3.30 (3.30) Acct: 5.30 (5.30) proj_loss: -0.6141 (-0.6141) time: 0.9301 data: 0.0003 [11-25 12:15:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.24 Lm: 6.618 (6.618) Lt: 5.886 (5.886) Accm: 2.93 (2.93) Acct: 4.49 (4.49) proj_loss: -0.6151 (-0.6151) time: 0.9301 data: 0.0003 [11-25 12:15:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.24 Lm: 6.496 (6.496) Lt: 5.774 (5.774) Accm: 3.56 (3.56) Acct: 5.60 (5.60) proj_loss: -0.6186 (-0.6186) time: 0.9301 data: 0.0003 [11-25 12:22:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 834/1669] eta: 0:13:00 tlr: 0.00016 tnm: 0.24 Lm: 6.435 (6.471) Lt: 5.700 (5.697) Accm: 3.76 (3.46) Acct: 5.82 (5.34) proj_loss: -0.6261 (-0.6197) time: 0.9281 data: 0.0003 [11-25 12:22:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 834/1669] eta: 0:13:00 tlr: 0.00016 tnm: 0.24 Lm: 6.480 (6.572) Lt: 5.742 (5.848) Accm: 3.21 (3.12) Acct: 5.30 (4.91) proj_loss: -0.6032 (-0.6036) time: 0.9281 data: 0.0003 [11-25 12:22:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 834/1669] eta: 0:13:00 tlr: 0.00016 tnm: 0.24 Lm: 6.514 (6.449) Lt: 5.682 (5.641) Accm: 3.51 (3.63) Acct: 5.51 (5.68) proj_loss: -0.5946 (-0.6013) time: 0.9281 data: 0.0003 [11-25 12:22:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 834/1669] eta: 0:13:00 tlr: 0.00016 tnm: 0.24 Lm: 6.510 (6.551) Lt: 5.707 (5.803) Accm: 3.25 (3.07) Acct: 5.17 (4.96) proj_loss: -0.6204 (-0.6162) time: 0.9281 data: 0.0003 [11-25 12:22:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 834/1669] eta: 0:13:00 tlr: 0.00016 tnm: 0.24 Lm: 6.540 (6.583) Lt: 5.738 (5.826) Accm: 3.26 (3.09) Acct: 4.96 (4.88) proj_loss: -0.5950 (-0.6022) time: 0.9281 data: 0.0003 [11-25 12:22:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 834/1669] eta: 0:13:00 tlr: 0.00016 tnm: 0.24 Lm: 6.655 (6.659) Lt: 5.922 (5.916) Accm: 2.72 (2.87) Acct: 4.44 (4.55) proj_loss: -0.5901 (-0.5921) time: 0.9281 data: 0.0003 [11-25 12:22:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 834/1669] eta: 0:13:00 tlr: 0.00016 tnm: 0.24 Lm: 6.596 (6.535) Lt: 5.827 (5.771) Accm: 3.19 (3.27) Acct: 5.13 (5.38) proj_loss: -0.6113 (-0.6109) time: 0.9281 data: 0.0003 [11-25 12:22:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 834/1669] eta: 0:13:00 tlr: 0.00016 tnm: 0.24 Lm: 6.662 (6.551) Lt: 5.941 (5.830) Accm: 3.03 (3.38) Acct: 4.92 (5.37) proj_loss: -0.6351 (-0.6272) time: 0.9281 data: 0.0003 [11-25 12:28:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1251/1669] eta: 0:06:31 tlr: 0.00016 tnm: 0.23 Lm: 6.550 (6.523) Lt: 5.768 (5.771) Accm: 3.28 (3.42) Acct: 5.18 (5.39) proj_loss: -0.6186 (-0.6200) time: 1.0477 data: 0.0003 [11-25 12:28:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1251/1669] eta: 0:06:31 tlr: 0.00016 tnm: 0.23 Lm: 6.392 (6.440) Lt: 5.664 (5.679) Accm: 3.73 (3.52) Acct: 5.73 (5.41) proj_loss: -0.6147 (-0.6156) time: 1.0477 data: 0.0002 [11-25 12:28:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1251/1669] eta: 0:06:31 tlr: 0.00016 tnm: 0.23 Lm: 6.545 (6.558) Lt: 5.767 (5.809) Accm: 3.21 (3.09) Acct: 4.99 (4.92) proj_loss: -0.6201 (-0.6171) time: 1.0477 data: 0.0003 [11-25 12:28:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1251/1669] eta: 0:06:31 tlr: 0.00016 tnm: 0.23 Lm: 6.547 (6.576) Lt: 5.783 (5.826) Accm: 3.16 (3.08) Acct: 4.86 (4.85) proj_loss: -0.6046 (-0.6052) time: 1.0477 data: 0.0003 [11-25 12:28:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1251/1669] eta: 0:06:31 tlr: 0.00016 tnm: 0.23 Lm: 6.477 (6.519) Lt: 5.733 (5.794) Accm: 3.31 (3.34) Acct: 5.34 (5.17) proj_loss: -0.6026 (-0.6032) time: 1.0477 data: 0.0003 [11-25 12:28:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1251/1669] eta: 0:06:31 tlr: 0.00016 tnm: 0.23 Lm: 6.557 (6.492) Lt: 5.754 (5.695) Accm: 3.41 (3.45) Acct: 5.32 (5.44) proj_loss: -0.5930 (-0.5988) time: 1.0477 data: 0.0003 [11-25 12:28:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1251/1669] eta: 0:06:31 tlr: 0.00016 tnm: 0.23 Lm: 6.492 (6.479) Lt: 5.715 (5.713) Accm: 3.47 (3.42) Acct: 5.63 (5.64) proj_loss: -0.6105 (-0.6106) time: 1.0477 data: 0.0003 [11-25 12:28:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1251/1669] eta: 0:06:31 tlr: 0.00016 tnm: 0.23 Lm: 6.596 (6.586) Lt: 5.850 (5.845) Accm: 2.98 (3.07) Acct: 4.77 (4.88) proj_loss: -0.5954 (-0.5994) time: 1.0477 data: 0.0003 [11-25 12:35:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.595 (6.588) Lt: 5.869 (5.850) Accm: 3.00 (3.06) Acct: 4.44 (4.78) proj_loss: -0.5901 (-0.5961) time: 0.9295 data: 0.0016 [11-25 12:35:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 131/350] Total time: 0:26:03 (0.937 s / it) [11-25 12:35:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.435 (6.464) Lt: 5.700 (5.705) Accm: 3.70 (3.38) Acct: 5.65 (5.26) proj_loss: -0.6033 (-0.6111) time: 0.9295 data: 0.0016 [11-25 12:35:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.596 (6.504) Lt: 5.827 (5.747) Accm: 3.19 (3.35) Acct: 5.13 (5.48) proj_loss: -0.6098 (-0.6094) time: 0.9295 data: 0.0015 [11-25 12:35:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.480 (6.515) Lt: 5.742 (5.786) Accm: 3.42 (3.38) Acct: 5.37 (5.27) proj_loss: -0.6019 (-0.6023) time: 0.9296 data: 0.0020 [11-25 12:35:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.567 (6.532) Lt: 5.798 (5.777) Accm: 3.12 (3.36) Acct: 5.23 (5.36) proj_loss: -0.6193 (-0.6198) time: 0.9296 data: 0.0017 [11-25 12:35:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.514 (6.464) Lt: 5.682 (5.681) Accm: 3.51 (3.47) Acct: 5.30 (5.41) proj_loss: -0.5946 (-0.6050) time: 0.9295 data: 0.0014 [11-25 12:35:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.540 (6.552) Lt: 5.799 (5.821) Accm: 3.26 (3.14) Acct: 4.96 (4.99) proj_loss: -0.6141 (-0.6150) time: 0.9296 data: 0.0018 [11-25 12:35:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.580 (6.568) Lt: 5.827 (5.815) Accm: 3.16 (3.10) Acct: 4.82 (4.84) proj_loss: -0.6198 (-0.6106) time: 0.9296 data: 0.0016 [11-25 12:35:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 131/350] Total time: 0:26:03 (0.937 s / it) [11-25 12:35:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 131/350] Total time: 0:26:03 (0.937 s / it) [11-25 12:35:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 131/350] Total time: 0:26:03 (0.937 s / it) [11-25 12:35:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 131/350] Total time: 0:26:03 (0.937 s / it) [11-25 12:35:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 131/350] Total time: 0:26:03 (0.937 s / it) [11-25 12:35:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 131/350] Total time: 0:26:03 (0.937 s / it) [11-25 12:35:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 131/350] Total time: 0:26:03 (0.937 s / it) [11-25 12:35:29] (/home/user/VAR/train.py , line 276)=> [ep131] (training ) Lm: 6.462 (6.482), Lt: 5.703 (5.730), Acc m&t: 3.49 5.51, Remain: 3 days, 22:31:17, Finish: 2024-11-28 19:06 [11-25 12:35:29] (/home/user/VAR/train.py , line 276)=> [ep131] (training ) Lm: 6.462 (6.482), Lt: 5.703 (5.730), Acc m&t: 3.49 5.51, Remain: 3 days, 22:33:38, Finish: 2024-11-28 19:09 [11-25 12:35:29] (/home/user/VAR/train.py , line 276)=> [ep131] (training ) Lm: 6.462 (6.482), Lt: 5.703 (5.730), Acc m&t: 3.49 5.51, Remain: 3 days, 22:33:56, Finish: 2024-11-28 19:09 [11-25 12:35:29] (/home/user/VAR/train.py , line 276)=> [ep131] (training ) Lm: 6.462 (6.482), Lt: 5.703 (5.730), Acc m&t: 3.49 5.51, Remain: 3 days, 22:33:40, Finish: 2024-11-28 19:09 [11-25 12:35:29] (/home/user/VAR/train.py , line 276)=> [ep131] (training ) Lm: 6.462 (6.482), Lt: 5.703 (5.730), Acc m&t: 3.49 5.51, Remain: 3 days, 22:31:53, Finish: 2024-11-28 19:07 [11-25 12:35:29] (/home/user/VAR/train.py , line 276)=> [ep131] (training ) Lm: 6.462 (6.482), Lt: 5.703 (5.730), Acc m&t: 3.49 5.51, Remain: 3 days, 22:32:52, Finish: 2024-11-28 19:08 [11-25 12:35:29] (/home/user/VAR/train.py , line 276)=> [ep131] (training ) Lm: 6.462 (6.482), Lt: 5.703 (5.730), Acc m&t: 3.49 5.51, Remain: 3 days, 22:33:52, Finish: 2024-11-28 19:09 [11-25 12:35:29] (/home/user/VAR/train.py , line 276)=> [ep131] (training ) Lm: 6.462 (6.482), Lt: 5.703 (5.730), Acc m&t: 3.49 5.51, Remain: 3 days, 22:33:22, Finish: 2024-11-28 19:08 [11-25 12:35:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 0/1669] eta: 0:25:41 tlr: 0.00016 tnm: 0.24 Lm: 6.433 (6.433) Lt: 5.545 (5.545) Accm: 3.92 (3.92) Acct: 6.44 (6.44) proj_loss: -0.5922 (-0.5922) time: 0.9238 data: 0.0004 [11-25 12:35:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 0/1669] eta: 0:25:41 tlr: 0.00016 tnm: 0.24 Lm: 6.490 (6.490) Lt: 5.770 (5.770) Accm: 3.02 (3.02) Acct: 4.82 (4.82) proj_loss: -0.6200 (-0.6200) time: 0.9238 data: 0.0004 [11-25 12:35:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 0/1669] eta: 0:25:42 tlr: 0.00016 tnm: 0.24 Lm: 6.370 (6.370) Lt: 5.584 (5.584) Accm: 3.80 (3.80) Acct: 5.79 (5.79) proj_loss: -0.6030 (-0.6030) time: 0.9241 data: 0.0003 [11-25 12:35:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 0/1669] eta: 0:25:41 tlr: 0.00016 tnm: 0.24 Lm: 6.417 (6.417) Lt: 5.723 (5.723) Accm: 3.34 (3.34) Acct: 4.92 (4.92) proj_loss: -0.5952 (-0.5952) time: 0.9234 data: 0.0004 [11-25 12:35:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 0/1669] eta: 0:25:42 tlr: 0.00016 tnm: 0.24 Lm: 6.451 (6.451) Lt: 5.659 (5.659) Accm: 3.53 (3.53) Acct: 5.82 (5.82) proj_loss: -0.6172 (-0.6172) time: 0.9243 data: 0.0004 [11-25 12:35:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 0/1669] eta: 0:25:42 tlr: 0.00016 tnm: 0.24 Lm: 6.375 (6.375) Lt: 5.601 (5.601) Accm: 3.61 (3.61) Acct: 5.92 (5.92) proj_loss: -0.5963 (-0.5963) time: 0.9244 data: 0.0004 [11-25 12:35:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 0/1669] eta: 0:25:42 tlr: 0.00016 tnm: 0.24 Lm: 6.564 (6.564) Lt: 5.827 (5.827) Accm: 3.57 (3.57) Acct: 5.58 (5.58) proj_loss: -0.5854 (-0.5854) time: 0.9245 data: 0.0004 [11-25 12:35:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 0/1669] eta: 0:25:43 tlr: 0.00016 tnm: 0.24 Lm: 6.424 (6.424) Lt: 5.713 (5.713) Accm: 3.74 (3.74) Acct: 5.85 (5.85) proj_loss: -0.6147 (-0.6147) time: 0.9246 data: 0.0003 [11-25 12:41:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.25 Lm: 6.345 (6.345) Lt: 5.580 (5.580) Accm: 3.96 (3.96) Acct: 6.44 (6.44) proj_loss: -0.6082 (-0.6082) time: 0.9307 data: 0.0003 [11-25 12:41:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.25 Lm: 6.470 (6.470) Lt: 5.710 (5.710) Accm: 3.53 (3.53) Acct: 5.53 (5.53) proj_loss: -0.6039 (-0.6039) time: 0.9307 data: 0.0002 [11-25 12:41:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.25 Lm: 6.477 (6.477) Lt: 5.717 (5.717) Accm: 3.47 (3.47) Acct: 5.35 (5.35) proj_loss: -0.5967 (-0.5967) time: 0.9307 data: 0.0003 [11-25 12:41:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.25 Lm: 6.539 (6.539) Lt: 5.709 (5.709) Accm: 3.42 (3.42) Acct: 5.66 (5.66) proj_loss: -0.6049 (-0.6049) time: 0.9307 data: 0.0003 [11-25 12:41:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.25 Lm: 6.448 (6.448) Lt: 5.658 (5.658) Accm: 3.66 (3.66) Acct: 5.96 (5.96) proj_loss: -0.5946 (-0.5946) time: 0.9307 data: 0.0003 [11-25 12:41:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.25 Lm: 6.321 (6.321) Lt: 5.485 (5.485) Accm: 3.84 (3.84) Acct: 5.92 (5.92) proj_loss: -0.6027 (-0.6027) time: 0.9307 data: 0.0003 [11-25 12:41:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.25 Lm: 6.477 (6.477) Lt: 5.775 (5.775) Accm: 3.36 (3.36) Acct: 4.98 (4.98) proj_loss: -0.6145 (-0.6145) time: 0.9307 data: 0.0003 [11-25 12:41:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.25 Lm: 6.470 (6.470) Lt: 5.743 (5.743) Accm: 3.21 (3.21) Acct: 5.22 (5.22) proj_loss: -0.5962 (-0.5962) time: 0.9307 data: 0.0002 [11-25 12:48:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.25 Lm: 6.402 (6.447) Lt: 5.630 (5.683) Accm: 3.57 (3.57) Acct: 5.58 (5.54) proj_loss: -0.5854 (-0.5946) time: 0.9282 data: 0.0002 [11-25 12:48:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.25 Lm: 6.370 (6.387) Lt: 5.584 (5.558) Accm: 3.80 (3.64) Acct: 5.79 (5.65) proj_loss: -0.6025 (-0.5997) time: 0.9282 data: 0.0003 [11-25 12:48:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.25 Lm: 6.417 (6.351) Lt: 5.723 (5.641) Accm: 3.38 (3.80) Acct: 5.03 (5.68) proj_loss: -0.6339 (-0.6225) time: 0.9282 data: 0.0003 [11-25 12:48:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.25 Lm: 6.510 (6.488) Lt: 5.834 (5.766) Accm: 3.38 (3.44) Acct: 4.96 (5.22) proj_loss: -0.5970 (-0.6098) time: 0.9282 data: 0.0003 [11-25 12:48:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.25 Lm: 6.444 (6.435) Lt: 5.657 (5.649) Accm: 3.61 (3.64) Acct: 5.99 (5.97) proj_loss: -0.5986 (-0.5960) time: 0.9282 data: 0.0003 [11-25 12:48:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.25 Lm: 6.424 (6.405) Lt: 5.713 (5.669) Accm: 3.74 (3.77) Acct: 5.85 (5.84) proj_loss: -0.6017 (-0.6054) time: 0.9282 data: 0.0003 [11-25 12:48:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.25 Lm: 6.435 (6.504) Lt: 5.647 (5.688) Accm: 3.74 (3.53) Acct: 5.92 (5.75) proj_loss: -0.6177 (-0.6199) time: 0.9282 data: 0.0003 [11-25 12:48:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.25 Lm: 6.490 (6.479) Lt: 5.716 (5.712) Accm: 3.32 (3.24) Acct: 5.61 (5.36) proj_loss: -0.6143 (-0.6022) time: 0.9281 data: 0.0004 [11-25 12:54:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.24 Lm: 6.494 (6.490) Lt: 5.707 (5.709) Accm: 3.21 (3.21) Acct: 5.25 (5.24) proj_loss: -0.6171 (-0.6080) time: 0.9296 data: 0.0003 [11-25 12:54:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.24 Lm: 6.389 (6.415) Lt: 5.611 (5.647) Accm: 3.61 (3.61) Acct: 5.58 (5.63) proj_loss: -0.5843 (-0.5918) time: 0.9296 data: 0.0002 [11-25 12:54:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.24 Lm: 6.434 (6.432) Lt: 5.644 (5.644) Accm: 3.70 (3.74) Acct: 6.04 (6.02) proj_loss: -0.6061 (-0.6004) time: 0.9296 data: 0.0003 [11-25 12:54:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.24 Lm: 6.443 (6.426) Lt: 5.717 (5.684) Accm: 3.49 (3.48) Acct: 5.23 (5.29) proj_loss: -0.6062 (-0.6112) time: 0.9296 data: 0.0003 [11-25 12:54:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.24 Lm: 6.540 (6.582) Lt: 5.760 (5.785) Accm: 3.34 (3.31) Acct: 5.41 (5.33) proj_loss: -0.6137 (-0.6173) time: 0.9296 data: 0.0003 [11-25 12:54:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.24 Lm: 6.440 (6.417) Lt: 5.685 (5.666) Accm: 3.58 (3.68) Acct: 5.72 (5.78) proj_loss: -0.6008 (-0.5919) time: 0.9296 data: 0.0003 [11-25 12:54:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.24 Lm: 6.365 (6.380) Lt: 5.609 (5.578) Accm: 3.84 (3.80) Acct: 5.92 (5.85) proj_loss: -0.6027 (-0.6054) time: 0.9296 data: 0.0003 [11-25 12:54:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.24 Lm: 6.477 (6.435) Lt: 5.775 (5.725) Accm: 3.36 (3.52) Acct: 4.98 (5.24) proj_loss: -0.6145 (-0.6143) time: 0.9296 data: 0.0003 [11-25 13:01:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.417 (6.421) Lt: 5.723 (5.696) Accm: 3.38 (3.55) Acct: 5.03 (5.37) proj_loss: -0.5988 (-0.6112) time: 0.9303 data: 0.0015 [11-25 13:01:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 132/350] Total time: 0:25:51 (0.929 s / it) [11-25 13:01:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.376 (6.403) Lt: 5.593 (5.634) Accm: 3.66 (3.62) Acct: 5.58 (5.67) proj_loss: -0.5854 (-0.5943) time: 0.9303 data: 0.0015 [11-25 13:01:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.360 (6.339) Lt: 5.584 (5.543) Accm: 3.88 (3.90) Acct: 6.06 (5.94) proj_loss: -0.6030 (-0.6138) time: 0.9303 data: 0.0017 [11-25 13:01:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.498 (6.517) Lt: 5.716 (5.752) Accm: 3.19 (3.20) Acct: 4.89 (5.15) proj_loss: -0.6143 (-0.6015) time: 0.9303 data: 0.0019 [11-25 13:01:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.463 (6.559) Lt: 5.660 (5.760) Accm: 3.41 (3.33) Acct: 5.61 (5.39) proj_loss: -0.6177 (-0.6219) time: 0.9303 data: 0.0015 [11-25 13:01:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.455 (6.429) Lt: 5.656 (5.661) Accm: 3.41 (3.62) Acct: 5.58 (5.71) proj_loss: -0.6017 (-0.5950) time: 0.9303 data: 0.0020 [11-25 13:01:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.444 (6.476) Lt: 5.657 (5.700) Accm: 3.61 (3.60) Acct: 5.99 (5.80) proj_loss: -0.5986 (-0.5982) time: 0.9303 data: 0.0020 [11-25 13:01:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.510 (6.447) Lt: 5.778 (5.703) Accm: 3.38 (3.45) Acct: 5.51 (5.37) proj_loss: -0.6154 (-0.6172) time: 0.9303 data: 0.0018 [11-25 13:01:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 132/350] Total time: 0:25:51 (0.929 s / it) [11-25 13:01:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 132/350] Total time: 0:25:51 (0.929 s / it) [11-25 13:01:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 132/350] Total time: 0:25:51 (0.929 s / it) [11-25 13:01:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 132/350] Total time: 0:25:51 (0.929 s / it) [11-25 13:01:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 132/350] Total time: 0:25:51 (0.929 s / it) [11-25 13:01:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 132/350] Total time: 0:25:51 (0.929 s / it) [11-25 13:01:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 132/350] Total time: 0:25:51 (0.929 s / it) [11-25 13:01:20] (/home/user/VAR/train.py , line 276)=> [ep132] (training ) Lm: 6.462 (6.466), Lt: 5.703 (5.711), Acc m&t: 3.49 5.51, Remain: 3 days, 22:20:48, Finish: 2024-11-28 19:22 [11-25 13:01:20] (/home/user/VAR/train.py , line 276)=> [ep132] (training ) Lm: 6.462 (6.466), Lt: 5.703 (5.711), Acc m&t: 3.49 5.51, Remain: 3 days, 22:22:04, Finish: 2024-11-28 19:23 [11-25 13:01:20] (/home/user/VAR/train.py , line 276)=> [ep132] (training ) Lm: 6.462 (6.466), Lt: 5.703 (5.711), Acc m&t: 3.49 5.51, Remain: 3 days, 22:21:52, Finish: 2024-11-28 19:23 [11-25 13:01:20] (/home/user/VAR/train.py , line 276)=> [ep132] (training ) Lm: 6.462 (6.466), Lt: 5.703 (5.711), Acc m&t: 3.49 5.51, Remain: 3 days, 22:22:08, Finish: 2024-11-28 19:23 [11-25 13:01:20] (/home/user/VAR/train.py , line 276)=> [ep132] (training ) Lm: 6.462 (6.466), Lt: 5.703 (5.711), Acc m&t: 3.49 5.51, Remain: 3 days, 22:20:19, Finish: 2024-11-28 19:21 [11-25 13:01:20] (/home/user/VAR/train.py , line 276)=> [ep132] (training ) Lm: 6.462 (6.466), Lt: 5.703 (5.711), Acc m&t: 3.49 5.51, Remain: 3 days, 22:20:25, Finish: 2024-11-28 19:21 [11-25 13:01:20] (/home/user/VAR/train.py , line 276)=> [ep132] (training ) Lm: 6.462 (6.466), Lt: 5.703 (5.711), Acc m&t: 3.49 5.51, Remain: 3 days, 22:21:58, Finish: 2024-11-28 19:23 [11-25 13:01:20] (/home/user/VAR/train.py , line 276)=> [ep132] (training ) Lm: 6.462 (6.466), Lt: 5.703 (5.711), Acc m&t: 3.49 5.51, Remain: 3 days, 22:22:24, Finish: 2024-11-28 19:23 [11-25 13:01:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 0/1669] eta: 0:25:34 tlr: 0.00016 tnm: 0.24 Lm: 6.226 (6.226) Lt: 5.475 (5.475) Accm: 4.39 (4.39) Acct: 6.82 (6.82) proj_loss: -0.6460 (-0.6460) time: 0.9194 data: 0.0003 [11-25 13:01:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 0/1669] eta: 0:25:34 tlr: 0.00016 tnm: 0.24 Lm: 6.411 (6.411) Lt: 5.669 (5.669) Accm: 3.77 (3.77) Acct: 5.54 (5.54) proj_loss: -0.6461 (-0.6461) time: 0.9192 data: 0.0004 [11-25 13:01:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 0/1669] eta: 0:25:34 tlr: 0.00016 tnm: 0.24 Lm: 6.496 (6.496) Lt: 5.809 (5.809) Accm: 3.35 (3.35) Acct: 5.27 (5.27) proj_loss: -0.6149 (-0.6149) time: 0.9193 data: 0.0003 [11-25 13:01:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 0/1669] eta: 0:25:34 tlr: 0.00016 tnm: 0.24 Lm: 6.097 (6.097) Lt: 5.348 (5.348) Accm: 4.44 (4.44) Acct: 6.65 (6.65) proj_loss: -0.6241 (-0.6241) time: 0.9192 data: 0.0004 [11-25 13:01:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 0/1669] eta: 0:25:34 tlr: 0.00016 tnm: 0.24 Lm: 6.458 (6.458) Lt: 5.665 (5.665) Accm: 3.76 (3.76) Acct: 5.99 (5.99) proj_loss: -0.6061 (-0.6061) time: 0.9195 data: 0.0004 [11-25 13:01:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 0/1669] eta: 0:25:34 tlr: 0.00016 tnm: 0.24 Lm: 6.478 (6.478) Lt: 5.792 (5.792) Accm: 3.55 (3.55) Acct: 5.06 (5.06) proj_loss: -0.6256 (-0.6256) time: 0.9195 data: 0.0004 [11-25 13:01:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 0/1669] eta: 0:25:34 tlr: 0.00016 tnm: 0.24 Lm: 6.348 (6.348) Lt: 5.600 (5.600) Accm: 4.05 (4.05) Acct: 6.61 (6.61) proj_loss: -0.6364 (-0.6364) time: 0.9196 data: 0.0004 [11-25 13:01:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 0/1669] eta: 0:25:35 tlr: 0.00016 tnm: 0.24 Lm: 6.499 (6.499) Lt: 5.780 (5.780) Accm: 3.29 (3.29) Acct: 5.48 (5.48) proj_loss: -0.6211 (-0.6211) time: 0.9202 data: 0.0004 [11-25 13:08:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 417/1669] eta: 0:20:10 tlr: 0.00016 tnm: 0.24 Lm: 6.556 (6.556) Lt: 5.818 (5.818) Accm: 3.39 (3.39) Acct: 5.22 (5.22) proj_loss: -0.6150 (-0.6150) time: 0.9293 data: 0.0003 [11-25 13:08:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 417/1669] eta: 0:20:10 tlr: 0.00016 tnm: 0.24 Lm: 6.568 (6.568) Lt: 5.825 (5.825) Accm: 3.18 (3.18) Acct: 4.94 (4.94) proj_loss: -0.6085 (-0.6085) time: 0.9293 data: 0.0003 [11-25 13:08:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 417/1669] eta: 0:20:10 tlr: 0.00016 tnm: 0.24 Lm: 6.286 (6.286) Lt: 5.572 (5.572) Accm: 3.71 (3.71) Acct: 5.65 (5.65) proj_loss: -0.6221 (-0.6221) time: 0.9293 data: 0.0003 [11-25 13:08:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 417/1669] eta: 0:20:10 tlr: 0.00016 tnm: 0.24 Lm: 6.448 (6.448) Lt: 5.675 (5.675) Accm: 3.57 (3.57) Acct: 5.60 (5.60) proj_loss: -0.6232 (-0.6232) time: 0.9293 data: 0.0003 [11-25 13:08:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 417/1669] eta: 0:20:10 tlr: 0.00016 tnm: 0.24 Lm: 6.543 (6.543) Lt: 5.857 (5.857) Accm: 3.34 (3.34) Acct: 4.89 (4.89) proj_loss: -0.6301 (-0.6301) time: 0.9293 data: 0.0003 [11-25 13:08:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 417/1669] eta: 0:20:10 tlr: 0.00016 tnm: 0.24 Lm: 6.240 (6.240) Lt: 5.442 (5.442) Accm: 4.22 (4.22) Acct: 6.71 (6.71) proj_loss: -0.6174 (-0.6174) time: 0.9293 data: 0.0003 [11-25 13:08:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 417/1669] eta: 0:20:10 tlr: 0.00016 tnm: 0.24 Lm: 6.472 (6.472) Lt: 5.726 (5.726) Accm: 3.55 (3.55) Acct: 5.87 (5.87) proj_loss: -0.6229 (-0.6229) time: 0.9293 data: 0.0003 [11-25 13:08:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 417/1669] eta: 0:20:10 tlr: 0.00016 tnm: 0.24 Lm: 6.467 (6.467) Lt: 5.731 (5.731) Accm: 3.42 (3.42) Acct: 5.32 (5.32) proj_loss: -0.6316 (-0.6316) time: 0.9293 data: 0.0003 [11-25 13:14:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 834/1669] eta: 0:13:11 tlr: 0.00016 tnm: 0.25 Lm: 6.411 (6.393) Lt: 5.669 (5.648) Accm: 3.77 (3.62) Acct: 5.54 (5.53) proj_loss: -0.6172 (-0.6248) time: 0.9271 data: 0.0003 [11-25 13:14:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 834/1669] eta: 0:13:11 tlr: 0.00016 tnm: 0.25 Lm: 6.640 (6.594) Lt: 5.841 (5.843) Accm: 3.00 (3.06) Acct: 4.61 (4.75) proj_loss: -0.6022 (-0.6026) time: 0.9271 data: 0.0003 [11-25 13:14:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 834/1669] eta: 0:13:11 tlr: 0.00016 tnm: 0.25 Lm: 6.526 (6.546) Lt: 5.816 (5.817) Accm: 3.47 (3.41) Acct: 5.34 (5.26) proj_loss: -0.6211 (-0.6204) time: 0.9271 data: 0.0003 [11-25 13:14:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 834/1669] eta: 0:13:11 tlr: 0.00016 tnm: 0.25 Lm: 6.255 (6.318) Lt: 5.475 (5.576) Accm: 4.05 (4.00) Acct: 6.61 (6.20) proj_loss: -0.6170 (-0.6172) time: 0.9271 data: 0.0003 [11-25 13:14:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 834/1669] eta: 0:13:11 tlr: 0.00016 tnm: 0.25 Lm: 6.399 (6.448) Lt: 5.600 (5.679) Accm: 3.57 (3.56) Acct: 5.72 (5.82) proj_loss: -0.6094 (-0.6121) time: 0.9271 data: 0.0003 [11-25 13:14:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 834/1669] eta: 0:13:11 tlr: 0.00016 tnm: 0.25 Lm: 6.474 (6.440) Lt: 5.796 (5.713) Accm: 2.97 (3.35) Acct: 4.65 (5.11) proj_loss: -0.6201 (-0.6162) time: 0.9271 data: 0.0003 [11-25 13:14:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 834/1669] eta: 0:13:11 tlr: 0.00016 tnm: 0.25 Lm: 6.478 (6.446) Lt: 5.792 (5.753) Accm: 3.55 (3.71) Acct: 5.06 (5.45) proj_loss: -0.6256 (-0.6267) time: 0.9271 data: 0.0003 [11-25 13:14:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 834/1669] eta: 0:13:11 tlr: 0.00016 tnm: 0.25 Lm: 6.438 (6.431) Lt: 5.665 (5.643) Accm: 3.50 (3.55) Acct: 5.68 (5.62) proj_loss: -0.6061 (-0.6131) time: 0.9271 data: 0.0003 [11-25 13:20:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1251/1669] eta: 0:06:33 tlr: 0.00016 tnm: 0.24 Lm: 6.438 (6.433) Lt: 5.675 (5.657) Accm: 3.44 (3.49) Acct: 5.44 (5.45) proj_loss: -0.6232 (-0.6247) time: 0.9285 data: 0.0003 [11-25 13:20:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1251/1669] eta: 0:06:33 tlr: 0.00016 tnm: 0.24 Lm: 6.568 (6.547) Lt: 5.825 (5.809) Accm: 3.18 (3.18) Acct: 4.89 (4.86) proj_loss: -0.6085 (-0.6066) time: 0.9285 data: 0.0003 [11-25 13:20:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1251/1669] eta: 0:06:33 tlr: 0.00016 tnm: 0.24 Lm: 6.513 (6.485) Lt: 5.798 (5.755) Accm: 3.47 (3.57) Acct: 5.41 (5.58) proj_loss: -0.6150 (-0.6175) time: 0.9285 data: 0.0003 [11-25 13:20:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1251/1669] eta: 0:06:33 tlr: 0.00016 tnm: 0.24 Lm: 6.331 (6.340) Lt: 5.596 (5.611) Accm: 3.81 (3.87) Acct: 5.89 (5.92) proj_loss: -0.6104 (-0.6139) time: 0.9286 data: 0.0003 [11-25 13:20:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1251/1669] eta: 0:06:33 tlr: 0.00016 tnm: 0.24 Lm: 6.384 (6.384) Lt: 5.623 (5.630) Accm: 3.89 (3.77) Acct: 5.75 (5.87) proj_loss: -0.6226 (-0.6256) time: 0.9285 data: 0.0003 [11-25 13:20:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1251/1669] eta: 0:06:33 tlr: 0.00016 tnm: 0.24 Lm: 6.594 (6.508) Lt: 5.896 (5.789) Accm: 2.93 (3.23) Acct: 4.58 (4.96) proj_loss: -0.6151 (-0.6146) time: 0.9285 data: 0.0003 [11-25 13:20:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1251/1669] eta: 0:06:33 tlr: 0.00016 tnm: 0.24 Lm: 6.396 (6.434) Lt: 5.602 (5.660) Accm: 3.62 (3.59) Acct: 5.92 (5.90) proj_loss: -0.6097 (-0.6116) time: 0.9285 data: 0.0003 [11-25 13:20:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1251/1669] eta: 0:06:33 tlr: 0.00016 tnm: 0.24 Lm: 6.543 (6.512) Lt: 5.857 (5.819) Accm: 3.34 (3.51) Acct: 4.89 (5.13) proj_loss: -0.6293 (-0.6283) time: 0.9285 data: 0.0003 [11-25 13:27:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.506 (6.511) Lt: 5.792 (5.811) Accm: 3.55 (3.53) Acct: 5.06 (5.21) proj_loss: -0.6261 (-0.6279) time: 0.9292 data: 0.0016 [11-25 13:27:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 133/350] Total time: 0:26:06 (0.939 s / it) [11-25 13:27:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.566 (6.551) Lt: 5.809 (5.803) Accm: 3.10 (3.17) Acct: 4.96 (4.88) proj_loss: -0.6022 (-0.6020) time: 0.9292 data: 0.0020 [11-25 13:27:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.411 (6.455) Lt: 5.669 (5.713) Accm: 3.77 (3.52) Acct: 5.54 (5.43) proj_loss: -0.6172 (-0.6213) time: 0.9292 data: 0.0021 [11-25 13:27:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.399 (6.432) Lt: 5.604 (5.652) Accm: 3.57 (3.54) Acct: 5.72 (5.79) proj_loss: -0.6094 (-0.6055) time: 0.9292 data: 0.0016 [11-25 13:27:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.439 (6.445) Lt: 5.684 (5.668) Accm: 3.41 (3.48) Acct: 5.27 (5.41) proj_loss: -0.6149 (-0.6227) time: 0.9292 data: 0.0023 [11-25 13:27:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.474 (6.496) Lt: 5.796 (5.778) Accm: 2.97 (3.26) Acct: 4.65 (4.96) proj_loss: -0.6101 (-0.6110) time: 0.9292 data: 0.0018 [11-25 13:27:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.407 (6.414) Lt: 5.717 (5.701) Accm: 3.57 (3.67) Acct: 5.17 (5.54) proj_loss: -0.6126 (-0.6136) time: 0.9292 data: 0.0014 [11-25 13:27:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.499 (6.482) Lt: 5.780 (5.748) Accm: 3.48 (3.60) Acct: 5.48 (5.63) proj_loss: -0.6211 (-0.6183) time: 0.9292 data: 0.0021 [11-25 13:27:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 133/350] Total time: 0:26:06 (0.939 s / it) [11-25 13:27:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 133/350] Total time: 0:26:06 (0.939 s / it) [11-25 13:27:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 133/350] Total time: 0:26:06 (0.939 s / it) [11-25 13:27:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 133/350] Total time: 0:26:06 (0.939 s / it) [11-25 13:27:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 133/350] Total time: 0:26:06 (0.939 s / it) [11-25 13:27:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 133/350] Total time: 0:26:06 (0.939 s / it) [11-25 13:27:26] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 133/350] Total time: 0:26:06 (0.939 s / it) [11-25 13:27:26] (/home/user/VAR/train.py , line 276)=> [ep133] (training ) Lm: 6.462 (6.473), Lt: 5.703 (5.722), Acc m&t: 3.49 5.51, Remain: 3 days, 21:42:21, Finish: 2024-11-28 19:09 [11-25 13:27:26] (/home/user/VAR/train.py , line 276)=> [ep133] (training ) Lm: 6.462 (6.473), Lt: 5.703 (5.722), Acc m&t: 3.49 5.51, Remain: 3 days, 21:41:29, Finish: 2024-11-28 19:08 [11-25 13:27:26] (/home/user/VAR/train.py , line 276)=> [ep133] (training ) Lm: 6.462 (6.473), Lt: 5.703 (5.722), Acc m&t: 3.49 5.51, Remain: 3 days, 21:46:45, Finish: 2024-11-28 19:14 [11-25 13:27:26] (/home/user/VAR/train.py , line 276)=> [ep133] (training ) Lm: 6.462 (6.473), Lt: 5.703 (5.722), Acc m&t: 3.49 5.51, Remain: 3 days, 21:41:16, Finish: 2024-11-28 19:08 [11-25 13:27:26] (/home/user/VAR/train.py , line 276)=> [ep133] (training ) Lm: 6.462 (6.473), Lt: 5.703 (5.722), Acc m&t: 3.49 5.51, Remain: 3 days, 21:39:27, Finish: 2024-11-28 19:06 [11-25 13:27:26] (/home/user/VAR/train.py , line 276)=> [ep133] (training ) Lm: 6.462 (6.473), Lt: 5.703 (5.722), Acc m&t: 3.49 5.51, Remain: 3 days, 21:40:54, Finish: 2024-11-28 19:08 [11-25 13:27:26] (/home/user/VAR/train.py , line 276)=> [ep133] (training ) Lm: 6.462 (6.473), Lt: 5.703 (5.722), Acc m&t: 3.49 5.51, Remain: 3 days, 21:42:15, Finish: 2024-11-28 19:09 [11-25 13:27:26] (/home/user/VAR/train.py , line 276)=> [ep133] (training ) Lm: 6.462 (6.473), Lt: 5.703 (5.722), Acc m&t: 3.49 5.51, Remain: 3 days, 21:39:55, Finish: 2024-11-28 19:07 [11-25 13:27:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 0/1669] eta: 0:25:30 tlr: 0.00016 tnm: 0.25 Lm: 6.457 (6.457) Lt: 5.672 (5.672) Accm: 3.44 (3.44) Acct: 5.61 (5.61) proj_loss: -0.6318 (-0.6318) time: 0.9172 data: 0.0003 [11-25 13:27:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 0/1669] eta: 0:25:20 tlr: 0.00016 tnm: 0.25 Lm: 6.512 (6.512) Lt: 5.740 (5.740) Accm: 3.29 (3.29) Acct: 5.34 (5.34) proj_loss: -0.6113 (-0.6113) time: 0.9111 data: 0.0004 [11-25 13:27:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 0/1669] eta: 0:25:21 tlr: 0.00016 tnm: 0.25 Lm: 6.206 (6.206) Lt: 5.447 (5.447) Accm: 4.11 (4.11) Acct: 6.03 (6.03) proj_loss: -0.6213 (-0.6213) time: 0.9114 data: 0.0004 [11-25 13:27:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 0/1669] eta: 0:25:20 tlr: 0.00016 tnm: 0.25 Lm: 6.518 (6.518) Lt: 5.815 (5.815) Accm: 3.38 (3.38) Acct: 5.03 (5.03) proj_loss: -0.6207 (-0.6207) time: 0.9109 data: 0.0004 [11-25 13:27:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 0/1669] eta: 0:25:20 tlr: 0.00016 tnm: 0.25 Lm: 6.621 (6.621) Lt: 5.810 (5.810) Accm: 3.04 (3.04) Acct: 4.68 (4.68) proj_loss: -0.5765 (-0.5765) time: 0.9109 data: 0.0004 [11-25 13:27:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 0/1669] eta: 0:25:21 tlr: 0.00016 tnm: 0.25 Lm: 6.563 (6.563) Lt: 5.901 (5.901) Accm: 2.96 (2.96) Acct: 4.30 (4.30) proj_loss: -0.5910 (-0.5910) time: 0.9114 data: 0.0004 [11-25 13:27:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 0/1669] eta: 0:25:21 tlr: 0.00016 tnm: 0.25 Lm: 6.691 (6.691) Lt: 5.879 (5.879) Accm: 2.80 (2.80) Acct: 4.17 (4.17) proj_loss: -0.5716 (-0.5716) time: 0.9115 data: 0.0004 [11-25 13:27:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 0/1669] eta: 0:25:30 tlr: 0.00016 tnm: 0.25 Lm: 6.542 (6.542) Lt: 5.755 (5.755) Accm: 3.61 (3.61) Acct: 5.68 (5.68) proj_loss: -0.5883 (-0.5883) time: 0.9171 data: 0.0004 [11-25 13:33:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 417/1669] eta: 0:19:22 tlr: 0.00016 tnm: 0.24 Lm: 6.531 (6.531) Lt: 5.771 (5.771) Accm: 3.41 (3.41) Acct: 5.18 (5.18) proj_loss: -0.5932 (-0.5932) time: 0.9291 data: 0.0003 [11-25 13:33:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 417/1669] eta: 0:19:22 tlr: 0.00016 tnm: 0.24 Lm: 6.598 (6.598) Lt: 5.873 (5.873) Accm: 3.26 (3.26) Acct: 5.17 (5.17) proj_loss: -0.6149 (-0.6149) time: 0.9291 data: 0.0003 [11-25 13:33:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 417/1669] eta: 0:19:22 tlr: 0.00016 tnm: 0.24 Lm: 6.443 (6.443) Lt: 5.659 (5.659) Accm: 3.52 (3.52) Acct: 5.82 (5.82) proj_loss: -0.5992 (-0.5992) time: 0.9291 data: 0.0003 [11-25 13:33:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 417/1669] eta: 0:19:22 tlr: 0.00016 tnm: 0.24 Lm: 6.549 (6.549) Lt: 5.822 (5.822) Accm: 3.01 (3.01) Acct: 4.51 (4.51) proj_loss: -0.6057 (-0.6057) time: 0.9291 data: 0.0003 [11-25 13:33:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 417/1669] eta: 0:19:22 tlr: 0.00016 tnm: 0.24 Lm: 6.635 (6.635) Lt: 5.878 (5.878) Accm: 2.89 (2.89) Acct: 4.46 (4.46) proj_loss: -0.6022 (-0.6022) time: 0.9291 data: 0.0003 [11-25 13:33:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 417/1669] eta: 0:19:22 tlr: 0.00016 tnm: 0.24 Lm: 6.467 (6.467) Lt: 5.750 (5.750) Accm: 3.50 (3.50) Acct: 5.53 (5.53) proj_loss: -0.6388 (-0.6388) time: 0.9291 data: 0.0003 [11-25 13:33:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 417/1669] eta: 0:19:22 tlr: 0.00016 tnm: 0.24 Lm: 6.617 (6.617) Lt: 5.903 (5.903) Accm: 2.95 (2.95) Acct: 4.44 (4.44) proj_loss: -0.5846 (-0.5846) time: 0.9291 data: 0.0003 [11-25 13:33:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 417/1669] eta: 0:19:22 tlr: 0.00016 tnm: 0.24 Lm: 6.328 (6.328) Lt: 5.557 (5.557) Accm: 3.60 (3.60) Acct: 5.48 (5.48) proj_loss: -0.6101 (-0.6101) time: 0.9291 data: 0.0003 [11-25 13:40:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 834/1669] eta: 0:13:07 tlr: 0.00016 tnm: 0.25 Lm: 6.421 (6.359) Lt: 5.667 (5.594) Accm: 3.34 (3.51) Acct: 5.20 (5.38) proj_loss: -0.6072 (-0.6091) time: 0.9290 data: 0.0003 [11-25 13:40:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 834/1669] eta: 0:13:07 tlr: 0.00016 tnm: 0.25 Lm: 6.519 (6.440) Lt: 5.755 (5.699) Accm: 3.61 (3.62) Acct: 5.68 (5.58) proj_loss: -0.5981 (-0.6083) time: 0.9290 data: 0.0003 [11-25 13:40:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 834/1669] eta: 0:13:07 tlr: 0.00016 tnm: 0.25 Lm: 6.374 (6.418) Lt: 5.626 (5.648) Accm: 3.74 (3.65) Acct: 5.65 (5.76) proj_loss: -0.6090 (-0.6025) time: 0.9290 data: 0.0003 [11-25 13:40:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 834/1669] eta: 0:13:07 tlr: 0.00016 tnm: 0.25 Lm: 6.678 (6.673) Lt: 5.932 (5.941) Accm: 3.13 (3.03) Acct: 5.03 (4.90) proj_loss: -0.6091 (-0.6091) time: 0.9290 data: 0.0003 [11-25 13:40:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 834/1669] eta: 0:13:07 tlr: 0.00016 tnm: 0.25 Lm: 6.457 (6.383) Lt: 5.672 (5.632) Accm: 3.57 (3.67) Acct: 5.61 (5.82) proj_loss: -0.6318 (-0.6257) time: 0.9290 data: 0.0005 [11-25 13:40:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 834/1669] eta: 0:13:07 tlr: 0.00016 tnm: 0.25 Lm: 6.579 (6.502) Lt: 5.878 (5.749) Accm: 2.99 (3.28) Acct: 4.75 (5.06) proj_loss: -0.5995 (-0.6013) time: 0.9290 data: 0.0003 [11-25 13:40:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 834/1669] eta: 0:13:07 tlr: 0.00016 tnm: 0.25 Lm: 6.626 (6.620) Lt: 5.901 (5.873) Accm: 2.96 (2.95) Acct: 4.58 (4.55) proj_loss: -0.5910 (-0.5923) time: 0.9290 data: 0.0003 [11-25 13:40:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 834/1669] eta: 0:13:07 tlr: 0.00016 tnm: 0.25 Lm: 6.477 (6.492) Lt: 5.810 (5.776) Accm: 3.04 (3.18) Acct: 4.68 (4.86) proj_loss: -0.6244 (-0.6119) time: 0.9290 data: 0.0003 [11-25 13:47:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1251/1669] eta: 0:06:32 tlr: 0.00016 tnm: 0.24 Lm: 6.483 (6.491) Lt: 5.778 (5.768) Accm: 3.05 (3.15) Acct: 4.63 (4.79) proj_loss: -0.6220 (-0.6138) time: 0.9308 data: 0.0003 [11-25 13:47:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1251/1669] eta: 0:06:32 tlr: 0.00016 tnm: 0.24 Lm: 6.389 (6.383) Lt: 5.655 (5.609) Accm: 3.80 (3.71) Acct: 6.03 (5.91) proj_loss: -0.5932 (-0.6033) time: 0.9308 data: 0.0003 [11-25 13:47:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1251/1669] eta: 0:06:32 tlr: 0.00016 tnm: 0.24 Lm: 6.424 (6.385) Lt: 5.668 (5.640) Accm: 3.65 (3.68) Acct: 5.75 (5.84) proj_loss: -0.6284 (-0.6255) time: 0.9308 data: 0.0003 [11-25 13:47:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1251/1669] eta: 0:06:32 tlr: 0.00016 tnm: 0.24 Lm: 6.595 (6.509) Lt: 5.857 (5.779) Accm: 2.96 (3.23) Acct: 4.67 (4.99) proj_loss: -0.5993 (-0.6047) time: 0.9308 data: 0.0003 [11-25 13:47:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1251/1669] eta: 0:06:32 tlr: 0.00016 tnm: 0.24 Lm: 6.557 (6.510) Lt: 5.869 (5.777) Accm: 3.18 (3.30) Acct: 4.91 (5.06) proj_loss: -0.6070 (-0.6046) time: 0.9308 data: 0.0003 [11-25 13:47:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1251/1669] eta: 0:06:32 tlr: 0.00016 tnm: 0.24 Lm: 6.598 (6.633) Lt: 5.873 (5.906) Accm: 3.16 (3.07) Acct: 5.01 (4.92) proj_loss: -0.6149 (-0.6121) time: 0.9308 data: 0.0002 [11-25 13:47:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1251/1669] eta: 0:06:32 tlr: 0.00016 tnm: 0.24 Lm: 6.404 (6.366) Lt: 5.667 (5.623) Accm: 3.72 (3.66) Acct: 5.53 (5.50) proj_loss: -0.6142 (-0.6199) time: 0.9308 data: 0.0003 [11-25 13:47:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1251/1669] eta: 0:06:32 tlr: 0.00016 tnm: 0.24 Lm: 6.443 (6.456) Lt: 5.683 (5.699) Accm: 3.52 (3.50) Acct: 5.49 (5.54) proj_loss: -0.6031 (-0.6012) time: 0.9308 data: 0.0003 [11-25 13:53:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.374 (6.420) Lt: 5.626 (5.652) Accm: 3.74 (3.72) Acct: 5.65 (5.83) proj_loss: -0.5971 (-0.6001) time: 0.9297 data: 0.0024 [11-25 13:53:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 134/350] Total time: 0:26:17 (0.945 s / it) [11-25 13:53:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.544 (6.615) Lt: 5.815 (5.882) Accm: 3.19 (3.10) Acct: 4.99 (4.92) proj_loss: -0.6100 (-0.6117) time: 0.9297 data: 0.0016 [11-25 13:53:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.477 (6.460) Lt: 5.746 (5.726) Accm: 3.06 (3.30) Acct: 4.68 (5.03) proj_loss: -0.6196 (-0.6093) time: 0.9297 data: 0.0014 [11-25 13:53:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.421 (6.403) Lt: 5.668 (5.662) Accm: 3.34 (3.53) Acct: 5.20 (5.30) proj_loss: -0.6072 (-0.6167) time: 0.9297 data: 0.0016 [11-25 13:53:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.626 (6.541) Lt: 5.901 (5.809) Accm: 2.96 (3.16) Acct: 4.58 (4.88) proj_loss: -0.6077 (-0.6101) time: 0.9297 data: 0.0017 [11-25 13:53:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.258 (6.350) Lt: 5.554 (5.580) Accm: 3.98 (3.85) Acct: 6.37 (6.01) proj_loss: -0.5981 (-0.6069) time: 0.9297 data: 0.0017 [11-25 13:53:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.536 (6.482) Lt: 5.860 (5.772) Accm: 3.37 (3.33) Acct: 4.92 (5.03) proj_loss: -0.6145 (-0.6157) time: 0.9297 data: 0.0019 [11-25 13:53:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.457 (6.418) Lt: 5.672 (5.678) Accm: 3.57 (3.66) Acct: 5.61 (5.73) proj_loss: -0.6318 (-0.6293) time: 0.9297 data: 0.0015 [11-25 13:53:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 134/350] Total time: 0:26:17 (0.945 s / it) [11-25 13:53:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 134/350] Total time: 0:26:17 (0.945 s / it) [11-25 13:53:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 134/350] Total time: 0:26:17 (0.945 s / it) [11-25 13:53:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 134/350] Total time: 0:26:17 (0.945 s / it) [11-25 13:53:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 134/350] Total time: 0:26:17 (0.945 s / it) [11-25 13:53:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 134/350] Total time: 0:26:17 (0.945 s / it) [11-25 13:53:44] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 134/350] Total time: 0:26:17 (0.945 s / it) [11-25 13:53:44] (/home/user/VAR/train.py , line 276)=> [ep134] (training ) Lm: 6.462 (6.463), Lt: 5.703 (5.710), Acc m&t: 3.49 5.51, Remain: 3 days, 21:16:54, Finish: 2024-11-28 19:10 [11-25 13:53:44] (/home/user/VAR/train.py , line 276)=> [ep134] (training ) Lm: 6.462 (6.463), Lt: 5.703 (5.710), Acc m&t: 3.49 5.51, Remain: 3 days, 21:16:42, Finish: 2024-11-28 19:10 [11-25 13:53:44] (/home/user/VAR/train.py , line 276)=> [ep134] (training ) Lm: 6.462 (6.463), Lt: 5.703 (5.710), Acc m&t: 3.49 5.51, Remain: 3 days, 21:17:32, Finish: 2024-11-28 19:11 [11-25 13:53:44] (/home/user/VAR/train.py , line 276)=> [ep134] (training ) Lm: 6.462 (6.463), Lt: 5.703 (5.710), Acc m&t: 3.49 5.51, Remain: 3 days, 21:16:01, Finish: 2024-11-28 19:09 [11-25 13:53:44] (/home/user/VAR/train.py , line 276)=> [ep134] (training ) Lm: 6.462 (6.463), Lt: 5.703 (5.710), Acc m&t: 3.49 5.51, Remain: 3 days, 21:17:05, Finish: 2024-11-28 19:10 [11-25 13:53:44] (/home/user/VAR/train.py , line 276)=> [ep134] (training ) Lm: 6.462 (6.463), Lt: 5.703 (5.710), Acc m&t: 3.49 5.51, Remain: 3 days, 21:17:41, Finish: 2024-11-28 19:11 [11-25 13:53:44] (/home/user/VAR/train.py , line 276)=> [ep134] (training ) Lm: 6.462 (6.463), Lt: 5.703 (5.710), Acc m&t: 3.49 5.51, Remain: 3 days, 21:17:01, Finish: 2024-11-28 19:10 [11-25 13:53:44] (/home/user/VAR/train.py , line 276)=> [ep134] (training ) Lm: 6.462 (6.463), Lt: 5.703 (5.710), Acc m&t: 3.49 5.51, Remain: 3 days, 21:16:26, Finish: 2024-11-28 19:10 [11-25 13:53:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 0/1669] eta: 0:25:02 tlr: 0.00016 tnm: 0.25 Lm: 6.674 (6.674) Lt: 5.921 (5.921) Accm: 2.74 (2.74) Acct: 4.61 (4.61) proj_loss: -0.6254 (-0.6254) time: 0.9001 data: 0.0004 [11-25 13:53:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 0/1669] eta: 0:25:02 tlr: 0.00016 tnm: 0.25 Lm: 6.265 (6.265) Lt: 5.461 (5.461) Accm: 4.30 (4.30) Acct: 6.51 (6.51) proj_loss: -0.6428 (-0.6428) time: 0.9002 data: 0.0004 [11-25 13:53:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 0/1669] eta: 0:25:03 tlr: 0.00016 tnm: 0.25 Lm: 6.276 (6.276) Lt: 5.526 (5.526) Accm: 3.73 (3.73) Acct: 5.99 (5.99) proj_loss: -0.6371 (-0.6371) time: 0.9006 data: 0.0004 [11-25 13:53:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 0/1669] eta: 0:25:02 tlr: 0.00016 tnm: 0.25 Lm: 6.302 (6.302) Lt: 5.643 (5.643) Accm: 3.50 (3.50) Acct: 5.51 (5.51) proj_loss: -0.6581 (-0.6581) time: 0.9004 data: 0.0004 [11-25 13:53:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 0/1669] eta: 0:25:02 tlr: 0.00016 tnm: 0.25 Lm: 6.640 (6.640) Lt: 5.945 (5.945) Accm: 2.58 (2.58) Acct: 3.79 (3.79) proj_loss: -0.5895 (-0.5895) time: 0.9005 data: 0.0004 [11-25 13:53:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 0/1669] eta: 0:24:54 tlr: 0.00016 tnm: 0.25 Lm: 6.483 (6.483) Lt: 5.743 (5.743) Accm: 3.12 (3.12) Acct: 4.72 (4.72) proj_loss: -0.6047 (-0.6047) time: 0.8957 data: 0.0004 [11-25 13:53:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 0/1669] eta: 0:25:03 tlr: 0.00016 tnm: 0.25 Lm: 6.440 (6.440) Lt: 5.747 (5.747) Accm: 4.41 (4.41) Acct: 6.82 (6.82) proj_loss: -0.6218 (-0.6218) time: 0.9010 data: 0.0005 [11-25 13:53:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 0/1669] eta: 0:25:03 tlr: 0.00016 tnm: 0.25 Lm: 6.640 (6.640) Lt: 5.995 (5.995) Accm: 3.19 (3.19) Acct: 4.79 (4.79) proj_loss: -0.6361 (-0.6361) time: 0.9009 data: 0.0004 [11-25 14:00:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.24 Lm: 6.650 (6.650) Lt: 5.944 (5.944) Accm: 3.09 (3.09) Acct: 4.73 (4.73) proj_loss: -0.6071 (-0.6071) time: 0.9299 data: 0.0003 [11-25 14:00:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.24 Lm: 6.382 (6.382) Lt: 5.629 (5.629) Accm: 3.70 (3.70) Acct: 5.84 (5.84) proj_loss: -0.6257 (-0.6257) time: 0.9299 data: 0.0003 [11-25 14:00:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.24 Lm: 6.379 (6.379) Lt: 5.654 (5.654) Accm: 3.45 (3.45) Acct: 5.27 (5.27) proj_loss: -0.6219 (-0.6219) time: 0.9299 data: 0.0003 [11-25 14:00:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.24 Lm: 6.355 (6.355) Lt: 5.599 (5.599) Accm: 3.51 (3.51) Acct: 5.39 (5.39) proj_loss: -0.6118 (-0.6118) time: 0.9299 data: 0.0003 [11-25 14:00:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.24 Lm: 6.430 (6.430) Lt: 5.689 (5.689) Accm: 4.06 (4.06) Acct: 6.20 (6.20) proj_loss: -0.6188 (-0.6188) time: 0.9299 data: 0.0003 [11-25 14:00:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.24 Lm: 6.270 (6.270) Lt: 5.502 (5.502) Accm: 4.27 (4.27) Acct: 6.37 (6.37) proj_loss: -0.6353 (-0.6353) time: 0.9299 data: 0.0003 [11-25 14:00:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.24 Lm: 6.512 (6.512) Lt: 5.738 (5.738) Accm: 3.04 (3.04) Acct: 4.67 (4.67) proj_loss: -0.5897 (-0.5897) time: 0.9299 data: 0.0003 [11-25 14:00:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 417/1669] eta: 0:19:23 tlr: 0.00016 tnm: 0.24 Lm: 6.508 (6.508) Lt: 5.799 (5.799) Accm: 3.26 (3.26) Acct: 5.15 (5.15) proj_loss: -0.6406 (-0.6406) time: 0.9299 data: 0.0003 [11-25 14:06:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.25 Lm: 6.275 (6.334) Lt: 5.544 (5.573) Accm: 4.24 (3.93) Acct: 6.23 (5.98) proj_loss: -0.6351 (-0.6352) time: 0.9268 data: 0.0003 [11-25 14:06:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.25 Lm: 6.281 (6.348) Lt: 5.496 (5.585) Accm: 4.31 (3.90) Acct: 6.89 (6.19) proj_loss: -0.6254 (-0.6181) time: 0.9268 data: 0.0003 [11-25 14:06:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.25 Lm: 6.427 (6.395) Lt: 5.643 (5.643) Accm: 3.50 (3.48) Acct: 5.51 (5.43) proj_loss: -0.6266 (-0.6235) time: 0.9268 data: 0.0003 [11-25 14:06:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.25 Lm: 6.383 (6.466) Lt: 5.530 (5.666) Accm: 3.51 (3.33) Acct: 5.54 (5.27) proj_loss: -0.5899 (-0.5903) time: 0.9268 data: 0.0003 [11-25 14:06:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.25 Lm: 6.640 (6.587) Lt: 5.893 (5.835) Accm: 3.19 (3.37) Acct: 4.79 (5.39) proj_loss: -0.5781 (-0.5938) time: 0.9268 data: 0.0003 [11-25 14:06:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.25 Lm: 6.317 (6.342) Lt: 5.503 (5.567) Accm: 3.64 (3.55) Acct: 5.48 (5.42) proj_loss: -0.6083 (-0.6106) time: 0.9268 data: 0.0003 [11-25 14:06:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.25 Lm: 6.704 (6.573) Lt: 5.966 (5.854) Accm: 2.90 (3.14) Acct: 4.68 (4.99) proj_loss: -0.6371 (-0.6306) time: 0.9268 data: 0.0003 [11-25 14:06:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 834/1669] eta: 0:12:55 tlr: 0.00016 tnm: 0.25 Lm: 6.421 (6.410) Lt: 5.631 (5.649) Accm: 3.72 (3.83) Acct: 5.58 (5.97) proj_loss: -0.6209 (-0.6195) time: 0.9268 data: 0.0003 [11-25 14:13:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.24 Lm: 6.430 (6.444) Lt: 5.689 (5.675) Accm: 3.56 (3.73) Acct: 5.60 (5.88) proj_loss: -0.6183 (-0.6104) time: 0.9300 data: 0.0003 [11-25 14:13:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.24 Lm: 6.402 (6.392) Lt: 5.619 (5.624) Accm: 3.88 (3.79) Acct: 6.15 (5.99) proj_loss: -0.6141 (-0.6130) time: 0.9300 data: 0.0002 [11-25 14:13:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.24 Lm: 6.441 (6.451) Lt: 5.654 (5.697) Accm: 3.45 (3.43) Acct: 5.42 (5.41) proj_loss: -0.6097 (-0.6158) time: 0.9300 data: 0.0003 [11-25 14:13:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.24 Lm: 6.428 (6.468) Lt: 5.635 (5.684) Accm: 3.50 (3.37) Acct: 5.32 (5.23) proj_loss: -0.5903 (-0.5904) time: 0.9300 data: 0.0003 [11-25 14:13:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.24 Lm: 6.581 (6.545) Lt: 5.859 (5.829) Accm: 3.13 (3.19) Acct: 5.03 (5.09) proj_loss: -0.6291 (-0.6282) time: 0.9300 data: 0.0003 [11-25 14:13:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.24 Lm: 6.310 (6.336) Lt: 5.561 (5.574) Accm: 4.08 (3.93) Acct: 6.10 (5.97) proj_loss: -0.6315 (-0.6303) time: 0.9300 data: 0.0003 [11-25 14:13:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.24 Lm: 6.361 (6.358) Lt: 5.585 (5.592) Accm: 3.50 (3.51) Acct: 5.29 (5.34) proj_loss: -0.6065 (-0.6067) time: 0.9300 data: 0.0003 [11-25 14:13:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.24 Lm: 6.569 (6.564) Lt: 5.872 (5.838) Accm: 3.10 (3.28) Acct: 4.73 (5.17) proj_loss: -0.6071 (-0.6051) time: 0.9300 data: 0.0003 [11-25 14:19:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.526 (6.557) Lt: 5.850 (5.822) Accm: 3.19 (3.31) Acct: 4.79 (5.23) proj_loss: -0.6140 (-0.6069) time: 0.9303 data: 0.0014 [11-25 14:19:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 135/350] Total time: 0:25:49 (0.929 s / it) [11-25 14:19:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.408 (6.395) Lt: 5.668 (5.633) Accm: 3.61 (3.75) Acct: 5.44 (5.88) proj_loss: -0.6032 (-0.6110) time: 0.9303 data: 0.0021 [11-25 14:19:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.456 (6.478) Lt: 5.666 (5.719) Accm: 3.39 (3.35) Acct: 5.34 (5.36) proj_loss: -0.5928 (-0.6072) time: 0.9303 data: 0.0022 [11-25 14:19:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.528 (6.541) Lt: 5.777 (5.819) Accm: 2.94 (3.14) Acct: 4.68 (4.86) proj_loss: -0.6211 (-0.6173) time: 0.9303 data: 0.0014 [11-25 14:19:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.345 (6.352) Lt: 5.577 (5.586) Accm: 3.99 (3.94) Acct: 6.16 (6.01) proj_loss: -0.6278 (-0.6269) time: 0.9303 data: 0.0018 [11-25 14:19:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.473 (6.483) Lt: 5.740 (5.707) Accm: 3.51 (3.41) Acct: 5.37 (5.25) proj_loss: -0.5906 (-0.5952) time: 0.9303 data: 0.0017 [11-25 14:19:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.440 (6.466) Lt: 5.747 (5.711) Accm: 3.41 (3.60) Acct: 5.58 (5.72) proj_loss: -0.6157 (-0.6105) time: 0.9303 data: 0.0023 [11-25 14:19:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.404 (6.374) Lt: 5.667 (5.622) Accm: 3.53 (3.51) Acct: 5.48 (5.42) proj_loss: -0.6083 (-0.6112) time: 0.9303 data: 0.0023 [11-25 14:19:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 135/350] Total time: 0:25:49 (0.929 s / it) [11-25 14:19:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 135/350] Total time: 0:25:49 (0.929 s / it) [11-25 14:19:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 135/350] Total time: 0:25:49 (0.929 s / it) [11-25 14:19:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 135/350] Total time: 0:25:49 (0.929 s / it) [11-25 14:19:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 135/350] Total time: 0:25:49 (0.929 s / it) [11-25 14:19:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 135/350] Total time: 0:25:49 (0.929 s / it) [11-25 14:19:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 135/350] Total time: 0:25:49 (0.929 s / it) [11-25 14:19:34] (/home/user/VAR/train.py , line 276)=> [ep135] (training ) Lm: 6.451 (6.451), Lt: 5.694 (5.694), Acc m&t: 3.52 5.54, Remain: 3 days, 21:03:06, Finish: 2024-11-28 19:22 [11-25 14:19:34] (/home/user/VAR/train.py , line 276)=> [ep135] (training ) Lm: 6.451 (6.451), Lt: 5.694 (5.694), Acc m&t: 3.52 5.54, Remain: 3 days, 21:03:18, Finish: 2024-11-28 19:22 [11-25 14:19:34] (/home/user/VAR/train.py , line 276)=> [ep135] (training ) Lm: 6.451 (6.451), Lt: 5.694 (5.694), Acc m&t: 3.52 5.54, Remain: 3 days, 21:03:31, Finish: 2024-11-28 19:23 [11-25 14:19:34] (/home/user/VAR/train.py , line 276)=> [ep135] (training ) Lm: 6.451 (6.451), Lt: 5.694 (5.694), Acc m&t: 3.52 5.54, Remain: 3 days, 21:02:13, Finish: 2024-11-28 19:21 [11-25 14:19:34] (/home/user/VAR/train.py , line 276)=> [ep135] (training ) Lm: 6.451 (6.451), Lt: 5.694 (5.694), Acc m&t: 3.52 5.54, Remain: 3 days, 21:03:24, Finish: 2024-11-28 19:22 [11-25 14:19:34] (/home/user/VAR/train.py , line 276)=> [ep135] (training ) Lm: 6.451 (6.451), Lt: 5.694 (5.694), Acc m&t: 3.52 5.54, Remain: 3 days, 21:03:13, Finish: 2024-11-28 19:22 [11-25 14:19:34] (/home/user/VAR/train.py , line 276)=> [ep135] (training ) Lm: 6.451 (6.451), Lt: 5.694 (5.694), Acc m&t: 3.52 5.54, Remain: 3 days, 21:03:45, Finish: 2024-11-28 19:23 [11-25 14:19:34] (/home/user/VAR/train.py , line 276)=> [ep135] (training ) Lm: 6.451 (6.451), Lt: 5.694 (5.694), Acc m&t: 3.52 5.54, Remain: 3 days, 21:03:02, Finish: 2024-11-28 19:22 [11-25 14:19:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 0/1669] eta: 0:24:40 tlr: 0.00016 tnm: 0.23 Lm: 6.571 (6.571) Lt: 5.821 (5.821) Accm: 3.37 (3.37) Acct: 5.20 (5.20) proj_loss: -0.6265 (-0.6265) time: 0.8869 data: 0.0003 [11-25 14:19:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 0/1669] eta: 0:24:39 tlr: 0.00016 tnm: 0.23 Lm: 6.287 (6.287) Lt: 5.504 (5.504) Accm: 4.11 (4.11) Acct: 6.23 (6.23) proj_loss: -0.6341 (-0.6341) time: 0.8865 data: 0.0004 [11-25 14:19:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 0/1669] eta: 0:24:42 tlr: 0.00016 tnm: 0.23 Lm: 6.443 (6.443) Lt: 5.771 (5.771) Accm: 3.83 (3.83) Acct: 5.58 (5.58) proj_loss: -0.6078 (-0.6078) time: 0.8881 data: 0.0003 [11-25 14:19:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 0/1669] eta: 0:24:41 tlr: 0.00016 tnm: 0.23 Lm: 6.529 (6.529) Lt: 5.724 (5.724) Accm: 3.09 (3.09) Acct: 4.79 (4.79) proj_loss: -0.6044 (-0.6044) time: 0.8875 data: 0.0004 [11-25 14:19:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 0/1669] eta: 0:24:41 tlr: 0.00016 tnm: 0.23 Lm: 6.529 (6.529) Lt: 5.742 (5.742) Accm: 3.42 (3.42) Acct: 5.30 (5.30) proj_loss: -0.5862 (-0.5862) time: 0.8874 data: 0.0004 [11-25 14:19:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 0/1669] eta: 0:24:41 tlr: 0.00016 tnm: 0.23 Lm: 6.231 (6.231) Lt: 5.403 (5.403) Accm: 4.12 (4.12) Acct: 6.20 (6.20) proj_loss: -0.6343 (-0.6343) time: 0.8877 data: 0.0004 [11-25 14:19:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 0/1669] eta: 0:24:41 tlr: 0.00016 tnm: 0.23 Lm: 6.418 (6.418) Lt: 5.723 (5.723) Accm: 3.60 (3.60) Acct: 5.68 (5.68) proj_loss: -0.6119 (-0.6119) time: 0.8875 data: 0.0004 [11-25 14:19:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 0/1669] eta: 0:24:41 tlr: 0.00016 tnm: 0.23 Lm: 6.450 (6.450) Lt: 5.696 (5.696) Accm: 3.54 (3.54) Acct: 5.54 (5.54) proj_loss: -0.6408 (-0.6408) time: 0.8876 data: 0.0004 [11-25 14:26:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 417/1669] eta: 0:20:24 tlr: 0.00016 tnm: 0.25 Lm: 6.388 (6.388) Lt: 5.577 (5.577) Accm: 3.61 (3.61) Acct: 5.49 (5.49) proj_loss: -0.6202 (-0.6202) time: 0.9273 data: 0.0003 [11-25 14:26:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 417/1669] eta: 0:20:24 tlr: 0.00016 tnm: 0.25 Lm: 6.468 (6.468) Lt: 5.723 (5.723) Accm: 3.39 (3.39) Acct: 5.10 (5.10) proj_loss: -0.6161 (-0.6161) time: 0.9273 data: 0.0003 [11-25 14:26:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 417/1669] eta: 0:20:24 tlr: 0.00016 tnm: 0.25 Lm: 6.408 (6.408) Lt: 5.705 (5.705) Accm: 3.51 (3.51) Acct: 5.41 (5.41) proj_loss: -0.6249 (-0.6249) time: 0.9273 data: 0.0003 [11-25 14:26:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 417/1669] eta: 0:20:24 tlr: 0.00016 tnm: 0.25 Lm: 6.493 (6.493) Lt: 5.704 (5.704) Accm: 3.18 (3.18) Acct: 4.94 (4.94) proj_loss: -0.6099 (-0.6099) time: 0.9273 data: 0.0003 [11-25 14:26:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 417/1669] eta: 0:20:24 tlr: 0.00016 tnm: 0.25 Lm: 6.386 (6.386) Lt: 5.635 (5.635) Accm: 3.74 (3.74) Acct: 5.35 (5.35) proj_loss: -0.6257 (-0.6257) time: 0.9273 data: 0.0003 [11-25 14:26:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 417/1669] eta: 0:20:24 tlr: 0.00016 tnm: 0.25 Lm: 6.305 (6.305) Lt: 5.579 (5.579) Accm: 4.07 (4.07) Acct: 6.10 (6.10) proj_loss: -0.6023 (-0.6023) time: 0.9273 data: 0.0003 [11-25 14:26:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 417/1669] eta: 0:20:24 tlr: 0.00016 tnm: 0.25 Lm: 6.271 (6.271) Lt: 5.498 (5.498) Accm: 4.35 (4.35) Acct: 6.80 (6.80) proj_loss: -0.6312 (-0.6312) time: 0.9273 data: 0.0003 [11-25 14:26:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 417/1669] eta: 0:20:24 tlr: 0.00016 tnm: 0.25 Lm: 6.478 (6.478) Lt: 5.653 (5.653) Accm: 3.77 (3.77) Acct: 5.96 (5.96) proj_loss: -0.5907 (-0.5907) time: 0.9273 data: 0.0003 ======================================================= RESTART [11-25 15:07:00] ======================================================= ======================================================= RESTART [11-25 15:07:00] ======================================================= ======================================================= RESTART [11-25 15:07:00] ======================================================= ======================================================= RESTART [11-25 15:07:00] ======================================================= ======================================================= RESTART [11-25 15:07:00] ======================================================= ======================================================= RESTART [11-25 15:07:00] ======================================================= ======================================================= RESTART [11-25 15:07:00] ======================================================= ======================================================= RESTART [11-25 15:07:00] ======================================================= [11-25 15:07:00] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 15:07:00] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 15:07:00] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 15:08:42] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 15:08:42] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main commit_msg : add } [11-25 15:08:42] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 15:08:44] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 15:08:44] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> [11-25 15:08:44] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 15:08:44] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> [11-25 15:08:44] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 15:08:44] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-25 15:08:44] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep130, it0 [11-25 15:08:44] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-25 15:07:00] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 15:07:00] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 15:07:00] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 15:08:42] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 15:08:42] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-25 15:08:42] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 15:08:44] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 15:08:44] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> [11-25 15:08:44] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 15:08:44] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> [11-25 15:08:44] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 15:08:44] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-25 15:08:44] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep130, it0 [11-25 15:08:44] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-25 15:07:00] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 15:07:00] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 15:07:00] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 15:08:42] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 15:08:42] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-25 15:08:42] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 15:08:44] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 15:08:44] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> [11-25 15:08:44] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 15:08:44] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> [11-25 15:08:44] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 15:08:44] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-25 15:08:44] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep130, it0 [11-25 15:08:44] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-25 15:07:00] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 15:07:00] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 15:07:00] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 15:08:42] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 15:08:42] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add } [11-25 15:08:42] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 15:08:44] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 15:08:44] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> [11-25 15:08:44] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 15:08:44] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> [11-25 15:08:44] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 15:08:44] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-25 15:08:44] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep130, it0 [11-25 15:08:44] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-25 15:07:00] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 15:07:00] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 15:07:00] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 15:08:42] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 15:08:42] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main } [11-25 15:08:42] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 15:08:44] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 15:08:44] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> [11-25 15:08:44] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 15:08:44] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> [11-25 15:08:44] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 15:08:44] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-25 15:08:44] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep130, it0 [11-25 15:08:44] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-25 15:07:00] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 15:07:00] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 15:07:00] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 15:08:42] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 15:08:42] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add } [11-25 15:08:42] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 15:08:44] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 15:08:44] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> [11-25 15:08:44] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 15:08:44] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> [11-25 15:08:44] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 15:08:44] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-25 15:08:44] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep130, it0 [11-25 15:08:44] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-25 15:07:00] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 15:07:00] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 15:07:00] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 15:08:42] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 15:08:42] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main } [11-25 15:08:42] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 15:08:44] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 15:08:44] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> [11-25 15:08:44] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 15:08:44] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 15:08:44] (e/user/VAR/utils/data.py, line 51)=> [11-25 15:08:44] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 15:08:44] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-25 15:08:44] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep130, it0 [11-25 15:08:44] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-25 15:07:00] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-25 15:07:00] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-25 15:07:00] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-25 15:08:42] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-25 15:08:42] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add branch : main } [11-25 15:08:42] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-25 15:08:47] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-25 15:08:47] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-25 15:08:47] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 15:08:47] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-25 15:08:47] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 15:08:47] (e/user/VAR/utils/data.py, line 51)=> [11-25 15:08:47] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 15:08:47] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-25 15:08:47] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-25 15:08:47] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-25 15:08:47] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-25 15:08:47] (e/user/VAR/utils/data.py, line 51)=> [11-25 15:08:47] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-25 15:08:47] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-25 15:08:47] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep130, it0 [11-25 15:08:47] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ... [dataloader multi processing](*) finished! (48.33s) [dataloader multi processing](*) finished! (49.38s) [dataloader multi processing](*) finished! (49.56s) [dataloader multi processing](*) finished! (49.61s) [dataloader multi processing](*) finished! (49.98s) [dataloader multi processing](*) finished! (47.93s) [dataloader multi processing](*) finished! (50.91s) [dataloader multi processing](*) finished! (51.11s) [11-25 15:09:34] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 15:09:37] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 15:09:37] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 15:09:38] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-25 15:09:33] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 15:09:37] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 15:09:37] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 15:09:39] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-25 15:09:34] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 15:09:38] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 15:09:38] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 15:09:40] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-25 15:09:34] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 15:09:39] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 15:09:39] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 15:09:40] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-25 15:09:34] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 15:09:39] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 15:09:39] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 15:09:40] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-25 15:09:35] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 15:09:40] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 15:09:40] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 15:09:41] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-25 15:09:35] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 15:09:40] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 15:09:40] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 15:09:41] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-25 15:09:35] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-25 15:09:40] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 15:09:40] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-25 15:09:41] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-25 15:09:41] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 15:10:08] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 15:10:08] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 15:10:08] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 15:10:08] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 15:10:08] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank0] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 15:09:44] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 15:10:08] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 15:10:08] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 15:10:08] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 15:10:08] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 15:10:08] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank8] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 15:09:45] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 15:10:08] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 15:10:08] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 15:10:08] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 15:10:08] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 15:10:09] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank16] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 15:09:43] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 15:10:08] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 15:10:08] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 15:10:08] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 15:10:08] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 15:10:09] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank24] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 15:09:44] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 15:10:08] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 15:10:08] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 15:10:08] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 15:10:08] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 15:10:09] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank32] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 15:09:43] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 15:10:08] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 15:10:08] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 15:10:08] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 15:10:08] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 15:10:09] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank40] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 15:09:42] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 15:10:08] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 15:10:08] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 15:10:08] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 15:10:08] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 15:10:09] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank48] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 15:09:43] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-25 15:10:08] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-25 15:10:08] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-25 15:10:08] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-25 15:10:08] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-25 15:10:09] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank56] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-25 15:10:09] (/VAR/utils/lr_control.py, line 105)=> [11-25 15:10:09] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 15:10:11] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 15:10:11] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 15:10:12] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 15:10:12] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 15:16:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 0/1669] eta: 6 days, 19:08:24 tlr: 0.00016 tnm: 0.23 Lm: 6.602 (6.602) Lt: 5.855 (5.855) Accm: 3.15 (3.15) Acct: 4.58 (4.58) proj_loss: -0.6377 (-0.6377) time: 351.8900 data: 0.0006 [11-25 15:10:09] (/VAR/utils/lr_control.py, line 105)=> [11-25 15:10:09] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 15:10:11] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 15:10:11] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 15:10:12] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 15:10:12] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 15:16:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 0/1669] eta: 6 days, 19:14:46 tlr: 0.00016 tnm: 0.23 Lm: 6.646 (6.646) Lt: 5.894 (5.894) Accm: 2.97 (2.97) Acct: 4.48 (4.48) proj_loss: -0.6146 (-0.6146) time: 352.1188 data: 0.0006 [11-25 15:10:09] (/VAR/utils/lr_control.py, line 105)=> [11-25 15:10:09] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 15:10:11] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 15:10:11] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 15:10:12] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 15:10:12] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 15:16:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 0/1669] eta: 6 days, 19:05:52 tlr: 0.00016 tnm: 0.23 Lm: 6.219 (6.219) Lt: 5.428 (5.428) Accm: 3.72 (3.72) Acct: 6.06 (6.06) proj_loss: -0.6195 (-0.6195) time: 351.7987 data: 0.0006 [11-25 15:10:09] (/VAR/utils/lr_control.py, line 105)=> [11-25 15:10:09] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 15:10:12] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 15:10:12] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 15:10:12] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 15:10:12] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 15:16:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 0/1669] eta: 6 days, 18:54:44 tlr: 0.00016 tnm: 0.23 Lm: 6.466 (6.466) Lt: 5.767 (5.767) Accm: 3.45 (3.45) Acct: 5.44 (5.44) proj_loss: -0.5963 (-0.5963) time: 351.3989 data: 0.0006 [11-25 15:10:09] (/VAR/utils/lr_control.py, line 105)=> [11-25 15:10:09] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 15:10:12] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 15:10:12] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 15:10:12] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 15:10:12] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 15:16:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 0/1669] eta: 6 days, 19:41:50 tlr: 0.00016 tnm: 0.23 Lm: 6.592 (6.592) Lt: 5.908 (5.908) Accm: 2.86 (2.86) Acct: 4.24 (4.24) proj_loss: -0.6393 (-0.6393) time: 353.0920 data: 0.0007 [11-25 15:10:09] (/VAR/utils/lr_control.py, line 105)=> [11-25 15:10:09] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 15:10:12] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 15:10:12] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 15:10:12] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 15:10:12] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 15:16:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 0/1669] eta: 6 days, 19:00:28 tlr: 0.00016 tnm: 0.23 Lm: 6.508 (6.508) Lt: 5.814 (5.814) Accm: 3.31 (3.31) Acct: 5.17 (5.17) proj_loss: -0.6167 (-0.6167) time: 351.6046 data: 0.0006 [11-25 15:10:09] (/VAR/utils/lr_control.py, line 105)=> [11-25 15:10:09] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 15:10:11] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 15:10:11] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 15:10:12] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 15:10:12] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 15:16:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 0/1669] eta: 6 days, 19:25:07 tlr: 0.00016 tnm: 0.23 Lm: 6.503 (6.503) Lt: 5.766 (5.766) Accm: 3.39 (3.39) Acct: 5.17 (5.17) proj_loss: -0.6344 (-0.6344) time: 352.4908 data: 0.0007 [11-25 15:10:09] (/VAR/utils/lr_control.py, line 105)=> [11-25 15:10:09] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-25 15:10:12] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-25 15:10:12] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-25 15:10:13] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-25 15:10:13] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-25 15:16:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 0/1669] eta: 6 days, 19:16:54 tlr: 0.00016 tnm: 0.23 Lm: 6.198 (6.198) Lt: 5.456 (5.456) Accm: 4.15 (4.15) Acct: 6.37 (6.37) proj_loss: -0.6145 (-0.6145) time: 352.1956 data: 0.0007 [11-25 15:31:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 417/1669] eta: 1:02:40 tlr: 0.00016 tnm: 0.25 Lm: 6.494 (6.494) Lt: 5.787 (5.787) Accm: 3.41 (3.41) Acct: 5.27 (5.27) proj_loss: -0.6307 (-0.6307) time: 0.9201 data: 0.0002 [11-25 15:31:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 417/1669] eta: 1:02:42 tlr: 0.00016 tnm: 0.25 Lm: 6.324 (6.324) Lt: 5.584 (5.584) Accm: 3.92 (3.92) Acct: 6.01 (6.01) proj_loss: -0.6073 (-0.6073) time: 0.9201 data: 0.0002 [11-25 15:31:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 417/1669] eta: 1:02:41 tlr: 0.00016 tnm: 0.25 Lm: 6.597 (6.597) Lt: 5.847 (5.847) Accm: 3.22 (3.22) Acct: 4.73 (4.73) proj_loss: -0.6233 (-0.6233) time: 0.9201 data: 0.0002 [11-25 15:31:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 417/1669] eta: 1:02:41 tlr: 0.00016 tnm: 0.25 Lm: 6.361 (6.361) Lt: 5.633 (5.633) Accm: 3.48 (3.48) Acct: 5.65 (5.65) proj_loss: -0.6338 (-0.6338) time: 0.9201 data: 0.0002 [11-25 15:31:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 417/1669] eta: 1:02:45 tlr: 0.00016 tnm: 0.25 Lm: 6.507 (6.507) Lt: 5.812 (5.812) Accm: 2.94 (2.94) Acct: 4.49 (4.49) proj_loss: -0.6320 (-0.6320) time: 0.9201 data: 0.0002 [11-25 15:31:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 417/1669] eta: 1:02:43 tlr: 0.00016 tnm: 0.25 Lm: 6.292 (6.292) Lt: 5.524 (5.524) Accm: 4.04 (4.04) Acct: 6.22 (6.22) proj_loss: -0.6266 (-0.6266) time: 0.9201 data: 0.0003 [11-25 15:31:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 417/1669] eta: 1:02:40 tlr: 0.00016 tnm: 0.25 Lm: 6.561 (6.561) Lt: 5.822 (5.822) Accm: 3.16 (3.16) Acct: 5.06 (5.06) proj_loss: -0.6043 (-0.6043) time: 0.9201 data: 0.0003 [11-25 15:31:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 417/1669] eta: 1:02:42 tlr: 0.00016 tnm: 0.25 Lm: 6.536 (6.536) Lt: 5.810 (5.810) Accm: 3.35 (3.35) Acct: 4.98 (4.98) proj_loss: -0.6086 (-0.6086) time: 0.9201 data: 0.0003 [11-25 15:37:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 834/1669] eta: 0:27:20 tlr: 0.00016 tnm: 0.24 Lm: 6.425 (6.417) Lt: 5.727 (5.677) Accm: 3.73 (3.88) Acct: 5.48 (5.82) proj_loss: -0.6026 (-0.6004) time: 0.9233 data: 0.0003 [11-25 15:37:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 834/1669] eta: 0:27:20 tlr: 0.00016 tnm: 0.24 Lm: 6.402 (6.350) Lt: 5.509 (5.559) Accm: 3.96 (3.93) Acct: 6.16 (6.06) proj_loss: -0.6002 (-0.6000) time: 0.9233 data: 0.0002 [11-25 15:37:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 834/1669] eta: 0:27:19 tlr: 0.00016 tnm: 0.24 Lm: 6.468 (6.530) Lt: 5.767 (5.786) Accm: 2.97 (3.10) Acct: 4.79 (4.97) proj_loss: -0.6121 (-0.6069) time: 0.9233 data: 0.0003 [11-25 15:37:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 834/1669] eta: 0:27:21 tlr: 0.00016 tnm: 0.24 Lm: 6.592 (6.543) Lt: 5.895 (5.839) Accm: 3.03 (3.09) Acct: 4.75 (4.73) proj_loss: -0.6247 (-0.6274) time: 0.9233 data: 0.0002 [11-25 15:37:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 834/1669] eta: 0:27:20 tlr: 0.00016 tnm: 0.24 Lm: 6.503 (6.415) Lt: 5.757 (5.674) Accm: 3.25 (3.38) Acct: 5.23 (5.50) proj_loss: -0.6476 (-0.6384) time: 0.9233 data: 0.0003 [11-25 15:37:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 834/1669] eta: 0:27:20 tlr: 0.00016 tnm: 0.24 Lm: 6.593 (6.514) Lt: 5.838 (5.750) Accm: 3.29 (3.37) Acct: 4.89 (5.08) proj_loss: -0.6089 (-0.6155) time: 0.9233 data: 0.0003 [11-25 15:37:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 834/1669] eta: 0:27:21 tlr: 0.00016 tnm: 0.24 Lm: 6.469 (6.351) Lt: 5.699 (5.582) Accm: 3.41 (3.83) Acct: 5.41 (5.95) proj_loss: -0.6188 (-0.6210) time: 0.9233 data: 0.0003 [11-25 15:37:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [ 834/1669] eta: 0:27:20 tlr: 0.00016 tnm: 0.24 Lm: 6.480 (6.462) Lt: 5.761 (5.724) Accm: 3.51 (3.50) Acct: 5.37 (5.49) proj_loss: -0.6167 (-0.6246) time: 0.9234 data: 0.0002 [11-25 15:44:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1251/1669] eta: 0:11:16 tlr: 0.00016 tnm: 0.24 Lm: 6.440 (6.423) Lt: 5.695 (5.700) Accm: 3.59 (3.60) Acct: 5.56 (5.55) proj_loss: -0.6307 (-0.6328) time: 0.9218 data: 0.0002 [11-25 15:44:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1251/1669] eta: 0:11:16 tlr: 0.00016 tnm: 0.24 Lm: 6.591 (6.533) Lt: 5.847 (5.793) Accm: 3.22 (3.27) Acct: 4.73 (4.95) proj_loss: -0.6205 (-0.6197) time: 0.9218 data: 0.0002 [11-25 15:44:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1251/1669] eta: 0:11:16 tlr: 0.00016 tnm: 0.24 Lm: 6.521 (6.520) Lt: 5.819 (5.815) Accm: 3.21 (3.26) Acct: 4.98 (4.96) proj_loss: -0.6252 (-0.6270) time: 0.9218 data: 0.0002 [11-25 15:44:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1251/1669] eta: 0:11:16 tlr: 0.00016 tnm: 0.24 Lm: 6.492 (6.431) Lt: 5.731 (5.682) Accm: 3.39 (3.41) Acct: 5.22 (5.42) proj_loss: -0.6335 (-0.6306) time: 0.9218 data: 0.0002 [11-25 15:44:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1251/1669] eta: 0:11:16 tlr: 0.00016 tnm: 0.24 Lm: 6.462 (6.437) Lt: 5.737 (5.694) Accm: 3.37 (3.66) Acct: 5.23 (5.61) proj_loss: -0.6086 (-0.6090) time: 0.9218 data: 0.0003 [11-25 15:44:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1251/1669] eta: 0:11:16 tlr: 0.00016 tnm: 0.24 Lm: 6.426 (6.398) Lt: 5.601 (5.593) Accm: 3.82 (3.73) Acct: 5.91 (5.80) proj_loss: -0.5953 (-0.5976) time: 0.9218 data: 0.0003 [11-25 15:44:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1251/1669] eta: 0:11:16 tlr: 0.00016 tnm: 0.24 Lm: 6.428 (6.360) Lt: 5.648 (5.586) Accm: 3.55 (3.80) Acct: 5.54 (5.88) proj_loss: -0.6184 (-0.6203) time: 0.9218 data: 0.0003 [11-25 15:44:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1251/1669] eta: 0:11:16 tlr: 0.00016 tnm: 0.24 Lm: 6.467 (6.500) Lt: 5.740 (5.733) Accm: 3.21 (3.19) Acct: 5.08 (5.07) proj_loss: -0.6042 (-0.6042) time: 0.9218 data: 0.0002 [11-25 15:50:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1668/1669] eta: 0:00:01 tlr: 0.00016 tnm: 0.23 Lm: 6.466 (6.483) Lt: 5.712 (5.716) Accm: 3.29 (3.21) Acct: 5.37 (5.13) proj_loss: -0.6121 (-0.6078) time: 0.9241 data: 0.0019 [11-25 15:50:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 130/350] Total time: 0:40:09 (1.444 s / it) [11-25 15:50:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1668/1669] eta: 0:00:01 tlr: 0.00016 tnm: 0.23 Lm: 6.400 (6.406) Lt: 5.629 (5.653) Accm: 3.67 (3.62) Acct: 5.75 (5.65) proj_loss: -0.6167 (-0.6292) time: 0.9241 data: 0.0017 [11-25 15:50:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1668/1669] eta: 0:00:01 tlr: 0.00016 tnm: 0.23 Lm: 6.589 (6.508) Lt: 5.838 (5.763) Accm: 3.29 (3.39) Acct: 4.89 (5.16) proj_loss: -0.6233 (-0.6204) time: 0.9241 data: 0.0015 [11-25 15:50:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1668/1669] eta: 0:00:01 tlr: 0.00016 tnm: 0.23 Lm: 6.469 (6.417) Lt: 5.699 (5.650) Accm: 3.41 (3.61) Acct: 5.41 (5.58) proj_loss: -0.6188 (-0.6221) time: 0.9241 data: 0.0015 [11-25 15:50:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1668/1669] eta: 0:00:01 tlr: 0.00016 tnm: 0.23 Lm: 6.498 (6.468) Lt: 5.747 (5.729) Accm: 3.07 (3.55) Acct: 4.99 (5.43) proj_loss: -0.6026 (-0.6060) time: 0.9241 data: 0.0016 [11-25 15:50:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1668/1669] eta: 0:00:01 tlr: 0.00016 tnm: 0.23 Lm: 6.450 (6.429) Lt: 5.694 (5.654) Accm: 3.69 (3.59) Acct: 5.65 (5.54) proj_loss: -0.6002 (-0.6010) time: 0.9241 data: 0.0014 [11-25 15:50:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1668/1669] eta: 0:00:01 tlr: 0.00016 tnm: 0.23 Lm: 6.592 (6.552) Lt: 5.895 (5.841) Accm: 3.03 (3.20) Acct: 4.75 (4.85) proj_loss: -0.6258 (-0.6278) time: 0.9241 data: 0.0019 [11-25 15:50:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 130/350] [1668/1669] eta: 0:00:01 tlr: 0.00016 tnm: 0.23 Lm: 6.481 (6.424) Lt: 5.705 (5.679) Accm: 3.41 (3.41) Acct: 5.20 (5.32) proj_loss: -0.6195 (-0.6237) time: 0.9241 data: 0.0016 [11-25 15:50:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 130/350] Total time: 0:40:10 (1.444 s / it) [11-25 15:50:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 130/350] Total time: 0:40:10 (1.444 s / it) [11-25 15:50:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 130/350] Total time: 0:40:11 (1.445 s / it) [11-25 15:50:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 130/350] Total time: 0:40:10 (1.444 s / it) [11-25 15:50:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 130/350] Total time: 0:40:10 (1.444 s / it) [11-25 15:50:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 130/350] Total time: 0:40:11 (1.445 s / it) [11-25 15:50:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 130/350] Total time: 0:40:10 (1.444 s / it) [11-25 15:50:32] (/home/user/VAR/train.py , line 276)=> [ep130] (training ) Lm: 6.463 (6.463), Lt: 5.710 (5.710), Acc m&t: 3.46 5.41, Remain: 3 days, 22:29:25, Finish: 2024-11-28 22:19 [11-25 15:50:32] (/home/user/VAR/train.py , line 276)=> [ep130] (training ) Lm: 6.463 (6.463), Lt: 5.710 (5.710), Acc m&t: 3.46 5.41, Remain: 3 days, 22:30:25, Finish: 2024-11-28 22:20 [11-25 15:50:32] (/home/user/VAR/train.py , line 276)=> [ep130] (training ) Lm: 6.463 (6.463), Lt: 5.710 (5.710), Acc m&t: 3.46 5.41, Remain: 3 days, 22:26:50, Finish: 2024-11-28 22:17 [11-25 15:50:32] (/home/user/VAR/train.py , line 276)=> [ep130] (training ) Lm: 6.463 (6.463), Lt: 5.710 (5.710), Acc m&t: 3.46 5.41, Remain: 3 days, 22:29:23, Finish: 2024-11-28 22:19 [11-25 15:50:32] (/home/user/VAR/train.py , line 276)=> [ep130] (training ) Lm: 6.463 (6.463), Lt: 5.710 (5.710), Acc m&t: 3.46 5.41, Remain: 3 days, 22:27:27, Finish: 2024-11-28 22:17 [11-25 15:50:32] (/home/user/VAR/train.py , line 276)=> [ep130] (training ) Lm: 6.463 (6.463), Lt: 5.710 (5.710), Acc m&t: 3.46 5.41, Remain: 3 days, 22:27:21, Finish: 2024-11-28 22:17 [11-25 15:50:32] (/home/user/VAR/train.py , line 276)=> [ep130] (training ) Lm: 6.463 (6.463), Lt: 5.710 (5.710), Acc m&t: 3.46 5.41, Remain: 3 days, 22:27:46, Finish: 2024-11-28 22:18 [11-25 15:50:32] (/home/user/VAR/train.py , line 276)=> [ep130] (training ) Lm: 6.463 (6.463), Lt: 5.710 (5.710), Acc m&t: 3.46 5.41, Remain: 3 days, 22:30:01, Finish: 2024-11-28 22:20 [11-25 15:50:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 0/1669] eta: 0:25:04 tlr: 0.00016 tnm: 0.23 Lm: 6.300 (6.300) Lt: 5.503 (5.503) Accm: 4.27 (4.27) Acct: 6.99 (6.99) proj_loss: -0.6306 (-0.6306) time: 0.9013 data: 0.0003 [11-25 15:50:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 0/1669] eta: 0:26:05 tlr: 0.00016 tnm: 0.23 Lm: 6.506 (6.506) Lt: 5.698 (5.698) Accm: 3.44 (3.44) Acct: 5.82 (5.82) proj_loss: -0.5874 (-0.5874) time: 0.9380 data: 0.0003 [11-25 15:50:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 0/1669] eta: 0:25:04 tlr: 0.00016 tnm: 0.23 Lm: 6.071 (6.071) Lt: 5.254 (5.254) Accm: 4.98 (4.98) Acct: 8.26 (8.26) proj_loss: -0.6344 (-0.6344) time: 0.9014 data: 0.0003 [11-25 15:50:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 0/1669] eta: 0:25:04 tlr: 0.00016 tnm: 0.23 Lm: 6.508 (6.508) Lt: 5.765 (5.765) Accm: 3.13 (3.13) Acct: 4.89 (4.89) proj_loss: -0.6300 (-0.6300) time: 0.9015 data: 0.0005 [11-25 15:50:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 0/1669] eta: 0:25:05 tlr: 0.00016 tnm: 0.23 Lm: 6.478 (6.478) Lt: 5.624 (5.624) Accm: 3.29 (3.29) Acct: 5.65 (5.65) proj_loss: -0.5886 (-0.5886) time: 0.9019 data: 0.0004 [11-25 15:50:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 0/1669] eta: 0:25:05 tlr: 0.00016 tnm: 0.23 Lm: 6.315 (6.315) Lt: 5.523 (5.523) Accm: 3.74 (3.74) Acct: 5.61 (5.61) proj_loss: -0.5913 (-0.5913) time: 0.9019 data: 0.0003 [11-25 15:50:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 0/1669] eta: 0:25:05 tlr: 0.00016 tnm: 0.23 Lm: 6.470 (6.470) Lt: 5.791 (5.791) Accm: 3.13 (3.13) Acct: 5.17 (5.17) proj_loss: -0.6062 (-0.6062) time: 0.9019 data: 0.0003 [11-25 15:50:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 0/1669] eta: 0:25:02 tlr: 0.00016 tnm: 0.23 Lm: 6.548 (6.548) Lt: 5.815 (5.815) Accm: 3.18 (3.18) Acct: 4.75 (4.75) proj_loss: -0.6107 (-0.6107) time: 0.9002 data: 0.0006 [11-25 15:57:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 417/1669] eta: 0:19:31 tlr: 0.00016 tnm: 0.25 Lm: 6.532 (6.532) Lt: 5.782 (5.782) Accm: 2.93 (2.93) Acct: 4.65 (4.65) proj_loss: -0.6057 (-0.6057) time: 0.9220 data: 0.0003 [11-25 15:57:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 417/1669] eta: 0:19:31 tlr: 0.00016 tnm: 0.25 Lm: 6.498 (6.498) Lt: 5.738 (5.738) Accm: 3.31 (3.31) Acct: 4.98 (4.98) proj_loss: -0.6081 (-0.6081) time: 0.9220 data: 0.0002 [11-25 15:57:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 417/1669] eta: 0:19:31 tlr: 0.00016 tnm: 0.25 Lm: 6.380 (6.380) Lt: 5.543 (5.543) Accm: 3.96 (3.96) Acct: 6.40 (6.40) proj_loss: -0.6027 (-0.6027) time: 0.9220 data: 0.0002 [11-25 15:57:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 417/1669] eta: 0:19:31 tlr: 0.00016 tnm: 0.25 Lm: 6.600 (6.600) Lt: 5.909 (5.909) Accm: 2.89 (2.89) Acct: 4.56 (4.56) proj_loss: -0.6124 (-0.6124) time: 0.9220 data: 0.0003 [11-25 15:57:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 417/1669] eta: 0:19:31 tlr: 0.00016 tnm: 0.25 Lm: 6.659 (6.659) Lt: 5.941 (5.941) Accm: 3.07 (3.07) Acct: 4.96 (4.96) proj_loss: -0.6129 (-0.6129) time: 0.9220 data: 0.0002 [11-25 15:57:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 417/1669] eta: 0:19:31 tlr: 0.00016 tnm: 0.25 Lm: 6.421 (6.421) Lt: 5.631 (5.631) Accm: 3.29 (3.29) Acct: 5.54 (5.54) proj_loss: -0.6115 (-0.6115) time: 0.9220 data: 0.0002 [11-25 15:57:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 417/1669] eta: 0:19:31 tlr: 0.00016 tnm: 0.25 Lm: 6.515 (6.515) Lt: 5.722 (5.722) Accm: 3.10 (3.10) Acct: 4.87 (4.87) proj_loss: -0.5998 (-0.5998) time: 0.9220 data: 0.0002 [11-25 15:57:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 417/1669] eta: 0:19:31 tlr: 0.00016 tnm: 0.25 Lm: 6.490 (6.490) Lt: 5.701 (5.701) Accm: 3.53 (3.53) Acct: 5.87 (5.87) proj_loss: -0.6155 (-0.6155) time: 0.9221 data: 0.0002 [11-25 16:03:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 834/1669] eta: 0:12:56 tlr: 0.00016 tnm: 0.25 Lm: 6.623 (6.535) Lt: 5.909 (5.771) Accm: 2.67 (3.24) Acct: 4.24 (5.33) proj_loss: -0.6344 (-0.6221) time: 0.9237 data: 0.0003 [11-25 16:03:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 834/1669] eta: 0:12:56 tlr: 0.00016 tnm: 0.25 Lm: 6.517 (6.612) Lt: 5.703 (5.862) Accm: 3.44 (3.23) Acct: 5.82 (5.31) proj_loss: -0.5874 (-0.6004) time: 0.9237 data: 0.0002 [11-25 16:03:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 834/1669] eta: 0:12:56 tlr: 0.00016 tnm: 0.25 Lm: 6.730 (6.665) Lt: 6.027 (5.967) Accm: 2.72 (2.84) Acct: 4.75 (4.63) proj_loss: -0.6062 (-0.6026) time: 0.9237 data: 0.0002 [11-25 16:03:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 834/1669] eta: 0:12:56 tlr: 0.00016 tnm: 0.25 Lm: 6.478 (6.520) Lt: 5.638 (5.751) Accm: 3.28 (3.17) Acct: 5.44 (5.18) proj_loss: -0.6059 (-0.6096) time: 0.9237 data: 0.0002 [11-25 16:03:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 834/1669] eta: 0:12:56 tlr: 0.00016 tnm: 0.25 Lm: 6.460 (6.443) Lt: 5.584 (5.649) Accm: 3.66 (3.64) Acct: 5.82 (5.83) proj_loss: -0.5925 (-0.5993) time: 0.9237 data: 0.0003 [11-25 16:03:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 834/1669] eta: 0:12:56 tlr: 0.00016 tnm: 0.25 Lm: 6.540 (6.535) Lt: 5.790 (5.784) Accm: 3.18 (3.05) Acct: 4.75 (4.91) proj_loss: -0.6107 (-0.6102) time: 0.9237 data: 0.0003 [11-25 16:03:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 834/1669] eta: 0:12:56 tlr: 0.00016 tnm: 0.25 Lm: 6.495 (6.508) Lt: 5.774 (5.739) Accm: 3.74 (3.32) Acct: 5.61 (5.15) proj_loss: -0.6082 (-0.6112) time: 0.9237 data: 0.0003 [11-25 16:03:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [ 834/1669] eta: 0:12:56 tlr: 0.00016 tnm: 0.25 Lm: 6.508 (6.559) Lt: 5.765 (5.814) Accm: 3.16 (3.26) Acct: 5.06 (5.03) proj_loss: -0.6067 (-0.6076) time: 0.9238 data: 0.0002 [11-25 16:09:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1251/1669] eta: 0:06:27 tlr: 0.00016 tnm: 0.24 Lm: 6.498 (6.507) Lt: 5.738 (5.750) Accm: 3.32 (3.33) Acct: 5.10 (5.18) proj_loss: -0.6063 (-0.6072) time: 0.9235 data: 0.0002 [11-25 16:09:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1251/1669] eta: 0:06:27 tlr: 0.00016 tnm: 0.24 Lm: 6.600 (6.586) Lt: 5.909 (5.874) Accm: 2.93 (3.04) Acct: 4.96 (4.97) proj_loss: -0.6085 (-0.6047) time: 0.9235 data: 0.0002 [11-25 16:09:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1251/1669] eta: 0:06:27 tlr: 0.00016 tnm: 0.24 Lm: 6.515 (6.482) Lt: 5.692 (5.687) Accm: 3.36 (3.49) Acct: 5.41 (5.62) proj_loss: -0.5918 (-0.5972) time: 0.9235 data: 0.0002 [11-25 16:09:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1251/1669] eta: 0:06:27 tlr: 0.00016 tnm: 0.24 Lm: 6.566 (6.553) Lt: 5.781 (5.794) Accm: 3.10 (3.07) Acct: 5.17 (5.11) proj_loss: -0.6112 (-0.6114) time: 0.9234 data: 0.0003 [11-25 16:09:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1251/1669] eta: 0:06:27 tlr: 0.00016 tnm: 0.24 Lm: 6.548 (6.603) Lt: 5.778 (5.860) Accm: 3.37 (3.25) Acct: 5.51 (5.29) proj_loss: -0.6038 (-0.6054) time: 0.9234 data: 0.0003 [11-25 16:09:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1251/1669] eta: 0:06:27 tlr: 0.00016 tnm: 0.24 Lm: 6.528 (6.494) Lt: 5.769 (5.737) Accm: 3.23 (3.27) Acct: 5.10 (5.30) proj_loss: -0.6096 (-0.6098) time: 0.9235 data: 0.0003 [11-25 16:09:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1251/1669] eta: 0:06:27 tlr: 0.00016 tnm: 0.24 Lm: 6.453 (6.484) Lt: 5.704 (5.713) Accm: 3.48 (3.30) Acct: 5.27 (5.10) proj_loss: -0.6098 (-0.6112) time: 0.9235 data: 0.0003 [11-25 16:09:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1251/1669] eta: 0:06:27 tlr: 0.00016 tnm: 0.24 Lm: 6.497 (6.494) Lt: 5.722 (5.712) Accm: 3.32 (3.43) Acct: 5.20 (5.54) proj_loss: -0.6155 (-0.6137) time: 0.9235 data: 0.0003 [11-25 16:16:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.508 (6.497) Lt: 5.733 (5.716) Accm: 3.61 (3.46) Acct: 5.06 (5.44) proj_loss: -0.6244 (-0.6158) time: 0.9249 data: 0.0016 [11-25 16:16:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 131/350] Total time: 0:25:46 (0.927 s / it) [11-25 16:16:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.538 (6.590) Lt: 5.850 (5.858) Accm: 3.32 (3.26) Acct: 5.20 (5.22) proj_loss: -0.6201 (-0.6131) time: 0.9249 data: 0.0015 [11-25 16:16:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.488 (6.493) Lt: 5.712 (5.727) Accm: 3.48 (3.37) Acct: 5.13 (5.19) proj_loss: -0.6067 (-0.6100) time: 0.9249 data: 0.0020 [11-25 16:16:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.555 (6.554) Lt: 5.804 (5.796) Accm: 3.28 (3.12) Acct: 5.23 (5.13) proj_loss: -0.6059 (-0.6081) time: 0.9249 data: 0.0016 [11-25 16:16:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.542 (6.577) Lt: 5.791 (5.849) Accm: 3.13 (3.11) Acct: 4.79 (4.93) proj_loss: -0.6062 (-0.6008) time: 0.9249 data: 0.0015 [11-25 16:16:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.460 (6.462) Lt: 5.630 (5.676) Accm: 3.29 (3.45) Acct: 5.03 (5.50) proj_loss: -0.5925 (-0.6037) time: 0.9249 data: 0.0017 [11-25 16:16:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.540 (6.519) Lt: 5.790 (5.769) Accm: 3.18 (3.19) Acct: 4.75 (5.18) proj_loss: -0.6085 (-0.6093) time: 0.9249 data: 0.0019 [11-25 16:16:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 131/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.495 (6.514) Lt: 5.774 (5.764) Accm: 3.23 (3.28) Acct: 4.99 (5.08) proj_loss: -0.6082 (-0.6090) time: 0.9248 data: 0.0015 [11-25 16:16:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 131/350] Total time: 0:25:46 (0.927 s / it) [11-25 16:16:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 131/350] Total time: 0:25:46 (0.927 s / it) [11-25 16:16:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 131/350] Total time: 0:25:46 (0.927 s / it) [11-25 16:16:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 131/350] Total time: 0:25:46 (0.927 s / it) [11-25 16:16:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 131/350] Total time: 0:25:46 (0.927 s / it) [11-25 16:16:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 131/350] Total time: 0:25:46 (0.927 s / it) [11-25 16:16:19] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 131/350] Total time: 0:25:46 (0.927 s / it) [11-25 16:16:19] (/home/user/VAR/train.py , line 276)=> [ep131] (training ) Lm: 6.463 (6.481), Lt: 5.710 (5.726), Acc m&t: 3.46 5.41, Remain: 3 days, 21:57:01, Finish: 2024-11-28 22:13 [11-25 16:16:19] (/home/user/VAR/train.py , line 276)=> [ep131] (training ) Lm: 6.463 (6.481), Lt: 5.710 (5.726), Acc m&t: 3.46 5.41, Remain: 3 days, 21:56:46, Finish: 2024-11-28 22:13 [11-25 16:16:19] (/home/user/VAR/train.py , line 276)=> [ep131] (training ) Lm: 6.463 (6.481), Lt: 5.710 (5.726), Acc m&t: 3.46 5.41, Remain: 3 days, 21:57:14, Finish: 2024-11-28 22:13 [11-25 16:16:19] (/home/user/VAR/train.py , line 276)=> [ep131] (training ) Lm: 6.463 (6.481), Lt: 5.710 (5.726), Acc m&t: 3.46 5.41, Remain: 3 days, 21:55:21, Finish: 2024-11-28 22:11 [11-25 16:16:19] (/home/user/VAR/train.py , line 276)=> [ep131] (training ) Lm: 6.463 (6.481), Lt: 5.710 (5.726), Acc m&t: 3.46 5.41, Remain: 3 days, 21:55:33, Finish: 2024-11-28 22:11 [11-25 16:16:19] (/home/user/VAR/train.py , line 276)=> [ep131] (training ) Lm: 6.463 (6.481), Lt: 5.710 (5.726), Acc m&t: 3.46 5.41, Remain: 3 days, 21:56:10, Finish: 2024-11-28 22:12 [11-25 16:16:19] (/home/user/VAR/train.py , line 276)=> [ep131] (training ) Lm: 6.463 (6.481), Lt: 5.710 (5.726), Acc m&t: 3.46 5.41, Remain: 3 days, 21:56:02, Finish: 2024-11-28 22:12 [11-25 16:16:19] (/home/user/VAR/train.py , line 276)=> [ep131] (training ) Lm: 6.463 (6.481), Lt: 5.710 (5.726), Acc m&t: 3.46 5.41, Remain: 3 days, 21:57:41, Finish: 2024-11-28 22:13 [11-25 16:16:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 0/1669] eta: 0:25:30 tlr: 0.00016 tnm: 0.24 Lm: 6.414 (6.414) Lt: 5.619 (5.619) Accm: 3.29 (3.29) Acct: 5.27 (5.27) proj_loss: -0.6015 (-0.6015) time: 0.9172 data: 0.0003 [11-25 16:16:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 0/1669] eta: 0:25:30 tlr: 0.00016 tnm: 0.24 Lm: 6.580 (6.580) Lt: 5.892 (5.892) Accm: 3.02 (3.02) Acct: 4.34 (4.34) proj_loss: -0.6154 (-0.6154) time: 0.9170 data: 0.0004 [11-25 16:16:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 0/1669] eta: 0:25:31 tlr: 0.00016 tnm: 0.24 Lm: 6.421 (6.421) Lt: 5.683 (5.683) Accm: 3.86 (3.86) Acct: 6.20 (6.20) proj_loss: -0.5912 (-0.5912) time: 0.9175 data: 0.0003 [11-25 16:16:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 0/1669] eta: 0:25:39 tlr: 0.00016 tnm: 0.24 Lm: 6.396 (6.396) Lt: 5.587 (5.587) Accm: 3.67 (3.67) Acct: 6.16 (6.16) proj_loss: -0.6093 (-0.6093) time: 0.9227 data: 0.0004 [11-25 16:16:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 0/1669] eta: 0:25:32 tlr: 0.00016 tnm: 0.24 Lm: 6.379 (6.379) Lt: 5.666 (5.666) Accm: 3.53 (3.53) Acct: 5.89 (5.89) proj_loss: -0.6037 (-0.6037) time: 0.9182 data: 0.0003 [11-25 16:16:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 0/1669] eta: 0:25:31 tlr: 0.00016 tnm: 0.24 Lm: 6.444 (6.444) Lt: 5.593 (5.593) Accm: 3.18 (3.18) Acct: 5.23 (5.23) proj_loss: -0.5918 (-0.5918) time: 0.9177 data: 0.0003 [11-25 16:16:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 0/1669] eta: 0:25:31 tlr: 0.00016 tnm: 0.24 Lm: 6.370 (6.370) Lt: 5.611 (5.611) Accm: 3.58 (3.58) Acct: 5.51 (5.51) proj_loss: -0.6209 (-0.6209) time: 0.9177 data: 0.0004 [11-25 16:16:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 0/1669] eta: 0:25:32 tlr: 0.00016 tnm: 0.24 Lm: 6.580 (6.580) Lt: 5.805 (5.805) Accm: 2.81 (2.81) Acct: 4.30 (4.30) proj_loss: -0.5664 (-0.5664) time: 0.9181 data: 0.0004 [11-25 16:22:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.456 (6.456) Lt: 5.711 (5.711) Accm: 3.21 (3.21) Acct: 5.17 (5.17) proj_loss: -0.5987 (-0.5987) time: 0.9227 data: 0.0003 [11-25 16:22:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.414 (6.414) Lt: 5.639 (5.639) Accm: 3.53 (3.53) Acct: 5.51 (5.51) proj_loss: -0.5938 (-0.5938) time: 0.9227 data: 0.0002 [11-25 16:22:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.382 (6.382) Lt: 5.632 (5.632) Accm: 3.47 (3.47) Acct: 5.70 (5.70) proj_loss: -0.6222 (-0.6222) time: 0.9227 data: 0.0002 [11-25 16:22:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.360 (6.360) Lt: 5.544 (5.544) Accm: 3.62 (3.62) Acct: 5.51 (5.51) proj_loss: -0.6004 (-0.6004) time: 0.9227 data: 0.0002 [11-25 16:22:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.474 (6.474) Lt: 5.739 (5.739) Accm: 3.72 (3.72) Acct: 5.89 (5.89) proj_loss: -0.5996 (-0.5996) time: 0.9227 data: 0.0003 [11-25 16:22:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.545 (6.545) Lt: 5.724 (5.724) Accm: 3.13 (3.13) Acct: 5.27 (5.27) proj_loss: -0.6043 (-0.6043) time: 0.9227 data: 0.0002 [11-25 16:22:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.318 (6.318) Lt: 5.588 (5.588) Accm: 3.89 (3.89) Acct: 5.99 (5.99) proj_loss: -0.6244 (-0.6244) time: 0.9227 data: 0.0003 [11-25 16:22:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.486 (6.486) Lt: 5.752 (5.752) Accm: 3.31 (3.31) Acct: 5.18 (5.18) proj_loss: -0.6002 (-0.6002) time: 0.9227 data: 0.0003 [11-25 16:29:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.24 Lm: 6.507 (6.493) Lt: 5.760 (5.754) Accm: 3.07 (3.23) Acct: 4.72 (5.03) proj_loss: -0.6154 (-0.6062) time: 0.9256 data: 0.0003 [11-25 16:29:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.24 Lm: 6.396 (6.407) Lt: 5.637 (5.639) Accm: 3.67 (3.61) Acct: 5.99 (5.67) proj_loss: -0.5965 (-0.5947) time: 0.9256 data: 0.0002 [11-25 16:29:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.24 Lm: 6.444 (6.496) Lt: 5.670 (5.706) Accm: 3.18 (3.28) Acct: 5.30 (5.48) proj_loss: -0.6169 (-0.6223) time: 0.9256 data: 0.0002 [11-25 16:29:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.24 Lm: 6.414 (6.421) Lt: 5.619 (5.623) Accm: 3.29 (3.46) Acct: 5.27 (5.35) proj_loss: -0.6015 (-0.6008) time: 0.9256 data: 0.0002 [11-25 16:29:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.24 Lm: 6.510 (6.486) Lt: 5.796 (5.779) Accm: 3.57 (3.55) Acct: 5.58 (5.64) proj_loss: -0.6080 (-0.6156) time: 0.9256 data: 0.0002 [11-25 16:29:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.24 Lm: 6.370 (6.391) Lt: 5.611 (5.671) Accm: 3.58 (3.66) Acct: 5.51 (5.60) proj_loss: -0.6209 (-0.6142) time: 0.9256 data: 0.0003 [11-25 16:29:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.24 Lm: 6.434 (6.449) Lt: 5.654 (5.692) Accm: 3.42 (3.28) Acct: 5.34 (5.22) proj_loss: -0.5785 (-0.5920) time: 0.9256 data: 0.0003 [11-25 16:29:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.24 Lm: 6.379 (6.296) Lt: 5.599 (5.545) Accm: 3.53 (3.85) Acct: 5.89 (6.20) proj_loss: -0.6372 (-0.6272) time: 0.9256 data: 0.0003 [11-25 16:35:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.23 Lm: 6.382 (6.394) Lt: 5.632 (5.654) Accm: 3.47 (3.64) Acct: 5.70 (5.91) proj_loss: -0.6204 (-0.6186) time: 0.9234 data: 0.0003 [11-25 16:35:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.23 Lm: 6.471 (6.478) Lt: 5.703 (5.727) Accm: 3.34 (3.35) Acct: 5.32 (5.25) proj_loss: -0.6168 (-0.6146) time: 0.9234 data: 0.0003 [11-25 16:35:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.23 Lm: 6.378 (6.401) Lt: 5.601 (5.613) Accm: 3.47 (3.50) Acct: 5.39 (5.39) proj_loss: -0.6016 (-0.6076) time: 0.9234 data: 0.0002 [11-25 16:35:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.23 Lm: 6.465 (6.431) Lt: 5.739 (5.710) Accm: 3.67 (3.61) Acct: 5.79 (5.72) proj_loss: -0.6073 (-0.6133) time: 0.9234 data: 0.0002 [11-25 16:35:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.23 Lm: 6.414 (6.418) Lt: 5.655 (5.647) Accm: 3.55 (3.57) Acct: 5.58 (5.54) proj_loss: -0.5995 (-0.5966) time: 0.9234 data: 0.0002 [11-25 16:35:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.23 Lm: 6.413 (6.407) Lt: 5.609 (5.655) Accm: 3.64 (3.67) Acct: 5.63 (5.64) proj_loss: -0.6074 (-0.6003) time: 0.9234 data: 0.0004 [11-25 16:35:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.23 Lm: 6.545 (6.595) Lt: 5.763 (5.827) Accm: 3.13 (3.06) Acct: 5.27 (5.07) proj_loss: -0.6143 (-0.6196) time: 0.9234 data: 0.0002 [11-25 16:35:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1251/1669] eta: 0:06:28 tlr: 0.00016 tnm: 0.23 Lm: 6.383 (6.387) Lt: 5.636 (5.610) Accm: 3.51 (3.53) Acct: 5.68 (5.54) proj_loss: -0.5954 (-0.5971) time: 0.9234 data: 0.0003 [11-25 16:42:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.339 (6.377) Lt: 5.617 (5.602) Accm: 3.60 (3.55) Acct: 5.44 (5.52) proj_loss: -0.6103 (-0.5997) time: 0.9248 data: 0.0015 [11-25 16:42:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 132/350] Total time: 0:25:48 (0.928 s / it) [11-25 16:42:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.506 (6.484) Lt: 5.751 (5.732) Accm: 3.32 (3.34) Acct: 4.92 (5.19) proj_loss: -0.6154 (-0.6102) time: 0.9248 data: 0.0017 [11-25 16:42:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.510 (6.459) Lt: 5.796 (5.735) Accm: 3.57 (3.54) Acct: 5.58 (5.58) proj_loss: -0.6080 (-0.6190) time: 0.9249 data: 0.0014 [11-25 16:42:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.342 (6.343) Lt: 5.584 (5.559) Accm: 3.64 (3.66) Acct: 5.51 (5.64) proj_loss: -0.6016 (-0.6152) time: 0.9249 data: 0.0015 [11-25 16:42:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.384 (6.399) Lt: 5.648 (5.652) Accm: 3.53 (3.63) Acct: 5.54 (5.84) proj_loss: -0.6037 (-0.6135) time: 0.9249 data: 0.0017 [11-25 16:42:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.456 (6.419) Lt: 5.611 (5.655) Accm: 3.58 (3.61) Acct: 5.61 (5.63) proj_loss: -0.5962 (-0.5995) time: 0.9248 data: 0.0016 [11-25 16:42:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.432 (6.468) Lt: 5.673 (5.708) Accm: 3.42 (3.48) Acct: 5.17 (5.45) proj_loss: -0.6024 (-0.5994) time: 0.9248 data: 0.0015 [11-25 16:42:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 132/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.490 (6.574) Lt: 5.723 (5.806) Accm: 3.18 (3.12) Acct: 5.23 (5.10) proj_loss: -0.6169 (-0.6231) time: 0.9248 data: 0.0017 [11-25 16:42:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 132/350] Total time: 0:25:48 (0.928 s / it) [11-25 16:42:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 132/350] Total time: 0:25:48 (0.928 s / it) [11-25 16:42:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 132/350] Total time: 0:25:48 (0.928 s / it) [11-25 16:42:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 132/350] Total time: 0:25:48 (0.928 s / it) [11-25 16:42:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 132/350] Total time: 0:25:48 (0.928 s / it) [11-25 16:42:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 132/350] Total time: 0:25:48 (0.928 s / it) [11-25 16:42:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 132/350] Total time: 0:25:48 (0.928 s / it) [11-25 16:42:07] (/home/user/VAR/train.py , line 276)=> [ep132] (training ) Lm: 6.463 (6.463), Lt: 5.708 (5.708), Acc m&t: 3.48 5.47, Remain: 3 days, 21:50:09, Finish: 2024-11-28 22:32 [11-25 16:42:07] (/home/user/VAR/train.py , line 276)=> [ep132] (training ) Lm: 6.463 (6.463), Lt: 5.708 (5.708), Acc m&t: 3.48 5.47, Remain: 3 days, 21:46:12, Finish: 2024-11-28 22:28 [11-25 16:42:07] (/home/user/VAR/train.py , line 276)=> [ep132] (training ) Lm: 6.463 (6.463), Lt: 5.708 (5.708), Acc m&t: 3.48 5.47, Remain: 3 days, 21:49:10, Finish: 2024-11-28 22:31 [11-25 16:42:07] (/home/user/VAR/train.py , line 276)=> [ep132] (training ) Lm: 6.463 (6.463), Lt: 5.708 (5.708), Acc m&t: 3.48 5.47, Remain: 3 days, 21:50:06, Finish: 2024-11-28 22:32 [11-25 16:42:07] (/home/user/VAR/train.py , line 276)=> [ep132] (training ) Lm: 6.463 (6.463), Lt: 5.708 (5.708), Acc m&t: 3.48 5.47, Remain: 3 days, 21:47:19, Finish: 2024-11-28 22:29 [11-25 16:42:07] (/home/user/VAR/train.py , line 276)=> [ep132] (training ) Lm: 6.463 (6.463), Lt: 5.708 (5.708), Acc m&t: 3.48 5.47, Remain: 3 days, 21:47:17, Finish: 2024-11-28 22:29 [11-25 16:42:07] (/home/user/VAR/train.py , line 276)=> [ep132] (training ) Lm: 6.463 (6.463), Lt: 5.708 (5.708), Acc m&t: 3.48 5.47, Remain: 3 days, 21:48:48, Finish: 2024-11-28 22:30 [11-25 16:42:07] (/home/user/VAR/train.py , line 276)=> [ep132] (training ) Lm: 6.463 (6.463), Lt: 5.708 (5.708), Acc m&t: 3.48 5.47, Remain: 3 days, 21:47:20, Finish: 2024-11-28 22:29 [11-25 16:42:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 0/1669] eta: 0:25:41 tlr: 0.00016 tnm: 0.24 Lm: 6.414 (6.414) Lt: 5.660 (5.660) Accm: 3.61 (3.61) Acct: 5.44 (5.44) proj_loss: -0.6134 (-0.6134) time: 0.9238 data: 0.0004 [11-25 16:42:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 0/1669] eta: 0:25:32 tlr: 0.00016 tnm: 0.24 Lm: 6.404 (6.404) Lt: 5.656 (5.656) Accm: 3.48 (3.48) Acct: 5.58 (5.58) proj_loss: -0.6127 (-0.6127) time: 0.9180 data: 0.0004 [11-25 16:42:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 0/1669] eta: 0:25:32 tlr: 0.00016 tnm: 0.24 Lm: 6.355 (6.355) Lt: 5.655 (5.655) Accm: 3.98 (3.98) Acct: 6.27 (6.27) proj_loss: -0.6406 (-0.6406) time: 0.9183 data: 0.0003 [11-25 16:42:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 0/1669] eta: 0:25:31 tlr: 0.00016 tnm: 0.24 Lm: 6.185 (6.185) Lt: 5.406 (5.406) Accm: 4.37 (4.37) Acct: 6.92 (6.92) proj_loss: -0.6382 (-0.6382) time: 0.9176 data: 0.0003 [11-25 16:42:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 0/1669] eta: 0:25:32 tlr: 0.00016 tnm: 0.24 Lm: 6.431 (6.431) Lt: 5.669 (5.669) Accm: 3.45 (3.45) Acct: 5.30 (5.30) proj_loss: -0.6127 (-0.6127) time: 0.9183 data: 0.0004 [11-25 16:42:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 0/1669] eta: 0:25:33 tlr: 0.00016 tnm: 0.24 Lm: 6.065 (6.065) Lt: 5.301 (5.301) Accm: 4.97 (4.97) Acct: 7.51 (7.51) proj_loss: -0.6229 (-0.6229) time: 0.9187 data: 0.0003 [11-25 16:42:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 0/1669] eta: 0:25:33 tlr: 0.00016 tnm: 0.24 Lm: 6.456 (6.456) Lt: 5.730 (5.730) Accm: 3.70 (3.70) Acct: 6.03 (6.03) proj_loss: -0.6171 (-0.6171) time: 0.9186 data: 0.0004 [11-25 16:42:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 0/1669] eta: 0:25:33 tlr: 0.00016 tnm: 0.24 Lm: 6.423 (6.423) Lt: 5.620 (5.620) Accm: 3.70 (3.70) Acct: 6.34 (6.34) proj_loss: -0.6467 (-0.6467) time: 0.9186 data: 0.0003 [11-25 16:48:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.398 (6.398) Lt: 5.602 (5.602) Accm: 3.73 (3.73) Acct: 5.99 (5.99) proj_loss: -0.6327 (-0.6327) time: 0.9254 data: 0.0003 [11-25 16:48:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.265 (6.265) Lt: 5.532 (5.532) Accm: 4.14 (4.14) Acct: 6.32 (6.32) proj_loss: -0.6251 (-0.6251) time: 0.9254 data: 0.0002 [11-25 16:48:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.421 (6.421) Lt: 5.678 (5.678) Accm: 3.64 (3.64) Acct: 5.96 (5.96) proj_loss: -0.6175 (-0.6175) time: 0.9254 data: 0.0002 [11-25 16:48:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.500 (6.500) Lt: 5.768 (5.768) Accm: 3.42 (3.42) Acct: 5.34 (5.34) proj_loss: -0.6179 (-0.6179) time: 0.9254 data: 0.0003 [11-25 16:48:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.495 (6.495) Lt: 5.810 (5.810) Accm: 3.58 (3.58) Acct: 5.48 (5.48) proj_loss: -0.6291 (-0.6291) time: 0.9254 data: 0.0002 [11-25 16:48:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.530 (6.530) Lt: 5.746 (5.746) Accm: 3.31 (3.31) Acct: 5.34 (5.34) proj_loss: -0.6067 (-0.6067) time: 0.9254 data: 0.0003 [11-25 16:48:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.240 (6.240) Lt: 5.472 (5.472) Accm: 4.21 (4.21) Acct: 6.71 (6.71) proj_loss: -0.6140 (-0.6140) time: 0.9254 data: 0.0002 [11-25 16:48:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.523 (6.523) Lt: 5.760 (5.760) Accm: 3.32 (3.32) Acct: 5.17 (5.17) proj_loss: -0.6109 (-0.6109) time: 0.9254 data: 0.0003 [11-25 16:54:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.23 Lm: 6.479 (6.509) Lt: 5.812 (5.777) Accm: 3.23 (3.29) Acct: 5.03 (4.98) proj_loss: -0.6127 (-0.6189) time: 0.9226 data: 0.0003 [11-25 16:54:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.23 Lm: 6.414 (6.400) Lt: 5.660 (5.687) Accm: 3.61 (3.75) Acct: 5.51 (5.82) proj_loss: -0.6232 (-0.6271) time: 0.9226 data: 0.0003 [11-25 16:54:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.23 Lm: 6.427 (6.423) Lt: 5.656 (5.636) Accm: 3.76 (3.68) Acct: 6.16 (6.03) proj_loss: -0.6127 (-0.6111) time: 0.9226 data: 0.0002 [11-25 16:54:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.23 Lm: 6.373 (6.356) Lt: 5.584 (5.590) Accm: 3.76 (3.88) Acct: 6.34 (6.18) proj_loss: -0.6187 (-0.6266) time: 0.9226 data: 0.0002 [11-25 16:54:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.23 Lm: 6.465 (6.417) Lt: 5.762 (5.661) Accm: 3.32 (3.69) Acct: 5.13 (5.79) proj_loss: -0.6229 (-0.6142) time: 0.9226 data: 0.0003 [11-25 16:54:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.23 Lm: 6.295 (6.305) Lt: 5.539 (5.561) Accm: 4.05 (3.93) Acct: 6.51 (6.21) proj_loss: -0.6087 (-0.6122) time: 0.9226 data: 0.0002 [11-25 16:54:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.23 Lm: 6.586 (6.549) Lt: 5.761 (5.754) Accm: 3.29 (3.30) Acct: 5.72 (5.46) proj_loss: -0.5963 (-0.5991) time: 0.9226 data: 0.0003 [11-25 16:54:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.23 Lm: 6.448 (6.483) Lt: 5.734 (5.756) Accm: 3.47 (3.44) Acct: 5.72 (5.46) proj_loss: -0.5993 (-0.6117) time: 0.9226 data: 0.0003 [11-25 17:01:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1251/1669] eta: 0:06:29 tlr: 0.00016 tnm: 0.24 Lm: 6.425 (6.463) Lt: 5.695 (5.724) Accm: 3.59 (3.51) Acct: 5.68 (5.51) proj_loss: -0.5986 (-0.6082) time: 0.9243 data: 0.0002 [11-25 17:01:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1251/1669] eta: 0:06:29 tlr: 0.00016 tnm: 0.24 Lm: 6.348 (6.348) Lt: 5.581 (5.587) Accm: 3.77 (3.85) Acct: 6.11 (6.10) proj_loss: -0.6266 (-0.6286) time: 0.9243 data: 0.0002 [11-25 17:01:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1251/1669] eta: 0:06:29 tlr: 0.00016 tnm: 0.24 Lm: 6.590 (6.492) Lt: 5.840 (5.730) Accm: 3.14 (3.50) Acct: 4.94 (5.53) proj_loss: -0.6164 (-0.6131) time: 0.9244 data: 0.0003 [11-25 17:01:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1251/1669] eta: 0:06:29 tlr: 0.00016 tnm: 0.24 Lm: 6.495 (6.476) Lt: 5.810 (5.768) Accm: 3.58 (3.50) Acct: 5.48 (5.49) proj_loss: -0.6257 (-0.6274) time: 0.9243 data: 0.0003 [11-25 17:01:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1251/1669] eta: 0:06:29 tlr: 0.00016 tnm: 0.24 Lm: 6.455 (6.463) Lt: 5.740 (5.738) Accm: 3.34 (3.41) Acct: 5.17 (5.06) proj_loss: -0.6109 (-0.6153) time: 0.9244 data: 0.0003 [11-25 17:01:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1251/1669] eta: 0:06:29 tlr: 0.00016 tnm: 0.24 Lm: 6.421 (6.421) Lt: 5.663 (5.645) Accm: 3.78 (3.73) Acct: 6.11 (6.03) proj_loss: -0.6175 (-0.6223) time: 0.9244 data: 0.0002 [11-25 17:01:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1251/1669] eta: 0:06:29 tlr: 0.00016 tnm: 0.24 Lm: 6.365 (6.343) Lt: 5.639 (5.608) Accm: 3.72 (3.79) Acct: 5.85 (5.88) proj_loss: -0.6075 (-0.6107) time: 0.9244 data: 0.0003 [11-25 17:01:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1251/1669] eta: 0:06:29 tlr: 0.00016 tnm: 0.24 Lm: 6.521 (6.511) Lt: 5.746 (5.736) Accm: 3.31 (3.31) Acct: 5.20 (5.27) proj_loss: -0.6067 (-0.6042) time: 0.9244 data: 0.0003 [11-25 17:08:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.530 (6.515) Lt: 5.761 (5.743) Accm: 3.29 (3.27) Acct: 4.92 (5.20) proj_loss: -0.5963 (-0.6013) time: 0.9264 data: 0.0015 [11-25 17:08:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.458 (6.473) Lt: 5.710 (5.756) Accm: 3.61 (3.53) Acct: 5.51 (5.52) proj_loss: -0.6232 (-0.6262) time: 0.9263 data: 0.0016 [11-25 17:08:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.433 (6.457) Lt: 5.655 (5.703) Accm: 3.47 (3.49) Acct: 5.65 (5.52) proj_loss: -0.5980 (-0.6034) time: 0.9263 data: 0.0018 [11-25 17:08:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.373 (6.414) Lt: 5.584 (5.658) Accm: 3.76 (3.64) Acct: 5.89 (5.74) proj_loss: -0.6317 (-0.6292) time: 0.9263 data: 0.0016 [11-25 17:08:00] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 133/350] Total time: 0:25:52 (0.930 s / it) [11-25 17:08:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.427 (6.441) Lt: 5.671 (5.678) Accm: 3.76 (3.60) Acct: 6.06 (5.78) proj_loss: -0.6223 (-0.6231) time: 0.9263 data: 0.0016 [11-25 17:08:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.431 (6.448) Lt: 5.669 (5.709) Accm: 3.45 (3.41) Acct: 5.27 (5.10) proj_loss: -0.6127 (-0.6167) time: 0.9264 data: 0.0018 [11-25 17:08:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.434 (6.415) Lt: 5.739 (5.697) Accm: 3.38 (3.54) Acct: 5.20 (5.41) proj_loss: -0.6062 (-0.6097) time: 0.9264 data: 0.0018 [11-25 17:08:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 133/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.465 (6.483) Lt: 5.762 (5.730) Accm: 3.32 (3.49) Acct: 5.13 (5.48) proj_loss: -0.6099 (-0.6106) time: 0.9263 data: 0.0020 [11-25 17:08:00] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 133/350] Total time: 0:25:52 (0.930 s / it) [11-25 17:08:00] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 133/350] Total time: 0:25:52 (0.930 s / it) [11-25 17:08:00] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 133/350] Total time: 0:25:52 (0.930 s / it) [11-25 17:08:00] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 133/350] Total time: 0:25:52 (0.930 s / it) [11-25 17:08:00] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 133/350] Total time: 0:25:52 (0.930 s / it) [11-25 17:08:00] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 133/350] Total time: 0:25:52 (0.930 s / it) [11-25 17:08:00] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 133/350] Total time: 0:25:52 (0.930 s / it) [11-25 17:08:00] (/home/user/VAR/train.py , line 276)=> [ep133] (training ) Lm: 6.463 (6.468), Lt: 5.708 (5.713), Acc m&t: 3.48 5.47, Remain: 3 days, 21:27:02, Finish: 2024-11-28 22:35 [11-25 17:08:00] (/home/user/VAR/train.py , line 276)=> [ep133] (training ) Lm: 6.463 (6.468), Lt: 5.708 (5.713), Acc m&t: 3.48 5.47, Remain: 3 days, 21:26:32, Finish: 2024-11-28 22:34 [11-25 17:08:00] (/home/user/VAR/train.py , line 276)=> [ep133] (training ) Lm: 6.463 (6.468), Lt: 5.708 (5.713), Acc m&t: 3.48 5.47, Remain: 3 days, 21:27:33, Finish: 2024-11-28 22:35 [11-25 17:08:00] (/home/user/VAR/train.py , line 276)=> [ep133] (training ) Lm: 6.463 (6.468), Lt: 5.708 (5.713), Acc m&t: 3.48 5.47, Remain: 3 days, 21:28:03, Finish: 2024-11-28 22:36 [11-25 17:08:00] (/home/user/VAR/train.py , line 276)=> [ep133] (training ) Lm: 6.463 (6.468), Lt: 5.708 (5.713), Acc m&t: 3.48 5.47, Remain: 3 days, 21:25:39, Finish: 2024-11-28 22:33 [11-25 17:08:00] (/home/user/VAR/train.py , line 276)=> [ep133] (training ) Lm: 6.463 (6.468), Lt: 5.708 (5.713), Acc m&t: 3.48 5.47, Remain: 3 days, 21:26:14, Finish: 2024-11-28 22:34 [11-25 17:08:00] (/home/user/VAR/train.py , line 276)=> [ep133] (training ) Lm: 6.463 (6.468), Lt: 5.708 (5.713), Acc m&t: 3.48 5.47, Remain: 3 days, 21:26:01, Finish: 2024-11-28 22:34 [11-25 17:08:00] (/home/user/VAR/train.py , line 276)=> [ep133] (training ) Lm: 6.463 (6.468), Lt: 5.708 (5.713), Acc m&t: 3.48 5.47, Remain: 3 days, 21:28:38, Finish: 2024-11-28 22:36 [11-25 17:08:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 0/1669] eta: 0:25:24 tlr: 0.00016 tnm: 0.24 Lm: 6.663 (6.663) Lt: 5.921 (5.921) Accm: 2.94 (2.94) Acct: 4.44 (4.44) proj_loss: -0.5750 (-0.5750) time: 0.9134 data: 0.0004 [11-25 17:08:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 0/1669] eta: 0:25:17 tlr: 0.00016 tnm: 0.24 Lm: 6.273 (6.273) Lt: 5.492 (5.492) Accm: 4.09 (4.09) Acct: 6.40 (6.40) proj_loss: -0.6168 (-0.6168) time: 0.9094 data: 0.0003 [11-25 17:08:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 0/1669] eta: 0:25:25 tlr: 0.00016 tnm: 0.24 Lm: 6.649 (6.649) Lt: 5.864 (5.864) Accm: 2.90 (2.90) Acct: 4.92 (4.92) proj_loss: -0.5858 (-0.5858) time: 0.9138 data: 0.0003 [11-25 17:08:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 0/1669] eta: 0:25:18 tlr: 0.00016 tnm: 0.24 Lm: 6.303 (6.303) Lt: 5.480 (5.480) Accm: 4.90 (4.90) Acct: 8.02 (8.02) proj_loss: -0.6075 (-0.6075) time: 0.9097 data: 0.0003 [11-25 17:08:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 0/1669] eta: 0:25:25 tlr: 0.00016 tnm: 0.24 Lm: 6.569 (6.569) Lt: 5.809 (5.809) Accm: 3.47 (3.47) Acct: 5.51 (5.51) proj_loss: -0.5903 (-0.5903) time: 0.9139 data: 0.0003 [11-25 17:08:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 0/1669] eta: 0:25:16 tlr: 0.00016 tnm: 0.24 Lm: 6.531 (6.531) Lt: 5.817 (5.817) Accm: 3.15 (3.15) Acct: 4.82 (4.82) proj_loss: -0.6078 (-0.6078) time: 0.9087 data: 0.0004 [11-25 17:08:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 0/1669] eta: 0:25:18 tlr: 0.00016 tnm: 0.24 Lm: 6.482 (6.482) Lt: 5.667 (5.667) Accm: 3.13 (3.13) Acct: 4.82 (4.82) proj_loss: -0.5936 (-0.5936) time: 0.9101 data: 0.0004 [11-25 17:08:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 0/1669] eta: 0:25:19 tlr: 0.00016 tnm: 0.24 Lm: 6.499 (6.499) Lt: 5.730 (5.730) Accm: 3.72 (3.72) Acct: 5.96 (5.96) proj_loss: -0.6258 (-0.6258) time: 0.9102 data: 0.0004 [11-25 17:14:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.619 (6.619) Lt: 5.876 (5.876) Accm: 2.96 (2.96) Acct: 4.84 (4.84) proj_loss: -0.6050 (-0.6050) time: 0.9235 data: 0.0003 [11-25 17:14:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.327 (6.327) Lt: 5.536 (5.536) Accm: 3.79 (3.79) Acct: 5.85 (5.85) proj_loss: -0.5983 (-0.5983) time: 0.9236 data: 0.0003 [11-25 17:14:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.353 (6.353) Lt: 5.549 (5.549) Accm: 4.38 (4.38) Acct: 7.09 (7.09) proj_loss: -0.6008 (-0.6008) time: 0.9236 data: 0.0003 [11-25 17:14:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.577 (6.577) Lt: 5.867 (5.867) Accm: 3.23 (3.23) Acct: 5.13 (5.13) proj_loss: -0.5978 (-0.5978) time: 0.9236 data: 0.0003 [11-25 17:14:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.486 (6.486) Lt: 5.750 (5.750) Accm: 3.55 (3.55) Acct: 5.63 (5.63) proj_loss: -0.6340 (-0.6340) time: 0.9236 data: 0.0003 [11-25 17:14:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.599 (6.599) Lt: 5.820 (5.820) Accm: 2.89 (2.89) Acct: 4.51 (4.51) proj_loss: -0.5847 (-0.5847) time: 0.9236 data: 0.0002 [11-25 17:14:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.567 (6.567) Lt: 5.828 (5.828) Accm: 3.25 (3.25) Acct: 5.25 (5.25) proj_loss: -0.6057 (-0.6057) time: 0.9236 data: 0.0003 [11-25 17:14:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.591 (6.591) Lt: 5.864 (5.864) Accm: 2.88 (2.88) Acct: 4.49 (4.49) proj_loss: -0.6074 (-0.6074) time: 0.9236 data: 0.0003 [11-25 17:20:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.650 (6.674) Lt: 5.911 (5.940) Accm: 2.62 (2.74) Acct: 4.17 (4.35) proj_loss: -0.6069 (-0.6005) time: 0.9244 data: 0.0003 [11-25 17:20:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.590 (6.477) Lt: 5.864 (5.687) Accm: 3.03 (3.42) Acct: 4.92 (5.41) proj_loss: -0.6111 (-0.6070) time: 0.9244 data: 0.0002 [11-25 17:20:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.381 (6.352) Lt: 5.581 (5.578) Accm: 3.83 (3.80) Acct: 5.58 (5.76) proj_loss: -0.6027 (-0.5998) time: 0.9244 data: 0.0003 [11-25 17:20:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.471 (6.521) Lt: 5.738 (5.798) Accm: 3.55 (3.42) Acct: 5.58 (5.36) proj_loss: -0.6244 (-0.6120) time: 0.9244 data: 0.0003 [11-25 17:20:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.569 (6.455) Lt: 5.809 (5.739) Accm: 3.47 (3.68) Acct: 5.51 (5.74) proj_loss: -0.6053 (-0.6102) time: 0.9244 data: 0.0003 [11-25 17:20:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.636 (6.612) Lt: 5.847 (5.829) Accm: 2.87 (2.88) Acct: 4.37 (4.47) proj_loss: -0.5936 (-0.5904) time: 0.9244 data: 0.0002 [11-25 17:20:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.472 (6.378) Lt: 5.730 (5.637) Accm: 3.72 (3.94) Acct: 5.96 (6.18) proj_loss: -0.6258 (-0.6221) time: 0.9244 data: 0.0003 [11-25 17:20:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.332 (6.346) Lt: 5.569 (5.555) Accm: 3.86 (4.17) Acct: 6.16 (6.62) proj_loss: -0.6075 (-0.6102) time: 0.9244 data: 0.0003 [11-25 17:27:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1251/1669] eta: 0:06:25 tlr: 0.00016 tnm: 0.24 Lm: 6.367 (6.410) Lt: 5.593 (5.624) Accm: 3.81 (3.90) Acct: 5.92 (6.22) proj_loss: -0.6037 (-0.6077) time: 0.9259 data: 0.0003 [11-25 17:27:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1251/1669] eta: 0:06:25 tlr: 0.00016 tnm: 0.24 Lm: 6.472 (6.509) Lt: 5.737 (5.783) Accm: 3.56 (3.46) Acct: 5.58 (5.41) proj_loss: -0.6264 (-0.6161) time: 0.9259 data: 0.0002 [11-25 17:27:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1251/1669] eta: 0:06:25 tlr: 0.00016 tnm: 0.24 Lm: 6.555 (6.488) Lt: 5.850 (5.724) Accm: 3.21 (3.41) Acct: 4.94 (5.29) proj_loss: -0.6103 (-0.6077) time: 0.9259 data: 0.0002 [11-25 17:27:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1251/1669] eta: 0:06:25 tlr: 0.00016 tnm: 0.24 Lm: 6.413 (6.372) Lt: 5.662 (5.626) Accm: 3.55 (3.80) Acct: 5.63 (5.96) proj_loss: -0.6245 (-0.6224) time: 0.9259 data: 0.0003 [11-25 17:27:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1251/1669] eta: 0:06:25 tlr: 0.00016 tnm: 0.24 Lm: 6.559 (6.504) Lt: 5.757 (5.747) Accm: 3.00 (3.20) Acct: 4.60 (4.98) proj_loss: -0.5977 (-0.6029) time: 0.9259 data: 0.0003 [11-25 17:27:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1251/1669] eta: 0:06:25 tlr: 0.00016 tnm: 0.24 Lm: 6.415 (6.407) Lt: 5.646 (5.642) Accm: 4.02 (3.91) Acct: 6.23 (6.07) proj_loss: -0.5978 (-0.6004) time: 0.9259 data: 0.0003 [11-25 17:27:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1251/1669] eta: 0:06:25 tlr: 0.00016 tnm: 0.24 Lm: 6.383 (6.360) Lt: 5.592 (5.584) Accm: 3.66 (3.69) Acct: 5.53 (5.69) proj_loss: -0.6098 (-0.6122) time: 0.9259 data: 0.0002 [11-25 17:27:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1251/1669] eta: 0:06:25 tlr: 0.00016 tnm: 0.24 Lm: 6.627 (6.657) Lt: 5.908 (5.931) Accm: 2.87 (2.83) Acct: 4.39 (4.42) proj_loss: -0.6074 (-0.6056) time: 0.9259 data: 0.0003 [11-25 17:33:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.636 (6.652) Lt: 5.906 (5.907) Accm: 3.03 (2.87) Acct: 4.61 (4.52) proj_loss: -0.6069 (-0.6021) time: 0.9255 data: 0.0016 [11-25 17:33:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 134/350] Total time: 0:25:41 (0.924 s / it) [11-25 17:33:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.521 (6.461) Lt: 5.835 (5.718) Accm: 3.38 (3.46) Acct: 4.96 (5.32) proj_loss: -0.6111 (-0.6184) time: 0.9255 data: 0.0015 [11-25 17:33:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.471 (6.490) Lt: 5.737 (5.741) Accm: 3.57 (3.51) Acct: 5.58 (5.51) proj_loss: -0.6244 (-0.6112) time: 0.9255 data: 0.0018 [11-25 17:33:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.636 (6.547) Lt: 5.847 (5.807) Accm: 2.87 (3.14) Acct: 4.41 (4.87) proj_loss: -0.6018 (-0.6076) time: 0.9255 data: 0.0016 [11-25 17:33:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.261 (6.360) Lt: 5.484 (5.608) Accm: 4.25 (3.98) Acct: 6.65 (6.18) proj_loss: -0.6053 (-0.6054) time: 0.9255 data: 0.0016 [11-25 17:33:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.332 (6.385) Lt: 5.569 (5.588) Accm: 3.86 (4.00) Acct: 6.16 (6.32) proj_loss: -0.6072 (-0.6076) time: 0.9255 data: 0.0016 [11-25 17:33:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.385 (6.395) Lt: 5.603 (5.630) Accm: 3.48 (3.61) Acct: 5.48 (5.56) proj_loss: -0.6168 (-0.6136) time: 0.9255 data: 0.0018 [11-25 17:33:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 134/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.472 (6.422) Lt: 5.730 (5.677) Accm: 3.38 (3.67) Acct: 5.30 (5.81) proj_loss: -0.6258 (-0.6247) time: 0.9255 data: 0.0017 [11-25 17:33:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 134/350] Total time: 0:25:41 (0.924 s / it) [11-25 17:33:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 134/350] Total time: 0:25:41 (0.924 s / it) [11-25 17:33:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 134/350] Total time: 0:25:41 (0.924 s / it) [11-25 17:33:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 134/350] Total time: 0:25:41 (0.924 s / it) [11-25 17:33:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 134/350] Total time: 0:25:41 (0.924 s / it) [11-25 17:33:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 134/350] Total time: 0:25:41 (0.924 s / it) [11-25 17:33:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 134/350] Total time: 0:25:41 (0.924 s / it) [11-25 17:33:41] (/home/user/VAR/train.py , line 276)=> [ep134] (training ) Lm: 6.461 (6.461), Lt: 5.705 (5.705), Acc m&t: 3.48 5.48, Remain: 3 days, 20:58:22, Finish: 2024-11-28 22:32 [11-25 17:33:41] (/home/user/VAR/train.py , line 276)=> [ep134] (training ) Lm: 6.461 (6.461), Lt: 5.705 (5.705), Acc m&t: 3.48 5.48, Remain: 3 days, 20:59:15, Finish: 2024-11-28 22:32 [11-25 17:33:41] (/home/user/VAR/train.py , line 276)=> [ep134] (training ) Lm: 6.461 (6.461), Lt: 5.705 (5.705), Acc m&t: 3.48 5.48, Remain: 3 days, 20:58:39, Finish: 2024-11-28 22:32 [11-25 17:33:41] (/home/user/VAR/train.py , line 276)=> [ep134] (training ) Lm: 6.461 (6.461), Lt: 5.705 (5.705), Acc m&t: 3.48 5.48, Remain: 3 days, 20:58:53, Finish: 2024-11-28 22:32 [11-25 17:33:41] (/home/user/VAR/train.py , line 276)=> [ep134] (training ) Lm: 6.461 (6.461), Lt: 5.705 (5.705), Acc m&t: 3.48 5.48, Remain: 3 days, 20:58:09, Finish: 2024-11-28 22:31 [11-25 17:33:41] (/home/user/VAR/train.py , line 276)=> [ep134] (training ) Lm: 6.461 (6.461), Lt: 5.705 (5.705), Acc m&t: 3.48 5.48, Remain: 3 days, 20:57:58, Finish: 2024-11-28 22:31 [11-25 17:33:41] (/home/user/VAR/train.py , line 276)=> [ep134] (training ) Lm: 6.461 (6.461), Lt: 5.705 (5.705), Acc m&t: 3.48 5.48, Remain: 3 days, 20:59:11, Finish: 2024-11-28 22:32 [11-25 17:33:41] (/home/user/VAR/train.py , line 276)=> [ep134] (training ) Lm: 6.461 (6.461), Lt: 5.705 (5.705), Acc m&t: 3.48 5.48, Remain: 3 days, 21:00:20, Finish: 2024-11-28 22:34 [11-25 17:33:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 0/1669] eta: 0:25:30 tlr: 0.00016 tnm: 0.25 Lm: 6.334 (6.334) Lt: 5.612 (5.612) Accm: 4.01 (4.01) Acct: 5.85 (5.85) proj_loss: -0.6513 (-0.6513) time: 0.9169 data: 0.0003 [11-25 17:33:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 0/1669] eta: 0:25:30 tlr: 0.00016 tnm: 0.25 Lm: 6.654 (6.654) Lt: 5.964 (5.964) Accm: 2.99 (2.99) Acct: 4.72 (4.72) proj_loss: -0.5955 (-0.5955) time: 0.9171 data: 0.0004 [11-25 17:33:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 0/1669] eta: 0:25:31 tlr: 0.00016 tnm: 0.25 Lm: 6.283 (6.283) Lt: 5.418 (5.418) Accm: 3.72 (3.72) Acct: 5.79 (5.79) proj_loss: -0.6365 (-0.6365) time: 0.9176 data: 0.0003 [11-25 17:33:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 0/1669] eta: 0:25:30 tlr: 0.00016 tnm: 0.25 Lm: 6.260 (6.260) Lt: 5.499 (5.499) Accm: 3.96 (3.96) Acct: 5.72 (5.72) proj_loss: -0.6445 (-0.6445) time: 0.9172 data: 0.0004 [11-25 17:33:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 0/1669] eta: 0:25:32 tlr: 0.00016 tnm: 0.25 Lm: 6.471 (6.471) Lt: 5.739 (5.739) Accm: 3.16 (3.16) Acct: 4.79 (4.79) proj_loss: -0.6092 (-0.6092) time: 0.9181 data: 0.0003 [11-25 17:33:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 0/1669] eta: 0:25:32 tlr: 0.00016 tnm: 0.25 Lm: 6.430 (6.430) Lt: 5.667 (5.667) Accm: 3.99 (3.99) Acct: 6.27 (6.27) proj_loss: -0.6235 (-0.6235) time: 0.9180 data: 0.0004 [11-25 17:33:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 0/1669] eta: 0:25:38 tlr: 0.00016 tnm: 0.25 Lm: 6.664 (6.664) Lt: 5.898 (5.898) Accm: 3.07 (3.07) Acct: 5.03 (5.03) proj_loss: -0.6390 (-0.6390) time: 0.9219 data: 0.0004 [11-25 17:33:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 0/1669] eta: 0:25:32 tlr: 0.00016 tnm: 0.25 Lm: 6.634 (6.634) Lt: 5.996 (5.996) Accm: 2.74 (2.74) Acct: 4.17 (4.17) proj_loss: -0.6361 (-0.6361) time: 0.9181 data: 0.0003 [11-25 17:40:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 417/1669] eta: 0:19:47 tlr: 0.00016 tnm: 0.24 Lm: 6.675 (6.675) Lt: 6.002 (6.002) Accm: 2.89 (2.89) Acct: 4.29 (4.29) proj_loss: -0.6112 (-0.6112) time: 0.9262 data: 0.0002 [11-25 17:40:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 417/1669] eta: 0:19:47 tlr: 0.00016 tnm: 0.24 Lm: 6.399 (6.399) Lt: 5.675 (5.675) Accm: 3.61 (3.61) Acct: 5.60 (5.60) proj_loss: -0.6270 (-0.6270) time: 0.9262 data: 0.0002 [11-25 17:40:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 417/1669] eta: 0:19:47 tlr: 0.00016 tnm: 0.24 Lm: 6.505 (6.505) Lt: 5.768 (5.768) Accm: 3.28 (3.28) Acct: 4.92 (4.92) proj_loss: -0.6392 (-0.6392) time: 0.9262 data: 0.0003 [11-25 17:40:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 417/1669] eta: 0:19:47 tlr: 0.00016 tnm: 0.24 Lm: 6.547 (6.547) Lt: 5.805 (5.805) Accm: 3.29 (3.29) Acct: 5.10 (5.10) proj_loss: -0.5903 (-0.5903) time: 0.9262 data: 0.0003 [11-25 17:40:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 417/1669] eta: 0:19:47 tlr: 0.00016 tnm: 0.24 Lm: 6.283 (6.283) Lt: 5.469 (5.469) Accm: 3.82 (3.82) Acct: 5.85 (5.85) proj_loss: -0.6294 (-0.6294) time: 0.9262 data: 0.0003 [11-25 17:40:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 417/1669] eta: 0:19:47 tlr: 0.00016 tnm: 0.24 Lm: 6.454 (6.454) Lt: 5.670 (5.670) Accm: 3.68 (3.68) Acct: 5.85 (5.85) proj_loss: -0.6183 (-0.6183) time: 0.9262 data: 0.0003 [11-25 17:40:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 417/1669] eta: 0:19:47 tlr: 0.00016 tnm: 0.24 Lm: 6.387 (6.387) Lt: 5.591 (5.591) Accm: 3.53 (3.53) Acct: 5.70 (5.70) proj_loss: -0.6107 (-0.6107) time: 0.9262 data: 0.0003 [11-25 17:40:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 417/1669] eta: 0:19:47 tlr: 0.00016 tnm: 0.24 Lm: 6.375 (6.375) Lt: 5.590 (5.590) Accm: 3.93 (3.93) Acct: 6.16 (6.16) proj_loss: -0.6365 (-0.6365) time: 0.9262 data: 0.0003 [11-25 17:46:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 834/1669] eta: 0:13:01 tlr: 0.00016 tnm: 0.24 Lm: 6.359 (6.370) Lt: 5.567 (5.582) Accm: 3.70 (3.86) Acct: 5.54 (5.96) proj_loss: -0.6341 (-0.6225) time: 0.9238 data: 0.0003 [11-25 17:46:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 834/1669] eta: 0:13:01 tlr: 0.00016 tnm: 0.24 Lm: 6.430 (6.433) Lt: 5.667 (5.638) Accm: 3.51 (3.62) Acct: 5.61 (5.77) proj_loss: -0.6134 (-0.6167) time: 0.9238 data: 0.0003 [11-25 17:46:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 834/1669] eta: 0:13:01 tlr: 0.00016 tnm: 0.24 Lm: 6.700 (6.570) Lt: 6.026 (5.854) Accm: 2.75 (3.10) Acct: 4.17 (4.67) proj_loss: -0.6339 (-0.6358) time: 0.9238 data: 0.0002 [11-25 17:46:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 834/1669] eta: 0:13:01 tlr: 0.00016 tnm: 0.24 Lm: 6.283 (6.319) Lt: 5.520 (5.529) Accm: 3.72 (3.76) Acct: 5.92 (5.90) proj_loss: -0.6288 (-0.6292) time: 0.9238 data: 0.0003 [11-25 17:46:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 834/1669] eta: 0:13:01 tlr: 0.00016 tnm: 0.24 Lm: 6.441 (6.508) Lt: 5.645 (5.716) Accm: 3.58 (3.42) Acct: 5.48 (5.44) proj_loss: -0.5877 (-0.5894) time: 0.9238 data: 0.0002 [11-25 17:46:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 834/1669] eta: 0:13:01 tlr: 0.00016 tnm: 0.24 Lm: 6.436 (6.412) Lt: 5.622 (5.658) Accm: 3.67 (3.63) Acct: 5.65 (5.61) proj_loss: -0.6262 (-0.6267) time: 0.9238 data: 0.0002 [11-25 17:46:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 834/1669] eta: 0:13:01 tlr: 0.00016 tnm: 0.24 Lm: 6.634 (6.615) Lt: 5.996 (5.890) Accm: 3.04 (3.11) Acct: 4.41 (4.63) proj_loss: -0.5864 (-0.5949) time: 0.9238 data: 0.0002 [11-25 17:46:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [ 834/1669] eta: 0:13:01 tlr: 0.00016 tnm: 0.24 Lm: 6.307 (6.360) Lt: 5.471 (5.551) Accm: 3.76 (3.61) Acct: 6.20 (5.87) proj_loss: -0.6092 (-0.6084) time: 0.9238 data: 0.0003 [11-25 17:53:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1251/1669] eta: 0:06:29 tlr: 0.00016 tnm: 0.24 Lm: 6.346 (6.366) Lt: 5.569 (5.580) Accm: 3.69 (3.61) Acct: 5.89 (5.79) proj_loss: -0.6066 (-0.6057) time: 0.9242 data: 0.0003 [11-25 17:53:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1251/1669] eta: 0:06:29 tlr: 0.00016 tnm: 0.24 Lm: 6.454 (6.464) Lt: 5.670 (5.665) Accm: 3.44 (3.50) Acct: 5.53 (5.65) proj_loss: -0.6133 (-0.6082) time: 0.9242 data: 0.0003 [11-25 17:53:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1251/1669] eta: 0:06:29 tlr: 0.00016 tnm: 0.24 Lm: 6.585 (6.545) Lt: 5.894 (5.831) Accm: 3.10 (3.19) Acct: 4.72 (4.82) proj_loss: -0.6314 (-0.6329) time: 0.9242 data: 0.0002 [11-25 17:53:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1251/1669] eta: 0:06:29 tlr: 0.00016 tnm: 0.24 Lm: 6.570 (6.588) Lt: 5.926 (5.881) Accm: 3.07 (3.11) Acct: 4.34 (4.54) proj_loss: -0.6103 (-0.6048) time: 0.9242 data: 0.0002 [11-25 17:53:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1251/1669] eta: 0:06:29 tlr: 0.00016 tnm: 0.24 Lm: 6.337 (6.344) Lt: 5.583 (5.558) Accm: 3.70 (3.74) Acct: 5.96 (5.97) proj_loss: -0.6255 (-0.6223) time: 0.9242 data: 0.0002 [11-25 17:53:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1251/1669] eta: 0:06:29 tlr: 0.00016 tnm: 0.24 Lm: 6.434 (6.405) Lt: 5.628 (5.609) Accm: 3.56 (3.75) Acct: 5.48 (5.82) proj_loss: -0.6245 (-0.6206) time: 0.9242 data: 0.0002 [11-25 17:53:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1251/1669] eta: 0:06:29 tlr: 0.00016 tnm: 0.24 Lm: 6.450 (6.439) Lt: 5.681 (5.688) Accm: 3.53 (3.57) Acct: 5.54 (5.57) proj_loss: -0.6145 (-0.6168) time: 0.9242 data: 0.0002 [11-25 17:53:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1251/1669] eta: 0:06:29 tlr: 0.00016 tnm: 0.24 Lm: 6.486 (6.514) Lt: 5.713 (5.732) Accm: 3.31 (3.33) Acct: 5.10 (5.25) proj_loss: -0.5916 (-0.5910) time: 0.9242 data: 0.0003 [11-25 17:59:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.465 (6.460) Lt: 5.739 (5.721) Accm: 3.39 (3.46) Acct: 5.44 (5.37) proj_loss: -0.6027 (-0.6099) time: 0.9273 data: 0.0017 [11-25 17:59:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.390 (6.375) Lt: 5.646 (5.608) Accm: 3.69 (3.69) Acct: 5.96 (5.96) proj_loss: -0.6223 (-0.6188) time: 0.9273 data: 0.0018 [11-25 17:59:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.652 (6.567) Lt: 5.869 (5.839) Accm: 2.99 (3.15) Acct: 4.58 (4.77) proj_loss: -0.6290 (-0.6196) time: 0.9273 data: 0.0017 [11-25 17:59:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.565 (6.583) Lt: 5.916 (5.888) Accm: 3.10 (3.12) Acct: 4.41 (4.63) proj_loss: -0.6092 (-0.6057) time: 0.9274 data: 0.0016 [11-25 17:59:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.479 (6.476) Lt: 5.674 (5.688) Accm: 3.37 (3.47) Acct: 5.44 (5.60) proj_loss: -0.6131 (-0.6053) time: 0.9274 data: 0.0017 [11-25 17:59:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.412 (6.406) Lt: 5.644 (5.616) Accm: 3.53 (3.70) Acct: 5.44 (5.74) proj_loss: -0.6149 (-0.6170) time: 0.9274 data: 0.0015 [11-25 17:59:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.369 (6.367) Lt: 5.658 (5.596) Accm: 3.61 (3.56) Acct: 5.58 (5.63) proj_loss: -0.6092 (-0.6107) time: 0.9274 data: 0.0015 [11-25 17:59:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 135/350] Total time: 0:25:51 (0.930 s / it) [11-25 17:59:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 135/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.474 (6.506) Lt: 5.741 (5.734) Accm: 3.51 (3.36) Acct: 5.37 (5.28) proj_loss: -0.5955 (-0.5969) time: 0.9274 data: 0.0015 [11-25 17:59:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 135/350] Total time: 0:25:51 (0.930 s / it) [11-25 17:59:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 135/350] Total time: 0:25:51 (0.930 s / it) [11-25 17:59:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 135/350] Total time: 0:25:51 (0.930 s / it) [11-25 17:59:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 135/350] Total time: 0:25:51 (0.930 s / it) [11-25 17:59:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 135/350] Total time: 0:25:51 (0.930 s / it) [11-25 17:59:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 135/350] Total time: 0:25:51 (0.930 s / it) [11-25 17:59:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 135/350] Total time: 0:25:51 (0.930 s / it) [11-25 17:59:33] (/home/user/VAR/train.py , line 276)=> [ep135] (training ) Lm: 6.460 (6.460), Lt: 5.702 (5.702), Acc m&t: 3.48 5.48, Remain: 3 days, 20:33:14, Finish: 2024-11-28 22:32 [11-25 17:59:33] (/home/user/VAR/train.py , line 276)=> [ep135] (training ) Lm: 6.460 (6.460), Lt: 5.702 (5.702), Acc m&t: 3.48 5.48, Remain: 3 days, 20:34:16, Finish: 2024-11-28 22:33 [11-25 17:59:33] (/home/user/VAR/train.py , line 276)=> [ep135] (training ) Lm: 6.460 (6.460), Lt: 5.702 (5.702), Acc m&t: 3.48 5.48, Remain: 3 days, 20:33:16, Finish: 2024-11-28 22:32 [11-25 17:59:33] (/home/user/VAR/train.py , line 276)=> [ep135] (training ) Lm: 6.460 (6.460), Lt: 5.702 (5.702), Acc m&t: 3.48 5.48, Remain: 3 days, 20:33:06, Finish: 2024-11-28 22:32 [11-25 17:59:33] (/home/user/VAR/train.py , line 276)=> [ep135] (training ) Lm: 6.460 (6.460), Lt: 5.702 (5.702), Acc m&t: 3.48 5.48, Remain: 3 days, 20:33:11, Finish: 2024-11-28 22:32 [11-25 17:59:33] (/home/user/VAR/train.py , line 276)=> [ep135] (training ) Lm: 6.460 (6.460), Lt: 5.702 (5.702), Acc m&t: 3.48 5.48, Remain: 3 days, 20:33:28, Finish: 2024-11-28 22:33 [11-25 17:59:33] (/home/user/VAR/train.py , line 276)=> [ep135] (training ) Lm: 6.460 (6.460), Lt: 5.702 (5.702), Acc m&t: 3.48 5.48, Remain: 3 days, 20:33:55, Finish: 2024-11-28 22:33 [11-25 17:59:33] (/home/user/VAR/train.py , line 276)=> [ep135] (training ) Lm: 6.460 (6.460), Lt: 5.702 (5.702), Acc m&t: 3.48 5.48, Remain: 3 days, 20:33:56, Finish: 2024-11-28 22:33 [11-25 17:59:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 0/1669] eta: 0:24:41 tlr: 0.00016 tnm: 0.24 Lm: 6.375 (6.375) Lt: 5.631 (5.631) Accm: 3.18 (3.18) Acct: 4.61 (4.61) proj_loss: -0.6372 (-0.6372) time: 0.8877 data: 0.0004 [11-25 17:59:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 0/1669] eta: 0:24:42 tlr: 0.00016 tnm: 0.24 Lm: 6.510 (6.510) Lt: 5.879 (5.879) Accm: 3.04 (3.04) Acct: 4.65 (4.65) proj_loss: -0.5890 (-0.5890) time: 0.8884 data: 0.0003 [11-25 17:59:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 0/1669] eta: 0:24:42 tlr: 0.00016 tnm: 0.24 Lm: 6.489 (6.489) Lt: 5.677 (5.677) Accm: 3.28 (3.28) Acct: 4.92 (4.92) proj_loss: -0.6052 (-0.6052) time: 0.8885 data: 0.0004 [11-25 17:59:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 0/1669] eta: 0:24:42 tlr: 0.00016 tnm: 0.24 Lm: 6.485 (6.485) Lt: 5.699 (5.699) Accm: 3.38 (3.38) Acct: 5.13 (5.13) proj_loss: -0.5847 (-0.5847) time: 0.8881 data: 0.0004 [11-25 17:59:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 0/1669] eta: 0:24:43 tlr: 0.00016 tnm: 0.24 Lm: 6.551 (6.551) Lt: 5.845 (5.845) Accm: 3.12 (3.12) Acct: 4.82 (4.82) proj_loss: -0.6299 (-0.6299) time: 0.8889 data: 0.0004 [11-25 17:59:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 0/1669] eta: 0:24:43 tlr: 0.00016 tnm: 0.24 Lm: 6.484 (6.484) Lt: 5.714 (5.714) Accm: 3.39 (3.39) Acct: 5.44 (5.44) proj_loss: -0.6086 (-0.6086) time: 0.8889 data: 0.0004 [11-25 17:59:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 0/1669] eta: 0:24:35 tlr: 0.00016 tnm: 0.24 Lm: 6.183 (6.183) Lt: 5.416 (5.416) Accm: 3.92 (3.92) Acct: 5.92 (5.92) proj_loss: -0.6328 (-0.6328) time: 0.8843 data: 0.0004 [11-25 17:59:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 0/1669] eta: 0:24:45 tlr: 0.00016 tnm: 0.24 Lm: 6.486 (6.486) Lt: 5.803 (5.803) Accm: 3.26 (3.26) Acct: 5.03 (5.03) proj_loss: -0.6415 (-0.6415) time: 0.8900 data: 0.0004 [11-25 18:05:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.389 (6.389) Lt: 5.645 (5.645) Accm: 3.74 (3.74) Acct: 5.92 (5.92) proj_loss: -0.6169 (-0.6169) time: 0.9235 data: 0.0003 [11-25 18:05:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.451 (6.451) Lt: 5.714 (5.714) Accm: 3.49 (3.49) Acct: 5.44 (5.44) proj_loss: -0.6194 (-0.6194) time: 0.9235 data: 0.0002 [11-25 18:05:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.397 (6.397) Lt: 5.670 (5.670) Accm: 3.69 (3.69) Acct: 5.65 (5.65) proj_loss: -0.6151 (-0.6151) time: 0.9235 data: 0.0003 [11-25 18:05:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.349 (6.349) Lt: 5.646 (5.646) Accm: 3.77 (3.77) Acct: 5.92 (5.92) proj_loss: -0.5894 (-0.5894) time: 0.9235 data: 0.0002 [11-25 18:05:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.457 (6.457) Lt: 5.647 (5.647) Accm: 3.63 (3.63) Acct: 5.54 (5.54) proj_loss: -0.5805 (-0.5805) time: 0.9235 data: 0.0002 [11-25 18:05:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.463 (6.463) Lt: 5.660 (5.660) Accm: 3.59 (3.59) Acct: 5.58 (5.58) proj_loss: -0.6094 (-0.6094) time: 0.9235 data: 0.0003 [11-25 18:05:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.255 (6.255) Lt: 5.488 (5.488) Accm: 4.24 (4.24) Acct: 6.30 (6.30) proj_loss: -0.6302 (-0.6302) time: 0.9235 data: 0.0003 [11-25 18:05:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.456 (6.456) Lt: 5.771 (5.771) Accm: 3.45 (3.45) Acct: 5.17 (5.17) proj_loss: -0.6229 (-0.6229) time: 0.9235 data: 0.0003 [11-25 18:12:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 834/1669] eta: 0:13:07 tlr: 0.00016 tnm: 0.24 Lm: 6.515 (6.476) Lt: 5.798 (5.780) Accm: 3.38 (3.43) Acct: 5.20 (5.18) proj_loss: -0.6209 (-0.6222) time: 0.9262 data: 0.0003 [11-25 18:12:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 834/1669] eta: 0:13:07 tlr: 0.00016 tnm: 0.24 Lm: 6.484 (6.471) Lt: 5.713 (5.683) Accm: 3.57 (3.52) Acct: 5.44 (5.64) proj_loss: -0.6086 (-0.6122) time: 0.9261 data: 0.0003 [11-25 18:12:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 834/1669] eta: 0:13:07 tlr: 0.00016 tnm: 0.24 Lm: 6.368 (6.382) Lt: 5.662 (5.651) Accm: 3.76 (3.75) Acct: 5.68 (5.84) proj_loss: -0.6318 (-0.6219) time: 0.9261 data: 0.0002 [11-25 18:12:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 834/1669] eta: 0:13:07 tlr: 0.00016 tnm: 0.24 Lm: 6.510 (6.436) Lt: 5.877 (5.723) Accm: 3.04 (3.50) Acct: 4.75 (5.53) proj_loss: -0.5898 (-0.5906) time: 0.9261 data: 0.0002 [11-25 18:12:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 834/1669] eta: 0:13:07 tlr: 0.00016 tnm: 0.24 Lm: 6.489 (6.489) Lt: 5.677 (5.689) Accm: 3.53 (3.57) Acct: 5.72 (5.62) proj_loss: -0.6052 (-0.6038) time: 0.9261 data: 0.0003 [11-25 18:12:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 834/1669] eta: 0:13:07 tlr: 0.00016 tnm: 0.24 Lm: 6.392 (6.395) Lt: 5.702 (5.681) Accm: 3.92 (3.80) Acct: 5.92 (5.76) proj_loss: -0.6163 (-0.6155) time: 0.9261 data: 0.0003 [11-25 18:12:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 834/1669] eta: 0:13:07 tlr: 0.00016 tnm: 0.24 Lm: 6.429 (6.418) Lt: 5.657 (5.650) Accm: 3.80 (3.69) Acct: 5.65 (5.58) proj_loss: -0.5847 (-0.5959) time: 0.9262 data: 0.0003 [11-25 18:12:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [ 834/1669] eta: 0:13:07 tlr: 0.00016 tnm: 0.24 Lm: 6.375 (6.296) Lt: 5.605 (5.527) Accm: 3.37 (3.95) Acct: 5.48 (6.03) proj_loss: -0.6372 (-0.6357) time: 0.9262 data: 0.0003 [11-25 18:19:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [1251/1669] eta: 0:06:31 tlr: 0.00016 tnm: 0.24 Lm: 6.294 (6.276) Lt: 5.534 (5.511) Accm: 3.96 (4.10) Acct: 6.16 (6.23) proj_loss: -0.6419 (-0.6406) time: 0.9249 data: 0.0003 [11-25 18:19:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [1251/1669] eta: 0:06:31 tlr: 0.00016 tnm: 0.24 Lm: 6.560 (6.485) Lt: 5.878 (5.767) Accm: 3.10 (3.42) Acct: 4.79 (5.35) proj_loss: -0.5895 (-0.5902) time: 0.9248 data: 0.0002 [11-25 18:19:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [1251/1669] eta: 0:06:31 tlr: 0.00016 tnm: 0.24 Lm: 6.485 (6.475) Lt: 5.714 (5.704) Accm: 3.48 (3.46) Acct: 5.44 (5.54) proj_loss: -0.6194 (-0.6217) time: 0.9248 data: 0.0003 [11-25 18:19:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [1251/1669] eta: 0:06:31 tlr: 0.00016 tnm: 0.24 Lm: 6.463 (6.435) Lt: 5.660 (5.611) Accm: 3.69 (3.64) Acct: 5.97 (5.83) proj_loss: -0.6068 (-0.6049) time: 0.9248 data: 0.0002 [11-25 18:19:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [1251/1669] eta: 0:06:31 tlr: 0.00016 tnm: 0.24 Lm: 6.498 (6.448) Lt: 5.745 (5.708) Accm: 3.69 (3.67) Acct: 5.65 (5.58) proj_loss: -0.6069 (-0.6094) time: 0.9248 data: 0.0003 [11-25 18:19:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [1251/1669] eta: 0:06:31 tlr: 0.00016 tnm: 0.24 Lm: 6.425 (6.407) Lt: 5.733 (5.693) Accm: 3.52 (3.63) Acct: 5.39 (5.66) proj_loss: -0.6306 (-0.6237) time: 0.9249 data: 0.0003 [11-25 18:19:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [1251/1669] eta: 0:06:31 tlr: 0.00016 tnm: 0.24 Lm: 6.407 (6.410) Lt: 5.663 (5.655) Accm: 3.68 (3.65) Acct: 5.54 (5.54) proj_loss: -0.5924 (-0.5969) time: 0.9249 data: 0.0002 [11-25 18:19:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [1251/1669] eta: 0:06:31 tlr: 0.00016 tnm: 0.24 Lm: 6.438 (6.437) Lt: 5.748 (5.728) Accm: 3.53 (3.49) Acct: 5.35 (5.29) proj_loss: -0.6219 (-0.6224) time: 0.9249 data: 0.0003 [11-25 18:25:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.515 (6.485) Lt: 5.798 (5.774) Accm: 3.38 (3.34) Acct: 5.20 (5.06) proj_loss: -0.6209 (-0.6184) time: 0.9246 data: 0.0015 [11-25 18:25:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 136/350] Total time: 0:25:57 (0.933 s / it) [11-25 18:25:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.375 (6.306) Lt: 5.605 (5.554) Accm: 3.57 (3.99) Acct: 5.48 (5.98) proj_loss: -0.6372 (-0.6393) time: 0.9246 data: 0.0019 [11-25 18:25:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.486 (6.507) Lt: 5.714 (5.745) Accm: 3.39 (3.39) Acct: 5.44 (5.47) proj_loss: -0.6196 (-0.6213) time: 0.9246 data: 0.0016 [11-25 18:25:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.368 (6.360) Lt: 5.662 (5.625) Accm: 3.76 (3.88) Acct: 5.68 (5.95) proj_loss: -0.6293 (-0.6208) time: 0.9246 data: 0.0017 [11-25 18:25:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.510 (6.488) Lt: 5.877 (5.748) Accm: 3.16 (3.37) Acct: 4.82 (5.30) proj_loss: -0.5891 (-0.5846) time: 0.9246 data: 0.0016 [11-25 18:25:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.438 (6.426) Lt: 5.644 (5.610) Accm: 3.54 (3.62) Acct: 5.72 (5.80) proj_loss: -0.6084 (-0.6108) time: 0.9246 data: 0.0016 [11-25 18:25:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.605 (6.481) Lt: 5.788 (5.753) Accm: 3.47 (3.59) Acct: 5.37 (5.45) proj_loss: -0.6134 (-0.6102) time: 0.9246 data: 0.0017 [11-25 18:25:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 136/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.24 Lm: 6.384 (6.392) Lt: 5.657 (5.618) Accm: 3.80 (3.77) Acct: 5.65 (5.81) proj_loss: -0.5967 (-0.5968) time: 0.9246 data: 0.0016 [11-25 18:25:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 136/350] Total time: 0:25:57 (0.933 s / it) [11-25 18:25:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 136/350] Total time: 0:25:57 (0.933 s / it) [11-25 18:25:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 136/350] Total time: 0:25:57 (0.933 s / it) [11-25 18:25:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 136/350] Total time: 0:25:57 (0.933 s / it) [11-25 18:25:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 136/350] Total time: 0:25:57 (0.933 s / it) [11-25 18:25:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 136/350] Total time: 0:25:57 (0.933 s / it) [11-25 18:25:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 136/350] Total time: 0:25:57 (0.933 s / it) [11-25 18:25:31] (/home/user/VAR/train.py , line 276)=> [ep136] (training ) Lm: 6.446 (6.446), Lt: 5.691 (5.691), Acc m&t: 3.55 5.55, Remain: 3 days, 20:02:41, Finish: 2024-11-28 22:28 [11-25 18:25:31] (/home/user/VAR/train.py , line 276)=> [ep136] (training ) Lm: 6.446 (6.446), Lt: 5.691 (5.691), Acc m&t: 3.55 5.55, Remain: 3 days, 20:02:15, Finish: 2024-11-28 22:27 [11-25 18:25:31] (/home/user/VAR/train.py , line 276)=> [ep136] (training ) Lm: 6.446 (6.446), Lt: 5.691 (5.691), Acc m&t: 3.55 5.55, Remain: 3 days, 20:02:46, Finish: 2024-11-28 22:28 [11-25 18:25:31] (/home/user/VAR/train.py , line 276)=> [ep136] (training ) Lm: 6.446 (6.446), Lt: 5.691 (5.691), Acc m&t: 3.55 5.55, Remain: 3 days, 20:02:31, Finish: 2024-11-28 22:28 [11-25 18:25:31] (/home/user/VAR/train.py , line 276)=> [ep136] (training ) Lm: 6.446 (6.446), Lt: 5.691 (5.691), Acc m&t: 3.55 5.55, Remain: 3 days, 20:01:47, Finish: 2024-11-28 22:27 [11-25 18:25:31] (/home/user/VAR/train.py , line 276)=> [ep136] (training ) Lm: 6.446 (6.446), Lt: 5.691 (5.691), Acc m&t: 3.55 5.55, Remain: 3 days, 20:02:38, Finish: 2024-11-28 22:28 [11-25 18:25:31] (/home/user/VAR/train.py , line 276)=> [ep136] (training ) Lm: 6.446 (6.446), Lt: 5.691 (5.691), Acc m&t: 3.55 5.55, Remain: 3 days, 20:02:03, Finish: 2024-11-28 22:27 [11-25 18:25:31] (/home/user/VAR/train.py , line 276)=> [ep136] (training ) Lm: 6.446 (6.446), Lt: 5.691 (5.691), Acc m&t: 3.55 5.55, Remain: 3 days, 20:02:10, Finish: 2024-11-28 22:27 [11-25 18:25:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 0/1669] eta: 0:25:15 tlr: 0.00016 tnm: 0.24 Lm: 6.729 (6.729) Lt: 6.082 (6.082) Accm: 2.55 (2.55) Acct: 3.86 (3.86) proj_loss: -0.6048 (-0.6048) time: 0.9082 data: 0.0003 [11-25 18:25:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 0/1669] eta: 0:25:16 tlr: 0.00016 tnm: 0.24 Lm: 6.577 (6.577) Lt: 5.854 (5.854) Accm: 2.70 (2.70) Acct: 4.27 (4.27) proj_loss: -0.6243 (-0.6243) time: 0.9085 data: 0.0004 [11-25 18:25:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 0/1669] eta: 0:25:15 tlr: 0.00016 tnm: 0.24 Lm: 6.406 (6.406) Lt: 5.687 (5.687) Accm: 3.95 (3.95) Acct: 6.13 (6.13) proj_loss: -0.6541 (-0.6541) time: 0.9081 data: 0.0004 [11-25 18:25:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 0/1669] eta: 0:25:16 tlr: 0.00016 tnm: 0.24 Lm: 6.573 (6.573) Lt: 5.816 (5.816) Accm: 3.16 (3.16) Acct: 4.89 (4.89) proj_loss: -0.5868 (-0.5868) time: 0.9086 data: 0.0004 [11-25 18:25:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 0/1669] eta: 0:25:16 tlr: 0.00016 tnm: 0.24 Lm: 6.519 (6.519) Lt: 5.683 (5.683) Accm: 3.21 (3.21) Acct: 5.17 (5.17) proj_loss: -0.6268 (-0.6268) time: 0.9088 data: 0.0004 [11-25 18:25:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 0/1669] eta: 0:25:17 tlr: 0.00016 tnm: 0.24 Lm: 6.526 (6.526) Lt: 5.825 (5.825) Accm: 2.99 (2.99) Acct: 4.72 (4.72) proj_loss: -0.6040 (-0.6040) time: 0.9092 data: 0.0004 [11-25 18:25:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 0/1669] eta: 0:25:17 tlr: 0.00016 tnm: 0.24 Lm: 6.449 (6.449) Lt: 5.587 (5.587) Accm: 3.48 (3.48) Acct: 5.85 (5.85) proj_loss: -0.5860 (-0.5860) time: 0.9092 data: 0.0003 [11-25 18:25:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 0/1669] eta: 0:25:17 tlr: 0.00016 tnm: 0.24 Lm: 6.427 (6.427) Lt: 5.750 (5.750) Accm: 3.23 (3.23) Acct: 5.10 (5.10) proj_loss: -0.6463 (-0.6463) time: 0.9091 data: 0.0004 [11-25 18:31:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.373 (6.373) Lt: 5.695 (5.695) Accm: 3.42 (3.42) Acct: 5.04 (5.04) proj_loss: -0.6354 (-0.6354) time: 0.9240 data: 0.0002 [11-25 18:31:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.614 (6.614) Lt: 5.897 (5.897) Accm: 2.88 (2.88) Acct: 4.51 (4.51) proj_loss: -0.5987 (-0.5987) time: 0.9240 data: 0.0002 [11-25 18:31:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.467 (6.467) Lt: 5.688 (5.688) Accm: 3.47 (3.47) Acct: 5.53 (5.53) proj_loss: -0.6029 (-0.6029) time: 0.9240 data: 0.0003 [11-25 18:31:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.482 (6.482) Lt: 5.789 (5.789) Accm: 3.26 (3.26) Acct: 5.10 (5.10) proj_loss: -0.6240 (-0.6240) time: 0.9240 data: 0.0002 [11-25 18:31:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.451 (6.451) Lt: 5.614 (5.614) Accm: 3.44 (3.44) Acct: 5.51 (5.51) proj_loss: -0.6081 (-0.6081) time: 0.9240 data: 0.0003 [11-25 18:31:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.367 (6.367) Lt: 5.608 (5.608) Accm: 3.55 (3.55) Acct: 5.63 (5.63) proj_loss: -0.6103 (-0.6103) time: 0.9240 data: 0.0003 [11-25 18:31:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.520 (6.520) Lt: 5.776 (5.776) Accm: 3.15 (3.15) Acct: 4.89 (4.89) proj_loss: -0.6120 (-0.6120) time: 0.9240 data: 0.0002 [11-25 18:31:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.431 (6.431) Lt: 5.649 (5.649) Accm: 3.67 (3.67) Acct: 5.72 (5.72) proj_loss: -0.5923 (-0.5923) time: 0.9240 data: 0.0003 [11-25 18:38:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.406 (6.423) Lt: 5.631 (5.643) Accm: 3.48 (3.61) Acct: 5.82 (5.75) proj_loss: -0.5978 (-0.5999) time: 0.9261 data: 0.0003 [11-25 18:38:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.383 (6.397) Lt: 5.546 (5.579) Accm: 3.67 (3.58) Acct: 5.85 (5.77) proj_loss: -0.6054 (-0.6072) time: 0.9261 data: 0.0003 [11-25 18:38:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.406 (6.429) Lt: 5.687 (5.716) Accm: 3.95 (3.55) Acct: 6.13 (5.61) proj_loss: -0.6263 (-0.6248) time: 0.9261 data: 0.0002 [11-25 18:38:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.320 (6.333) Lt: 5.640 (5.620) Accm: 3.61 (3.68) Acct: 5.10 (5.59) proj_loss: -0.6246 (-0.6309) time: 0.9261 data: 0.0003 [11-25 18:38:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.463 (6.454) Lt: 5.697 (5.696) Accm: 3.61 (3.39) Acct: 5.51 (5.11) proj_loss: -0.6156 (-0.6132) time: 0.9261 data: 0.0003 [11-25 18:38:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.449 (6.407) Lt: 5.587 (5.645) Accm: 3.48 (3.73) Acct: 5.85 (5.80) proj_loss: -0.6197 (-0.6157) time: 0.9261 data: 0.0003 [11-25 18:38:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.216 (6.316) Lt: 5.429 (5.548) Accm: 4.12 (3.93) Acct: 6.54 (6.22) proj_loss: -0.6165 (-0.6143) time: 0.9261 data: 0.0003 [11-25 18:38:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.499 (6.541) Lt: 5.712 (5.806) Accm: 3.21 (3.18) Acct: 5.17 (4.98) proj_loss: -0.6048 (-0.6018) time: 0.9261 data: 0.0003 [11-25 18:44:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.24 Lm: 6.447 (6.501) Lt: 5.669 (5.737) Accm: 3.49 (3.36) Acct: 5.54 (5.35) proj_loss: -0.5987 (-0.5986) time: 0.9640 data: 0.0003 [11-25 18:44:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.24 Lm: 6.373 (6.413) Lt: 5.695 (5.683) Accm: 3.42 (3.53) Acct: 5.04 (5.41) proj_loss: -0.6233 (-0.6257) time: 0.9640 data: 0.0003 [11-25 18:44:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.24 Lm: 6.316 (6.342) Lt: 5.528 (5.568) Accm: 3.79 (3.81) Acct: 6.10 (6.08) proj_loss: -0.6156 (-0.6144) time: 0.9640 data: 0.0003 [11-25 18:44:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.24 Lm: 6.451 (6.455) Lt: 5.614 (5.654) Accm: 3.44 (3.40) Acct: 5.51 (5.48) proj_loss: -0.5974 (-0.5997) time: 0.9640 data: 0.0003 [11-25 18:44:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.24 Lm: 6.520 (6.491) Lt: 5.776 (5.748) Accm: 3.44 (3.36) Acct: 5.29 (5.10) proj_loss: -0.6090 (-0.6105) time: 0.9640 data: 0.0002 [11-25 18:44:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.24 Lm: 6.446 (6.443) Lt: 5.685 (5.708) Accm: 3.69 (3.52) Acct: 5.89 (5.62) proj_loss: -0.6125 (-0.6183) time: 0.9640 data: 0.0003 [11-25 18:44:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.24 Lm: 6.480 (6.456) Lt: 5.723 (5.693) Accm: 3.32 (3.43) Acct: 5.35 (5.43) proj_loss: -0.6064 (-0.6037) time: 0.9640 data: 0.0003 [11-25 18:44:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.24 Lm: 6.370 (6.378) Lt: 5.573 (5.622) Accm: 3.77 (3.81) Acct: 5.91 (5.84) proj_loss: -0.6181 (-0.6159) time: 0.9640 data: 0.0003 [11-25 18:51:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.408 (6.384) Lt: 5.587 (5.629) Accm: 3.58 (3.77) Acct: 5.85 (5.78) proj_loss: -0.6197 (-0.6192) time: 0.9260 data: 0.0017 [11-25 18:51:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 137/350] Total time: 0:25:56 (0.932 s / it) [11-25 18:51:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.408 (6.482) Lt: 5.683 (5.727) Accm: 3.63 (3.41) Acct: 5.82 (5.44) proj_loss: -0.6048 (-0.6066) time: 0.9260 data: 0.0019 [11-25 18:51:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.547 (6.502) Lt: 5.838 (5.766) Accm: 3.26 (3.28) Acct: 5.06 (5.03) proj_loss: -0.6155 (-0.6115) time: 0.9260 data: 0.0019 [11-25 18:51:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.427 (6.431) Lt: 5.720 (5.690) Accm: 3.31 (3.48) Acct: 5.10 (5.39) proj_loss: -0.6219 (-0.6234) time: 0.9260 data: 0.0016 [11-25 18:51:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.485 (6.466) Lt: 5.687 (5.720) Accm: 3.42 (3.48) Acct: 5.65 (5.58) proj_loss: -0.6077 (-0.6161) time: 0.9260 data: 0.0016 [11-25 18:51:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.501 (6.465) Lt: 5.761 (5.707) Accm: 3.16 (3.35) Acct: 4.89 (5.28) proj_loss: -0.6149 (-0.6126) time: 0.9260 data: 0.0019 [11-25 18:51:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.441 (6.452) Lt: 5.669 (5.657) Accm: 3.42 (3.41) Acct: 5.30 (5.44) proj_loss: -0.6040 (-0.6006) time: 0.9260 data: 0.0016 [11-25 18:51:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 137/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.417 (6.375) Lt: 5.627 (5.586) Accm: 3.58 (3.77) Acct: 5.79 (6.02) proj_loss: -0.6147 (-0.6102) time: 0.9260 data: 0.0020 [11-25 18:51:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 137/350] Total time: 0:25:56 (0.932 s / it) [11-25 18:51:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 137/350] Total time: 0:25:56 (0.932 s / it) [11-25 18:51:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 137/350] Total time: 0:25:56 (0.932 s / it) [11-25 18:51:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 137/350] Total time: 0:25:56 (0.932 s / it) [11-25 18:51:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 137/350] Total time: 0:25:56 (0.932 s / it) [11-25 18:51:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 137/350] Total time: 0:25:56 (0.932 s / it) [11-25 18:51:27] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 137/350] Total time: 0:25:56 (0.932 s / it) [11-25 18:51:27] (/home/user/VAR/train.py , line 276)=> [ep137] (training ) Lm: 6.446 (6.446), Lt: 5.691 (5.695), Acc m&t: 3.55 5.55, Remain: 3 days, 19:44:49, Finish: 2024-11-28 22:36 [11-25 18:51:27] (/home/user/VAR/train.py , line 276)=> [ep137] (training ) Lm: 6.446 (6.446), Lt: 5.691 (5.695), Acc m&t: 3.55 5.55, Remain: 3 days, 19:43:31, Finish: 2024-11-28 22:34 [11-25 18:51:27] (/home/user/VAR/train.py , line 276)=> [ep137] (training ) Lm: 6.446 (6.446), Lt: 5.691 (5.695), Acc m&t: 3.55 5.55, Remain: 3 days, 19:42:29, Finish: 2024-11-28 22:33 [11-25 18:51:27] (/home/user/VAR/train.py , line 276)=> [ep137] (training ) Lm: 6.446 (6.446), Lt: 5.691 (5.695), Acc m&t: 3.55 5.55, Remain: 3 days, 19:42:06, Finish: 2024-11-28 22:33 [11-25 18:51:27] (/home/user/VAR/train.py , line 276)=> [ep137] (training ) Lm: 6.446 (6.446), Lt: 5.691 (5.695), Acc m&t: 3.55 5.55, Remain: 3 days, 19:42:40, Finish: 2024-11-28 22:34 [11-25 18:51:27] (/home/user/VAR/train.py , line 276)=> [ep137] (training ) Lm: 6.446 (6.446), Lt: 5.691 (5.695), Acc m&t: 3.55 5.55, Remain: 3 days, 19:43:37, Finish: 2024-11-28 22:35 [11-25 18:51:27] (/home/user/VAR/train.py , line 276)=> [ep137] (training ) Lm: 6.446 (6.446), Lt: 5.691 (5.695), Acc m&t: 3.55 5.55, Remain: 3 days, 19:44:40, Finish: 2024-11-28 22:36 [11-25 18:51:27] (/home/user/VAR/train.py , line 276)=> [ep137] (training ) Lm: 6.446 (6.446), Lt: 5.691 (5.695), Acc m&t: 3.55 5.55, Remain: 3 days, 19:43:19, Finish: 2024-11-28 22:34 [11-25 18:51:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 0/1669] eta: 0:25:01 tlr: 0.00016 tnm: 0.24 Lm: 6.641 (6.641) Lt: 5.933 (5.933) Accm: 2.96 (2.96) Acct: 4.30 (4.30) proj_loss: -0.6059 (-0.6059) time: 0.8994 data: 0.0004 [11-25 18:51:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 0/1669] eta: 0:25:01 tlr: 0.00016 tnm: 0.24 Lm: 6.327 (6.327) Lt: 5.518 (5.518) Accm: 4.17 (4.17) Acct: 6.68 (6.68) proj_loss: -0.6238 (-0.6238) time: 0.8995 data: 0.0003 [11-25 18:51:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 0/1669] eta: 0:25:01 tlr: 0.00016 tnm: 0.24 Lm: 6.391 (6.391) Lt: 5.682 (5.682) Accm: 3.86 (3.86) Acct: 6.13 (6.13) proj_loss: -0.6265 (-0.6265) time: 0.8996 data: 0.0004 [11-25 18:51:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 0/1669] eta: 0:25:01 tlr: 0.00016 tnm: 0.24 Lm: 6.429 (6.429) Lt: 5.746 (5.746) Accm: 3.29 (3.29) Acct: 4.75 (4.75) proj_loss: -0.6393 (-0.6393) time: 0.8998 data: 0.0004 [11-25 18:51:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 0/1669] eta: 0:25:01 tlr: 0.00016 tnm: 0.24 Lm: 6.296 (6.296) Lt: 5.519 (5.519) Accm: 4.20 (4.20) Acct: 6.37 (6.37) proj_loss: -0.6219 (-0.6219) time: 0.8998 data: 0.0004 [11-25 18:51:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 0/1669] eta: 0:25:02 tlr: 0.00016 tnm: 0.24 Lm: 6.383 (6.383) Lt: 5.551 (5.551) Accm: 3.93 (3.93) Acct: 6.44 (6.44) proj_loss: -0.6176 (-0.6176) time: 0.9003 data: 0.0004 [11-25 18:51:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 0/1669] eta: 0:25:02 tlr: 0.00016 tnm: 0.24 Lm: 6.556 (6.556) Lt: 5.797 (5.797) Accm: 3.19 (3.19) Acct: 5.34 (5.34) proj_loss: -0.5911 (-0.5911) time: 0.9002 data: 0.0004 [11-25 18:51:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 0/1669] eta: 0:25:02 tlr: 0.00016 tnm: 0.24 Lm: 6.764 (6.764) Lt: 6.095 (6.095) Accm: 2.64 (2.64) Acct: 3.93 (3.93) proj_loss: -0.6290 (-0.6290) time: 0.9001 data: 0.0003 [11-25 18:57:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 417/1669] eta: 0:19:15 tlr: 0.00016 tnm: 0.25 Lm: 6.601 (6.601) Lt: 5.894 (5.894) Accm: 3.08 (3.08) Acct: 4.63 (4.63) proj_loss: -0.6388 (-0.6388) time: 0.9202 data: 0.0002 [11-25 18:57:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 417/1669] eta: 0:19:15 tlr: 0.00016 tnm: 0.25 Lm: 6.346 (6.346) Lt: 5.547 (5.547) Accm: 3.93 (3.93) Acct: 6.20 (6.20) proj_loss: -0.6100 (-0.6100) time: 0.9202 data: 0.0003 [11-25 18:57:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 417/1669] eta: 0:19:15 tlr: 0.00016 tnm: 0.25 Lm: 6.632 (6.632) Lt: 5.929 (5.929) Accm: 2.81 (2.81) Acct: 4.10 (4.10) proj_loss: -0.6145 (-0.6145) time: 0.9202 data: 0.0003 [11-25 18:57:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 417/1669] eta: 0:19:15 tlr: 0.00016 tnm: 0.25 Lm: 6.438 (6.438) Lt: 5.705 (5.705) Accm: 3.67 (3.67) Acct: 5.68 (5.68) proj_loss: -0.6150 (-0.6150) time: 0.9202 data: 0.0002 [11-25 18:57:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 417/1669] eta: 0:19:15 tlr: 0.00016 tnm: 0.25 Lm: 6.450 (6.450) Lt: 5.722 (5.722) Accm: 3.43 (3.43) Acct: 5.25 (5.25) proj_loss: -0.6296 (-0.6296) time: 0.9202 data: 0.0003 [11-25 18:57:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 417/1669] eta: 0:19:15 tlr: 0.00016 tnm: 0.25 Lm: 6.443 (6.443) Lt: 5.675 (5.675) Accm: 3.62 (3.62) Acct: 5.79 (5.79) proj_loss: -0.6195 (-0.6195) time: 0.9202 data: 0.0002 [11-25 18:57:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 417/1669] eta: 0:19:15 tlr: 0.00016 tnm: 0.25 Lm: 6.414 (6.414) Lt: 5.603 (5.603) Accm: 3.66 (3.66) Acct: 5.85 (5.85) proj_loss: -0.6231 (-0.6231) time: 0.9202 data: 0.0003 [11-25 18:57:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 417/1669] eta: 0:19:15 tlr: 0.00016 tnm: 0.25 Lm: 6.541 (6.541) Lt: 5.775 (5.775) Accm: 3.29 (3.29) Acct: 5.48 (5.48) proj_loss: -0.5956 (-0.5956) time: 0.9203 data: 0.0003 [11-25 19:04:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 834/1669] eta: 0:12:50 tlr: 0.00016 tnm: 0.25 Lm: 6.534 (6.539) Lt: 5.797 (5.803) Accm: 3.39 (3.35) Acct: 5.61 (5.52) proj_loss: -0.6001 (-0.6044) time: 0.9260 data: 0.0002 [11-25 19:04:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 834/1669] eta: 0:12:50 tlr: 0.00016 tnm: 0.25 Lm: 6.391 (6.386) Lt: 5.682 (5.627) Accm: 3.86 (3.92) Acct: 6.13 (6.14) proj_loss: -0.6265 (-0.6229) time: 0.9260 data: 0.0002 [11-25 19:04:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 834/1669] eta: 0:12:50 tlr: 0.00016 tnm: 0.25 Lm: 6.396 (6.408) Lt: 5.576 (5.652) Accm: 3.67 (3.67) Acct: 6.03 (5.64) proj_loss: -0.6199 (-0.6133) time: 0.9260 data: 0.0003 [11-25 19:04:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 834/1669] eta: 0:12:50 tlr: 0.00016 tnm: 0.25 Lm: 6.565 (6.589) Lt: 5.857 (5.882) Accm: 3.53 (3.26) Acct: 5.34 (4.96) proj_loss: -0.6290 (-0.6323) time: 0.9260 data: 0.0003 [11-25 19:04:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 834/1669] eta: 0:12:50 tlr: 0.00016 tnm: 0.25 Lm: 6.623 (6.610) Lt: 5.924 (5.893) Accm: 2.87 (2.83) Acct: 4.30 (4.27) proj_loss: -0.6059 (-0.6108) time: 0.9260 data: 0.0003 [11-25 19:04:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 834/1669] eta: 0:12:50 tlr: 0.00016 tnm: 0.25 Lm: 6.429 (6.387) Lt: 5.698 (5.657) Accm: 3.57 (3.67) Acct: 5.75 (5.46) proj_loss: -0.6199 (-0.6222) time: 0.9260 data: 0.0002 [11-25 19:04:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 834/1669] eta: 0:12:50 tlr: 0.00016 tnm: 0.25 Lm: 6.444 (6.499) Lt: 5.654 (5.723) Accm: 3.39 (3.41) Acct: 5.27 (5.41) proj_loss: -0.6285 (-0.6252) time: 0.9260 data: 0.0003 [11-25 19:04:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [ 834/1669] eta: 0:12:50 tlr: 0.00016 tnm: 0.25 Lm: 6.485 (6.457) Lt: 5.711 (5.687) Accm: 3.83 (3.69) Acct: 6.06 (5.88) proj_loss: -0.6184 (-0.6192) time: 0.9260 data: 0.0002 [11-25 19:10:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [1251/1669] eta: 0:06:25 tlr: 0.00016 tnm: 0.25 Lm: 6.522 (6.531) Lt: 5.772 (5.787) Accm: 3.45 (3.46) Acct: 5.48 (5.48) proj_loss: -0.6205 (-0.6200) time: 0.9255 data: 0.0003 [11-25 19:10:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [1251/1669] eta: 0:06:25 tlr: 0.00016 tnm: 0.25 Lm: 6.464 (6.456) Lt: 5.718 (5.713) Accm: 3.40 (3.47) Acct: 5.27 (5.35) proj_loss: -0.6132 (-0.6116) time: 0.9255 data: 0.0003 [11-25 19:10:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [1251/1669] eta: 0:06:25 tlr: 0.00016 tnm: 0.25 Lm: 6.450 (6.425) Lt: 5.722 (5.688) Accm: 3.69 (3.71) Acct: 5.80 (5.56) proj_loss: -0.6174 (-0.6204) time: 0.9254 data: 0.0002 [11-25 19:10:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [1251/1669] eta: 0:06:25 tlr: 0.00016 tnm: 0.25 Lm: 6.664 (6.644) Lt: 5.968 (5.931) Accm: 3.08 (2.98) Acct: 4.63 (4.55) proj_loss: -0.6245 (-0.6292) time: 0.9254 data: 0.0003 [11-25 19:10:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [1251/1669] eta: 0:06:25 tlr: 0.00016 tnm: 0.25 Lm: 6.457 (6.492) Lt: 5.745 (5.751) Accm: 3.50 (3.46) Acct: 5.29 (5.38) proj_loss: -0.6290 (-0.6309) time: 0.9255 data: 0.0003 [11-25 19:10:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [1251/1669] eta: 0:06:25 tlr: 0.00016 tnm: 0.25 Lm: 6.337 (6.359) Lt: 5.585 (5.592) Accm: 3.69 (3.82) Acct: 5.94 (6.04) proj_loss: -0.6270 (-0.6241) time: 0.9255 data: 0.0003 [11-25 19:10:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [1251/1669] eta: 0:06:25 tlr: 0.00016 tnm: 0.25 Lm: 6.632 (6.655) Lt: 5.929 (5.975) Accm: 2.77 (2.76) Acct: 4.10 (4.05) proj_loss: -0.6145 (-0.6144) time: 0.9254 data: 0.0003 [11-25 19:10:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [1251/1669] eta: 0:06:25 tlr: 0.00016 tnm: 0.25 Lm: 6.531 (6.534) Lt: 5.803 (5.805) Accm: 3.43 (3.39) Acct: 5.48 (5.42) proj_loss: -0.6090 (-0.6078) time: 0.9255 data: 0.0003 [11-25 19:17:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.534 (6.554) Lt: 5.809 (5.854) Accm: 3.39 (3.37) Acct: 5.34 (5.37) proj_loss: -0.6179 (-0.6099) time: 0.9236 data: 0.0016 [11-25 19:17:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 138/350] Total time: 0:26:02 (0.936 s / it) [11-25 19:17:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.391 (6.395) Lt: 5.682 (5.639) Accm: 3.53 (3.72) Acct: 5.75 (5.84) proj_loss: -0.6272 (-0.6247) time: 0.9236 data: 0.0017 [11-25 19:17:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.437 (6.427) Lt: 5.745 (5.699) Accm: 3.57 (3.62) Acct: 5.75 (5.44) proj_loss: -0.6149 (-0.6180) time: 0.9236 data: 0.0016 [11-25 19:17:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.485 (6.506) Lt: 5.711 (5.752) Accm: 3.64 (3.50) Acct: 5.96 (5.57) proj_loss: -0.6184 (-0.6161) time: 0.9236 data: 0.0018 [11-25 19:17:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.396 (6.442) Lt: 5.672 (5.705) Accm: 3.67 (3.52) Acct: 5.65 (5.41) proj_loss: -0.6064 (-0.6103) time: 0.9236 data: 0.0018 [11-25 19:17:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.623 (6.622) Lt: 5.924 (5.921) Accm: 2.87 (2.92) Acct: 4.30 (4.40) proj_loss: -0.6059 (-0.6119) time: 0.9236 data: 0.0015 [11-25 19:17:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.565 (6.585) Lt: 5.857 (5.855) Accm: 3.53 (3.14) Acct: 5.34 (4.77) proj_loss: -0.6290 (-0.6325) time: 0.9236 data: 0.0017 [11-25 19:17:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 138/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.25 Lm: 6.469 (6.524) Lt: 5.835 (5.792) Accm: 3.39 (3.35) Acct: 5.27 (5.21) proj_loss: -0.6285 (-0.6267) time: 0.9237 data: 0.0020 [11-25 19:17:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 138/350] Total time: 0:26:02 (0.936 s / it) [11-25 19:17:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 138/350] Total time: 0:26:02 (0.936 s / it) [11-25 19:17:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 138/350] Total time: 0:26:02 (0.936 s / it) [11-25 19:17:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 138/350] Total time: 0:26:02 (0.936 s / it) [11-25 19:17:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 138/350] Total time: 0:26:02 (0.936 s / it) [11-25 19:17:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 138/350] Total time: 0:26:02 (0.936 s / it) [11-25 19:17:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 138/350] Total time: 0:26:02 (0.936 s / it) [11-25 19:17:29] (/home/user/VAR/train.py , line 276)=> [ep138] (training ) Lm: 6.446 (6.454), Lt: 5.691 (5.698), Acc m&t: 3.55 5.55, Remain: 3 days, 19:05:50, Finish: 2024-11-28 22:23 [11-25 19:17:29] (/home/user/VAR/train.py , line 276)=> [ep138] (training ) Lm: 6.446 (6.454), Lt: 5.691 (5.698), Acc m&t: 3.55 5.55, Remain: 3 days, 19:05:52, Finish: 2024-11-28 22:23 [11-25 19:17:29] (/home/user/VAR/train.py , line 276)=> [ep138] (training ) Lm: 6.446 (6.454), Lt: 5.691 (5.698), Acc m&t: 3.55 5.55, Remain: 3 days, 19:05:15, Finish: 2024-11-28 22:22 [11-25 19:17:29] (/home/user/VAR/train.py , line 276)=> [ep138] (training ) Lm: 6.446 (6.454), Lt: 5.691 (5.698), Acc m&t: 3.55 5.55, Remain: 3 days, 19:05:04, Finish: 2024-11-28 22:22 [11-25 19:17:29] (/home/user/VAR/train.py , line 276)=> [ep138] (training ) Lm: 6.446 (6.454), Lt: 5.691 (5.698), Acc m&t: 3.55 5.55, Remain: 3 days, 19:04:49, Finish: 2024-11-28 22:22 [11-25 19:17:29] (/home/user/VAR/train.py , line 276)=> [ep138] (training ) Lm: 6.446 (6.454), Lt: 5.691 (5.698), Acc m&t: 3.55 5.55, Remain: 3 days, 19:05:41, Finish: 2024-11-28 22:23 [11-25 19:17:29] (/home/user/VAR/train.py , line 276)=> [ep138] (training ) Lm: 6.446 (6.454), Lt: 5.691 (5.698), Acc m&t: 3.55 5.55, Remain: 3 days, 19:04:20, Finish: 2024-11-28 22:21 [11-25 19:17:29] (/home/user/VAR/train.py , line 276)=> [ep138] (training ) Lm: 6.446 (6.454), Lt: 5.691 (5.698), Acc m&t: 3.55 5.55, Remain: 3 days, 19:04:57, Finish: 2024-11-28 22:22 [11-25 19:17:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 0/1669] eta: 0:25:08 tlr: 0.00016 tnm: 0.25 Lm: 6.332 (6.332) Lt: 5.575 (5.575) Accm: 3.55 (3.55) Acct: 5.92 (5.92) proj_loss: -0.6144 (-0.6144) time: 0.9040 data: 0.0004 [11-25 19:17:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 0/1669] eta: 0:25:15 tlr: 0.00016 tnm: 0.25 Lm: 6.641 (6.641) Lt: 5.945 (5.945) Accm: 2.91 (2.91) Acct: 4.20 (4.20) proj_loss: -0.6236 (-0.6236) time: 0.9082 data: 0.0004 [11-25 19:17:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 0/1669] eta: 0:25:11 tlr: 0.00016 tnm: 0.25 Lm: 6.485 (6.485) Lt: 5.679 (5.679) Accm: 3.67 (3.67) Acct: 6.06 (6.06) proj_loss: -0.6071 (-0.6071) time: 0.9055 data: 0.0003 [11-25 19:17:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 0/1669] eta: 0:25:10 tlr: 0.00016 tnm: 0.25 Lm: 6.481 (6.481) Lt: 5.679 (5.679) Accm: 3.41 (3.41) Acct: 5.44 (5.44) proj_loss: -0.6135 (-0.6135) time: 0.9053 data: 0.0004 [11-25 19:17:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 0/1669] eta: 0:25:12 tlr: 0.00016 tnm: 0.25 Lm: 6.529 (6.529) Lt: 5.777 (5.777) Accm: 3.28 (3.28) Acct: 4.79 (4.79) proj_loss: -0.6133 (-0.6133) time: 0.9063 data: 0.0004 [11-25 19:17:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 0/1669] eta: 0:25:11 tlr: 0.00016 tnm: 0.25 Lm: 6.090 (6.090) Lt: 5.429 (5.429) Accm: 4.63 (4.63) Acct: 6.75 (6.75) proj_loss: -0.6092 (-0.6092) time: 0.9055 data: 0.0004 [11-25 19:17:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 0/1669] eta: 0:25:11 tlr: 0.00016 tnm: 0.25 Lm: 6.278 (6.278) Lt: 5.410 (5.410) Accm: 4.02 (4.02) Acct: 6.13 (6.13) proj_loss: -0.5901 (-0.5901) time: 0.9054 data: 0.0005 [11-25 19:17:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 0/1669] eta: 0:25:11 tlr: 0.00016 tnm: 0.25 Lm: 6.538 (6.538) Lt: 5.853 (5.853) Accm: 3.58 (3.58) Acct: 5.58 (5.58) proj_loss: -0.6409 (-0.6409) time: 0.9058 data: 0.0004 [11-25 19:23:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.460 (6.460) Lt: 5.718 (5.718) Accm: 3.58 (3.58) Acct: 5.89 (5.89) proj_loss: -0.6220 (-0.6220) time: 0.9240 data: 0.0003 [11-25 19:23:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.419 (6.419) Lt: 5.589 (5.589) Accm: 3.54 (3.54) Acct: 5.77 (5.77) proj_loss: -0.6122 (-0.6122) time: 0.9240 data: 0.0002 [11-25 19:23:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.633 (6.633) Lt: 5.938 (5.938) Accm: 2.87 (2.87) Acct: 4.29 (4.29) proj_loss: -0.6242 (-0.6242) time: 0.9241 data: 0.0003 [11-25 19:23:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.549 (6.549) Lt: 5.815 (5.815) Accm: 3.12 (3.12) Acct: 5.25 (5.25) proj_loss: -0.6183 (-0.6183) time: 0.9241 data: 0.0002 [11-25 19:23:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.323 (6.323) Lt: 5.520 (5.520) Accm: 3.77 (3.77) Acct: 5.79 (5.79) proj_loss: -0.6174 (-0.6174) time: 0.9241 data: 0.0003 [11-25 19:23:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.400 (6.400) Lt: 5.578 (5.578) Accm: 4.01 (4.01) Acct: 6.42 (6.42) proj_loss: -0.5997 (-0.5997) time: 0.9241 data: 0.0003 [11-25 19:23:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.507 (6.507) Lt: 5.747 (5.747) Accm: 3.22 (3.22) Acct: 4.80 (4.80) proj_loss: -0.6224 (-0.6224) time: 0.9241 data: 0.0003 [11-25 19:23:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 417/1669] eta: 0:19:16 tlr: 0.00016 tnm: 0.24 Lm: 6.304 (6.304) Lt: 5.623 (5.623) Accm: 3.99 (3.99) Acct: 5.84 (5.84) proj_loss: -0.6004 (-0.6004) time: 0.9241 data: 0.0003 [11-25 19:30:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.518 (6.418) Lt: 5.817 (5.694) Accm: 3.35 (3.75) Acct: 5.27 (5.65) proj_loss: -0.5915 (-0.5877) time: 0.9245 data: 0.0003 [11-25 19:30:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.485 (6.436) Lt: 5.679 (5.621) Accm: 3.67 (3.72) Acct: 6.06 (5.89) proj_loss: -0.6071 (-0.6158) time: 0.9245 data: 0.0003 [11-25 19:30:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.503 (6.475) Lt: 5.819 (5.751) Accm: 3.58 (3.47) Acct: 5.58 (5.61) proj_loss: -0.6035 (-0.6158) time: 0.9245 data: 0.0003 [11-25 19:30:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.485 (6.463) Lt: 5.717 (5.692) Accm: 3.28 (3.54) Acct: 4.82 (5.41) proj_loss: -0.6133 (-0.6133) time: 0.9245 data: 0.0002 [11-25 19:30:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.368 (6.405) Lt: 5.630 (5.635) Accm: 3.53 (3.50) Acct: 5.44 (5.35) proj_loss: -0.6341 (-0.6230) time: 0.9245 data: 0.0002 [11-25 19:30:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.481 (6.486) Lt: 5.679 (5.698) Accm: 3.41 (3.32) Acct: 5.44 (5.14) proj_loss: -0.6135 (-0.6129) time: 0.9245 data: 0.0003 [11-25 19:30:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.576 (6.558) Lt: 5.892 (5.841) Accm: 2.93 (3.05) Acct: 4.82 (5.11) proj_loss: -0.6152 (-0.6173) time: 0.9245 data: 0.0003 [11-25 19:30:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [ 834/1669] eta: 0:12:51 tlr: 0.00016 tnm: 0.25 Lm: 6.625 (6.545) Lt: 5.930 (5.808) Accm: 2.91 (3.20) Acct: 4.37 (4.95) proj_loss: -0.6236 (-0.6217) time: 0.9245 data: 0.0003 [11-25 19:36:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.24 Lm: 6.550 (6.528) Lt: 5.855 (5.801) Accm: 3.18 (3.26) Acct: 4.94 (5.09) proj_loss: -0.6201 (-0.6182) time: 0.9257 data: 0.0003 [11-25 19:36:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.24 Lm: 6.500 (6.476) Lt: 5.731 (5.705) Accm: 3.33 (3.50) Acct: 4.94 (5.32) proj_loss: -0.6180 (-0.6157) time: 0.9258 data: 0.0002 [11-25 19:36:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.24 Lm: 6.454 (6.411) Lt: 5.705 (5.669) Accm: 3.50 (3.73) Acct: 5.63 (5.73) proj_loss: -0.6004 (-0.5952) time: 0.9257 data: 0.0003 [11-25 19:36:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.24 Lm: 6.521 (6.501) Lt: 5.801 (5.759) Accm: 3.53 (3.47) Acct: 5.63 (5.63) proj_loss: -0.6047 (-0.6133) time: 0.9258 data: 0.0003 [11-25 19:36:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.24 Lm: 6.551 (6.521) Lt: 5.797 (5.753) Accm: 3.20 (3.24) Acct: 5.10 (5.04) proj_loss: -0.6139 (-0.6175) time: 0.9257 data: 0.0002 [11-25 19:36:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.24 Lm: 6.323 (6.365) Lt: 5.543 (5.590) Accm: 3.74 (3.61) Acct: 5.77 (5.54) proj_loss: -0.6330 (-0.6252) time: 0.9258 data: 0.0003 [11-25 19:36:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.24 Lm: 6.493 (6.521) Lt: 5.828 (5.822) Accm: 3.24 (3.20) Acct: 5.01 (5.13) proj_loss: -0.6187 (-0.6220) time: 0.9257 data: 0.0002 [11-25 19:36:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [1251/1669] eta: 0:06:26 tlr: 0.00016 tnm: 0.24 Lm: 6.474 (6.443) Lt: 5.694 (5.650) Accm: 3.57 (3.66) Acct: 5.49 (5.65) proj_loss: -0.6186 (-0.6193) time: 0.9257 data: 0.0003 [11-25 19:43:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.26 Lm: 6.464 (6.426) Lt: 5.679 (5.647) Accm: 3.60 (3.65) Acct: 4.99 (5.52) proj_loss: -0.6121 (-0.6179) time: 0.9262 data: 0.0015 [11-25 19:43:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 139/350] Total time: 0:25:41 (0.924 s / it) [11-25 19:43:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.26 Lm: 6.503 (6.493) Lt: 5.784 (5.740) Accm: 3.58 (3.51) Acct: 5.58 (5.61) proj_loss: -0.6035 (-0.6082) time: 0.9262 data: 0.0015 [11-25 19:43:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.26 Lm: 6.487 (6.515) Lt: 5.735 (5.749) Accm: 3.25 (3.24) Acct: 5.44 (5.12) proj_loss: -0.6144 (-0.6219) time: 0.9262 data: 0.0015 [11-25 19:43:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.26 Lm: 6.368 (6.379) Lt: 5.630 (5.605) Accm: 3.95 (3.68) Acct: 5.96 (5.62) proj_loss: -0.6319 (-0.6206) time: 0.9262 data: 0.0014 [11-25 19:43:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.26 Lm: 6.516 (6.511) Lt: 5.746 (5.746) Accm: 3.28 (3.44) Acct: 4.82 (5.22) proj_loss: -0.6216 (-0.6168) time: 0.9262 data: 0.0020 [11-25 19:43:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.26 Lm: 6.410 (6.495) Lt: 5.763 (5.773) Accm: 3.55 (3.37) Acct: 5.20 (5.50) proj_loss: -0.6152 (-0.6178) time: 0.9262 data: 0.0019 [11-25 19:43:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.26 Lm: 6.475 (6.487) Lt: 5.779 (5.747) Accm: 3.44 (3.42) Acct: 5.51 (5.30) proj_loss: -0.6167 (-0.6167) time: 0.9262 data: 0.0015 [11-25 19:43:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 139/350] [1668/1669] eta: 0:00:00 tlr: 0.00016 tnm: 0.26 Lm: 6.391 (6.390) Lt: 5.594 (5.628) Accm: 3.66 (3.79) Acct: 5.99 (5.79) proj_loss: -0.6092 (-0.6012) time: 0.9262 data: 0.0017 [11-25 19:43:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 139/350] Total time: 0:25:41 (0.924 s / it) [11-25 19:43:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 139/350] Total time: 0:25:41 (0.924 s / it) [11-25 19:43:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 139/350] Total time: 0:25:41 (0.924 s / it) [11-25 19:43:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 139/350] Total time: 0:25:41 (0.924 s / it) [11-25 19:43:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 139/350] Total time: 0:25:41 (0.924 s / it) [11-25 19:43:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 139/350] Total time: 0:25:41 (0.924 s / it) [11-25 19:43:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 139/350] Total time: 0:25:41 (0.924 s / it) [11-25 19:47:37] (home/user/VAR/trainer.py, line 114)=> FID: 3.533165835590694 [11-25 19:47:39] (/home/user/VAR/train.py , line 259)=> [*] [ep139] (val 50000) Lm: 6.4465, Lt: 5.6889, Acc m&t: 3.53 5.52, Val cost: 266.75s [11-25 19:47:39] (/home/user/VAR/train.py , line 264)=> [saving ckpt] ... [saving ckpt](*) finished! @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth [11-25 19:48:56] (/home/user/VAR/train.py , line 276)=> [ep139] (training ) Lm: 6.446 (6.447), Lt: 5.689 (5.689), Acc m&t: 3.55 5.55, Remain: 3 days, 18:51:01, Finish: 2024-11-28 22:34 [11-25 19:48:56] (/home/user/VAR/train.py , line 276)=> [ep139] (training ) Lm: 6.446 (6.447), Lt: 5.689 (5.689), Acc m&t: 3.55 5.55, Remain: 3 days, 18:52:36, Finish: 2024-11-28 22:35 [11-25 19:48:56] (/home/user/VAR/train.py , line 276)=> [ep139] (training ) Lm: 6.446 (6.447), Lt: 5.689 (5.689), Acc m&t: 3.55 5.55, Remain: 3 days, 18:52:49, Finish: 2024-11-28 22:36 [11-25 19:48:56] (/home/user/VAR/train.py , line 276)=> [ep139] (training ) Lm: 6.446 (6.447), Lt: 5.689 (5.689), Acc m&t: 3.55 5.55, Remain: 3 days, 18:51:24, Finish: 2024-11-28 22:34 [11-25 19:48:56] (/home/user/VAR/train.py , line 276)=> [ep139] (training ) Lm: 6.446 (6.447), Lt: 5.689 (5.689), Acc m&t: 3.55 5.55, Remain: 3 days, 18:53:12, Finish: 2024-11-28 22:36 [11-25 19:48:56] (/home/user/VAR/train.py , line 276)=> [ep139] (training ) Lm: 6.446 (6.447), Lt: 5.689 (5.689), Acc m&t: 3.55 5.55, Remain: 3 days, 18:52:30, Finish: 2024-11-28 22:35 [11-25 19:48:56] (/home/user/VAR/train.py , line 276)=> [ep139] (training ) Lm: 6.446 (6.447), Lt: 5.689 (5.689), Acc m&t: 3.55 5.55, Remain: 3 days, 18:55:05, Finish: 2024-11-28 22:38 [11-25 19:48:56] (/home/user/VAR/train.py , line 276)=> [ep139] (training ) Lm: 6.446 (6.447), Lt: 5.689 (5.689), Acc m&t: 3.55 5.55, Remain: 3 days, 18:51:41, Finish: 2024-11-28 22:34 [11-25 19:48:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 0/1669] eta: 0:25:30 tlr: 0.00016 tnm: 0.25 Lm: 6.620 (6.620) Lt: 5.910 (5.910) Accm: 3.07 (3.07) Acct: 4.89 (4.89) proj_loss: -0.6348 (-0.6348) time: 0.9172 data: 0.0004 [11-25 19:48:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 0/1669] eta: 0:25:29 tlr: 0.00016 tnm: 0.25 Lm: 6.610 (6.610) Lt: 5.879 (5.879) Accm: 2.84 (2.84) Acct: 4.51 (4.51) proj_loss: -0.6155 (-0.6155) time: 0.9167 data: 0.0003 [11-25 19:48:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 0/1669] eta: 0:25:29 tlr: 0.00016 tnm: 0.25 Lm: 6.632 (6.632) Lt: 5.884 (5.884) Accm: 2.90 (2.90) Acct: 4.44 (4.44) proj_loss: -0.6014 (-0.6014) time: 0.9164 data: 0.0004 [11-25 19:48:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 0/1669] eta: 0:25:27 tlr: 0.00016 tnm: 0.25 Lm: 6.584 (6.584) Lt: 5.772 (5.772) Accm: 2.94 (2.94) Acct: 4.79 (4.79) proj_loss: -0.6074 (-0.6074) time: 0.9155 data: 0.0003 [11-25 19:48:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 0/1669] eta: 0:25:43 tlr: 0.00016 tnm: 0.25 Lm: 6.228 (6.228) Lt: 5.407 (5.407) Accm: 4.15 (4.15) Acct: 6.61 (6.61) proj_loss: -0.6279 (-0.6279) time: 0.9246 data: 0.0004 [11-25 19:48:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 0/1669] eta: 0:26:25 tlr: 0.00016 tnm: 0.25 Lm: 6.318 (6.318) Lt: 5.559 (5.559) Accm: 3.88 (3.88) Acct: 5.92 (5.92) proj_loss: -0.6110 (-0.6110) time: 0.9501 data: 0.0004 [11-25 19:48:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 0/1669] eta: 0:25:29 tlr: 0.00016 tnm: 0.25 Lm: 6.636 (6.636) Lt: 5.913 (5.913) Accm: 2.75 (2.75) Acct: 4.24 (4.24) proj_loss: -0.5992 (-0.5992) time: 0.9166 data: 0.0004 [11-25 19:48:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 0/1669] eta: 0:25:31 tlr: 0.00016 tnm: 0.25 Lm: 6.211 (6.211) Lt: 5.329 (5.329) Accm: 4.79 (4.79) Acct: 7.54 (7.54) proj_loss: -0.6165 (-0.6165) time: 0.9174 data: 0.0004 [11-25 19:55:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 417/1669] eta: 0:19:17 tlr: 0.00016 tnm: 0.24 Lm: 6.316 (6.316) Lt: 5.492 (5.492) Accm: 4.26 (4.26) Acct: 6.58 (6.58) proj_loss: -0.5980 (-0.5980) time: 0.9255 data: 0.0002 [11-25 19:55:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 417/1669] eta: 0:19:17 tlr: 0.00016 tnm: 0.24 Lm: 6.507 (6.507) Lt: 5.785 (5.785) Accm: 3.10 (3.10) Acct: 4.65 (4.65) proj_loss: -0.6155 (-0.6155) time: 0.9255 data: 0.0003 [11-25 19:55:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 417/1669] eta: 0:19:17 tlr: 0.00016 tnm: 0.24 Lm: 6.563 (6.563) Lt: 5.841 (5.841) Accm: 3.04 (3.04) Acct: 4.60 (4.60) proj_loss: -0.6141 (-0.6141) time: 0.9255 data: 0.0002 [11-25 19:55:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 417/1669] eta: 0:19:17 tlr: 0.00016 tnm: 0.24 Lm: 6.579 (6.579) Lt: 5.851 (5.851) Accm: 2.93 (2.93) Acct: 4.65 (4.65) proj_loss: -0.6394 (-0.6394) time: 0.9256 data: 0.0003 [11-25 19:55:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 417/1669] eta: 0:19:17 tlr: 0.00016 tnm: 0.24 Lm: 6.379 (6.379) Lt: 5.643 (5.643) Accm: 3.74 (3.74) Acct: 5.85 (5.85) proj_loss: -0.6011 (-0.6011) time: 0.9255 data: 0.0003 [11-25 19:55:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 417/1669] eta: 0:19:17 tlr: 0.00016 tnm: 0.24 Lm: 6.422 (6.422) Lt: 5.648 (5.648) Accm: 3.52 (3.52) Acct: 5.39 (5.39) proj_loss: -0.6067 (-0.6067) time: 0.9256 data: 0.0002 [11-25 19:55:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 417/1669] eta: 0:19:17 tlr: 0.00016 tnm: 0.24 Lm: 6.334 (6.334) Lt: 5.537 (5.537) Accm: 3.93 (3.93) Acct: 6.11 (6.11) proj_loss: -0.6125 (-0.6125) time: 0.9256 data: 0.0002 [11-25 19:55:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 417/1669] eta: 0:19:17 tlr: 0.00016 tnm: 0.24 Lm: 6.587 (6.587) Lt: 5.880 (5.880) Accm: 3.23 (3.23) Acct: 5.03 (5.03) proj_loss: -0.6331 (-0.6331) time: 0.9256 data: 0.0003 [11-25 20:01:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 834/1669] eta: 0:12:52 tlr: 0.00016 tnm: 0.25 Lm: 6.553 (6.552) Lt: 5.850 (5.836) Accm: 3.38 (3.31) Acct: 5.17 (5.21) proj_loss: -0.6314 (-0.6241) time: 0.9265 data: 0.0003 [11-25 20:01:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 834/1669] eta: 0:12:52 tlr: 0.00016 tnm: 0.25 Lm: 6.421 (6.405) Lt: 5.655 (5.602) Accm: 3.73 (4.03) Acct: 5.61 (6.22) proj_loss: -0.6165 (-0.6161) time: 0.9265 data: 0.0002 [11-25 20:01:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 834/1669] eta: 0:12:52 tlr: 0.00016 tnm: 0.25 Lm: 6.495 (6.534) Lt: 5.809 (5.830) Accm: 3.15 (3.08) Acct: 4.75 (4.66) proj_loss: -0.6267 (-0.6202) time: 0.9265 data: 0.0002 [11-25 20:01:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 834/1669] eta: 0:12:52 tlr: 0.00016 tnm: 0.25 Lm: 6.556 (6.408) Lt: 5.772 (5.632) Accm: 3.18 (3.68) Acct: 4.79 (5.62) proj_loss: -0.6074 (-0.6088) time: 0.9265 data: 0.0003 [11-25 20:01:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 834/1669] eta: 0:12:52 tlr: 0.00016 tnm: 0.25 Lm: 6.530 (6.438) Lt: 5.813 (5.700) Accm: 3.34 (3.59) Acct: 5.10 (5.60) proj_loss: -0.5819 (-0.5947) time: 0.9265 data: 0.0003 [11-25 20:01:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 834/1669] eta: 0:12:52 tlr: 0.00016 tnm: 0.25 Lm: 6.501 (6.448) Lt: 5.737 (5.683) Accm: 3.67 (3.57) Acct: 5.75 (5.51) proj_loss: -0.6110 (-0.6120) time: 0.9265 data: 0.0002 [11-25 20:01:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 834/1669] eta: 0:12:52 tlr: 0.00016 tnm: 0.25 Lm: 6.378 (6.457) Lt: 5.658 (5.711) Accm: 3.45 (3.30) Acct: 5.06 (5.12) proj_loss: -0.6319 (-0.6220) time: 0.9264 data: 0.0003 [11-25 20:01:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [ 834/1669] eta: 0:12:52 tlr: 0.00016 tnm: 0.25 Lm: 6.549 (6.555) Lt: 5.824 (5.816) Accm: 3.02 (3.05) Acct: 4.79 (4.83) proj_loss: -0.6155 (-0.6276) time: 0.9265 data: 0.0003 [11-25 20:08:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.24 Lm: 6.528 (6.495) Lt: 5.785 (5.739) Accm: 3.15 (3.20) Acct: 4.99 (4.99) proj_loss: -0.6144 (-0.6240) time: 0.9248 data: 0.0003 [11-25 20:08:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.24 Lm: 6.518 (6.520) Lt: 5.799 (5.803) Accm: 3.32 (3.30) Acct: 5.03 (5.13) proj_loss: -0.6187 (-0.6156) time: 0.9248 data: 0.0003 [11-25 20:08:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.24 Lm: 6.485 (6.478) Lt: 5.803 (5.753) Accm: 3.17 (3.30) Acct: 4.77 (5.07) proj_loss: -0.6173 (-0.6171) time: 0.9248 data: 0.0002 [11-25 20:08:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.24 Lm: 6.410 (6.411) Lt: 5.685 (5.671) Accm: 3.77 (3.66) Acct: 5.56 (5.48) proj_loss: -0.6143 (-0.6134) time: 0.9248 data: 0.0002 [11-25 20:08:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.24 Lm: 6.380 (6.389) Lt: 5.644 (5.610) Accm: 3.65 (3.89) Acct: 5.56 (5.97) proj_loss: -0.6248 (-0.6203) time: 0.9248 data: 0.0002 [11-25 20:08:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.24 Lm: 6.393 (6.444) Lt: 5.643 (5.690) Accm: 3.57 (3.41) Acct: 5.56 (5.35) proj_loss: -0.6155 (-0.6115) time: 0.9248 data: 0.0003 [11-25 20:08:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.24 Lm: 6.464 (6.428) Lt: 5.737 (5.690) Accm: 3.48 (3.60) Acct: 5.11 (5.48) proj_loss: -0.6045 (-0.6028) time: 0.9248 data: 0.0003 [11-25 20:08:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.24 Lm: 6.494 (6.414) Lt: 5.713 (5.637) Accm: 3.45 (3.69) Acct: 5.30 (5.67) proj_loss: -0.6115 (-0.6105) time: 0.9248 data: 0.0003 [11-25 20:14:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.556 (6.453) Lt: 5.772 (5.682) Accm: 3.19 (3.59) Acct: 5.10 (5.56) proj_loss: -0.6155 (-0.6115) time: 0.9274 data: 0.0016 [11-25 20:14:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.408 (6.465) Lt: 5.658 (5.710) Accm: 3.45 (3.40) Acct: 5.44 (5.37) proj_loss: -0.6044 (-0.6100) time: 0.9273 data: 0.0019 [11-25 20:14:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.421 (6.428) Lt: 5.655 (5.650) Accm: 3.57 (3.69) Acct: 5.51 (5.73) proj_loss: -0.6165 (-0.6166) time: 0.9274 data: 0.0016 [11-25 20:14:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.549 (6.524) Lt: 5.824 (5.781) Accm: 3.02 (3.07) Acct: 4.79 (4.76) proj_loss: -0.6133 (-0.6209) time: 0.9274 data: 0.0016 [11-25 20:14:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.553 (6.528) Lt: 5.786 (5.800) Accm: 3.38 (3.32) Acct: 5.13 (5.13) proj_loss: -0.6188 (-0.6162) time: 0.9274 data: 0.0015 [11-25 20:14:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.501 (6.455) Lt: 5.737 (5.723) Accm: 3.67 (3.51) Acct: 5.37 (5.31) proj_loss: -0.6177 (-0.6189) time: 0.9274 data: 0.0017 [11-25 20:14:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.475 (6.450) Lt: 5.797 (5.717) Accm: 3.19 (3.33) Acct: 4.79 (5.16) proj_loss: -0.6216 (-0.6180) time: 0.9274 data: 0.0018 [11-25 20:14:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 140/350] Total time: 0:25:43 (0.925 s / it) [11-25 20:14:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 140/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.473 (6.437) Lt: 5.731 (5.698) Accm: 3.44 (3.57) Acct: 5.10 (5.37) proj_loss: -0.5857 (-0.5994) time: 0.9274 data: 0.0019 [11-25 20:14:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 140/350] Total time: 0:25:43 (0.925 s / it) [11-25 20:14:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 140/350] Total time: 0:25:43 (0.925 s / it) [11-25 20:14:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 140/350] Total time: 0:25:43 (0.925 s / it) [11-25 20:14:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 140/350] Total time: 0:25:43 (0.925 s / it) [11-25 20:14:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 140/350] Total time: 0:25:43 (0.925 s / it) [11-25 20:14:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 140/350] Total time: 0:25:43 (0.925 s / it) [11-25 20:14:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 140/350] Total time: 0:25:43 (0.925 s / it) [11-25 20:14:40] (/home/user/VAR/train.py , line 276)=> [ep140] (training ) Lm: 6.446 (6.467), Lt: 5.689 (5.716), Acc m&t: 3.55 5.55, Remain: 3 days, 18:37:19, Finish: 2024-11-28 22:51 [11-25 20:14:40] (/home/user/VAR/train.py , line 276)=> [ep140] (training ) Lm: 6.446 (6.467), Lt: 5.689 (5.716), Acc m&t: 3.55 5.55, Remain: 3 days, 18:38:17, Finish: 2024-11-28 22:52 [11-25 20:14:40] (/home/user/VAR/train.py , line 276)=> [ep140] (training ) Lm: 6.446 (6.467), Lt: 5.689 (5.716), Acc m&t: 3.55 5.55, Remain: 3 days, 18:38:07, Finish: 2024-11-28 22:52 [11-25 20:14:40] (/home/user/VAR/train.py , line 276)=> [ep140] (training ) Lm: 6.446 (6.467), Lt: 5.689 (5.716), Acc m&t: 3.55 5.55, Remain: 3 days, 18:38:13, Finish: 2024-11-28 22:52 [11-25 20:14:40] (/home/user/VAR/train.py , line 276)=> [ep140] (training ) Lm: 6.446 (6.467), Lt: 5.689 (5.716), Acc m&t: 3.55 5.55, Remain: 3 days, 18:37:02, Finish: 2024-11-28 22:51 [11-25 20:14:40] (/home/user/VAR/train.py , line 276)=> [ep140] (training ) Lm: 6.446 (6.467), Lt: 5.689 (5.716), Acc m&t: 3.55 5.55, Remain: 3 days, 18:37:39, Finish: 2024-11-28 22:52 [11-25 20:14:40] (/home/user/VAR/train.py , line 276)=> [ep140] (training ) Lm: 6.446 (6.467), Lt: 5.689 (5.716), Acc m&t: 3.55 5.55, Remain: 3 days, 18:37:33, Finish: 2024-11-28 22:52 [11-25 20:14:40] (/home/user/VAR/train.py , line 276)=> [ep140] (training ) Lm: 6.446 (6.467), Lt: 5.689 (5.716), Acc m&t: 3.55 5.55, Remain: 3 days, 18:37:24, Finish: 2024-11-28 22:52 [11-25 20:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 0/1669] eta: 0:24:37 tlr: 0.00015 tnm: 0.26 Lm: 6.282 (6.282) Lt: 5.515 (5.515) Accm: 3.55 (3.55) Acct: 5.30 (5.30) proj_loss: -0.6410 (-0.6410) time: 0.8852 data: 0.0003 [11-25 20:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 0/1669] eta: 0:24:38 tlr: 0.00015 tnm: 0.26 Lm: 6.391 (6.391) Lt: 5.640 (5.640) Accm: 3.29 (3.29) Acct: 4.86 (4.86) proj_loss: -0.6260 (-0.6260) time: 0.8858 data: 0.0004 [11-25 20:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 0/1669] eta: 0:24:38 tlr: 0.00015 tnm: 0.26 Lm: 6.408 (6.408) Lt: 5.663 (5.663) Accm: 3.37 (3.37) Acct: 5.23 (5.23) proj_loss: -0.6401 (-0.6401) time: 0.8859 data: 0.0003 [11-25 20:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 0/1669] eta: 0:24:37 tlr: 0.00015 tnm: 0.26 Lm: 6.486 (6.486) Lt: 5.804 (5.804) Accm: 3.19 (3.19) Acct: 5.03 (5.03) proj_loss: -0.5978 (-0.5978) time: 0.8855 data: 0.0004 [11-25 20:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 0/1669] eta: 0:24:38 tlr: 0.00015 tnm: 0.26 Lm: 6.674 (6.674) Lt: 5.913 (5.913) Accm: 2.81 (2.81) Acct: 4.37 (4.37) proj_loss: -0.6177 (-0.6177) time: 0.8860 data: 0.0004 [11-25 20:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 0/1669] eta: 0:24:38 tlr: 0.00015 tnm: 0.26 Lm: 6.524 (6.524) Lt: 5.774 (5.774) Accm: 3.44 (3.44) Acct: 5.44 (5.44) proj_loss: -0.6036 (-0.6036) time: 0.8861 data: 0.0003 [11-25 20:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 0/1669] eta: 0:25:45 tlr: 0.00015 tnm: 0.26 Lm: 6.057 (6.057) Lt: 5.351 (5.351) Accm: 5.42 (5.42) Acct: 7.95 (7.95) proj_loss: -0.6491 (-0.6491) time: 0.9263 data: 0.0003 [11-25 20:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 0/1669] eta: 0:24:45 tlr: 0.00015 tnm: 0.26 Lm: 6.603 (6.603) Lt: 5.845 (5.845) Accm: 2.90 (2.90) Acct: 4.55 (4.55) proj_loss: -0.5986 (-0.5986) time: 0.8899 data: 0.0005 [11-25 20:21:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 417/1669] eta: 0:19:23 tlr: 0.00015 tnm: 0.24 Lm: 6.588 (6.588) Lt: 5.852 (5.852) Accm: 2.83 (2.83) Acct: 4.49 (4.49) proj_loss: -0.6060 (-0.6060) time: 0.9904 data: 0.0003 [11-25 20:21:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 417/1669] eta: 0:19:23 tlr: 0.00015 tnm: 0.24 Lm: 6.405 (6.405) Lt: 5.690 (5.690) Accm: 3.72 (3.72) Acct: 5.53 (5.53) proj_loss: -0.6254 (-0.6254) time: 0.9904 data: 0.0002 [11-25 20:21:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 417/1669] eta: 0:19:23 tlr: 0.00015 tnm: 0.24 Lm: 6.532 (6.532) Lt: 5.731 (5.731) Accm: 3.22 (3.22) Acct: 5.11 (5.11) proj_loss: -0.6162 (-0.6162) time: 0.9904 data: 0.0003 [11-25 20:21:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 417/1669] eta: 0:19:23 tlr: 0.00015 tnm: 0.24 Lm: 6.394 (6.394) Lt: 5.657 (5.657) Accm: 3.70 (3.70) Acct: 5.63 (5.63) proj_loss: -0.6155 (-0.6155) time: 0.9904 data: 0.0003 [11-25 20:21:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 417/1669] eta: 0:19:23 tlr: 0.00015 tnm: 0.24 Lm: 6.506 (6.506) Lt: 5.781 (5.781) Accm: 3.24 (3.24) Acct: 5.27 (5.27) proj_loss: -0.6194 (-0.6194) time: 0.9904 data: 0.0002 [11-25 20:21:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 417/1669] eta: 0:19:23 tlr: 0.00015 tnm: 0.24 Lm: 6.218 (6.218) Lt: 5.473 (5.473) Accm: 4.55 (4.55) Acct: 6.87 (6.87) proj_loss: -0.6336 (-0.6336) time: 0.9904 data: 0.0003 [11-25 20:21:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 417/1669] eta: 0:19:23 tlr: 0.00015 tnm: 0.24 Lm: 6.446 (6.446) Lt: 5.732 (5.732) Accm: 3.20 (3.20) Acct: 4.84 (4.84) proj_loss: -0.6272 (-0.6272) time: 0.9904 data: 0.0003 [11-25 20:21:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 417/1669] eta: 0:19:23 tlr: 0.00015 tnm: 0.24 Lm: 6.447 (6.447) Lt: 5.664 (5.664) Accm: 3.25 (3.25) Acct: 5.11 (5.11) proj_loss: -0.6388 (-0.6388) time: 0.9904 data: 0.0002 [11-25 20:27:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 834/1669] eta: 0:13:07 tlr: 0.00015 tnm: 0.24 Lm: 6.439 (6.444) Lt: 5.578 (5.635) Accm: 3.45 (3.32) Acct: 5.30 (5.42) proj_loss: -0.6367 (-0.6269) time: 0.9240 data: 0.0002 [11-25 20:27:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 834/1669] eta: 0:13:07 tlr: 0.00015 tnm: 0.24 Lm: 6.408 (6.408) Lt: 5.650 (5.654) Accm: 3.37 (3.53) Acct: 5.23 (5.45) proj_loss: -0.6035 (-0.6115) time: 0.9240 data: 0.0003 [11-25 20:27:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 834/1669] eta: 0:13:07 tlr: 0.00015 tnm: 0.24 Lm: 6.511 (6.525) Lt: 5.705 (5.723) Accm: 2.94 (3.13) Acct: 4.79 (5.00) proj_loss: -0.6163 (-0.6163) time: 0.9240 data: 0.0002 [11-25 20:27:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 834/1669] eta: 0:13:07 tlr: 0.00015 tnm: 0.24 Lm: 6.502 (6.540) Lt: 5.824 (5.866) Accm: 3.10 (3.01) Acct: 4.82 (4.61) proj_loss: -0.6260 (-0.6150) time: 0.9240 data: 0.0003 [11-25 20:27:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 834/1669] eta: 0:13:07 tlr: 0.00015 tnm: 0.24 Lm: 6.428 (6.413) Lt: 5.611 (5.664) Accm: 3.44 (3.56) Acct: 5.44 (5.45) proj_loss: -0.6036 (-0.6149) time: 0.9240 data: 0.0002 [11-25 20:27:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 834/1669] eta: 0:13:07 tlr: 0.00015 tnm: 0.24 Lm: 6.379 (6.304) Lt: 5.595 (5.584) Accm: 3.67 (4.14) Acct: 5.79 (6.31) proj_loss: -0.6354 (-0.6342) time: 0.9240 data: 0.0003 [11-25 20:27:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 834/1669] eta: 0:13:07 tlr: 0.00015 tnm: 0.24 Lm: 6.486 (6.489) Lt: 5.758 (5.736) Accm: 3.19 (3.17) Acct: 5.03 (5.06) proj_loss: -0.6260 (-0.6216) time: 0.9240 data: 0.0003 [11-25 20:27:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [ 834/1669] eta: 0:13:07 tlr: 0.00015 tnm: 0.24 Lm: 6.603 (6.618) Lt: 5.859 (5.886) Accm: 2.90 (2.94) Acct: 4.55 (4.56) proj_loss: -0.6052 (-0.6057) time: 0.9240 data: 0.0003 [11-25 20:34:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [1251/1669] eta: 0:06:31 tlr: 0.00015 tnm: 0.24 Lm: 6.588 (6.565) Lt: 5.852 (5.820) Accm: 3.03 (3.08) Acct: 4.61 (4.86) proj_loss: -0.6093 (-0.6208) time: 0.9225 data: 0.0003 [11-25 20:34:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [1251/1669] eta: 0:06:31 tlr: 0.00015 tnm: 0.24 Lm: 6.462 (6.454) Lt: 5.658 (5.661) Accm: 3.32 (3.29) Acct: 5.17 (5.32) proj_loss: -0.6208 (-0.6214) time: 0.9225 data: 0.0002 [11-25 20:34:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [1251/1669] eta: 0:06:31 tlr: 0.00015 tnm: 0.24 Lm: 6.405 (6.405) Lt: 5.655 (5.672) Accm: 3.70 (3.66) Acct: 5.53 (5.51) proj_loss: -0.6150 (-0.6178) time: 0.9225 data: 0.0003 [11-25 20:34:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [1251/1669] eta: 0:06:31 tlr: 0.00015 tnm: 0.24 Lm: 6.370 (6.318) Lt: 5.553 (5.565) Accm: 3.87 (4.12) Acct: 6.15 (6.36) proj_loss: -0.6373 (-0.6354) time: 0.9225 data: 0.0003 [11-25 20:34:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [1251/1669] eta: 0:06:31 tlr: 0.00015 tnm: 0.24 Lm: 6.422 (6.425) Lt: 5.657 (5.690) Accm: 3.37 (3.49) Acct: 5.25 (5.41) proj_loss: -0.6139 (-0.6147) time: 0.9225 data: 0.0003 [11-25 20:34:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [1251/1669] eta: 0:06:31 tlr: 0.00015 tnm: 0.24 Lm: 6.446 (6.456) Lt: 5.732 (5.760) Accm: 3.20 (3.35) Acct: 4.84 (5.13) proj_loss: -0.6251 (-0.6173) time: 0.9225 data: 0.0002 [11-25 20:34:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [1251/1669] eta: 0:06:31 tlr: 0.00015 tnm: 0.24 Lm: 6.451 (6.460) Lt: 5.627 (5.670) Accm: 3.29 (3.34) Acct: 5.32 (5.34) proj_loss: -0.6170 (-0.6185) time: 0.9225 data: 0.0003 [11-25 20:34:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [1251/1669] eta: 0:06:31 tlr: 0.00015 tnm: 0.24 Lm: 6.487 (6.489) Lt: 5.781 (5.759) Accm: 3.22 (3.19) Acct: 5.20 (5.14) proj_loss: -0.6283 (-0.6238) time: 0.9225 data: 0.0003 [11-25 20:40:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.24 Lm: 6.489 (6.491) Lt: 5.758 (5.749) Accm: 3.22 (3.19) Acct: 5.10 (5.13) proj_loss: -0.6260 (-0.6189) time: 0.9248 data: 0.0017 [11-25 20:40:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 141/350] Total time: 0:25:58 (0.934 s / it) [11-25 20:40:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.24 Lm: 6.502 (6.473) Lt: 5.781 (5.764) Accm: 3.29 (3.39) Acct: 4.86 (5.28) proj_loss: -0.6242 (-0.6164) time: 0.9248 data: 0.0020 [11-25 20:40:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.24 Lm: 6.379 (6.384) Lt: 5.595 (5.643) Accm: 3.67 (3.88) Acct: 5.79 (5.98) proj_loss: -0.6354 (-0.6321) time: 0.9248 data: 0.0018 [11-25 20:40:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.24 Lm: 6.428 (6.435) Lt: 5.699 (5.718) Accm: 3.44 (3.54) Acct: 5.44 (5.34) proj_loss: -0.6180 (-0.6178) time: 0.9248 data: 0.0019 [11-25 20:40:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.24 Lm: 6.511 (6.500) Lt: 5.705 (5.720) Accm: 3.37 (3.34) Acct: 4.92 (5.25) proj_loss: -0.6163 (-0.6162) time: 0.9248 data: 0.0016 [11-25 20:40:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.24 Lm: 6.475 (6.458) Lt: 5.711 (5.671) Accm: 3.29 (3.29) Acct: 5.03 (5.21) proj_loss: -0.6050 (-0.6174) time: 0.9248 data: 0.0020 [11-25 20:40:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.24 Lm: 6.436 (6.434) Lt: 5.663 (5.692) Accm: 3.37 (3.47) Acct: 5.23 (5.31) proj_loss: -0.6035 (-0.6097) time: 0.9248 data: 0.0017 [11-25 20:40:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 141/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.24 Lm: 6.603 (6.578) Lt: 5.859 (5.835) Accm: 2.90 (3.04) Acct: 4.68 (4.84) proj_loss: -0.6052 (-0.6153) time: 0.9248 data: 0.0017 [11-25 20:40:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 141/350] Total time: 0:25:58 (0.934 s / it) [11-25 20:40:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 141/350] Total time: 0:25:58 (0.934 s / it) [11-25 20:40:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 141/350] Total time: 0:25:58 (0.934 s / it) [11-25 20:40:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 141/350] Total time: 0:25:58 (0.934 s / it) [11-25 20:40:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 141/350] Total time: 0:25:58 (0.934 s / it) [11-25 20:40:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 141/350] Total time: 0:25:58 (0.934 s / it) [11-25 20:40:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 141/350] Total time: 0:25:58 (0.934 s / it) [11-25 20:40:38] (/home/user/VAR/train.py , line 276)=> [ep141] (training ) Lm: 6.446 (6.457), Lt: 5.689 (5.706), Acc m&t: 3.55 5.55, Remain: 3 days, 17:53:41, Finish: 2024-11-28 22:34 [11-25 20:40:38] (/home/user/VAR/train.py , line 276)=> [ep141] (training ) Lm: 6.446 (6.457), Lt: 5.689 (5.706), Acc m&t: 3.55 5.55, Remain: 3 days, 17:54:05, Finish: 2024-11-28 22:34 [11-25 20:40:38] (/home/user/VAR/train.py , line 276)=> [ep141] (training ) Lm: 6.446 (6.457), Lt: 5.689 (5.706), Acc m&t: 3.55 5.55, Remain: 3 days, 17:53:51, Finish: 2024-11-28 22:34 [11-25 20:40:38] (/home/user/VAR/train.py , line 276)=> [ep141] (training ) Lm: 6.446 (6.457), Lt: 5.689 (5.706), Acc m&t: 3.55 5.55, Remain: 3 days, 17:53:11, Finish: 2024-11-28 22:33 [11-25 20:40:38] (/home/user/VAR/train.py , line 276)=> [ep141] (training ) Lm: 6.446 (6.457), Lt: 5.689 (5.706), Acc m&t: 3.55 5.55, Remain: 3 days, 17:54:04, Finish: 2024-11-28 22:34 [11-25 20:40:38] (/home/user/VAR/train.py , line 276)=> [ep141] (training ) Lm: 6.446 (6.457), Lt: 5.689 (5.706), Acc m&t: 3.55 5.55, Remain: 3 days, 17:53:23, Finish: 2024-11-28 22:34 [11-25 20:40:38] (/home/user/VAR/train.py , line 276)=> [ep141] (training ) Lm: 6.446 (6.457), Lt: 5.689 (5.706), Acc m&t: 3.55 5.55, Remain: 3 days, 17:54:03, Finish: 2024-11-28 22:34 [11-25 20:40:38] (/home/user/VAR/train.py , line 276)=> [ep141] (training ) Lm: 6.446 (6.457), Lt: 5.689 (5.706), Acc m&t: 3.55 5.55, Remain: 3 days, 17:53:53, Finish: 2024-11-28 22:34 [11-25 20:40:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 0/1669] eta: 0:25:19 tlr: 0.00015 tnm: 0.24 Lm: 6.367 (6.367) Lt: 5.637 (5.637) Accm: 3.64 (3.64) Acct: 5.72 (5.72) proj_loss: -0.6165 (-0.6165) time: 0.9105 data: 0.0003 [11-25 20:40:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 0/1669] eta: 0:25:21 tlr: 0.00015 tnm: 0.24 Lm: 6.642 (6.642) Lt: 5.901 (5.901) Accm: 2.81 (2.81) Acct: 4.41 (4.41) proj_loss: -0.6008 (-0.6008) time: 0.9113 data: 0.0004 [11-25 20:40:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 0/1669] eta: 0:25:26 tlr: 0.00015 tnm: 0.24 Lm: 6.416 (6.416) Lt: 5.597 (5.597) Accm: 3.45 (3.45) Acct: 5.48 (5.48) proj_loss: -0.6094 (-0.6094) time: 0.9149 data: 0.0003 [11-25 20:40:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 0/1669] eta: 0:25:21 tlr: 0.00015 tnm: 0.24 Lm: 6.448 (6.448) Lt: 5.715 (5.715) Accm: 3.50 (3.50) Acct: 5.03 (5.03) proj_loss: -0.6139 (-0.6139) time: 0.9118 data: 0.0004 [11-25 20:40:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 0/1669] eta: 0:25:21 tlr: 0.00015 tnm: 0.24 Lm: 6.725 (6.725) Lt: 6.058 (6.058) Accm: 2.97 (2.97) Acct: 4.55 (4.55) proj_loss: -0.6114 (-0.6114) time: 0.9118 data: 0.0004 [11-25 20:40:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 0/1669] eta: 0:25:20 tlr: 0.00015 tnm: 0.24 Lm: 6.527 (6.527) Lt: 5.749 (5.749) Accm: 3.48 (3.48) Acct: 5.51 (5.51) proj_loss: -0.5846 (-0.5846) time: 0.9111 data: 0.0004 [11-25 20:40:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 0/1669] eta: 0:25:21 tlr: 0.00015 tnm: 0.24 Lm: 6.440 (6.440) Lt: 5.648 (5.648) Accm: 3.77 (3.77) Acct: 5.72 (5.72) proj_loss: -0.5948 (-0.5948) time: 0.9115 data: 0.0004 [11-25 20:40:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 0/1669] eta: 0:25:20 tlr: 0.00015 tnm: 0.24 Lm: 6.394 (6.394) Lt: 5.718 (5.718) Accm: 3.34 (3.34) Acct: 5.58 (5.58) proj_loss: -0.6285 (-0.6285) time: 0.9112 data: 0.0003 [11-25 20:47:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.24 Lm: 6.436 (6.436) Lt: 5.702 (5.702) Accm: 3.47 (3.47) Acct: 5.77 (5.77) proj_loss: -0.6082 (-0.6082) time: 0.9241 data: 0.0002 [11-25 20:47:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.24 Lm: 6.401 (6.401) Lt: 5.604 (5.604) Accm: 3.61 (3.61) Acct: 5.49 (5.49) proj_loss: -0.6137 (-0.6137) time: 0.9241 data: 0.0002 [11-25 20:47:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.24 Lm: 6.306 (6.306) Lt: 5.584 (5.584) Accm: 3.86 (3.86) Acct: 6.04 (6.04) proj_loss: -0.6260 (-0.6260) time: 0.9241 data: 0.0003 [11-25 20:47:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.24 Lm: 6.625 (6.625) Lt: 5.865 (5.865) Accm: 2.88 (2.88) Acct: 4.65 (4.65) proj_loss: -0.5867 (-0.5867) time: 0.9241 data: 0.0003 [11-25 20:47:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.24 Lm: 6.434 (6.434) Lt: 5.654 (5.654) Accm: 3.51 (3.51) Acct: 5.63 (5.63) proj_loss: -0.6071 (-0.6071) time: 0.9241 data: 0.0003 [11-25 20:47:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.24 Lm: 6.588 (6.588) Lt: 5.886 (5.886) Accm: 3.28 (3.28) Acct: 5.13 (5.13) proj_loss: -0.6118 (-0.6118) time: 0.9241 data: 0.0002 [11-25 20:47:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.24 Lm: 6.420 (6.420) Lt: 5.637 (5.637) Accm: 3.77 (3.77) Acct: 5.58 (5.58) proj_loss: -0.6160 (-0.6160) time: 0.9241 data: 0.0003 [11-25 20:47:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.24 Lm: 6.534 (6.534) Lt: 5.754 (5.754) Accm: 3.32 (3.32) Acct: 5.32 (5.32) proj_loss: -0.5849 (-0.5849) time: 0.9241 data: 0.0003 [11-25 20:53:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.527 (6.479) Lt: 5.749 (5.682) Accm: 3.48 (3.38) Acct: 5.34 (5.33) proj_loss: -0.5852 (-0.5854) time: 0.9260 data: 0.0003 [11-25 20:53:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.418 (6.406) Lt: 5.700 (5.636) Accm: 3.50 (3.42) Acct: 5.03 (5.22) proj_loss: -0.6135 (-0.6085) time: 0.9260 data: 0.0002 [11-25 20:53:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.608 (6.521) Lt: 5.830 (5.740) Accm: 2.94 (3.30) Acct: 4.89 (5.20) proj_loss: -0.6008 (-0.5993) time: 0.9260 data: 0.0002 [11-25 20:53:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.505 (6.560) Lt: 5.749 (5.841) Accm: 3.58 (3.39) Acct: 5.58 (5.28) proj_loss: -0.6123 (-0.6123) time: 0.9260 data: 0.0002 [11-25 20:53:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.452 (6.449) Lt: 5.671 (5.660) Accm: 3.45 (3.47) Acct: 5.51 (5.59) proj_loss: -0.6094 (-0.6085) time: 0.9260 data: 0.0003 [11-25 20:53:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.367 (6.398) Lt: 5.637 (5.661) Accm: 3.64 (3.70) Acct: 5.72 (5.72) proj_loss: -0.6165 (-0.6173) time: 0.9260 data: 0.0002 [11-25 20:53:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.478 (6.461) Lt: 5.718 (5.741) Accm: 3.34 (3.39) Acct: 5.58 (5.50) proj_loss: -0.6145 (-0.6103) time: 0.9260 data: 0.0002 [11-25 20:53:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.400 (6.395) Lt: 5.626 (5.622) Accm: 3.77 (3.82) Acct: 5.72 (5.75) proj_loss: -0.6298 (-0.6206) time: 0.9260 data: 0.0003 [11-25 20:59:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.23 Lm: 6.420 (6.422) Lt: 5.637 (5.645) Accm: 3.77 (3.73) Acct: 5.65 (5.71) proj_loss: -0.6146 (-0.6153) time: 0.9258 data: 0.0003 [11-25 20:59:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.23 Lm: 6.307 (6.360) Lt: 5.584 (5.605) Accm: 3.86 (3.80) Acct: 6.01 (5.86) proj_loss: -0.6155 (-0.6166) time: 0.9258 data: 0.0003 [11-25 20:59:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.23 Lm: 6.407 (6.404) Lt: 5.645 (5.625) Accm: 3.61 (3.50) Acct: 5.29 (5.30) proj_loss: -0.6137 (-0.6150) time: 0.9259 data: 0.0002 [11-25 20:59:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.23 Lm: 6.465 (6.468) Lt: 5.692 (5.694) Accm: 3.42 (3.39) Acct: 5.49 (5.48) proj_loss: -0.6071 (-0.6062) time: 0.9259 data: 0.0003 [11-25 20:59:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.23 Lm: 6.478 (6.461) Lt: 5.732 (5.727) Accm: 3.60 (3.62) Acct: 5.65 (5.64) proj_loss: -0.6128 (-0.6143) time: 0.9259 data: 0.0002 [11-25 20:59:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.23 Lm: 6.534 (6.500) Lt: 5.754 (5.735) Accm: 3.42 (3.37) Acct: 5.23 (5.24) proj_loss: -0.5858 (-0.5925) time: 0.9258 data: 0.0003 [11-25 20:59:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.23 Lm: 6.450 (6.451) Lt: 5.702 (5.720) Accm: 3.47 (3.46) Acct: 5.77 (5.62) proj_loss: -0.6215 (-0.6215) time: 0.9258 data: 0.0003 [11-25 20:59:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.23 Lm: 6.578 (6.528) Lt: 5.801 (5.748) Accm: 3.23 (3.35) Acct: 5.46 (5.41) proj_loss: -0.6032 (-0.6009) time: 0.9259 data: 0.0002 [11-25 21:06:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.549 (6.527) Lt: 5.830 (5.772) Accm: 3.51 (3.40) Acct: 5.34 (5.39) proj_loss: -0.6057 (-0.6056) time: 0.9279 data: 0.0015 [11-25 21:06:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.478 (6.482) Lt: 5.718 (5.756) Accm: 3.34 (3.36) Acct: 5.58 (5.44) proj_loss: -0.6229 (-0.6218) time: 0.9278 data: 0.0016 [11-25 21:06:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 142/350] Total time: 0:25:44 (0.925 s / it) [11-25 21:06:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.440 (6.455) Lt: 5.648 (5.680) Accm: 3.76 (3.61) Acct: 5.58 (5.57) proj_loss: -0.6298 (-0.6209) time: 0.9278 data: 0.0015 [11-25 21:06:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.418 (6.417) Lt: 5.700 (5.643) Accm: 3.50 (3.48) Acct: 5.06 (5.25) proj_loss: -0.6139 (-0.6169) time: 0.9278 data: 0.0017 [11-25 21:06:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.505 (6.508) Lt: 5.749 (5.781) Accm: 3.58 (3.43) Acct: 5.58 (5.38) proj_loss: -0.6123 (-0.6072) time: 0.9278 data: 0.0020 [11-25 21:06:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.355 (6.359) Lt: 5.548 (5.593) Accm: 3.64 (3.76) Acct: 6.30 (5.96) proj_loss: -0.6144 (-0.6118) time: 0.9278 data: 0.0018 [11-25 21:06:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.452 (6.453) Lt: 5.671 (5.667) Accm: 3.45 (3.43) Acct: 5.51 (5.55) proj_loss: -0.6079 (-0.6065) time: 0.9279 data: 0.0018 [11-25 21:06:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 142/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.542 (6.510) Lt: 5.759 (5.742) Accm: 3.37 (3.35) Acct: 5.34 (5.29) proj_loss: -0.5864 (-0.5934) time: 0.9279 data: 0.0017 [11-25 21:06:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 142/350] Total time: 0:25:44 (0.925 s / it) [11-25 21:06:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 142/350] Total time: 0:25:44 (0.925 s / it) [11-25 21:06:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 142/350] Total time: 0:25:44 (0.925 s / it) [11-25 21:06:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 142/350] Total time: 0:25:44 (0.925 s / it) [11-25 21:06:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 142/350] Total time: 0:25:44 (0.925 s / it) [11-25 21:06:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 142/350] Total time: 0:25:44 (0.925 s / it) [11-25 21:06:22] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 142/350] Total time: 0:25:44 (0.925 s / it) [11-25 21:06:22] (/home/user/VAR/train.py , line 276)=> [ep142] (training ) Lm: 6.446 (6.459), Lt: 5.689 (5.700), Acc m&t: 3.55 5.55, Remain: 3 days, 17:39:41, Finish: 2024-11-28 22:46 [11-25 21:06:22] (/home/user/VAR/train.py , line 276)=> [ep142] (training ) Lm: 6.446 (6.459), Lt: 5.689 (5.700), Acc m&t: 3.55 5.55, Remain: 3 days, 17:39:07, Finish: 2024-11-28 22:45 [11-25 21:06:22] (/home/user/VAR/train.py , line 276)=> [ep142] (training ) Lm: 6.446 (6.459), Lt: 5.689 (5.700), Acc m&t: 3.55 5.55, Remain: 3 days, 17:39:14, Finish: 2024-11-28 22:45 [11-25 21:06:22] (/home/user/VAR/train.py , line 276)=> [ep142] (training ) Lm: 6.446 (6.459), Lt: 5.689 (5.700), Acc m&t: 3.55 5.55, Remain: 3 days, 17:40:01, Finish: 2024-11-28 22:46 [11-25 21:06:22] (/home/user/VAR/train.py , line 276)=> [ep142] (training ) Lm: 6.446 (6.459), Lt: 5.689 (5.700), Acc m&t: 3.55 5.55, Remain: 3 days, 17:40:10, Finish: 2024-11-28 22:46 [11-25 21:06:22] (/home/user/VAR/train.py , line 276)=> [ep142] (training ) Lm: 6.446 (6.459), Lt: 5.689 (5.700), Acc m&t: 3.55 5.55, Remain: 3 days, 17:39:59, Finish: 2024-11-28 22:46 [11-25 21:06:22] (/home/user/VAR/train.py , line 276)=> [ep142] (training ) Lm: 6.446 (6.459), Lt: 5.689 (5.700), Acc m&t: 3.55 5.55, Remain: 3 days, 17:39:42, Finish: 2024-11-28 22:46 [11-25 21:06:22] (/home/user/VAR/train.py , line 276)=> [ep142] (training ) Lm: 6.446 (6.459), Lt: 5.689 (5.700), Acc m&t: 3.55 5.55, Remain: 3 days, 17:38:25, Finish: 2024-11-28 22:44 [11-25 21:06:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 0/1669] eta: 0:25:20 tlr: 0.00015 tnm: 0.26 Lm: 6.496 (6.496) Lt: 5.790 (5.790) Accm: 3.42 (3.42) Acct: 5.68 (5.68) proj_loss: -0.6267 (-0.6267) time: 0.9113 data: 0.0003 [11-25 21:06:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 0/1669] eta: 0:25:20 tlr: 0.00015 tnm: 0.26 Lm: 6.731 (6.731) Lt: 6.084 (6.084) Accm: 2.59 (2.59) Acct: 3.93 (3.93) proj_loss: -0.6150 (-0.6150) time: 0.9112 data: 0.0004 [11-25 21:06:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 0/1669] eta: 0:25:20 tlr: 0.00015 tnm: 0.26 Lm: 6.586 (6.586) Lt: 5.822 (5.822) Accm: 3.12 (3.12) Acct: 5.10 (5.10) proj_loss: -0.5853 (-0.5853) time: 0.9113 data: 0.0003 [11-25 21:06:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 0/1669] eta: 0:25:21 tlr: 0.00015 tnm: 0.26 Lm: 6.492 (6.492) Lt: 5.684 (5.684) Accm: 2.86 (2.86) Acct: 4.61 (4.61) proj_loss: -0.6128 (-0.6128) time: 0.9116 data: 0.0003 [11-25 21:06:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 0/1669] eta: 0:25:21 tlr: 0.00015 tnm: 0.26 Lm: 6.706 (6.706) Lt: 6.088 (6.088) Accm: 2.55 (2.55) Acct: 3.93 (3.93) proj_loss: -0.6248 (-0.6248) time: 0.9116 data: 0.0004 [11-25 21:06:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 0/1669] eta: 0:25:21 tlr: 0.00015 tnm: 0.26 Lm: 6.593 (6.593) Lt: 5.734 (5.734) Accm: 3.21 (3.21) Acct: 5.30 (5.30) proj_loss: -0.5948 (-0.5948) time: 0.9118 data: 0.0004 [11-25 21:06:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 0/1669] eta: 0:25:21 tlr: 0.00015 tnm: 0.26 Lm: 6.678 (6.678) Lt: 5.968 (5.968) Accm: 3.22 (3.22) Acct: 4.68 (4.68) proj_loss: -0.6125 (-0.6125) time: 0.9119 data: 0.0003 [11-25 21:06:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 0/1669] eta: 0:25:22 tlr: 0.00015 tnm: 0.26 Lm: 6.424 (6.424) Lt: 5.616 (5.616) Accm: 3.38 (3.38) Acct: 5.54 (5.54) proj_loss: -0.6035 (-0.6035) time: 0.9119 data: 0.0003 [11-25 21:12:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 417/1669] eta: 0:19:49 tlr: 0.00015 tnm: 0.25 Lm: 6.387 (6.387) Lt: 5.597 (5.597) Accm: 3.74 (3.74) Acct: 5.96 (5.96) proj_loss: -0.6180 (-0.6180) time: 0.9290 data: 0.0003 [11-25 21:12:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 417/1669] eta: 0:19:49 tlr: 0.00015 tnm: 0.25 Lm: 6.540 (6.540) Lt: 5.741 (5.741) Accm: 3.13 (3.13) Acct: 5.10 (5.10) proj_loss: -0.6058 (-0.6058) time: 0.9290 data: 0.0003 [11-25 21:12:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 417/1669] eta: 0:19:49 tlr: 0.00015 tnm: 0.25 Lm: 6.462 (6.462) Lt: 5.735 (5.735) Accm: 3.58 (3.58) Acct: 5.61 (5.61) proj_loss: -0.6146 (-0.6146) time: 0.9290 data: 0.0003 [11-25 21:12:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 417/1669] eta: 0:19:49 tlr: 0.00015 tnm: 0.25 Lm: 6.667 (6.667) Lt: 5.882 (5.882) Accm: 2.78 (2.78) Acct: 4.53 (4.53) proj_loss: -0.5919 (-0.5919) time: 0.9290 data: 0.0002 [11-25 21:12:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 417/1669] eta: 0:19:49 tlr: 0.00015 tnm: 0.25 Lm: 6.618 (6.618) Lt: 5.944 (5.944) Accm: 2.82 (2.82) Acct: 4.58 (4.58) proj_loss: -0.6167 (-0.6167) time: 0.9290 data: 0.0003 [11-25 21:12:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 417/1669] eta: 0:19:49 tlr: 0.00015 tnm: 0.25 Lm: 6.415 (6.415) Lt: 5.741 (5.741) Accm: 3.55 (3.55) Acct: 5.53 (5.53) proj_loss: -0.6401 (-0.6401) time: 0.9290 data: 0.0002 [11-25 21:12:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 417/1669] eta: 0:19:49 tlr: 0.00015 tnm: 0.25 Lm: 6.493 (6.493) Lt: 5.650 (5.650) Accm: 3.48 (3.48) Acct: 5.65 (5.65) proj_loss: -0.6174 (-0.6174) time: 0.9290 data: 0.0003 [11-25 21:12:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 417/1669] eta: 0:19:49 tlr: 0.00015 tnm: 0.25 Lm: 6.431 (6.431) Lt: 5.679 (5.679) Accm: 3.80 (3.80) Acct: 5.89 (5.89) proj_loss: -0.6199 (-0.6199) time: 0.9290 data: 0.0003 [11-25 21:19:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 834/1669] eta: 0:13:02 tlr: 0.00015 tnm: 0.25 Lm: 6.530 (6.524) Lt: 5.800 (5.807) Accm: 3.09 (3.23) Acct: 5.23 (5.18) proj_loss: -0.6085 (-0.6105) time: 0.9254 data: 0.0003 [11-25 21:19:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 834/1669] eta: 0:13:02 tlr: 0.00015 tnm: 0.25 Lm: 6.492 (6.447) Lt: 5.684 (5.643) Accm: 3.39 (3.57) Acct: 5.58 (5.77) proj_loss: -0.6128 (-0.6158) time: 0.9254 data: 0.0002 [11-25 21:19:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 834/1669] eta: 0:13:02 tlr: 0.00015 tnm: 0.25 Lm: 6.424 (6.428) Lt: 5.616 (5.677) Accm: 3.42 (3.64) Acct: 5.54 (5.67) proj_loss: -0.6310 (-0.6223) time: 0.9254 data: 0.0003 [11-25 21:19:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 834/1669] eta: 0:13:02 tlr: 0.00015 tnm: 0.25 Lm: 6.250 (6.391) Lt: 5.470 (5.647) Accm: 3.72 (3.62) Acct: 5.99 (5.74) proj_loss: -0.6150 (-0.6269) time: 0.9254 data: 0.0002 [11-25 21:19:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 834/1669] eta: 0:13:02 tlr: 0.00015 tnm: 0.25 Lm: 6.586 (6.609) Lt: 5.822 (5.839) Accm: 3.12 (3.03) Acct: 5.10 (4.88) proj_loss: -0.5968 (-0.5935) time: 0.9254 data: 0.0002 [11-25 21:19:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 834/1669] eta: 0:13:02 tlr: 0.00015 tnm: 0.25 Lm: 6.496 (6.496) Lt: 5.790 (5.795) Accm: 3.42 (3.22) Acct: 5.37 (4.96) proj_loss: -0.6267 (-0.6278) time: 0.9254 data: 0.0002 [11-25 21:19:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 834/1669] eta: 0:13:02 tlr: 0.00015 tnm: 0.25 Lm: 6.512 (6.499) Lt: 5.734 (5.684) Accm: 3.21 (3.38) Acct: 5.30 (5.45) proj_loss: -0.6353 (-0.6234) time: 0.9254 data: 0.0003 [11-25 21:19:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [ 834/1669] eta: 0:13:02 tlr: 0.00015 tnm: 0.25 Lm: 6.517 (6.460) Lt: 5.700 (5.686) Accm: 3.22 (3.60) Acct: 4.72 (5.50) proj_loss: -0.6125 (-0.6149) time: 0.9254 data: 0.0003 [11-25 21:25:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [1251/1669] eta: 0:06:29 tlr: 0.00015 tnm: 0.25 Lm: 6.470 (6.450) Lt: 5.665 (5.672) Accm: 3.47 (3.63) Acct: 5.37 (5.63) proj_loss: -0.6086 (-0.6092) time: 0.9240 data: 0.0003 [11-25 21:25:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [1251/1669] eta: 0:06:29 tlr: 0.00015 tnm: 0.25 Lm: 6.602 (6.562) Lt: 5.902 (5.856) Accm: 3.07 (3.19) Acct: 4.94 (5.04) proj_loss: -0.6054 (-0.6084) time: 0.9239 data: 0.0002 [11-25 21:25:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [1251/1669] eta: 0:06:29 tlr: 0.00015 tnm: 0.25 Lm: 6.387 (6.405) Lt: 5.595 (5.608) Accm: 3.63 (3.65) Acct: 5.82 (5.85) proj_loss: -0.6116 (-0.6144) time: 0.9239 data: 0.0002 [11-25 21:25:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [1251/1669] eta: 0:06:29 tlr: 0.00015 tnm: 0.25 Lm: 6.351 (6.406) Lt: 5.588 (5.661) Accm: 3.66 (3.62) Acct: 5.79 (5.70) proj_loss: -0.6213 (-0.6271) time: 0.9239 data: 0.0003 [11-25 21:25:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [1251/1669] eta: 0:06:29 tlr: 0.00015 tnm: 0.25 Lm: 6.627 (6.623) Lt: 5.832 (5.840) Accm: 3.02 (3.00) Acct: 5.01 (4.89) proj_loss: -0.5925 (-0.5922) time: 0.9239 data: 0.0003 [11-25 21:25:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [1251/1669] eta: 0:06:29 tlr: 0.00015 tnm: 0.25 Lm: 6.577 (6.545) Lt: 5.846 (5.842) Accm: 3.06 (3.09) Acct: 4.80 (4.78) proj_loss: -0.6153 (-0.6218) time: 0.9240 data: 0.0002 [11-25 21:25:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [1251/1669] eta: 0:06:29 tlr: 0.00015 tnm: 0.25 Lm: 6.453 (6.467) Lt: 5.671 (5.665) Accm: 3.36 (3.41) Acct: 5.18 (5.33) proj_loss: -0.6151 (-0.6160) time: 0.9239 data: 0.0002 [11-25 21:25:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [1251/1669] eta: 0:06:29 tlr: 0.00015 tnm: 0.25 Lm: 6.397 (6.413) Lt: 5.633 (5.670) Accm: 3.48 (3.61) Acct: 5.48 (5.60) proj_loss: -0.6298 (-0.6239) time: 0.9240 data: 0.0003 [11-25 21:32:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.371 (6.349) Lt: 5.616 (5.585) Accm: 3.54 (3.85) Acct: 5.54 (5.95) proj_loss: -0.6286 (-0.6211) time: 0.9240 data: 0.0021 [11-25 21:32:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 143/350] Total time: 0:25:53 (0.931 s / it) [11-25 21:32:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.394 (6.438) Lt: 5.609 (5.639) Accm: 3.51 (3.51) Acct: 5.30 (5.54) proj_loss: -0.6233 (-0.6174) time: 0.9240 data: 0.0016 [11-25 21:32:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.496 (6.531) Lt: 5.790 (5.819) Accm: 3.42 (3.18) Acct: 5.30 (4.88) proj_loss: -0.6038 (-0.6173) time: 0.9240 data: 0.0019 [11-25 21:32:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.674 (6.589) Lt: 5.938 (5.873) Accm: 3.04 (3.11) Acct: 4.65 (4.95) proj_loss: -0.6085 (-0.6109) time: 0.9240 data: 0.0016 [11-25 21:32:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.422 (6.440) Lt: 5.630 (5.658) Accm: 3.72 (3.67) Acct: 5.99 (5.70) proj_loss: -0.6048 (-0.6079) time: 0.9240 data: 0.0015 [11-25 21:32:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.586 (6.577) Lt: 5.822 (5.769) Accm: 3.12 (3.15) Acct: 5.10 (5.08) proj_loss: -0.5968 (-0.6000) time: 0.9240 data: 0.0015 [11-25 21:32:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.404 (6.406) Lt: 5.635 (5.656) Accm: 3.61 (3.55) Acct: 5.58 (5.52) proj_loss: -0.6150 (-0.6237) time: 0.9240 data: 0.0017 [11-25 21:32:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 143/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.492 (6.492) Lt: 5.684 (5.731) Accm: 3.39 (3.39) Acct: 5.58 (5.37) proj_loss: -0.6128 (-0.6172) time: 0.9240 data: 0.0015 [11-25 21:32:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 143/350] Total time: 0:25:53 (0.931 s / it) [11-25 21:32:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 143/350] Total time: 0:25:53 (0.931 s / it) [11-25 21:32:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 143/350] Total time: 0:25:53 (0.931 s / it) [11-25 21:32:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 143/350] Total time: 0:25:53 (0.931 s / it) [11-25 21:32:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 143/350] Total time: 0:25:53 (0.931 s / it) [11-25 21:32:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 143/350] Total time: 0:25:53 (0.931 s / it) [11-25 21:32:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 143/350] Total time: 0:25:53 (0.931 s / it) [11-25 21:32:15] (/home/user/VAR/train.py , line 276)=> [ep143] (training ) Lm: 6.446 (6.464), Lt: 5.689 (5.711), Acc m&t: 3.55 5.55, Remain: 3 days, 16:50:18, Finish: 2024-11-28 22:22 [11-25 21:32:15] (/home/user/VAR/train.py , line 276)=> [ep143] (training ) Lm: 6.446 (6.464), Lt: 5.689 (5.711), Acc m&t: 3.55 5.55, Remain: 3 days, 16:49:15, Finish: 2024-11-28 22:21 [11-25 21:32:15] (/home/user/VAR/train.py , line 276)=> [ep143] (training ) Lm: 6.446 (6.464), Lt: 5.689 (5.711), Acc m&t: 3.55 5.55, Remain: 3 days, 16:50:43, Finish: 2024-11-28 22:22 [11-25 21:32:15] (/home/user/VAR/train.py , line 276)=> [ep143] (training ) Lm: 6.446 (6.464), Lt: 5.689 (5.711), Acc m&t: 3.55 5.55, Remain: 3 days, 16:49:48, Finish: 2024-11-28 22:22 [11-25 21:32:15] (/home/user/VAR/train.py , line 276)=> [ep143] (training ) Lm: 6.446 (6.464), Lt: 5.689 (5.711), Acc m&t: 3.55 5.55, Remain: 3 days, 16:49:23, Finish: 2024-11-28 22:21 [11-25 21:32:15] (/home/user/VAR/train.py , line 276)=> [ep143] (training ) Lm: 6.446 (6.464), Lt: 5.689 (5.711), Acc m&t: 3.55 5.55, Remain: 3 days, 16:49:17, Finish: 2024-11-28 22:21 [11-25 21:32:15] (/home/user/VAR/train.py , line 276)=> [ep143] (training ) Lm: 6.446 (6.464), Lt: 5.689 (5.711), Acc m&t: 3.55 5.55, Remain: 3 days, 16:48:48, Finish: 2024-11-28 22:21 [11-25 21:32:15] (/home/user/VAR/train.py , line 276)=> [ep143] (training ) Lm: 6.446 (6.464), Lt: 5.689 (5.711), Acc m&t: 3.55 5.55, Remain: 3 days, 16:48:39, Finish: 2024-11-28 22:20 [11-25 21:32:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 0/1669] eta: 0:24:47 tlr: 0.00015 tnm: 0.24 Lm: 6.422 (6.422) Lt: 5.654 (5.654) Accm: 3.77 (3.77) Acct: 6.34 (6.34) proj_loss: -0.6117 (-0.6117) time: 0.8913 data: 0.0004 [11-25 21:32:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 0/1669] eta: 0:24:47 tlr: 0.00015 tnm: 0.24 Lm: 6.338 (6.338) Lt: 5.549 (5.549) Accm: 3.38 (3.38) Acct: 5.34 (5.34) proj_loss: -0.6287 (-0.6287) time: 0.8914 data: 0.0003 [11-25 21:32:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 0/1669] eta: 0:24:48 tlr: 0.00015 tnm: 0.24 Lm: 6.611 (6.611) Lt: 5.862 (5.862) Accm: 3.37 (3.37) Acct: 5.75 (5.75) proj_loss: -0.6122 (-0.6122) time: 0.8917 data: 0.0004 [11-25 21:32:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 0/1669] eta: 0:24:48 tlr: 0.00015 tnm: 0.24 Lm: 6.638 (6.638) Lt: 5.861 (5.861) Accm: 2.59 (2.59) Acct: 4.20 (4.20) proj_loss: -0.6136 (-0.6136) time: 0.8916 data: 0.0005 [11-25 21:32:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 0/1669] eta: 0:24:48 tlr: 0.00015 tnm: 0.24 Lm: 6.587 (6.587) Lt: 5.928 (5.928) Accm: 2.90 (2.90) Acct: 4.86 (4.86) proj_loss: -0.6190 (-0.6190) time: 0.8916 data: 0.0004 [11-25 21:32:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 0/1669] eta: 0:24:48 tlr: 0.00015 tnm: 0.24 Lm: 6.393 (6.393) Lt: 5.654 (5.654) Accm: 3.32 (3.32) Acct: 5.10 (5.10) proj_loss: -0.6427 (-0.6427) time: 0.8919 data: 0.0004 [11-25 21:32:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 0/1669] eta: 0:24:48 tlr: 0.00015 tnm: 0.24 Lm: 6.380 (6.380) Lt: 5.613 (5.613) Accm: 3.98 (3.98) Acct: 5.92 (5.92) proj_loss: -0.6323 (-0.6323) time: 0.8917 data: 0.0003 [11-25 21:32:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 0/1669] eta: 0:24:48 tlr: 0.00015 tnm: 0.24 Lm: 6.380 (6.380) Lt: 5.604 (5.604) Accm: 3.54 (3.54) Acct: 5.30 (5.30) proj_loss: -0.6166 (-0.6166) time: 0.8920 data: 0.0004 [11-25 21:38:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.476 (6.476) Lt: 5.717 (5.717) Accm: 3.26 (3.26) Acct: 5.03 (5.03) proj_loss: -0.5917 (-0.5917) time: 0.9287 data: 0.0003 [11-25 21:38:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.443 (6.443) Lt: 5.682 (5.682) Accm: 3.63 (3.63) Acct: 5.89 (5.89) proj_loss: -0.6258 (-0.6258) time: 0.9287 data: 0.0002 [11-25 21:38:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.333 (6.333) Lt: 5.567 (5.567) Accm: 3.69 (3.69) Acct: 5.66 (5.66) proj_loss: -0.6360 (-0.6360) time: 0.9287 data: 0.0002 [11-25 21:38:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.491 (6.491) Lt: 5.746 (5.746) Accm: 3.21 (3.21) Acct: 5.01 (5.01) proj_loss: -0.6024 (-0.6024) time: 0.9287 data: 0.0003 [11-25 21:38:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.431 (6.431) Lt: 5.645 (5.645) Accm: 3.75 (3.75) Acct: 6.20 (6.20) proj_loss: -0.6107 (-0.6107) time: 0.9287 data: 0.0003 [11-25 21:38:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.619 (6.619) Lt: 5.892 (5.892) Accm: 3.04 (3.04) Acct: 5.10 (5.10) proj_loss: -0.6180 (-0.6180) time: 0.9287 data: 0.0003 [11-25 21:38:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.522 (6.522) Lt: 5.741 (5.741) Accm: 3.12 (3.12) Acct: 4.82 (4.82) proj_loss: -0.6041 (-0.6041) time: 0.9287 data: 0.0003 [11-25 21:38:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.354 (6.354) Lt: 5.603 (5.603) Accm: 3.95 (3.95) Acct: 6.03 (6.03) proj_loss: -0.6287 (-0.6287) time: 0.9287 data: 0.0003 [11-25 21:45:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 834/1669] eta: 0:13:17 tlr: 0.00015 tnm: 0.25 Lm: 6.380 (6.392) Lt: 5.613 (5.635) Accm: 3.92 (3.75) Acct: 5.92 (5.81) proj_loss: -0.6252 (-0.6171) time: 0.9239 data: 0.0003 [11-25 21:45:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 834/1669] eta: 0:13:17 tlr: 0.00015 tnm: 0.25 Lm: 6.407 (6.384) Lt: 5.621 (5.587) Accm: 3.64 (3.67) Acct: 5.44 (5.61) proj_loss: -0.6136 (-0.6086) time: 0.9239 data: 0.0002 [11-25 21:45:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 834/1669] eta: 0:13:17 tlr: 0.00015 tnm: 0.25 Lm: 6.611 (6.556) Lt: 5.862 (5.830) Accm: 3.37 (3.20) Acct: 5.34 (5.18) proj_loss: -0.6238 (-0.6230) time: 0.9239 data: 0.0003 [11-25 21:45:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 834/1669] eta: 0:13:17 tlr: 0.00015 tnm: 0.25 Lm: 6.422 (6.419) Lt: 5.654 (5.646) Accm: 3.60 (3.62) Acct: 5.82 (5.87) proj_loss: -0.6210 (-0.6242) time: 0.9239 data: 0.0002 [11-25 21:45:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 834/1669] eta: 0:13:17 tlr: 0.00015 tnm: 0.25 Lm: 6.458 (6.480) Lt: 5.678 (5.724) Accm: 3.25 (3.22) Acct: 5.10 (5.13) proj_loss: -0.5939 (-0.5996) time: 0.9239 data: 0.0002 [11-25 21:45:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 834/1669] eta: 0:13:17 tlr: 0.00015 tnm: 0.25 Lm: 6.380 (6.423) Lt: 5.604 (5.640) Accm: 3.54 (3.49) Acct: 5.30 (5.51) proj_loss: -0.6161 (-0.5998) time: 0.9239 data: 0.0003 [11-25 21:45:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 834/1669] eta: 0:13:17 tlr: 0.00015 tnm: 0.25 Lm: 6.338 (6.342) Lt: 5.549 (5.561) Accm: 3.86 (3.74) Acct: 5.99 (5.77) proj_loss: -0.6287 (-0.6283) time: 0.9239 data: 0.0002 [11-25 21:45:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [ 834/1669] eta: 0:13:17 tlr: 0.00015 tnm: 0.25 Lm: 6.275 (6.366) Lt: 5.521 (5.604) Accm: 4.11 (3.87) Acct: 6.51 (6.30) proj_loss: -0.6190 (-0.6227) time: 0.9239 data: 0.0003 [11-25 21:51:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [1251/1669] eta: 0:06:35 tlr: 0.00015 tnm: 0.24 Lm: 6.431 (6.424) Lt: 5.663 (5.654) Accm: 3.68 (3.72) Acct: 5.91 (6.05) proj_loss: -0.6107 (-0.6150) time: 0.9276 data: 0.0003 [11-25 21:51:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [1251/1669] eta: 0:06:35 tlr: 0.00015 tnm: 0.24 Lm: 6.425 (6.458) Lt: 5.666 (5.681) Accm: 3.29 (3.33) Acct: 5.23 (5.38) proj_loss: -0.5915 (-0.5970) time: 0.9276 data: 0.0002 [11-25 21:51:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [1251/1669] eta: 0:06:35 tlr: 0.00015 tnm: 0.24 Lm: 6.520 (6.446) Lt: 5.784 (5.689) Accm: 3.43 (3.54) Acct: 5.54 (5.72) proj_loss: -0.6180 (-0.6190) time: 0.9276 data: 0.0003 [11-25 21:51:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [1251/1669] eta: 0:06:35 tlr: 0.00015 tnm: 0.24 Lm: 6.354 (6.376) Lt: 5.624 (5.635) Accm: 3.92 (3.80) Acct: 6.03 (5.93) proj_loss: -0.6134 (-0.6132) time: 0.9276 data: 0.0003 [11-25 21:51:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [1251/1669] eta: 0:06:35 tlr: 0.00015 tnm: 0.24 Lm: 6.333 (6.335) Lt: 5.555 (5.561) Accm: 3.77 (3.73) Acct: 5.66 (5.66) proj_loss: -0.6222 (-0.6252) time: 0.9276 data: 0.0003 [11-25 21:51:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [1251/1669] eta: 0:06:35 tlr: 0.00015 tnm: 0.24 Lm: 6.396 (6.400) Lt: 5.639 (5.640) Accm: 3.69 (3.69) Acct: 5.79 (5.84) proj_loss: -0.6305 (-0.6285) time: 0.9276 data: 0.0002 [11-25 21:51:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [1251/1669] eta: 0:06:35 tlr: 0.00015 tnm: 0.24 Lm: 6.394 (6.419) Lt: 5.634 (5.646) Accm: 3.50 (3.49) Acct: 5.41 (5.51) proj_loss: -0.6119 (-0.6018) time: 0.9276 data: 0.0003 [11-25 21:51:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [1251/1669] eta: 0:06:35 tlr: 0.00015 tnm: 0.24 Lm: 6.522 (6.463) Lt: 5.741 (5.678) Accm: 3.34 (3.51) Acct: 5.17 (5.43) proj_loss: -0.6124 (-0.6093) time: 0.9277 data: 0.0003 [11-25 21:58:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.533 (6.477) Lt: 5.771 (5.697) Accm: 3.34 (3.47) Acct: 5.10 (5.37) proj_loss: -0.6111 (-0.6074) time: 0.9275 data: 0.0015 [11-25 21:58:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 144/350] Total time: 0:26:09 (0.940 s / it) [11-25 21:58:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.338 (6.341) Lt: 5.559 (5.560) Accm: 3.69 (3.72) Acct: 5.92 (5.72) proj_loss: -0.6287 (-0.6274) time: 0.9275 data: 0.0014 [11-25 21:58:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.611 (6.485) Lt: 5.862 (5.735) Accm: 3.37 (3.37) Acct: 5.34 (5.44) proj_loss: -0.6238 (-0.6224) time: 0.9276 data: 0.0016 [11-25 21:58:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.409 (6.428) Lt: 5.664 (5.650) Accm: 3.47 (3.48) Acct: 5.51 (5.52) proj_loss: -0.6161 (-0.6073) time: 0.9275 data: 0.0015 [11-25 21:58:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.333 (6.367) Lt: 5.613 (5.599) Accm: 3.92 (3.88) Acct: 6.13 (6.14) proj_loss: -0.6047 (-0.6115) time: 0.9276 data: 0.0018 [11-25 21:58:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.422 (6.421) Lt: 5.654 (5.667) Accm: 3.60 (3.65) Acct: 5.75 (5.67) proj_loss: -0.6237 (-0.6276) time: 0.9276 data: 0.0015 [11-25 21:58:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.379 (6.415) Lt: 5.552 (5.633) Accm: 3.74 (3.72) Acct: 5.99 (6.04) proj_loss: -0.6095 (-0.6139) time: 0.9275 data: 0.0015 [11-25 21:58:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 144/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.458 (6.504) Lt: 5.678 (5.732) Accm: 3.25 (3.25) Acct: 5.10 (5.19) proj_loss: -0.5892 (-0.5918) time: 0.9276 data: 0.0019 [11-25 21:58:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 144/350] Total time: 0:26:09 (0.940 s / it) [11-25 21:58:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 144/350] Total time: 0:26:09 (0.940 s / it) [11-25 21:58:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 144/350] Total time: 0:26:09 (0.940 s / it) [11-25 21:58:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 144/350] Total time: 0:26:09 (0.940 s / it) [11-25 21:58:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 144/350] Total time: 0:26:09 (0.940 s / it) [11-25 21:58:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 144/350] Total time: 0:26:09 (0.940 s / it) [11-25 21:58:24] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 144/350] Total time: 0:26:09 (0.940 s / it) [11-25 21:58:24] (/home/user/VAR/train.py , line 276)=> [ep144] (training ) Lm: 6.446 (6.451), Lt: 5.689 (5.696), Acc m&t: 3.55 5.55, Remain: 3 days, 16:47:18, Finish: 2024-11-28 22:45 [11-25 21:58:24] (/home/user/VAR/train.py , line 276)=> [ep144] (training ) Lm: 6.446 (6.451), Lt: 5.689 (5.696), Acc m&t: 3.55 5.55, Remain: 3 days, 16:47:43, Finish: 2024-11-28 22:46 [11-25 21:58:24] (/home/user/VAR/train.py , line 276)=> [ep144] (training ) Lm: 6.446 (6.451), Lt: 5.689 (5.696), Acc m&t: 3.55 5.55, Remain: 3 days, 16:46:56, Finish: 2024-11-28 22:45 [11-25 21:58:24] (/home/user/VAR/train.py , line 276)=> [ep144] (training ) Lm: 6.446 (6.451), Lt: 5.689 (5.696), Acc m&t: 3.55 5.55, Remain: 3 days, 16:46:55, Finish: 2024-11-28 22:45 [11-25 21:58:24] (/home/user/VAR/train.py , line 276)=> [ep144] (training ) Lm: 6.446 (6.451), Lt: 5.689 (5.696), Acc m&t: 3.55 5.55, Remain: 3 days, 16:47:08, Finish: 2024-11-28 22:45 [11-25 21:58:24] (/home/user/VAR/train.py , line 276)=> [ep144] (training ) Lm: 6.446 (6.451), Lt: 5.689 (5.696), Acc m&t: 3.55 5.55, Remain: 3 days, 16:48:16, Finish: 2024-11-28 22:46 [11-25 21:58:24] (/home/user/VAR/train.py , line 276)=> [ep144] (training ) Lm: 6.446 (6.451), Lt: 5.689 (5.696), Acc m&t: 3.55 5.55, Remain: 3 days, 16:47:46, Finish: 2024-11-28 22:46 [11-25 21:58:24] (/home/user/VAR/train.py , line 276)=> [ep144] (training ) Lm: 6.446 (6.451), Lt: 5.689 (5.696), Acc m&t: 3.55 5.55, Remain: 3 days, 16:47:41, Finish: 2024-11-28 22:46 [11-25 21:58:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 0/1669] eta: 0:25:11 tlr: 0.00015 tnm: 0.25 Lm: 6.472 (6.472) Lt: 5.681 (5.681) Accm: 3.88 (3.88) Acct: 6.34 (6.34) proj_loss: -0.6085 (-0.6085) time: 0.9056 data: 0.0003 [11-25 21:58:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 0/1669] eta: 0:25:11 tlr: 0.00015 tnm: 0.25 Lm: 6.453 (6.453) Lt: 5.715 (5.715) Accm: 3.69 (3.69) Acct: 6.03 (6.03) proj_loss: -0.6190 (-0.6190) time: 0.9059 data: 0.0003 [11-25 21:58:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 0/1669] eta: 0:25:12 tlr: 0.00015 tnm: 0.25 Lm: 6.411 (6.411) Lt: 5.673 (5.673) Accm: 3.12 (3.12) Acct: 4.99 (4.99) proj_loss: -0.6084 (-0.6084) time: 0.9062 data: 0.0004 [11-25 21:58:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 0/1669] eta: 0:25:10 tlr: 0.00015 tnm: 0.25 Lm: 6.208 (6.208) Lt: 5.398 (5.398) Accm: 3.89 (3.89) Acct: 5.99 (5.99) proj_loss: -0.6139 (-0.6139) time: 0.9053 data: 0.0003 [11-25 21:58:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 0/1669] eta: 0:25:12 tlr: 0.00015 tnm: 0.25 Lm: 6.322 (6.322) Lt: 5.463 (5.463) Accm: 3.54 (3.54) Acct: 5.58 (5.58) proj_loss: -0.6003 (-0.6003) time: 0.9064 data: 0.0003 [11-25 21:58:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 0/1669] eta: 0:25:12 tlr: 0.00015 tnm: 0.25 Lm: 6.580 (6.580) Lt: 5.812 (5.812) Accm: 2.72 (2.72) Acct: 4.34 (4.34) proj_loss: -0.6110 (-0.6110) time: 0.9064 data: 0.0004 [11-25 21:58:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 0/1669] eta: 0:25:13 tlr: 0.00015 tnm: 0.25 Lm: 6.517 (6.517) Lt: 5.722 (5.722) Accm: 3.25 (3.25) Acct: 5.65 (5.65) proj_loss: -0.6406 (-0.6406) time: 0.9066 data: 0.0003 [11-25 21:58:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 0/1669] eta: 0:25:12 tlr: 0.00015 tnm: 0.25 Lm: 6.764 (6.764) Lt: 6.116 (6.116) Accm: 2.56 (2.56) Acct: 4.10 (4.10) proj_loss: -0.6033 (-0.6033) time: 0.9065 data: 0.0004 [11-25 22:04:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.599 (6.599) Lt: 5.921 (5.921) Accm: 3.09 (3.09) Acct: 4.84 (4.84) proj_loss: -0.6035 (-0.6035) time: 0.9248 data: 0.0003 [11-25 22:04:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.489 (6.489) Lt: 5.744 (5.744) Accm: 3.76 (3.76) Acct: 5.92 (5.92) proj_loss: -0.6236 (-0.6236) time: 0.9248 data: 0.0002 [11-25 22:04:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.419 (6.419) Lt: 5.654 (5.654) Accm: 3.45 (3.45) Acct: 5.30 (5.30) proj_loss: -0.6169 (-0.6169) time: 0.9248 data: 0.0002 [11-25 22:04:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.562 (6.562) Lt: 5.797 (5.797) Accm: 2.82 (2.82) Acct: 4.30 (4.30) proj_loss: -0.6209 (-0.6209) time: 0.9248 data: 0.0003 [11-25 22:04:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.436 (6.436) Lt: 5.674 (5.674) Accm: 3.42 (3.42) Acct: 5.53 (5.53) proj_loss: -0.5968 (-0.5968) time: 0.9248 data: 0.0003 [11-25 22:04:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.312 (6.312) Lt: 5.500 (5.500) Accm: 3.68 (3.68) Acct: 5.61 (5.61) proj_loss: -0.6063 (-0.6063) time: 0.9248 data: 0.0003 [11-25 22:04:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.573 (6.573) Lt: 5.842 (5.842) Accm: 3.31 (3.31) Acct: 5.18 (5.18) proj_loss: -0.6080 (-0.6080) time: 0.9248 data: 0.0003 [11-25 22:04:51] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.510 (6.510) Lt: 5.759 (5.759) Accm: 3.33 (3.33) Acct: 5.42 (5.42) proj_loss: -0.6264 (-0.6264) time: 0.9248 data: 0.0003 [11-25 22:11:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.517 (6.514) Lt: 5.796 (5.776) Accm: 3.25 (3.25) Acct: 5.20 (5.19) proj_loss: -0.6298 (-0.6275) time: 0.9252 data: 0.0002 [11-25 22:11:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.322 (6.433) Lt: 5.537 (5.674) Accm: 3.54 (3.41) Acct: 5.58 (5.13) proj_loss: -0.6037 (-0.6054) time: 0.9252 data: 0.0003 [11-25 22:11:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.545 (6.502) Lt: 5.782 (5.741) Accm: 2.91 (3.03) Acct: 4.34 (4.67) proj_loss: -0.6110 (-0.6080) time: 0.9252 data: 0.0002 [11-25 22:11:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.452 (6.430) Lt: 5.626 (5.644) Accm: 3.69 (3.53) Acct: 5.99 (5.59) proj_loss: -0.6150 (-0.6163) time: 0.9252 data: 0.0002 [11-25 22:11:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.453 (6.469) Lt: 5.715 (5.698) Accm: 3.69 (3.55) Acct: 6.03 (5.59) proj_loss: -0.6190 (-0.6146) time: 0.9252 data: 0.0003 [11-25 22:11:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.472 (6.448) Lt: 5.681 (5.670) Accm: 3.86 (3.79) Acct: 6.34 (6.06) proj_loss: -0.6085 (-0.6148) time: 0.9252 data: 0.0002 [11-25 22:11:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.461 (6.501) Lt: 5.675 (5.749) Accm: 3.22 (3.36) Acct: 5.54 (5.53) proj_loss: -0.6084 (-0.6148) time: 0.9252 data: 0.0003 [11-25 22:11:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.537 (6.579) Lt: 5.771 (5.871) Accm: 3.12 (3.10) Acct: 4.75 (4.81) proj_loss: -0.6038 (-0.6086) time: 0.9252 data: 0.0003 [11-25 22:17:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.550 (6.575) Lt: 5.799 (5.860) Accm: 2.99 (3.04) Acct: 4.55 (4.69) proj_loss: -0.6100 (-0.6105) time: 0.9239 data: 0.0003 [11-25 22:17:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.463 (6.439) Lt: 5.705 (5.669) Accm: 3.18 (3.31) Acct: 4.87 (5.28) proj_loss: -0.6131 (-0.6098) time: 0.9238 data: 0.0002 [11-25 22:17:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.440 (6.481) Lt: 5.733 (5.760) Accm: 3.29 (3.36) Acct: 5.30 (5.41) proj_loss: -0.6163 (-0.6171) time: 0.9238 data: 0.0003 [11-25 22:17:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.419 (6.388) Lt: 5.601 (5.584) Accm: 3.87 (3.89) Acct: 6.34 (6.22) proj_loss: -0.6028 (-0.6078) time: 0.9239 data: 0.0002 [11-25 22:17:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.510 (6.497) Lt: 5.776 (5.770) Accm: 3.33 (3.31) Acct: 5.23 (5.21) proj_loss: -0.6233 (-0.6248) time: 0.9239 data: 0.0002 [11-25 22:17:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.330 (6.367) Lt: 5.512 (5.541) Accm: 3.79 (3.78) Acct: 6.08 (6.03) proj_loss: -0.6145 (-0.6137) time: 0.9238 data: 0.0002 [11-25 22:17:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.420 (6.448) Lt: 5.680 (5.684) Accm: 3.70 (3.59) Acct: 5.84 (5.60) proj_loss: -0.6206 (-0.6165) time: 0.9239 data: 0.0003 [11-25 22:17:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.441 (6.465) Lt: 5.699 (5.721) Accm: 3.42 (3.38) Acct: 5.44 (5.17) proj_loss: -0.6020 (-0.6035) time: 0.9239 data: 0.0003 [11-25 22:24:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.525 (6.477) Lt: 5.714 (5.719) Accm: 3.54 (3.44) Acct: 5.58 (5.41) proj_loss: -0.6037 (-0.6082) time: 0.9251 data: 0.0016 [11-25 22:24:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 145/350] Total time: 0:25:42 (0.924 s / it) [11-25 22:24:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.471 (6.404) Lt: 5.681 (5.616) Accm: 3.86 (3.78) Acct: 6.34 (5.95) proj_loss: -0.6085 (-0.6141) time: 0.9251 data: 0.0014 [11-25 22:24:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.461 (6.477) Lt: 5.725 (5.753) Accm: 3.34 (3.35) Acct: 5.23 (5.38) proj_loss: -0.6084 (-0.6143) time: 0.9251 data: 0.0015 [11-25 22:24:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.517 (6.535) Lt: 5.796 (5.809) Accm: 3.25 (3.19) Acct: 5.20 (5.02) proj_loss: -0.6249 (-0.6248) time: 0.9251 data: 0.0016 [11-25 22:24:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.541 (6.460) Lt: 5.772 (5.689) Accm: 3.42 (3.34) Acct: 5.03 (5.23) proj_loss: -0.6110 (-0.6100) time: 0.9251 data: 0.0015 [11-25 22:24:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.397 (6.438) Lt: 5.644 (5.667) Accm: 3.69 (3.51) Acct: 5.65 (5.43) proj_loss: -0.6190 (-0.6116) time: 0.9251 data: 0.0016 [11-25 22:24:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.394 (6.373) Lt: 5.616 (5.556) Accm: 3.69 (3.74) Acct: 5.99 (5.92) proj_loss: -0.6139 (-0.6118) time: 0.9251 data: 0.0017 [11-25 22:24:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 145/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.549 (6.569) Lt: 5.771 (5.836) Accm: 3.12 (3.11) Acct: 4.75 (4.86) proj_loss: -0.6038 (-0.6088) time: 0.9251 data: 0.0015 [11-25 22:24:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 145/350] Total time: 0:25:42 (0.924 s / it) [11-25 22:24:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 145/350] Total time: 0:25:42 (0.924 s / it) [11-25 22:24:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 145/350] Total time: 0:25:42 (0.924 s / it) [11-25 22:24:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 145/350] Total time: 0:25:42 (0.924 s / it) [11-25 22:24:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 145/350] Total time: 0:25:42 (0.924 s / it) [11-25 22:24:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 145/350] Total time: 0:25:42 (0.924 s / it) [11-25 22:24:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 145/350] Total time: 0:25:42 (0.924 s / it) [11-25 22:24:07] (/home/user/VAR/train.py , line 276)=> [ep145] (training ) Lm: 6.446 (6.458), Lt: 5.689 (5.705), Acc m&t: 3.55 5.55, Remain: 3 days, 16:06:23, Finish: 2024-11-28 22:30 [11-25 22:24:07] (/home/user/VAR/train.py , line 276)=> [ep145] (training ) Lm: 6.446 (6.458), Lt: 5.689 (5.705), Acc m&t: 3.55 5.55, Remain: 3 days, 16:05:51, Finish: 2024-11-28 22:29 [11-25 22:24:07] (/home/user/VAR/train.py , line 276)=> [ep145] (training ) Lm: 6.446 (6.458), Lt: 5.689 (5.705), Acc m&t: 3.55 5.55, Remain: 3 days, 16:05:19, Finish: 2024-11-28 22:29 [11-25 22:24:07] (/home/user/VAR/train.py , line 276)=> [ep145] (training ) Lm: 6.446 (6.458), Lt: 5.689 (5.705), Acc m&t: 3.55 5.55, Remain: 3 days, 16:04:58, Finish: 2024-11-28 22:29 [11-25 22:24:07] (/home/user/VAR/train.py , line 276)=> [ep145] (training ) Lm: 6.446 (6.458), Lt: 5.689 (5.705), Acc m&t: 3.55 5.55, Remain: 3 days, 16:04:13, Finish: 2024-11-28 22:28 [11-25 22:24:07] (/home/user/VAR/train.py , line 276)=> [ep145] (training ) Lm: 6.446 (6.458), Lt: 5.689 (5.705), Acc m&t: 3.55 5.55, Remain: 3 days, 16:05:27, Finish: 2024-11-28 22:29 [11-25 22:24:07] (/home/user/VAR/train.py , line 276)=> [ep145] (training ) Lm: 6.446 (6.458), Lt: 5.689 (5.705), Acc m&t: 3.55 5.55, Remain: 3 days, 16:06:26, Finish: 2024-11-28 22:30 [11-25 22:24:07] (/home/user/VAR/train.py , line 276)=> [ep145] (training ) Lm: 6.446 (6.458), Lt: 5.689 (5.705), Acc m&t: 3.55 5.55, Remain: 3 days, 16:05:28, Finish: 2024-11-28 22:29 [11-25 22:24:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 0/1669] eta: 0:24:35 tlr: 0.00015 tnm: 0.25 Lm: 6.362 (6.362) Lt: 5.660 (5.660) Accm: 4.08 (4.08) Acct: 5.89 (5.89) proj_loss: -0.6251 (-0.6251) time: 0.8841 data: 0.0004 [11-25 22:24:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 0/1669] eta: 0:24:36 tlr: 0.00015 tnm: 0.25 Lm: 6.531 (6.531) Lt: 5.789 (5.789) Accm: 3.34 (3.34) Acct: 5.03 (5.03) proj_loss: -0.6096 (-0.6096) time: 0.8844 data: 0.0004 [11-25 22:24:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 0/1669] eta: 0:24:36 tlr: 0.00015 tnm: 0.25 Lm: 6.374 (6.374) Lt: 5.627 (5.627) Accm: 3.51 (3.51) Acct: 5.41 (5.41) proj_loss: -0.6266 (-0.6266) time: 0.8845 data: 0.0003 [11-25 22:24:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 0/1669] eta: 0:24:36 tlr: 0.00015 tnm: 0.25 Lm: 6.386 (6.386) Lt: 5.550 (5.550) Accm: 3.69 (3.69) Acct: 5.99 (5.99) proj_loss: -0.5970 (-0.5970) time: 0.8846 data: 0.0004 [11-25 22:24:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 0/1669] eta: 0:24:36 tlr: 0.00015 tnm: 0.25 Lm: 6.334 (6.334) Lt: 5.578 (5.578) Accm: 3.69 (3.69) Acct: 5.65 (5.65) proj_loss: -0.6425 (-0.6425) time: 0.8845 data: 0.0003 [11-25 22:24:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 0/1669] eta: 0:24:36 tlr: 0.00015 tnm: 0.25 Lm: 6.267 (6.267) Lt: 5.485 (5.485) Accm: 3.85 (3.85) Acct: 5.92 (5.92) proj_loss: -0.6237 (-0.6237) time: 0.8845 data: 0.0003 [11-25 22:24:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 0/1669] eta: 0:24:36 tlr: 0.00015 tnm: 0.25 Lm: 6.762 (6.762) Lt: 6.156 (6.156) Accm: 2.74 (2.74) Acct: 3.58 (3.58) proj_loss: -0.5969 (-0.5969) time: 0.8846 data: 0.0003 [11-25 22:24:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 0/1669] eta: 0:24:36 tlr: 0.00015 tnm: 0.25 Lm: 6.395 (6.395) Lt: 5.635 (5.635) Accm: 3.70 (3.70) Acct: 6.03 (6.03) proj_loss: -0.6160 (-0.6160) time: 0.8847 data: 0.0003 [11-25 22:30:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 417/1669] eta: 0:20:14 tlr: 0.00015 tnm: 0.26 Lm: 6.305 (6.305) Lt: 5.518 (5.518) Accm: 4.06 (4.06) Acct: 6.40 (6.40) proj_loss: -0.6179 (-0.6179) time: 0.9240 data: 0.0003 [11-25 22:30:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 417/1669] eta: 0:20:14 tlr: 0.00015 tnm: 0.26 Lm: 6.320 (6.320) Lt: 5.604 (5.604) Accm: 4.01 (4.01) Acct: 5.96 (5.96) proj_loss: -0.6293 (-0.6293) time: 0.9240 data: 0.0003 [11-25 22:30:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 417/1669] eta: 0:20:14 tlr: 0.00015 tnm: 0.26 Lm: 6.459 (6.459) Lt: 5.624 (5.624) Accm: 3.37 (3.37) Acct: 5.49 (5.49) proj_loss: -0.6170 (-0.6170) time: 0.9240 data: 0.0003 [11-25 22:30:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 417/1669] eta: 0:20:14 tlr: 0.00015 tnm: 0.26 Lm: 6.239 (6.239) Lt: 5.472 (5.472) Accm: 4.06 (4.06) Acct: 6.22 (6.22) proj_loss: -0.6241 (-0.6241) time: 0.9240 data: 0.0003 [11-25 22:30:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 417/1669] eta: 0:20:14 tlr: 0.00015 tnm: 0.26 Lm: 6.477 (6.477) Lt: 5.776 (5.776) Accm: 3.39 (3.39) Acct: 5.17 (5.17) proj_loss: -0.5913 (-0.5913) time: 0.9240 data: 0.0002 [11-25 22:30:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 417/1669] eta: 0:20:14 tlr: 0.00015 tnm: 0.26 Lm: 6.432 (6.432) Lt: 5.681 (5.681) Accm: 3.47 (3.47) Acct: 5.53 (5.53) proj_loss: -0.6205 (-0.6205) time: 0.9240 data: 0.0003 [11-25 22:30:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 417/1669] eta: 0:20:14 tlr: 0.00015 tnm: 0.26 Lm: 6.282 (6.282) Lt: 5.523 (5.523) Accm: 3.82 (3.82) Acct: 6.03 (6.03) proj_loss: -0.6369 (-0.6369) time: 0.9240 data: 0.0002 [11-25 22:30:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 417/1669] eta: 0:20:14 tlr: 0.00015 tnm: 0.26 Lm: 6.387 (6.387) Lt: 5.615 (5.615) Accm: 3.59 (3.59) Acct: 5.65 (5.65) proj_loss: -0.6206 (-0.6206) time: 0.9241 data: 0.0003 [11-25 22:37:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 834/1669] eta: 0:13:10 tlr: 0.00015 tnm: 0.25 Lm: 6.426 (6.400) Lt: 5.624 (5.618) Accm: 3.42 (3.54) Acct: 5.23 (5.51) proj_loss: -0.6096 (-0.6104) time: 0.9257 data: 0.0003 [11-25 22:37:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 834/1669] eta: 0:13:10 tlr: 0.00015 tnm: 0.25 Lm: 6.334 (6.415) Lt: 5.578 (5.666) Accm: 3.69 (3.59) Acct: 5.65 (5.70) proj_loss: -0.6313 (-0.6333) time: 0.9257 data: 0.0002 [11-25 22:37:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 834/1669] eta: 0:13:10 tlr: 0.00015 tnm: 0.25 Lm: 6.490 (6.459) Lt: 5.736 (5.724) Accm: 3.42 (3.33) Acct: 5.41 (5.19) proj_loss: -0.6144 (-0.6183) time: 0.9257 data: 0.0002 [11-25 22:37:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 834/1669] eta: 0:13:10 tlr: 0.00015 tnm: 0.25 Lm: 6.462 (6.472) Lt: 5.701 (5.751) Accm: 3.69 (3.49) Acct: 5.82 (5.38) proj_loss: -0.5969 (-0.5943) time: 0.9257 data: 0.0002 [11-25 22:37:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 834/1669] eta: 0:13:10 tlr: 0.00015 tnm: 0.25 Lm: 6.215 (6.251) Lt: 5.400 (5.452) Accm: 4.43 (4.36) Acct: 6.78 (6.89) proj_loss: -0.6198 (-0.6217) time: 0.9257 data: 0.0002 [11-25 22:37:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 834/1669] eta: 0:13:10 tlr: 0.00015 tnm: 0.25 Lm: 6.267 (6.288) Lt: 5.485 (5.511) Accm: 3.85 (3.97) Acct: 5.99 (6.14) proj_loss: -0.6244 (-0.6251) time: 0.9257 data: 0.0002 [11-25 22:37:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 834/1669] eta: 0:13:10 tlr: 0.00015 tnm: 0.25 Lm: 6.456 (6.458) Lt: 5.618 (5.622) Accm: 3.42 (3.39) Acct: 5.51 (5.50) proj_loss: -0.6077 (-0.6139) time: 0.9257 data: 0.0003 [11-25 22:37:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [ 834/1669] eta: 0:13:10 tlr: 0.00015 tnm: 0.25 Lm: 6.278 (6.281) Lt: 5.548 (5.543) Accm: 4.08 (4.08) Acct: 6.03 (6.06) proj_loss: -0.6251 (-0.6277) time: 0.9257 data: 0.0003 [11-25 22:43:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [1251/1669] eta: 0:06:32 tlr: 0.00015 tnm: 0.24 Lm: 6.320 (6.386) Lt: 5.604 (5.651) Accm: 4.01 (3.75) Acct: 5.96 (5.64) proj_loss: -0.6248 (-0.6181) time: 0.9225 data: 0.0002 [11-25 22:43:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [1251/1669] eta: 0:06:32 tlr: 0.00015 tnm: 0.24 Lm: 6.326 (6.334) Lt: 5.538 (5.593) Accm: 3.81 (3.88) Acct: 5.96 (6.06) proj_loss: -0.6258 (-0.6298) time: 0.9225 data: 0.0002 [11-25 22:43:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [1251/1669] eta: 0:06:32 tlr: 0.00015 tnm: 0.24 Lm: 6.305 (6.349) Lt: 5.518 (5.593) Accm: 4.06 (4.06) Acct: 6.40 (6.28) proj_loss: -0.6179 (-0.6146) time: 0.9225 data: 0.0002 [11-25 22:43:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [1251/1669] eta: 0:06:32 tlr: 0.00015 tnm: 0.24 Lm: 6.396 (6.391) Lt: 5.554 (5.584) Accm: 3.63 (3.63) Acct: 5.75 (5.72) proj_loss: -0.6033 (-0.6070) time: 0.9225 data: 0.0003 [11-25 22:43:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [1251/1669] eta: 0:06:32 tlr: 0.00015 tnm: 0.24 Lm: 6.327 (6.400) Lt: 5.549 (5.657) Accm: 3.86 (3.70) Acct: 6.25 (5.71) proj_loss: -0.5987 (-0.6041) time: 0.9225 data: 0.0002 [11-25 22:43:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [1251/1669] eta: 0:06:32 tlr: 0.00015 tnm: 0.24 Lm: 6.502 (6.485) Lt: 5.741 (5.730) Accm: 3.47 (3.39) Acct: 5.53 (5.33) proj_loss: -0.6141 (-0.6112) time: 0.9225 data: 0.0003 [11-25 22:43:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [1251/1669] eta: 0:06:32 tlr: 0.00015 tnm: 0.24 Lm: 6.508 (6.482) Lt: 5.765 (5.755) Accm: 3.41 (3.42) Acct: 5.35 (5.35) proj_loss: -0.6287 (-0.6237) time: 0.9225 data: 0.0002 [11-25 22:43:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [1251/1669] eta: 0:06:32 tlr: 0.00015 tnm: 0.24 Lm: 6.421 (6.428) Lt: 5.605 (5.614) Accm: 3.55 (3.51) Acct: 5.75 (5.70) proj_loss: -0.6152 (-0.6161) time: 0.9225 data: 0.0003 [11-25 22:50:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.456 (6.487) Lt: 5.618 (5.690) Accm: 3.42 (3.37) Acct: 5.51 (5.45) proj_loss: -0.6127 (-0.6154) time: 0.9272 data: 0.0015 [11-25 22:50:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.334 (6.423) Lt: 5.578 (5.686) Accm: 3.69 (3.71) Acct: 5.65 (5.87) proj_loss: -0.6311 (-0.6252) time: 0.9272 data: 0.0015 [11-25 22:50:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.462 (6.426) Lt: 5.701 (5.671) Accm: 3.69 (3.60) Acct: 5.82 (5.64) proj_loss: -0.6005 (-0.6070) time: 0.9272 data: 0.0019 [11-25 22:50:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.511 (6.490) Lt: 5.747 (5.747) Accm: 3.42 (3.32) Acct: 5.41 (5.17) proj_loss: -0.6144 (-0.6136) time: 0.9272 data: 0.0021 [11-25 22:50:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.280 (6.335) Lt: 5.475 (5.569) Accm: 3.72 (3.99) Acct: 6.03 (6.18) proj_loss: -0.6198 (-0.6184) time: 0.9272 data: 0.0014 [11-25 22:50:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.362 (6.394) Lt: 5.660 (5.655) Accm: 3.95 (3.79) Acct: 6.03 (5.74) proj_loss: -0.6245 (-0.6140) time: 0.9272 data: 0.0021 [11-25 22:50:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.386 (6.378) Lt: 5.591 (5.632) Accm: 3.77 (3.75) Acct: 5.92 (5.80) proj_loss: -0.6244 (-0.6236) time: 0.9272 data: 0.0018 [11-25 22:50:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 146/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.367 (6.351) Lt: 5.484 (5.551) Accm: 3.85 (3.83) Acct: 6.27 (6.12) proj_loss: -0.5993 (-0.6055) time: 0.9272 data: 0.0015 [11-25 22:50:09] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 146/350] Total time: 0:26:01 (0.936 s / it) [11-25 22:50:09] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 146/350] Total time: 0:26:01 (0.936 s / it) [11-25 22:50:09] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 146/350] Total time: 0:26:01 (0.936 s / it) [11-25 22:50:09] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 146/350] Total time: 0:26:01 (0.936 s / it) [11-25 22:50:09] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 146/350] Total time: 0:26:01 (0.936 s / it) [11-25 22:50:09] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 146/350] Total time: 0:26:01 (0.936 s / it) [11-25 22:50:09] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 146/350] Total time: 0:26:01 (0.936 s / it) [11-25 22:50:09] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 146/350] Total time: 0:26:01 (0.936 s / it) [11-25 22:50:09] (/home/user/VAR/train.py , line 276)=> [ep146] (training ) Lm: 6.440 (6.440), Lt: 5.689 (5.689), Acc m&t: 3.55 5.57, Remain: 3 days, 15:56:57, Finish: 2024-11-28 22:47 [11-25 22:50:09] (/home/user/VAR/train.py , line 276)=> [ep146] (training ) Lm: 6.440 (6.440), Lt: 5.689 (5.689), Acc m&t: 3.55 5.57, Remain: 3 days, 15:56:27, Finish: 2024-11-28 22:46 [11-25 22:50:09] (/home/user/VAR/train.py , line 276)=> [ep146] (training ) Lm: 6.440 (6.440), Lt: 5.689 (5.689), Acc m&t: 3.55 5.57, Remain: 3 days, 15:57:00, Finish: 2024-11-28 22:47 [11-25 22:50:09] (/home/user/VAR/train.py , line 276)=> [ep146] (training ) Lm: 6.440 (6.440), Lt: 5.689 (5.689), Acc m&t: 3.55 5.57, Remain: 3 days, 15:56:36, Finish: 2024-11-28 22:46 [11-25 22:50:09] (/home/user/VAR/train.py , line 276)=> [ep146] (training ) Lm: 6.440 (6.440), Lt: 5.689 (5.689), Acc m&t: 3.55 5.57, Remain: 3 days, 15:55:53, Finish: 2024-11-28 22:46 [11-25 22:50:09] (/home/user/VAR/train.py , line 276)=> [ep146] (training ) Lm: 6.440 (6.440), Lt: 5.689 (5.689), Acc m&t: 3.55 5.57, Remain: 3 days, 15:55:41, Finish: 2024-11-28 22:45 [11-25 22:50:09] (/home/user/VAR/train.py , line 276)=> [ep146] (training ) Lm: 6.440 (6.440), Lt: 5.689 (5.689), Acc m&t: 3.55 5.57, Remain: 3 days, 15:57:25, Finish: 2024-11-28 22:47 [11-25 22:50:09] (/home/user/VAR/train.py , line 276)=> [ep146] (training ) Lm: 6.440 (6.440), Lt: 5.689 (5.689), Acc m&t: 3.55 5.57, Remain: 3 days, 15:56:13, Finish: 2024-11-28 22:46 [11-25 22:50:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 0/1669] eta: 0:25:25 tlr: 0.00015 tnm: 0.25 Lm: 6.707 (6.707) Lt: 6.001 (6.001) Accm: 3.32 (3.32) Acct: 5.13 (5.13) proj_loss: -0.6021 (-0.6021) time: 0.9142 data: 0.0003 [11-25 22:50:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 0/1669] eta: 0:25:26 tlr: 0.00015 tnm: 0.25 Lm: 6.595 (6.595) Lt: 5.792 (5.792) Accm: 3.22 (3.22) Acct: 4.99 (4.99) proj_loss: -0.6062 (-0.6062) time: 0.9146 data: 0.0003 [11-25 22:50:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 0/1669] eta: 0:25:26 tlr: 0.00015 tnm: 0.25 Lm: 6.490 (6.490) Lt: 5.643 (5.643) Accm: 3.58 (3.58) Acct: 6.37 (6.37) proj_loss: -0.6267 (-0.6267) time: 0.9147 data: 0.0004 [11-25 22:50:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 0/1669] eta: 0:25:26 tlr: 0.00015 tnm: 0.25 Lm: 6.291 (6.291) Lt: 5.536 (5.536) Accm: 3.93 (3.93) Acct: 6.03 (6.03) proj_loss: -0.5860 (-0.5860) time: 0.9148 data: 0.0003 [11-25 22:50:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 0/1669] eta: 0:25:27 tlr: 0.00015 tnm: 0.25 Lm: 6.836 (6.836) Lt: 6.195 (6.195) Accm: 2.39 (2.39) Acct: 3.51 (3.51) proj_loss: -0.6328 (-0.6328) time: 0.9150 data: 0.0004 [11-25 22:50:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 0/1669] eta: 0:25:26 tlr: 0.00015 tnm: 0.25 Lm: 6.411 (6.411) Lt: 5.659 (5.659) Accm: 3.77 (3.77) Acct: 6.27 (6.27) proj_loss: -0.6048 (-0.6048) time: 0.9149 data: 0.0004 [11-25 22:50:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 0/1669] eta: 0:25:26 tlr: 0.00015 tnm: 0.25 Lm: 6.481 (6.481) Lt: 5.730 (5.730) Accm: 3.61 (3.61) Acct: 5.92 (5.92) proj_loss: -0.6221 (-0.6221) time: 0.9149 data: 0.0004 [11-25 22:50:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 0/1669] eta: 0:25:27 tlr: 0.00015 tnm: 0.25 Lm: 6.391 (6.391) Lt: 5.798 (5.798) Accm: 3.57 (3.57) Acct: 5.27 (5.27) proj_loss: -0.6316 (-0.6316) time: 0.9151 data: 0.0004 [11-25 22:56:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.26 Lm: 6.432 (6.432) Lt: 5.765 (5.765) Accm: 3.72 (3.72) Acct: 5.79 (5.79) proj_loss: -0.6184 (-0.6184) time: 0.9240 data: 0.0003 [11-25 22:56:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.26 Lm: 6.603 (6.603) Lt: 5.857 (5.857) Accm: 3.31 (3.31) Acct: 5.41 (5.41) proj_loss: -0.6069 (-0.6069) time: 0.9240 data: 0.0002 [11-25 22:56:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.26 Lm: 6.431 (6.431) Lt: 5.689 (5.689) Accm: 3.66 (3.66) Acct: 5.82 (5.82) proj_loss: -0.6321 (-0.6321) time: 0.9240 data: 0.0003 [11-25 22:56:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.26 Lm: 6.387 (6.387) Lt: 5.606 (5.606) Accm: 3.66 (3.66) Acct: 5.92 (5.92) proj_loss: -0.5944 (-0.5944) time: 0.9240 data: 0.0003 [11-25 22:56:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.26 Lm: 6.565 (6.565) Lt: 5.811 (5.811) Accm: 3.04 (3.04) Acct: 4.84 (4.84) proj_loss: -0.6192 (-0.6192) time: 0.9240 data: 0.0003 [11-25 22:56:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.26 Lm: 6.684 (6.684) Lt: 5.963 (5.963) Accm: 2.89 (2.89) Acct: 4.27 (4.27) proj_loss: -0.6241 (-0.6241) time: 0.9240 data: 0.0003 [11-25 22:56:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.26 Lm: 6.388 (6.388) Lt: 5.627 (5.627) Accm: 3.62 (3.62) Acct: 5.77 (5.77) proj_loss: -0.6296 (-0.6296) time: 0.9240 data: 0.0003 [11-25 22:56:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.26 Lm: 6.365 (6.365) Lt: 5.489 (5.489) Accm: 3.96 (3.96) Acct: 6.77 (6.77) proj_loss: -0.6175 (-0.6175) time: 0.9240 data: 0.0003 [11-25 23:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 834/1669] eta: 0:13:28 tlr: 0.00015 tnm: 0.27 Lm: 6.490 (6.427) Lt: 5.643 (5.610) Accm: 3.58 (3.68) Acct: 6.37 (6.24) proj_loss: -0.6256 (-0.6202) time: 0.9227 data: 0.0002 [11-25 23:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 834/1669] eta: 0:13:28 tlr: 0.00015 tnm: 0.27 Lm: 6.294 (6.356) Lt: 5.541 (5.584) Accm: 3.93 (3.81) Acct: 6.03 (6.22) proj_loss: -0.6027 (-0.6085) time: 0.9227 data: 0.0003 [11-25 23:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 834/1669] eta: 0:13:28 tlr: 0.00015 tnm: 0.27 Lm: 6.499 (6.494) Lt: 5.713 (5.753) Accm: 3.32 (3.48) Acct: 5.68 (5.65) proj_loss: -0.6116 (-0.6170) time: 0.9226 data: 0.0003 [11-25 23:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 834/1669] eta: 0:13:28 tlr: 0.00015 tnm: 0.27 Lm: 6.532 (6.615) Lt: 5.755 (5.894) Accm: 3.12 (2.97) Acct: 4.79 (4.44) proj_loss: -0.6248 (-0.6244) time: 0.9227 data: 0.0002 [11-25 23:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 834/1669] eta: 0:13:28 tlr: 0.00015 tnm: 0.27 Lm: 6.473 (6.470) Lt: 5.798 (5.797) Accm: 3.57 (3.37) Acct: 5.27 (5.26) proj_loss: -0.6316 (-0.6265) time: 0.9226 data: 0.0003 [11-25 23:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 834/1669] eta: 0:13:28 tlr: 0.00015 tnm: 0.27 Lm: 6.481 (6.488) Lt: 5.730 (5.737) Accm: 3.61 (3.42) Acct: 5.72 (5.50) proj_loss: -0.6221 (-0.6178) time: 0.9227 data: 0.0002 [11-25 23:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 834/1669] eta: 0:13:28 tlr: 0.00015 tnm: 0.27 Lm: 6.365 (6.378) Lt: 5.659 (5.650) Accm: 3.77 (3.73) Acct: 5.96 (5.83) proj_loss: -0.6185 (-0.6259) time: 0.9227 data: 0.0003 [11-25 23:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [ 834/1669] eta: 0:13:28 tlr: 0.00015 tnm: 0.27 Lm: 6.538 (6.556) Lt: 5.831 (5.834) Accm: 3.19 (3.09) Acct: 4.82 (4.83) proj_loss: -0.6321 (-0.6247) time: 0.9227 data: 0.0003 [11-25 23:10:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [1251/1669] eta: 0:06:38 tlr: 0.00015 tnm: 0.25 Lm: 6.537 (6.541) Lt: 5.811 (5.816) Accm: 3.21 (3.19) Acct: 4.91 (4.97) proj_loss: -0.6280 (-0.6245) time: 0.9226 data: 0.0003 [11-25 23:10:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [1251/1669] eta: 0:06:38 tlr: 0.00015 tnm: 0.25 Lm: 6.504 (6.568) Lt: 5.746 (5.855) Accm: 3.26 (3.20) Acct: 4.91 (4.81) proj_loss: -0.6279 (-0.6260) time: 0.9226 data: 0.0002 [11-25 23:10:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [1251/1669] eta: 0:06:38 tlr: 0.00015 tnm: 0.25 Lm: 6.522 (6.475) Lt: 5.748 (5.696) Accm: 3.36 (3.51) Acct: 5.79 (5.93) proj_loss: -0.6245 (-0.6210) time: 0.9226 data: 0.0002 [11-25 23:10:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [1251/1669] eta: 0:06:38 tlr: 0.00015 tnm: 0.25 Lm: 6.388 (6.438) Lt: 5.678 (5.713) Accm: 3.62 (3.55) Acct: 5.61 (5.66) proj_loss: -0.6117 (-0.6180) time: 0.9226 data: 0.0003 [11-25 23:10:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [1251/1669] eta: 0:06:38 tlr: 0.00015 tnm: 0.25 Lm: 6.458 (6.475) Lt: 5.664 (5.719) Accm: 3.43 (3.50) Acct: 5.77 (5.70) proj_loss: -0.6125 (-0.6161) time: 0.9226 data: 0.0002 [11-25 23:10:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [1251/1669] eta: 0:06:38 tlr: 0.00015 tnm: 0.25 Lm: 6.481 (6.487) Lt: 5.689 (5.715) Accm: 3.48 (3.41) Acct: 5.63 (5.51) proj_loss: -0.6056 (-0.6090) time: 0.9226 data: 0.0003 [11-25 23:10:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [1251/1669] eta: 0:06:38 tlr: 0.00015 tnm: 0.25 Lm: 6.321 (6.354) Lt: 5.583 (5.594) Accm: 3.80 (3.78) Acct: 5.92 (6.03) proj_loss: -0.6197 (-0.6189) time: 0.9226 data: 0.0003 [11-25 23:10:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [1251/1669] eta: 0:06:38 tlr: 0.00015 tnm: 0.25 Lm: 6.510 (6.510) Lt: 5.829 (5.846) Accm: 3.36 (3.31) Acct: 5.04 (5.15) proj_loss: -0.6372 (-0.6314) time: 0.9226 data: 0.0003 [11-25 23:16:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.538 (6.551) Lt: 5.831 (5.831) Accm: 3.19 (3.16) Acct: 4.82 (4.92) proj_loss: -0.6243 (-0.6244) time: 0.9225 data: 0.0018 [11-25 23:16:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.476 (6.543) Lt: 5.737 (5.814) Accm: 3.39 (3.24) Acct: 5.03 (4.95) proj_loss: -0.6248 (-0.6251) time: 0.9225 data: 0.0017 [11-25 23:16:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.365 (6.414) Lt: 5.659 (5.672) Accm: 3.73 (3.59) Acct: 5.96 (5.75) proj_loss: -0.6048 (-0.6103) time: 0.9225 data: 0.0015 [11-25 23:16:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.537 (6.516) Lt: 5.798 (5.815) Accm: 3.15 (3.26) Acct: 5.13 (5.14) proj_loss: -0.6316 (-0.6238) time: 0.9225 data: 0.0020 [11-25 23:16:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.490 (6.452) Lt: 5.643 (5.682) Accm: 3.58 (3.54) Acct: 5.92 (5.93) proj_loss: -0.6256 (-0.6234) time: 0.9225 data: 0.0015 [11-25 23:16:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.349 (6.361) Lt: 5.624 (5.610) Accm: 3.93 (3.84) Acct: 6.03 (6.03) proj_loss: -0.6320 (-0.6215) time: 0.9225 data: 0.0018 [11-25 23:16:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.443 (6.469) Lt: 5.615 (5.692) Accm: 3.48 (3.49) Acct: 5.82 (5.72) proj_loss: -0.6116 (-0.6025) time: 0.9225 data: 0.0018 [11-25 23:16:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 147/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.481 (6.485) Lt: 5.648 (5.694) Accm: 3.35 (3.39) Acct: 5.54 (5.48) proj_loss: -0.5892 (-0.6026) time: 0.9225 data: 0.0016 [11-25 23:16:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 147/350] Total time: 0:26:19 (0.947 s / it) [11-25 23:16:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 147/350] Total time: 0:26:19 (0.947 s / it) [11-25 23:16:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 147/350] Total time: 0:26:19 (0.947 s / it) [11-25 23:16:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 147/350] Total time: 0:26:19 (0.947 s / it) [11-25 23:16:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 147/350] Total time: 0:26:19 (0.947 s / it) [11-25 23:16:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 147/350] Total time: 0:26:19 (0.947 s / it) [11-25 23:16:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 147/350] Total time: 0:26:19 (0.947 s / it) [11-25 23:16:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 147/350] Total time: 0:26:19 (0.947 s / it) [11-25 23:16:29] (/home/user/VAR/train.py , line 276)=> [ep147] (training ) Lm: 6.438 (6.438), Lt: 5.683 (5.683), Acc m&t: 3.55 5.57, Remain: 3 days, 15:20:06, Finish: 2024-11-28 22:36 [11-25 23:16:29] (/home/user/VAR/train.py , line 276)=> [ep147] (training ) Lm: 6.438 (6.438), Lt: 5.683 (5.683), Acc m&t: 3.55 5.57, Remain: 3 days, 15:20:18, Finish: 2024-11-28 22:36 [11-25 23:16:29] (/home/user/VAR/train.py , line 276)=> [ep147] (training ) Lm: 6.438 (6.438), Lt: 5.683 (5.683), Acc m&t: 3.55 5.57, Remain: 3 days, 15:19:18, Finish: 2024-11-28 22:35 [11-25 23:16:29] (/home/user/VAR/train.py , line 276)=> [ep147] (training ) Lm: 6.438 (6.438), Lt: 5.683 (5.683), Acc m&t: 3.55 5.57, Remain: 3 days, 15:16:58, Finish: 2024-11-28 22:33 [11-25 23:16:29] (/home/user/VAR/train.py , line 276)=> [ep147] (training ) Lm: 6.438 (6.438), Lt: 5.683 (5.683), Acc m&t: 3.55 5.57, Remain: 3 days, 15:18:10, Finish: 2024-11-28 22:34 [11-25 23:16:29] (/home/user/VAR/train.py , line 276)=> [ep147] (training ) Lm: 6.438 (6.438), Lt: 5.683 (5.683), Acc m&t: 3.55 5.57, Remain: 3 days, 15:17:18, Finish: 2024-11-28 22:33 [11-25 23:16:29] (/home/user/VAR/train.py , line 276)=> [ep147] (training ) Lm: 6.438 (6.438), Lt: 5.683 (5.683), Acc m&t: 3.55 5.57, Remain: 3 days, 15:17:35, Finish: 2024-11-28 22:34 [11-25 23:16:29] (/home/user/VAR/train.py , line 276)=> [ep147] (training ) Lm: 6.438 (6.438), Lt: 5.683 (5.683), Acc m&t: 3.55 5.57, Remain: 3 days, 15:20:16, Finish: 2024-11-28 22:36 [11-25 23:16:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 0/1669] eta: 0:24:38 tlr: 0.00015 tnm: 0.26 Lm: 6.535 (6.535) Lt: 5.765 (5.765) Accm: 3.51 (3.51) Acct: 5.75 (5.75) proj_loss: -0.5955 (-0.5955) time: 0.8857 data: 0.0004 [11-25 23:16:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 0/1669] eta: 0:24:32 tlr: 0.00015 tnm: 0.26 Lm: 6.115 (6.115) Lt: 5.331 (5.331) Accm: 4.65 (4.65) Acct: 7.40 (7.40) proj_loss: -0.6533 (-0.6533) time: 0.8822 data: 0.0004 [11-25 23:16:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 0/1669] eta: 0:24:32 tlr: 0.00015 tnm: 0.26 Lm: 6.651 (6.651) Lt: 5.995 (5.995) Accm: 2.80 (2.80) Acct: 3.89 (3.89) proj_loss: -0.6008 (-0.6008) time: 0.8824 data: 0.0004 [11-25 23:16:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 0/1669] eta: 0:24:39 tlr: 0.00015 tnm: 0.26 Lm: 6.477 (6.477) Lt: 5.722 (5.722) Accm: 3.61 (3.61) Acct: 5.13 (5.13) proj_loss: -0.6155 (-0.6155) time: 0.8864 data: 0.0004 [11-25 23:16:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 0/1669] eta: 0:24:39 tlr: 0.00015 tnm: 0.26 Lm: 6.559 (6.559) Lt: 5.782 (5.782) Accm: 3.19 (3.19) Acct: 5.41 (5.41) proj_loss: -0.6043 (-0.6043) time: 0.8867 data: 0.0003 [11-25 23:16:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 0/1669] eta: 0:24:39 tlr: 0.00015 tnm: 0.26 Lm: 6.401 (6.401) Lt: 5.673 (5.673) Accm: 3.73 (3.73) Acct: 6.40 (6.40) proj_loss: -0.6213 (-0.6213) time: 0.8866 data: 0.0004 [11-25 23:16:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 0/1669] eta: 0:24:40 tlr: 0.00015 tnm: 0.26 Lm: 6.457 (6.457) Lt: 5.688 (5.688) Accm: 3.63 (3.63) Acct: 5.48 (5.48) proj_loss: -0.6218 (-0.6218) time: 0.8869 data: 0.0004 [11-25 23:16:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 0/1669] eta: 0:24:41 tlr: 0.00015 tnm: 0.26 Lm: 6.416 (6.416) Lt: 5.615 (5.615) Accm: 3.83 (3.83) Acct: 6.96 (6.96) proj_loss: -0.6225 (-0.6225) time: 0.8879 data: 0.0003 [11-25 23:22:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 417/1669] eta: 0:19:18 tlr: 0.00015 tnm: 0.25 Lm: 6.256 (6.256) Lt: 5.432 (5.432) Accm: 4.25 (4.25) Acct: 7.28 (7.28) proj_loss: -0.6120 (-0.6120) time: 0.9242 data: 0.0002 [11-25 23:22:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 417/1669] eta: 0:19:18 tlr: 0.00015 tnm: 0.25 Lm: 6.426 (6.426) Lt: 5.691 (5.691) Accm: 3.53 (3.53) Acct: 5.58 (5.58) proj_loss: -0.6300 (-0.6300) time: 0.9242 data: 0.0002 [11-25 23:22:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 417/1669] eta: 0:19:18 tlr: 0.00015 tnm: 0.25 Lm: 6.470 (6.470) Lt: 5.725 (5.725) Accm: 3.57 (3.57) Acct: 5.85 (5.85) proj_loss: -0.6291 (-0.6291) time: 0.9242 data: 0.0002 [11-25 23:22:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 417/1669] eta: 0:19:18 tlr: 0.00015 tnm: 0.25 Lm: 6.596 (6.596) Lt: 5.904 (5.904) Accm: 3.00 (3.00) Acct: 4.32 (4.32) proj_loss: -0.5984 (-0.5984) time: 0.9242 data: 0.0003 [11-25 23:22:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 417/1669] eta: 0:19:18 tlr: 0.00015 tnm: 0.25 Lm: 6.614 (6.614) Lt: 5.847 (5.847) Accm: 3.10 (3.10) Acct: 4.91 (4.91) proj_loss: -0.6124 (-0.6124) time: 0.9242 data: 0.0002 [11-25 23:22:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 417/1669] eta: 0:19:18 tlr: 0.00015 tnm: 0.25 Lm: 6.336 (6.336) Lt: 5.574 (5.574) Accm: 4.03 (4.03) Acct: 6.27 (6.27) proj_loss: -0.6201 (-0.6201) time: 0.9242 data: 0.0003 [11-25 23:22:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 417/1669] eta: 0:19:18 tlr: 0.00015 tnm: 0.25 Lm: 6.347 (6.347) Lt: 5.558 (5.558) Accm: 3.69 (3.69) Acct: 6.13 (6.13) proj_loss: -0.6237 (-0.6237) time: 0.9242 data: 0.0002 [11-25 23:22:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 417/1669] eta: 0:19:18 tlr: 0.00015 tnm: 0.25 Lm: 6.279 (6.279) Lt: 5.482 (5.482) Accm: 4.36 (4.36) Acct: 6.63 (6.63) proj_loss: -0.6265 (-0.6265) time: 0.9242 data: 0.0003 [11-25 23:29:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 834/1669] eta: 0:12:52 tlr: 0.00015 tnm: 0.24 Lm: 6.477 (6.410) Lt: 5.722 (5.632) Accm: 3.61 (3.86) Acct: 5.13 (5.96) proj_loss: -0.6155 (-0.6142) time: 0.9242 data: 0.0002 [11-25 23:29:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 834/1669] eta: 0:12:52 tlr: 0.00015 tnm: 0.24 Lm: 6.535 (6.510) Lt: 5.765 (5.752) Accm: 3.51 (3.37) Acct: 5.41 (5.34) proj_loss: -0.6092 (-0.6231) time: 0.9242 data: 0.0002 [11-25 23:29:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 834/1669] eta: 0:12:52 tlr: 0.00015 tnm: 0.24 Lm: 6.513 (6.485) Lt: 5.755 (5.735) Accm: 3.66 (3.60) Acct: 5.65 (5.79) proj_loss: -0.6442 (-0.6342) time: 0.9242 data: 0.0003 [11-25 23:29:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 834/1669] eta: 0:12:52 tlr: 0.00015 tnm: 0.24 Lm: 6.457 (6.496) Lt: 5.688 (5.740) Accm: 3.63 (3.49) Acct: 5.48 (5.14) proj_loss: -0.6129 (-0.6125) time: 0.9242 data: 0.0003 [11-25 23:29:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 834/1669] eta: 0:12:52 tlr: 0.00015 tnm: 0.24 Lm: 6.651 (6.628) Lt: 5.995 (5.935) Accm: 2.80 (2.91) Acct: 3.89 (4.16) proj_loss: -0.6008 (-0.6037) time: 0.9242 data: 0.0003 [11-25 23:29:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 834/1669] eta: 0:12:52 tlr: 0.00015 tnm: 0.24 Lm: 6.498 (6.390) Lt: 5.794 (5.647) Accm: 3.41 (3.67) Acct: 5.13 (5.77) proj_loss: -0.6390 (-0.6264) time: 0.9242 data: 0.0003 [11-25 23:29:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 834/1669] eta: 0:12:52 tlr: 0.00015 tnm: 0.24 Lm: 6.416 (6.394) Lt: 5.615 (5.612) Accm: 3.83 (3.84) Acct: 6.96 (6.42) proj_loss: -0.6018 (-0.6086) time: 0.9242 data: 0.0003 [11-25 23:29:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [ 834/1669] eta: 0:12:52 tlr: 0.00015 tnm: 0.24 Lm: 6.293 (6.299) Lt: 5.502 (5.539) Accm: 3.73 (3.85) Acct: 6.37 (6.21) proj_loss: -0.6261 (-0.6324) time: 0.9242 data: 0.0002 [11-25 23:35:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.25 Lm: 6.248 (6.274) Lt: 5.472 (5.509) Accm: 3.88 (3.89) Acct: 6.25 (6.19) proj_loss: -0.6237 (-0.6270) time: 0.9246 data: 0.0003 [11-25 23:35:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.25 Lm: 6.446 (6.472) Lt: 5.691 (5.680) Accm: 3.53 (3.44) Acct: 5.58 (5.48) proj_loss: -0.6057 (-0.6178) time: 0.9246 data: 0.0003 [11-25 23:35:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.25 Lm: 6.448 (6.431) Lt: 5.712 (5.669) Accm: 3.80 (3.70) Acct: 5.84 (5.85) proj_loss: -0.6264 (-0.6278) time: 0.9246 data: 0.0003 [11-25 23:35:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.25 Lm: 6.527 (6.472) Lt: 5.805 (5.734) Accm: 3.18 (3.39) Acct: 4.96 (5.36) proj_loss: -0.6280 (-0.6240) time: 0.9246 data: 0.0003 [11-25 23:35:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.25 Lm: 6.484 (6.430) Lt: 5.751 (5.669) Accm: 3.49 (3.73) Acct: 5.04 (5.71) proj_loss: -0.6102 (-0.6119) time: 0.9246 data: 0.0003 [11-25 23:35:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.25 Lm: 6.414 (6.464) Lt: 5.700 (5.733) Accm: 3.63 (3.53) Acct: 5.51 (5.24) proj_loss: -0.6123 (-0.6123) time: 0.9246 data: 0.0003 [11-25 23:35:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.25 Lm: 6.503 (6.443) Lt: 5.727 (5.668) Accm: 3.43 (3.59) Acct: 5.82 (5.90) proj_loss: -0.6122 (-0.6132) time: 0.9246 data: 0.0002 [11-25 23:35:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.25 Lm: 6.596 (6.597) Lt: 5.904 (5.891) Accm: 3.00 (3.08) Acct: 4.32 (4.50) proj_loss: -0.6074 (-0.6081) time: 0.9246 data: 0.0003 [11-25 23:42:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.540 (6.572) Lt: 5.813 (5.849) Accm: 3.09 (3.08) Acct: 4.75 (4.60) proj_loss: -0.6052 (-0.6075) time: 0.9273 data: 0.0016 [11-25 23:42:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 148/350] Total time: 0:25:45 (0.926 s / it) [11-25 23:42:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.382 (6.397) Lt: 5.668 (5.634) Accm: 3.95 (3.85) Acct: 6.03 (6.12) proj_loss: -0.6303 (-0.6283) time: 0.9273 data: 0.0014 [11-25 23:42:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.590 (6.478) Lt: 5.839 (5.724) Accm: 3.18 (3.51) Acct: 5.20 (5.76) proj_loss: -0.6173 (-0.6140) time: 0.9273 data: 0.0015 [11-25 23:42:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.432 (6.458) Lt: 5.699 (5.726) Accm: 3.63 (3.53) Acct: 5.54 (5.33) proj_loss: -0.6129 (-0.6154) time: 0.9273 data: 0.0016 [11-25 23:42:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.535 (6.515) Lt: 5.765 (5.755) Accm: 3.51 (3.30) Acct: 5.41 (5.20) proj_loss: -0.6092 (-0.6210) time: 0.9273 data: 0.0016 [11-25 23:42:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.557 (6.493) Lt: 5.817 (5.788) Accm: 2.99 (3.31) Acct: 4.79 (5.21) proj_loss: -0.6170 (-0.6215) time: 0.9273 data: 0.0016 [11-25 23:42:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.477 (6.425) Lt: 5.722 (5.649) Accm: 3.37 (3.65) Acct: 5.13 (5.61) proj_loss: -0.6048 (-0.6094) time: 0.9273 data: 0.0017 [11-25 23:42:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 148/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.293 (6.291) Lt: 5.502 (5.512) Accm: 4.04 (3.94) Acct: 6.37 (6.28) proj_loss: -0.6213 (-0.6191) time: 0.9273 data: 0.0016 [11-25 23:42:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 148/350] Total time: 0:25:45 (0.926 s / it) [11-25 23:42:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 148/350] Total time: 0:25:45 (0.926 s / it) [11-25 23:42:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 148/350] Total time: 0:25:45 (0.926 s / it) [11-25 23:42:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 148/350] Total time: 0:25:45 (0.926 s / it) [11-25 23:42:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 148/350] Total time: 0:25:45 (0.926 s / it) [11-25 23:42:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 148/350] Total time: 0:25:45 (0.926 s / it) [11-25 23:42:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 148/350] Total time: 0:25:45 (0.926 s / it) [11-25 23:42:15] (/home/user/VAR/train.py , line 276)=> [ep148] (training ) Lm: 6.438 (6.444), Lt: 5.683 (5.691), Acc m&t: 3.55 5.57, Remain: 3 days, 15:09:43, Finish: 2024-11-28 22:51 [11-25 23:42:15] (/home/user/VAR/train.py , line 276)=> [ep148] (training ) Lm: 6.438 (6.444), Lt: 5.683 (5.691), Acc m&t: 3.55 5.57, Remain: 3 days, 15:09:22, Finish: 2024-11-28 22:51 [11-25 23:42:15] (/home/user/VAR/train.py , line 276)=> [ep148] (training ) Lm: 6.438 (6.444), Lt: 5.683 (5.691), Acc m&t: 3.55 5.57, Remain: 3 days, 15:08:44, Finish: 2024-11-28 22:50 [11-25 23:42:15] (/home/user/VAR/train.py , line 276)=> [ep148] (training ) Lm: 6.438 (6.444), Lt: 5.683 (5.691), Acc m&t: 3.55 5.57, Remain: 3 days, 15:07:10, Finish: 2024-11-28 22:49 [11-25 23:42:15] (/home/user/VAR/train.py , line 276)=> [ep148] (training ) Lm: 6.438 (6.444), Lt: 5.683 (5.691), Acc m&t: 3.55 5.57, Remain: 3 days, 15:07:53, Finish: 2024-11-28 22:50 [11-25 23:42:15] (/home/user/VAR/train.py , line 276)=> [ep148] (training ) Lm: 6.438 (6.444), Lt: 5.683 (5.691), Acc m&t: 3.55 5.57, Remain: 3 days, 15:06:23, Finish: 2024-11-28 22:48 [11-25 23:42:15] (/home/user/VAR/train.py , line 276)=> [ep148] (training ) Lm: 6.438 (6.444), Lt: 5.683 (5.691), Acc m&t: 3.55 5.57, Remain: 3 days, 15:07:40, Finish: 2024-11-28 22:49 [11-25 23:42:15] (/home/user/VAR/train.py , line 276)=> [ep148] (training ) Lm: 6.438 (6.444), Lt: 5.683 (5.691), Acc m&t: 3.55 5.57, Remain: 3 days, 15:07:56, Finish: 2024-11-28 22:50 [11-25 23:42:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 0/1669] eta: 0:24:57 tlr: 0.00015 tnm: 0.25 Lm: 6.640 (6.640) Lt: 5.943 (5.943) Accm: 2.87 (2.87) Acct: 4.34 (4.34) proj_loss: -0.6344 (-0.6344) time: 0.8970 data: 0.0003 [11-25 23:42:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 0/1669] eta: 0:24:57 tlr: 0.00015 tnm: 0.25 Lm: 6.286 (6.286) Lt: 5.550 (5.550) Accm: 4.22 (4.22) Acct: 6.99 (6.99) proj_loss: -0.6180 (-0.6180) time: 0.8970 data: 0.0003 [11-25 23:42:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 0/1669] eta: 0:24:55 tlr: 0.00015 tnm: 0.25 Lm: 6.269 (6.269) Lt: 5.456 (5.456) Accm: 4.47 (4.47) Acct: 7.13 (7.13) proj_loss: -0.5990 (-0.5990) time: 0.8960 data: 0.0004 [11-25 23:42:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 0/1669] eta: 0:24:55 tlr: 0.00015 tnm: 0.25 Lm: 6.070 (6.070) Lt: 5.261 (5.261) Accm: 4.98 (4.98) Acct: 7.54 (7.54) proj_loss: -0.6402 (-0.6402) time: 0.8960 data: 0.0004 [11-25 23:42:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 0/1669] eta: 0:24:57 tlr: 0.00015 tnm: 0.25 Lm: 6.531 (6.531) Lt: 5.732 (5.732) Accm: 2.93 (2.93) Acct: 4.68 (4.68) proj_loss: -0.5682 (-0.5682) time: 0.8971 data: 0.0004 [11-25 23:42:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 0/1669] eta: 0:24:57 tlr: 0.00015 tnm: 0.25 Lm: 6.452 (6.452) Lt: 5.720 (5.720) Accm: 3.41 (3.41) Acct: 4.82 (4.82) proj_loss: -0.5843 (-0.5843) time: 0.8975 data: 0.0004 [11-25 23:42:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 0/1669] eta: 0:24:56 tlr: 0.00015 tnm: 0.25 Lm: 6.595 (6.595) Lt: 5.816 (5.816) Accm: 3.28 (3.28) Acct: 4.99 (4.99) proj_loss: -0.6180 (-0.6180) time: 0.8969 data: 0.0004 [11-25 23:42:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 0/1669] eta: 0:24:57 tlr: 0.00015 tnm: 0.25 Lm: 6.340 (6.340) Lt: 5.554 (5.554) Accm: 4.28 (4.28) Acct: 6.68 (6.68) proj_loss: -0.6439 (-0.6439) time: 0.8970 data: 0.0004 [11-25 23:49:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 417/1669] eta: 0:20:32 tlr: 0.00015 tnm: 0.25 Lm: 6.472 (6.472) Lt: 5.648 (5.648) Accm: 3.58 (3.58) Acct: 5.73 (5.73) proj_loss: -0.6243 (-0.6243) time: 0.9211 data: 0.0002 [11-25 23:49:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 417/1669] eta: 0:20:32 tlr: 0.00015 tnm: 0.25 Lm: 6.429 (6.429) Lt: 5.653 (5.653) Accm: 3.81 (3.81) Acct: 6.20 (6.20) proj_loss: -0.6124 (-0.6124) time: 0.9211 data: 0.0002 [11-25 23:49:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 417/1669] eta: 0:20:32 tlr: 0.00015 tnm: 0.25 Lm: 6.392 (6.392) Lt: 5.612 (5.612) Accm: 3.94 (3.94) Acct: 6.25 (6.25) proj_loss: -0.6201 (-0.6201) time: 0.9211 data: 0.0003 [11-25 23:49:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 417/1669] eta: 0:20:32 tlr: 0.00015 tnm: 0.25 Lm: 6.581 (6.581) Lt: 5.847 (5.847) Accm: 3.18 (3.18) Acct: 4.99 (4.99) proj_loss: -0.6110 (-0.6110) time: 0.9211 data: 0.0002 [11-25 23:49:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 417/1669] eta: 0:20:32 tlr: 0.00015 tnm: 0.25 Lm: 6.515 (6.515) Lt: 5.759 (5.759) Accm: 3.16 (3.16) Acct: 4.96 (4.96) proj_loss: -0.5910 (-0.5910) time: 0.9211 data: 0.0002 [11-25 23:49:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 417/1669] eta: 0:20:32 tlr: 0.00015 tnm: 0.25 Lm: 6.140 (6.140) Lt: 5.369 (5.369) Accm: 4.79 (4.79) Acct: 7.15 (7.15) proj_loss: -0.6342 (-0.6342) time: 0.9211 data: 0.0003 [11-25 23:49:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 417/1669] eta: 0:20:32 tlr: 0.00015 tnm: 0.25 Lm: 6.504 (6.504) Lt: 5.721 (5.721) Accm: 3.43 (3.43) Acct: 5.17 (5.17) proj_loss: -0.6066 (-0.6066) time: 0.9211 data: 0.0003 [11-25 23:49:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 417/1669] eta: 0:20:32 tlr: 0.00015 tnm: 0.25 Lm: 6.540 (6.540) Lt: 5.807 (5.807) Accm: 3.31 (3.31) Acct: 5.11 (5.11) proj_loss: -0.6027 (-0.6027) time: 0.9211 data: 0.0003 [11-25 23:55:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 834/1669] eta: 0:13:16 tlr: 0.00015 tnm: 0.27 Lm: 6.467 (6.516) Lt: 5.720 (5.773) Accm: 3.41 (3.39) Acct: 5.41 (5.27) proj_loss: -0.6210 (-0.6112) time: 0.9242 data: 0.0003 [11-25 23:55:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 834/1669] eta: 0:13:16 tlr: 0.00015 tnm: 0.27 Lm: 6.514 (6.454) Lt: 5.769 (5.710) Accm: 3.41 (3.76) Acct: 5.41 (5.97) proj_loss: -0.6411 (-0.6298) time: 0.9242 data: 0.0002 [11-25 23:55:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 834/1669] eta: 0:13:16 tlr: 0.00015 tnm: 0.27 Lm: 6.337 (6.398) Lt: 5.565 (5.623) Accm: 3.99 (3.87) Acct: 6.40 (6.27) proj_loss: -0.6180 (-0.6153) time: 0.9242 data: 0.0003 [11-25 23:55:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 834/1669] eta: 0:13:16 tlr: 0.00015 tnm: 0.27 Lm: 6.523 (6.486) Lt: 5.751 (5.700) Accm: 3.50 (3.54) Acct: 5.65 (5.49) proj_loss: -0.5892 (-0.6037) time: 0.9242 data: 0.0003 [11-25 23:55:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 834/1669] eta: 0:13:16 tlr: 0.00015 tnm: 0.27 Lm: 6.498 (6.464) Lt: 5.732 (5.686) Accm: 3.39 (3.38) Acct: 5.23 (5.38) proj_loss: -0.6029 (-0.5950) time: 0.9242 data: 0.0003 [11-25 23:55:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 834/1669] eta: 0:13:16 tlr: 0.00015 tnm: 0.27 Lm: 6.554 (6.520) Lt: 5.812 (5.752) Accm: 3.34 (3.40) Acct: 5.27 (5.20) proj_loss: -0.6125 (-0.6085) time: 0.9242 data: 0.0003 [11-25 23:55:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 834/1669] eta: 0:13:16 tlr: 0.00015 tnm: 0.27 Lm: 6.492 (6.479) Lt: 5.722 (5.673) Accm: 3.22 (3.46) Acct: 5.03 (5.50) proj_loss: -0.6439 (-0.6353) time: 0.9242 data: 0.0003 [11-25 23:55:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [ 834/1669] eta: 0:13:16 tlr: 0.00015 tnm: 0.27 Lm: 6.161 (6.147) Lt: 5.341 (5.360) Accm: 4.60 (4.67) Acct: 6.89 (7.06) proj_loss: -0.6282 (-0.6248) time: 0.9242 data: 0.0003 [11-26 00:01:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [1251/1669] eta: 0:06:34 tlr: 0.00015 tnm: 0.25 Lm: 6.185 (6.215) Lt: 5.409 (5.414) Accm: 4.51 (4.44) Acct: 6.82 (6.72) proj_loss: -0.6171 (-0.6200) time: 0.9233 data: 0.0003 [11-26 00:01:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [1251/1669] eta: 0:06:34 tlr: 0.00015 tnm: 0.25 Lm: 6.425 (6.448) Lt: 5.639 (5.643) Accm: 3.46 (3.52) Acct: 5.56 (5.65) proj_loss: -0.6350 (-0.6330) time: 0.9233 data: 0.0002 [11-26 00:01:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [1251/1669] eta: 0:06:34 tlr: 0.00015 tnm: 0.25 Lm: 6.409 (6.399) Lt: 5.579 (5.605) Accm: 3.79 (3.67) Acct: 6.03 (5.72) proj_loss: -0.6057 (-0.6083) time: 0.9233 data: 0.0002 [11-26 00:01:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [1251/1669] eta: 0:06:34 tlr: 0.00015 tnm: 0.25 Lm: 6.478 (6.451) Lt: 5.738 (5.709) Accm: 3.48 (3.71) Acct: 5.46 (5.85) proj_loss: -0.6303 (-0.6272) time: 0.9233 data: 0.0003 [11-26 00:01:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [1251/1669] eta: 0:06:34 tlr: 0.00015 tnm: 0.25 Lm: 6.483 (6.480) Lt: 5.720 (5.711) Accm: 3.46 (3.49) Acct: 5.30 (5.29) proj_loss: -0.6152 (-0.6129) time: 0.9233 data: 0.0003 [11-26 00:01:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [1251/1669] eta: 0:06:34 tlr: 0.00015 tnm: 0.25 Lm: 6.452 (6.449) Lt: 5.702 (5.683) Accm: 3.53 (3.45) Acct: 5.42 (5.44) proj_loss: -0.6084 (-0.6039) time: 0.9233 data: 0.0002 [11-26 00:01:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [1251/1669] eta: 0:06:34 tlr: 0.00015 tnm: 0.25 Lm: 6.460 (6.466) Lt: 5.712 (5.738) Accm: 3.47 (3.49) Acct: 5.49 (5.50) proj_loss: -0.6047 (-0.6055) time: 0.9233 data: 0.0003 [11-26 00:01:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [1251/1669] eta: 0:06:34 tlr: 0.00015 tnm: 0.25 Lm: 6.433 (6.431) Lt: 5.660 (5.664) Accm: 3.82 (3.81) Acct: 5.91 (6.03) proj_loss: -0.6124 (-0.6118) time: 0.9233 data: 0.0003 [11-26 00:08:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.475 (6.440) Lt: 5.755 (5.684) Accm: 3.64 (3.76) Acct: 5.44 (5.92) proj_loss: -0.6180 (-0.6217) time: 0.9273 data: 0.0017 [11-26 00:08:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 149/350] Total time: 0:26:07 (0.939 s / it) [11-26 00:08:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.514 (6.482) Lt: 5.769 (5.744) Accm: 3.41 (3.59) Acct: 5.41 (5.62) proj_loss: -0.6194 (-0.6215) time: 0.9273 data: 0.0023 [11-26 00:08:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.407 (6.371) Lt: 5.671 (5.584) Accm: 3.67 (3.78) Acct: 5.61 (5.98) proj_loss: -0.6029 (-0.6004) time: 0.9273 data: 0.0015 [11-26 00:08:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.296 (6.366) Lt: 5.509 (5.586) Accm: 3.74 (3.69) Acct: 6.23 (5.82) proj_loss: -0.6156 (-0.6098) time: 0.9273 data: 0.0014 [11-26 00:08:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.433 (6.445) Lt: 5.646 (5.644) Accm: 3.61 (3.54) Acct: 6.10 (5.76) proj_loss: -0.6261 (-0.6314) time: 0.9273 data: 0.0018 [11-26 00:08:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.209 (6.230) Lt: 5.477 (5.428) Accm: 4.41 (4.37) Acct: 6.75 (6.68) proj_loss: -0.6282 (-0.6260) time: 0.9273 data: 0.0023 [11-26 00:08:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.412 (6.466) Lt: 5.676 (5.704) Accm: 3.54 (3.50) Acct: 5.34 (5.39) proj_loss: -0.6125 (-0.6122) time: 0.9273 data: 0.0018 [11-26 00:08:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 149/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.457 (6.464) Lt: 5.704 (5.717) Accm: 3.41 (3.45) Acct: 5.51 (5.50) proj_loss: -0.5986 (-0.6041) time: 0.9273 data: 0.0015 [11-26 00:08:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 149/350] Total time: 0:26:07 (0.939 s / it) [11-26 00:08:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 149/350] Total time: 0:26:07 (0.939 s / it) [11-26 00:08:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 149/350] Total time: 0:26:07 (0.939 s / it) [11-26 00:08:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 149/350] Total time: 0:26:07 (0.939 s / it) [11-26 00:08:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 149/350] Total time: 0:26:07 (0.939 s / it) [11-26 00:08:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 149/350] Total time: 0:26:07 (0.939 s / it) [11-26 00:08:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 149/350] Total time: 0:26:07 (0.939 s / it) [11-26 00:10:31] (home/user/VAR/trainer.py, line 114)=> FID: 3.4460273188096266 [11-26 00:10:32] (/home/user/VAR/train.py , line 259)=> [*] [ep149] (val 50000) Lm: 6.4342, Lt: 5.6773, Acc m&t: 3.57 5.59, Val cost: 128.31s [11-26 00:10:32] (/home/user/VAR/train.py , line 264)=> [saving ckpt] ... [saving ckpt](*) finished! @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth [11-26 00:11:52] (/home/user/VAR/train.py , line 276)=> [ep149] (training ) Lm: 6.434 (6.434), Lt: 5.677 (5.677), Acc m&t: 3.57 5.59, Remain: 3 days, 14:29:36, Finish: 2024-11-28 22:37 [11-26 00:11:52] (/home/user/VAR/train.py , line 276)=> [ep149] (training ) Lm: 6.434 (6.434), Lt: 5.677 (5.677), Acc m&t: 3.57 5.59, Remain: 3 days, 14:31:30, Finish: 2024-11-28 22:39 [11-26 00:11:52] (/home/user/VAR/train.py , line 276)=> [ep149] (training ) Lm: 6.434 (6.434), Lt: 5.677 (5.677), Acc m&t: 3.57 5.59, Remain: 3 days, 14:31:35, Finish: 2024-11-28 22:39 [11-26 00:11:52] (/home/user/VAR/train.py , line 276)=> [ep149] (training ) Lm: 6.434 (6.434), Lt: 5.677 (5.677), Acc m&t: 3.57 5.59, Remain: 3 days, 14:30:53, Finish: 2024-11-28 22:39 [11-26 00:11:52] (/home/user/VAR/train.py , line 276)=> [ep149] (training ) Lm: 6.434 (6.434), Lt: 5.677 (5.677), Acc m&t: 3.57 5.59, Remain: 3 days, 14:31:43, Finish: 2024-11-28 22:40 [11-26 00:11:52] (/home/user/VAR/train.py , line 276)=> [ep149] (training ) Lm: 6.434 (6.434), Lt: 5.677 (5.677), Acc m&t: 3.57 5.59, Remain: 3 days, 14:32:21, Finish: 2024-11-28 22:40 [11-26 00:11:52] (/home/user/VAR/train.py , line 276)=> [ep149] (training ) Lm: 6.434 (6.434), Lt: 5.677 (5.677), Acc m&t: 3.57 5.59, Remain: 3 days, 14:30:15, Finish: 2024-11-28 22:38 [11-26 00:11:52] (/home/user/VAR/train.py , line 276)=> [ep149] (training ) Lm: 6.434 (6.434), Lt: 5.677 (5.677), Acc m&t: 3.57 5.59, Remain: 3 days, 14:31:27, Finish: 2024-11-28 22:39 [11-26 00:11:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 0/1669] eta: 0:25:14 tlr: 0.00015 tnm: 0.25 Lm: 6.247 (6.247) Lt: 5.455 (5.455) Accm: 4.21 (4.21) Acct: 6.82 (6.82) proj_loss: -0.6082 (-0.6082) time: 0.9077 data: 0.0003 [11-26 00:11:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 0/1669] eta: 0:25:13 tlr: 0.00015 tnm: 0.25 Lm: 6.692 (6.692) Lt: 5.993 (5.993) Accm: 2.65 (2.65) Acct: 4.17 (4.17) proj_loss: -0.6162 (-0.6162) time: 0.9070 data: 0.0003 [11-26 00:11:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 0/1669] eta: 0:25:14 tlr: 0.00015 tnm: 0.25 Lm: 6.650 (6.650) Lt: 5.993 (5.993) Accm: 2.80 (2.80) Acct: 4.34 (4.34) proj_loss: -0.6325 (-0.6325) time: 0.9075 data: 0.0004 [11-26 00:11:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 0/1669] eta: 0:26:05 tlr: 0.00015 tnm: 0.25 Lm: 6.378 (6.378) Lt: 5.631 (5.631) Accm: 3.61 (3.61) Acct: 5.68 (5.68) proj_loss: -0.6172 (-0.6172) time: 0.9381 data: 0.0003 [11-26 00:11:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 0/1669] eta: 0:25:14 tlr: 0.00015 tnm: 0.25 Lm: 6.418 (6.418) Lt: 5.728 (5.728) Accm: 3.51 (3.51) Acct: 5.34 (5.34) proj_loss: -0.6236 (-0.6236) time: 0.9075 data: 0.0004 [11-26 00:11:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 0/1669] eta: 0:25:15 tlr: 0.00015 tnm: 0.25 Lm: 6.372 (6.372) Lt: 5.520 (5.520) Accm: 3.57 (3.57) Acct: 5.75 (5.75) proj_loss: -0.6127 (-0.6127) time: 0.9080 data: 0.0003 [11-26 00:11:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 0/1669] eta: 0:25:15 tlr: 0.00015 tnm: 0.25 Lm: 6.345 (6.345) Lt: 5.628 (5.628) Accm: 3.93 (3.93) Acct: 6.16 (6.16) proj_loss: -0.6230 (-0.6230) time: 0.9082 data: 0.0004 [11-26 00:11:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 0/1669] eta: 0:25:14 tlr: 0.00015 tnm: 0.25 Lm: 6.426 (6.426) Lt: 5.705 (5.705) Accm: 3.15 (3.15) Acct: 4.48 (4.48) proj_loss: -0.6271 (-0.6271) time: 0.9072 data: 0.0004 [11-26 00:18:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.26 Lm: 6.446 (6.446) Lt: 5.708 (5.708) Accm: 3.15 (3.15) Acct: 4.61 (4.61) proj_loss: -0.6117 (-0.6117) time: 0.9242 data: 0.0003 [11-26 00:18:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.26 Lm: 6.540 (6.540) Lt: 5.804 (5.804) Accm: 3.28 (3.28) Acct: 5.03 (5.03) proj_loss: -0.6179 (-0.6179) time: 0.9242 data: 0.0003 [11-26 00:18:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.26 Lm: 6.474 (6.474) Lt: 5.700 (5.700) Accm: 3.42 (3.42) Acct: 5.25 (5.25) proj_loss: -0.6057 (-0.6057) time: 0.9242 data: 0.0002 [11-26 00:18:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.26 Lm: 6.386 (6.386) Lt: 5.632 (5.632) Accm: 3.60 (3.60) Acct: 5.60 (5.60) proj_loss: -0.6193 (-0.6193) time: 0.9242 data: 0.0002 [11-26 00:18:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.26 Lm: 6.571 (6.571) Lt: 5.805 (5.805) Accm: 2.94 (2.94) Acct: 4.86 (4.86) proj_loss: -0.6196 (-0.6196) time: 0.9242 data: 0.0002 [11-26 00:18:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.26 Lm: 6.123 (6.123) Lt: 5.281 (5.281) Accm: 4.70 (4.70) Acct: 7.73 (7.73) proj_loss: -0.5864 (-0.5864) time: 0.9242 data: 0.0002 [11-26 00:18:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.26 Lm: 6.331 (6.331) Lt: 5.529 (5.529) Accm: 3.70 (3.70) Acct: 5.85 (5.85) proj_loss: -0.6167 (-0.6167) time: 0.9242 data: 0.0003 [11-26 00:18:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.26 Lm: 6.473 (6.473) Lt: 5.722 (5.722) Accm: 3.31 (3.31) Acct: 5.23 (5.23) proj_loss: -0.5981 (-0.5981) time: 0.9242 data: 0.0003 [11-26 00:24:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.601 (6.541) Lt: 5.816 (5.810) Accm: 2.70 (3.10) Acct: 4.30 (4.79) proj_loss: -0.6230 (-0.6097) time: 0.9245 data: 0.0003 [11-26 00:24:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.469 (6.472) Lt: 5.768 (5.733) Accm: 3.23 (3.34) Acct: 4.82 (5.06) proj_loss: -0.6172 (-0.6171) time: 0.9245 data: 0.0002 [11-26 00:24:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.521 (6.534) Lt: 5.677 (5.762) Accm: 3.22 (3.26) Acct: 5.06 (5.04) proj_loss: -0.6195 (-0.6186) time: 0.9245 data: 0.0003 [11-26 00:24:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.542 (6.562) Lt: 5.826 (5.812) Accm: 2.80 (2.88) Acct: 4.34 (4.58) proj_loss: -0.6263 (-0.6218) time: 0.9245 data: 0.0003 [11-26 00:24:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.247 (6.214) Lt: 5.455 (5.408) Accm: 4.21 (4.36) Acct: 6.82 (7.00) proj_loss: -0.5915 (-0.5881) time: 0.9245 data: 0.0002 [11-26 00:24:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.326 (6.330) Lt: 5.537 (5.550) Accm: 3.83 (3.90) Acct: 5.96 (6.14) proj_loss: -0.6207 (-0.6215) time: 0.9245 data: 0.0002 [11-26 00:24:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.355 (6.315) Lt: 5.536 (5.541) Accm: 3.69 (3.99) Acct: 5.85 (6.13) proj_loss: -0.6151 (-0.6156) time: 0.9245 data: 0.0002 [11-26 00:24:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.25 Lm: 6.465 (6.471) Lt: 5.711 (5.754) Accm: 3.16 (3.18) Acct: 4.75 (4.68) proj_loss: -0.6224 (-0.6153) time: 0.9245 data: 0.0003 [11-26 00:31:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.477 (6.475) Lt: 5.731 (5.753) Accm: 3.19 (3.25) Acct: 4.79 (4.82) proj_loss: -0.6248 (-0.6210) time: 0.9251 data: 0.0003 [11-26 00:31:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.474 (6.474) Lt: 5.733 (5.724) Accm: 3.38 (3.38) Acct: 5.25 (5.29) proj_loss: -0.6057 (-0.6066) time: 0.9251 data: 0.0002 [11-26 00:31:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.321 (6.297) Lt: 5.559 (5.517) Accm: 3.94 (4.06) Acct: 6.18 (6.53) proj_loss: -0.5999 (-0.5975) time: 0.9251 data: 0.0002 [11-26 00:31:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.518 (6.538) Lt: 5.781 (5.793) Accm: 2.94 (2.97) Acct: 4.75 (4.73) proj_loss: -0.6253 (-0.6225) time: 0.9251 data: 0.0003 [11-26 00:31:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.349 (6.345) Lt: 5.548 (5.553) Accm: 3.86 (3.90) Acct: 6.11 (6.17) proj_loss: -0.6167 (-0.6149) time: 0.9251 data: 0.0002 [11-26 00:31:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.386 (6.348) Lt: 5.628 (5.586) Accm: 3.75 (3.95) Acct: 5.73 (6.00) proj_loss: -0.6193 (-0.6178) time: 0.9251 data: 0.0003 [11-26 00:31:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.533 (6.537) Lt: 5.698 (5.751) Accm: 3.12 (3.20) Acct: 5.10 (5.06) proj_loss: -0.6179 (-0.6103) time: 0.9251 data: 0.0003 [11-26 00:31:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.473 (6.433) Lt: 5.722 (5.673) Accm: 3.31 (3.43) Acct: 5.23 (5.38) proj_loss: -0.6197 (-0.6114) time: 0.9251 data: 0.0003 [11-26 00:37:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.471 (6.441) Lt: 5.700 (5.678) Accm: 3.37 (3.42) Acct: 5.54 (5.41) proj_loss: -0.6165 (-0.6028) time: 0.9269 data: 0.0018 [11-26 00:37:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 150/350] Total time: 0:25:42 (0.924 s / it) [11-26 00:37:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.545 (6.557) Lt: 5.718 (5.779) Accm: 3.22 (3.23) Acct: 5.13 (5.10) proj_loss: -0.6195 (-0.6157) time: 0.9269 data: 0.0019 [11-26 00:37:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.395 (6.324) Lt: 5.635 (5.541) Accm: 3.67 (3.95) Acct: 5.54 (6.28) proj_loss: -0.5942 (-0.5968) time: 0.9269 data: 0.0015 [11-26 00:37:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.493 (6.518) Lt: 5.736 (5.771) Accm: 3.07 (3.14) Acct: 5.17 (4.96) proj_loss: -0.6263 (-0.6235) time: 0.9269 data: 0.0015 [11-26 00:37:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.469 (6.460) Lt: 5.698 (5.713) Accm: 3.53 (3.51) Acct: 5.68 (5.45) proj_loss: -0.6172 (-0.6101) time: 0.9269 data: 0.0014 [11-26 00:37:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.465 (6.416) Lt: 5.711 (5.688) Accm: 3.22 (3.56) Acct: 4.82 (5.31) proj_loss: -0.6224 (-0.6192) time: 0.9269 data: 0.0022 [11-26 00:37:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.418 (6.410) Lt: 5.720 (5.656) Accm: 3.69 (3.74) Acct: 5.61 (5.72) proj_loss: -0.6212 (-0.6185) time: 0.9269 data: 0.0019 [11-26 00:37:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.372 (6.352) Lt: 5.559 (5.554) Accm: 3.88 (3.90) Acct: 5.99 (6.14) proj_loss: -0.6169 (-0.6153) time: 0.9269 data: 0.0018 [11-26 00:37:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 150/350] Total time: 0:25:42 (0.924 s / it) [11-26 00:37:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 150/350] Total time: 0:25:42 (0.924 s / it) [11-26 00:37:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 150/350] Total time: 0:25:42 (0.924 s / it) [11-26 00:37:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 150/350] Total time: 0:25:42 (0.924 s / it) [11-26 00:37:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 150/350] Total time: 0:25:42 (0.924 s / it) [11-26 00:37:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 150/350] Total time: 0:25:42 (0.924 s / it) [11-26 00:37:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 150/350] Total time: 0:25:42 (0.924 s / it) [11-26 00:37:34] (/home/user/VAR/train.py , line 276)=> [ep150] (training ) Lm: 6.434 (6.436), Lt: 5.677 (5.677), Acc m&t: 3.57 5.59, Remain: 3 days, 13:55:16, Finish: 2024-11-28 22:32 [11-26 00:37:34] (/home/user/VAR/train.py , line 276)=> [ep150] (training ) Lm: 6.434 (6.436), Lt: 5.677 (5.677), Acc m&t: 3.57 5.59, Remain: 3 days, 13:55:54, Finish: 2024-11-28 22:33 [11-26 00:37:34] (/home/user/VAR/train.py , line 276)=> [ep150] (training ) Lm: 6.434 (6.436), Lt: 5.677 (5.677), Acc m&t: 3.57 5.59, Remain: 3 days, 13:55:34, Finish: 2024-11-28 22:33 [11-26 00:37:34] (/home/user/VAR/train.py , line 276)=> [ep150] (training ) Lm: 6.434 (6.436), Lt: 5.677 (5.677), Acc m&t: 3.57 5.59, Remain: 3 days, 13:55:56, Finish: 2024-11-28 22:33 [11-26 00:37:34] (/home/user/VAR/train.py , line 276)=> [ep150] (training ) Lm: 6.434 (6.436), Lt: 5.677 (5.677), Acc m&t: 3.57 5.59, Remain: 3 days, 13:54:56, Finish: 2024-11-28 22:32 [11-26 00:37:34] (/home/user/VAR/train.py , line 276)=> [ep150] (training ) Lm: 6.434 (6.436), Lt: 5.677 (5.677), Acc m&t: 3.57 5.59, Remain: 3 days, 13:54:32, Finish: 2024-11-28 22:32 [11-26 00:37:34] (/home/user/VAR/train.py , line 276)=> [ep150] (training ) Lm: 6.434 (6.436), Lt: 5.677 (5.677), Acc m&t: 3.57 5.59, Remain: 3 days, 13:55:39, Finish: 2024-11-28 22:33 [11-26 00:37:34] (/home/user/VAR/train.py , line 276)=> [ep150] (training ) Lm: 6.434 (6.436), Lt: 5.677 (5.677), Acc m&t: 3.57 5.59, Remain: 3 days, 13:56:40, Finish: 2024-11-28 22:34 [11-26 00:37:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 0/1669] eta: 0:25:29 tlr: 0.00015 tnm: 0.26 Lm: 6.311 (6.311) Lt: 5.493 (5.493) Accm: 3.96 (3.96) Acct: 5.85 (5.85) proj_loss: -0.5920 (-0.5920) time: 0.9165 data: 0.0004 [11-26 00:37:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 0/1669] eta: 0:25:30 tlr: 0.00015 tnm: 0.26 Lm: 6.366 (6.366) Lt: 5.589 (5.589) Accm: 3.99 (3.99) Acct: 6.10 (6.10) proj_loss: -0.6155 (-0.6155) time: 0.9172 data: 0.0003 [11-26 00:37:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 0/1669] eta: 0:25:30 tlr: 0.00015 tnm: 0.26 Lm: 6.444 (6.444) Lt: 5.761 (5.761) Accm: 3.41 (3.41) Acct: 5.41 (5.41) proj_loss: -0.6055 (-0.6055) time: 0.9170 data: 0.0004 [11-26 00:37:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 0/1669] eta: 0:25:30 tlr: 0.00015 tnm: 0.26 Lm: 6.331 (6.331) Lt: 5.548 (5.548) Accm: 3.92 (3.92) Acct: 6.30 (6.30) proj_loss: -0.6336 (-0.6336) time: 0.9167 data: 0.0004 [11-26 00:37:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 0/1669] eta: 0:25:32 tlr: 0.00015 tnm: 0.26 Lm: 6.700 (6.700) Lt: 5.996 (5.996) Accm: 2.62 (2.62) Acct: 3.75 (3.75) proj_loss: -0.5862 (-0.5862) time: 0.9185 data: 0.0004 [11-26 00:37:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 0/1669] eta: 0:25:31 tlr: 0.00015 tnm: 0.26 Lm: 6.538 (6.538) Lt: 5.873 (5.873) Accm: 3.16 (3.16) Acct: 4.65 (4.65) proj_loss: -0.5993 (-0.5993) time: 0.9174 data: 0.0004 [11-26 00:37:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 0/1669] eta: 0:25:31 tlr: 0.00015 tnm: 0.26 Lm: 6.398 (6.398) Lt: 5.676 (5.676) Accm: 3.85 (3.85) Acct: 5.75 (5.75) proj_loss: -0.5985 (-0.5985) time: 0.9174 data: 0.0004 [11-26 00:37:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 0/1669] eta: 0:25:31 tlr: 0.00015 tnm: 0.26 Lm: 6.374 (6.374) Lt: 5.570 (5.570) Accm: 3.79 (3.79) Acct: 6.03 (6.03) proj_loss: -0.6194 (-0.6194) time: 0.9177 data: 0.0003 [11-26 00:44:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.24 Lm: 6.557 (6.557) Lt: 5.782 (5.782) Accm: 3.20 (3.20) Acct: 5.11 (5.11) proj_loss: -0.6085 (-0.6085) time: 0.9255 data: 0.0002 [11-26 00:44:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.24 Lm: 6.457 (6.457) Lt: 5.693 (5.693) Accm: 3.53 (3.53) Acct: 5.49 (5.49) proj_loss: -0.6211 (-0.6211) time: 0.9255 data: 0.0002 [11-26 00:44:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.24 Lm: 6.391 (6.391) Lt: 5.620 (5.620) Accm: 3.52 (3.52) Acct: 5.61 (5.61) proj_loss: -0.6280 (-0.6280) time: 0.9255 data: 0.0003 [11-26 00:44:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.24 Lm: 6.315 (6.315) Lt: 5.487 (5.487) Accm: 3.98 (3.98) Acct: 6.30 (6.30) proj_loss: -0.6201 (-0.6201) time: 0.9255 data: 0.0003 [11-26 00:44:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.24 Lm: 6.529 (6.529) Lt: 5.839 (5.839) Accm: 3.33 (3.33) Acct: 4.91 (4.91) proj_loss: -0.6225 (-0.6225) time: 0.9255 data: 0.0003 [11-26 00:44:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.24 Lm: 6.493 (6.493) Lt: 5.770 (5.770) Accm: 3.46 (3.46) Acct: 5.25 (5.25) proj_loss: -0.6238 (-0.6238) time: 0.9255 data: 0.0002 [11-26 00:44:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.24 Lm: 6.559 (6.559) Lt: 5.819 (5.819) Accm: 3.21 (3.21) Acct: 4.94 (4.94) proj_loss: -0.6051 (-0.6051) time: 0.9255 data: 0.0003 [11-26 00:44:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.24 Lm: 6.428 (6.428) Lt: 5.724 (5.724) Accm: 3.69 (3.69) Acct: 5.94 (5.94) proj_loss: -0.6168 (-0.6168) time: 0.9256 data: 0.0003 [11-26 00:50:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 834/1669] eta: 0:12:58 tlr: 0.00015 tnm: 0.26 Lm: 6.444 (6.539) Lt: 5.761 (5.814) Accm: 3.41 (3.35) Acct: 5.41 (5.42) proj_loss: -0.6127 (-0.6154) time: 0.9231 data: 0.0003 [11-26 00:50:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 834/1669] eta: 0:12:58 tlr: 0.00015 tnm: 0.26 Lm: 6.538 (6.533) Lt: 5.840 (5.839) Accm: 3.18 (3.28) Acct: 5.03 (4.95) proj_loss: -0.6056 (-0.6169) time: 0.9231 data: 0.0002 [11-26 00:50:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 834/1669] eta: 0:12:58 tlr: 0.00015 tnm: 0.26 Lm: 6.374 (6.479) Lt: 5.570 (5.665) Accm: 3.79 (3.43) Acct: 6.03 (5.65) proj_loss: -0.6189 (-0.6120) time: 0.9231 data: 0.0003 [11-26 00:50:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 834/1669] eta: 0:12:58 tlr: 0.00015 tnm: 0.26 Lm: 6.317 (6.410) Lt: 5.572 (5.653) Accm: 3.77 (3.61) Acct: 5.85 (5.74) proj_loss: -0.6222 (-0.6215) time: 0.9231 data: 0.0002 [11-26 00:50:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 834/1669] eta: 0:12:58 tlr: 0.00015 tnm: 0.26 Lm: 6.331 (6.356) Lt: 5.548 (5.581) Accm: 3.92 (3.83) Acct: 6.30 (6.04) proj_loss: -0.6336 (-0.6325) time: 0.9231 data: 0.0003 [11-26 00:50:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 834/1669] eta: 0:12:58 tlr: 0.00015 tnm: 0.26 Lm: 6.366 (6.352) Lt: 5.589 (5.553) Accm: 3.96 (3.76) Acct: 6.10 (5.93) proj_loss: -0.6246 (-0.6315) time: 0.9231 data: 0.0003 [11-26 00:50:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 834/1669] eta: 0:12:58 tlr: 0.00015 tnm: 0.26 Lm: 6.417 (6.461) Lt: 5.641 (5.736) Accm: 3.80 (3.52) Acct: 6.13 (5.51) proj_loss: -0.6231 (-0.6111) time: 0.9231 data: 0.0003 [11-26 00:50:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 834/1669] eta: 0:12:58 tlr: 0.00015 tnm: 0.26 Lm: 6.537 (6.508) Lt: 5.754 (5.764) Accm: 3.21 (3.38) Acct: 4.75 (5.08) proj_loss: -0.5985 (-0.6058) time: 0.9231 data: 0.0003 [11-26 00:57:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1251/1669] eta: 0:06:30 tlr: 0.00015 tnm: 0.26 Lm: 6.468 (6.448) Lt: 5.715 (5.709) Accm: 3.53 (3.61) Acct: 5.25 (5.50) proj_loss: -0.6138 (-0.6116) time: 1.0418 data: 0.0003 [11-26 00:57:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1251/1669] eta: 0:06:30 tlr: 0.00015 tnm: 0.26 Lm: 6.529 (6.432) Lt: 5.822 (5.723) Accm: 3.34 (3.54) Acct: 5.10 (5.51) proj_loss: -0.6155 (-0.6190) time: 1.0418 data: 0.0002 [11-26 00:57:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1251/1669] eta: 0:06:30 tlr: 0.00015 tnm: 0.26 Lm: 6.391 (6.462) Lt: 5.615 (5.664) Accm: 3.67 (3.46) Acct: 5.75 (5.60) proj_loss: -0.6191 (-0.6153) time: 1.0418 data: 0.0003 [11-26 00:57:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1251/1669] eta: 0:06:30 tlr: 0.00015 tnm: 0.26 Lm: 6.493 (6.540) Lt: 5.813 (5.827) Accm: 3.37 (3.34) Acct: 5.35 (5.39) proj_loss: -0.6204 (-0.6224) time: 1.0418 data: 0.0003 [11-26 00:57:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1251/1669] eta: 0:06:30 tlr: 0.00015 tnm: 0.26 Lm: 6.395 (6.419) Lt: 5.637 (5.636) Accm: 3.65 (3.53) Acct: 5.65 (5.53) proj_loss: -0.6201 (-0.6163) time: 1.0418 data: 0.0003 [11-26 00:57:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1251/1669] eta: 0:06:30 tlr: 0.00015 tnm: 0.26 Lm: 6.314 (6.368) Lt: 5.533 (5.608) Accm: 3.85 (3.69) Acct: 5.99 (5.84) proj_loss: -0.6290 (-0.6251) time: 1.0418 data: 0.0003 [11-26 00:57:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1251/1669] eta: 0:06:30 tlr: 0.00015 tnm: 0.26 Lm: 6.391 (6.383) Lt: 5.620 (5.635) Accm: 3.64 (3.71) Acct: 5.70 (5.80) proj_loss: -0.6280 (-0.6290) time: 1.0418 data: 0.0003 [11-26 00:57:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1251/1669] eta: 0:06:30 tlr: 0.00015 tnm: 0.26 Lm: 6.516 (6.499) Lt: 5.769 (5.777) Accm: 3.49 (3.43) Acct: 5.49 (5.35) proj_loss: -0.6169 (-0.6110) time: 1.0418 data: 0.0003 [11-26 01:03:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.614 (6.565) Lt: 5.898 (5.854) Accm: 3.18 (3.19) Acct: 4.86 (4.93) proj_loss: -0.6106 (-0.6108) time: 0.9251 data: 0.0018 [11-26 01:03:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.537 (6.472) Lt: 5.754 (5.733) Accm: 3.21 (3.46) Acct: 4.75 (5.30) proj_loss: -0.6102 (-0.6113) time: 0.9251 data: 0.0015 [11-26 01:03:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.520 (6.423) Lt: 5.805 (5.732) Accm: 3.50 (3.56) Acct: 5.17 (5.49) proj_loss: -0.6254 (-0.6218) time: 0.9251 data: 0.0015 [11-26 01:03:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.408 (6.496) Lt: 5.660 (5.699) Accm: 3.55 (3.39) Acct: 5.48 (5.48) proj_loss: -0.6189 (-0.6145) time: 0.9251 data: 0.0016 [11-26 01:03:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 151/350] Total time: 0:25:56 (0.933 s / it) [11-26 01:03:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.366 (6.388) Lt: 5.589 (5.607) Accm: 3.96 (3.63) Acct: 6.10 (5.68) proj_loss: -0.6246 (-0.6195) time: 0.9251 data: 0.0016 [11-26 01:03:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.489 (6.530) Lt: 5.761 (5.812) Accm: 3.39 (3.35) Acct: 5.30 (5.35) proj_loss: -0.6281 (-0.6261) time: 0.9251 data: 0.0015 [11-26 01:03:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.377 (6.382) Lt: 5.548 (5.614) Accm: 3.92 (3.76) Acct: 6.30 (5.91) proj_loss: -0.6224 (-0.6264) time: 0.9251 data: 0.0016 [11-26 01:03:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.317 (6.399) Lt: 5.572 (5.630) Accm: 3.77 (3.57) Acct: 5.85 (5.69) proj_loss: -0.6359 (-0.6294) time: 0.9251 data: 0.0014 [11-26 01:03:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 151/350] Total time: 0:25:56 (0.933 s / it) [11-26 01:03:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 151/350] Total time: 0:25:56 (0.933 s / it) [11-26 01:03:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 151/350] Total time: 0:25:56 (0.933 s / it) [11-26 01:03:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 151/350] Total time: 0:25:56 (0.933 s / it) [11-26 01:03:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 151/350] Total time: 0:25:56 (0.933 s / it) [11-26 01:03:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 151/350] Total time: 0:25:56 (0.933 s / it) [11-26 01:03:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 151/350] Total time: 0:25:56 (0.933 s / it) [11-26 01:03:31] (/home/user/VAR/train.py , line 276)=> [ep151] (training ) Lm: 6.434 (6.440), Lt: 5.677 (5.682), Acc m&t: 3.57 5.59, Remain: 3 days, 13:28:59, Finish: 2024-11-28 22:32 [11-26 01:03:31] (/home/user/VAR/train.py , line 276)=> [ep151] (training ) Lm: 6.434 (6.440), Lt: 5.677 (5.682), Acc m&t: 3.57 5.59, Remain: 3 days, 13:27:07, Finish: 2024-11-28 22:30 [11-26 01:03:31] (/home/user/VAR/train.py , line 276)=> [ep151] (training ) Lm: 6.434 (6.440), Lt: 5.677 (5.682), Acc m&t: 3.57 5.59, Remain: 3 days, 13:27:04, Finish: 2024-11-28 22:30 [11-26 01:03:31] (/home/user/VAR/train.py , line 276)=> [ep151] (training ) Lm: 6.434 (6.440), Lt: 5.677 (5.682), Acc m&t: 3.57 5.59, Remain: 3 days, 13:27:08, Finish: 2024-11-28 22:30 [11-26 01:03:31] (/home/user/VAR/train.py , line 276)=> [ep151] (training ) Lm: 6.434 (6.440), Lt: 5.677 (5.682), Acc m&t: 3.57 5.59, Remain: 3 days, 13:26:13, Finish: 2024-11-28 22:29 [11-26 01:03:31] (/home/user/VAR/train.py , line 276)=> [ep151] (training ) Lm: 6.434 (6.440), Lt: 5.677 (5.682), Acc m&t: 3.57 5.59, Remain: 3 days, 13:26:59, Finish: 2024-11-28 22:30 [11-26 01:03:31] (/home/user/VAR/train.py , line 276)=> [ep151] (training ) Lm: 6.434 (6.440), Lt: 5.677 (5.682), Acc m&t: 3.57 5.59, Remain: 3 days, 13:26:25, Finish: 2024-11-28 22:29 [11-26 01:03:31] (/home/user/VAR/train.py , line 276)=> [ep151] (training ) Lm: 6.434 (6.440), Lt: 5.677 (5.682), Acc m&t: 3.57 5.59, Remain: 3 days, 13:26:08, Finish: 2024-11-28 22:29 [11-26 01:03:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 0/1669] eta: 0:25:06 tlr: 0.00015 tnm: 0.25 Lm: 6.423 (6.423) Lt: 5.629 (5.629) Accm: 3.79 (3.79) Acct: 6.16 (6.16) proj_loss: -0.6137 (-0.6137) time: 0.9028 data: 0.0003 [11-26 01:03:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 0/1669] eta: 0:25:06 tlr: 0.00015 tnm: 0.25 Lm: 6.484 (6.484) Lt: 5.751 (5.751) Accm: 3.21 (3.21) Acct: 5.17 (5.17) proj_loss: -0.6190 (-0.6190) time: 0.9025 data: 0.0004 [11-26 01:03:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 0/1669] eta: 0:25:06 tlr: 0.00015 tnm: 0.25 Lm: 6.661 (6.661) Lt: 5.997 (5.997) Accm: 2.84 (2.84) Acct: 4.34 (4.34) proj_loss: -0.6402 (-0.6402) time: 0.9025 data: 0.0004 [11-26 01:03:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 0/1669] eta: 0:25:06 tlr: 0.00015 tnm: 0.25 Lm: 6.647 (6.647) Lt: 5.932 (5.932) Accm: 2.88 (2.88) Acct: 4.58 (4.58) proj_loss: -0.6219 (-0.6219) time: 0.9025 data: 0.0004 [11-26 01:03:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 0/1669] eta: 0:25:06 tlr: 0.00015 tnm: 0.25 Lm: 6.281 (6.281) Lt: 5.510 (5.510) Accm: 4.33 (4.33) Acct: 7.09 (7.09) proj_loss: -0.6276 (-0.6276) time: 0.9028 data: 0.0004 [11-26 01:03:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 0/1669] eta: 0:25:06 tlr: 0.00015 tnm: 0.25 Lm: 6.564 (6.564) Lt: 5.823 (5.823) Accm: 3.15 (3.15) Acct: 4.92 (4.92) proj_loss: -0.6548 (-0.6548) time: 0.9026 data: 0.0004 [11-26 01:03:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 0/1669] eta: 0:25:06 tlr: 0.00015 tnm: 0.25 Lm: 6.247 (6.247) Lt: 5.460 (5.460) Accm: 4.40 (4.40) Acct: 6.61 (6.61) proj_loss: -0.6104 (-0.6104) time: 0.9025 data: 0.0003 [11-26 01:03:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 0/1669] eta: 0:25:01 tlr: 0.00015 tnm: 0.25 Lm: 6.347 (6.347) Lt: 5.633 (5.633) Accm: 4.14 (4.14) Acct: 6.34 (6.34) proj_loss: -0.6035 (-0.6035) time: 0.8997 data: 0.0005 [11-26 01:09:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 417/1669] eta: 0:19:16 tlr: 0.00015 tnm: 0.25 Lm: 6.290 (6.290) Lt: 5.525 (5.525) Accm: 4.09 (4.09) Acct: 6.30 (6.30) proj_loss: -0.6077 (-0.6077) time: 0.9240 data: 0.0003 [11-26 01:09:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.442 (6.442) Lt: 5.715 (5.715) Accm: 3.70 (3.70) Acct: 5.58 (5.58) proj_loss: -0.6121 (-0.6121) time: 0.9240 data: 0.0003 [11-26 01:09:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.440 (6.440) Lt: 5.667 (5.667) Accm: 3.59 (3.59) Acct: 5.87 (5.87) proj_loss: -0.6169 (-0.6169) time: 0.9240 data: 0.0002 [11-26 01:09:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.327 (6.327) Lt: 5.578 (5.578) Accm: 4.04 (4.04) Acct: 6.32 (6.32) proj_loss: -0.6216 (-0.6216) time: 0.9240 data: 0.0002 [11-26 01:09:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.375 (6.375) Lt: 5.607 (5.607) Accm: 3.67 (3.67) Acct: 5.58 (5.58) proj_loss: -0.6353 (-0.6353) time: 0.9240 data: 0.0002 [11-26 01:09:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.584 (6.584) Lt: 5.834 (5.834) Accm: 3.15 (3.15) Acct: 4.99 (4.99) proj_loss: -0.6184 (-0.6184) time: 0.9240 data: 0.0003 [11-26 01:09:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.513 (6.513) Lt: 5.830 (5.830) Accm: 3.26 (3.26) Acct: 5.11 (5.11) proj_loss: -0.6409 (-0.6409) time: 0.9240 data: 0.0003 [11-26 01:09:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 417/1669] eta: 0:19:17 tlr: 0.00015 tnm: 0.25 Lm: 6.395 (6.395) Lt: 5.657 (5.657) Accm: 3.84 (3.84) Acct: 5.84 (5.84) proj_loss: -0.6194 (-0.6194) time: 0.9240 data: 0.0003 [11-26 01:16:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.26 Lm: 6.542 (6.449) Lt: 5.855 (5.725) Accm: 3.88 (3.85) Acct: 5.92 (5.87) proj_loss: -0.6273 (-0.6220) time: 0.9242 data: 0.0003 [11-26 01:16:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.26 Lm: 6.564 (6.448) Lt: 5.823 (5.683) Accm: 3.15 (3.41) Acct: 4.92 (5.28) proj_loss: -0.6158 (-0.6233) time: 0.9242 data: 0.0003 [11-26 01:16:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.26 Lm: 6.520 (6.486) Lt: 5.735 (5.753) Accm: 3.42 (3.38) Acct: 5.41 (5.19) proj_loss: -0.6149 (-0.6147) time: 0.9242 data: 0.0003 [11-26 01:16:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.26 Lm: 6.395 (6.378) Lt: 5.584 (5.608) Accm: 3.98 (3.87) Acct: 6.58 (6.28) proj_loss: -0.6190 (-0.6306) time: 0.9242 data: 0.0003 [11-26 01:16:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.26 Lm: 6.423 (6.340) Lt: 5.629 (5.591) Accm: 3.79 (4.18) Acct: 6.16 (6.11) proj_loss: -0.6136 (-0.6126) time: 0.9242 data: 0.0003 [11-26 01:16:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.26 Lm: 6.331 (6.329) Lt: 5.528 (5.561) Accm: 3.74 (3.94) Acct: 6.23 (6.29) proj_loss: -0.6157 (-0.6186) time: 0.9242 data: 0.0002 [11-26 01:16:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.26 Lm: 6.425 (6.483) Lt: 5.699 (5.786) Accm: 3.38 (3.30) Acct: 5.27 (5.17) proj_loss: -0.6402 (-0.6351) time: 0.9242 data: 0.0003 [11-26 01:16:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 834/1669] eta: 0:12:51 tlr: 0.00015 tnm: 0.26 Lm: 6.235 (6.272) Lt: 5.478 (5.509) Accm: 4.14 (4.20) Acct: 6.34 (6.40) proj_loss: -0.6118 (-0.6140) time: 0.9242 data: 0.0003 [11-26 01:22:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.291 (6.327) Lt: 5.555 (5.587) Accm: 4.09 (3.89) Acct: 6.30 (5.90) proj_loss: -0.6193 (-0.6198) time: 0.9256 data: 0.0003 [11-26 01:22:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.508 (6.489) Lt: 5.718 (5.740) Accm: 3.30 (3.33) Acct: 5.17 (5.12) proj_loss: -0.6184 (-0.6202) time: 0.9256 data: 0.0003 [11-26 01:22:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.424 (6.413) Lt: 5.689 (5.675) Accm: 3.93 (3.89) Acct: 6.01 (5.92) proj_loss: -0.6249 (-0.6222) time: 0.9256 data: 0.0002 [11-26 01:22:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.579 (6.489) Lt: 5.829 (5.724) Accm: 3.31 (3.43) Acct: 5.20 (5.33) proj_loss: -0.6140 (-0.6205) time: 0.9256 data: 0.0003 [11-26 01:22:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.333 (6.316) Lt: 5.548 (5.560) Accm: 4.08 (4.23) Acct: 6.44 (6.26) proj_loss: -0.6136 (-0.6200) time: 0.9256 data: 0.0003 [11-26 01:22:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.543 (6.532) Lt: 5.845 (5.837) Accm: 3.23 (3.25) Acct: 5.01 (5.06) proj_loss: -0.6319 (-0.6287) time: 0.9256 data: 0.0003 [11-26 01:22:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.353 (6.363) Lt: 5.587 (5.626) Accm: 3.74 (3.79) Acct: 5.89 (5.99) proj_loss: -0.6185 (-0.6193) time: 0.9256 data: 0.0003 [11-26 01:22:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1251/1669] eta: 0:06:26 tlr: 0.00015 tnm: 0.26 Lm: 6.374 (6.372) Lt: 5.591 (5.606) Accm: 4.10 (3.96) Acct: 6.53 (6.33) proj_loss: -0.6228 (-0.6296) time: 0.9256 data: 0.0002 [11-26 01:29:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.395 (6.413) Lt: 5.599 (5.657) Accm: 3.98 (3.77) Acct: 6.47 (5.96) proj_loss: -0.6190 (-0.6271) time: 0.9274 data: 0.0014 [11-26 01:29:14] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 152/350] Total time: 0:25:42 (0.924 s / it) [11-26 01:29:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.564 (6.452) Lt: 5.823 (5.678) Accm: 3.48 (3.56) Acct: 5.48 (5.48) proj_loss: -0.6158 (-0.6196) time: 0.9274 data: 0.0018 [11-26 01:29:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.331 (6.317) Lt: 5.528 (5.563) Accm: 3.74 (3.97) Acct: 6.23 (6.29) proj_loss: -0.6157 (-0.6167) time: 0.9274 data: 0.0017 [11-26 01:29:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.391 (6.331) Lt: 5.623 (5.573) Accm: 3.79 (4.14) Acct: 6.16 (6.19) proj_loss: -0.6136 (-0.6174) time: 0.9274 data: 0.0016 [11-26 01:29:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.614 (6.548) Lt: 5.918 (5.853) Accm: 3.09 (3.19) Acct: 4.75 (4.98) proj_loss: -0.6236 (-0.6251) time: 0.9274 data: 0.0019 [11-26 01:29:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.497 (6.487) Lt: 5.735 (5.742) Accm: 3.18 (3.30) Acct: 4.92 (5.01) proj_loss: -0.6219 (-0.6245) time: 0.9274 data: 0.0020 [11-26 01:29:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.521 (6.435) Lt: 5.740 (5.688) Accm: 3.88 (3.75) Acct: 5.92 (5.70) proj_loss: -0.6226 (-0.6204) time: 0.9274 data: 0.0018 [11-26 01:29:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.347 (6.344) Lt: 5.633 (5.613) Accm: 4.04 (3.76) Acct: 6.27 (5.70) proj_loss: -0.6226 (-0.6203) time: 0.9274 data: 0.0015 [11-26 01:29:14] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 152/350] Total time: 0:25:42 (0.924 s / it) [11-26 01:29:14] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 152/350] Total time: 0:25:42 (0.924 s / it) [11-26 01:29:14] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 152/350] Total time: 0:25:42 (0.924 s / it) [11-26 01:29:14] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 152/350] Total time: 0:25:42 (0.924 s / it) [11-26 01:29:14] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 152/350] Total time: 0:25:42 (0.924 s / it) [11-26 01:29:14] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 152/350] Total time: 0:25:42 (0.924 s / it) [11-26 01:29:14] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 152/350] Total time: 0:25:42 (0.924 s / it) [11-26 01:29:14] (/home/user/VAR/train.py , line 276)=> [ep152] (training ) Lm: 6.434 (6.456), Lt: 5.677 (5.702), Acc m&t: 3.57 5.59, Remain: 3 days, 13:20:46, Finish: 2024-11-28 22:50 [11-26 01:29:14] (/home/user/VAR/train.py , line 276)=> [ep152] (training ) Lm: 6.434 (6.456), Lt: 5.677 (5.702), Acc m&t: 3.57 5.59, Remain: 3 days, 13:21:05, Finish: 2024-11-28 22:50 [11-26 01:29:14] (/home/user/VAR/train.py , line 276)=> [ep152] (training ) Lm: 6.434 (6.456), Lt: 5.677 (5.702), Acc m&t: 3.57 5.59, Remain: 3 days, 13:23:06, Finish: 2024-11-28 22:52 [11-26 01:29:14] (/home/user/VAR/train.py , line 276)=> [ep152] (training ) Lm: 6.434 (6.456), Lt: 5.677 (5.702), Acc m&t: 3.57 5.59, Remain: 3 days, 13:20:47, Finish: 2024-11-28 22:50 [11-26 01:29:14] (/home/user/VAR/train.py , line 276)=> [ep152] (training ) Lm: 6.434 (6.456), Lt: 5.677 (5.702), Acc m&t: 3.57 5.59, Remain: 3 days, 13:21:52, Finish: 2024-11-28 22:51 [11-26 01:29:14] (/home/user/VAR/train.py , line 276)=> [ep152] (training ) Lm: 6.434 (6.456), Lt: 5.677 (5.702), Acc m&t: 3.57 5.59, Remain: 3 days, 13:22:15, Finish: 2024-11-28 22:51 [11-26 01:29:14] (/home/user/VAR/train.py , line 276)=> [ep152] (training ) Lm: 6.434 (6.456), Lt: 5.677 (5.702), Acc m&t: 3.57 5.59, Remain: 3 days, 13:21:30, Finish: 2024-11-28 22:50 [11-26 01:29:14] (/home/user/VAR/train.py , line 276)=> [ep152] (training ) Lm: 6.434 (6.456), Lt: 5.677 (5.702), Acc m&t: 3.57 5.59, Remain: 3 days, 13:20:20, Finish: 2024-11-28 22:49 [11-26 01:29:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 0/1669] eta: 0:24:39 tlr: 0.00015 tnm: 0.26 Lm: 6.009 (6.009) Lt: 5.207 (5.207) Accm: 4.68 (4.68) Acct: 7.13 (7.13) proj_loss: -0.6479 (-0.6479) time: 0.8864 data: 0.0004 [11-26 01:29:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 0/1669] eta: 0:24:39 tlr: 0.00015 tnm: 0.26 Lm: 6.460 (6.460) Lt: 5.694 (5.694) Accm: 3.63 (3.63) Acct: 5.65 (5.65) proj_loss: -0.6036 (-0.6036) time: 0.8865 data: 0.0003 [11-26 01:29:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 0/1669] eta: 0:24:39 tlr: 0.00015 tnm: 0.26 Lm: 6.089 (6.089) Lt: 5.395 (5.395) Accm: 4.88 (4.88) Acct: 6.71 (6.71) proj_loss: -0.6321 (-0.6321) time: 0.8866 data: 0.0004 [11-26 01:29:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 0/1669] eta: 0:24:39 tlr: 0.00015 tnm: 0.26 Lm: 6.459 (6.459) Lt: 5.621 (5.621) Accm: 3.98 (3.98) Acct: 6.20 (6.20) proj_loss: -0.5965 (-0.5965) time: 0.8867 data: 0.0003 [11-26 01:29:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 0/1669] eta: 0:24:40 tlr: 0.00015 tnm: 0.26 Lm: 6.567 (6.567) Lt: 5.799 (5.799) Accm: 3.26 (3.26) Acct: 5.06 (5.06) proj_loss: -0.6343 (-0.6343) time: 0.8868 data: 0.0003 [11-26 01:29:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 0/1669] eta: 0:24:40 tlr: 0.00015 tnm: 0.26 Lm: 6.444 (6.444) Lt: 5.642 (5.642) Accm: 3.79 (3.79) Acct: 5.72 (5.72) proj_loss: -0.5876 (-0.5876) time: 0.8869 data: 0.0005 [11-26 01:29:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 0/1669] eta: 0:24:40 tlr: 0.00015 tnm: 0.26 Lm: 6.641 (6.641) Lt: 5.969 (5.969) Accm: 3.07 (3.07) Acct: 4.86 (4.86) proj_loss: -0.6026 (-0.6026) time: 0.8869 data: 0.0004 [11-26 01:29:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 0/1669] eta: 0:24:41 tlr: 0.00015 tnm: 0.26 Lm: 6.356 (6.356) Lt: 5.605 (5.605) Accm: 3.48 (3.48) Acct: 5.41 (5.41) proj_loss: -0.6398 (-0.6398) time: 0.8875 data: 0.0003 [11-26 01:35:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 417/1669] eta: 0:19:56 tlr: 0.00015 tnm: 0.25 Lm: 6.366 (6.366) Lt: 5.617 (5.617) Accm: 3.66 (3.66) Acct: 5.68 (5.68) proj_loss: -0.6396 (-0.6396) time: 0.9236 data: 0.0003 [11-26 01:35:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 417/1669] eta: 0:19:56 tlr: 0.00015 tnm: 0.25 Lm: 6.564 (6.564) Lt: 5.868 (5.868) Accm: 3.27 (3.27) Acct: 5.01 (5.01) proj_loss: -0.6133 (-0.6133) time: 0.9236 data: 0.0002 [11-26 01:35:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 417/1669] eta: 0:19:56 tlr: 0.00015 tnm: 0.25 Lm: 6.241 (6.241) Lt: 5.506 (5.506) Accm: 4.14 (4.14) Acct: 6.15 (6.15) proj_loss: -0.6216 (-0.6216) time: 0.9236 data: 0.0002 [11-26 01:35:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 417/1669] eta: 0:19:56 tlr: 0.00015 tnm: 0.25 Lm: 6.523 (6.523) Lt: 5.773 (5.773) Accm: 3.17 (3.17) Acct: 4.79 (4.79) proj_loss: -0.6089 (-0.6089) time: 0.9237 data: 0.0003 [11-26 01:35:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 417/1669] eta: 0:19:56 tlr: 0.00015 tnm: 0.25 Lm: 6.500 (6.500) Lt: 5.767 (5.767) Accm: 3.17 (3.17) Acct: 4.91 (4.91) proj_loss: -0.6248 (-0.6248) time: 0.9236 data: 0.0003 [11-26 01:35:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 417/1669] eta: 0:19:56 tlr: 0.00015 tnm: 0.25 Lm: 6.524 (6.524) Lt: 5.744 (5.744) Accm: 3.47 (3.47) Acct: 5.48 (5.48) proj_loss: -0.5961 (-0.5961) time: 0.9236 data: 0.0002 [11-26 01:35:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 417/1669] eta: 0:19:56 tlr: 0.00015 tnm: 0.25 Lm: 6.509 (6.509) Lt: 5.774 (5.774) Accm: 3.53 (3.53) Acct: 5.22 (5.22) proj_loss: -0.6159 (-0.6159) time: 0.9237 data: 0.0003 [11-26 01:35:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 417/1669] eta: 0:19:56 tlr: 0.00015 tnm: 0.25 Lm: 6.311 (6.311) Lt: 5.516 (5.516) Accm: 3.97 (3.97) Acct: 6.28 (6.28) proj_loss: -0.6194 (-0.6194) time: 0.9237 data: 0.0003 [11-26 01:42:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 834/1669] eta: 0:13:05 tlr: 0.00015 tnm: 0.26 Lm: 6.548 (6.390) Lt: 5.762 (5.598) Accm: 3.26 (3.71) Acct: 5.44 (5.82) proj_loss: -0.6160 (-0.6182) time: 0.9253 data: 0.0003 [11-26 01:42:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 834/1669] eta: 0:13:05 tlr: 0.00015 tnm: 0.26 Lm: 6.460 (6.473) Lt: 5.694 (5.697) Accm: 3.63 (3.37) Acct: 5.65 (5.18) proj_loss: -0.6142 (-0.6189) time: 0.9253 data: 0.0002 [11-26 01:42:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 834/1669] eta: 0:13:05 tlr: 0.00015 tnm: 0.26 Lm: 6.458 (6.502) Lt: 5.761 (5.750) Accm: 3.16 (3.37) Acct: 5.23 (5.33) proj_loss: -0.6046 (-0.6020) time: 0.9253 data: 0.0002 [11-26 01:42:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 834/1669] eta: 0:13:05 tlr: 0.00015 tnm: 0.26 Lm: 6.459 (6.431) Lt: 5.621 (5.688) Accm: 3.96 (3.67) Acct: 6.20 (5.67) proj_loss: -0.6254 (-0.6191) time: 0.9253 data: 0.0003 [11-26 01:42:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 834/1669] eta: 0:13:05 tlr: 0.00015 tnm: 0.26 Lm: 6.392 (6.385) Lt: 5.618 (5.646) Accm: 3.39 (3.83) Acct: 5.58 (5.77) proj_loss: -0.6207 (-0.6213) time: 0.9253 data: 0.0003 [11-26 01:42:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 834/1669] eta: 0:13:05 tlr: 0.00015 tnm: 0.26 Lm: 6.487 (6.520) Lt: 5.768 (5.811) Accm: 3.47 (3.34) Acct: 5.13 (5.05) proj_loss: -0.6241 (-0.6171) time: 0.9253 data: 0.0003 [11-26 01:42:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 834/1669] eta: 0:13:05 tlr: 0.00015 tnm: 0.26 Lm: 6.377 (6.376) Lt: 5.605 (5.598) Accm: 3.72 (3.68) Acct: 5.96 (5.87) proj_loss: -0.6395 (-0.6275) time: 0.9253 data: 0.0003 [11-26 01:42:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 834/1669] eta: 0:13:05 tlr: 0.00015 tnm: 0.26 Lm: 6.554 (6.518) Lt: 5.799 (5.782) Accm: 3.26 (3.29) Acct: 5.06 (5.11) proj_loss: -0.6343 (-0.6314) time: 0.9253 data: 0.0003 [11-26 01:48:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1251/1669] eta: 0:06:30 tlr: 0.00015 tnm: 0.26 Lm: 6.560 (6.546) Lt: 5.806 (5.808) Accm: 3.17 (3.23) Acct: 4.99 (5.06) proj_loss: -0.6294 (-0.6296) time: 0.9235 data: 0.0003 [11-26 01:48:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1251/1669] eta: 0:06:30 tlr: 0.00015 tnm: 0.26 Lm: 6.481 (6.502) Lt: 5.790 (5.767) Accm: 3.23 (3.35) Acct: 5.13 (5.24) proj_loss: -0.6093 (-0.6070) time: 0.9235 data: 0.0002 [11-26 01:48:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1251/1669] eta: 0:06:30 tlr: 0.00015 tnm: 0.26 Lm: 6.498 (6.489) Lt: 5.773 (5.751) Accm: 3.38 (3.31) Acct: 5.20 (5.07) proj_loss: -0.6265 (-0.6244) time: 0.9235 data: 0.0002 [11-26 01:48:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1251/1669] eta: 0:06:30 tlr: 0.00015 tnm: 0.26 Lm: 6.466 (6.441) Lt: 5.665 (5.693) Accm: 3.75 (3.64) Acct: 5.85 (5.63) proj_loss: -0.6245 (-0.6202) time: 0.9235 data: 0.0003 [11-26 01:48:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1251/1669] eta: 0:06:30 tlr: 0.00015 tnm: 0.26 Lm: 6.413 (6.362) Lt: 5.628 (5.572) Accm: 3.56 (3.74) Acct: 5.85 (5.93) proj_loss: -0.6138 (-0.6166) time: 0.9235 data: 0.0003 [11-26 01:48:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1251/1669] eta: 0:06:30 tlr: 0.00015 tnm: 0.26 Lm: 6.545 (6.541) Lt: 5.831 (5.832) Accm: 3.27 (3.22) Acct: 4.99 (4.87) proj_loss: -0.6168 (-0.6152) time: 0.9235 data: 0.0003 [11-26 01:48:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1251/1669] eta: 0:06:30 tlr: 0.00015 tnm: 0.26 Lm: 6.387 (6.413) Lt: 5.617 (5.623) Accm: 3.60 (3.49) Acct: 5.68 (5.58) proj_loss: -0.6214 (-0.6200) time: 0.9235 data: 0.0003 [11-26 01:48:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1251/1669] eta: 0:06:30 tlr: 0.00015 tnm: 0.26 Lm: 6.451 (6.416) Lt: 5.680 (5.670) Accm: 3.36 (3.70) Acct: 5.41 (5.64) proj_loss: -0.6159 (-0.6172) time: 0.9235 data: 0.0003 ======================================================= RESTART [11-26 03:00:17] ======================================================= ======================================================= RESTART [11-26 03:00:17] ======================================================= ======================================================= RESTART [11-26 03:00:17] ======================================================= ======================================================= RESTART [11-26 03:00:17] ======================================================= ======================================================= RESTART [11-26 03:00:17] ======================================================= ======================================================= RESTART [11-26 03:00:17] ======================================================= ======================================================= RESTART [11-26 03:00:17] ======================================================= ======================================================= RESTART [11-26 03:00:17] ======================================================= [11-26 03:00:17] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 03:00:17] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 03:00:17] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 03:01:59] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 03:01:59] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add branch : main } [11-26 03:01:59] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 03:02:02] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 03:02:02] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> [11-26 03:02:02] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 03:02:02] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> [11-26 03:02:02] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 03:02:02] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 03:02:02] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep150, it0 [11-26 03:02:02] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 03:00:17] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 03:00:17] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 03:00:17] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 03:01:59] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 03:01:59] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-26 03:01:59] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 03:02:02] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 03:02:02] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> [11-26 03:02:02] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 03:02:02] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> [11-26 03:02:02] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 03:02:02] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 03:02:02] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep150, it0 [11-26 03:02:02] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 03:00:17] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 03:00:17] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 03:00:17] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 03:01:59] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 03:01:59] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add } [11-26 03:01:59] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 03:02:02] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 03:02:02] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> [11-26 03:02:02] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 03:02:02] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> [11-26 03:02:02] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 03:02:02] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 03:02:02] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep150, it0 [11-26 03:02:02] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 03:00:17] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 03:00:17] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 03:00:17] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 03:01:59] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 03:01:59] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-26 03:01:59] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 03:02:02] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 03:02:02] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> [11-26 03:02:02] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 03:02:02] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> [11-26 03:02:02] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 03:02:02] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 03:02:02] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep150, it0 [11-26 03:02:02] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 03:00:17] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 03:00:17] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 03:00:17] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 03:01:59] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 03:01:59] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-26 03:01:59] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 03:02:02] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 03:02:02] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> [11-26 03:02:02] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 03:02:02] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> [11-26 03:02:02] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 03:02:02] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 03:02:02] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep150, it0 [11-26 03:02:02] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 03:00:17] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 03:00:17] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 03:00:17] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 03:01:59] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 03:01:59] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-26 03:01:59] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 03:02:02] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 03:02:02] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> [11-26 03:02:02] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 03:02:02] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> [11-26 03:02:02] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 03:02:02] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 03:02:02] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep150, it0 [11-26 03:02:02] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 03:00:17] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 03:00:17] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 03:00:17] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 03:01:59] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 03:01:59] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-26 03:01:59] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 03:02:02] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 03:02:02] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> [11-26 03:02:02] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 03:02:02] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 03:02:02] (e/user/VAR/utils/data.py, line 51)=> [11-26 03:02:02] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 03:02:02] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 03:02:02] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep150, it0 [11-26 03:02:02] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 03:00:17] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 03:00:17] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 03:00:17] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 03:01:59] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 03:01:59] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add } [11-26 03:01:59] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 03:02:04] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 03:02:04] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 03:02:04] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 03:02:04] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 03:02:04] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 03:02:04] (e/user/VAR/utils/data.py, line 51)=> [11-26 03:02:04] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 03:02:04] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 03:02:04] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 03:02:04] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 03:02:04] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 03:02:04] (e/user/VAR/utils/data.py, line 51)=> [11-26 03:02:04] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 03:02:05] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 03:02:05] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep150, it0 [11-26 03:02:05] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ... [dataloader multi processing](*) finished! (47.48s) [dataloader multi processing](*) finished! (48.72s) [dataloader multi processing](*) finished! (50.04s) [dataloader multi processing](*) finished! (50.40s) [dataloader multi processing](*) finished! (50.05s) [11-26 03:02:49] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 03:02:54] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 03:02:54] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 03:02:55] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [dataloader multi processing](*) finished! (53.78s) [11-26 03:02:50] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 03:02:55] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 03:02:55] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 03:02:56] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [dataloader multi processing](*) finished! (55.15s) [dataloader multi processing](*) finished! (55.74s) [11-26 03:02:52] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 03:02:57] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 03:02:57] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 03:02:58] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 03:02:52] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 03:02:57] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 03:02:57] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 03:02:58] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 03:02:55] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 03:02:57] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 03:02:57] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 03:02:59] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 03:02:55] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 03:03:00] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 03:03:00] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 03:03:02] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 03:02:57] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 03:03:01] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 03:03:01] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 03:03:03] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 03:02:58] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 03:03:02] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 03:03:02] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 03:03:03] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 03:03:02] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 03:03:28] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 03:03:28] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 03:03:28] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 03:03:28] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 03:03:28] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank0] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 03:03:05] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 03:03:28] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 03:03:28] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 03:03:28] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 03:03:28] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 03:03:28] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank8] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 03:03:01] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 03:03:28] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 03:03:28] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 03:03:28] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 03:03:28] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 03:03:29] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank16] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 03:03:07] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 03:03:28] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 03:03:28] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 03:03:28] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 03:03:28] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 03:03:29] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank24] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 03:02:59] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 03:03:28] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 03:03:28] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 03:03:28] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 03:03:28] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 03:03:29] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank32] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 03:03:01] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 03:03:28] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 03:03:28] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 03:03:28] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 03:03:28] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 03:03:29] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank40] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 03:02:58] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 03:03:28] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 03:03:28] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 03:03:28] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 03:03:28] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 03:03:29] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank48] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 03:03:06] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 03:03:28] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 03:03:28] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 03:03:28] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 03:03:28] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 03:03:29] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank56] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 03:03:29] (/VAR/utils/lr_control.py, line 105)=> [11-26 03:03:29] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 03:03:31] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 03:03:31] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 03:03:32] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 03:03:32] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 03:09:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 0/1669] eta: 6 days, 21:28:45 tlr: 0.00015 tnm: 0.26 Lm: 6.607 (6.607) Lt: 5.887 (5.887) Accm: 3.03 (3.03) Acct: 5.10 (5.10) proj_loss: -0.6212 (-0.6212) time: 356.9353 data: 0.0006 [11-26 03:03:29] (/VAR/utils/lr_control.py, line 105)=> [11-26 03:03:29] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 03:03:31] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 03:03:31] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 03:03:31] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 03:03:31] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 03:09:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 0/1669] eta: 6 days, 20:39:25 tlr: 0.00015 tnm: 0.26 Lm: 6.456 (6.456) Lt: 5.738 (5.738) Accm: 3.26 (3.26) Acct: 5.06 (5.06) proj_loss: -0.6080 (-0.6080) time: 355.1619 data: 0.0007 [11-26 03:03:29] (/VAR/utils/lr_control.py, line 105)=> [11-26 03:03:29] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 03:03:32] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 03:03:32] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 03:03:32] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 03:03:32] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 03:09:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 0/1669] eta: 6 days, 21:16:27 tlr: 0.00015 tnm: 0.26 Lm: 6.391 (6.391) Lt: 5.597 (5.597) Accm: 3.89 (3.89) Acct: 6.37 (6.37) proj_loss: -0.6312 (-0.6312) time: 356.4937 data: 0.0007 [11-26 03:03:29] (/VAR/utils/lr_control.py, line 105)=> [11-26 03:03:29] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 03:03:31] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 03:03:31] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 03:03:32] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 03:03:32] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 03:09:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 0/1669] eta: 6 days, 21:35:54 tlr: 0.00015 tnm: 0.26 Lm: 6.357 (6.357) Lt: 5.494 (5.494) Accm: 3.95 (3.95) Acct: 6.23 (6.23) proj_loss: -0.6156 (-0.6156) time: 357.1925 data: 0.0005 [11-26 03:03:29] (/VAR/utils/lr_control.py, line 105)=> [11-26 03:03:29] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 03:03:31] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 03:03:31] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 03:03:32] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 03:03:32] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 03:09:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 0/1669] eta: 6 days, 21:31:56 tlr: 0.00015 tnm: 0.26 Lm: 6.334 (6.334) Lt: 5.578 (5.578) Accm: 3.38 (3.38) Acct: 5.58 (5.58) proj_loss: -0.6108 (-0.6108) time: 357.0502 data: 0.0006 [11-26 03:03:29] (/VAR/utils/lr_control.py, line 105)=> [11-26 03:03:29] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 03:03:31] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 03:03:31] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 03:03:31] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 03:03:31] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 03:09:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 0/1669] eta: 6 days, 21:19:27 tlr: 0.00015 tnm: 0.26 Lm: 6.297 (6.297) Lt: 5.524 (5.524) Accm: 3.74 (3.74) Acct: 5.79 (5.79) proj_loss: -0.6228 (-0.6228) time: 356.6014 data: 0.0006 [11-26 03:03:29] (/VAR/utils/lr_control.py, line 105)=> [11-26 03:03:29] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 03:03:32] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 03:03:32] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 03:03:32] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 03:03:32] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 03:09:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 0/1669] eta: 6 days, 21:22:38 tlr: 0.00015 tnm: 0.26 Lm: 6.586 (6.586) Lt: 5.899 (5.899) Accm: 3.25 (3.25) Acct: 4.37 (4.37) proj_loss: -0.6298 (-0.6298) time: 356.7160 data: 0.0007 [11-26 03:03:29] (/VAR/utils/lr_control.py, line 105)=> [11-26 03:03:29] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 03:03:31] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 03:03:31] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 03:03:32] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 03:03:32] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 03:09:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 0/1669] eta: 6 days, 21:35:01 tlr: 0.00015 tnm: 0.26 Lm: 6.425 (6.425) Lt: 5.786 (5.786) Accm: 3.38 (3.38) Acct: 5.27 (5.27) proj_loss: -0.6285 (-0.6285) time: 357.1606 data: 0.0005 [11-26 03:24:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 417/1669] eta: 1:02:12 tlr: 0.00015 tnm: 0.25 Lm: 6.222 (6.222) Lt: 5.417 (5.417) Accm: 3.87 (3.87) Acct: 6.03 (6.03) proj_loss: -0.5874 (-0.5874) time: 0.9220 data: 0.0002 [11-26 03:24:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 417/1669] eta: 1:02:11 tlr: 0.00015 tnm: 0.25 Lm: 6.332 (6.332) Lt: 5.581 (5.581) Accm: 3.61 (3.61) Acct: 5.53 (5.53) proj_loss: -0.6242 (-0.6242) time: 0.9220 data: 0.0003 [11-26 03:24:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 417/1669] eta: 1:02:11 tlr: 0.00015 tnm: 0.25 Lm: 6.515 (6.515) Lt: 5.699 (5.699) Accm: 3.26 (3.26) Acct: 4.99 (4.99) proj_loss: -0.6195 (-0.6195) time: 0.9220 data: 0.0003 [11-26 03:24:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 417/1669] eta: 1:02:13 tlr: 0.00015 tnm: 0.25 Lm: 6.522 (6.522) Lt: 5.706 (5.706) Accm: 3.37 (3.37) Acct: 5.42 (5.42) proj_loss: -0.5956 (-0.5956) time: 0.9220 data: 0.0002 [11-26 03:24:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 417/1669] eta: 1:02:12 tlr: 0.00015 tnm: 0.25 Lm: 6.490 (6.490) Lt: 5.742 (5.742) Accm: 3.58 (3.58) Acct: 5.82 (5.82) proj_loss: -0.6239 (-0.6239) time: 0.9220 data: 0.0003 [11-26 03:24:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 417/1669] eta: 1:02:13 tlr: 0.00015 tnm: 0.25 Lm: 6.372 (6.372) Lt: 5.623 (5.623) Accm: 3.82 (3.82) Acct: 6.11 (6.11) proj_loss: -0.6130 (-0.6130) time: 0.9220 data: 0.0002 [11-26 03:24:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 417/1669] eta: 1:02:11 tlr: 0.00015 tnm: 0.25 Lm: 6.441 (6.441) Lt: 5.680 (5.680) Accm: 3.77 (3.77) Acct: 5.94 (5.94) proj_loss: -0.6163 (-0.6163) time: 0.9220 data: 0.0003 [11-26 03:24:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 417/1669] eta: 1:02:07 tlr: 0.00015 tnm: 0.25 Lm: 6.505 (6.505) Lt: 5.740 (5.740) Accm: 3.10 (3.10) Acct: 4.80 (4.80) proj_loss: -0.6000 (-0.6000) time: 0.9220 data: 0.0002 [11-26 03:30:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 834/1669] eta: 0:27:09 tlr: 0.00015 tnm: 0.25 Lm: 6.456 (6.479) Lt: 5.742 (5.743) Accm: 3.26 (3.34) Acct: 5.06 (5.10) proj_loss: -0.6080 (-0.6108) time: 0.9227 data: 0.0002 [11-26 03:30:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 834/1669] eta: 0:27:11 tlr: 0.00015 tnm: 0.25 Lm: 6.663 (6.569) Lt: 5.917 (5.782) Accm: 3.04 (3.26) Acct: 4.75 (5.20) proj_loss: -0.6156 (-0.6039) time: 0.9227 data: 0.0003 [11-26 03:30:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 834/1669] eta: 0:27:10 tlr: 0.00015 tnm: 0.25 Lm: 6.557 (6.512) Lt: 5.748 (5.744) Accm: 3.15 (3.44) Acct: 5.10 (5.53) proj_loss: -0.6248 (-0.6242) time: 0.9228 data: 0.0002 [11-26 03:30:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 834/1669] eta: 0:27:10 tlr: 0.00015 tnm: 0.25 Lm: 6.320 (6.299) Lt: 5.461 (5.538) Accm: 4.25 (4.12) Acct: 6.96 (6.58) proj_loss: -0.6084 (-0.6115) time: 0.9227 data: 0.0003 [11-26 03:30:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 834/1669] eta: 0:27:10 tlr: 0.00015 tnm: 0.25 Lm: 6.334 (6.271) Lt: 5.520 (5.451) Accm: 3.50 (3.74) Acct: 5.99 (6.01) proj_loss: -0.5891 (-0.5880) time: 0.9228 data: 0.0003 [11-26 03:30:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 834/1669] eta: 0:27:10 tlr: 0.00015 tnm: 0.25 Lm: 6.491 (6.504) Lt: 5.762 (5.758) Accm: 3.66 (3.55) Acct: 5.51 (5.56) proj_loss: -0.6245 (-0.6190) time: 0.9227 data: 0.0002 [11-26 03:30:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 834/1669] eta: 0:27:10 tlr: 0.00015 tnm: 0.25 Lm: 6.571 (6.534) Lt: 5.879 (5.759) Accm: 3.25 (3.17) Acct: 4.72 (4.90) proj_loss: -0.6241 (-0.6210) time: 0.9228 data: 0.0003 [11-26 03:30:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [ 834/1669] eta: 0:27:10 tlr: 0.00015 tnm: 0.25 Lm: 6.366 (6.347) Lt: 5.638 (5.606) Accm: 3.72 (3.65) Acct: 5.79 (5.68) proj_loss: -0.6256 (-0.6257) time: 0.9228 data: 0.0003 [11-26 03:37:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1251/1669] eta: 0:11:12 tlr: 0.00015 tnm: 0.27 Lm: 6.372 (6.379) Lt: 5.646 (5.620) Accm: 3.66 (3.64) Acct: 5.82 (5.72) proj_loss: -0.6242 (-0.6164) time: 0.9226 data: 0.0002 [11-26 03:37:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1251/1669] eta: 0:11:12 tlr: 0.00015 tnm: 0.27 Lm: 6.462 (6.476) Lt: 5.740 (5.729) Accm: 3.45 (3.42) Acct: 5.37 (5.27) proj_loss: -0.6000 (-0.6022) time: 0.9225 data: 0.0002 [11-26 03:37:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1251/1669] eta: 0:11:12 tlr: 0.00015 tnm: 0.27 Lm: 6.510 (6.446) Lt: 5.706 (5.647) Accm: 3.50 (3.61) Acct: 5.49 (5.73) proj_loss: -0.6180 (-0.6101) time: 0.9225 data: 0.0003 [11-26 03:37:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1251/1669] eta: 0:11:12 tlr: 0.00015 tnm: 0.27 Lm: 6.372 (6.338) Lt: 5.604 (5.590) Accm: 3.82 (3.88) Acct: 6.11 (6.11) proj_loss: -0.6156 (-0.6143) time: 0.9225 data: 0.0002 [11-26 03:37:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1251/1669] eta: 0:11:12 tlr: 0.00015 tnm: 0.27 Lm: 6.503 (6.507) Lt: 5.800 (5.778) Accm: 3.52 (3.50) Acct: 5.23 (5.41) proj_loss: -0.6263 (-0.6213) time: 0.9226 data: 0.0003 [11-26 03:37:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1251/1669] eta: 0:11:12 tlr: 0.00015 tnm: 0.27 Lm: 6.508 (6.510) Lt: 5.801 (5.750) Accm: 3.26 (3.38) Acct: 5.17 (5.25) proj_loss: -0.6221 (-0.6208) time: 0.9226 data: 0.0002 [11-26 03:37:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1251/1669] eta: 0:11:12 tlr: 0.00015 tnm: 0.27 Lm: 6.352 (6.357) Lt: 5.549 (5.564) Accm: 3.44 (3.56) Acct: 5.79 (5.68) proj_loss: -0.5999 (-0.5966) time: 0.9226 data: 0.0003 [11-26 03:37:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1251/1669] eta: 0:11:12 tlr: 0.00015 tnm: 0.27 Lm: 6.582 (6.539) Lt: 5.790 (5.766) Accm: 3.10 (3.34) Acct: 5.10 (5.42) proj_loss: -0.6230 (-0.6157) time: 0.9226 data: 0.0003 [11-26 03:43:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1668/1669] eta: 0:00:01 tlr: 0.00015 tnm: 0.26 Lm: 6.607 (6.557) Lt: 5.832 (5.797) Accm: 3.06 (3.27) Acct: 5.10 (5.32) proj_loss: -0.6212 (-0.6167) time: 0.9251 data: 0.0022 [11-26 03:43:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 150/350] Total time: 0:40:00 (1.438 s / it) [11-26 03:43:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1668/1669] eta: 0:00:01 tlr: 0.00015 tnm: 0.26 Lm: 6.355 (6.357) Lt: 5.531 (5.558) Accm: 3.50 (3.55) Acct: 5.65 (5.67) proj_loss: -0.5999 (-0.5972) time: 0.9251 data: 0.0016 [11-26 03:43:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1668/1669] eta: 0:00:01 tlr: 0.00015 tnm: 0.26 Lm: 6.444 (6.495) Lt: 5.722 (5.734) Accm: 3.26 (3.39) Acct: 5.06 (5.21) proj_loss: -0.6202 (-0.6192) time: 0.9251 data: 0.0014 [11-26 03:43:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1668/1669] eta: 0:00:01 tlr: 0.00015 tnm: 0.26 Lm: 6.378 (6.382) Lt: 5.638 (5.611) Accm: 3.61 (3.61) Acct: 5.79 (5.68) proj_loss: -0.6228 (-0.6128) time: 0.9251 data: 0.0022 [11-26 03:43:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1668/1669] eta: 0:00:01 tlr: 0.00015 tnm: 0.26 Lm: 6.557 (6.468) Lt: 5.834 (5.684) Accm: 3.19 (3.53) Acct: 4.89 (5.56) proj_loss: -0.6156 (-0.6015) time: 0.9251 data: 0.0018 [11-26 03:43:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1668/1669] eta: 0:00:01 tlr: 0.00015 tnm: 0.26 Lm: 6.425 (6.400) Lt: 5.747 (5.660) Accm: 3.51 (3.80) Acct: 5.30 (5.95) proj_loss: -0.6228 (-0.6167) time: 0.9251 data: 0.0019 [11-26 03:43:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1668/1669] eta: 0:00:01 tlr: 0.00015 tnm: 0.26 Lm: 6.456 (6.444) Lt: 5.738 (5.692) Accm: 3.64 (3.60) Acct: 5.68 (5.50) proj_loss: -0.6080 (-0.6054) time: 0.9251 data: 0.0014 [11-26 03:43:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 150/350] [1668/1669] eta: 0:00:01 tlr: 0.00015 tnm: 0.26 Lm: 6.491 (6.436) Lt: 5.762 (5.690) Accm: 3.66 (3.78) Acct: 5.51 (5.88) proj_loss: -0.6245 (-0.6183) time: 0.9251 data: 0.0017 [11-26 03:43:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 150/350] Total time: 0:40:00 (1.438 s / it) [11-26 03:43:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 150/350] Total time: 0:39:59 (1.438 s / it) [11-26 03:43:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 150/350] Total time: 0:39:59 (1.438 s / it) [11-26 03:43:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 150/350] Total time: 0:40:00 (1.438 s / it) [11-26 03:43:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 150/350] Total time: 0:40:00 (1.438 s / it) [11-26 03:43:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 150/350] Total time: 0:39:58 (1.437 s / it) [11-26 03:43:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 150/350] Total time: 0:39:59 (1.438 s / it) [11-26 03:43:41] (/home/user/VAR/train.py , line 276)=> [ep150] (training ) Lm: 6.436 (6.436), Lt: 5.678 (5.678), Acc m&t: 3.57 5.59, Remain: 3 days, 13:57:18, Finish: 2024-11-29 01:40 [11-26 03:43:41] (/home/user/VAR/train.py , line 276)=> [ep150] (training ) Lm: 6.436 (6.436), Lt: 5.678 (5.678), Acc m&t: 3.57 5.59, Remain: 3 days, 13:56:59, Finish: 2024-11-29 01:40 [11-26 03:43:41] (/home/user/VAR/train.py , line 276)=> [ep150] (training ) Lm: 6.436 (6.436), Lt: 5.678 (5.678), Acc m&t: 3.57 5.59, Remain: 3 days, 13:56:51, Finish: 2024-11-29 01:40 [11-26 03:43:41] (/home/user/VAR/train.py , line 276)=> [ep150] (training ) Lm: 6.436 (6.436), Lt: 5.678 (5.678), Acc m&t: 3.57 5.59, Remain: 3 days, 13:57:08, Finish: 2024-11-29 01:40 [11-26 03:43:41] (/home/user/VAR/train.py , line 276)=> [ep150] (training ) Lm: 6.436 (6.436), Lt: 5.678 (5.678), Acc m&t: 3.57 5.59, Remain: 3 days, 13:57:42, Finish: 2024-11-29 01:41 [11-26 03:43:41] (/home/user/VAR/train.py , line 276)=> [ep150] (training ) Lm: 6.436 (6.436), Lt: 5.678 (5.678), Acc m&t: 3.57 5.59, Remain: 3 days, 13:57:22, Finish: 2024-11-29 01:41 [11-26 03:43:41] (/home/user/VAR/train.py , line 276)=> [ep150] (training ) Lm: 6.436 (6.436), Lt: 5.678 (5.678), Acc m&t: 3.57 5.59, Remain: 3 days, 13:58:28, Finish: 2024-11-29 01:42 [11-26 03:43:41] (/home/user/VAR/train.py , line 276)=> [ep150] (training ) Lm: 6.436 (6.436), Lt: 5.678 (5.678), Acc m&t: 3.57 5.59, Remain: 3 days, 13:56:14, Finish: 2024-11-29 01:39 [11-26 03:43:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 0/1669] eta: 0:25:45 tlr: 0.00015 tnm: 0.26 Lm: 6.542 (6.542) Lt: 5.862 (5.862) Accm: 3.28 (3.28) Acct: 4.68 (4.68) proj_loss: -0.5990 (-0.5990) time: 0.9258 data: 0.0004 [11-26 03:43:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 0/1669] eta: 0:25:47 tlr: 0.00015 tnm: 0.26 Lm: 6.415 (6.415) Lt: 5.741 (5.741) Accm: 3.53 (3.53) Acct: 5.03 (5.03) proj_loss: -0.6052 (-0.6052) time: 0.9274 data: 0.0004 [11-26 03:43:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 0/1669] eta: 0:25:48 tlr: 0.00015 tnm: 0.26 Lm: 6.307 (6.307) Lt: 5.600 (5.600) Accm: 3.92 (3.92) Acct: 6.03 (6.03) proj_loss: -0.6039 (-0.6039) time: 0.9281 data: 0.0004 [11-26 03:43:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 0/1669] eta: 0:25:46 tlr: 0.00015 tnm: 0.26 Lm: 6.336 (6.336) Lt: 5.564 (5.564) Accm: 4.02 (4.02) Acct: 6.85 (6.85) proj_loss: -0.6197 (-0.6197) time: 0.9267 data: 0.0003 [11-26 03:43:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 0/1669] eta: 0:25:46 tlr: 0.00015 tnm: 0.26 Lm: 6.681 (6.681) Lt: 5.881 (5.881) Accm: 2.75 (2.75) Acct: 4.68 (4.68) proj_loss: -0.5860 (-0.5860) time: 0.9269 data: 0.0004 [11-26 03:43:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 0/1669] eta: 0:25:47 tlr: 0.00015 tnm: 0.26 Lm: 6.362 (6.362) Lt: 5.511 (5.511) Accm: 3.79 (3.79) Acct: 5.85 (5.85) proj_loss: -0.6290 (-0.6290) time: 0.9270 data: 0.0004 [11-26 03:43:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 0/1669] eta: 0:25:47 tlr: 0.00015 tnm: 0.26 Lm: 6.261 (6.261) Lt: 5.490 (5.490) Accm: 4.01 (4.01) Acct: 6.68 (6.68) proj_loss: -0.6269 (-0.6269) time: 0.9270 data: 0.0004 [11-26 03:43:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 0/1669] eta: 0:26:57 tlr: 0.00015 tnm: 0.26 Lm: 6.430 (6.430) Lt: 5.562 (5.562) Accm: 3.77 (3.77) Acct: 5.85 (5.85) proj_loss: -0.5995 (-0.5995) time: 0.9694 data: 0.0003 [11-26 03:50:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 417/1669] eta: 0:19:33 tlr: 0.00015 tnm: 0.26 Lm: 6.503 (6.503) Lt: 5.681 (5.681) Accm: 3.58 (3.58) Acct: 5.68 (5.68) proj_loss: -0.6221 (-0.6221) time: 0.9219 data: 0.0003 [11-26 03:50:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 417/1669] eta: 0:19:32 tlr: 0.00015 tnm: 0.26 Lm: 6.552 (6.552) Lt: 5.744 (5.744) Accm: 3.18 (3.18) Acct: 5.11 (5.11) proj_loss: -0.6058 (-0.6058) time: 0.9220 data: 0.0002 [11-26 03:50:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 417/1669] eta: 0:19:33 tlr: 0.00015 tnm: 0.26 Lm: 6.550 (6.550) Lt: 5.763 (5.763) Accm: 3.49 (3.49) Acct: 5.73 (5.73) proj_loss: -0.6111 (-0.6111) time: 0.9220 data: 0.0002 [11-26 03:50:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 417/1669] eta: 0:19:32 tlr: 0.00015 tnm: 0.26 Lm: 6.323 (6.323) Lt: 5.476 (5.476) Accm: 3.96 (3.96) Acct: 6.22 (6.22) proj_loss: -0.6246 (-0.6246) time: 0.9220 data: 0.0002 [11-26 03:50:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 417/1669] eta: 0:19:33 tlr: 0.00015 tnm: 0.26 Lm: 6.493 (6.493) Lt: 5.823 (5.823) Accm: 3.47 (3.47) Acct: 5.10 (5.10) proj_loss: -0.6227 (-0.6227) time: 0.9220 data: 0.0003 [11-26 03:50:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 417/1669] eta: 0:19:33 tlr: 0.00015 tnm: 0.26 Lm: 6.399 (6.399) Lt: 5.677 (5.677) Accm: 3.57 (3.57) Acct: 5.32 (5.32) proj_loss: -0.6165 (-0.6165) time: 0.9220 data: 0.0002 [11-26 03:50:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 417/1669] eta: 0:19:32 tlr: 0.00015 tnm: 0.26 Lm: 6.339 (6.339) Lt: 5.588 (5.588) Accm: 3.73 (3.73) Acct: 6.13 (6.13) proj_loss: -0.6264 (-0.6264) time: 0.9220 data: 0.0002 [11-26 03:50:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 417/1669] eta: 0:19:33 tlr: 0.00015 tnm: 0.26 Lm: 6.525 (6.525) Lt: 5.836 (5.836) Accm: 3.28 (3.28) Acct: 4.87 (4.87) proj_loss: -0.6168 (-0.6168) time: 0.9220 data: 0.0003 [11-26 03:56:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 834/1669] eta: 0:12:56 tlr: 0.00015 tnm: 0.26 Lm: 6.542 (6.532) Lt: 5.813 (5.828) Accm: 3.28 (3.27) Acct: 5.06 (4.99) proj_loss: -0.6155 (-0.6164) time: 0.9224 data: 0.0003 [11-26 03:56:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 834/1669] eta: 0:12:56 tlr: 0.00015 tnm: 0.26 Lm: 6.424 (6.468) Lt: 5.606 (5.678) Accm: 3.61 (3.57) Acct: 5.54 (5.53) proj_loss: -0.6116 (-0.6077) time: 0.9224 data: 0.0002 [11-26 03:56:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 834/1669] eta: 0:12:56 tlr: 0.00015 tnm: 0.26 Lm: 6.415 (6.511) Lt: 5.741 (5.796) Accm: 3.53 (3.47) Acct: 5.03 (5.20) proj_loss: -0.6104 (-0.6145) time: 0.9224 data: 0.0002 [11-26 03:56:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 834/1669] eta: 0:12:56 tlr: 0.00015 tnm: 0.26 Lm: 6.430 (6.430) Lt: 5.562 (5.639) Accm: 3.77 (3.70) Acct: 5.85 (5.88) proj_loss: -0.6178 (-0.6206) time: 0.9224 data: 0.0003 [11-26 03:56:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 834/1669] eta: 0:12:56 tlr: 0.00015 tnm: 0.26 Lm: 6.338 (6.479) Lt: 5.564 (5.670) Accm: 4.02 (3.74) Acct: 6.65 (6.04) proj_loss: -0.6180 (-0.6134) time: 0.9224 data: 0.0003 [11-26 03:56:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 834/1669] eta: 0:12:56 tlr: 0.00015 tnm: 0.26 Lm: 6.362 (6.360) Lt: 5.511 (5.541) Accm: 3.79 (3.80) Acct: 5.85 (6.01) proj_loss: -0.6290 (-0.6277) time: 0.9224 data: 0.0002 [11-26 03:56:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 834/1669] eta: 0:12:56 tlr: 0.00015 tnm: 0.26 Lm: 6.261 (6.309) Lt: 5.490 (5.539) Accm: 4.01 (3.97) Acct: 6.68 (6.52) proj_loss: -0.6269 (-0.6330) time: 0.9224 data: 0.0003 [11-26 03:56:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [ 834/1669] eta: 0:12:56 tlr: 0.00015 tnm: 0.26 Lm: 6.524 (6.503) Lt: 5.738 (5.795) Accm: 3.47 (3.47) Acct: 5.27 (5.15) proj_loss: -0.6039 (-0.6060) time: 0.9224 data: 0.0002 [11-26 04:03:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1251/1669] eta: 0:06:27 tlr: 0.00015 tnm: 0.26 Lm: 6.415 (6.453) Lt: 5.673 (5.748) Accm: 3.69 (3.60) Acct: 5.65 (5.40) proj_loss: -0.6150 (-0.6110) time: 0.9231 data: 0.0002 [11-26 04:03:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1251/1669] eta: 0:06:27 tlr: 0.00015 tnm: 0.26 Lm: 6.357 (6.369) Lt: 5.559 (5.587) Accm: 3.86 (3.80) Acct: 5.91 (5.90) proj_loss: -0.6255 (-0.6238) time: 0.9231 data: 0.0002 [11-26 04:03:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1251/1669] eta: 0:06:27 tlr: 0.00015 tnm: 0.26 Lm: 6.398 (6.442) Lt: 5.592 (5.626) Accm: 3.64 (3.63) Acct: 5.73 (5.79) proj_loss: -0.6246 (-0.6142) time: 0.9231 data: 0.0002 [11-26 04:03:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1251/1669] eta: 0:06:27 tlr: 0.00015 tnm: 0.26 Lm: 6.473 (6.516) Lt: 5.784 (5.803) Accm: 3.45 (3.45) Acct: 4.99 (5.11) proj_loss: -0.6191 (-0.6236) time: 0.9231 data: 0.0002 [11-26 04:03:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1251/1669] eta: 0:06:27 tlr: 0.00015 tnm: 0.26 Lm: 6.516 (6.503) Lt: 5.744 (5.730) Accm: 3.35 (3.45) Acct: 5.11 (5.32) proj_loss: -0.6153 (-0.6105) time: 0.9231 data: 0.0002 [11-26 04:03:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1251/1669] eta: 0:06:27 tlr: 0.00015 tnm: 0.26 Lm: 6.375 (6.462) Lt: 5.605 (5.664) Accm: 3.80 (3.70) Acct: 6.32 (6.03) proj_loss: -0.6161 (-0.6136) time: 0.9231 data: 0.0003 [11-26 04:03:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1251/1669] eta: 0:06:27 tlr: 0.00015 tnm: 0.26 Lm: 6.525 (6.449) Lt: 5.812 (5.734) Accm: 3.28 (3.41) Acct: 5.15 (5.18) proj_loss: -0.6204 (-0.6186) time: 0.9231 data: 0.0002 [11-26 04:03:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1251/1669] eta: 0:06:27 tlr: 0.00015 tnm: 0.26 Lm: 6.339 (6.345) Lt: 5.588 (5.602) Accm: 3.73 (3.77) Acct: 6.13 (6.06) proj_loss: -0.6287 (-0.6324) time: 0.9231 data: 0.0002 [11-26 04:09:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.322 (6.340) Lt: 5.490 (5.577) Accm: 4.01 (3.83) Acct: 6.68 (6.25) proj_loss: -0.6304 (-0.6323) time: 0.9260 data: 0.0014 [11-26 04:09:28] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 151/350] Total time: 0:25:46 (0.926 s / it) [11-26 04:09:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.608 (6.577) Lt: 5.881 (5.824) Accm: 3.09 (3.20) Acct: 4.68 (4.90) proj_loss: -0.6190 (-0.6137) time: 0.9260 data: 0.0018 [11-26 04:09:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.430 (6.404) Lt: 5.562 (5.633) Accm: 3.77 (3.72) Acct: 5.85 (5.83) proj_loss: -0.6332 (-0.6298) time: 0.9260 data: 0.0019 [11-26 04:09:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.492 (6.511) Lt: 5.749 (5.793) Accm: 3.53 (3.56) Acct: 5.03 (5.40) proj_loss: -0.6183 (-0.6225) time: 0.9259 data: 0.0015 [11-26 04:09:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.524 (6.470) Lt: 5.738 (5.763) Accm: 3.47 (3.53) Acct: 5.27 (5.28) proj_loss: -0.6116 (-0.6111) time: 0.9260 data: 0.0017 [11-26 04:09:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.362 (6.407) Lt: 5.511 (5.585) Accm: 3.60 (3.63) Acct: 5.82 (5.80) proj_loss: -0.6290 (-0.6172) time: 0.9260 data: 0.0016 [11-26 04:09:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.509 (6.434) Lt: 5.810 (5.724) Accm: 3.28 (3.49) Acct: 5.23 (5.32) proj_loss: -0.6253 (-0.6200) time: 0.9260 data: 0.0017 [11-26 04:09:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 151/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.26 Lm: 6.412 (6.510) Lt: 5.647 (5.707) Accm: 3.57 (3.51) Acct: 5.99 (5.70) proj_loss: -0.6143 (-0.6133) time: 0.9260 data: 0.0015 [11-26 04:09:28] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 151/350] Total time: 0:25:46 (0.926 s / it) [11-26 04:09:28] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 151/350] Total time: 0:25:46 (0.926 s / it) [11-26 04:09:28] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 151/350] Total time: 0:25:46 (0.926 s / it) [11-26 04:09:28] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 151/350] Total time: 0:25:46 (0.926 s / it) [11-26 04:09:28] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 151/350] Total time: 0:25:46 (0.926 s / it) [11-26 04:09:28] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 151/350] Total time: 0:25:46 (0.926 s / it) [11-26 04:09:28] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 151/350] Total time: 0:25:46 (0.926 s / it) [11-26 04:09:28] (/home/user/VAR/train.py , line 276)=> [ep151] (training ) Lm: 6.436 (6.440), Lt: 5.678 (5.682), Acc m&t: 3.57 5.59, Remain: 3 days, 13:37:19, Finish: 2024-11-29 01:46 [11-26 04:09:28] (/home/user/VAR/train.py , line 276)=> [ep151] (training ) Lm: 6.436 (6.440), Lt: 5.678 (5.682), Acc m&t: 3.57 5.59, Remain: 3 days, 13:40:52, Finish: 2024-11-29 01:50 [11-26 04:09:28] (/home/user/VAR/train.py , line 276)=> [ep151] (training ) Lm: 6.436 (6.440), Lt: 5.678 (5.682), Acc m&t: 3.57 5.59, Remain: 3 days, 13:37:56, Finish: 2024-11-29 01:47 [11-26 04:09:28] (/home/user/VAR/train.py , line 276)=> [ep151] (training ) Lm: 6.436 (6.440), Lt: 5.678 (5.682), Acc m&t: 3.57 5.59, Remain: 3 days, 13:39:20, Finish: 2024-11-29 01:48 [11-26 04:09:28] (/home/user/VAR/train.py , line 276)=> [ep151] (training ) Lm: 6.436 (6.440), Lt: 5.678 (5.682), Acc m&t: 3.57 5.59, Remain: 3 days, 13:38:35, Finish: 2024-11-29 01:48 [11-26 04:09:28] (/home/user/VAR/train.py , line 276)=> [ep151] (training ) Lm: 6.436 (6.440), Lt: 5.678 (5.682), Acc m&t: 3.57 5.59, Remain: 3 days, 13:37:47, Finish: 2024-11-29 01:47 [11-26 04:09:28] (/home/user/VAR/train.py , line 276)=> [ep151] (training ) Lm: 6.436 (6.440), Lt: 5.678 (5.682), Acc m&t: 3.57 5.59, Remain: 3 days, 13:35:50, Finish: 2024-11-29 01:45 [11-26 04:09:28] (/home/user/VAR/train.py , line 276)=> [ep151] (training ) Lm: 6.436 (6.440), Lt: 5.678 (5.682), Acc m&t: 3.57 5.59, Remain: 3 days, 13:40:22, Finish: 2024-11-29 01:49 [11-26 04:09:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 0/1669] eta: 0:24:54 tlr: 0.00015 tnm: 0.25 Lm: 6.275 (6.275) Lt: 5.529 (5.529) Accm: 4.09 (4.09) Acct: 5.75 (5.75) proj_loss: -0.6069 (-0.6069) time: 0.8954 data: 0.0003 [11-26 04:09:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 0/1669] eta: 0:24:54 tlr: 0.00015 tnm: 0.25 Lm: 6.564 (6.564) Lt: 5.873 (5.873) Accm: 3.38 (3.38) Acct: 5.13 (5.13) proj_loss: -0.6260 (-0.6260) time: 0.8956 data: 0.0004 [11-26 04:09:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 0/1669] eta: 0:24:54 tlr: 0.00015 tnm: 0.25 Lm: 6.666 (6.666) Lt: 6.015 (6.015) Accm: 2.86 (2.86) Acct: 4.27 (4.27) proj_loss: -0.6445 (-0.6445) time: 0.8956 data: 0.0004 [11-26 04:09:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 0/1669] eta: 0:24:55 tlr: 0.00015 tnm: 0.25 Lm: 6.539 (6.539) Lt: 5.871 (5.871) Accm: 2.93 (2.93) Acct: 4.44 (4.44) proj_loss: -0.6518 (-0.6518) time: 0.8959 data: 0.0004 [11-26 04:09:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 0/1669] eta: 0:24:54 tlr: 0.00015 tnm: 0.25 Lm: 6.320 (6.320) Lt: 5.654 (5.654) Accm: 3.83 (3.83) Acct: 5.61 (5.61) proj_loss: -0.6249 (-0.6249) time: 0.8952 data: 0.0004 [11-26 04:09:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 0/1669] eta: 0:24:55 tlr: 0.00015 tnm: 0.25 Lm: 6.410 (6.410) Lt: 5.658 (5.658) Accm: 3.48 (3.48) Acct: 5.79 (5.79) proj_loss: -0.6104 (-0.6104) time: 0.8963 data: 0.0004 [11-26 04:09:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 0/1669] eta: 0:24:56 tlr: 0.00015 tnm: 0.25 Lm: 6.542 (6.542) Lt: 5.796 (5.796) Accm: 2.99 (2.99) Acct: 5.13 (5.13) proj_loss: -0.6139 (-0.6139) time: 0.8964 data: 0.0004 [11-26 04:09:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 0/1669] eta: 0:24:56 tlr: 0.00015 tnm: 0.25 Lm: 6.292 (6.292) Lt: 5.589 (5.589) Accm: 4.14 (4.14) Acct: 6.10 (6.10) proj_loss: -0.6285 (-0.6285) time: 0.8967 data: 0.0004 [11-26 04:15:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 417/1669] eta: 0:19:14 tlr: 0.00015 tnm: 0.26 Lm: 6.283 (6.283) Lt: 5.553 (5.553) Accm: 3.98 (3.98) Acct: 6.18 (6.18) proj_loss: -0.6252 (-0.6252) time: 0.9221 data: 0.0002 [11-26 04:15:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 417/1669] eta: 0:19:14 tlr: 0.00015 tnm: 0.26 Lm: 6.419 (6.419) Lt: 5.685 (5.685) Accm: 3.77 (3.77) Acct: 5.46 (5.46) proj_loss: -0.6251 (-0.6251) time: 0.9221 data: 0.0002 [11-26 04:15:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 417/1669] eta: 0:19:14 tlr: 0.00015 tnm: 0.26 Lm: 6.439 (6.439) Lt: 5.733 (5.733) Accm: 3.35 (3.35) Acct: 5.29 (5.29) proj_loss: -0.6075 (-0.6075) time: 0.9221 data: 0.0002 [11-26 04:15:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 417/1669] eta: 0:19:14 tlr: 0.00015 tnm: 0.26 Lm: 6.317 (6.317) Lt: 5.619 (5.619) Accm: 4.17 (4.17) Acct: 6.40 (6.40) proj_loss: -0.6152 (-0.6152) time: 0.9221 data: 0.0002 [11-26 04:15:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 417/1669] eta: 0:19:14 tlr: 0.00015 tnm: 0.26 Lm: 6.532 (6.532) Lt: 5.837 (5.837) Accm: 3.14 (3.14) Acct: 4.79 (4.79) proj_loss: -0.6420 (-0.6420) time: 0.9221 data: 0.0003 [11-26 04:15:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 417/1669] eta: 0:19:14 tlr: 0.00015 tnm: 0.26 Lm: 6.350 (6.350) Lt: 5.601 (5.601) Accm: 3.63 (3.63) Acct: 5.54 (5.54) proj_loss: -0.6262 (-0.6262) time: 0.9221 data: 0.0003 [11-26 04:15:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 417/1669] eta: 0:19:14 tlr: 0.00015 tnm: 0.26 Lm: 6.501 (6.501) Lt: 5.761 (5.761) Accm: 3.04 (3.04) Acct: 5.22 (5.22) proj_loss: -0.6196 (-0.6196) time: 0.9221 data: 0.0003 [11-26 04:15:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 417/1669] eta: 0:19:14 tlr: 0.00015 tnm: 0.26 Lm: 6.578 (6.578) Lt: 5.866 (5.866) Accm: 3.26 (3.26) Acct: 5.04 (5.04) proj_loss: -0.6183 (-0.6183) time: 0.9222 data: 0.0002 [11-26 04:22:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 834/1669] eta: 0:12:50 tlr: 0.00015 tnm: 0.26 Lm: 6.539 (6.438) Lt: 5.861 (5.688) Accm: 3.03 (3.43) Acct: 4.99 (5.36) proj_loss: -0.6058 (-0.6194) time: 0.9252 data: 0.0003 [11-26 04:22:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 834/1669] eta: 0:12:50 tlr: 0.00015 tnm: 0.26 Lm: 6.313 (6.308) Lt: 5.584 (5.566) Accm: 4.40 (4.25) Acct: 6.82 (6.54) proj_loss: -0.6217 (-0.6173) time: 0.9252 data: 0.0002 [11-26 04:22:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 834/1669] eta: 0:12:50 tlr: 0.00015 tnm: 0.26 Lm: 6.562 (6.484) Lt: 5.840 (5.773) Accm: 3.45 (3.55) Acct: 5.17 (5.27) proj_loss: -0.6433 (-0.6314) time: 0.9252 data: 0.0002 [11-26 04:22:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 834/1669] eta: 0:12:50 tlr: 0.00015 tnm: 0.26 Lm: 6.410 (6.328) Lt: 5.658 (5.583) Accm: 3.48 (3.95) Acct: 5.79 (6.20) proj_loss: -0.6104 (-0.6101) time: 0.9252 data: 0.0003 [11-26 04:22:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 834/1669] eta: 0:12:50 tlr: 0.00015 tnm: 0.26 Lm: 6.422 (6.495) Lt: 5.788 (5.821) Accm: 3.38 (3.22) Acct: 5.27 (4.95) proj_loss: -0.6394 (-0.6390) time: 0.9252 data: 0.0003 [11-26 04:22:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 834/1669] eta: 0:12:50 tlr: 0.00015 tnm: 0.26 Lm: 6.292 (6.286) Lt: 5.550 (5.552) Accm: 3.82 (3.92) Acct: 6.10 (6.11) proj_loss: -0.6220 (-0.6236) time: 0.9252 data: 0.0003 [11-26 04:22:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 834/1669] eta: 0:12:50 tlr: 0.00015 tnm: 0.26 Lm: 6.564 (6.492) Lt: 5.859 (5.774) Accm: 3.38 (3.49) Acct: 5.13 (5.52) proj_loss: -0.6255 (-0.6207) time: 0.9252 data: 0.0003 [11-26 04:22:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [ 834/1669] eta: 0:12:50 tlr: 0.00015 tnm: 0.26 Lm: 6.459 (6.424) Lt: 5.727 (5.662) Accm: 3.10 (3.53) Acct: 5.30 (5.80) proj_loss: -0.6253 (-0.6313) time: 0.9253 data: 0.0002 [11-26 04:28:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1251/1669] eta: 0:06:28 tlr: 0.00015 tnm: 0.25 Lm: 6.373 (6.390) Lt: 5.648 (5.638) Accm: 3.39 (3.56) Acct: 5.51 (5.78) proj_loss: -0.6266 (-0.6305) time: 0.9210 data: 0.0002 [11-26 04:28:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1251/1669] eta: 0:06:28 tlr: 0.00015 tnm: 0.25 Lm: 6.317 (6.377) Lt: 5.619 (5.649) Accm: 4.12 (4.04) Acct: 6.22 (6.21) proj_loss: -0.6233 (-0.6223) time: 0.9210 data: 0.0002 [11-26 04:28:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1251/1669] eta: 0:06:28 tlr: 0.00015 tnm: 0.25 Lm: 6.347 (6.317) Lt: 5.613 (5.579) Accm: 3.93 (4.06) Acct: 6.32 (6.36) proj_loss: -0.6129 (-0.6168) time: 0.9210 data: 0.0002 [11-26 04:28:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1251/1669] eta: 0:06:28 tlr: 0.00015 tnm: 0.25 Lm: 6.425 (6.435) Lt: 5.704 (5.722) Accm: 3.77 (3.69) Acct: 5.46 (5.58) proj_loss: -0.6377 (-0.6316) time: 0.9210 data: 0.0002 [11-26 04:28:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1251/1669] eta: 0:06:28 tlr: 0.00015 tnm: 0.25 Lm: 6.292 (6.314) Lt: 5.569 (5.586) Accm: 3.82 (3.86) Acct: 6.03 (5.99) proj_loss: -0.6212 (-0.6224) time: 0.9210 data: 0.0002 [11-26 04:28:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1251/1669] eta: 0:06:28 tlr: 0.00015 tnm: 0.25 Lm: 6.546 (6.467) Lt: 5.866 (5.733) Accm: 3.18 (3.41) Acct: 5.01 (5.28) proj_loss: -0.6059 (-0.6161) time: 0.9210 data: 0.0002 [11-26 04:28:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1251/1669] eta: 0:06:28 tlr: 0.00015 tnm: 0.25 Lm: 6.540 (6.498) Lt: 5.802 (5.767) Accm: 3.35 (3.45) Acct: 5.13 (5.42) proj_loss: -0.6258 (-0.6237) time: 0.9210 data: 0.0003 [11-26 04:28:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1251/1669] eta: 0:06:28 tlr: 0.00015 tnm: 0.25 Lm: 6.515 (6.524) Lt: 5.824 (5.830) Accm: 3.26 (3.20) Acct: 5.27 (5.03) proj_loss: -0.6362 (-0.6343) time: 0.9210 data: 0.0003 [11-26 04:35:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.27 Lm: 6.574 (6.534) Lt: 5.833 (5.831) Accm: 3.31 (3.22) Acct: 5.27 (5.04) proj_loss: -0.6330 (-0.6324) time: 0.9249 data: 0.0017 [11-26 04:35:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 152/350] Total time: 0:25:47 (0.927 s / it) [11-26 04:35:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.27 Lm: 6.293 (6.312) Lt: 5.568 (5.570) Accm: 3.92 (4.03) Acct: 6.06 (6.30) proj_loss: -0.6132 (-0.6161) time: 0.9249 data: 0.0015 [11-26 04:35:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.27 Lm: 6.459 (6.422) Lt: 5.727 (5.673) Accm: 3.23 (3.50) Acct: 5.30 (5.62) proj_loss: -0.6253 (-0.6273) time: 0.9249 data: 0.0021 [11-26 04:35:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.27 Lm: 6.320 (6.393) Lt: 5.654 (5.677) Accm: 3.83 (3.95) Acct: 5.61 (6.08) proj_loss: -0.6249 (-0.6238) time: 0.9249 data: 0.0019 [11-26 04:35:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.27 Lm: 6.292 (6.287) Lt: 5.550 (5.532) Accm: 3.82 (3.98) Acct: 6.10 (6.15) proj_loss: -0.6204 (-0.6189) time: 0.9249 data: 0.0018 [11-26 04:35:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.27 Lm: 6.539 (6.438) Lt: 5.861 (5.679) Accm: 3.34 (3.49) Acct: 5.03 (5.50) proj_loss: -0.6061 (-0.6149) time: 0.9249 data: 0.0015 [11-26 04:35:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.27 Lm: 6.526 (6.503) Lt: 5.803 (5.774) Accm: 3.38 (3.44) Acct: 5.13 (5.51) proj_loss: -0.6260 (-0.6299) time: 0.9249 data: 0.0016 [11-26 04:35:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 152/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.27 Lm: 6.376 (6.423) Lt: 5.576 (5.693) Accm: 3.95 (3.74) Acct: 5.75 (5.72) proj_loss: -0.6321 (-0.6258) time: 0.9250 data: 0.0019 [11-26 04:35:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 152/350] Total time: 0:25:47 (0.927 s / it) [11-26 04:35:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 152/350] Total time: 0:25:47 (0.927 s / it) [11-26 04:35:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 152/350] Total time: 0:25:47 (0.927 s / it) [11-26 04:35:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 152/350] Total time: 0:25:47 (0.927 s / it) [11-26 04:35:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 152/350] Total time: 0:25:47 (0.927 s / it) [11-26 04:35:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 152/350] Total time: 0:25:47 (0.927 s / it) [11-26 04:35:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 152/350] Total time: 0:25:47 (0.927 s / it) [11-26 04:35:15] (/home/user/VAR/train.py , line 276)=> [ep152] (training ) Lm: 6.436 (6.450), Lt: 5.678 (5.697), Acc m&t: 3.57 5.59, Remain: 3 days, 13:03:17, Finish: 2024-11-29 01:38 [11-26 04:35:15] (/home/user/VAR/train.py , line 276)=> [ep152] (training ) Lm: 6.436 (6.450), Lt: 5.678 (5.697), Acc m&t: 3.57 5.59, Remain: 3 days, 13:03:17, Finish: 2024-11-29 01:38 [11-26 04:35:15] (/home/user/VAR/train.py , line 276)=> [ep152] (training ) Lm: 6.436 (6.450), Lt: 5.678 (5.697), Acc m&t: 3.57 5.59, Remain: 3 days, 13:01:19, Finish: 2024-11-29 01:36 [11-26 04:35:15] (/home/user/VAR/train.py , line 276)=> [ep152] (training ) Lm: 6.436 (6.450), Lt: 5.678 (5.697), Acc m&t: 3.57 5.59, Remain: 3 days, 13:01:38, Finish: 2024-11-29 01:36 [11-26 04:35:15] (/home/user/VAR/train.py , line 276)=> [ep152] (training ) Lm: 6.436 (6.450), Lt: 5.678 (5.697), Acc m&t: 3.57 5.59, Remain: 3 days, 13:03:05, Finish: 2024-11-29 01:38 [11-26 04:35:15] (/home/user/VAR/train.py , line 276)=> [ep152] (training ) Lm: 6.436 (6.450), Lt: 5.678 (5.697), Acc m&t: 3.57 5.59, Remain: 3 days, 13:02:31, Finish: 2024-11-29 01:37 [11-26 04:35:15] (/home/user/VAR/train.py , line 276)=> [ep152] (training ) Lm: 6.436 (6.450), Lt: 5.678 (5.697), Acc m&t: 3.57 5.59, Remain: 3 days, 13:02:36, Finish: 2024-11-29 01:37 [11-26 04:35:15] (/home/user/VAR/train.py , line 276)=> [ep152] (training ) Lm: 6.436 (6.450), Lt: 5.678 (5.697), Acc m&t: 3.57 5.59, Remain: 3 days, 13:04:10, Finish: 2024-11-29 01:39 [11-26 04:35:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 0/1669] eta: 0:24:30 tlr: 0.00015 tnm: 0.25 Lm: 6.582 (6.582) Lt: 5.908 (5.908) Accm: 3.18 (3.18) Acct: 5.23 (5.23) proj_loss: -0.6207 (-0.6207) time: 0.8810 data: 0.0003 [11-26 04:35:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 0/1669] eta: 0:24:36 tlr: 0.00015 tnm: 0.25 Lm: 6.627 (6.627) Lt: 5.890 (5.890) Accm: 2.99 (2.99) Acct: 4.68 (4.68) proj_loss: -0.6363 (-0.6363) time: 0.8846 data: 0.0003 [11-26 04:35:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 0/1669] eta: 0:24:31 tlr: 0.00015 tnm: 0.25 Lm: 6.359 (6.359) Lt: 5.580 (5.580) Accm: 3.66 (3.66) Acct: 5.54 (5.54) proj_loss: -0.6387 (-0.6387) time: 0.8817 data: 0.0004 [11-26 04:35:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 0/1669] eta: 0:24:38 tlr: 0.00015 tnm: 0.25 Lm: 6.042 (6.042) Lt: 5.183 (5.183) Accm: 5.06 (5.06) Acct: 7.68 (7.68) proj_loss: -0.6519 (-0.6519) time: 0.8859 data: 0.0004 [11-26 04:35:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 0/1669] eta: 0:24:38 tlr: 0.00015 tnm: 0.25 Lm: 6.455 (6.455) Lt: 5.599 (5.599) Accm: 3.48 (3.48) Acct: 6.06 (6.06) proj_loss: -0.5878 (-0.5878) time: 0.8860 data: 0.0004 [11-26 04:35:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 0/1669] eta: 0:24:38 tlr: 0.00015 tnm: 0.25 Lm: 6.544 (6.544) Lt: 5.771 (5.771) Accm: 3.29 (3.29) Acct: 5.41 (5.41) proj_loss: -0.5958 (-0.5958) time: 0.8861 data: 0.0004 [11-26 04:35:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 0/1669] eta: 0:24:39 tlr: 0.00015 tnm: 0.25 Lm: 6.111 (6.111) Lt: 5.388 (5.388) Accm: 4.98 (4.98) Acct: 7.33 (7.33) proj_loss: -0.6127 (-0.6127) time: 0.8862 data: 0.0004 [11-26 04:35:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 0/1669] eta: 0:24:38 tlr: 0.00015 tnm: 0.25 Lm: 6.466 (6.466) Lt: 5.662 (5.662) Accm: 3.41 (3.41) Acct: 5.23 (5.23) proj_loss: -0.6019 (-0.6019) time: 0.8861 data: 0.0004 [11-26 04:41:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 417/1669] eta: 0:19:16 tlr: 0.00015 tnm: 0.26 Lm: 6.504 (6.504) Lt: 5.768 (5.768) Accm: 3.45 (3.45) Acct: 4.94 (4.94) proj_loss: -0.6248 (-0.6248) time: 0.9222 data: 0.0003 [11-26 04:41:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 417/1669] eta: 0:19:16 tlr: 0.00015 tnm: 0.26 Lm: 6.364 (6.364) Lt: 5.629 (5.629) Accm: 3.84 (3.84) Acct: 5.61 (5.61) proj_loss: -0.6420 (-0.6420) time: 0.9222 data: 0.0002 [11-26 04:41:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 417/1669] eta: 0:19:16 tlr: 0.00015 tnm: 0.26 Lm: 6.348 (6.348) Lt: 5.513 (5.513) Accm: 3.93 (3.93) Acct: 6.15 (6.15) proj_loss: -0.6213 (-0.6213) time: 0.9222 data: 0.0002 [11-26 04:41:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 417/1669] eta: 0:19:16 tlr: 0.00015 tnm: 0.26 Lm: 6.532 (6.532) Lt: 5.808 (5.808) Accm: 3.07 (3.07) Acct: 4.73 (4.73) proj_loss: -0.6260 (-0.6260) time: 0.9222 data: 0.0002 [11-26 04:41:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 417/1669] eta: 0:19:16 tlr: 0.00015 tnm: 0.26 Lm: 6.579 (6.579) Lt: 5.860 (5.860) Accm: 3.17 (3.17) Acct: 5.15 (5.15) proj_loss: -0.6241 (-0.6241) time: 0.9222 data: 0.0002 [11-26 04:41:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 417/1669] eta: 0:19:16 tlr: 0.00015 tnm: 0.26 Lm: 6.276 (6.276) Lt: 5.568 (5.568) Accm: 4.30 (4.30) Acct: 6.53 (6.53) proj_loss: -0.6080 (-0.6080) time: 0.9222 data: 0.0003 [11-26 04:41:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 417/1669] eta: 0:19:16 tlr: 0.00015 tnm: 0.26 Lm: 6.525 (6.525) Lt: 5.707 (5.707) Accm: 3.30 (3.30) Acct: 5.41 (5.41) proj_loss: -0.5894 (-0.5894) time: 0.9222 data: 0.0003 [11-26 04:41:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 417/1669] eta: 0:19:16 tlr: 0.00015 tnm: 0.26 Lm: 6.543 (6.543) Lt: 5.812 (5.812) Accm: 3.13 (3.13) Acct: 4.87 (4.87) proj_loss: -0.6061 (-0.6061) time: 0.9222 data: 0.0003 [11-26 04:48:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 834/1669] eta: 0:12:50 tlr: 0.00015 tnm: 0.27 Lm: 6.543 (6.488) Lt: 5.771 (5.728) Accm: 3.29 (3.33) Acct: 5.41 (5.34) proj_loss: -0.6165 (-0.6255) time: 0.9238 data: 0.0003 [11-26 04:48:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 834/1669] eta: 0:12:50 tlr: 0.00015 tnm: 0.27 Lm: 6.547 (6.537) Lt: 5.758 (5.792) Accm: 3.16 (3.19) Acct: 4.79 (5.14) proj_loss: -0.6363 (-0.6315) time: 0.9238 data: 0.0002 [11-26 04:48:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 834/1669] eta: 0:12:50 tlr: 0.00015 tnm: 0.27 Lm: 6.466 (6.415) Lt: 5.662 (5.671) Accm: 3.48 (3.73) Acct: 5.23 (5.50) proj_loss: -0.6179 (-0.6225) time: 0.9238 data: 0.0003 [11-26 04:48:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 834/1669] eta: 0:12:50 tlr: 0.00015 tnm: 0.27 Lm: 6.513 (6.403) Lt: 5.694 (5.574) Accm: 3.29 (3.72) Acct: 4.89 (5.73) proj_loss: -0.6150 (-0.6192) time: 0.9238 data: 0.0003 [11-26 04:48:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 834/1669] eta: 0:12:50 tlr: 0.00015 tnm: 0.27 Lm: 6.370 (6.374) Lt: 5.618 (5.625) Accm: 3.77 (3.82) Acct: 5.68 (5.77) proj_loss: -0.6387 (-0.6309) time: 0.9238 data: 0.0002 [11-26 04:48:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 834/1669] eta: 0:12:50 tlr: 0.00015 tnm: 0.27 Lm: 6.441 (6.406) Lt: 5.749 (5.690) Accm: 3.61 (3.85) Acct: 5.72 (5.93) proj_loss: -0.6127 (-0.6119) time: 0.9238 data: 0.0003 [11-26 04:48:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 834/1669] eta: 0:12:50 tlr: 0.00015 tnm: 0.27 Lm: 6.576 (6.545) Lt: 5.811 (5.815) Accm: 3.18 (3.25) Acct: 5.10 (5.13) proj_loss: -0.6230 (-0.6237) time: 0.9238 data: 0.0003 [11-26 04:48:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [ 834/1669] eta: 0:12:50 tlr: 0.00015 tnm: 0.27 Lm: 6.470 (6.507) Lt: 5.768 (5.728) Accm: 3.42 (3.34) Acct: 5.34 (5.38) proj_loss: -0.5911 (-0.6002) time: 0.9238 data: 0.0003 [11-26 04:54:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1251/1669] eta: 0:06:29 tlr: 0.00015 tnm: 0.26 Lm: 6.492 (6.509) Lt: 5.789 (5.748) Accm: 3.27 (3.23) Acct: 5.04 (5.17) proj_loss: -0.6057 (-0.6052) time: 0.9244 data: 0.0002 [11-26 04:54:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1251/1669] eta: 0:06:29 tlr: 0.00015 tnm: 0.26 Lm: 6.572 (6.552) Lt: 5.802 (5.805) Accm: 3.07 (3.11) Acct: 4.73 (5.00) proj_loss: -0.6276 (-0.6283) time: 0.9244 data: 0.0002 [11-26 04:54:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1251/1669] eta: 0:06:29 tlr: 0.00015 tnm: 0.26 Lm: 6.486 (6.437) Lt: 5.758 (5.710) Accm: 3.34 (3.66) Acct: 5.23 (5.64) proj_loss: -0.6080 (-0.6055) time: 0.9244 data: 0.0003 [11-26 04:54:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1251/1669] eta: 0:06:29 tlr: 0.00015 tnm: 0.26 Lm: 6.417 (6.382) Lt: 5.632 (5.573) Accm: 3.58 (3.76) Acct: 5.56 (5.85) proj_loss: -0.6242 (-0.6227) time: 0.9244 data: 0.0003 [11-26 04:54:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1251/1669] eta: 0:06:29 tlr: 0.00015 tnm: 0.26 Lm: 6.519 (6.490) Lt: 5.812 (5.759) Accm: 3.23 (3.29) Acct: 5.17 (5.23) proj_loss: -0.6321 (-0.6310) time: 0.9244 data: 0.0003 [11-26 04:54:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1251/1669] eta: 0:06:29 tlr: 0.00015 tnm: 0.26 Lm: 6.382 (6.408) Lt: 5.648 (5.653) Accm: 3.72 (3.66) Acct: 5.61 (5.54) proj_loss: -0.6237 (-0.6218) time: 0.9244 data: 0.0002 [11-26 04:54:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1251/1669] eta: 0:06:29 tlr: 0.00015 tnm: 0.26 Lm: 6.579 (6.560) Lt: 5.860 (5.840) Accm: 3.17 (3.07) Acct: 5.08 (4.88) proj_loss: -0.6218 (-0.6200) time: 0.9244 data: 0.0003 [11-26 04:54:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1251/1669] eta: 0:06:29 tlr: 0.00015 tnm: 0.26 Lm: 6.475 (6.432) Lt: 5.692 (5.684) Accm: 3.45 (3.56) Acct: 4.94 (5.29) proj_loss: -0.6162 (-0.6205) time: 0.9244 data: 0.0003 [11-26 05:01:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.484 (6.474) Lt: 5.723 (5.725) Accm: 3.48 (3.56) Acct: 5.23 (5.32) proj_loss: -0.6170 (-0.6198) time: 0.9250 data: 0.0015 [11-26 05:01:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 153/350] Total time: 0:25:51 (0.930 s / it) [11-26 05:01:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.576 (6.537) Lt: 5.811 (5.806) Accm: 3.16 (3.08) Acct: 5.10 (4.95) proj_loss: -0.6230 (-0.6213) time: 0.9251 data: 0.0015 [11-26 05:01:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.394 (6.417) Lt: 5.677 (5.669) Accm: 3.66 (3.63) Acct: 5.54 (5.45) proj_loss: -0.6224 (-0.6219) time: 0.9251 data: 0.0019 [11-26 05:01:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.470 (6.458) Lt: 5.768 (5.666) Accm: 3.42 (3.44) Acct: 5.34 (5.55) proj_loss: -0.6204 (-0.6111) time: 0.9251 data: 0.0021 [11-26 05:01:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.490 (6.404) Lt: 5.694 (5.604) Accm: 3.29 (3.59) Acct: 4.89 (5.57) proj_loss: -0.6173 (-0.6216) time: 0.9251 data: 0.0020 [11-26 05:01:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.496 (6.442) Lt: 5.771 (5.688) Accm: 3.29 (3.39) Acct: 5.41 (5.43) proj_loss: -0.6246 (-0.6298) time: 0.9251 data: 0.0017 [11-26 05:01:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.531 (6.460) Lt: 5.762 (5.720) Accm: 3.07 (3.53) Acct: 4.75 (5.44) proj_loss: -0.6033 (-0.6029) time: 0.9251 data: 0.0015 [11-26 05:01:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 153/350] [1668/1669] eta: 0:00:00 tlr: 0.00015 tnm: 0.25 Lm: 6.547 (6.523) Lt: 5.758 (5.766) Accm: 3.16 (3.18) Acct: 4.79 (5.14) proj_loss: -0.6188 (-0.6197) time: 0.9251 data: 0.0017 [11-26 05:01:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 153/350] Total time: 0:25:51 (0.930 s / it) [11-26 05:01:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 153/350] Total time: 0:25:51 (0.930 s / it) [11-26 05:01:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 153/350] Total time: 0:25:51 (0.930 s / it) [11-26 05:01:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 153/350] Total time: 0:25:51 (0.930 s / it) [11-26 05:01:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 153/350] Total time: 0:25:51 (0.930 s / it) [11-26 05:01:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 153/350] Total time: 0:25:51 (0.930 s / it) [11-26 05:01:07] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 153/350] Total time: 0:25:51 (0.930 s / it) [11-26 05:01:07] (/home/user/VAR/train.py , line 276)=> [ep153] (training ) Lm: 6.436 (6.446), Lt: 5.678 (5.689), Acc m&t: 3.57 5.59, Remain: 3 days, 12:41:29, Finish: 2024-11-29 01:42 [11-26 05:01:07] (/home/user/VAR/train.py , line 276)=> [ep153] (training ) Lm: 6.436 (6.446), Lt: 5.678 (5.689), Acc m&t: 3.57 5.59, Remain: 3 days, 12:42:11, Finish: 2024-11-29 01:43 [11-26 05:01:07] (/home/user/VAR/train.py , line 276)=> [ep153] (training ) Lm: 6.436 (6.446), Lt: 5.678 (5.689), Acc m&t: 3.57 5.59, Remain: 3 days, 12:41:31, Finish: 2024-11-29 01:42 [11-26 05:01:07] (/home/user/VAR/train.py , line 276)=> [ep153] (training ) Lm: 6.436 (6.446), Lt: 5.678 (5.689), Acc m&t: 3.57 5.59, Remain: 3 days, 12:41:56, Finish: 2024-11-29 01:43 [11-26 05:01:07] (/home/user/VAR/train.py , line 276)=> [ep153] (training ) Lm: 6.436 (6.446), Lt: 5.678 (5.689), Acc m&t: 3.57 5.59, Remain: 3 days, 12:41:36, Finish: 2024-11-29 01:42 [11-26 05:01:07] (/home/user/VAR/train.py , line 276)=> [ep153] (training ) Lm: 6.436 (6.446), Lt: 5.678 (5.689), Acc m&t: 3.57 5.59, Remain: 3 days, 12:41:59, Finish: 2024-11-29 01:43 [11-26 05:01:07] (/home/user/VAR/train.py , line 276)=> [ep153] (training ) Lm: 6.436 (6.446), Lt: 5.678 (5.689), Acc m&t: 3.57 5.59, Remain: 3 days, 12:42:29, Finish: 2024-11-29 01:43 [11-26 05:01:07] (/home/user/VAR/train.py , line 276)=> [ep153] (training ) Lm: 6.436 (6.446), Lt: 5.678 (5.689), Acc m&t: 3.57 5.59, Remain: 3 days, 12:41:37, Finish: 2024-11-29 01:42 [11-26 05:01:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 0/1669] eta: 0:25:07 tlr: 0.00015 tnm: 0.25 Lm: 6.535 (6.535) Lt: 5.871 (5.871) Accm: 3.10 (3.10) Acct: 4.72 (4.72) proj_loss: -0.6210 (-0.6210) time: 0.9033 data: 0.0003 [11-26 05:01:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 0/1669] eta: 0:25:08 tlr: 0.00015 tnm: 0.25 Lm: 6.346 (6.346) Lt: 5.483 (5.483) Accm: 4.09 (4.09) Acct: 6.89 (6.89) proj_loss: -0.6369 (-0.6369) time: 0.9040 data: 0.0003 [11-26 05:01:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 0/1669] eta: 0:25:25 tlr: 0.00015 tnm: 0.25 Lm: 6.556 (6.556) Lt: 5.827 (5.827) Accm: 3.28 (3.28) Acct: 5.48 (5.48) proj_loss: -0.6300 (-0.6300) time: 0.9143 data: 0.0003 [11-26 05:01:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 0/1669] eta: 0:25:25 tlr: 0.00015 tnm: 0.25 Lm: 6.627 (6.627) Lt: 5.937 (5.937) Accm: 2.87 (2.87) Acct: 4.55 (4.55) proj_loss: -0.5821 (-0.5821) time: 0.9143 data: 0.0003 [11-26 05:01:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 0/1669] eta: 0:25:26 tlr: 0.00015 tnm: 0.25 Lm: 6.301 (6.301) Lt: 5.481 (5.481) Accm: 3.90 (3.90) Acct: 6.16 (6.16) proj_loss: -0.5999 (-0.5999) time: 0.9144 data: 0.0004 [11-26 05:01:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 0/1669] eta: 0:25:23 tlr: 0.00015 tnm: 0.25 Lm: 6.472 (6.472) Lt: 5.749 (5.749) Accm: 3.37 (3.37) Acct: 5.27 (5.27) proj_loss: -0.6337 (-0.6337) time: 0.9128 data: 0.0004 [11-26 05:01:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 0/1669] eta: 0:25:08 tlr: 0.00015 tnm: 0.25 Lm: 6.424 (6.424) Lt: 5.668 (5.668) Accm: 3.76 (3.76) Acct: 5.79 (5.79) proj_loss: -0.6104 (-0.6104) time: 0.9036 data: 0.0004 [11-26 05:01:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 0/1669] eta: 0:25:25 tlr: 0.00015 tnm: 0.25 Lm: 6.415 (6.415) Lt: 5.610 (5.610) Accm: 3.58 (3.58) Acct: 5.92 (5.92) proj_loss: -0.6015 (-0.6015) time: 0.9141 data: 0.0005 [11-26 05:07:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 417/1669] eta: 0:19:15 tlr: 0.00015 tnm: 0.26 Lm: 6.429 (6.429) Lt: 5.627 (5.627) Accm: 3.46 (3.46) Acct: 5.80 (5.80) proj_loss: -0.5898 (-0.5898) time: 0.9232 data: 0.0003 [11-26 05:07:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 417/1669] eta: 0:19:15 tlr: 0.00015 tnm: 0.26 Lm: 6.568 (6.568) Lt: 5.844 (5.844) Accm: 3.16 (3.16) Acct: 5.01 (5.01) proj_loss: -0.5933 (-0.5933) time: 0.9232 data: 0.0002 [11-26 05:07:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 417/1669] eta: 0:19:15 tlr: 0.00015 tnm: 0.26 Lm: 6.390 (6.390) Lt: 5.597 (5.597) Accm: 3.95 (3.95) Acct: 6.39 (6.39) proj_loss: -0.6399 (-0.6399) time: 0.9232 data: 0.0002 [11-26 05:07:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 417/1669] eta: 0:19:15 tlr: 0.00015 tnm: 0.26 Lm: 6.528 (6.528) Lt: 5.799 (5.799) Accm: 3.34 (3.34) Acct: 5.13 (5.13) proj_loss: -0.6011 (-0.6011) time: 0.9232 data: 0.0002 [11-26 05:07:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 417/1669] eta: 0:19:15 tlr: 0.00015 tnm: 0.26 Lm: 6.498 (6.498) Lt: 5.760 (5.760) Accm: 3.23 (3.23) Acct: 5.04 (5.04) proj_loss: -0.6084 (-0.6084) time: 0.9232 data: 0.0002 [11-26 05:07:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 417/1669] eta: 0:19:15 tlr: 0.00015 tnm: 0.26 Lm: 6.505 (6.505) Lt: 5.771 (5.771) Accm: 3.18 (3.18) Acct: 4.94 (4.94) proj_loss: -0.6128 (-0.6128) time: 0.9232 data: 0.0003 [11-26 05:07:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 417/1669] eta: 0:19:15 tlr: 0.00015 tnm: 0.26 Lm: 6.451 (6.451) Lt: 5.715 (5.715) Accm: 3.56 (3.56) Acct: 5.66 (5.66) proj_loss: -0.6059 (-0.6059) time: 0.9233 data: 0.0003 [11-26 05:07:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 417/1669] eta: 0:19:15 tlr: 0.00015 tnm: 0.26 Lm: 6.701 (6.701) Lt: 5.967 (5.967) Accm: 2.75 (2.75) Acct: 4.30 (4.30) proj_loss: -0.6302 (-0.6302) time: 0.9233 data: 0.0002 [11-26 05:13:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 834/1669] eta: 0:12:50 tlr: 0.00014 tnm: 0.25 Lm: 6.659 (6.687) Lt: 6.005 (5.980) Accm: 2.91 (2.80) Acct: 4.75 (4.45) proj_loss: -0.6300 (-0.6199) time: 0.9214 data: 0.0002 [11-26 05:13:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 834/1669] eta: 0:12:50 tlr: 0.00014 tnm: 0.25 Lm: 6.522 (6.506) Lt: 5.752 (5.758) Accm: 3.31 (3.25) Acct: 4.72 (4.92) proj_loss: -0.5957 (-0.6016) time: 0.9214 data: 0.0002 [11-26 05:13:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 834/1669] eta: 0:12:50 tlr: 0.00014 tnm: 0.25 Lm: 6.498 (6.503) Lt: 5.757 (5.766) Accm: 3.37 (3.28) Acct: 5.23 (5.04) proj_loss: -0.6188 (-0.6148) time: 0.9214 data: 0.0003 [11-26 05:13:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 834/1669] eta: 0:12:50 tlr: 0.00014 tnm: 0.25 Lm: 6.375 (6.426) Lt: 5.660 (5.697) Accm: 3.64 (3.59) Acct: 5.17 (5.45) proj_loss: -0.6025 (-0.6048) time: 0.9214 data: 0.0003 [11-26 05:13:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 834/1669] eta: 0:12:50 tlr: 0.00014 tnm: 0.25 Lm: 6.574 (6.543) Lt: 5.914 (5.837) Accm: 3.29 (3.32) Acct: 4.61 (4.96) proj_loss: -0.6104 (-0.6050) time: 0.9214 data: 0.0002 [11-26 05:13:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 834/1669] eta: 0:12:50 tlr: 0.00014 tnm: 0.25 Lm: 6.508 (6.456) Lt: 5.750 (5.722) Accm: 3.45 (3.42) Acct: 5.48 (5.37) proj_loss: -0.6044 (-0.6000) time: 0.9214 data: 0.0003 [11-26 05:13:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 834/1669] eta: 0:12:50 tlr: 0.00014 tnm: 0.25 Lm: 6.346 (6.342) Lt: 5.526 (5.573) Accm: 3.80 (3.87) Acct: 5.89 (6.11) proj_loss: -0.6369 (-0.6333) time: 0.9214 data: 0.0002 [11-26 05:13:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [ 834/1669] eta: 0:12:50 tlr: 0.00014 tnm: 0.25 Lm: 6.415 (6.379) Lt: 5.610 (5.587) Accm: 3.58 (3.63) Acct: 5.92 (5.89) proj_loss: -0.6015 (-0.5981) time: 0.9214 data: 0.0003 [11-26 05:20:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [1251/1669] eta: 0:06:25 tlr: 0.00014 tnm: 0.25 Lm: 6.429 (6.406) Lt: 5.627 (5.617) Accm: 3.47 (3.57) Acct: 5.80 (5.76) proj_loss: -0.6082 (-0.6053) time: 0.9206 data: 0.0002 [11-26 05:20:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [1251/1669] eta: 0:06:25 tlr: 0.00014 tnm: 0.25 Lm: 6.351 (6.345) Lt: 5.568 (5.582) Accm: 3.77 (3.83) Acct: 5.91 (6.06) proj_loss: -0.6350 (-0.6333) time: 0.9206 data: 0.0002 [11-26 05:20:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [1251/1669] eta: 0:06:25 tlr: 0.00014 tnm: 0.25 Lm: 6.492 (6.461) Lt: 5.699 (5.704) Accm: 3.42 (3.41) Acct: 5.60 (5.46) proj_loss: -0.5975 (-0.5976) time: 0.9206 data: 0.0002 [11-26 05:20:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [1251/1669] eta: 0:06:25 tlr: 0.00014 tnm: 0.25 Lm: 6.608 (6.598) Lt: 5.916 (5.876) Accm: 3.10 (3.00) Acct: 5.11 (4.73) proj_loss: -0.6302 (-0.6238) time: 0.9206 data: 0.0002 [11-26 05:20:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [1251/1669] eta: 0:06:25 tlr: 0.00014 tnm: 0.25 Lm: 6.492 (6.484) Lt: 5.701 (5.730) Accm: 3.33 (3.42) Acct: 5.04 (5.27) proj_loss: -0.6011 (-0.6028) time: 0.9205 data: 0.0002 [11-26 05:20:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [1251/1669] eta: 0:06:25 tlr: 0.00014 tnm: 0.25 Lm: 6.436 (6.444) Lt: 5.696 (5.706) Accm: 3.57 (3.57) Acct: 5.13 (5.36) proj_loss: -0.6072 (-0.6083) time: 0.9206 data: 0.0003 [11-26 05:20:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [1251/1669] eta: 0:06:25 tlr: 0.00014 tnm: 0.25 Lm: 6.485 (6.431) Lt: 5.753 (5.654) Accm: 3.43 (3.62) Acct: 5.25 (5.59) proj_loss: -0.6174 (-0.6151) time: 0.9206 data: 0.0002 [11-26 05:20:22] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [1251/1669] eta: 0:06:25 tlr: 0.00014 tnm: 0.25 Lm: 6.499 (6.484) Lt: 5.791 (5.750) Accm: 3.53 (3.61) Acct: 5.20 (5.48) proj_loss: -0.6117 (-0.6091) time: 0.9206 data: 0.0003 [11-26 05:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.424 (6.470) Lt: 5.669 (5.734) Accm: 3.29 (3.52) Acct: 5.06 (5.39) proj_loss: -0.6130 (-0.6141) time: 0.9253 data: 0.0016 [11-26 05:26:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 154/350] Total time: 0:25:39 (0.923 s / it) [11-26 05:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.648 (6.608) Lt: 5.842 (5.869) Accm: 3.19 (3.04) Acct: 5.10 (4.81) proj_loss: -0.6300 (-0.6170) time: 0.9253 data: 0.0017 [11-26 05:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.472 (6.389) Lt: 5.749 (5.607) Accm: 3.50 (3.75) Acct: 5.27 (5.81) proj_loss: -0.6188 (-0.6164) time: 0.9253 data: 0.0018 [11-26 05:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.510 (6.489) Lt: 5.752 (5.742) Accm: 3.31 (3.39) Acct: 4.72 (5.14) proj_loss: -0.6064 (-0.6091) time: 0.9253 data: 0.0016 [11-26 05:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.375 (6.382) Lt: 5.660 (5.626) Accm: 3.64 (3.85) Acct: 5.17 (5.92) proj_loss: -0.6120 (-0.6121) time: 0.9253 data: 0.0021 [11-26 05:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.357 (6.353) Lt: 5.610 (5.615) Accm: 3.73 (3.80) Acct: 5.89 (5.93) proj_loss: -0.6369 (-0.6362) time: 0.9253 data: 0.0014 [11-26 05:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.442 (6.425) Lt: 5.645 (5.641) Accm: 3.47 (3.55) Acct: 5.68 (5.72) proj_loss: -0.6074 (-0.6057) time: 0.9253 data: 0.0015 [11-26 05:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 154/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.508 (6.513) Lt: 5.750 (5.762) Accm: 3.39 (3.31) Acct: 5.48 (5.27) proj_loss: -0.6044 (-0.6006) time: 0.9253 data: 0.0015 [11-26 05:26:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 154/350] Total time: 0:25:39 (0.923 s / it) [11-26 05:26:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 154/350] Total time: 0:25:39 (0.923 s / it) [11-26 05:26:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 154/350] Total time: 0:25:39 (0.923 s / it) [11-26 05:26:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 154/350] Total time: 0:25:39 (0.923 s / it) [11-26 05:26:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 154/350] Total time: 0:25:39 (0.923 s / it) [11-26 05:26:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 154/350] Total time: 0:25:39 (0.923 s / it) [11-26 05:26:47] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 154/350] Total time: 0:25:39 (0.923 s / it) [11-26 05:26:47] (/home/user/VAR/train.py , line 276)=> [ep154] (training ) Lm: 6.436 (6.447), Lt: 5.678 (5.698), Acc m&t: 3.57 5.59, Remain: 3 days, 12:08:10, Finish: 2024-11-29 01:34 [11-26 05:26:47] (/home/user/VAR/train.py , line 276)=> [ep154] (training ) Lm: 6.436 (6.447), Lt: 5.678 (5.698), Acc m&t: 3.57 5.59, Remain: 3 days, 12:15:17, Finish: 2024-11-29 01:42 [11-26 05:26:47] (/home/user/VAR/train.py , line 276)=> [ep154] (training ) Lm: 6.436 (6.447), Lt: 5.678 (5.698), Acc m&t: 3.57 5.59, Remain: 3 days, 12:10:33, Finish: 2024-11-29 01:37 [11-26 05:26:47] (/home/user/VAR/train.py , line 276)=> [ep154] (training ) Lm: 6.436 (6.447), Lt: 5.678 (5.698), Acc m&t: 3.57 5.59, Remain: 3 days, 12:10:16, Finish: 2024-11-29 01:37 [11-26 05:26:47] (/home/user/VAR/train.py , line 276)=> [ep154] (training ) Lm: 6.436 (6.447), Lt: 5.678 (5.698), Acc m&t: 3.57 5.59, Remain: 3 days, 12:11:11, Finish: 2024-11-29 01:37 [11-26 05:26:47] (/home/user/VAR/train.py , line 276)=> [ep154] (training ) Lm: 6.436 (6.447), Lt: 5.678 (5.698), Acc m&t: 3.57 5.59, Remain: 3 days, 12:08:52, Finish: 2024-11-29 01:35 [11-26 05:26:47] (/home/user/VAR/train.py , line 276)=> [ep154] (training ) Lm: 6.436 (6.447), Lt: 5.678 (5.698), Acc m&t: 3.57 5.59, Remain: 3 days, 12:07:55, Finish: 2024-11-29 01:34 [11-26 05:26:47] (/home/user/VAR/train.py , line 276)=> [ep154] (training ) Lm: 6.436 (6.447), Lt: 5.678 (5.698), Acc m&t: 3.57 5.59, Remain: 3 days, 12:11:47, Finish: 2024-11-29 01:38 [11-26 05:26:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 0/1669] eta: 0:24:34 tlr: 0.00014 tnm: 0.25 Lm: 6.527 (6.527) Lt: 5.819 (5.819) Accm: 3.74 (3.74) Acct: 5.85 (5.85) proj_loss: -0.6126 (-0.6126) time: 0.8833 data: 0.0003 [11-26 05:26:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 0/1669] eta: 0:24:34 tlr: 0.00014 tnm: 0.25 Lm: 6.341 (6.341) Lt: 5.565 (5.565) Accm: 3.69 (3.69) Acct: 6.03 (6.03) proj_loss: -0.6056 (-0.6056) time: 0.8835 data: 0.0004 [11-26 05:26:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 0/1669] eta: 0:24:34 tlr: 0.00014 tnm: 0.25 Lm: 6.247 (6.247) Lt: 5.478 (5.478) Accm: 4.95 (4.95) Acct: 7.44 (7.44) proj_loss: -0.6455 (-0.6455) time: 0.8834 data: 0.0004 [11-26 05:26:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 0/1669] eta: 0:24:34 tlr: 0.00014 tnm: 0.25 Lm: 6.649 (6.649) Lt: 5.862 (5.862) Accm: 2.72 (2.72) Acct: 4.61 (4.61) proj_loss: -0.6073 (-0.6073) time: 0.8834 data: 0.0003 [11-26 05:26:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 0/1669] eta: 0:24:29 tlr: 0.00014 tnm: 0.25 Lm: 6.577 (6.577) Lt: 5.759 (5.759) Accm: 3.09 (3.09) Acct: 5.03 (5.03) proj_loss: -0.6121 (-0.6121) time: 0.8807 data: 0.0004 [11-26 05:26:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 0/1669] eta: 0:24:34 tlr: 0.00014 tnm: 0.25 Lm: 6.269 (6.269) Lt: 5.543 (5.543) Accm: 4.20 (4.20) Acct: 6.23 (6.23) proj_loss: -0.6014 (-0.6014) time: 0.8837 data: 0.0003 [11-26 05:26:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 0/1669] eta: 0:24:35 tlr: 0.00014 tnm: 0.25 Lm: 6.457 (6.457) Lt: 5.724 (5.724) Accm: 3.54 (3.54) Acct: 5.44 (5.44) proj_loss: -0.6185 (-0.6185) time: 0.8838 data: 0.0003 [11-26 05:26:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 0/1669] eta: 0:24:35 tlr: 0.00014 tnm: 0.25 Lm: 6.377 (6.377) Lt: 5.658 (5.658) Accm: 4.05 (4.05) Acct: 6.44 (6.44) proj_loss: -0.6149 (-0.6149) time: 0.8842 data: 0.0003 [11-26 05:33:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 417/1669] eta: 0:19:45 tlr: 0.00014 tnm: 0.26 Lm: 6.370 (6.370) Lt: 5.657 (5.657) Accm: 3.93 (3.93) Acct: 5.91 (5.91) proj_loss: -0.6277 (-0.6277) time: 0.9239 data: 0.0003 [11-26 05:33:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 417/1669] eta: 0:19:45 tlr: 0.00014 tnm: 0.26 Lm: 6.362 (6.362) Lt: 5.575 (5.575) Accm: 3.74 (3.74) Acct: 5.84 (5.84) proj_loss: -0.6085 (-0.6085) time: 0.9239 data: 0.0003 [11-26 05:33:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 417/1669] eta: 0:19:45 tlr: 0.00014 tnm: 0.26 Lm: 6.508 (6.508) Lt: 5.674 (5.674) Accm: 3.34 (3.34) Acct: 5.53 (5.53) proj_loss: -0.6116 (-0.6116) time: 0.9239 data: 0.0003 [11-26 05:33:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 417/1669] eta: 0:19:45 tlr: 0.00014 tnm: 0.26 Lm: 6.469 (6.469) Lt: 5.670 (5.670) Accm: 3.52 (3.52) Acct: 5.46 (5.46) proj_loss: -0.6124 (-0.6124) time: 0.9239 data: 0.0003 [11-26 05:33:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 417/1669] eta: 0:19:45 tlr: 0.00014 tnm: 0.26 Lm: 6.341 (6.341) Lt: 5.572 (5.572) Accm: 4.03 (4.03) Acct: 6.35 (6.35) proj_loss: -0.6278 (-0.6278) time: 0.9239 data: 0.0003 [11-26 05:33:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 417/1669] eta: 0:19:45 tlr: 0.00014 tnm: 0.26 Lm: 6.345 (6.345) Lt: 5.586 (5.586) Accm: 3.82 (3.82) Acct: 5.87 (5.87) proj_loss: -0.6134 (-0.6134) time: 0.9239 data: 0.0002 [11-26 05:33:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 417/1669] eta: 0:19:45 tlr: 0.00014 tnm: 0.26 Lm: 6.464 (6.464) Lt: 5.724 (5.724) Accm: 3.95 (3.95) Acct: 6.34 (6.34) proj_loss: -0.6093 (-0.6093) time: 0.9239 data: 0.0002 [11-26 05:33:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 417/1669] eta: 0:19:45 tlr: 0.00014 tnm: 0.26 Lm: 6.562 (6.562) Lt: 5.831 (5.831) Accm: 3.10 (3.10) Acct: 4.75 (4.75) proj_loss: -0.6070 (-0.6070) time: 0.9239 data: 0.0003 [11-26 05:39:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 834/1669] eta: 0:13:00 tlr: 0.00014 tnm: 0.27 Lm: 6.477 (6.533) Lt: 5.724 (5.774) Accm: 3.54 (3.31) Acct: 5.44 (5.26) proj_loss: -0.6185 (-0.6117) time: 0.9228 data: 0.0003 [11-26 05:39:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 834/1669] eta: 0:13:00 tlr: 0.00014 tnm: 0.27 Lm: 6.401 (6.420) Lt: 5.630 (5.688) Accm: 3.77 (3.89) Acct: 5.85 (6.12) proj_loss: -0.6059 (-0.6024) time: 0.9228 data: 0.0002 [11-26 05:39:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 834/1669] eta: 0:13:00 tlr: 0.00014 tnm: 0.27 Lm: 6.577 (6.533) Lt: 5.759 (5.737) Accm: 3.09 (3.24) Acct: 5.13 (5.39) proj_loss: -0.6121 (-0.6161) time: 0.9229 data: 0.0002 [11-26 05:39:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 834/1669] eta: 0:13:00 tlr: 0.00014 tnm: 0.27 Lm: 6.383 (6.483) Lt: 5.586 (5.714) Accm: 3.69 (3.26) Acct: 5.65 (5.00) proj_loss: -0.6114 (-0.6151) time: 0.9229 data: 0.0002 [11-26 05:39:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 834/1669] eta: 0:13:00 tlr: 0.00014 tnm: 0.27 Lm: 6.435 (6.414) Lt: 5.665 (5.666) Accm: 3.12 (3.72) Acct: 5.37 (6.03) proj_loss: -0.6363 (-0.6306) time: 0.9229 data: 0.0003 [11-26 05:39:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 834/1669] eta: 0:13:00 tlr: 0.00014 tnm: 0.27 Lm: 6.317 (6.336) Lt: 5.543 (5.572) Accm: 3.80 (3.82) Acct: 5.99 (5.91) proj_loss: -0.6235 (-0.6168) time: 0.9229 data: 0.0003 [11-26 05:39:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 834/1669] eta: 0:13:00 tlr: 0.00014 tnm: 0.27 Lm: 6.433 (6.457) Lt: 5.743 (5.694) Accm: 3.66 (3.56) Acct: 5.20 (5.37) proj_loss: -0.6175 (-0.6227) time: 0.9229 data: 0.0002 [11-26 05:39:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [ 834/1669] eta: 0:13:00 tlr: 0.00014 tnm: 0.27 Lm: 6.363 (6.358) Lt: 5.658 (5.664) Accm: 3.86 (3.90) Acct: 5.37 (5.66) proj_loss: -0.6149 (-0.6227) time: 0.9229 data: 0.0003 [11-26 05:46:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [1251/1669] eta: 0:06:29 tlr: 0.00014 tnm: 0.26 Lm: 6.370 (6.368) Lt: 5.657 (5.651) Accm: 3.96 (3.97) Acct: 5.91 (6.01) proj_loss: -0.6180 (-0.6223) time: 0.9249 data: 0.0003 [11-26 05:46:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [1251/1669] eta: 0:06:29 tlr: 0.00014 tnm: 0.26 Lm: 6.498 (6.460) Lt: 5.757 (5.712) Accm: 3.21 (3.62) Acct: 5.32 (5.80) proj_loss: -0.6232 (-0.6236) time: 0.9249 data: 0.0003 [11-26 05:46:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [1251/1669] eta: 0:06:29 tlr: 0.00014 tnm: 0.26 Lm: 6.440 (6.455) Lt: 5.732 (5.701) Accm: 3.49 (3.50) Acct: 5.30 (5.38) proj_loss: -0.6304 (-0.6313) time: 0.9249 data: 0.0002 [11-26 05:46:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [1251/1669] eta: 0:06:29 tlr: 0.00014 tnm: 0.26 Lm: 6.369 (6.410) Lt: 5.586 (5.644) Accm: 3.63 (3.57) Acct: 5.75 (5.67) proj_loss: -0.6220 (-0.6177) time: 0.9249 data: 0.0002 [11-26 05:46:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [1251/1669] eta: 0:06:29 tlr: 0.00014 tnm: 0.26 Lm: 6.426 (6.479) Lt: 5.699 (5.739) Accm: 3.61 (3.33) Acct: 5.32 (5.00) proj_loss: -0.6199 (-0.6191) time: 0.9249 data: 0.0002 [11-26 05:46:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [1251/1669] eta: 0:06:29 tlr: 0.00014 tnm: 0.26 Lm: 6.558 (6.535) Lt: 5.795 (5.761) Accm: 3.07 (3.18) Acct: 5.08 (5.21) proj_loss: -0.6186 (-0.6234) time: 0.9249 data: 0.0002 [11-26 05:46:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [1251/1669] eta: 0:06:29 tlr: 0.00014 tnm: 0.26 Lm: 6.467 (6.486) Lt: 5.691 (5.728) Accm: 3.59 (3.39) Acct: 5.51 (5.34) proj_loss: -0.6198 (-0.6168) time: 0.9249 data: 0.0003 [11-26 05:46:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [1251/1669] eta: 0:06:29 tlr: 0.00014 tnm: 0.26 Lm: 6.367 (6.353) Lt: 5.623 (5.569) Accm: 3.96 (4.14) Acct: 6.34 (6.57) proj_loss: -0.5973 (-0.5979) time: 0.9249 data: 0.0003 [11-26 05:52:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.401 (6.384) Lt: 5.630 (5.611) Accm: 3.77 (3.95) Acct: 5.85 (6.34) proj_loss: -0.6022 (-0.5987) time: 0.9254 data: 0.0016 [11-26 05:52:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 155/350] Total time: 0:25:51 (0.930 s / it) [11-26 05:52:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.522 (6.473) Lt: 5.801 (5.730) Accm: 3.31 (3.61) Acct: 5.37 (5.81) proj_loss: -0.6363 (-0.6288) time: 0.9254 data: 0.0018 [11-26 05:52:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.433 (6.435) Lt: 5.721 (5.686) Accm: 3.66 (3.54) Acct: 5.41 (5.46) proj_loss: -0.6175 (-0.6273) time: 0.9254 data: 0.0014 [11-26 05:52:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.421 (6.471) Lt: 5.630 (5.705) Accm: 3.45 (3.39) Acct: 5.51 (5.43) proj_loss: -0.6235 (-0.6203) time: 0.9254 data: 0.0017 [11-26 05:52:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.468 (6.493) Lt: 5.787 (5.748) Accm: 3.53 (3.23) Acct: 4.99 (4.90) proj_loss: -0.6194 (-0.6192) time: 0.9254 data: 0.0016 [11-26 05:52:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.539 (6.528) Lt: 5.759 (5.754) Accm: 3.09 (3.19) Acct: 5.13 (5.23) proj_loss: -0.6121 (-0.6175) time: 0.9254 data: 0.0019 [11-26 05:52:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.377 (6.427) Lt: 5.658 (5.710) Accm: 3.86 (3.70) Acct: 5.37 (5.65) proj_loss: -0.6149 (-0.6203) time: 0.9254 data: 0.0021 [11-26 05:52:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 155/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.457 (6.461) Lt: 5.658 (5.694) Accm: 3.63 (3.44) Acct: 5.58 (5.42) proj_loss: -0.6210 (-0.6198) time: 0.9254 data: 0.0018 [11-26 05:52:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 155/350] Total time: 0:25:51 (0.930 s / it) [11-26 05:52:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 155/350] Total time: 0:25:51 (0.930 s / it) [11-26 05:52:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 155/350] Total time: 0:25:51 (0.930 s / it) [11-26 05:52:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 155/350] Total time: 0:25:51 (0.930 s / it) [11-26 05:52:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 155/350] Total time: 0:25:51 (0.930 s / it) [11-26 05:52:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 155/350] Total time: 0:25:51 (0.930 s / it) [11-26 05:52:38] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 155/350] Total time: 0:25:51 (0.930 s / it) [11-26 05:52:38] (/home/user/VAR/train.py , line 276)=> [ep155] (training ) Lm: 6.436 (6.454), Lt: 5.678 (5.698), Acc m&t: 3.57 5.59, Remain: 3 days, 12:01:52, Finish: 2024-11-29 01:54 [11-26 05:52:38] (/home/user/VAR/train.py , line 276)=> [ep155] (training ) Lm: 6.436 (6.454), Lt: 5.678 (5.698), Acc m&t: 3.57 5.59, Remain: 3 days, 12:01:46, Finish: 2024-11-29 01:54 [11-26 05:52:38] (/home/user/VAR/train.py , line 276)=> [ep155] (training ) Lm: 6.436 (6.454), Lt: 5.678 (5.698), Acc m&t: 3.57 5.59, Remain: 3 days, 12:01:11, Finish: 2024-11-29 01:53 [11-26 05:52:38] (/home/user/VAR/train.py , line 276)=> [ep155] (training ) Lm: 6.436 (6.454), Lt: 5.678 (5.698), Acc m&t: 3.57 5.59, Remain: 3 days, 12:01:59, Finish: 2024-11-29 01:54 [11-26 05:52:38] (/home/user/VAR/train.py , line 276)=> [ep155] (training ) Lm: 6.436 (6.454), Lt: 5.678 (5.698), Acc m&t: 3.57 5.59, Remain: 3 days, 12:01:36, Finish: 2024-11-29 01:54 [11-26 05:52:38] (/home/user/VAR/train.py , line 276)=> [ep155] (training ) Lm: 6.436 (6.454), Lt: 5.678 (5.698), Acc m&t: 3.57 5.59, Remain: 3 days, 12:02:08, Finish: 2024-11-29 01:54 [11-26 05:52:38] (/home/user/VAR/train.py , line 276)=> [ep155] (training ) Lm: 6.436 (6.454), Lt: 5.678 (5.698), Acc m&t: 3.57 5.59, Remain: 3 days, 12:01:32, Finish: 2024-11-29 01:54 [11-26 05:52:38] (/home/user/VAR/train.py , line 276)=> [ep155] (training ) Lm: 6.436 (6.454), Lt: 5.678 (5.698), Acc m&t: 3.57 5.59, Remain: 3 days, 12:03:46, Finish: 2024-11-29 01:56 [11-26 05:52:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 0/1669] eta: 0:25:04 tlr: 0.00014 tnm: 0.27 Lm: 6.816 (6.816) Lt: 6.128 (6.128) Accm: 2.14 (2.14) Acct: 3.31 (3.31) proj_loss: -0.6353 (-0.6353) time: 0.9014 data: 0.0003 [11-26 05:52:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 0/1669] eta: 0:25:05 tlr: 0.00014 tnm: 0.27 Lm: 6.057 (6.057) Lt: 5.350 (5.350) Accm: 4.56 (4.56) Acct: 6.58 (6.58) proj_loss: -0.6328 (-0.6328) time: 0.9021 data: 0.0003 [11-26 05:52:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 0/1669] eta: 0:25:05 tlr: 0.00014 tnm: 0.27 Lm: 6.337 (6.337) Lt: 5.660 (5.660) Accm: 3.89 (3.89) Acct: 5.54 (5.54) proj_loss: -0.6415 (-0.6415) time: 0.9021 data: 0.0003 [11-26 05:52:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 0/1669] eta: 0:25:03 tlr: 0.00014 tnm: 0.27 Lm: 6.350 (6.350) Lt: 5.584 (5.584) Accm: 3.80 (3.80) Acct: 6.13 (6.13) proj_loss: -0.6020 (-0.6020) time: 0.9006 data: 0.0003 [11-26 05:52:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 0/1669] eta: 0:25:06 tlr: 0.00014 tnm: 0.27 Lm: 6.332 (6.332) Lt: 5.566 (5.566) Accm: 3.41 (3.41) Acct: 5.13 (5.13) proj_loss: -0.6205 (-0.6205) time: 0.9024 data: 0.0004 [11-26 05:52:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 0/1669] eta: 0:25:05 tlr: 0.00014 tnm: 0.27 Lm: 6.520 (6.520) Lt: 5.830 (5.830) Accm: 3.53 (3.53) Acct: 5.61 (5.61) proj_loss: -0.6592 (-0.6592) time: 0.9022 data: 0.0003 [11-26 05:52:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 0/1669] eta: 0:25:06 tlr: 0.00014 tnm: 0.27 Lm: 6.438 (6.438) Lt: 5.687 (5.687) Accm: 3.54 (3.54) Acct: 5.37 (5.37) proj_loss: -0.6065 (-0.6065) time: 0.9026 data: 0.0004 [11-26 05:52:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 0/1669] eta: 0:25:06 tlr: 0.00014 tnm: 0.27 Lm: 6.302 (6.302) Lt: 5.551 (5.551) Accm: 4.24 (4.24) Acct: 6.71 (6.71) proj_loss: -0.6206 (-0.6206) time: 0.9027 data: 0.0002 [11-26 05:59:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 417/1669] eta: 0:19:15 tlr: 0.00014 tnm: 0.27 Lm: 6.384 (6.384) Lt: 5.657 (5.657) Accm: 3.84 (3.84) Acct: 5.99 (5.99) proj_loss: -0.6171 (-0.6171) time: 0.9237 data: 0.0003 [11-26 05:59:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 417/1669] eta: 0:19:15 tlr: 0.00014 tnm: 0.27 Lm: 6.096 (6.096) Lt: 5.382 (5.382) Accm: 4.49 (4.49) Acct: 6.58 (6.58) proj_loss: -0.6351 (-0.6351) time: 0.9237 data: 0.0002 [11-26 05:59:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 417/1669] eta: 0:19:15 tlr: 0.00014 tnm: 0.27 Lm: 6.500 (6.500) Lt: 5.751 (5.751) Accm: 3.45 (3.45) Acct: 5.42 (5.42) proj_loss: -0.6112 (-0.6112) time: 0.9237 data: 0.0003 [11-26 05:59:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 417/1669] eta: 0:19:15 tlr: 0.00014 tnm: 0.27 Lm: 6.456 (6.456) Lt: 5.763 (5.763) Accm: 3.37 (3.37) Acct: 5.18 (5.18) proj_loss: -0.6368 (-0.6368) time: 0.9237 data: 0.0002 [11-26 05:59:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 417/1669] eta: 0:19:15 tlr: 0.00014 tnm: 0.27 Lm: 6.606 (6.606) Lt: 5.887 (5.887) Accm: 2.93 (2.93) Acct: 4.51 (4.51) proj_loss: -0.6362 (-0.6362) time: 0.9237 data: 0.0003 [11-26 05:59:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 417/1669] eta: 0:19:15 tlr: 0.00014 tnm: 0.27 Lm: 6.332 (6.332) Lt: 5.557 (5.557) Accm: 3.35 (3.35) Acct: 5.32 (5.32) proj_loss: -0.6139 (-0.6139) time: 0.9237 data: 0.0002 [11-26 05:59:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 417/1669] eta: 0:19:15 tlr: 0.00014 tnm: 0.27 Lm: 6.377 (6.377) Lt: 5.663 (5.663) Accm: 3.58 (3.58) Acct: 5.37 (5.37) proj_loss: -0.6209 (-0.6209) time: 0.9237 data: 0.0003 [11-26 05:59:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 417/1669] eta: 0:19:15 tlr: 0.00014 tnm: 0.27 Lm: 6.502 (6.502) Lt: 5.724 (5.724) Accm: 3.42 (3.42) Acct: 5.04 (5.04) proj_loss: -0.6058 (-0.6058) time: 0.9237 data: 0.0003 [11-26 06:05:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 834/1669] eta: 0:13:05 tlr: 0.00014 tnm: 0.26 Lm: 6.438 (6.447) Lt: 5.687 (5.691) Accm: 3.54 (3.52) Acct: 5.37 (5.18) proj_loss: -0.6065 (-0.6078) time: 0.9231 data: 0.0003 [11-26 06:05:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 834/1669] eta: 0:13:05 tlr: 0.00014 tnm: 0.26 Lm: 6.392 (6.428) Lt: 5.695 (5.726) Accm: 3.53 (3.46) Acct: 5.30 (5.22) proj_loss: -0.6246 (-0.6327) time: 0.9231 data: 0.0003 [11-26 06:05:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 834/1669] eta: 0:13:05 tlr: 0.00014 tnm: 0.26 Lm: 6.302 (6.351) Lt: 5.551 (5.618) Accm: 3.92 (3.87) Acct: 6.16 (6.05) proj_loss: -0.6206 (-0.6205) time: 0.9231 data: 0.0003 [11-26 06:05:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 834/1669] eta: 0:13:05 tlr: 0.00014 tnm: 0.26 Lm: 6.416 (6.410) Lt: 5.666 (5.686) Accm: 3.26 (3.36) Acct: 5.20 (5.17) proj_loss: -0.6202 (-0.6207) time: 0.9231 data: 0.0003 [11-26 06:05:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 834/1669] eta: 0:13:05 tlr: 0.00014 tnm: 0.26 Lm: 6.135 (6.208) Lt: 5.414 (5.472) Accm: 4.43 (4.14) Acct: 6.58 (6.27) proj_loss: -0.6373 (-0.6386) time: 0.9231 data: 0.0003 [11-26 06:05:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 834/1669] eta: 0:13:05 tlr: 0.00014 tnm: 0.26 Lm: 6.533 (6.582) Lt: 5.881 (5.885) Accm: 3.55 (3.14) Acct: 5.72 (4.94) proj_loss: -0.6353 (-0.6316) time: 0.9231 data: 0.0003 [11-26 06:05:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 834/1669] eta: 0:13:05 tlr: 0.00014 tnm: 0.26 Lm: 6.371 (6.457) Lt: 5.584 (5.676) Accm: 3.45 (3.45) Acct: 5.23 (5.36) proj_loss: -0.6160 (-0.6128) time: 0.9231 data: 0.0003 [11-26 06:05:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [ 834/1669] eta: 0:13:05 tlr: 0.00014 tnm: 0.26 Lm: 6.333 (6.425) Lt: 5.566 (5.658) Accm: 3.29 (3.21) Acct: 5.13 (5.17) proj_loss: -0.6205 (-0.6236) time: 0.9231 data: 0.0003 [11-26 06:12:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [1251/1669] eta: 0:06:30 tlr: 0.00014 tnm: 0.27 Lm: 6.252 (6.248) Lt: 5.518 (5.510) Accm: 3.95 (3.97) Acct: 6.11 (6.11) proj_loss: -0.6351 (-0.6302) time: 0.9251 data: 0.0003 [11-26 06:12:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [1251/1669] eta: 0:06:30 tlr: 0.00014 tnm: 0.27 Lm: 6.399 (6.449) Lt: 5.636 (5.679) Accm: 3.48 (3.46) Acct: 5.30 (5.36) proj_loss: -0.6139 (-0.6125) time: 0.9251 data: 0.0003 [11-26 06:12:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [1251/1669] eta: 0:06:30 tlr: 0.00014 tnm: 0.27 Lm: 6.456 (6.467) Lt: 5.763 (5.767) Accm: 3.37 (3.40) Acct: 5.18 (5.18) proj_loss: -0.6196 (-0.6282) time: 0.9251 data: 0.0003 [11-26 06:12:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [1251/1669] eta: 0:06:30 tlr: 0.00014 tnm: 0.27 Lm: 6.588 (6.597) Lt: 5.901 (5.894) Accm: 3.12 (3.02) Acct: 5.04 (4.80) proj_loss: -0.6289 (-0.6246) time: 0.9251 data: 0.0003 [11-26 06:12:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [1251/1669] eta: 0:06:30 tlr: 0.00014 tnm: 0.27 Lm: 6.384 (6.382) Lt: 5.642 (5.647) Accm: 3.71 (3.77) Acct: 5.91 (5.95) proj_loss: -0.6239 (-0.6230) time: 0.9251 data: 0.0003 [11-26 06:12:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [1251/1669] eta: 0:06:30 tlr: 0.00014 tnm: 0.27 Lm: 6.502 (6.477) Lt: 5.724 (5.723) Accm: 3.49 (3.50) Acct: 5.41 (5.34) proj_loss: -0.6088 (-0.6086) time: 0.9251 data: 0.0003 [11-26 06:12:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [1251/1669] eta: 0:06:30 tlr: 0.00014 tnm: 0.27 Lm: 6.447 (6.468) Lt: 5.699 (5.751) Accm: 3.17 (3.29) Acct: 4.99 (5.07) proj_loss: -0.6202 (-0.6206) time: 0.9251 data: 0.0003 [11-26 06:12:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [1251/1669] eta: 0:06:30 tlr: 0.00014 tnm: 0.27 Lm: 6.390 (6.431) Lt: 5.631 (5.667) Accm: 3.23 (3.20) Acct: 5.06 (5.12) proj_loss: -0.6283 (-0.6268) time: 0.9251 data: 0.0002 [11-26 06:18:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.354 (6.415) Lt: 5.676 (5.669) Accm: 3.29 (3.34) Acct: 5.13 (5.36) proj_loss: -0.6205 (-0.6251) time: 0.9252 data: 0.0021 [11-26 06:18:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 156/350] Total time: 0:25:55 (0.932 s / it) [11-26 06:18:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.427 (6.454) Lt: 5.689 (5.696) Accm: 3.45 (3.42) Acct: 5.23 (5.28) proj_loss: -0.6160 (-0.6161) time: 0.9252 data: 0.0017 [11-26 06:18:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.302 (6.328) Lt: 5.551 (5.565) Accm: 3.92 (4.00) Acct: 6.16 (6.40) proj_loss: -0.6265 (-0.6237) time: 0.9252 data: 0.0018 [11-26 06:18:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.227 (6.244) Lt: 5.471 (5.502) Accm: 4.43 (4.09) Acct: 6.58 (6.42) proj_loss: -0.6353 (-0.6312) time: 0.9252 data: 0.0016 [11-26 06:18:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.485 (6.471) Lt: 5.717 (5.757) Accm: 3.53 (3.44) Acct: 5.30 (5.23) proj_loss: -0.6164 (-0.6259) time: 0.9252 data: 0.0014 [11-26 06:18:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.478 (6.473) Lt: 5.732 (5.749) Accm: 3.09 (3.25) Acct: 5.10 (5.08) proj_loss: -0.6202 (-0.6204) time: 0.9252 data: 0.0020 [11-26 06:18:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.533 (6.566) Lt: 5.881 (5.850) Accm: 3.55 (3.15) Acct: 5.37 (4.91) proj_loss: -0.6225 (-0.6210) time: 0.9252 data: 0.0018 [11-26 06:18:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 156/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.459 (6.474) Lt: 5.743 (5.727) Accm: 3.44 (3.46) Acct: 5.37 (5.33) proj_loss: -0.6111 (-0.6145) time: 0.9252 data: 0.0016 [11-26 06:18:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 156/350] Total time: 0:25:55 (0.932 s / it) [11-26 06:18:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 156/350] Total time: 0:25:55 (0.932 s / it) [11-26 06:18:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 156/350] Total time: 0:25:55 (0.932 s / it) [11-26 06:18:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 156/350] Total time: 0:25:55 (0.932 s / it) [11-26 06:18:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 156/350] Total time: 0:25:55 (0.932 s / it) [11-26 06:18:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 156/350] Total time: 0:25:55 (0.932 s / it) [11-26 06:18:34] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 156/350] Total time: 0:25:55 (0.932 s / it) [11-26 06:18:34] (/home/user/VAR/train.py , line 276)=> [ep156] (training ) Lm: 6.436 (6.438), Lt: 5.678 (5.684), Acc m&t: 3.57 5.59, Remain: 3 days, 11:22:19, Finish: 2024-11-29 01:40 [11-26 06:18:34] (/home/user/VAR/train.py , line 276)=> [ep156] (training ) Lm: 6.436 (6.438), Lt: 5.678 (5.684), Acc m&t: 3.57 5.59, Remain: 3 days, 11:19:43, Finish: 2024-11-29 01:38 [11-26 06:18:34] (/home/user/VAR/train.py , line 276)=> [ep156] (training ) Lm: 6.436 (6.438), Lt: 5.678 (5.684), Acc m&t: 3.57 5.59, Remain: 3 days, 11:19:49, Finish: 2024-11-29 01:38 [11-26 06:18:34] (/home/user/VAR/train.py , line 276)=> [ep156] (training ) Lm: 6.436 (6.438), Lt: 5.678 (5.684), Acc m&t: 3.57 5.59, Remain: 3 days, 11:21:12, Finish: 2024-11-29 01:39 [11-26 06:18:34] (/home/user/VAR/train.py , line 276)=> [ep156] (training ) Lm: 6.436 (6.438), Lt: 5.678 (5.684), Acc m&t: 3.57 5.59, Remain: 3 days, 11:22:10, Finish: 2024-11-29 01:40 [11-26 06:18:34] (/home/user/VAR/train.py , line 276)=> [ep156] (training ) Lm: 6.436 (6.438), Lt: 5.678 (5.684), Acc m&t: 3.57 5.59, Remain: 3 days, 11:20:04, Finish: 2024-11-29 01:38 [11-26 06:18:34] (/home/user/VAR/train.py , line 276)=> [ep156] (training ) Lm: 6.436 (6.438), Lt: 5.678 (5.684), Acc m&t: 3.57 5.59, Remain: 3 days, 11:19:06, Finish: 2024-11-29 01:37 [11-26 06:18:34] (/home/user/VAR/train.py , line 276)=> [ep156] (training ) Lm: 6.436 (6.438), Lt: 5.678 (5.684), Acc m&t: 3.57 5.59, Remain: 3 days, 11:19:21, Finish: 2024-11-29 01:37 [11-26 06:18:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 0/1669] eta: 0:25:39 tlr: 0.00014 tnm: 0.25 Lm: 6.495 (6.495) Lt: 5.807 (5.807) Accm: 3.39 (3.39) Acct: 5.23 (5.23) proj_loss: -0.6033 (-0.6033) time: 0.9225 data: 0.0003 [11-26 06:18:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 0/1669] eta: 0:25:13 tlr: 0.00014 tnm: 0.25 Lm: 6.485 (6.485) Lt: 5.771 (5.771) Accm: 3.57 (3.57) Acct: 6.06 (6.06) proj_loss: -0.6266 (-0.6266) time: 0.9069 data: 0.0003 [11-26 06:18:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 0/1669] eta: 0:25:40 tlr: 0.00014 tnm: 0.25 Lm: 6.420 (6.420) Lt: 5.687 (5.687) Accm: 4.02 (4.02) Acct: 6.37 (6.37) proj_loss: -0.6136 (-0.6136) time: 0.9227 data: 0.0004 [11-26 06:18:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 0/1669] eta: 0:25:40 tlr: 0.00014 tnm: 0.25 Lm: 6.501 (6.501) Lt: 5.792 (5.792) Accm: 3.42 (3.42) Acct: 5.20 (5.20) proj_loss: -0.5983 (-0.5983) time: 0.9228 data: 0.0003 [11-26 06:18:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 0/1669] eta: 0:25:40 tlr: 0.00014 tnm: 0.25 Lm: 6.234 (6.234) Lt: 5.506 (5.506) Accm: 3.76 (3.76) Acct: 5.37 (5.37) proj_loss: -0.6527 (-0.6527) time: 0.9230 data: 0.0004 [11-26 06:18:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 0/1669] eta: 0:25:40 tlr: 0.00014 tnm: 0.25 Lm: 6.360 (6.360) Lt: 5.663 (5.663) Accm: 3.69 (3.69) Acct: 5.44 (5.44) proj_loss: -0.6301 (-0.6301) time: 0.9230 data: 0.0004 [11-26 06:18:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 0/1669] eta: 0:25:40 tlr: 0.00014 tnm: 0.25 Lm: 6.407 (6.407) Lt: 5.724 (5.724) Accm: 3.51 (3.51) Acct: 5.54 (5.54) proj_loss: -0.6270 (-0.6270) time: 0.9231 data: 0.0004 [11-26 06:18:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 0/1669] eta: 0:25:40 tlr: 0.00014 tnm: 0.25 Lm: 6.520 (6.520) Lt: 5.728 (5.728) Accm: 3.04 (3.04) Acct: 4.82 (4.82) proj_loss: -0.5909 (-0.5909) time: 0.9228 data: 0.0004 [11-26 06:25:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 417/1669] eta: 0:19:16 tlr: 0.00014 tnm: 0.25 Lm: 6.579 (6.579) Lt: 5.823 (5.823) Accm: 3.02 (3.02) Acct: 4.80 (4.80) proj_loss: -0.6072 (-0.6072) time: 0.9236 data: 0.0003 [11-26 06:25:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 417/1669] eta: 0:19:16 tlr: 0.00014 tnm: 0.25 Lm: 6.267 (6.267) Lt: 5.486 (5.486) Accm: 4.06 (4.06) Acct: 6.22 (6.22) proj_loss: -0.6180 (-0.6180) time: 0.9236 data: 0.0003 [11-26 06:25:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 417/1669] eta: 0:19:16 tlr: 0.00014 tnm: 0.25 Lm: 6.402 (6.402) Lt: 5.729 (5.729) Accm: 3.44 (3.44) Acct: 5.11 (5.11) proj_loss: -0.6281 (-0.6281) time: 0.9236 data: 0.0003 [11-26 06:25:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 417/1669] eta: 0:19:16 tlr: 0.00014 tnm: 0.25 Lm: 6.526 (6.526) Lt: 5.808 (5.808) Accm: 3.37 (3.37) Acct: 5.39 (5.39) proj_loss: -0.6095 (-0.6095) time: 0.9236 data: 0.0002 [11-26 06:25:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 417/1669] eta: 0:19:16 tlr: 0.00014 tnm: 0.25 Lm: 6.463 (6.463) Lt: 5.726 (5.726) Accm: 3.44 (3.44) Acct: 5.37 (5.37) proj_loss: -0.6092 (-0.6092) time: 0.9236 data: 0.0003 [11-26 06:25:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 417/1669] eta: 0:19:16 tlr: 0.00014 tnm: 0.25 Lm: 6.595 (6.595) Lt: 5.952 (5.952) Accm: 3.15 (3.15) Acct: 4.80 (4.80) proj_loss: -0.6358 (-0.6358) time: 0.9236 data: 0.0003 [11-26 06:25:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 417/1669] eta: 0:19:16 tlr: 0.00014 tnm: 0.25 Lm: 6.412 (6.412) Lt: 5.720 (5.720) Accm: 3.56 (3.56) Acct: 5.56 (5.56) proj_loss: -0.6239 (-0.6239) time: 0.9236 data: 0.0003 [11-26 06:25:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 417/1669] eta: 0:19:16 tlr: 0.00014 tnm: 0.25 Lm: 6.288 (6.288) Lt: 5.535 (5.535) Accm: 3.79 (3.79) Acct: 5.65 (5.65) proj_loss: -0.6196 (-0.6196) time: 0.9236 data: 0.0003 [11-26 06:31:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.26 Lm: 6.342 (6.345) Lt: 5.563 (5.618) Accm: 3.76 (3.75) Acct: 5.79 (5.69) proj_loss: -0.6325 (-0.6239) time: 0.9234 data: 0.0003 [11-26 06:31:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.26 Lm: 6.437 (6.454) Lt: 5.792 (5.751) Accm: 3.45 (3.47) Acct: 5.20 (5.25) proj_loss: -0.6063 (-0.6082) time: 0.9234 data: 0.0002 [11-26 06:31:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.26 Lm: 6.139 (6.224) Lt: 5.288 (5.420) Accm: 4.09 (4.23) Acct: 6.37 (6.51) proj_loss: -0.6225 (-0.6215) time: 0.9234 data: 0.0002 [11-26 06:31:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.26 Lm: 6.485 (6.422) Lt: 5.771 (5.693) Accm: 3.57 (3.60) Acct: 6.06 (5.64) proj_loss: -0.5986 (-0.6059) time: 0.9234 data: 0.0002 [11-26 06:31:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.26 Lm: 6.390 (6.398) Lt: 5.663 (5.680) Accm: 3.69 (3.58) Acct: 5.44 (5.41) proj_loss: -0.6262 (-0.6213) time: 0.9234 data: 0.0002 [11-26 06:31:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.26 Lm: 6.407 (6.527) Lt: 5.724 (5.829) Accm: 3.51 (3.31) Acct: 5.54 (5.22) proj_loss: -0.6270 (-0.6280) time: 0.9234 data: 0.0003 [11-26 06:31:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.26 Lm: 6.520 (6.541) Lt: 5.728 (5.781) Accm: 3.04 (3.06) Acct: 4.82 (4.84) proj_loss: -0.6057 (-0.6067) time: 0.9233 data: 0.0003 [11-26 06:31:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.26 Lm: 6.495 (6.507) Lt: 5.807 (5.793) Accm: 3.39 (3.28) Acct: 5.23 (5.20) proj_loss: -0.6320 (-0.6266) time: 0.9234 data: 0.0003 [11-26 06:37:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.26 Lm: 6.483 (6.498) Lt: 5.807 (5.797) Accm: 3.17 (3.20) Acct: 4.86 (5.01) proj_loss: -0.6326 (-0.6283) time: 0.9674 data: 0.0003 [11-26 06:37:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.26 Lm: 6.515 (6.551) Lt: 5.783 (5.833) Accm: 3.15 (3.13) Acct: 4.80 (4.92) proj_loss: -0.6238 (-0.6261) time: 0.9674 data: 0.0003 [11-26 06:37:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.26 Lm: 6.291 (6.318) Lt: 5.535 (5.585) Accm: 3.79 (3.84) Acct: 5.85 (5.85) proj_loss: -0.6307 (-0.6252) time: 0.9674 data: 0.0003 [11-26 06:37:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.26 Lm: 6.526 (6.462) Lt: 5.777 (5.716) Accm: 3.37 (3.48) Acct: 5.63 (5.53) proj_loss: -0.6034 (-0.6065) time: 0.9674 data: 0.0002 [11-26 06:37:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.26 Lm: 6.579 (6.570) Lt: 5.823 (5.834) Accm: 3.02 (3.02) Acct: 4.80 (4.65) proj_loss: -0.6146 (-0.6143) time: 0.9674 data: 0.0003 [11-26 06:37:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.26 Lm: 6.431 (6.433) Lt: 5.726 (5.709) Accm: 3.49 (3.53) Acct: 5.37 (5.48) proj_loss: -0.6132 (-0.6196) time: 0.9674 data: 0.0003 [11-26 06:37:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.26 Lm: 6.413 (6.407) Lt: 5.637 (5.662) Accm: 3.44 (3.44) Acct: 5.17 (5.28) proj_loss: -0.6240 (-0.6214) time: 0.9674 data: 0.0003 [11-26 06:37:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.26 Lm: 6.258 (6.263) Lt: 5.394 (5.440) Accm: 4.06 (4.12) Acct: 6.28 (6.43) proj_loss: -0.6180 (-0.6175) time: 0.9674 data: 0.0003 [11-26 06:44:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.377 (6.308) Lt: 5.499 (5.499) Accm: 4.02 (4.03) Acct: 6.20 (6.28) proj_loss: -0.6197 (-0.6180) time: 0.9276 data: 0.0018 [11-26 06:44:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.516 (6.473) Lt: 5.771 (5.725) Accm: 3.41 (3.46) Acct: 5.54 (5.53) proj_loss: -0.5986 (-0.6028) time: 0.9276 data: 0.0015 [11-26 06:44:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 157/350] Total time: 0:25:54 (0.932 s / it) [11-26 06:44:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.342 (6.354) Lt: 5.563 (5.615) Accm: 3.76 (3.72) Acct: 5.79 (5.76) proj_loss: -0.6300 (-0.6261) time: 0.9276 data: 0.0020 [11-26 06:44:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.437 (6.459) Lt: 5.792 (5.744) Accm: 3.45 (3.47) Acct: 5.20 (5.33) proj_loss: -0.6063 (-0.6164) time: 0.9276 data: 0.0015 [11-26 06:44:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.407 (6.508) Lt: 5.724 (5.785) Accm: 3.51 (3.21) Acct: 5.23 (4.99) proj_loss: -0.6270 (-0.6272) time: 0.9276 data: 0.0017 [11-26 06:44:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.495 (6.501) Lt: 5.807 (5.792) Accm: 3.39 (3.25) Acct: 5.23 (5.08) proj_loss: -0.6320 (-0.6250) time: 0.9276 data: 0.0015 [11-26 06:44:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.390 (6.399) Lt: 5.610 (5.646) Accm: 3.69 (3.54) Acct: 5.44 (5.40) proj_loss: -0.6262 (-0.6237) time: 0.9276 data: 0.0014 [11-26 06:44:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 157/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.520 (6.545) Lt: 5.728 (5.810) Accm: 3.04 (3.11) Acct: 4.82 (4.70) proj_loss: -0.6235 (-0.6175) time: 0.9276 data: 0.0019 [11-26 06:44:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 157/350] Total time: 0:25:54 (0.932 s / it) [11-26 06:44:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 157/350] Total time: 0:25:54 (0.932 s / it) [11-26 06:44:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 157/350] Total time: 0:25:54 (0.932 s / it) [11-26 06:44:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 157/350] Total time: 0:25:54 (0.932 s / it) [11-26 06:44:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 157/350] Total time: 0:25:54 (0.932 s / it) [11-26 06:44:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 157/350] Total time: 0:25:54 (0.932 s / it) [11-26 06:44:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 157/350] Total time: 0:25:54 (0.932 s / it) [11-26 06:44:29] (/home/user/VAR/train.py , line 276)=> [ep157] (training ) Lm: 6.431 (6.431), Lt: 5.678 (5.679), Acc m&t: 3.57 5.59, Remain: 3 days, 11:02:38, Finish: 2024-11-29 01:47 [11-26 06:44:29] (/home/user/VAR/train.py , line 276)=> [ep157] (training ) Lm: 6.431 (6.431), Lt: 5.678 (5.679), Acc m&t: 3.57 5.59, Remain: 3 days, 11:04:02, Finish: 2024-11-29 01:48 [11-26 06:44:29] (/home/user/VAR/train.py , line 276)=> [ep157] (training ) Lm: 6.431 (6.431), Lt: 5.678 (5.679), Acc m&t: 3.57 5.59, Remain: 3 days, 11:04:16, Finish: 2024-11-29 01:48 [11-26 06:44:29] (/home/user/VAR/train.py , line 276)=> [ep157] (training ) Lm: 6.431 (6.431), Lt: 5.678 (5.679), Acc m&t: 3.57 5.59, Remain: 3 days, 11:01:49, Finish: 2024-11-29 01:46 [11-26 06:44:29] (/home/user/VAR/train.py , line 276)=> [ep157] (training ) Lm: 6.431 (6.431), Lt: 5.678 (5.679), Acc m&t: 3.57 5.59, Remain: 3 days, 11:02:56, Finish: 2024-11-29 01:47 [11-26 06:44:29] (/home/user/VAR/train.py , line 276)=> [ep157] (training ) Lm: 6.431 (6.431), Lt: 5.678 (5.679), Acc m&t: 3.57 5.59, Remain: 3 days, 11:02:19, Finish: 2024-11-29 01:46 [11-26 06:44:29] (/home/user/VAR/train.py , line 276)=> [ep157] (training ) Lm: 6.431 (6.431), Lt: 5.678 (5.679), Acc m&t: 3.57 5.59, Remain: 3 days, 11:03:58, Finish: 2024-11-29 01:48 [11-26 06:44:29] (/home/user/VAR/train.py , line 276)=> [ep157] (training ) Lm: 6.431 (6.431), Lt: 5.678 (5.679), Acc m&t: 3.57 5.59, Remain: 3 days, 11:02:57, Finish: 2024-11-29 01:47 [11-26 06:44:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 0/1669] eta: 0:25:09 tlr: 0.00014 tnm: 0.27 Lm: 6.382 (6.382) Lt: 5.705 (5.705) Accm: 3.53 (3.53) Acct: 5.10 (5.10) proj_loss: -0.6295 (-0.6295) time: 0.9044 data: 0.0004 [11-26 06:44:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 0/1669] eta: 0:25:08 tlr: 0.00014 tnm: 0.27 Lm: 6.567 (6.567) Lt: 5.806 (5.806) Accm: 2.87 (2.87) Acct: 4.41 (4.41) proj_loss: -0.6234 (-0.6234) time: 0.9036 data: 0.0003 [11-26 06:44:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 0/1669] eta: 0:25:09 tlr: 0.00014 tnm: 0.27 Lm: 6.116 (6.116) Lt: 5.290 (5.290) Accm: 4.63 (4.63) Acct: 7.30 (7.30) proj_loss: -0.6290 (-0.6290) time: 0.9044 data: 0.0004 [11-26 06:44:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 0/1669] eta: 0:25:08 tlr: 0.00014 tnm: 0.27 Lm: 6.462 (6.462) Lt: 5.676 (5.676) Accm: 3.50 (3.50) Acct: 5.65 (5.65) proj_loss: -0.5810 (-0.5810) time: 0.9038 data: 0.0003 [11-26 06:44:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 0/1669] eta: 0:25:08 tlr: 0.00014 tnm: 0.27 Lm: 6.249 (6.249) Lt: 5.398 (5.398) Accm: 4.22 (4.22) Acct: 6.99 (6.99) proj_loss: -0.5938 (-0.5938) time: 0.9039 data: 0.0004 [11-26 06:44:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 0/1669] eta: 0:25:07 tlr: 0.00014 tnm: 0.27 Lm: 6.436 (6.436) Lt: 5.662 (5.662) Accm: 3.83 (3.83) Acct: 6.23 (6.23) proj_loss: -0.6167 (-0.6167) time: 0.9032 data: 0.0004 [11-26 06:44:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 0/1669] eta: 0:25:08 tlr: 0.00014 tnm: 0.27 Lm: 6.487 (6.487) Lt: 5.704 (5.704) Accm: 3.58 (3.58) Acct: 5.41 (5.41) proj_loss: -0.6107 (-0.6107) time: 0.9040 data: 0.0003 [11-26 06:44:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 0/1669] eta: 0:25:08 tlr: 0.00014 tnm: 0.27 Lm: 6.570 (6.570) Lt: 5.726 (5.726) Accm: 3.26 (3.26) Acct: 5.37 (5.37) proj_loss: -0.5771 (-0.5771) time: 0.9038 data: 0.0004 [11-26 06:50:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.541 (6.541) Lt: 5.735 (5.735) Accm: 3.28 (3.28) Acct: 5.29 (5.29) proj_loss: -0.5911 (-0.5911) time: 0.9235 data: 0.0003 [11-26 06:50:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.294 (6.294) Lt: 5.513 (5.513) Accm: 3.90 (3.90) Acct: 5.99 (5.99) proj_loss: -0.6221 (-0.6221) time: 0.9235 data: 0.0003 [11-26 06:50:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.407 (6.407) Lt: 5.628 (5.628) Accm: 3.71 (3.71) Acct: 5.65 (5.65) proj_loss: -0.6252 (-0.6252) time: 0.9234 data: 0.0002 [11-26 06:50:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.518 (6.518) Lt: 5.716 (5.716) Accm: 3.35 (3.35) Acct: 5.42 (5.42) proj_loss: -0.5751 (-0.5751) time: 0.9235 data: 0.0002 [11-26 06:50:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.395 (6.395) Lt: 5.688 (5.688) Accm: 3.45 (3.45) Acct: 5.11 (5.11) proj_loss: -0.6276 (-0.6276) time: 0.9234 data: 0.0002 [11-26 06:50:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.229 (6.229) Lt: 5.411 (5.411) Accm: 4.58 (4.58) Acct: 7.25 (7.25) proj_loss: -0.6369 (-0.6369) time: 0.9234 data: 0.0004 [11-26 06:50:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.399 (6.399) Lt: 5.594 (5.594) Accm: 3.77 (3.77) Acct: 6.10 (6.10) proj_loss: -0.5972 (-0.5972) time: 0.9234 data: 0.0003 [11-26 06:50:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.524 (6.524) Lt: 5.797 (5.797) Accm: 3.39 (3.39) Acct: 5.48 (5.48) proj_loss: -0.6193 (-0.6193) time: 0.9235 data: 0.0003 [11-26 06:57:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.25 Lm: 6.574 (6.541) Lt: 5.835 (5.810) Accm: 3.10 (3.30) Acct: 5.34 (5.43) proj_loss: -0.6220 (-0.6250) time: 0.9230 data: 0.0003 [11-26 06:57:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.25 Lm: 6.462 (6.442) Lt: 5.676 (5.669) Accm: 3.50 (3.49) Acct: 5.65 (5.66) proj_loss: -0.5810 (-0.5983) time: 0.9230 data: 0.0003 [11-26 06:57:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.25 Lm: 6.223 (6.271) Lt: 5.428 (5.485) Accm: 4.12 (3.97) Acct: 6.34 (6.11) proj_loss: -0.6234 (-0.6286) time: 0.9230 data: 0.0002 [11-26 06:57:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.25 Lm: 6.570 (6.561) Lt: 5.744 (5.786) Accm: 3.26 (3.16) Acct: 5.20 (5.17) proj_loss: -0.6050 (-0.6063) time: 0.9230 data: 0.0003 [11-26 06:57:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.25 Lm: 6.342 (6.409) Lt: 5.532 (5.616) Accm: 4.53 (3.89) Acct: 7.20 (6.22) proj_loss: -0.6290 (-0.6307) time: 0.9230 data: 0.0002 [11-26 06:57:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.25 Lm: 6.487 (6.479) Lt: 5.704 (5.705) Accm: 3.58 (3.53) Acct: 5.41 (5.26) proj_loss: -0.6144 (-0.6216) time: 0.9230 data: 0.0002 [11-26 06:57:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.25 Lm: 6.382 (6.382) Lt: 5.671 (5.646) Accm: 3.37 (3.36) Acct: 5.13 (5.22) proj_loss: -0.6257 (-0.6200) time: 0.9230 data: 0.0003 [11-26 06:57:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.25 Lm: 6.469 (6.422) Lt: 5.751 (5.646) Accm: 3.31 (3.60) Acct: 5.20 (5.77) proj_loss: -0.6006 (-0.6105) time: 0.9230 data: 0.0003 [11-26 07:03:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.25 Lm: 6.458 (6.428) Lt: 5.730 (5.662) Accm: 3.68 (3.72) Acct: 5.79 (5.92) proj_loss: -0.6080 (-0.6117) time: 0.9248 data: 0.0003 [11-26 07:03:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.25 Lm: 6.577 (6.566) Lt: 5.790 (5.798) Accm: 3.28 (3.26) Acct: 5.29 (5.28) proj_loss: -0.6163 (-0.6116) time: 0.9248 data: 0.0003 [11-26 07:03:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.25 Lm: 6.307 (6.375) Lt: 5.468 (5.563) Accm: 4.39 (3.97) Acct: 6.89 (6.31) proj_loss: -0.6236 (-0.6238) time: 0.9248 data: 0.0002 [11-26 07:03:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.25 Lm: 6.556 (6.516) Lt: 5.755 (5.731) Accm: 3.38 (3.41) Acct: 5.35 (5.27) proj_loss: -0.6199 (-0.6226) time: 0.9248 data: 0.0002 [11-26 07:03:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.25 Lm: 6.341 (6.318) Lt: 5.588 (5.551) Accm: 3.85 (3.87) Acct: 5.92 (5.96) proj_loss: -0.6221 (-0.6252) time: 0.9248 data: 0.0002 [11-26 07:03:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.25 Lm: 6.518 (6.500) Lt: 5.716 (5.712) Accm: 3.35 (3.42) Acct: 5.42 (5.49) proj_loss: -0.5876 (-0.5973) time: 0.9248 data: 0.0002 [11-26 07:03:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.25 Lm: 6.395 (6.481) Lt: 5.688 (5.768) Accm: 3.28 (3.16) Acct: 5.11 (4.87) proj_loss: -0.6276 (-0.6225) time: 0.9248 data: 0.0003 [11-26 07:03:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.25 Lm: 6.505 (6.502) Lt: 5.749 (5.748) Accm: 3.47 (3.43) Acct: 5.61 (5.54) proj_loss: -0.6292 (-0.6279) time: 0.9248 data: 0.0003 [11-26 07:10:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.28 Lm: 6.574 (6.518) Lt: 5.835 (5.768) Accm: 3.10 (3.33) Acct: 5.34 (5.28) proj_loss: -0.6220 (-0.6247) time: 0.9656 data: 0.0020 [11-26 07:10:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 158/350] Total time: 0:25:59 (0.934 s / it) [11-26 07:10:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.28 Lm: 6.487 (6.499) Lt: 5.736 (5.732) Accm: 3.58 (3.49) Acct: 5.41 (5.34) proj_loss: -0.6254 (-0.6237) time: 0.9656 data: 0.0015 [11-26 07:10:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.28 Lm: 6.462 (6.459) Lt: 5.676 (5.680) Accm: 3.50 (3.49) Acct: 5.65 (5.58) proj_loss: -0.5943 (-0.6005) time: 0.9656 data: 0.0013 [11-26 07:10:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.28 Lm: 6.570 (6.533) Lt: 5.744 (5.767) Accm: 3.29 (3.34) Acct: 5.37 (5.38) proj_loss: -0.6124 (-0.6117) time: 0.9656 data: 0.0018 [11-26 07:10:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.28 Lm: 6.259 (6.306) Lt: 5.428 (5.516) Accm: 4.12 (3.93) Acct: 6.34 (6.23) proj_loss: -0.6208 (-0.6215) time: 0.9656 data: 0.0019 [11-26 07:10:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.28 Lm: 6.409 (6.523) Lt: 5.705 (5.805) Accm: 3.19 (3.07) Acct: 5.10 (4.77) proj_loss: -0.6257 (-0.6135) time: 0.9657 data: 0.0015 [11-26 07:10:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.28 Lm: 6.447 (6.398) Lt: 5.710 (5.650) Accm: 3.82 (3.74) Acct: 5.96 (5.93) proj_loss: -0.6154 (-0.6137) time: 0.9656 data: 0.0020 [11-26 07:10:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 158/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.28 Lm: 6.342 (6.421) Lt: 5.532 (5.611) Accm: 4.24 (3.81) Acct: 6.58 (6.06) proj_loss: -0.6183 (-0.6169) time: 0.9656 data: 0.0018 [11-26 07:10:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 158/350] Total time: 0:25:59 (0.934 s / it) [11-26 07:10:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 158/350] Total time: 0:25:59 (0.934 s / it) [11-26 07:10:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 158/350] Total time: 0:25:59 (0.934 s / it) [11-26 07:10:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 158/350] Total time: 0:25:59 (0.934 s / it) [11-26 07:10:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 158/350] Total time: 0:25:59 (0.934 s / it) [11-26 07:10:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 158/350] Total time: 0:25:59 (0.934 s / it) [11-26 07:10:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 158/350] Total time: 0:25:59 (0.934 s / it) [11-26 07:10:29] (/home/user/VAR/train.py , line 276)=> [ep158] (training ) Lm: 6.431 (6.441), Lt: 5.678 (5.683), Acc m&t: 3.57 5.59, Remain: 3 days, 10:22:35, Finish: 2024-11-29 01:33 [11-26 07:10:29] (/home/user/VAR/train.py , line 276)=> [ep158] (training ) Lm: 6.431 (6.441), Lt: 5.678 (5.683), Acc m&t: 3.57 5.59, Remain: 3 days, 10:23:07, Finish: 2024-11-29 01:33 [11-26 07:10:29] (/home/user/VAR/train.py , line 276)=> [ep158] (training ) Lm: 6.431 (6.441), Lt: 5.678 (5.683), Acc m&t: 3.57 5.59, Remain: 3 days, 10:23:22, Finish: 2024-11-29 01:33 [11-26 07:10:29] (/home/user/VAR/train.py , line 276)=> [ep158] (training ) Lm: 6.431 (6.441), Lt: 5.678 (5.683), Acc m&t: 3.57 5.59, Remain: 3 days, 10:22:11, Finish: 2024-11-29 01:32 [11-26 07:10:29] (/home/user/VAR/train.py , line 276)=> [ep158] (training ) Lm: 6.431 (6.441), Lt: 5.678 (5.683), Acc m&t: 3.57 5.59, Remain: 3 days, 10:22:58, Finish: 2024-11-29 01:33 [11-26 07:10:29] (/home/user/VAR/train.py , line 276)=> [ep158] (training ) Lm: 6.431 (6.441), Lt: 5.678 (5.683), Acc m&t: 3.57 5.59, Remain: 3 days, 10:23:56, Finish: 2024-11-29 01:34 [11-26 07:10:29] (/home/user/VAR/train.py , line 276)=> [ep158] (training ) Lm: 6.431 (6.441), Lt: 5.678 (5.683), Acc m&t: 3.57 5.59, Remain: 3 days, 10:22:18, Finish: 2024-11-29 01:32 [11-26 07:10:29] (/home/user/VAR/train.py , line 276)=> [ep158] (training ) Lm: 6.431 (6.441), Lt: 5.678 (5.683), Acc m&t: 3.57 5.59, Remain: 3 days, 10:24:52, Finish: 2024-11-29 01:35 [11-26 07:10:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 0/1669] eta: 0:24:36 tlr: 0.00014 tnm: 0.26 Lm: 6.525 (6.525) Lt: 5.842 (5.842) Accm: 3.15 (3.15) Acct: 5.03 (5.03) proj_loss: -0.5897 (-0.5897) time: 0.8844 data: 0.0004 [11-26 07:10:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 0/1669] eta: 0:24:37 tlr: 0.00014 tnm: 0.26 Lm: 6.507 (6.507) Lt: 5.786 (5.786) Accm: 3.28 (3.28) Acct: 5.17 (5.17) proj_loss: -0.6104 (-0.6104) time: 0.8850 data: 0.0004 [11-26 07:10:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 0/1669] eta: 0:24:37 tlr: 0.00014 tnm: 0.26 Lm: 6.173 (6.173) Lt: 5.391 (5.391) Accm: 5.04 (5.04) Acct: 7.89 (7.89) proj_loss: -0.6236 (-0.6236) time: 0.8851 data: 0.0004 [11-26 07:10:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 0/1669] eta: 0:24:37 tlr: 0.00014 tnm: 0.26 Lm: 6.364 (6.364) Lt: 5.567 (5.567) Accm: 4.30 (4.30) Acct: 7.16 (7.16) proj_loss: -0.6423 (-0.6423) time: 0.8850 data: 0.0003 [11-26 07:10:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 0/1669] eta: 0:24:37 tlr: 0.00014 tnm: 0.26 Lm: 6.596 (6.596) Lt: 5.844 (5.844) Accm: 3.13 (3.13) Acct: 4.37 (4.37) proj_loss: -0.6261 (-0.6261) time: 0.8852 data: 0.0003 [11-26 07:10:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 0/1669] eta: 0:24:35 tlr: 0.00014 tnm: 0.26 Lm: 6.338 (6.338) Lt: 5.544 (5.544) Accm: 3.77 (3.77) Acct: 5.99 (5.99) proj_loss: -0.5875 (-0.5875) time: 0.8840 data: 0.0004 [11-26 07:10:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 0/1669] eta: 0:24:38 tlr: 0.00014 tnm: 0.26 Lm: 6.437 (6.437) Lt: 5.648 (5.648) Accm: 3.41 (3.41) Acct: 5.54 (5.54) proj_loss: -0.6193 (-0.6193) time: 0.8860 data: 0.0004 [11-26 07:10:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 0/1669] eta: 0:24:33 tlr: 0.00014 tnm: 0.26 Lm: 6.455 (6.455) Lt: 5.715 (5.715) Accm: 3.48 (3.48) Acct: 5.48 (5.48) proj_loss: -0.6252 (-0.6252) time: 0.8827 data: 0.0004 [11-26 07:16:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.26 Lm: 6.326 (6.326) Lt: 5.579 (5.579) Accm: 3.94 (3.94) Acct: 6.13 (6.13) proj_loss: -0.6201 (-0.6201) time: 0.9252 data: 0.0003 [11-26 07:16:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.26 Lm: 6.484 (6.484) Lt: 5.709 (5.709) Accm: 3.35 (3.35) Acct: 5.10 (5.10) proj_loss: -0.6239 (-0.6239) time: 0.9252 data: 0.0002 [11-26 07:16:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 417/1669] eta: 0:19:18 tlr: 0.00014 tnm: 0.26 Lm: 6.333 (6.333) Lt: 5.543 (5.543) Accm: 4.24 (4.24) Acct: 6.71 (6.71) proj_loss: -0.6187 (-0.6187) time: 0.9252 data: 0.0002 [11-26 07:16:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 417/1669] eta: 0:19:18 tlr: 0.00014 tnm: 0.26 Lm: 6.557 (6.557) Lt: 5.824 (5.824) Accm: 3.45 (3.45) Acct: 5.72 (5.72) proj_loss: -0.6334 (-0.6334) time: 0.9252 data: 0.0003 [11-26 07:16:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.26 Lm: 6.427 (6.427) Lt: 5.661 (5.661) Accm: 3.42 (3.42) Acct: 5.48 (5.48) proj_loss: -0.6263 (-0.6263) time: 0.9252 data: 0.0002 [11-26 07:16:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 417/1669] eta: 0:19:18 tlr: 0.00014 tnm: 0.26 Lm: 6.591 (6.591) Lt: 5.903 (5.903) Accm: 2.76 (2.76) Acct: 4.46 (4.46) proj_loss: -0.6039 (-0.6039) time: 0.9252 data: 0.0003 [11-26 07:16:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 417/1669] eta: 0:19:18 tlr: 0.00014 tnm: 0.26 Lm: 6.411 (6.411) Lt: 5.661 (5.661) Accm: 3.74 (3.74) Acct: 5.79 (5.79) proj_loss: -0.5999 (-0.5999) time: 0.9252 data: 0.0002 [11-26 07:16:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.26 Lm: 6.327 (6.327) Lt: 5.577 (5.577) Accm: 4.17 (4.17) Acct: 6.39 (6.39) proj_loss: -0.6028 (-0.6028) time: 0.9252 data: 0.0003 [11-26 07:23:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.25 Lm: 6.316 (6.306) Lt: 5.544 (5.532) Accm: 3.96 (4.10) Acct: 5.99 (6.24) proj_loss: -0.6181 (-0.6095) time: 0.9250 data: 0.0003 [11-26 07:23:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.25 Lm: 6.489 (6.534) Lt: 5.750 (5.799) Accm: 3.12 (3.34) Acct: 4.89 (5.44) proj_loss: -0.6245 (-0.6276) time: 0.9250 data: 0.0003 [11-26 07:23:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.25 Lm: 6.437 (6.500) Lt: 5.674 (5.750) Accm: 3.41 (3.19) Acct: 5.41 (5.15) proj_loss: -0.6193 (-0.6193) time: 0.9250 data: 0.0003 [11-26 07:23:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.25 Lm: 6.525 (6.425) Lt: 5.842 (5.714) Accm: 3.15 (3.29) Acct: 5.03 (5.18) proj_loss: -0.6181 (-0.6090) time: 0.9250 data: 0.0002 [11-26 07:23:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.25 Lm: 6.507 (6.444) Lt: 5.732 (5.685) Accm: 3.28 (3.58) Acct: 5.27 (5.61) proj_loss: -0.6104 (-0.6060) time: 0.9250 data: 0.0003 [11-26 07:23:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.25 Lm: 6.455 (6.403) Lt: 5.715 (5.667) Accm: 3.48 (3.78) Acct: 5.48 (5.77) proj_loss: -0.6252 (-0.6263) time: 0.9250 data: 0.0003 [11-26 07:23:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.25 Lm: 6.555 (6.507) Lt: 5.844 (5.754) Accm: 3.15 (3.28) Acct: 4.92 (5.04) proj_loss: -0.6218 (-0.6211) time: 0.9250 data: 0.0003 [11-26 07:23:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.25 Lm: 6.253 (6.307) Lt: 5.518 (5.535) Accm: 3.64 (4.04) Acct: 5.99 (6.47) proj_loss: -0.6236 (-0.6259) time: 0.9250 data: 0.0003 [11-26 07:29:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.26 Lm: 6.373 (6.372) Lt: 5.607 (5.594) Accm: 3.54 (3.83) Acct: 5.77 (6.08) proj_loss: -0.6187 (-0.6210) time: 0.9254 data: 0.0003 [11-26 07:29:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.26 Lm: 6.485 (6.508) Lt: 5.741 (5.764) Accm: 3.42 (3.26) Acct: 5.35 (5.19) proj_loss: -0.6263 (-0.6236) time: 0.9254 data: 0.0002 [11-26 07:29:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.26 Lm: 6.411 (6.384) Lt: 5.634 (5.616) Accm: 3.65 (3.69) Acct: 5.84 (5.86) proj_loss: -0.6143 (-0.6167) time: 0.9254 data: 0.0003 [11-26 07:29:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.26 Lm: 6.463 (6.419) Lt: 5.711 (5.681) Accm: 3.45 (3.41) Acct: 5.44 (5.35) proj_loss: -0.6039 (-0.6039) time: 0.9254 data: 0.0002 [11-26 07:29:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.26 Lm: 6.289 (6.290) Lt: 5.494 (5.509) Accm: 4.12 (4.15) Acct: 6.39 (6.41) proj_loss: -0.6052 (-0.6052) time: 0.9254 data: 0.0003 [11-26 07:29:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.26 Lm: 6.547 (6.515) Lt: 5.812 (5.761) Accm: 3.30 (3.33) Acct: 5.04 (5.07) proj_loss: -0.6185 (-0.6169) time: 0.9254 data: 0.0002 [11-26 07:29:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.26 Lm: 6.427 (6.450) Lt: 5.658 (5.697) Accm: 3.59 (3.52) Acct: 5.68 (5.70) proj_loss: -0.6203 (-0.6164) time: 0.9254 data: 0.0003 [11-26 07:29:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.26 Lm: 6.470 (6.423) Lt: 5.732 (5.688) Accm: 3.47 (3.61) Acct: 5.27 (5.41) proj_loss: -0.6233 (-0.6251) time: 0.9254 data: 0.0003 [11-26 07:36:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.455 (6.428) Lt: 5.715 (5.684) Accm: 3.48 (3.62) Acct: 5.48 (5.54) proj_loss: -0.6215 (-0.6203) time: 0.9244 data: 0.0020 [11-26 07:36:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 159/350] Total time: 0:25:42 (0.924 s / it) [11-26 07:36:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.316 (6.303) Lt: 5.544 (5.530) Accm: 3.96 (4.06) Acct: 5.99 (6.32) proj_loss: -0.6181 (-0.6108) time: 0.9244 data: 0.0019 [11-26 07:36:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.437 (6.457) Lt: 5.674 (5.706) Accm: 3.44 (3.43) Acct: 5.41 (5.45) proj_loss: -0.6332 (-0.6256) time: 0.9244 data: 0.0014 [11-26 07:36:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.470 (6.401) Lt: 5.639 (5.620) Accm: 3.54 (3.66) Acct: 6.03 (5.90) proj_loss: -0.6104 (-0.6142) time: 0.9244 data: 0.0018 [11-26 07:36:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.540 (6.498) Lt: 5.781 (5.737) Accm: 3.45 (3.40) Acct: 5.17 (5.25) proj_loss: -0.6153 (-0.6159) time: 0.9244 data: 0.0021 [11-26 07:36:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.402 (6.395) Lt: 5.581 (5.647) Accm: 3.76 (3.50) Acct: 5.85 (5.56) proj_loss: -0.6181 (-0.6095) time: 0.9244 data: 0.0019 [11-26 07:36:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.489 (6.467) Lt: 5.750 (5.748) Accm: 3.26 (3.47) Acct: 4.89 (5.41) proj_loss: -0.6225 (-0.6176) time: 0.9244 data: 0.0015 [11-26 07:36:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 159/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.330 (6.363) Lt: 5.587 (5.592) Accm: 3.64 (3.91) Acct: 5.99 (6.15) proj_loss: -0.6236 (-0.6234) time: 0.9244 data: 0.0018 [11-26 07:36:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 159/350] Total time: 0:25:42 (0.924 s / it) [11-26 07:36:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 159/350] Total time: 0:25:42 (0.924 s / it) [11-26 07:36:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 159/350] Total time: 0:25:42 (0.924 s / it) [11-26 07:36:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 159/350] Total time: 0:25:42 (0.924 s / it) [11-26 07:36:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 159/350] Total time: 0:25:42 (0.924 s / it) [11-26 07:36:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 159/350] Total time: 0:25:42 (0.924 s / it) [11-26 07:36:11] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 159/350] Total time: 0:25:42 (0.924 s / it) [11-26 07:40:30] (home/user/VAR/trainer.py, line 114)=> FID: 3.4398689619737866 [11-26 07:40:31] (/home/user/VAR/train.py , line 259)=> [*] [ep159] (val 50000) Lm: 6.4208, Lt: 5.6664, Acc m&t: 3.61 5.66, Val cost: 258.77s [11-26 07:40:31] (/home/user/VAR/train.py , line 264)=> [saving ckpt] ... [saving ckpt](*) finished! @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth [11-26 07:41:51] (/home/user/VAR/train.py , line 276)=> [ep159] (training ) Lm: 6.421 (6.421), Lt: 5.666 (5.666), Acc m&t: 3.61 5.66, Remain: 3 days, 10:07:48, Finish: 2024-11-29 01:43 [11-26 07:41:51] (/home/user/VAR/train.py , line 276)=> [ep159] (training ) Lm: 6.421 (6.421), Lt: 5.666 (5.666), Acc m&t: 3.61 5.66, Remain: 3 days, 10:08:32, Finish: 2024-11-29 01:44 [11-26 07:41:51] (/home/user/VAR/train.py , line 276)=> [ep159] (training ) Lm: 6.421 (6.421), Lt: 5.666 (5.666), Acc m&t: 3.61 5.66, Remain: 3 days, 10:07:29, Finish: 2024-11-29 01:43 [11-26 07:41:51] (/home/user/VAR/train.py , line 276)=> [ep159] (training ) Lm: 6.421 (6.421), Lt: 5.666 (5.666), Acc m&t: 3.61 5.66, Remain: 3 days, 10:07:28, Finish: 2024-11-29 01:43 [11-26 07:41:51] (/home/user/VAR/train.py , line 276)=> [ep159] (training ) Lm: 6.421 (6.421), Lt: 5.666 (5.666), Acc m&t: 3.61 5.66, Remain: 3 days, 10:07:14, Finish: 2024-11-29 01:43 [11-26 07:41:51] (/home/user/VAR/train.py , line 276)=> [ep159] (training ) Lm: 6.421 (6.421), Lt: 5.666 (5.666), Acc m&t: 3.61 5.66, Remain: 3 days, 10:07:27, Finish: 2024-11-29 01:43 [11-26 07:41:51] (/home/user/VAR/train.py , line 276)=> [ep159] (training ) Lm: 6.421 (6.421), Lt: 5.666 (5.666), Acc m&t: 3.61 5.66, Remain: 3 days, 10:07:04, Finish: 2024-11-29 01:43 [11-26 07:41:51] (/home/user/VAR/train.py , line 276)=> [ep159] (training ) Lm: 6.421 (6.421), Lt: 5.666 (5.666), Acc m&t: 3.61 5.66, Remain: 3 days, 10:07:49, Finish: 2024-11-29 01:44 [11-26 07:41:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 0:26:55 tlr: 0.00014 tnm: 0.27 Lm: 6.250 (6.250) Lt: 5.514 (5.514) Accm: 4.20 (4.20) Acct: 6.58 (6.58) proj_loss: -0.6546 (-0.6546) time: 0.9678 data: 0.0004 [11-26 07:41:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 0:27:10 tlr: 0.00014 tnm: 0.27 Lm: 6.389 (6.389) Lt: 5.649 (5.649) Accm: 3.80 (3.80) Acct: 5.99 (5.99) proj_loss: -0.6115 (-0.6115) time: 0.9766 data: 0.0003 [11-26 07:41:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 0:27:46 tlr: 0.00014 tnm: 0.27 Lm: 6.488 (6.488) Lt: 5.668 (5.668) Accm: 3.70 (3.70) Acct: 6.03 (6.03) proj_loss: -0.6153 (-0.6153) time: 0.9986 data: 0.0004 [11-26 07:41:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 0:26:54 tlr: 0.00014 tnm: 0.27 Lm: 6.471 (6.471) Lt: 5.654 (5.654) Accm: 3.32 (3.32) Acct: 5.06 (5.06) proj_loss: -0.6182 (-0.6182) time: 0.9674 data: 0.0004 [11-26 07:41:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 0:26:54 tlr: 0.00014 tnm: 0.27 Lm: 6.446 (6.446) Lt: 5.652 (5.652) Accm: 3.41 (3.41) Acct: 5.34 (5.34) proj_loss: -0.6126 (-0.6126) time: 0.9673 data: 0.0003 [11-26 07:41:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 0:26:53 tlr: 0.00014 tnm: 0.27 Lm: 6.633 (6.633) Lt: 5.846 (5.846) Accm: 2.87 (2.87) Acct: 4.55 (4.55) proj_loss: -0.6257 (-0.6257) time: 0.9670 data: 0.0004 [11-26 07:41:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 0:26:55 tlr: 0.00014 tnm: 0.27 Lm: 6.507 (6.507) Lt: 5.732 (5.732) Accm: 2.96 (2.96) Acct: 4.41 (4.41) proj_loss: -0.6169 (-0.6169) time: 0.9677 data: 0.0003 [11-26 07:41:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 0:26:54 tlr: 0.00014 tnm: 0.27 Lm: 6.617 (6.617) Lt: 5.872 (5.872) Accm: 3.37 (3.37) Acct: 4.99 (4.99) proj_loss: -0.6180 (-0.6180) time: 0.9675 data: 0.0004 [11-26 07:48:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.26 Lm: 6.560 (6.560) Lt: 5.817 (5.817) Accm: 3.53 (3.53) Acct: 5.58 (5.58) proj_loss: -0.6249 (-0.6249) time: 0.9252 data: 0.0003 [11-26 07:48:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.26 Lm: 6.484 (6.484) Lt: 5.781 (5.781) Accm: 3.25 (3.25) Acct: 4.96 (4.96) proj_loss: -0.6159 (-0.6159) time: 0.9252 data: 0.0002 [11-26 07:48:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.26 Lm: 6.447 (6.447) Lt: 5.607 (5.607) Accm: 3.87 (3.87) Acct: 6.13 (6.13) proj_loss: -0.5861 (-0.5861) time: 0.9252 data: 0.0003 [11-26 07:48:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.26 Lm: 6.400 (6.400) Lt: 5.620 (5.620) Accm: 3.47 (3.47) Acct: 5.30 (5.30) proj_loss: -0.6072 (-0.6072) time: 0.9252 data: 0.0003 [11-26 07:48:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.26 Lm: 6.358 (6.358) Lt: 5.590 (5.590) Accm: 3.90 (3.90) Acct: 6.20 (6.20) proj_loss: -0.6305 (-0.6305) time: 0.9252 data: 0.0002 [11-26 07:48:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.26 Lm: 6.499 (6.499) Lt: 5.715 (5.715) Accm: 3.26 (3.26) Acct: 5.20 (5.20) proj_loss: -0.6261 (-0.6261) time: 0.9252 data: 0.0003 [11-26 07:48:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.26 Lm: 6.362 (6.362) Lt: 5.561 (5.561) Accm: 3.72 (3.72) Acct: 5.65 (5.65) proj_loss: -0.6047 (-0.6047) time: 0.9252 data: 0.0002 [11-26 07:48:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.26 Lm: 6.383 (6.383) Lt: 5.622 (5.622) Accm: 3.69 (3.69) Acct: 5.39 (5.39) proj_loss: -0.6113 (-0.6113) time: 0.9252 data: 0.0002 [11-26 07:54:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.507 (6.432) Lt: 5.732 (5.666) Accm: 3.23 (3.54) Acct: 4.86 (5.21) proj_loss: -0.6169 (-0.6182) time: 0.9267 data: 0.0003 [11-26 07:54:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.466 (6.455) Lt: 5.667 (5.699) Accm: 3.61 (3.57) Acct: 5.82 (5.80) proj_loss: -0.6065 (-0.6221) time: 0.9267 data: 0.0003 [11-26 07:54:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.503 (6.520) Lt: 5.762 (5.753) Accm: 3.37 (3.47) Acct: 5.30 (5.49) proj_loss: -0.6180 (-0.6197) time: 0.9267 data: 0.0003 [11-26 07:54:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.442 (6.389) Lt: 5.654 (5.607) Accm: 3.44 (3.63) Acct: 5.65 (5.65) proj_loss: -0.5977 (-0.6024) time: 0.9267 data: 0.0003 [11-26 07:54:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.580 (6.522) Lt: 5.852 (5.805) Accm: 3.32 (3.27) Acct: 5.17 (5.03) proj_loss: -0.6202 (-0.6225) time: 0.9267 data: 0.0003 [11-26 07:54:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.405 (6.362) Lt: 5.546 (5.542) Accm: 4.04 (3.97) Acct: 6.23 (6.29) proj_loss: -0.6153 (-0.5986) time: 0.9267 data: 0.0003 [11-26 07:54:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.577 (6.525) Lt: 5.823 (5.751) Accm: 3.38 (3.30) Acct: 4.92 (5.11) proj_loss: -0.6264 (-0.6281) time: 0.9267 data: 0.0003 [11-26 07:54:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.446 (6.505) Lt: 5.652 (5.735) Accm: 3.41 (3.22) Acct: 5.27 (4.94) proj_loss: -0.6018 (-0.6024) time: 0.9267 data: 0.0003 [11-26 08:01:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.26 Lm: 6.518 (6.527) Lt: 5.783 (5.779) Accm: 3.36 (3.25) Acct: 5.25 (5.01) proj_loss: -0.6072 (-0.6098) time: 0.9247 data: 0.0003 [11-26 08:01:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.26 Lm: 6.457 (6.415) Lt: 5.666 (5.625) Accm: 3.47 (3.60) Acct: 5.61 (5.63) proj_loss: -0.6080 (-0.6091) time: 0.9247 data: 0.0003 [11-26 08:01:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.26 Lm: 6.549 (6.522) Lt: 5.835 (5.808) Accm: 3.30 (3.27) Acct: 4.82 (4.89) proj_loss: -0.6280 (-0.6289) time: 0.9247 data: 0.0003 [11-26 08:01:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.26 Lm: 6.387 (6.391) Lt: 5.622 (5.624) Accm: 3.50 (3.59) Acct: 5.54 (5.47) proj_loss: -0.6191 (-0.6190) time: 0.9247 data: 0.0003 [11-26 08:01:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.26 Lm: 6.447 (6.448) Lt: 5.610 (5.663) Accm: 3.69 (3.62) Acct: 6.11 (5.95) proj_loss: -0.6058 (-0.6162) time: 0.9247 data: 0.0002 [11-26 08:01:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.26 Lm: 6.345 (6.343) Lt: 5.500 (5.520) Accm: 4.10 (4.08) Acct: 6.42 (6.40) proj_loss: -0.6161 (-0.6032) time: 0.9247 data: 0.0003 [11-26 08:01:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.26 Lm: 6.472 (6.449) Lt: 5.693 (5.687) Accm: 3.53 (3.69) Acct: 5.73 (5.78) proj_loss: -0.6136 (-0.6141) time: 0.9247 data: 0.0003 [11-26 08:01:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.26 Lm: 6.533 (6.516) Lt: 5.802 (5.759) Accm: 3.28 (3.27) Acct: 4.86 (5.03) proj_loss: -0.6281 (-0.6285) time: 0.9247 data: 0.0003 [11-26 08:07:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.489 (6.492) Lt: 5.781 (5.729) Accm: 3.38 (3.34) Acct: 4.92 (5.21) proj_loss: -0.6297 (-0.6301) time: 0.9276 data: 0.0016 [11-26 08:07:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:25:43 (0.925 s / it) [11-26 08:07:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.457 (6.423) Lt: 5.677 (5.637) Accm: 3.44 (3.57) Acct: 5.58 (5.59) proj_loss: -0.5977 (-0.6043) time: 0.9276 data: 0.0014 [11-26 08:07:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.428 (6.407) Lt: 5.554 (5.636) Accm: 3.76 (3.79) Acct: 6.40 (6.08) proj_loss: -0.6065 (-0.6279) time: 0.9276 data: 0.0015 [11-26 08:07:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.519 (6.516) Lt: 5.818 (5.799) Accm: 3.32 (3.32) Acct: 5.17 (5.05) proj_loss: -0.6202 (-0.6255) time: 0.9276 data: 0.0020 [11-26 08:07:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.289 (6.332) Lt: 5.454 (5.506) Accm: 4.17 (4.11) Acct: 6.61 (6.45) proj_loss: -0.6170 (-0.6095) time: 0.9276 data: 0.0020 [11-26 08:07:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.406 (6.394) Lt: 5.660 (5.631) Accm: 3.76 (3.63) Acct: 5.65 (5.50) proj_loss: -0.6214 (-0.6211) time: 0.9276 data: 0.0014 [11-26 08:07:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.579 (6.537) Lt: 5.896 (5.803) Accm: 3.31 (3.14) Acct: 5.23 (4.86) proj_loss: -0.6025 (-0.6084) time: 0.9276 data: 0.0021 [11-26 08:07:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.503 (6.466) Lt: 5.762 (5.706) Accm: 3.37 (3.59) Acct: 5.30 (5.54) proj_loss: -0.6122 (-0.6137) time: 0.9276 data: 0.0016 [11-26 08:07:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:25:43 (0.925 s / it) [11-26 08:07:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:25:43 (0.925 s / it) [11-26 08:07:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:25:44 (0.925 s / it) [11-26 08:07:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:25:44 (0.925 s / it) [11-26 08:07:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:25:44 (0.925 s / it) [11-26 08:07:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:25:44 (0.925 s / it) [11-26 08:07:35] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:25:44 (0.925 s / it) [11-26 08:07:35] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.421 (6.432), Lt: 5.666 (5.670), Acc m&t: 3.61 5.66, Remain: 3 days, 9:49:45, Finish: 2024-11-29 01:57 [11-26 08:07:35] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.421 (6.432), Lt: 5.666 (5.670), Acc m&t: 3.61 5.66, Remain: 3 days, 9:48:21, Finish: 2024-11-29 01:55 [11-26 08:07:35] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.421 (6.432), Lt: 5.666 (5.670), Acc m&t: 3.61 5.66, Remain: 3 days, 9:48:36, Finish: 2024-11-29 01:56 [11-26 08:07:35] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.421 (6.432), Lt: 5.666 (5.670), Acc m&t: 3.61 5.66, Remain: 3 days, 9:48:33, Finish: 2024-11-29 01:56 [11-26 08:07:35] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.421 (6.432), Lt: 5.666 (5.670), Acc m&t: 3.61 5.66, Remain: 3 days, 9:49:21, Finish: 2024-11-29 01:56 [11-26 08:07:35] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.421 (6.432), Lt: 5.666 (5.670), Acc m&t: 3.61 5.66, Remain: 3 days, 9:49:48, Finish: 2024-11-29 01:57 [11-26 08:07:35] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.421 (6.432), Lt: 5.666 (5.670), Acc m&t: 3.61 5.66, Remain: 3 days, 9:49:42, Finish: 2024-11-29 01:57 [11-26 08:07:35] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.421 (6.432), Lt: 5.666 (5.670), Acc m&t: 3.61 5.66, Remain: 3 days, 9:48:11, Finish: 2024-11-29 01:55 [11-26 08:07:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:44 tlr: 0.00014 tnm: 0.27 Lm: 6.391 (6.391) Lt: 5.666 (5.666) Accm: 3.74 (3.74) Acct: 5.23 (5.23) proj_loss: -0.6042 (-0.6042) time: 0.9252 data: 0.0003 [11-26 08:07:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:43 tlr: 0.00014 tnm: 0.27 Lm: 6.424 (6.424) Lt: 5.564 (5.564) Accm: 3.92 (3.92) Acct: 6.58 (6.58) proj_loss: -0.5988 (-0.5988) time: 0.9250 data: 0.0004 [11-26 08:07:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:43 tlr: 0.00014 tnm: 0.27 Lm: 6.205 (6.205) Lt: 5.416 (5.416) Accm: 4.06 (4.06) Acct: 6.27 (6.27) proj_loss: -0.6103 (-0.6103) time: 0.9250 data: 0.0003 [11-26 08:07:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:43 tlr: 0.00014 tnm: 0.27 Lm: 6.569 (6.569) Lt: 5.810 (5.810) Accm: 3.41 (3.41) Acct: 5.17 (5.17) proj_loss: -0.6072 (-0.6072) time: 0.9246 data: 0.0003 [11-26 08:07:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:44 tlr: 0.00014 tnm: 0.27 Lm: 6.426 (6.426) Lt: 5.684 (5.684) Accm: 3.74 (3.74) Acct: 5.96 (5.96) proj_loss: -0.5878 (-0.5878) time: 0.9252 data: 0.0004 [11-26 08:07:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:44 tlr: 0.00014 tnm: 0.27 Lm: 6.620 (6.620) Lt: 5.918 (5.918) Accm: 2.99 (2.99) Acct: 4.72 (4.72) proj_loss: -0.6223 (-0.6223) time: 0.9252 data: 0.0003 [11-26 08:07:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:44 tlr: 0.00014 tnm: 0.27 Lm: 6.313 (6.313) Lt: 5.575 (5.575) Accm: 4.18 (4.18) Acct: 7.20 (7.20) proj_loss: -0.6150 (-0.6150) time: 0.9253 data: 0.0004 [11-26 08:07:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:44 tlr: 0.00014 tnm: 0.27 Lm: 6.443 (6.443) Lt: 5.703 (5.703) Accm: 3.58 (3.58) Acct: 5.61 (5.61) proj_loss: -0.5942 (-0.5942) time: 0.9256 data: 0.0003 [11-26 08:14:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:24 tlr: 0.00014 tnm: 0.26 Lm: 6.470 (6.470) Lt: 5.706 (5.706) Accm: 3.56 (3.56) Acct: 5.60 (5.60) proj_loss: -0.6066 (-0.6066) time: 0.9952 data: 0.0003 [11-26 08:14:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:24 tlr: 0.00014 tnm: 0.26 Lm: 6.596 (6.596) Lt: 5.886 (5.886) Accm: 2.97 (2.97) Acct: 4.60 (4.60) proj_loss: -0.6306 (-0.6306) time: 0.9952 data: 0.0002 [11-26 08:14:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:24 tlr: 0.00014 tnm: 0.26 Lm: 6.308 (6.308) Lt: 5.562 (5.562) Accm: 4.11 (4.11) Acct: 6.68 (6.68) proj_loss: -0.6268 (-0.6268) time: 0.9952 data: 0.0003 [11-26 08:14:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:24 tlr: 0.00014 tnm: 0.26 Lm: 6.407 (6.407) Lt: 5.672 (5.672) Accm: 3.92 (3.92) Acct: 5.87 (5.87) proj_loss: -0.6086 (-0.6086) time: 0.9952 data: 0.0003 [11-26 08:14:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:24 tlr: 0.00014 tnm: 0.26 Lm: 6.300 (6.300) Lt: 5.561 (5.561) Accm: 3.90 (3.90) Acct: 5.79 (5.79) proj_loss: -0.6144 (-0.6144) time: 0.9952 data: 0.0002 [11-26 08:14:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:24 tlr: 0.00014 tnm: 0.26 Lm: 6.499 (6.499) Lt: 5.724 (5.724) Accm: 3.37 (3.37) Acct: 5.04 (5.04) proj_loss: -0.6131 (-0.6131) time: 0.9952 data: 0.0002 [11-26 08:14:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:24 tlr: 0.00014 tnm: 0.26 Lm: 6.417 (6.417) Lt: 5.578 (5.578) Accm: 3.72 (3.72) Acct: 6.20 (6.20) proj_loss: -0.6102 (-0.6102) time: 0.9952 data: 0.0002 [11-26 08:14:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:24 tlr: 0.00014 tnm: 0.26 Lm: 6.292 (6.292) Lt: 5.514 (5.514) Accm: 3.80 (3.80) Acct: 5.68 (5.68) proj_loss: -0.6068 (-0.6068) time: 0.9952 data: 0.0003 [11-26 08:20:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:13:09 tlr: 0.00014 tnm: 0.27 Lm: 6.391 (6.341) Lt: 5.666 (5.581) Accm: 3.74 (3.64) Acct: 5.34 (5.57) proj_loss: -0.6094 (-0.6131) time: 0.9252 data: 0.0003 [11-26 08:20:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:13:09 tlr: 0.00014 tnm: 0.27 Lm: 6.496 (6.510) Lt: 5.710 (5.769) Accm: 3.54 (3.35) Acct: 5.58 (5.27) proj_loss: -0.6175 (-0.6102) time: 0.9252 data: 0.0003 [11-26 08:20:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:13:09 tlr: 0.00014 tnm: 0.27 Lm: 6.324 (6.308) Lt: 5.564 (5.562) Accm: 4.06 (4.04) Acct: 6.27 (6.00) proj_loss: -0.6185 (-0.6211) time: 0.9252 data: 0.0002 [11-26 08:20:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:13:09 tlr: 0.00014 tnm: 0.27 Lm: 6.429 (6.456) Lt: 5.637 (5.677) Accm: 3.41 (3.41) Acct: 5.17 (5.18) proj_loss: -0.6072 (-0.6075) time: 0.9252 data: 0.0003 [11-26 08:20:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:13:09 tlr: 0.00014 tnm: 0.27 Lm: 6.426 (6.449) Lt: 5.684 (5.676) Accm: 3.74 (3.62) Acct: 5.79 (5.56) proj_loss: -0.6173 (-0.6115) time: 0.9252 data: 0.0003 [11-26 08:20:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:13:09 tlr: 0.00014 tnm: 0.27 Lm: 6.313 (6.389) Lt: 5.575 (5.645) Accm: 4.04 (3.70) Acct: 6.16 (5.93) proj_loss: -0.6150 (-0.6210) time: 0.9252 data: 0.0003 [11-26 08:20:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:13:09 tlr: 0.00014 tnm: 0.27 Lm: 6.573 (6.482) Lt: 5.854 (5.751) Accm: 2.99 (3.49) Acct: 4.72 (5.49) proj_loss: -0.6223 (-0.6128) time: 0.9252 data: 0.0002 [11-26 08:20:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:13:09 tlr: 0.00014 tnm: 0.27 Lm: 6.424 (6.460) Lt: 5.592 (5.643) Accm: 3.53 (3.35) Acct: 5.82 (5.54) proj_loss: -0.5990 (-0.6064) time: 0.9252 data: 0.0003 [11-26 08:27:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:32 tlr: 0.00014 tnm: 0.26 Lm: 6.417 (6.427) Lt: 5.578 (5.623) Accm: 3.58 (3.42) Acct: 5.77 (5.59) proj_loss: -0.6001 (-0.6052) time: 0.9268 data: 0.0003 [11-26 08:27:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:32 tlr: 0.00014 tnm: 0.26 Lm: 6.308 (6.366) Lt: 5.590 (5.635) Accm: 3.98 (3.76) Acct: 5.87 (5.85) proj_loss: -0.6268 (-0.6274) time: 0.9268 data: 0.0004 [11-26 08:27:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:32 tlr: 0.00014 tnm: 0.26 Lm: 6.407 (6.408) Lt: 5.672 (5.632) Accm: 3.91 (3.74) Acct: 5.87 (5.68) proj_loss: -0.6209 (-0.6147) time: 0.9268 data: 0.0003 [11-26 08:27:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:32 tlr: 0.00014 tnm: 0.26 Lm: 6.414 (6.422) Lt: 5.676 (5.687) Accm: 3.62 (3.68) Acct: 5.46 (5.66) proj_loss: -0.6269 (-0.6175) time: 0.9268 data: 0.0003 [11-26 08:27:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:32 tlr: 0.00014 tnm: 0.26 Lm: 6.485 (6.502) Lt: 5.722 (5.761) Accm: 3.45 (3.35) Acct: 5.41 (5.26) proj_loss: -0.6059 (-0.6052) time: 0.9268 data: 0.0003 [11-26 08:27:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:32 tlr: 0.00014 tnm: 0.26 Lm: 6.359 (6.381) Lt: 5.635 (5.625) Accm: 3.90 (3.72) Acct: 5.79 (5.70) proj_loss: -0.6146 (-0.6185) time: 0.9268 data: 0.0002 [11-26 08:27:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:32 tlr: 0.00014 tnm: 0.26 Lm: 6.444 (6.457) Lt: 5.664 (5.681) Accm: 3.45 (3.50) Acct: 5.30 (5.33) proj_loss: -0.6131 (-0.6144) time: 0.9268 data: 0.0003 [11-26 08:27:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:32 tlr: 0.00014 tnm: 0.26 Lm: 6.396 (6.356) Lt: 5.649 (5.594) Accm: 3.63 (3.61) Acct: 5.53 (5.60) proj_loss: -0.6152 (-0.6151) time: 0.9268 data: 0.0003 [11-26 08:33:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.391 (6.350) Lt: 5.633 (5.562) Accm: 3.53 (3.59) Acct: 5.72 (5.65) proj_loss: -0.6094 (-0.6103) time: 0.9278 data: 0.0019 [11-26 08:33:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 161/350] Total time: 0:26:01 (0.935 s / it) [11-26 08:33:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.426 (6.454) Lt: 5.684 (5.680) Accm: 3.74 (3.58) Acct: 5.79 (5.51) proj_loss: -0.6173 (-0.6092) time: 0.9278 data: 0.0018 [11-26 08:33:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.324 (6.360) Lt: 5.564 (5.589) Accm: 4.06 (3.80) Acct: 6.27 (5.90) proj_loss: -0.6107 (-0.6115) time: 0.9278 data: 0.0015 [11-26 08:33:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.459 (6.463) Lt: 5.681 (5.681) Accm: 3.41 (3.42) Acct: 5.17 (5.28) proj_loss: -0.6191 (-0.6155) time: 0.9278 data: 0.0016 [11-26 08:33:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.410 (6.391) Lt: 5.564 (5.570) Accm: 3.64 (3.56) Acct: 5.82 (5.79) proj_loss: -0.5999 (-0.6041) time: 0.9278 data: 0.0018 [11-26 08:33:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.313 (6.394) Lt: 5.606 (5.670) Accm: 3.92 (3.69) Acct: 5.58 (5.66) proj_loss: -0.6246 (-0.6268) time: 0.9278 data: 0.0015 [11-26 08:33:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.522 (6.442) Lt: 5.827 (5.715) Accm: 3.61 (3.67) Acct: 5.75 (5.68) proj_loss: -0.6223 (-0.6168) time: 0.9278 data: 0.0021 [11-26 08:33:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.475 (6.417) Lt: 5.710 (5.659) Accm: 3.54 (3.64) Acct: 5.58 (5.76) proj_loss: -0.6175 (-0.6115) time: 0.9278 data: 0.0016 [11-26 08:33:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 161/350] Total time: 0:26:01 (0.935 s / it) [11-26 08:33:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 161/350] Total time: 0:26:01 (0.935 s / it) [11-26 08:33:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 161/350] Total time: 0:26:01 (0.935 s / it) [11-26 08:33:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 161/350] Total time: 0:26:01 (0.935 s / it) [11-26 08:33:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 161/350] Total time: 0:26:01 (0.935 s / it) [11-26 08:33:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 161/350] Total time: 0:26:01 (0.935 s / it) [11-26 08:33:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 161/350] Total time: 0:26:01 (0.935 s / it) [11-26 08:33:36] (/home/user/VAR/train.py , line 276)=> [ep161] (training ) Lm: 6.421 (6.446), Lt: 5.666 (5.689), Acc m&t: 3.61 5.66, Remain: 3 days, 9:19:21, Finish: 2024-11-29 01:52 [11-26 08:33:36] (/home/user/VAR/train.py , line 276)=> [ep161] (training ) Lm: 6.421 (6.446), Lt: 5.666 (5.689), Acc m&t: 3.61 5.66, Remain: 3 days, 9:20:46, Finish: 2024-11-29 01:54 [11-26 08:33:36] (/home/user/VAR/train.py , line 276)=> [ep161] (training ) Lm: 6.421 (6.446), Lt: 5.666 (5.689), Acc m&t: 3.61 5.66, Remain: 3 days, 9:21:13, Finish: 2024-11-29 01:54 [11-26 08:33:36] (/home/user/VAR/train.py , line 276)=> [ep161] (training ) Lm: 6.421 (6.446), Lt: 5.666 (5.689), Acc m&t: 3.61 5.66, Remain: 3 days, 9:21:19, Finish: 2024-11-29 01:54 [11-26 08:33:36] (/home/user/VAR/train.py , line 276)=> [ep161] (training ) Lm: 6.421 (6.446), Lt: 5.666 (5.689), Acc m&t: 3.61 5.66, Remain: 3 days, 9:21:09, Finish: 2024-11-29 01:54 [11-26 08:33:36] (/home/user/VAR/train.py , line 276)=> [ep161] (training ) Lm: 6.421 (6.446), Lt: 5.666 (5.689), Acc m&t: 3.61 5.66, Remain: 3 days, 9:20:47, Finish: 2024-11-29 01:54 [11-26 08:33:36] (/home/user/VAR/train.py , line 276)=> [ep161] (training ) Lm: 6.421 (6.446), Lt: 5.666 (5.689), Acc m&t: 3.61 5.66, Remain: 3 days, 9:20:47, Finish: 2024-11-29 01:54 [11-26 08:33:36] (/home/user/VAR/train.py , line 276)=> [ep161] (training ) Lm: 6.421 (6.446), Lt: 5.666 (5.689), Acc m&t: 3.61 5.66, Remain: 3 days, 9:20:46, Finish: 2024-11-29 01:54 [11-26 08:33:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 0/1669] eta: 0:24:21 tlr: 0.00014 tnm: 0.26 Lm: 6.418 (6.418) Lt: 5.640 (5.640) Accm: 3.28 (3.28) Acct: 5.44 (5.44) proj_loss: -0.6166 (-0.6166) time: 0.8756 data: 0.0004 [11-26 08:33:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 0/1669] eta: 0:24:21 tlr: 0.00014 tnm: 0.26 Lm: 6.357 (6.357) Lt: 5.620 (5.620) Accm: 3.60 (3.60) Acct: 5.17 (5.17) proj_loss: -0.6150 (-0.6150) time: 0.8757 data: 0.0003 [11-26 08:33:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 0/1669] eta: 0:24:25 tlr: 0.00014 tnm: 0.26 Lm: 6.500 (6.500) Lt: 5.799 (5.799) Accm: 3.21 (3.21) Acct: 5.06 (5.06) proj_loss: -0.6220 (-0.6220) time: 0.8780 data: 0.0003 [11-26 08:33:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 0/1669] eta: 0:24:06 tlr: 0.00014 tnm: 0.26 Lm: 6.243 (6.243) Lt: 5.451 (5.451) Accm: 3.82 (3.82) Acct: 6.16 (6.16) proj_loss: -0.6443 (-0.6443) time: 0.8669 data: 0.0003 [11-26 08:33:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 0/1669] eta: 0:28:01 tlr: 0.00014 tnm: 0.26 Lm: 6.197 (6.197) Lt: 5.449 (5.449) Accm: 4.02 (4.02) Acct: 6.06 (6.06) proj_loss: -0.6306 (-0.6306) time: 1.0076 data: 0.0004 [11-26 08:33:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 0/1669] eta: 0:28:02 tlr: 0.00014 tnm: 0.26 Lm: 6.624 (6.624) Lt: 5.902 (5.902) Accm: 3.22 (3.22) Acct: 5.03 (5.03) proj_loss: -0.6259 (-0.6259) time: 1.0080 data: 0.0004 [11-26 08:33:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 0/1669] eta: 0:24:22 tlr: 0.00014 tnm: 0.26 Lm: 6.764 (6.764) Lt: 6.092 (6.092) Accm: 2.70 (2.70) Acct: 4.34 (4.34) proj_loss: -0.5990 (-0.5990) time: 0.8762 data: 0.0004 [11-26 08:33:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 0/1669] eta: 0:24:21 tlr: 0.00014 tnm: 0.26 Lm: 6.247 (6.247) Lt: 5.523 (5.523) Accm: 4.37 (4.37) Acct: 6.71 (6.71) proj_loss: -0.6692 (-0.6692) time: 0.8757 data: 0.0004 [11-26 08:40:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 417/1669] eta: 0:19:18 tlr: 0.00014 tnm: 0.26 Lm: 6.227 (6.227) Lt: 5.532 (5.532) Accm: 4.17 (4.17) Acct: 6.28 (6.28) proj_loss: -0.6477 (-0.6477) time: 0.9251 data: 0.0003 [11-26 08:40:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 417/1669] eta: 0:19:19 tlr: 0.00014 tnm: 0.26 Lm: 6.535 (6.535) Lt: 5.796 (5.796) Accm: 3.33 (3.33) Acct: 5.18 (5.18) proj_loss: -0.6210 (-0.6210) time: 0.9251 data: 0.0003 [11-26 08:40:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 417/1669] eta: 0:19:19 tlr: 0.00014 tnm: 0.26 Lm: 6.510 (6.510) Lt: 5.816 (5.816) Accm: 3.31 (3.31) Acct: 5.17 (5.17) proj_loss: -0.6301 (-0.6301) time: 0.9251 data: 0.0002 [11-26 08:40:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 417/1669] eta: 0:19:19 tlr: 0.00014 tnm: 0.26 Lm: 6.363 (6.363) Lt: 5.612 (5.612) Accm: 3.53 (3.53) Acct: 5.44 (5.44) proj_loss: -0.6088 (-0.6088) time: 0.9251 data: 0.0003 [11-26 08:40:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 417/1669] eta: 0:19:19 tlr: 0.00014 tnm: 0.26 Lm: 6.370 (6.370) Lt: 5.573 (5.573) Accm: 3.45 (3.45) Acct: 5.49 (5.49) proj_loss: -0.6077 (-0.6077) time: 0.9251 data: 0.0003 [11-26 08:40:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 417/1669] eta: 0:19:18 tlr: 0.00014 tnm: 0.26 Lm: 6.592 (6.592) Lt: 5.886 (5.886) Accm: 3.26 (3.26) Acct: 5.34 (5.34) proj_loss: -0.6204 (-0.6204) time: 0.9251 data: 0.0002 [11-26 08:40:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 417/1669] eta: 0:19:18 tlr: 0.00014 tnm: 0.26 Lm: 6.320 (6.320) Lt: 5.547 (5.547) Accm: 3.71 (3.71) Acct: 5.99 (5.99) proj_loss: -0.6379 (-0.6379) time: 0.9251 data: 0.0003 [11-26 08:40:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 417/1669] eta: 0:19:19 tlr: 0.00014 tnm: 0.26 Lm: 6.411 (6.411) Lt: 5.664 (5.664) Accm: 3.41 (3.41) Acct: 5.32 (5.32) proj_loss: -0.6218 (-0.6218) time: 0.9252 data: 0.0003 [11-26 08:46:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 834/1669] eta: 0:12:53 tlr: 0.00014 tnm: 0.26 Lm: 6.446 (6.395) Lt: 5.679 (5.609) Accm: 3.34 (3.41) Acct: 5.03 (5.34) proj_loss: -0.6134 (-0.6096) time: 0.9281 data: 0.0003 [11-26 08:46:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 834/1669] eta: 0:12:53 tlr: 0.00014 tnm: 0.26 Lm: 6.541 (6.537) Lt: 5.842 (5.811) Accm: 3.44 (3.41) Acct: 5.34 (5.23) proj_loss: -0.6259 (-0.6254) time: 0.9281 data: 0.0002 [11-26 08:46:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.26 Lm: 6.500 (6.503) Lt: 5.799 (5.781) Accm: 3.21 (3.25) Acct: 5.27 (5.38) proj_loss: -0.6220 (-0.6175) time: 0.9281 data: 0.0003 [11-26 08:46:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.26 Lm: 6.369 (6.366) Lt: 5.620 (5.643) Accm: 3.45 (3.49) Acct: 5.17 (5.34) proj_loss: -0.6150 (-0.6207) time: 0.9282 data: 0.0003 [11-26 08:46:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.26 Lm: 6.328 (6.322) Lt: 5.578 (5.558) Accm: 3.82 (3.78) Acct: 5.85 (5.95) proj_loss: -0.6316 (-0.6258) time: 0.9281 data: 0.0003 [11-26 08:46:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.26 Lm: 6.590 (6.591) Lt: 5.864 (5.879) Accm: 3.12 (3.21) Acct: 4.86 (5.18) proj_loss: -0.6355 (-0.6254) time: 0.9282 data: 0.0002 [11-26 08:46:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.26 Lm: 6.247 (6.252) Lt: 5.542 (5.536) Accm: 3.96 (4.05) Acct: 5.85 (6.12) proj_loss: -0.6692 (-0.6611) time: 0.9282 data: 0.0003 [11-26 08:46:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.26 Lm: 6.404 (6.369) Lt: 5.640 (5.621) Accm: 3.54 (3.61) Acct: 5.44 (5.48) proj_loss: -0.6166 (-0.6182) time: 0.9282 data: 0.0003 [11-26 08:52:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.27 Lm: 6.411 (6.425) Lt: 5.664 (5.679) Accm: 3.41 (3.48) Acct: 5.32 (5.34) proj_loss: -0.6218 (-0.6230) time: 0.9236 data: 0.0003 [11-26 08:52:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.27 Lm: 6.363 (6.352) Lt: 5.612 (5.632) Accm: 3.53 (3.57) Acct: 5.23 (5.33) proj_loss: -0.6180 (-0.6208) time: 0.9236 data: 0.0002 [11-26 08:52:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.27 Lm: 6.494 (6.465) Lt: 5.766 (5.717) Accm: 3.50 (3.52) Acct: 5.34 (5.46) proj_loss: -0.6210 (-0.6122) time: 0.9236 data: 0.0003 [11-26 08:52:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.27 Lm: 6.505 (6.506) Lt: 5.772 (5.765) Accm: 3.34 (3.30) Acct: 5.56 (5.45) proj_loss: -0.6198 (-0.6201) time: 0.9236 data: 0.0002 [11-26 08:52:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.27 Lm: 6.442 (6.406) Lt: 5.668 (5.621) Accm: 3.29 (3.37) Acct: 5.13 (5.31) proj_loss: -0.6191 (-0.6134) time: 0.9236 data: 0.0003 [11-26 08:52:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.27 Lm: 6.494 (6.491) Lt: 5.755 (5.732) Accm: 3.31 (3.34) Acct: 5.54 (5.52) proj_loss: -0.6115 (-0.6133) time: 0.9236 data: 0.0003 [11-26 08:52:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.27 Lm: 6.285 (6.296) Lt: 5.515 (5.524) Accm: 3.88 (3.92) Acct: 6.01 (6.16) proj_loss: -0.6222 (-0.6225) time: 0.9236 data: 0.0003 [11-26 08:52:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.27 Lm: 6.275 (6.360) Lt: 5.543 (5.665) Accm: 3.90 (3.74) Acct: 5.82 (5.71) proj_loss: -0.6707 (-0.6638) time: 0.9236 data: 0.0003 [11-26 08:59:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.247 (6.295) Lt: 5.542 (5.578) Accm: 3.96 (3.92) Acct: 5.85 (5.96) proj_loss: -0.6692 (-0.6567) time: 0.9250 data: 0.0022 [11-26 08:59:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 162/350] Total time: 0:25:46 (0.927 s / it) [11-26 08:59:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.438 (6.380) Lt: 5.658 (5.590) Accm: 3.34 (3.44) Acct: 5.23 (5.43) proj_loss: -0.6134 (-0.6109) time: 0.9250 data: 0.0017 [11-26 08:59:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.541 (6.480) Lt: 5.782 (5.730) Accm: 3.44 (3.44) Acct: 5.34 (5.36) proj_loss: -0.6162 (-0.6093) time: 0.9250 data: 0.0015 [11-26 08:59:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.357 (6.346) Lt: 5.604 (5.618) Accm: 3.60 (3.59) Acct: 5.30 (5.43) proj_loss: -0.6150 (-0.6187) time: 0.9250 data: 0.0016 [11-26 08:59:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.489 (6.461) Lt: 5.711 (5.711) Accm: 3.41 (3.46) Acct: 5.72 (5.56) proj_loss: -0.6220 (-0.6180) time: 0.9250 data: 0.0014 [11-26 08:59:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.419 (6.468) Lt: 5.680 (5.709) Accm: 3.57 (3.45) Acct: 6.27 (5.71) proj_loss: -0.6040 (-0.6154) time: 0.9250 data: 0.0017 [11-26 08:59:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.328 (6.359) Lt: 5.578 (5.575) Accm: 3.82 (3.73) Acct: 5.85 (6.02) proj_loss: -0.6129 (-0.6188) time: 0.9251 data: 0.0017 [11-26 08:59:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.418 (6.428) Lt: 5.640 (5.658) Accm: 3.54 (3.54) Acct: 5.44 (5.54) proj_loss: -0.6166 (-0.6172) time: 0.9250 data: 0.0022 [11-26 08:59:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 162/350] Total time: 0:25:46 (0.927 s / it) [11-26 08:59:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 162/350] Total time: 0:25:46 (0.927 s / it) [11-26 08:59:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 162/350] Total time: 0:25:46 (0.927 s / it) [11-26 08:59:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 162/350] Total time: 0:25:46 (0.927 s / it) [11-26 08:59:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 162/350] Total time: 0:25:46 (0.927 s / it) [11-26 08:59:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 162/350] Total time: 0:25:46 (0.927 s / it) [11-26 08:59:23] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 162/350] Total time: 0:25:46 (0.927 s / it) [11-26 08:59:23] (/home/user/VAR/train.py , line 276)=> [ep162] (training ) Lm: 6.421 (6.424), Lt: 5.666 (5.668), Acc m&t: 3.61 5.66, Remain: 3 days, 8:47:44, Finish: 2024-11-29 01:47 [11-26 08:59:23] (/home/user/VAR/train.py , line 276)=> [ep162] (training ) Lm: 6.421 (6.424), Lt: 5.666 (5.668), Acc m&t: 3.61 5.66, Remain: 3 days, 8:48:11, Finish: 2024-11-29 01:47 [11-26 08:59:23] (/home/user/VAR/train.py , line 276)=> [ep162] (training ) Lm: 6.421 (6.424), Lt: 5.666 (5.668), Acc m&t: 3.61 5.66, Remain: 3 days, 8:47:49, Finish: 2024-11-29 01:47 [11-26 08:59:23] (/home/user/VAR/train.py , line 276)=> [ep162] (training ) Lm: 6.421 (6.424), Lt: 5.666 (5.668), Acc m&t: 3.61 5.66, Remain: 3 days, 8:48:48, Finish: 2024-11-29 01:48 [11-26 08:59:23] (/home/user/VAR/train.py , line 276)=> [ep162] (training ) Lm: 6.421 (6.424), Lt: 5.666 (5.668), Acc m&t: 3.61 5.66, Remain: 3 days, 8:49:12, Finish: 2024-11-29 01:48 [11-26 08:59:23] (/home/user/VAR/train.py , line 276)=> [ep162] (training ) Lm: 6.421 (6.424), Lt: 5.666 (5.668), Acc m&t: 3.61 5.66, Remain: 3 days, 8:49:45, Finish: 2024-11-29 01:49 [11-26 08:59:23] (/home/user/VAR/train.py , line 276)=> [ep162] (training ) Lm: 6.421 (6.424), Lt: 5.666 (5.668), Acc m&t: 3.61 5.66, Remain: 3 days, 8:48:51, Finish: 2024-11-29 01:48 [11-26 08:59:23] (/home/user/VAR/train.py , line 276)=> [ep162] (training ) Lm: 6.421 (6.424), Lt: 5.666 (5.668), Acc m&t: 3.61 5.66, Remain: 3 days, 8:47:41, Finish: 2024-11-29 01:47 [11-26 08:59:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 0/1669] eta: 0:24:38 tlr: 0.00014 tnm: 0.27 Lm: 6.321 (6.321) Lt: 5.536 (5.536) Accm: 3.99 (3.99) Acct: 6.47 (6.47) proj_loss: -0.6242 (-0.6242) time: 0.8861 data: 0.0004 [11-26 08:59:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 0/1669] eta: 0:24:38 tlr: 0.00014 tnm: 0.27 Lm: 6.340 (6.340) Lt: 5.587 (5.587) Accm: 4.01 (4.01) Acct: 6.44 (6.44) proj_loss: -0.6325 (-0.6325) time: 0.8861 data: 0.0004 [11-26 08:59:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 0/1669] eta: 0:24:32 tlr: 0.00014 tnm: 0.27 Lm: 6.367 (6.367) Lt: 5.622 (5.622) Accm: 3.80 (3.80) Acct: 5.85 (5.85) proj_loss: -0.6769 (-0.6769) time: 0.8822 data: 0.0003 [11-26 08:59:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 0/1669] eta: 0:24:39 tlr: 0.00014 tnm: 0.27 Lm: 6.250 (6.250) Lt: 5.488 (5.488) Accm: 4.43 (4.43) Acct: 6.85 (6.85) proj_loss: -0.6193 (-0.6193) time: 0.8865 data: 0.0003 [11-26 08:59:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 0/1669] eta: 0:24:38 tlr: 0.00014 tnm: 0.27 Lm: 6.540 (6.540) Lt: 5.779 (5.779) Accm: 3.22 (3.22) Acct: 4.86 (4.86) proj_loss: -0.6282 (-0.6282) time: 0.8860 data: 0.0003 [11-26 08:59:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 0/1669] eta: 0:24:39 tlr: 0.00014 tnm: 0.27 Lm: 6.440 (6.440) Lt: 5.710 (5.710) Accm: 3.06 (3.06) Acct: 4.96 (4.96) proj_loss: -0.6002 (-0.6002) time: 0.8865 data: 0.0003 [11-26 08:59:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 0/1669] eta: 0:24:39 tlr: 0.00014 tnm: 0.27 Lm: 6.431 (6.431) Lt: 5.684 (5.684) Accm: 3.26 (3.26) Acct: 5.17 (5.17) proj_loss: -0.6324 (-0.6324) time: 0.8867 data: 0.0004 [11-26 08:59:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 0/1669] eta: 0:24:38 tlr: 0.00014 tnm: 0.27 Lm: 6.565 (6.565) Lt: 5.867 (5.867) Accm: 3.18 (3.18) Acct: 4.96 (4.96) proj_loss: -0.6118 (-0.6118) time: 0.8858 data: 0.0003 ======================================================= RESTART [11-26 09:50:26] ======================================================= ======================================================= RESTART [11-26 09:50:26] ======================================================= ======================================================= RESTART [11-26 09:50:26] ======================================================= ======================================================= RESTART [11-26 09:50:26] ======================================================= ======================================================= RESTART [11-26 09:50:26] ======================================================= ======================================================= RESTART [11-26 09:50:26] ======================================================= ======================================================= RESTART [11-26 09:50:26] ======================================================= ======================================================= RESTART [11-26 09:50:26] ======================================================= [11-26 09:50:26] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 09:50:26] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 09:50:26] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 09:52:08] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 09:52:08] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-26 09:52:08] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 09:52:11] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 09:52:11] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> [11-26 09:52:11] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 09:52:11] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> [11-26 09:52:11] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 09:52:11] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 09:52:11] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 09:52:11] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 09:50:26] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 09:50:26] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 09:50:26] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 09:52:08] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 09:52:08] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-26 09:52:08] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 09:52:11] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 09:52:11] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> [11-26 09:52:11] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 09:52:11] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> [11-26 09:52:11] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 09:52:11] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 09:52:11] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 09:52:11] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 09:50:26] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 09:50:26] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 09:50:26] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 09:52:08] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 09:52:08] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add branch : main } [11-26 09:52:08] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 09:52:11] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 09:52:11] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> [11-26 09:52:11] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 09:52:11] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> [11-26 09:52:11] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 09:52:11] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 09:52:11] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 09:52:11] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 09:50:26] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 09:50:26] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 09:50:26] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 09:52:08] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 09:52:08] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add branch : main } [11-26 09:52:08] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 09:52:11] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 09:52:11] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> [11-26 09:52:11] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 09:52:11] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> [11-26 09:52:11] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 09:52:11] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 09:52:11] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 09:52:11] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 09:50:26] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 09:50:26] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 09:50:26] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 09:52:08] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 09:52:08] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-26 09:52:08] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 09:52:11] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 09:52:11] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> [11-26 09:52:11] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 09:52:11] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> [11-26 09:52:11] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 09:52:11] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 09:52:11] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 09:52:11] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 09:50:26] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 09:50:26] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 09:50:26] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 09:52:08] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 09:52:08] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main } [11-26 09:52:08] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 09:52:11] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 09:52:11] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> [11-26 09:52:11] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 09:52:11] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> [11-26 09:52:11] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 09:52:11] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 09:52:11] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 09:52:11] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 09:50:26] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 09:50:26] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 09:50:26] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 09:52:08] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 09:52:08] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-26 09:52:08] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 09:52:11] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 09:52:11] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> [11-26 09:52:11] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 09:52:11] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 09:52:11] (e/user/VAR/utils/data.py, line 51)=> [11-26 09:52:11] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 09:52:11] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 09:52:11] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 09:52:11] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 09:50:26] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 09:50:26] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 09:50:26] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 09:52:08] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 09:52:08] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add } [11-26 09:52:08] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 09:52:14] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 09:52:14] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 09:52:14] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 09:52:14] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 09:52:14] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 09:52:14] (e/user/VAR/utils/data.py, line 51)=> [11-26 09:52:14] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 09:52:14] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 09:52:14] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 09:52:14] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 09:52:14] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 09:52:14] (e/user/VAR/utils/data.py, line 51)=> [11-26 09:52:14] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 09:52:14] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 09:52:14] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 09:52:14] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ... [dataloader multi processing](*) finished! (48.40s) [dataloader multi processing](*) finished! (49.41s) [dataloader multi processing](*) finished! (49.48s) [dataloader multi processing](*) finished! (49.79s) [dataloader multi processing](*) finished! (49.85s) [dataloader multi processing](*) finished! (48.71s) [11-26 09:53:00] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 09:53:03] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 09:53:03] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 09:53:04] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [dataloader multi processing](*) finished! (54.26s) [11-26 09:52:59] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 09:53:04] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 09:53:04] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 09:53:05] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 09:53:00] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 09:53:05] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 09:53:05] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 09:53:06] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 09:53:01] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 09:53:05] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 09:53:05] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 09:53:07] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [dataloader multi processing](*) finished! (55.88s) [11-26 09:53:01] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 09:53:06] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 09:53:06] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 09:53:07] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 09:53:03] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 09:53:07] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 09:53:07] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 09:53:09] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 09:53:05] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 09:53:10] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 09:53:10] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 09:53:11] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 09:53:07] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 09:53:12] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 09:53:12] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 09:53:13] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 09:53:08] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 09:53:38] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 09:53:38] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 09:53:38] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 09:53:38] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 09:53:38] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank0] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 09:53:16] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 09:53:38] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 09:53:38] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 09:53:38] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 09:53:38] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 09:53:38] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank8] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 09:53:14] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 09:53:38] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 09:53:38] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 09:53:38] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 09:53:38] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 09:53:38] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank16] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 09:53:15] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 09:53:38] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 09:53:38] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 09:53:38] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 09:53:38] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 09:53:38] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank24] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 09:53:09] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 09:53:38] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 09:53:38] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 09:53:38] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 09:53:38] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 09:53:38] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank32] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 09:53:12] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 09:53:38] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 09:53:38] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 09:53:38] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 09:53:38] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 09:53:39] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank40] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 09:53:10] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 09:53:38] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 09:53:38] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 09:53:38] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 09:53:38] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 09:53:39] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank48] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 09:53:10] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 09:53:38] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 09:53:38] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 09:53:38] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 09:53:38] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 09:53:39] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank56] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 09:53:39] (/VAR/utils/lr_control.py, line 105)=> [11-26 09:53:39] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 09:53:41] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 09:53:41] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 09:53:41] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 09:53:41] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 09:59:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 6 days, 19:43:03 tlr: 0.00014 tnm: 0.26 Lm: 6.569 (6.569) Lt: 5.778 (5.778) Accm: 3.06 (3.06) Acct: 5.03 (5.03) proj_loss: -0.6143 (-0.6143) time: 353.1355 data: 0.0007 [11-26 09:53:39] (/VAR/utils/lr_control.py, line 105)=> [11-26 09:53:39] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 09:53:41] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 09:53:41] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 09:53:42] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 09:53:42] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 09:59:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 6 days, 19:47:19 tlr: 0.00014 tnm: 0.26 Lm: 6.412 (6.412) Lt: 5.654 (5.654) Accm: 3.61 (3.61) Acct: 5.72 (5.72) proj_loss: -0.6296 (-0.6296) time: 353.2894 data: 0.0005 [11-26 09:53:39] (/VAR/utils/lr_control.py, line 105)=> [11-26 09:53:39] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 09:53:41] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 09:53:41] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 09:53:41] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 09:53:41] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 09:59:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 6 days, 19:40:54 tlr: 0.00014 tnm: 0.26 Lm: 6.248 (6.248) Lt: 5.494 (5.494) Accm: 3.95 (3.95) Acct: 6.03 (6.03) proj_loss: -0.6433 (-0.6433) time: 353.0582 data: 0.0007 [11-26 09:53:39] (/VAR/utils/lr_control.py, line 105)=> [11-26 09:53:39] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 09:53:42] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 09:53:42] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 09:53:42] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 09:53:42] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 09:59:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 6 days, 19:16:48 tlr: 0.00014 tnm: 0.26 Lm: 6.482 (6.482) Lt: 5.700 (5.700) Accm: 3.60 (3.60) Acct: 5.72 (5.72) proj_loss: -0.6099 (-0.6099) time: 352.1921 data: 0.0005 [11-26 09:53:39] (/VAR/utils/lr_control.py, line 105)=> [11-26 09:53:39] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 09:53:41] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 09:53:41] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 09:53:41] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 09:53:41] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 09:59:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 6 days, 19:50:33 tlr: 0.00014 tnm: 0.26 Lm: 6.607 (6.607) Lt: 5.888 (5.888) Accm: 3.04 (3.04) Acct: 4.75 (4.75) proj_loss: -0.6207 (-0.6207) time: 353.4056 data: 0.0006 [11-26 09:53:39] (/VAR/utils/lr_control.py, line 105)=> [11-26 09:53:39] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 09:53:41] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 09:53:41] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 09:53:41] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 09:53:41] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 09:59:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 6 days, 19:30:58 tlr: 0.00014 tnm: 0.26 Lm: 6.449 (6.449) Lt: 5.739 (5.739) Accm: 3.53 (3.53) Acct: 5.65 (5.65) proj_loss: -0.6087 (-0.6087) time: 352.7016 data: 0.0005 [11-26 09:53:39] (/VAR/utils/lr_control.py, line 105)=> [11-26 09:53:39] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 09:53:42] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 09:53:42] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 09:53:42] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 09:53:42] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 09:59:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 6 days, 19:56:42 tlr: 0.00014 tnm: 0.26 Lm: 6.504 (6.504) Lt: 5.755 (5.755) Accm: 3.09 (3.09) Acct: 4.55 (4.55) proj_loss: -0.6173 (-0.6173) time: 353.6261 data: 0.0007 [11-26 09:53:39] (/VAR/utils/lr_control.py, line 105)=> [11-26 09:53:39] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 09:53:42] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 09:53:42] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 09:53:42] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 09:53:42] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 09:59:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 6 days, 19:48:22 tlr: 0.00014 tnm: 0.26 Lm: 6.604 (6.604) Lt: 5.838 (5.838) Accm: 3.22 (3.22) Acct: 5.03 (5.03) proj_loss: -0.6359 (-0.6359) time: 353.3266 data: 0.0006 [11-26 10:14:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 1:02:24 tlr: 0.00014 tnm: 0.26 Lm: 6.321 (6.321) Lt: 5.540 (5.540) Accm: 3.81 (3.81) Acct: 6.20 (6.20) proj_loss: -0.6310 (-0.6310) time: 0.9226 data: 0.0003 [11-26 10:14:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 1:02:22 tlr: 0.00014 tnm: 0.26 Lm: 6.535 (6.535) Lt: 5.858 (5.858) Accm: 3.31 (3.31) Acct: 4.99 (4.99) proj_loss: -0.6152 (-0.6152) time: 0.9226 data: 0.0003 [11-26 10:14:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 1:02:25 tlr: 0.00014 tnm: 0.26 Lm: 6.385 (6.385) Lt: 5.592 (5.592) Accm: 3.50 (3.50) Acct: 5.44 (5.44) proj_loss: -0.5966 (-0.5966) time: 0.9226 data: 0.0003 [11-26 10:14:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 1:02:24 tlr: 0.00014 tnm: 0.26 Lm: 6.434 (6.434) Lt: 5.648 (5.648) Accm: 3.79 (3.79) Acct: 5.94 (5.94) proj_loss: -0.6039 (-0.6039) time: 0.9226 data: 0.0003 [11-26 10:14:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 1:02:24 tlr: 0.00014 tnm: 0.26 Lm: 6.514 (6.514) Lt: 5.723 (5.723) Accm: 3.53 (3.53) Acct: 5.82 (5.82) proj_loss: -0.6268 (-0.6268) time: 0.9226 data: 0.0003 [11-26 10:14:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 1:02:24 tlr: 0.00014 tnm: 0.26 Lm: 6.344 (6.344) Lt: 5.573 (5.573) Accm: 3.78 (3.78) Acct: 5.99 (5.99) proj_loss: -0.6231 (-0.6231) time: 0.9226 data: 0.0003 [11-26 10:14:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 1:02:21 tlr: 0.00014 tnm: 0.26 Lm: 6.471 (6.471) Lt: 5.663 (5.663) Accm: 3.52 (3.52) Acct: 5.72 (5.72) proj_loss: -0.5851 (-0.5851) time: 0.9226 data: 0.0003 [11-26 10:14:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 1:02:25 tlr: 0.00014 tnm: 0.26 Lm: 6.593 (6.593) Lt: 5.876 (5.876) Accm: 3.13 (3.13) Acct: 4.77 (4.77) proj_loss: -0.6237 (-0.6237) time: 0.9226 data: 0.0003 [11-26 10:21:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:27:14 tlr: 0.00014 tnm: 0.26 Lm: 6.579 (6.528) Lt: 5.864 (5.780) Accm: 3.22 (3.24) Acct: 4.79 (5.04) proj_loss: -0.6207 (-0.6169) time: 0.9220 data: 0.0003 [11-26 10:21:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:27:13 tlr: 0.00014 tnm: 0.26 Lm: 6.460 (6.391) Lt: 5.626 (5.594) Accm: 3.60 (3.66) Acct: 5.72 (5.81) proj_loss: -0.6099 (-0.5972) time: 0.9220 data: 0.0002 [11-26 10:21:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:27:14 tlr: 0.00014 tnm: 0.26 Lm: 6.596 (6.555) Lt: 5.838 (5.851) Accm: 3.09 (3.16) Acct: 4.48 (4.82) proj_loss: -0.6216 (-0.6240) time: 0.9220 data: 0.0003 [11-26 10:21:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:27:14 tlr: 0.00014 tnm: 0.26 Lm: 6.394 (6.425) Lt: 5.585 (5.660) Accm: 3.67 (3.38) Acct: 6.03 (5.48) proj_loss: -0.6188 (-0.6229) time: 0.9220 data: 0.0003 [11-26 10:21:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:27:14 tlr: 0.00014 tnm: 0.26 Lm: 6.516 (6.461) Lt: 5.736 (5.677) Accm: 3.47 (3.68) Acct: 5.51 (5.80) proj_loss: -0.6143 (-0.6094) time: 0.9220 data: 0.0003 [11-26 10:21:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:27:15 tlr: 0.00014 tnm: 0.26 Lm: 6.439 (6.403) Lt: 5.677 (5.620) Accm: 3.29 (3.43) Acct: 5.37 (5.42) proj_loss: -0.5960 (-0.5964) time: 0.9220 data: 0.0002 [11-26 10:21:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:27:14 tlr: 0.00014 tnm: 0.26 Lm: 6.481 (6.503) Lt: 5.772 (5.739) Accm: 3.26 (3.44) Acct: 5.13 (5.59) proj_loss: -0.6310 (-0.6282) time: 0.9220 data: 0.0003 [11-26 10:21:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:27:14 tlr: 0.00014 tnm: 0.26 Lm: 6.412 (6.460) Lt: 5.654 (5.693) Accm: 3.61 (3.40) Acct: 5.72 (5.41) proj_loss: -0.6166 (-0.6136) time: 0.9220 data: 0.0003 [11-26 10:27:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:11:14 tlr: 0.00014 tnm: 0.26 Lm: 6.508 (6.496) Lt: 5.794 (5.757) Accm: 3.42 (3.36) Acct: 5.23 (5.24) proj_loss: -0.6195 (-0.6157) time: 0.9201 data: 0.0002 [11-26 10:27:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:11:14 tlr: 0.00014 tnm: 0.26 Lm: 6.488 (6.467) Lt: 5.727 (5.699) Accm: 3.34 (3.53) Acct: 5.18 (5.53) proj_loss: -0.6120 (-0.6098) time: 0.9200 data: 0.0002 [11-26 10:27:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:11:14 tlr: 0.00014 tnm: 0.26 Lm: 6.453 (6.480) Lt: 5.740 (5.732) Accm: 3.47 (3.50) Acct: 5.42 (5.62) proj_loss: -0.6335 (-0.6310) time: 0.9200 data: 0.0003 [11-26 10:27:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:11:14 tlr: 0.00014 tnm: 0.26 Lm: 6.415 (6.424) Lt: 5.640 (5.644) Accm: 3.63 (3.71) Acct: 5.60 (5.77) proj_loss: -0.6154 (-0.6112) time: 0.9200 data: 0.0002 [11-26 10:27:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:11:14 tlr: 0.00014 tnm: 0.26 Lm: 6.448 (6.417) Lt: 5.689 (5.640) Accm: 3.45 (3.47) Acct: 5.58 (5.51) proj_loss: -0.6066 (-0.6066) time: 0.9200 data: 0.0002 [11-26 10:27:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:11:14 tlr: 0.00014 tnm: 0.26 Lm: 6.415 (6.428) Lt: 5.592 (5.645) Accm: 3.56 (3.40) Acct: 5.65 (5.42) proj_loss: -0.6138 (-0.6194) time: 0.9201 data: 0.0002 [11-26 10:27:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:11:13 tlr: 0.00014 tnm: 0.26 Lm: 6.560 (6.547) Lt: 5.833 (5.846) Accm: 3.26 (3.22) Acct: 4.80 (4.90) proj_loss: -0.6316 (-0.6315) time: 0.9201 data: 0.0002 [11-26 10:27:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:11:13 tlr: 0.00014 tnm: 0.26 Lm: 6.391 (6.374) Lt: 5.579 (5.578) Accm: 3.59 (3.64) Acct: 5.72 (5.71) proj_loss: -0.6157 (-0.6046) time: 0.9201 data: 0.0003 [11-26 10:33:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:01 tlr: 0.00014 tnm: 0.26 Lm: 6.322 (6.359) Lt: 5.531 (5.564) Accm: 3.60 (3.76) Acct: 5.72 (5.87) proj_loss: -0.6179 (-0.6072) time: 0.9216 data: 0.0019 [11-26 10:33:55] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:40:02 (1.439 s / it) [11-26 10:33:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:01 tlr: 0.00014 tnm: 0.26 Lm: 6.424 (6.464) Lt: 5.709 (5.711) Accm: 3.42 (3.48) Acct: 5.72 (5.64) proj_loss: -0.6310 (-0.6305) time: 0.9216 data: 0.0018 [11-26 10:33:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:01 tlr: 0.00014 tnm: 0.26 Lm: 6.441 (6.421) Lt: 5.677 (5.646) Accm: 3.58 (3.49) Acct: 5.75 (5.56) proj_loss: -0.5982 (-0.6049) time: 0.9216 data: 0.0015 [11-26 10:33:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:01 tlr: 0.00014 tnm: 0.26 Lm: 6.394 (6.393) Lt: 5.585 (5.623) Accm: 3.67 (3.58) Acct: 6.03 (5.67) proj_loss: -0.6188 (-0.6306) time: 0.9216 data: 0.0015 [11-26 10:33:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:01 tlr: 0.00014 tnm: 0.26 Lm: 6.538 (6.545) Lt: 5.838 (5.852) Accm: 3.16 (3.21) Acct: 4.68 (4.86) proj_loss: -0.6216 (-0.6238) time: 0.9216 data: 0.0015 [11-26 10:33:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:01 tlr: 0.00014 tnm: 0.26 Lm: 6.459 (6.466) Lt: 5.654 (5.690) Accm: 3.29 (3.48) Acct: 5.30 (5.48) proj_loss: -0.6207 (-0.6125) time: 0.9216 data: 0.0018 [11-26 10:33:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:01 tlr: 0.00014 tnm: 0.26 Lm: 6.391 (6.418) Lt: 5.592 (5.633) Accm: 3.47 (3.65) Acct: 5.51 (5.70) proj_loss: -0.6166 (-0.6133) time: 0.9216 data: 0.0017 [11-26 10:33:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:01 tlr: 0.00014 tnm: 0.26 Lm: 6.548 (6.506) Lt: 5.864 (5.778) Accm: 3.22 (3.28) Acct: 4.75 (5.02) proj_loss: -0.6166 (-0.6142) time: 0.9216 data: 0.0016 [11-26 10:33:55] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:40:03 (1.440 s / it) [11-26 10:33:55] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:40:03 (1.440 s / it) [11-26 10:33:55] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:40:03 (1.440 s / it) [11-26 10:33:55] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:40:02 (1.440 s / it) [11-26 10:33:55] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:40:03 (1.440 s / it) [11-26 10:33:55] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:40:03 (1.440 s / it) [11-26 10:33:55] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:40:03 (1.440 s / it) [11-26 10:33:55] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.433 (6.433), Lt: 5.677 (5.677), Acc m&t: 3.56 5.58, Remain: 3 days, 9:32:31, Finish: 2024-11-29 04:06 [11-26 10:33:55] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.433 (6.433), Lt: 5.677 (5.677), Acc m&t: 3.56 5.58, Remain: 3 days, 9:32:53, Finish: 2024-11-29 04:06 [11-26 10:33:55] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.433 (6.433), Lt: 5.677 (5.677), Acc m&t: 3.56 5.58, Remain: 3 days, 9:33:22, Finish: 2024-11-29 04:07 [11-26 10:33:55] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.433 (6.433), Lt: 5.677 (5.677), Acc m&t: 3.56 5.58, Remain: 3 days, 9:33:45, Finish: 2024-11-29 04:07 [11-26 10:33:55] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.433 (6.433), Lt: 5.677 (5.677), Acc m&t: 3.56 5.58, Remain: 3 days, 9:33:49, Finish: 2024-11-29 04:07 [11-26 10:33:55] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.433 (6.433), Lt: 5.677 (5.677), Acc m&t: 3.56 5.58, Remain: 3 days, 9:33:06, Finish: 2024-11-29 04:07 [11-26 10:33:55] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.433 (6.433), Lt: 5.677 (5.677), Acc m&t: 3.56 5.58, Remain: 3 days, 9:33:38, Finish: 2024-11-29 04:07 [11-26 10:33:55] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.433 (6.433), Lt: 5.677 (5.677), Acc m&t: 3.56 5.58, Remain: 3 days, 9:31:49, Finish: 2024-11-29 04:05 [11-26 10:33:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:37 tlr: 0.00014 tnm: 0.26 Lm: 6.580 (6.580) Lt: 5.753 (5.753) Accm: 3.06 (3.06) Acct: 4.61 (4.61) proj_loss: -0.6136 (-0.6136) time: 0.9211 data: 0.0003 [11-26 10:33:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:37 tlr: 0.00014 tnm: 0.26 Lm: 6.471 (6.471) Lt: 5.699 (5.699) Accm: 3.06 (3.06) Acct: 5.06 (5.06) proj_loss: -0.5935 (-0.5935) time: 0.9209 data: 0.0003 [11-26 10:33:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:37 tlr: 0.00014 tnm: 0.26 Lm: 6.383 (6.383) Lt: 5.701 (5.701) Accm: 3.73 (3.73) Acct: 5.48 (5.48) proj_loss: -0.6136 (-0.6136) time: 0.9211 data: 0.0004 [11-26 10:33:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:36 tlr: 0.00014 tnm: 0.26 Lm: 6.374 (6.374) Lt: 5.568 (5.568) Accm: 4.41 (4.41) Acct: 7.20 (7.20) proj_loss: -0.5863 (-0.5863) time: 0.9206 data: 0.0003 [11-26 10:33:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:36 tlr: 0.00014 tnm: 0.26 Lm: 6.416 (6.416) Lt: 5.628 (5.628) Accm: 3.31 (3.31) Acct: 4.92 (4.92) proj_loss: -0.6109 (-0.6109) time: 0.9207 data: 0.0004 [11-26 10:33:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:36 tlr: 0.00014 tnm: 0.26 Lm: 6.203 (6.203) Lt: 5.401 (5.401) Accm: 4.14 (4.14) Acct: 6.44 (6.44) proj_loss: -0.6091 (-0.6091) time: 0.9208 data: 0.0004 [11-26 10:33:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:26:46 tlr: 0.00014 tnm: 0.26 Lm: 6.322 (6.322) Lt: 5.540 (5.540) Accm: 4.27 (4.27) Acct: 6.61 (6.61) proj_loss: -0.6083 (-0.6083) time: 0.9628 data: 0.0004 [11-26 10:33:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:37 tlr: 0.00014 tnm: 0.26 Lm: 6.671 (6.671) Lt: 5.912 (5.912) Accm: 2.90 (2.90) Acct: 4.75 (4.75) proj_loss: -0.6234 (-0.6234) time: 0.9213 data: 0.0004 [11-26 10:40:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:32 tlr: 0.00014 tnm: 0.27 Lm: 6.618 (6.618) Lt: 5.892 (5.892) Accm: 2.93 (2.93) Acct: 4.56 (4.56) proj_loss: -0.6293 (-0.6293) time: 0.9238 data: 0.0003 [11-26 10:40:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:32 tlr: 0.00014 tnm: 0.27 Lm: 6.467 (6.467) Lt: 5.701 (5.701) Accm: 3.17 (3.17) Acct: 4.84 (4.84) proj_loss: -0.6109 (-0.6109) time: 0.9238 data: 0.0002 [11-26 10:40:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:32 tlr: 0.00014 tnm: 0.27 Lm: 6.403 (6.403) Lt: 5.634 (5.634) Accm: 3.45 (3.45) Acct: 5.58 (5.58) proj_loss: -0.6123 (-0.6123) time: 0.9238 data: 0.0003 [11-26 10:40:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:32 tlr: 0.00014 tnm: 0.27 Lm: 6.365 (6.365) Lt: 5.640 (5.640) Accm: 3.64 (3.64) Acct: 5.48 (5.48) proj_loss: -0.6311 (-0.6311) time: 0.9238 data: 0.0003 [11-26 10:40:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:32 tlr: 0.00014 tnm: 0.27 Lm: 6.335 (6.335) Lt: 5.574 (5.574) Accm: 3.77 (3.77) Acct: 5.77 (5.77) proj_loss: -0.6096 (-0.6096) time: 0.9238 data: 0.0003 [11-26 10:40:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:32 tlr: 0.00014 tnm: 0.27 Lm: 6.413 (6.413) Lt: 5.646 (5.646) Accm: 4.04 (4.04) Acct: 6.32 (6.32) proj_loss: -0.6094 (-0.6094) time: 0.9238 data: 0.0003 [11-26 10:40:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:32 tlr: 0.00014 tnm: 0.27 Lm: 6.226 (6.226) Lt: 5.423 (5.423) Accm: 4.39 (4.39) Acct: 7.04 (7.04) proj_loss: -0.6110 (-0.6110) time: 0.9238 data: 0.0003 [11-26 10:40:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:32 tlr: 0.00014 tnm: 0.27 Lm: 6.505 (6.505) Lt: 5.749 (5.749) Accm: 3.14 (3.14) Acct: 4.79 (4.79) proj_loss: -0.6145 (-0.6145) time: 0.9238 data: 0.0002 [11-26 10:46:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:12:56 tlr: 0.00014 tnm: 0.26 Lm: 6.429 (6.436) Lt: 5.744 (5.682) Accm: 3.22 (3.33) Acct: 4.96 (5.05) proj_loss: -0.6136 (-0.6128) time: 0.9258 data: 0.0003 [11-26 10:46:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:12:56 tlr: 0.00014 tnm: 0.26 Lm: 6.452 (6.444) Lt: 5.723 (5.672) Accm: 3.66 (3.80) Acct: 5.44 (5.91) proj_loss: -0.5961 (-0.6050) time: 0.9258 data: 0.0003 [11-26 10:46:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:12:56 tlr: 0.00014 tnm: 0.26 Lm: 6.517 (6.487) Lt: 5.774 (5.749) Accm: 3.31 (3.25) Acct: 4.92 (5.00) proj_loss: -0.6110 (-0.6169) time: 0.9258 data: 0.0002 [11-26 10:46:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:12:56 tlr: 0.00014 tnm: 0.26 Lm: 6.322 (6.282) Lt: 5.540 (5.497) Accm: 4.27 (4.05) Acct: 6.61 (6.44) proj_loss: -0.6138 (-0.6144) time: 0.9258 data: 0.0003 [11-26 10:46:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:12:56 tlr: 0.00014 tnm: 0.26 Lm: 6.566 (6.481) Lt: 5.872 (5.752) Accm: 2.96 (3.57) Acct: 4.75 (5.33) proj_loss: -0.6234 (-0.6112) time: 0.9258 data: 0.0003 [11-26 10:46:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:12:56 tlr: 0.00014 tnm: 0.26 Lm: 6.383 (6.444) Lt: 5.701 (5.703) Accm: 3.55 (3.52) Acct: 5.48 (5.48) proj_loss: -0.6136 (-0.6209) time: 0.9258 data: 0.0002 [11-26 10:46:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:12:56 tlr: 0.00014 tnm: 0.26 Lm: 6.471 (6.463) Lt: 5.699 (5.677) Accm: 3.06 (3.24) Acct: 5.06 (5.22) proj_loss: -0.6294 (-0.6180) time: 0.9258 data: 0.0003 [11-26 10:46:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:12:56 tlr: 0.00014 tnm: 0.26 Lm: 6.317 (6.329) Lt: 5.564 (5.571) Accm: 4.12 (3.89) Acct: 6.37 (5.97) proj_loss: -0.6102 (-0.6156) time: 0.9258 data: 0.0003 [11-26 10:53:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.392 (6.377) Lt: 5.656 (5.627) Accm: 3.76 (3.74) Acct: 5.73 (5.66) proj_loss: -0.6141 (-0.6162) time: 0.9222 data: 0.0003 [11-26 10:53:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.399 (6.419) Lt: 5.680 (5.665) Accm: 3.37 (3.38) Acct: 5.15 (5.12) proj_loss: -0.6145 (-0.6218) time: 0.9222 data: 0.0002 [11-26 10:53:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.413 (6.402) Lt: 5.646 (5.621) Accm: 3.80 (3.84) Acct: 5.97 (6.06) proj_loss: -0.6029 (-0.6062) time: 0.9222 data: 0.0002 [11-26 10:53:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.403 (6.420) Lt: 5.651 (5.658) Accm: 3.45 (3.41) Acct: 5.49 (5.40) proj_loss: -0.6262 (-0.6192) time: 0.9222 data: 0.0002 [11-26 10:53:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.365 (6.413) Lt: 5.662 (5.683) Accm: 3.61 (3.56) Acct: 5.48 (5.53) proj_loss: -0.6311 (-0.6316) time: 0.9222 data: 0.0002 [11-26 10:53:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.406 (6.423) Lt: 5.702 (5.697) Accm: 3.72 (3.80) Acct: 5.80 (5.71) proj_loss: -0.6274 (-0.6163) time: 0.9222 data: 0.0003 [11-26 10:53:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.473 (6.473) Lt: 5.725 (5.731) Accm: 3.27 (3.25) Acct: 5.08 (5.06) proj_loss: -0.6109 (-0.6099) time: 0.9222 data: 0.0002 [11-26 10:53:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.348 (6.305) Lt: 5.580 (5.527) Accm: 3.90 (3.92) Acct: 5.92 (6.14) proj_loss: -0.6175 (-0.6167) time: 0.9222 data: 0.0002 ======================================================= RESTART [11-26 11:11:13] ======================================================= ======================================================= RESTART [11-26 11:11:13] ======================================================= ======================================================= RESTART [11-26 11:11:13] ======================================================= ======================================================= RESTART [11-26 11:11:13] ======================================================= ======================================================= RESTART [11-26 11:11:13] ======================================================= ======================================================= RESTART [11-26 11:11:13] ======================================================= ======================================================= RESTART [11-26 11:11:13] ======================================================= ======================================================= RESTART [11-26 11:11:13] ======================================================= [11-26 11:11:13] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:11:13] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:11:13] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 11:12:58] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 11:12:58] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main } [11-26 11:12:58] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 11:13:01] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 11:13:01] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:13:01] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:13:01] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:13:01] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:13:01] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 11:13:01] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 11:13:01] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 11:11:13] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:11:13] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:11:13] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 11:12:58] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 11:12:58] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-26 11:12:58] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 11:13:01] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 11:13:01] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:13:01] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:13:01] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:13:01] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:13:01] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 11:13:01] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 11:13:01] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 11:11:13] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:11:13] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:11:13] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 11:12:58] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 11:12:58] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main } [11-26 11:12:58] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 11:13:01] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 11:13:01] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:13:01] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:13:01] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:13:01] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:13:01] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 11:13:01] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 11:13:01] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 11:11:13] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:11:13] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:11:13] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 11:12:58] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 11:12:58] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main commit_msg : add } [11-26 11:12:58] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 11:13:01] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 11:13:01] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:13:01] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:13:01] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:13:01] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:13:01] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 11:13:01] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 11:13:01] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 11:11:13] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:11:13] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:11:13] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 11:12:58] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 11:12:58] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add branch : main } [11-26 11:12:58] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 11:13:01] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 11:13:01] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:13:01] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:13:01] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:13:01] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:13:01] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 11:13:01] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 11:13:01] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 11:11:13] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:11:13] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:11:13] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 11:12:58] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 11:12:58] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add branch : main } [11-26 11:12:58] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 11:13:01] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 11:13:01] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:13:01] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:13:01] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:13:01] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:13:01] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 11:13:01] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 11:13:01] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 11:11:13] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:11:13] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:11:13] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 11:12:58] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 11:12:58] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-26 11:12:58] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 11:13:01] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 11:13:01] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:13:01] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:13:01] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:13:01] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:13:01] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:13:01] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 11:13:01] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 11:13:01] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 11:11:13] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:11:13] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:11:13] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 11:12:58] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 11:12:58] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add } [11-26 11:12:58] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 11:13:02] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 11:13:02] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 11:13:02] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:13:02] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 11:13:02] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:13:02] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:13:02] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:13:02] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 11:13:02] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:13:02] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 11:13:02] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:13:02] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:13:02] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:13:02] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 11:13:02] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 11:13:02] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ... [dataloader multi processing](*) finished! (48.12s) [dataloader multi processing](*) finished! (49.28s) [dataloader multi processing](*) finished! (50.56s) [dataloader multi processing](*) finished! (51.78s) [dataloader multi processing](*) finished! (52.05s) [dataloader multi processing](*) finished! (53.08s) [dataloader multi processing](*) finished! (52.91s) [dataloader multi processing](*) finished! (54.56s) [11-26 11:13:49] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 11:13:54] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:13:54] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:13:57] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 11:13:51] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 11:13:55] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:13:55] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:13:57] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 11:13:54] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 11:13:57] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:13:57] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:13:58] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 11:13:53] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 11:13:58] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:13:58] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:14:00] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 11:13:53] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 11:13:58] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:13:58] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:14:00] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 11:13:52] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 11:13:56] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:13:56] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:14:00] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 11:13:55] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 11:14:00] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:14:00] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:14:02] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 11:13:56] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 11:14:00] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:14:00] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:14:02] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 11:14:02] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 11:14:30] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 11:14:30] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 11:14:30] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 11:14:30] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 11:14:32] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank0] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 11:14:06] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 11:14:32] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 11:14:32] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 11:14:32] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 11:14:32] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 11:14:33] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank8] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 11:14:06] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 11:14:32] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 11:14:32] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 11:14:32] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 11:14:32] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 11:14:33] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank16] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 11:14:04] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 11:14:32] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 11:14:32] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 11:14:32] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 11:14:32] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 11:14:33] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank24] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 11:14:04] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 11:14:32] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 11:14:32] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 11:14:32] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 11:14:32] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 11:14:33] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank32] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 11:14:01] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 11:14:32] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 11:14:32] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 11:14:32] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 11:14:32] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 11:14:33] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank40] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 11:14:01] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 11:14:32] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 11:14:32] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 11:14:32] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 11:14:32] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 11:14:33] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank48] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 11:14:06] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 11:14:32] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 11:14:32] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 11:14:32] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 11:14:32] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 11:14:34] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank56] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 11:14:34] (/VAR/utils/lr_control.py, line 105)=> [11-26 11:14:34] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 11:14:36] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 11:14:36] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 11:14:37] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 11:14:37] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 11:14:34] (/VAR/utils/lr_control.py, line 105)=> [11-26 11:14:34] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 11:14:36] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 11:14:36] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 11:14:37] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 11:14:37] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 11:14:34] (/VAR/utils/lr_control.py, line 105)=> [11-26 11:14:34] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 11:14:36] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 11:14:36] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 11:14:37] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 11:14:37] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 11:14:34] (/VAR/utils/lr_control.py, line 105)=> [11-26 11:14:34] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 11:14:36] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 11:14:36] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 11:14:37] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 11:14:37] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 11:14:34] (/VAR/utils/lr_control.py, line 105)=> [11-26 11:14:34] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 11:14:36] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 11:14:36] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 11:14:37] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 11:14:37] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 11:14:34] (/VAR/utils/lr_control.py, line 105)=> [11-26 11:14:34] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 11:14:36] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 11:14:36] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 11:14:37] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 11:14:37] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 11:14:34] (/VAR/utils/lr_control.py, line 105)=> [11-26 11:14:34] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 11:14:37] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 11:14:37] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 11:14:38] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 11:14:38] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] ======================================================= RESTART [11-26 11:28:09] ======================================================= ======================================================= RESTART [11-26 11:28:10] ======================================================= ======================================================= RESTART [11-26 11:28:11] ======================================================= ======================================================= RESTART [11-26 11:28:11] ======================================================= ======================================================= RESTART [11-26 11:28:11] ======================================================= ======================================================= RESTART [11-26 11:28:11] ======================================================= ======================================================= RESTART [11-26 11:28:11] ======================================================= [11-26 11:28:11] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:28:11] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:28:11] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 11:28:11] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:28:11] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:28:11] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 11:28:11] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:28:11] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:28:11] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 11:28:09] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:28:09] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:28:09] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 11:28:10] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:28:10] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:28:10] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 11:28:11] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:28:11] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:28:11] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 11:28:11] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:28:11] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:28:11] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True ======================================================= RESTART [11-26 11:39:09] ======================================================= ======================================================= RESTART [11-26 11:39:09] ======================================================= ======================================================= RESTART [11-26 11:39:09] ======================================================= ======================================================= RESTART [11-26 11:39:09] ======================================================= ======================================================= RESTART [11-26 11:39:09] ======================================================= ======================================================= RESTART [11-26 11:39:09] ======================================================= ======================================================= RESTART [11-26 11:39:09] ======================================================= ======================================================= RESTART [11-26 11:39:09] ======================================================= [11-26 11:39:09] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:39:09] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:39:09] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 11:40:51] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 11:40:51] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main } [11-26 11:40:51] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 11:40:54] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 11:40:54] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:40:54] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:40:54] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:40:54] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:40:54] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 11:40:54] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 11:40:54] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 11:39:09] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:39:09] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:39:09] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 11:40:51] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 11:40:51] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-26 11:40:51] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 11:40:54] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 11:40:54] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:40:54] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:40:54] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:40:54] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:40:54] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 11:40:54] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 11:40:54] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 11:39:09] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:39:09] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:39:09] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 11:40:51] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 11:40:51] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-26 11:40:51] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 11:40:54] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 11:40:54] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:40:54] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:40:54] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:40:54] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:40:54] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 11:40:54] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 11:40:54] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 11:39:09] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:39:09] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:39:09] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 11:40:51] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 11:40:51] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-26 11:40:51] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 11:40:54] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 11:40:54] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:40:54] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:40:54] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:40:54] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:40:54] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 11:40:54] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 11:40:54] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 11:39:09] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:39:09] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:39:09] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 11:40:51] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 11:40:51] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add } [11-26 11:40:51] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 11:40:54] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 11:40:54] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:40:54] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:40:54] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:40:54] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:40:54] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 11:40:54] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 11:40:54] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 11:39:09] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:39:09] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:39:09] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 11:40:51] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 11:40:51] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main commit_msg : add } [11-26 11:40:51] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 11:40:54] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 11:40:54] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:40:54] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:40:54] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:40:54] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:40:54] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:40:54] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 11:40:54] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 11:40:54] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 11:39:09] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:39:09] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:39:09] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 11:40:51] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 11:40:51] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add } [11-26 11:40:51] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 11:40:55] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 11:40:55] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 11:40:55] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:40:55] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 11:40:55] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:40:55] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:40:55] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:40:55] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 11:40:55] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:40:55] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 11:40:55] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:40:55] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:40:55] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:40:55] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 11:40:55] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 11:40:55] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-26 11:39:09] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-26 11:39:09] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-26 11:39:09] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-26 11:40:51] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-26 11:40:51] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main } [11-26 11:40:51] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-26 11:40:57] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-26 11:40:57] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-26 11:40:57] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:40:57] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-26 11:40:57] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:40:57] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:40:57] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:40:57] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-26 11:40:57] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-26 11:40:57] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-26 11:40:57] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-26 11:40:57] (e/user/VAR/utils/data.py, line 51)=> [11-26 11:40:57] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-26 11:40:57] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-best.pth ... [11-26 11:40:57] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep160, it0 [11-26 11:40:57] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ... [dataloader multi processing](*) finished! (47.71s) [dataloader multi processing](*) finished! (47.89s) [dataloader multi processing](*) finished! (47.73s) [dataloader multi processing](*) finished! (49.50s) [dataloader multi processing](*) finished! (49.72s) [dataloader multi processing](*) finished! (49.09s) [dataloader multi processing](*) finished! (50.89s) [11-26 11:41:42] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 11:41:45] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:41:45] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:41:46] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [dataloader multi processing](*) finished! (49.50s) [11-26 11:41:42] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 11:41:47] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:41:47] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:41:48] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 11:41:42] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 11:41:47] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:41:47] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:41:48] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 11:41:44] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 11:41:48] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:41:48] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:41:50] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 11:41:44] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 11:41:48] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:41:48] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:41:50] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 11:41:44] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 11:41:49] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:41:49] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:41:51] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 11:41:45] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 11:41:50] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:41:50] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:41:51] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 11:41:47] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-26 11:41:51] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:41:51] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-26 11:41:53] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-26 11:41:49] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 11:42:20] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 11:42:20] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 11:42:20] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 11:42:20] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 11:42:20] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank0] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 11:41:51] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 11:42:20] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 11:42:20] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 11:42:20] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 11:42:20] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 11:42:20] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank8] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 11:41:51] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 11:42:20] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 11:42:20] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 11:42:20] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 11:42:20] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 11:42:20] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank16] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 11:41:53] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 11:42:20] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 11:42:20] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 11:42:20] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 11:42:20] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 11:42:21] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank24] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 11:41:54] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 11:42:20] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 11:42:20] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 11:42:20] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 11:42:20] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 11:42:21] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank32] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 11:41:53] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 11:42:20] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 11:42:20] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 11:42:20] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 11:42:20] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 11:42:21] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank40] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 11:41:55] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 11:42:20] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 11:42:20] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 11:42:20] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 11:42:20] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 11:42:21] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank48] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 11:41:56] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-26 11:42:20] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-26 11:42:20] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-26 11:42:20] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-26 11:42:20] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-26 11:42:21] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank56] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-26 11:42:21] (/VAR/utils/lr_control.py, line 105)=> [11-26 11:42:21] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 11:42:23] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 11:42:23] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 11:42:24] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 11:42:24] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 11:48:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 6 days, 19:13:31 tlr: 0.00014 tnm: 0.26 Lm: 6.580 (6.580) Lt: 5.890 (5.890) Accm: 3.51 (3.51) Acct: 5.37 (5.37) proj_loss: -0.6044 (-0.6044) time: 352.0740 data: 0.0006 [11-26 11:42:21] (/VAR/utils/lr_control.py, line 105)=> [11-26 11:42:21] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 11:42:23] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 11:42:23] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 11:42:23] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 11:42:23] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 11:48:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 6 days, 18:57:25 tlr: 0.00014 tnm: 0.26 Lm: 6.509 (6.509) Lt: 5.765 (5.765) Accm: 3.39 (3.39) Acct: 5.03 (5.03) proj_loss: -0.6196 (-0.6196) time: 351.4954 data: 0.0005 [11-26 11:42:21] (/VAR/utils/lr_control.py, line 105)=> [11-26 11:42:21] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 11:42:23] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 11:42:23] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 11:42:23] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 11:42:23] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 11:48:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 6 days, 19:08:18 tlr: 0.00014 tnm: 0.26 Lm: 6.214 (6.214) Lt: 5.477 (5.477) Accm: 3.92 (3.92) Acct: 5.68 (5.68) proj_loss: -0.6498 (-0.6498) time: 351.8866 data: 0.0006 [11-26 11:42:21] (/VAR/utils/lr_control.py, line 105)=> [11-26 11:42:21] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 11:42:23] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 11:42:23] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 11:42:24] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 11:42:24] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 11:48:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 6 days, 19:05:52 tlr: 0.00014 tnm: 0.26 Lm: 6.455 (6.455) Lt: 5.671 (5.671) Accm: 3.35 (3.35) Acct: 5.20 (5.20) proj_loss: -0.6288 (-0.6288) time: 351.7988 data: 0.0006 [11-26 11:42:21] (/VAR/utils/lr_control.py, line 105)=> [11-26 11:42:21] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 11:42:23] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 11:42:23] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 11:42:24] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 11:42:24] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 11:48:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 6 days, 19:18:53 tlr: 0.00014 tnm: 0.26 Lm: 6.551 (6.551) Lt: 5.793 (5.793) Accm: 3.32 (3.32) Acct: 5.20 (5.20) proj_loss: -0.6221 (-0.6221) time: 352.2670 data: 0.0006 [11-26 11:42:21] (/VAR/utils/lr_control.py, line 105)=> [11-26 11:42:21] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 11:42:23] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 11:42:23] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 11:42:24] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 11:42:24] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 11:48:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 6 days, 19:22:20 tlr: 0.00014 tnm: 0.26 Lm: 6.522 (6.522) Lt: 5.711 (5.711) Accm: 3.25 (3.25) Acct: 4.96 (4.96) proj_loss: -0.6076 (-0.6076) time: 352.3912 data: 0.0006 [11-26 11:42:21] (/VAR/utils/lr_control.py, line 105)=> [11-26 11:42:21] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 11:42:23] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 11:42:23] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 11:42:24] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 11:42:24] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 11:48:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 6 days, 19:17:13 tlr: 0.00014 tnm: 0.26 Lm: 6.563 (6.563) Lt: 5.809 (5.809) Accm: 3.29 (3.29) Acct: 5.41 (5.41) proj_loss: -0.6128 (-0.6128) time: 352.2069 data: 0.0005 [11-26 11:42:21] (/VAR/utils/lr_control.py, line 105)=> [11-26 11:42:21] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-26 11:42:24] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-26 11:42:24] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-26 11:42:24] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-26 11:42:24] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-26 11:48:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 0/1669] eta: 6 days, 19:10:46 tlr: 0.00014 tnm: 0.26 Lm: 6.529 (6.529) Lt: 5.852 (5.852) Accm: 3.44 (3.44) Acct: 5.06 (5.06) proj_loss: -0.6095 (-0.6095) time: 351.9749 data: 0.0006 [11-26 12:03:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 1:02:01 tlr: 0.00014 tnm: 0.26 Lm: 6.487 (6.487) Lt: 5.745 (5.745) Accm: 3.39 (3.39) Acct: 5.63 (5.63) proj_loss: -0.6214 (-0.6214) time: 0.9226 data: 0.0003 [11-26 12:03:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 1:02:02 tlr: 0.00014 tnm: 0.26 Lm: 6.436 (6.436) Lt: 5.620 (5.620) Accm: 3.77 (3.77) Acct: 6.03 (6.03) proj_loss: -0.6005 (-0.6005) time: 0.9226 data: 0.0003 [11-26 12:03:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 1:02:00 tlr: 0.00014 tnm: 0.26 Lm: 6.526 (6.526) Lt: 5.839 (5.839) Accm: 3.37 (3.37) Acct: 4.92 (4.92) proj_loss: -0.6126 (-0.6126) time: 0.9226 data: 0.0002 [11-26 12:03:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 1:02:01 tlr: 0.00014 tnm: 0.26 Lm: 6.412 (6.412) Lt: 5.680 (5.680) Accm: 3.82 (3.82) Acct: 5.91 (5.91) proj_loss: -0.6164 (-0.6164) time: 0.9226 data: 0.0003 [11-26 12:03:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 1:02:00 tlr: 0.00014 tnm: 0.26 Lm: 6.395 (6.395) Lt: 5.572 (5.572) Accm: 3.45 (3.45) Acct: 5.49 (5.49) proj_loss: -0.6159 (-0.6159) time: 0.9226 data: 0.0003 [11-26 12:03:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 1:01:59 tlr: 0.00014 tnm: 0.26 Lm: 6.484 (6.484) Lt: 5.681 (5.681) Accm: 3.41 (3.41) Acct: 5.44 (5.44) proj_loss: -0.5928 (-0.5928) time: 0.9226 data: 0.0002 [11-26 12:03:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 1:02:00 tlr: 0.00014 tnm: 0.26 Lm: 6.355 (6.355) Lt: 5.600 (5.600) Accm: 3.79 (3.79) Acct: 5.48 (5.48) proj_loss: -0.6298 (-0.6298) time: 0.9226 data: 0.0002 [11-26 12:03:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 417/1669] eta: 1:02:01 tlr: 0.00014 tnm: 0.26 Lm: 6.560 (6.560) Lt: 5.831 (5.831) Accm: 3.25 (3.25) Acct: 5.11 (5.11) proj_loss: -0.6106 (-0.6106) time: 0.9226 data: 0.0002 [11-26 12:09:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:27:07 tlr: 0.00014 tnm: 0.25 Lm: 6.541 (6.527) Lt: 5.771 (5.780) Accm: 3.47 (3.32) Acct: 5.37 (5.23) proj_loss: -0.6054 (-0.6088) time: 0.9238 data: 0.0003 [11-26 12:09:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:27:07 tlr: 0.00014 tnm: 0.25 Lm: 6.459 (6.392) Lt: 5.598 (5.610) Accm: 3.42 (3.71) Acct: 5.85 (5.92) proj_loss: -0.6196 (-0.6028) time: 0.9238 data: 0.0002 [11-26 12:09:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:27:07 tlr: 0.00014 tnm: 0.25 Lm: 6.517 (6.497) Lt: 5.765 (5.752) Accm: 3.50 (3.53) Acct: 5.85 (5.77) proj_loss: -0.6248 (-0.6225) time: 0.9238 data: 0.0003 [11-26 12:09:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:27:07 tlr: 0.00014 tnm: 0.25 Lm: 6.551 (6.469) Lt: 5.793 (5.721) Accm: 3.32 (3.59) Acct: 5.20 (5.64) proj_loss: -0.6200 (-0.6176) time: 0.9238 data: 0.0003 [11-26 12:09:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:27:07 tlr: 0.00014 tnm: 0.25 Lm: 6.522 (6.468) Lt: 5.711 (5.667) Accm: 3.25 (3.45) Acct: 4.96 (5.49) proj_loss: -0.5967 (-0.5992) time: 0.9238 data: 0.0003 [11-26 12:09:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:27:07 tlr: 0.00014 tnm: 0.25 Lm: 6.455 (6.522) Lt: 5.671 (5.750) Accm: 3.35 (3.15) Acct: 5.20 (5.00) proj_loss: -0.6031 (-0.6076) time: 0.9238 data: 0.0003 [11-26 12:09:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:27:07 tlr: 0.00014 tnm: 0.25 Lm: 6.529 (6.565) Lt: 5.852 (5.883) Accm: 3.29 (3.27) Acct: 4.79 (4.79) proj_loss: -0.6156 (-0.6240) time: 0.9238 data: 0.0002 [11-26 12:09:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [ 834/1669] eta: 0:27:07 tlr: 0.00014 tnm: 0.25 Lm: 6.496 (6.445) Lt: 5.723 (5.695) Accm: 3.66 (3.49) Acct: 5.27 (5.21) proj_loss: -0.6098 (-0.6224) time: 0.9238 data: 0.0003 [11-26 12:16:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:11:12 tlr: 0.00014 tnm: 0.26 Lm: 6.465 (6.442) Lt: 5.651 (5.666) Accm: 3.79 (3.63) Acct: 5.48 (5.60) proj_loss: -0.6111 (-0.6199) time: 0.9253 data: 0.0002 [11-26 12:16:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:11:11 tlr: 0.00014 tnm: 0.26 Lm: 6.426 (6.392) Lt: 5.615 (5.615) Accm: 3.61 (3.73) Acct: 5.61 (5.79) proj_loss: -0.6212 (-0.6092) time: 0.9253 data: 0.0003 [11-26 12:16:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:11:12 tlr: 0.00014 tnm: 0.26 Lm: 6.527 (6.555) Lt: 5.843 (5.871) Accm: 3.24 (3.25) Acct: 4.87 (4.83) proj_loss: -0.6306 (-0.6294) time: 0.9253 data: 0.0002 [11-26 12:16:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:11:12 tlr: 0.00014 tnm: 0.26 Lm: 6.501 (6.469) Lt: 5.725 (5.708) Accm: 3.49 (3.47) Acct: 5.42 (5.43) proj_loss: -0.6049 (-0.5990) time: 0.9253 data: 0.0002 [11-26 12:16:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:11:12 tlr: 0.00014 tnm: 0.26 Lm: 6.486 (6.463) Lt: 5.709 (5.677) Accm: 3.27 (3.41) Acct: 5.11 (5.43) proj_loss: -0.6022 (-0.6053) time: 0.9253 data: 0.0002 [11-26 12:16:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:11:12 tlr: 0.00014 tnm: 0.26 Lm: 6.499 (6.493) Lt: 5.761 (5.753) Accm: 3.44 (3.49) Acct: 5.63 (5.65) proj_loss: -0.6274 (-0.6247) time: 0.9253 data: 0.0003 [11-26 12:16:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:11:12 tlr: 0.00014 tnm: 0.26 Lm: 6.520 (6.538) Lt: 5.788 (5.789) Accm: 3.42 (3.24) Acct: 5.23 (5.07) proj_loss: -0.6159 (-0.6150) time: 0.9253 data: 0.0003 [11-26 12:16:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1251/1669] eta: 0:11:12 tlr: 0.00014 tnm: 0.26 Lm: 6.441 (6.435) Lt: 5.680 (5.677) Accm: 3.32 (3.52) Acct: 5.22 (5.54) proj_loss: -0.6210 (-0.6189) time: 0.9253 data: 0.0002 [11-26 12:22:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:01 tlr: 0.00014 tnm: 0.26 Lm: 6.426 (6.433) Lt: 5.579 (5.657) Accm: 3.32 (3.55) Acct: 5.23 (5.63) proj_loss: -0.6200 (-0.6168) time: 0.9263 data: 0.0014 [11-26 12:22:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:39:58 (1.437 s / it) [11-26 12:22:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:01 tlr: 0.00014 tnm: 0.26 Lm: 6.481 (6.473) Lt: 5.757 (5.722) Accm: 3.50 (3.54) Acct: 5.72 (5.66) proj_loss: -0.6299 (-0.6280) time: 0.9263 data: 0.0016 [11-26 12:22:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:01 tlr: 0.00014 tnm: 0.26 Lm: 6.450 (6.456) Lt: 5.707 (5.661) Accm: 3.29 (3.48) Acct: 5.27 (5.50) proj_loss: -0.5991 (-0.6041) time: 0.9263 data: 0.0018 [11-26 12:22:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:01 tlr: 0.00014 tnm: 0.26 Lm: 6.533 (6.481) Lt: 5.771 (5.725) Accm: 3.51 (3.52) Acct: 5.48 (5.52) proj_loss: -0.6054 (-0.6046) time: 0.9263 data: 0.0018 [11-26 12:22:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:01 tlr: 0.00014 tnm: 0.26 Lm: 6.392 (6.374) Lt: 5.598 (5.598) Accm: 3.79 (3.80) Acct: 5.85 (5.96) proj_loss: -0.6196 (-0.6106) time: 0.9263 data: 0.0016 [11-26 12:22:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:01 tlr: 0.00014 tnm: 0.26 Lm: 6.529 (6.556) Lt: 5.833 (5.860) Accm: 3.19 (3.23) Acct: 4.89 (4.84) proj_loss: -0.6156 (-0.6238) time: 0.9263 data: 0.0016 [11-26 12:22:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:01 tlr: 0.00014 tnm: 0.26 Lm: 6.573 (6.545) Lt: 5.875 (5.806) Accm: 3.35 (3.16) Acct: 5.20 (4.94) proj_loss: -0.6099 (-0.6140) time: 0.9263 data: 0.0016 [11-26 12:22:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 160/350] [1668/1669] eta: 0:00:01 tlr: 0.00014 tnm: 0.26 Lm: 6.434 (6.402) Lt: 5.579 (5.642) Accm: 3.80 (3.66) Acct: 5.68 (5.63) proj_loss: -0.6124 (-0.6288) time: 0.9263 data: 0.0019 [11-26 12:22:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:39:58 (1.437 s / it) [11-26 12:22:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:39:59 (1.437 s / it) [11-26 12:22:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:39:58 (1.437 s / it) [11-26 12:22:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:39:58 (1.437 s / it) [11-26 12:22:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:39:58 (1.437 s / it) [11-26 12:22:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:39:58 (1.437 s / it) [11-26 12:22:33] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 160/350] Total time: 0:39:58 (1.437 s / it) [11-26 12:22:33] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.433 (6.433), Lt: 5.675 (5.675), Acc m&t: 3.56 5.58, Remain: 3 days, 9:48:12, Finish: 2024-11-29 06:10 [11-26 12:22:33] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.433 (6.433), Lt: 5.675 (5.675), Acc m&t: 3.56 5.58, Remain: 3 days, 9:48:56, Finish: 2024-11-29 06:11 [11-26 12:22:33] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.433 (6.433), Lt: 5.675 (5.675), Acc m&t: 3.56 5.58, Remain: 3 days, 9:49:18, Finish: 2024-11-29 06:11 [11-26 12:22:33] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.433 (6.433), Lt: 5.675 (5.675), Acc m&t: 3.56 5.58, Remain: 3 days, 9:49:30, Finish: 2024-11-29 06:12 [11-26 12:22:33] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.433 (6.433), Lt: 5.675 (5.675), Acc m&t: 3.56 5.58, Remain: 3 days, 9:50:16, Finish: 2024-11-29 06:12 [11-26 12:22:33] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.433 (6.433), Lt: 5.675 (5.675), Acc m&t: 3.56 5.58, Remain: 3 days, 9:49:33, Finish: 2024-11-29 06:12 [11-26 12:22:33] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.433 (6.433), Lt: 5.675 (5.675), Acc m&t: 3.56 5.58, Remain: 3 days, 9:49:15, Finish: 2024-11-29 06:11 [11-26 12:22:33] (/home/user/VAR/train.py , line 276)=> [ep160] (training ) Lm: 6.433 (6.433), Lt: 5.675 (5.675), Acc m&t: 3.56 5.58, Remain: 3 days, 9:48:49, Finish: 2024-11-29 06:11 [11-26 12:22:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:43 tlr: 0.00014 tnm: 0.26 Lm: 6.368 (6.368) Lt: 5.561 (5.561) Accm: 3.64 (3.64) Acct: 5.85 (5.85) proj_loss: -0.6028 (-0.6028) time: 0.9249 data: 0.0003 [11-26 12:22:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:43 tlr: 0.00014 tnm: 0.26 Lm: 6.427 (6.427) Lt: 5.622 (5.622) Accm: 3.34 (3.34) Acct: 4.55 (4.55) proj_loss: -0.5944 (-0.5944) time: 0.9247 data: 0.0004 [11-26 12:22:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:44 tlr: 0.00014 tnm: 0.26 Lm: 6.658 (6.658) Lt: 5.873 (5.873) Accm: 2.74 (2.74) Acct: 4.34 (4.34) proj_loss: -0.6212 (-0.6212) time: 0.9256 data: 0.0003 [11-26 12:22:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:44 tlr: 0.00014 tnm: 0.26 Lm: 6.503 (6.503) Lt: 5.642 (5.642) Accm: 3.66 (3.66) Acct: 6.40 (6.40) proj_loss: -0.5914 (-0.5914) time: 0.9254 data: 0.0004 [11-26 12:22:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:44 tlr: 0.00014 tnm: 0.26 Lm: 6.340 (6.340) Lt: 5.641 (5.641) Accm: 3.76 (3.76) Acct: 5.72 (5.72) proj_loss: -0.6153 (-0.6153) time: 0.9252 data: 0.0004 [11-26 12:22:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:44 tlr: 0.00014 tnm: 0.26 Lm: 6.456 (6.456) Lt: 5.744 (5.744) Accm: 3.38 (3.38) Acct: 4.79 (4.79) proj_loss: -0.6095 (-0.6095) time: 0.9252 data: 0.0004 [11-26 12:22:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:46 tlr: 0.00014 tnm: 0.26 Lm: 6.589 (6.589) Lt: 5.757 (5.757) Accm: 3.16 (3.16) Acct: 5.17 (5.17) proj_loss: -0.6159 (-0.6159) time: 0.9265 data: 0.0004 [11-26 12:22:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 0/1669] eta: 0:25:44 tlr: 0.00014 tnm: 0.26 Lm: 6.265 (6.265) Lt: 5.416 (5.416) Accm: 4.59 (4.59) Acct: 7.30 (7.30) proj_loss: -0.6119 (-0.6119) time: 0.9255 data: 0.0003 [11-26 12:29:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:29 tlr: 0.00014 tnm: 0.26 Lm: 6.360 (6.360) Lt: 5.571 (5.571) Accm: 4.04 (4.04) Acct: 6.44 (6.44) proj_loss: -0.6114 (-0.6114) time: 0.9253 data: 0.0003 [11-26 12:29:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:29 tlr: 0.00014 tnm: 0.26 Lm: 6.505 (6.505) Lt: 5.779 (5.779) Accm: 3.50 (3.50) Acct: 5.27 (5.27) proj_loss: -0.6124 (-0.6124) time: 0.9253 data: 0.0002 [11-26 12:29:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:29 tlr: 0.00014 tnm: 0.26 Lm: 6.625 (6.625) Lt: 5.863 (5.863) Accm: 2.83 (2.83) Acct: 4.53 (4.53) proj_loss: -0.6252 (-0.6252) time: 0.9252 data: 0.0002 [11-26 12:29:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:29 tlr: 0.00014 tnm: 0.26 Lm: 6.408 (6.408) Lt: 5.631 (5.631) Accm: 3.66 (3.66) Acct: 5.37 (5.37) proj_loss: -0.6141 (-0.6141) time: 0.9252 data: 0.0002 [11-26 12:29:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:29 tlr: 0.00014 tnm: 0.26 Lm: 6.482 (6.482) Lt: 5.675 (5.675) Accm: 3.42 (3.42) Acct: 5.97 (5.97) proj_loss: -0.6154 (-0.6154) time: 0.9252 data: 0.0002 [11-26 12:29:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:29 tlr: 0.00014 tnm: 0.26 Lm: 6.326 (6.326) Lt: 5.559 (5.559) Accm: 3.91 (3.91) Acct: 5.94 (5.94) proj_loss: -0.6397 (-0.6397) time: 0.9252 data: 0.0002 [11-26 12:29:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:29 tlr: 0.00014 tnm: 0.26 Lm: 6.252 (6.252) Lt: 5.439 (5.439) Accm: 4.06 (4.06) Acct: 6.32 (6.32) proj_loss: -0.6110 (-0.6110) time: 0.9252 data: 0.0003 [11-26 12:29:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 417/1669] eta: 0:19:29 tlr: 0.00014 tnm: 0.26 Lm: 6.507 (6.507) Lt: 5.731 (5.731) Accm: 3.21 (3.21) Acct: 5.13 (5.13) proj_loss: -0.6169 (-0.6169) time: 0.9252 data: 0.0003 [11-26 12:35:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:12:55 tlr: 0.00014 tnm: 0.26 Lm: 6.425 (6.438) Lt: 5.705 (5.653) Accm: 3.25 (3.52) Acct: 5.17 (5.56) proj_loss: -0.6159 (-0.6138) time: 0.9251 data: 0.0003 [11-26 12:35:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:12:55 tlr: 0.00014 tnm: 0.26 Lm: 6.368 (6.304) Lt: 5.561 (5.535) Accm: 3.64 (3.82) Acct: 5.85 (5.87) proj_loss: -0.6121 (-0.6114) time: 0.9251 data: 0.0002 [11-26 12:35:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:12:55 tlr: 0.00014 tnm: 0.26 Lm: 6.554 (6.529) Lt: 5.815 (5.813) Accm: 3.38 (3.32) Acct: 4.79 (5.07) proj_loss: -0.6153 (-0.6152) time: 0.9251 data: 0.0003 [11-26 12:35:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:12:55 tlr: 0.00014 tnm: 0.26 Lm: 6.331 (6.351) Lt: 5.589 (5.577) Accm: 3.95 (4.01) Acct: 6.10 (6.32) proj_loss: -0.6119 (-0.6206) time: 0.9251 data: 0.0003 [11-26 12:35:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:12:55 tlr: 0.00014 tnm: 0.26 Lm: 6.460 (6.471) Lt: 5.642 (5.663) Accm: 3.60 (3.48) Acct: 5.54 (5.77) proj_loss: -0.5951 (-0.6086) time: 0.9251 data: 0.0002 [11-26 12:35:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:12:55 tlr: 0.00014 tnm: 0.26 Lm: 6.592 (6.518) Lt: 5.852 (5.758) Accm: 2.91 (3.29) Acct: 4.72 (5.17) proj_loss: -0.6212 (-0.6126) time: 0.9251 data: 0.0002 [11-26 12:35:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:12:55 tlr: 0.00014 tnm: 0.26 Lm: 6.427 (6.470) Lt: 5.640 (5.686) Accm: 3.34 (3.52) Acct: 5.48 (5.41) proj_loss: -0.6283 (-0.6188) time: 0.9251 data: 0.0003 [11-26 12:35:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [ 834/1669] eta: 0:12:55 tlr: 0.00014 tnm: 0.26 Lm: 6.340 (6.399) Lt: 5.641 (5.642) Accm: 3.76 (3.65) Acct: 5.72 (5.56) proj_loss: -0.6153 (-0.6295) time: 0.9251 data: 0.0003 [11-26 12:41:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.26 Lm: 6.326 (6.376) Lt: 5.654 (5.648) Accm: 3.68 (3.63) Acct: 5.56 (5.52) proj_loss: -0.6397 (-0.6393) time: 0.9203 data: 0.0002 [11-26 12:41:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.26 Lm: 6.454 (6.443) Lt: 5.640 (5.634) Accm: 3.55 (3.49) Acct: 5.60 (5.74) proj_loss: -0.5953 (-0.6054) time: 0.9203 data: 0.0003 [11-26 12:41:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.26 Lm: 6.448 (6.441) Lt: 5.700 (5.665) Accm: 3.56 (3.54) Acct: 5.58 (5.58) proj_loss: -0.6252 (-0.6172) time: 0.9203 data: 0.0002 [11-26 12:41:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.26 Lm: 6.393 (6.403) Lt: 5.658 (5.639) Accm: 3.74 (3.89) Acct: 5.84 (5.94) proj_loss: -0.6147 (-0.6198) time: 0.9203 data: 0.0002 [11-26 12:41:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.26 Lm: 6.555 (6.536) Lt: 5.799 (5.806) Accm: 3.42 (3.35) Acct: 5.22 (5.22) proj_loss: -0.6124 (-0.6075) time: 0.9203 data: 0.0003 [11-26 12:41:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.26 Lm: 6.408 (6.426) Lt: 5.631 (5.636) Accm: 3.63 (3.62) Acct: 5.84 (5.70) proj_loss: -0.6256 (-0.6198) time: 0.9203 data: 0.0002 [11-26 12:41:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.26 Lm: 6.355 (6.313) Lt: 5.566 (5.544) Accm: 3.59 (3.75) Acct: 5.79 (5.83) proj_loss: -0.6157 (-0.6156) time: 0.9203 data: 0.0002 [11-26 12:41:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.26 Lm: 6.389 (6.417) Lt: 5.625 (5.626) Accm: 3.65 (3.65) Acct: 5.79 (5.96) proj_loss: -0.6169 (-0.6236) time: 0.9203 data: 0.0003 [11-26 12:48:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.425 (6.418) Lt: 5.705 (5.656) Accm: 3.35 (3.59) Acct: 5.20 (5.81) proj_loss: -0.6179 (-0.6261) time: 0.9283 data: 0.0021 [11-26 12:48:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 161/350] Total time: 0:25:47 (0.927 s / it) [11-26 12:48:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.340 (6.395) Lt: 5.666 (5.683) Accm: 3.60 (3.62) Acct: 5.44 (5.50) proj_loss: -0.6176 (-0.6350) time: 0.9283 data: 0.0015 [11-26 12:48:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.522 (6.457) Lt: 5.786 (5.689) Accm: 3.72 (3.58) Acct: 5.96 (5.65) proj_loss: -0.6212 (-0.6170) time: 0.9283 data: 0.0016 [11-26 12:48:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.355 (6.393) Lt: 5.589 (5.615) Accm: 3.72 (3.85) Acct: 6.10 (5.98) proj_loss: -0.6119 (-0.6138) time: 0.9283 data: 0.0017 [11-26 12:48:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.449 (6.406) Lt: 5.638 (5.583) Accm: 3.60 (3.73) Acct: 5.65 (6.06) proj_loss: -0.5956 (-0.6058) time: 0.9283 data: 0.0018 [11-26 12:48:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.427 (6.469) Lt: 5.640 (5.683) Accm: 3.34 (3.44) Acct: 5.48 (5.45) proj_loss: -0.6228 (-0.6131) time: 0.9283 data: 0.0017 [11-26 12:48:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.342 (6.311) Lt: 5.561 (5.533) Accm: 3.64 (3.78) Acct: 5.85 (5.92) proj_loss: -0.6121 (-0.6102) time: 0.9283 data: 0.0016 [11-26 12:48:20] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 161/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.554 (6.441) Lt: 5.784 (5.701) Accm: 3.45 (3.59) Acct: 5.65 (5.63) proj_loss: -0.6153 (-0.6144) time: 0.9283 data: 0.0018 [11-26 12:48:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 161/350] Total time: 0:25:47 (0.927 s / it) [11-26 12:48:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 161/350] Total time: 0:25:47 (0.927 s / it) [11-26 12:48:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 161/350] Total time: 0:25:47 (0.927 s / it) [11-26 12:48:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 161/350] Total time: 0:25:47 (0.927 s / it) [11-26 12:48:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 161/350] Total time: 0:25:47 (0.927 s / it) [11-26 12:48:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 161/350] Total time: 0:25:47 (0.927 s / it) [11-26 12:48:20] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 161/350] Total time: 0:25:47 (0.927 s / it) [11-26 12:48:20] (/home/user/VAR/train.py , line 276)=> [ep161] (training ) Lm: 6.433 (6.447), Lt: 5.675 (5.690), Acc m&t: 3.56 5.58, Remain: 3 days, 9:34:49, Finish: 2024-11-29 06:23 [11-26 12:48:20] (/home/user/VAR/train.py , line 276)=> [ep161] (training ) Lm: 6.433 (6.447), Lt: 5.675 (5.690), Acc m&t: 3.56 5.58, Remain: 3 days, 9:35:59, Finish: 2024-11-29 06:24 [11-26 12:48:20] (/home/user/VAR/train.py , line 276)=> [ep161] (training ) Lm: 6.433 (6.447), Lt: 5.675 (5.690), Acc m&t: 3.56 5.58, Remain: 3 days, 9:35:12, Finish: 2024-11-29 06:23 [11-26 12:48:20] (/home/user/VAR/train.py , line 276)=> [ep161] (training ) Lm: 6.433 (6.447), Lt: 5.675 (5.690), Acc m&t: 3.56 5.58, Remain: 3 days, 9:35:33, Finish: 2024-11-29 06:23 [11-26 12:48:20] (/home/user/VAR/train.py , line 276)=> [ep161] (training ) Lm: 6.433 (6.447), Lt: 5.675 (5.690), Acc m&t: 3.56 5.58, Remain: 3 days, 9:35:17, Finish: 2024-11-29 06:23 [11-26 12:48:20] (/home/user/VAR/train.py , line 276)=> [ep161] (training ) Lm: 6.433 (6.447), Lt: 5.675 (5.690), Acc m&t: 3.56 5.58, Remain: 3 days, 9:35:57, Finish: 2024-11-29 06:24 [11-26 12:48:20] (/home/user/VAR/train.py , line 276)=> [ep161] (training ) Lm: 6.433 (6.447), Lt: 5.675 (5.690), Acc m&t: 3.56 5.58, Remain: 3 days, 9:35:45, Finish: 2024-11-29 06:24 [11-26 12:48:20] (/home/user/VAR/train.py , line 276)=> [ep161] (training ) Lm: 6.433 (6.447), Lt: 5.675 (5.690), Acc m&t: 3.56 5.58, Remain: 3 days, 9:35:17, Finish: 2024-11-29 06:23 [11-26 12:48:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 0/1669] eta: 0:25:06 tlr: 0.00014 tnm: 0.27 Lm: 6.302 (6.302) Lt: 5.571 (5.571) Accm: 3.90 (3.90) Acct: 6.23 (6.23) proj_loss: -0.6366 (-0.6366) time: 0.9028 data: 0.0003 [11-26 12:48:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 0/1669] eta: 0:25:06 tlr: 0.00014 tnm: 0.27 Lm: 6.318 (6.318) Lt: 5.527 (5.527) Accm: 4.11 (4.11) Acct: 6.58 (6.58) proj_loss: -0.6049 (-0.6049) time: 0.9028 data: 0.0004 [11-26 12:48:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 0/1669] eta: 0:25:07 tlr: 0.00014 tnm: 0.27 Lm: 6.399 (6.399) Lt: 5.704 (5.704) Accm: 3.09 (3.09) Acct: 4.89 (4.89) proj_loss: -0.6211 (-0.6211) time: 0.9031 data: 0.0004 [11-26 12:48:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 0/1669] eta: 0:25:07 tlr: 0.00014 tnm: 0.27 Lm: 6.218 (6.218) Lt: 5.457 (5.457) Accm: 4.18 (4.18) Acct: 6.44 (6.44) proj_loss: -0.6272 (-0.6272) time: 0.9030 data: 0.0004 [11-26 12:48:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 0/1669] eta: 0:25:07 tlr: 0.00014 tnm: 0.27 Lm: 6.566 (6.566) Lt: 5.823 (5.823) Accm: 2.94 (2.94) Acct: 4.61 (4.61) proj_loss: -0.6215 (-0.6215) time: 0.9032 data: 0.0004 [11-26 12:48:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 0/1669] eta: 0:25:07 tlr: 0.00014 tnm: 0.27 Lm: 6.427 (6.427) Lt: 5.657 (5.657) Accm: 3.64 (3.64) Acct: 5.92 (5.92) proj_loss: -0.6134 (-0.6134) time: 0.9032 data: 0.0004 [11-26 12:48:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 0/1669] eta: 0:25:07 tlr: 0.00014 tnm: 0.27 Lm: 6.730 (6.730) Lt: 6.037 (6.037) Accm: 2.70 (2.70) Acct: 4.37 (4.37) proj_loss: -0.6120 (-0.6120) time: 0.9033 data: 0.0004 [11-26 12:48:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 0/1669] eta: 0:25:06 tlr: 0.00014 tnm: 0.27 Lm: 6.252 (6.252) Lt: 5.489 (5.489) Accm: 3.99 (3.99) Acct: 5.82 (5.82) proj_loss: -0.6691 (-0.6691) time: 0.9025 data: 0.0004 [11-26 12:54:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.26 Lm: 6.229 (6.229) Lt: 5.520 (5.520) Accm: 4.08 (4.08) Acct: 6.03 (6.03) proj_loss: -0.6511 (-0.6511) time: 0.9242 data: 0.0002 [11-26 12:54:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.26 Lm: 6.336 (6.336) Lt: 5.571 (5.571) Accm: 3.79 (3.79) Acct: 6.13 (6.13) proj_loss: -0.6084 (-0.6084) time: 0.9242 data: 0.0003 [11-26 12:54:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.26 Lm: 6.401 (6.401) Lt: 5.685 (5.685) Accm: 3.42 (3.42) Acct: 5.22 (5.22) proj_loss: -0.6288 (-0.6288) time: 0.9243 data: 0.0003 [11-26 12:54:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.26 Lm: 6.595 (6.595) Lt: 5.886 (5.886) Accm: 2.84 (2.84) Acct: 4.53 (4.53) proj_loss: -0.6277 (-0.6277) time: 0.9242 data: 0.0002 [11-26 12:54:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.26 Lm: 6.352 (6.352) Lt: 5.577 (5.577) Accm: 3.88 (3.88) Acct: 6.25 (6.25) proj_loss: -0.6280 (-0.6280) time: 0.9243 data: 0.0002 [11-26 12:54:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.26 Lm: 6.538 (6.538) Lt: 5.776 (5.776) Accm: 3.13 (3.13) Acct: 5.01 (5.01) proj_loss: -0.6144 (-0.6144) time: 0.9242 data: 0.0003 [11-26 12:54:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.26 Lm: 6.352 (6.352) Lt: 5.550 (5.550) Accm: 3.74 (3.74) Acct: 5.96 (5.96) proj_loss: -0.6127 (-0.6127) time: 0.9243 data: 0.0003 [11-26 12:54:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.26 Lm: 6.457 (6.457) Lt: 5.728 (5.728) Accm: 3.41 (3.41) Acct: 5.46 (5.46) proj_loss: -0.6281 (-0.6281) time: 0.9243 data: 0.0002 [11-26 13:01:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.487 (6.483) Lt: 5.704 (5.720) Accm: 3.18 (3.29) Acct: 5.03 (5.31) proj_loss: -0.6134 (-0.6139) time: 0.9298 data: 0.0002 [11-26 13:01:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.302 (6.316) Lt: 5.571 (5.544) Accm: 3.90 (3.96) Acct: 6.23 (6.14) proj_loss: -0.6193 (-0.6180) time: 0.9298 data: 0.0002 [11-26 13:01:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.318 (6.329) Lt: 5.572 (5.580) Accm: 3.67 (3.72) Acct: 5.41 (5.77) proj_loss: -0.6206 (-0.6231) time: 0.9298 data: 0.0003 [11-26 13:01:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.252 (6.244) Lt: 5.550 (5.531) Accm: 4.17 (4.17) Acct: 6.23 (6.26) proj_loss: -0.6691 (-0.6640) time: 0.9298 data: 0.0002 [11-26 13:01:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.538 (6.576) Lt: 5.899 (5.890) Accm: 2.99 (2.99) Acct: 4.68 (4.58) proj_loss: -0.6288 (-0.6280) time: 0.9298 data: 0.0003 [11-26 13:01:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.566 (6.568) Lt: 5.823 (5.854) Accm: 3.31 (3.21) Acct: 4.86 (4.96) proj_loss: -0.6215 (-0.6187) time: 0.9298 data: 0.0003 [11-26 13:01:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.454 (6.389) Lt: 5.686 (5.657) Accm: 3.39 (3.57) Acct: 5.82 (5.74) proj_loss: -0.6176 (-0.6115) time: 0.9298 data: 0.0003 [11-26 13:01:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.399 (6.377) Lt: 5.666 (5.651) Accm: 3.58 (3.47) Acct: 5.54 (5.33) proj_loss: -0.6211 (-0.6208) time: 0.9298 data: 0.0003 [11-26 13:07:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.401 (6.459) Lt: 5.685 (5.749) Accm: 3.34 (3.25) Acct: 5.22 (5.01) proj_loss: -0.6270 (-0.6239) time: 0.9253 data: 0.0002 [11-26 13:07:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.485 (6.483) Lt: 5.681 (5.701) Accm: 3.12 (3.22) Acct: 5.01 (5.18) proj_loss: -0.6062 (-0.6102) time: 0.9253 data: 0.0002 [11-26 13:07:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.474 (6.415) Lt: 5.713 (5.678) Accm: 3.28 (3.47) Acct: 5.51 (5.60) proj_loss: -0.6162 (-0.6123) time: 0.9253 data: 0.0002 [11-26 13:07:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.300 (6.311) Lt: 5.550 (5.556) Accm: 3.81 (3.77) Acct: 5.97 (5.97) proj_loss: -0.6253 (-0.6248) time: 0.9253 data: 0.0003 [11-26 13:07:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.273 (6.284) Lt: 5.524 (5.496) Accm: 3.88 (3.91) Acct: 6.08 (6.03) proj_loss: -0.6170 (-0.6172) time: 0.9253 data: 0.0003 [11-26 13:07:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.263 (6.353) Lt: 5.552 (5.667) Accm: 4.08 (3.82) Acct: 6.03 (5.71) proj_loss: -0.6705 (-0.6660) time: 0.9253 data: 0.0002 [11-26 13:07:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.498 (6.504) Lt: 5.817 (5.792) Accm: 3.13 (3.19) Acct: 4.68 (4.94) proj_loss: -0.6204 (-0.6209) time: 0.9253 data: 0.0003 [11-26 13:07:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.538 (6.509) Lt: 5.776 (5.773) Accm: 3.34 (3.35) Acct: 5.13 (5.13) proj_loss: -0.6144 (-0.6093) time: 0.9253 data: 0.0003 [11-26 13:14:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.28 Lm: 6.302 (6.353) Lt: 5.571 (5.568) Accm: 3.85 (3.68) Acct: 5.92 (5.67) proj_loss: -0.6171 (-0.6172) time: 0.9267 data: 0.0015 [11-26 13:14:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.28 Lm: 6.483 (6.442) Lt: 5.657 (5.654) Accm: 3.18 (3.38) Acct: 5.03 (5.30) proj_loss: -0.6134 (-0.6148) time: 0.9268 data: 0.0014 [11-26 13:14:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.28 Lm: 6.318 (6.332) Lt: 5.572 (5.569) Accm: 3.67 (3.65) Acct: 5.41 (5.71) proj_loss: -0.6206 (-0.6212) time: 0.9268 data: 0.0016 [11-26 13:14:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.28 Lm: 6.454 (6.396) Lt: 5.686 (5.645) Accm: 3.39 (3.57) Acct: 5.82 (5.76) proj_loss: -0.6149 (-0.6101) time: 0.9267 data: 0.0019 [11-26 13:14:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.28 Lm: 6.566 (6.537) Lt: 5.823 (5.796) Accm: 3.31 (3.24) Acct: 4.86 (5.00) proj_loss: -0.6073 (-0.6068) time: 0.9268 data: 0.0015 [11-26 13:14:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.28 Lm: 6.459 (6.455) Lt: 5.735 (5.737) Accm: 3.28 (3.39) Acct: 4.68 (5.16) proj_loss: -0.6120 (-0.6178) time: 0.9268 data: 0.0017 [11-26 13:14:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.28 Lm: 6.402 (6.456) Lt: 5.691 (5.737) Accm: 3.29 (3.25) Acct: 5.20 (5.05) proj_loss: -0.6211 (-0.6193) time: 0.9267 data: 0.0016 [11-26 13:14:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 162/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.28 Lm: 6.252 (6.304) Lt: 5.550 (5.590) Accm: 4.17 (3.97) Acct: 6.23 (6.07) proj_loss: -0.6691 (-0.6595) time: 0.9268 data: 0.0016 [11-26 13:14:09] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 162/350] Total time: 0:25:48 (0.928 s / it) [11-26 13:14:09] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 162/350] Total time: 0:25:48 (0.928 s / it) [11-26 13:14:09] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 162/350] Total time: 0:25:48 (0.928 s / it) [11-26 13:14:09] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 162/350] Total time: 0:25:48 (0.928 s / it) [11-26 13:14:09] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 162/350] Total time: 0:25:48 (0.928 s / it) [11-26 13:14:09] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 162/350] Total time: 0:25:48 (0.928 s / it) [11-26 13:14:09] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 162/350] Total time: 0:25:48 (0.928 s / it) [11-26 13:14:09] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 162/350] Total time: 0:25:48 (0.928 s / it) [11-26 13:14:09] (/home/user/VAR/train.py , line 276)=> [ep162] (training ) Lm: 6.424 (6.424), Lt: 5.664 (5.664), Acc m&t: 3.58 5.61, Remain: 3 days, 8:52:15, Finish: 2024-11-29 06:06 [11-26 13:14:09] (/home/user/VAR/train.py , line 276)=> [ep162] (training ) Lm: 6.424 (6.424), Lt: 5.664 (5.664), Acc m&t: 3.58 5.61, Remain: 3 days, 8:51:44, Finish: 2024-11-29 06:05 [11-26 13:14:09] (/home/user/VAR/train.py , line 276)=> [ep162] (training ) Lm: 6.424 (6.424), Lt: 5.664 (5.664), Acc m&t: 3.58 5.61, Remain: 3 days, 8:50:59, Finish: 2024-11-29 06:05 [11-26 13:14:09] (/home/user/VAR/train.py , line 276)=> [ep162] (training ) Lm: 6.424 (6.424), Lt: 5.664 (5.664), Acc m&t: 3.58 5.61, Remain: 3 days, 8:50:49, Finish: 2024-11-29 06:04 [11-26 13:14:09] (/home/user/VAR/train.py , line 276)=> [ep162] (training ) Lm: 6.424 (6.424), Lt: 5.664 (5.664), Acc m&t: 3.58 5.61, Remain: 3 days, 8:51:09, Finish: 2024-11-29 06:05 [11-26 13:14:09] (/home/user/VAR/train.py , line 276)=> [ep162] (training ) Lm: 6.424 (6.424), Lt: 5.664 (5.664), Acc m&t: 3.58 5.61, Remain: 3 days, 8:52:18, Finish: 2024-11-29 06:06 [11-26 13:14:09] (/home/user/VAR/train.py , line 276)=> [ep162] (training ) Lm: 6.424 (6.424), Lt: 5.664 (5.664), Acc m&t: 3.58 5.61, Remain: 3 days, 8:52:13, Finish: 2024-11-29 06:06 [11-26 13:14:09] (/home/user/VAR/train.py , line 276)=> [ep162] (training ) Lm: 6.424 (6.424), Lt: 5.664 (5.664), Acc m&t: 3.58 5.61, Remain: 3 days, 8:50:36, Finish: 2024-11-29 06:04 [11-26 13:14:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 0/1669] eta: 0:24:46 tlr: 0.00014 tnm: 0.26 Lm: 6.607 (6.607) Lt: 5.865 (5.865) Accm: 2.94 (2.94) Acct: 4.51 (4.51) proj_loss: -0.6327 (-0.6327) time: 0.8907 data: 0.0004 [11-26 13:14:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 0/1669] eta: 0:24:46 tlr: 0.00014 tnm: 0.26 Lm: 6.450 (6.450) Lt: 5.674 (5.674) Accm: 3.42 (3.42) Acct: 4.92 (4.92) proj_loss: -0.6273 (-0.6273) time: 0.8907 data: 0.0004 [11-26 13:14:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 0/1669] eta: 0:24:47 tlr: 0.00014 tnm: 0.26 Lm: 6.438 (6.438) Lt: 5.700 (5.700) Accm: 3.22 (3.22) Acct: 4.99 (4.99) proj_loss: -0.6085 (-0.6085) time: 0.8910 data: 0.0003 [11-26 13:14:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 0/1669] eta: 0:24:47 tlr: 0.00014 tnm: 0.26 Lm: 6.333 (6.333) Lt: 5.650 (5.650) Accm: 3.80 (3.80) Acct: 5.03 (5.03) proj_loss: -0.6791 (-0.6791) time: 0.8910 data: 0.0003 [11-26 13:14:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 0/1669] eta: 0:24:47 tlr: 0.00014 tnm: 0.26 Lm: 6.249 (6.249) Lt: 5.429 (5.429) Accm: 4.22 (4.22) Acct: 6.82 (6.82) proj_loss: -0.6286 (-0.6286) time: 0.8911 data: 0.0004 [11-26 13:14:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 0/1669] eta: 0:24:46 tlr: 0.00014 tnm: 0.26 Lm: 6.553 (6.553) Lt: 5.803 (5.803) Accm: 3.39 (3.39) Acct: 5.23 (5.23) proj_loss: -0.6203 (-0.6203) time: 0.8904 data: 0.0004 [11-26 13:14:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 0/1669] eta: 0:24:47 tlr: 0.00014 tnm: 0.26 Lm: 6.322 (6.322) Lt: 5.443 (5.443) Accm: 3.92 (3.92) Acct: 6.65 (6.65) proj_loss: -0.5983 (-0.5983) time: 0.8915 data: 0.0004 [11-26 13:14:10] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 0/1669] eta: 0:24:50 tlr: 0.00014 tnm: 0.26 Lm: 6.321 (6.321) Lt: 5.589 (5.589) Accm: 4.20 (4.20) Acct: 6.13 (6.13) proj_loss: -0.6385 (-0.6385) time: 0.8933 data: 0.0004 [11-26 13:20:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 417/1669] eta: 0:19:18 tlr: 0.00014 tnm: 0.26 Lm: 6.367 (6.367) Lt: 5.566 (5.566) Accm: 4.05 (4.05) Acct: 6.10 (6.10) proj_loss: -0.6257 (-0.6257) time: 0.9250 data: 0.0002 [11-26 13:20:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 417/1669] eta: 0:19:18 tlr: 0.00014 tnm: 0.26 Lm: 6.306 (6.306) Lt: 5.523 (5.523) Accm: 3.97 (3.97) Acct: 6.34 (6.34) proj_loss: -0.6389 (-0.6389) time: 0.9250 data: 0.0003 [11-26 13:20:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 417/1669] eta: 0:19:18 tlr: 0.00014 tnm: 0.26 Lm: 6.574 (6.574) Lt: 5.790 (5.790) Accm: 3.26 (3.26) Acct: 5.10 (5.10) proj_loss: -0.6169 (-0.6169) time: 0.9250 data: 0.0002 [11-26 13:20:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 417/1669] eta: 0:19:18 tlr: 0.00014 tnm: 0.26 Lm: 6.512 (6.512) Lt: 5.741 (5.741) Accm: 3.31 (3.31) Acct: 5.23 (5.23) proj_loss: -0.6117 (-0.6117) time: 0.9250 data: 0.0003 [11-26 13:20:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 417/1669] eta: 0:19:18 tlr: 0.00014 tnm: 0.26 Lm: 6.569 (6.569) Lt: 5.812 (5.812) Accm: 3.16 (3.16) Acct: 4.73 (4.73) proj_loss: -0.6088 (-0.6088) time: 0.9250 data: 0.0003 [11-26 13:20:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 417/1669] eta: 0:19:18 tlr: 0.00014 tnm: 0.26 Lm: 6.518 (6.518) Lt: 5.799 (5.799) Accm: 3.43 (3.43) Acct: 5.22 (5.22) proj_loss: -0.6211 (-0.6211) time: 0.9250 data: 0.0002 [11-26 13:20:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 417/1669] eta: 0:19:18 tlr: 0.00014 tnm: 0.26 Lm: 6.391 (6.391) Lt: 5.592 (5.592) Accm: 3.69 (3.69) Acct: 6.06 (6.06) proj_loss: -0.6051 (-0.6051) time: 0.9250 data: 0.0003 [11-26 13:20:35] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 417/1669] eta: 0:19:18 tlr: 0.00014 tnm: 0.26 Lm: 6.532 (6.532) Lt: 5.795 (5.795) Accm: 3.36 (3.36) Acct: 4.98 (4.98) proj_loss: -0.6360 (-0.6360) time: 0.9250 data: 0.0003 [11-26 13:27:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.26 Lm: 6.333 (6.408) Lt: 5.650 (5.648) Accm: 3.80 (3.76) Acct: 5.03 (5.67) proj_loss: -0.6259 (-0.6326) time: 0.9259 data: 0.0003 [11-26 13:27:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.26 Lm: 6.429 (6.466) Lt: 5.733 (5.767) Accm: 3.83 (3.56) Acct: 5.92 (5.45) proj_loss: -0.6327 (-0.6272) time: 0.9258 data: 0.0002 [11-26 13:27:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.26 Lm: 6.321 (6.287) Lt: 5.543 (5.487) Accm: 4.20 (4.22) Acct: 6.13 (6.46) proj_loss: -0.6129 (-0.6151) time: 0.9259 data: 0.0002 [11-26 13:27:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.26 Lm: 6.450 (6.450) Lt: 5.674 (5.708) Accm: 3.42 (3.60) Acct: 4.92 (5.56) proj_loss: -0.6273 (-0.6230) time: 0.9259 data: 0.0003 [11-26 13:27:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.26 Lm: 6.553 (6.522) Lt: 5.776 (5.706) Accm: 3.39 (3.42) Acct: 5.23 (5.41) proj_loss: -0.6175 (-0.6171) time: 0.9259 data: 0.0003 [11-26 13:27:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.26 Lm: 6.490 (6.505) Lt: 5.720 (5.734) Accm: 3.22 (3.27) Acct: 4.99 (5.11) proj_loss: -0.6150 (-0.6128) time: 0.9259 data: 0.0002 [11-26 13:27:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.26 Lm: 6.364 (6.369) Lt: 5.617 (5.586) Accm: 3.89 (3.94) Acct: 5.85 (6.12) proj_loss: -0.6286 (-0.6293) time: 0.9259 data: 0.0002 [11-26 13:27:01] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.26 Lm: 6.410 (6.398) Lt: 5.614 (5.599) Accm: 3.51 (3.63) Acct: 5.85 (5.99) proj_loss: -0.6105 (-0.6069) time: 0.9259 data: 0.0003 [11-26 13:33:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [1251/1669] eta: 0:06:28 tlr: 0.00014 tnm: 0.26 Lm: 6.366 (6.374) Lt: 5.584 (5.588) Accm: 3.67 (3.68) Acct: 5.96 (6.01) proj_loss: -0.6097 (-0.6074) time: 0.9263 data: 0.0003 [11-26 13:33:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [1251/1669] eta: 0:06:28 tlr: 0.00014 tnm: 0.26 Lm: 6.497 (6.491) Lt: 5.748 (5.766) Accm: 3.59 (3.51) Acct: 5.34 (5.28) proj_loss: -0.6211 (-0.6206) time: 0.9263 data: 0.0002 [11-26 13:33:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [1251/1669] eta: 0:06:28 tlr: 0.00014 tnm: 0.26 Lm: 6.346 (6.398) Lt: 5.587 (5.634) Accm: 3.85 (3.77) Acct: 5.91 (5.89) proj_loss: -0.6388 (-0.6298) time: 0.9263 data: 0.0002 [11-26 13:33:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [1251/1669] eta: 0:06:28 tlr: 0.00014 tnm: 0.26 Lm: 6.405 (6.425) Lt: 5.704 (5.675) Accm: 3.51 (3.63) Acct: 4.98 (5.45) proj_loss: -0.6249 (-0.6304) time: 0.9263 data: 0.0003 [11-26 13:33:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [1251/1669] eta: 0:06:28 tlr: 0.00014 tnm: 0.26 Lm: 6.365 (6.317) Lt: 5.547 (5.503) Accm: 4.05 (4.04) Acct: 6.10 (6.31) proj_loss: -0.6092 (-0.6127) time: 0.9263 data: 0.0003 [11-26 13:33:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [1251/1669] eta: 0:06:28 tlr: 0.00014 tnm: 0.26 Lm: 6.485 (6.436) Lt: 5.657 (5.628) Accm: 3.56 (3.71) Acct: 5.63 (5.71) proj_loss: -0.6189 (-0.6196) time: 0.9263 data: 0.0002 [11-26 13:33:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [1251/1669] eta: 0:06:28 tlr: 0.00014 tnm: 0.26 Lm: 6.464 (6.428) Lt: 5.710 (5.652) Accm: 3.31 (3.54) Acct: 5.23 (5.54) proj_loss: -0.6133 (-0.6125) time: 0.9264 data: 0.0003 [11-26 13:33:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [1251/1669] eta: 0:06:28 tlr: 0.00014 tnm: 0.26 Lm: 6.414 (6.393) Lt: 5.665 (5.621) Accm: 3.80 (3.77) Acct: 5.77 (5.88) proj_loss: -0.6278 (-0.6287) time: 0.9264 data: 0.0003 [11-26 13:39:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.364 (6.386) Lt: 5.617 (5.602) Accm: 3.72 (3.74) Acct: 5.68 (5.82) proj_loss: -0.6269 (-0.6236) time: 0.9270 data: 0.0016 [11-26 13:39:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 163/350] Total time: 0:25:48 (0.928 s / it) [11-26 13:39:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.449 (6.408) Lt: 5.662 (5.640) Accm: 3.45 (3.71) Acct: 5.58 (5.83) proj_loss: -0.6273 (-0.6256) time: 0.9270 data: 0.0015 [11-26 13:39:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.410 (6.356) Lt: 5.551 (5.568) Accm: 3.90 (3.83) Acct: 6.06 (5.96) proj_loss: -0.6129 (-0.6153) time: 0.9270 data: 0.0016 [11-26 13:39:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.429 (6.470) Lt: 5.733 (5.732) Accm: 3.66 (3.54) Acct: 5.92 (5.43) proj_loss: -0.6327 (-0.6235) time: 0.9270 data: 0.0016 [11-26 13:39:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.417 (6.417) Lt: 5.560 (5.614) Accm: 3.73 (3.75) Acct: 6.03 (5.79) proj_loss: -0.6203 (-0.6223) time: 0.9270 data: 0.0021 [11-26 13:39:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.438 (6.378) Lt: 5.700 (5.598) Accm: 3.41 (3.71) Acct: 5.48 (5.82) proj_loss: -0.6150 (-0.6159) time: 0.9270 data: 0.0016 [11-26 13:39:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.429 (6.426) Lt: 5.659 (5.672) Accm: 3.26 (3.55) Acct: 4.92 (5.34) proj_loss: -0.6240 (-0.6224) time: 0.9270 data: 0.0014 [11-26 13:39:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 163/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.322 (6.317) Lt: 5.553 (5.518) Accm: 3.83 (3.94) Acct: 6.06 (6.36) proj_loss: -0.6105 (-0.6089) time: 0.9270 data: 0.0016 [11-26 13:39:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 163/350] Total time: 0:25:48 (0.928 s / it) [11-26 13:39:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 163/350] Total time: 0:25:48 (0.928 s / it) [11-26 13:39:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 163/350] Total time: 0:25:48 (0.928 s / it) [11-26 13:39:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 163/350] Total time: 0:25:48 (0.928 s / it) [11-26 13:39:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 163/350] Total time: 0:25:48 (0.928 s / it) [11-26 13:39:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 163/350] Total time: 0:25:48 (0.928 s / it) [11-26 13:39:58] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 163/350] Total time: 0:25:48 (0.928 s / it) [11-26 13:39:58] (/home/user/VAR/train.py , line 276)=> [ep163] (training ) Lm: 6.424 (6.450), Lt: 5.664 (5.696), Acc m&t: 3.58 5.61, Remain: 3 days, 8:25:45, Finish: 2024-11-29 06:05 [11-26 13:39:58] (/home/user/VAR/train.py , line 276)=> [ep163] (training ) Lm: 6.424 (6.450), Lt: 5.664 (5.696), Acc m&t: 3.58 5.61, Remain: 3 days, 8:25:22, Finish: 2024-11-29 06:05 [11-26 13:39:58] (/home/user/VAR/train.py , line 276)=> [ep163] (training ) Lm: 6.424 (6.450), Lt: 5.664 (5.696), Acc m&t: 3.58 5.61, Remain: 3 days, 8:26:38, Finish: 2024-11-29 06:06 [11-26 13:39:58] (/home/user/VAR/train.py , line 276)=> [ep163] (training ) Lm: 6.424 (6.450), Lt: 5.664 (5.696), Acc m&t: 3.58 5.61, Remain: 3 days, 8:26:43, Finish: 2024-11-29 06:06 [11-26 13:39:58] (/home/user/VAR/train.py , line 276)=> [ep163] (training ) Lm: 6.424 (6.450), Lt: 5.664 (5.696), Acc m&t: 3.58 5.61, Remain: 3 days, 8:26:44, Finish: 2024-11-29 06:06 [11-26 13:39:58] (/home/user/VAR/train.py , line 276)=> [ep163] (training ) Lm: 6.424 (6.450), Lt: 5.664 (5.696), Acc m&t: 3.58 5.61, Remain: 3 days, 8:25:17, Finish: 2024-11-29 06:05 [11-26 13:39:58] (/home/user/VAR/train.py , line 276)=> [ep163] (training ) Lm: 6.424 (6.450), Lt: 5.664 (5.696), Acc m&t: 3.58 5.61, Remain: 3 days, 8:25:50, Finish: 2024-11-29 06:05 [11-26 13:39:58] (/home/user/VAR/train.py , line 276)=> [ep163] (training ) Lm: 6.424 (6.450), Lt: 5.664 (5.696), Acc m&t: 3.58 5.61, Remain: 3 days, 8:25:58, Finish: 2024-11-29 06:05 [11-26 13:39:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 0/1669] eta: 0:25:12 tlr: 0.00014 tnm: 0.26 Lm: 6.401 (6.401) Lt: 5.745 (5.745) Accm: 3.55 (3.55) Acct: 5.27 (5.27) proj_loss: -0.6112 (-0.6112) time: 0.9063 data: 0.0004 [11-26 13:39:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 0/1669] eta: 0:25:14 tlr: 0.00014 tnm: 0.26 Lm: 6.507 (6.507) Lt: 5.788 (5.788) Accm: 3.51 (3.51) Acct: 5.61 (5.61) proj_loss: -0.6035 (-0.6035) time: 0.9073 data: 0.0004 [11-26 13:39:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 0/1669] eta: 0:25:14 tlr: 0.00014 tnm: 0.26 Lm: 6.575 (6.575) Lt: 5.840 (5.840) Accm: 3.32 (3.32) Acct: 5.79 (5.79) proj_loss: -0.6499 (-0.6499) time: 0.9072 data: 0.0003 [11-26 13:39:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 0/1669] eta: 0:25:14 tlr: 0.00014 tnm: 0.26 Lm: 6.427 (6.427) Lt: 5.652 (5.652) Accm: 3.39 (3.39) Acct: 5.34 (5.34) proj_loss: -0.5919 (-0.5919) time: 0.9072 data: 0.0004 [11-26 13:39:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 0/1669] eta: 0:25:13 tlr: 0.00014 tnm: 0.26 Lm: 6.424 (6.424) Lt: 5.620 (5.620) Accm: 3.58 (3.58) Acct: 5.58 (5.58) proj_loss: -0.6000 (-0.6000) time: 0.9069 data: 0.0004 [11-26 13:39:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 0/1669] eta: 0:25:14 tlr: 0.00014 tnm: 0.26 Lm: 6.345 (6.345) Lt: 5.623 (5.623) Accm: 4.28 (4.28) Acct: 6.34 (6.34) proj_loss: -0.6571 (-0.6571) time: 0.9073 data: 0.0004 [11-26 13:39:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 0/1669] eta: 0:25:14 tlr: 0.00014 tnm: 0.26 Lm: 6.484 (6.484) Lt: 5.759 (5.759) Accm: 3.19 (3.19) Acct: 4.86 (4.86) proj_loss: -0.5999 (-0.5999) time: 0.9074 data: 0.0003 [11-26 13:39:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 0/1669] eta: 0:25:13 tlr: 0.00014 tnm: 0.26 Lm: 6.386 (6.386) Lt: 5.535 (5.535) Accm: 3.19 (3.19) Acct: 5.44 (5.44) proj_loss: -0.6266 (-0.6266) time: 0.9070 data: 0.0003 [11-26 13:46:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.449 (6.449) Lt: 5.678 (5.678) Accm: 3.43 (3.43) Acct: 5.46 (5.46) proj_loss: -0.6137 (-0.6137) time: 0.9260 data: 0.0002 [11-26 13:46:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.459 (6.459) Lt: 5.720 (5.720) Accm: 3.55 (3.55) Acct: 5.42 (5.42) proj_loss: -0.6278 (-0.6278) time: 0.9260 data: 0.0002 [11-26 13:46:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.560 (6.560) Lt: 5.807 (5.807) Accm: 3.06 (3.06) Acct: 5.11 (5.11) proj_loss: -0.6365 (-0.6365) time: 0.9260 data: 0.0002 [11-26 13:46:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.509 (6.509) Lt: 5.782 (5.782) Accm: 3.33 (3.33) Acct: 5.20 (5.20) proj_loss: -0.6117 (-0.6117) time: 0.9260 data: 0.0003 [11-26 13:46:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.447 (6.447) Lt: 5.675 (5.675) Accm: 3.43 (3.43) Acct: 5.37 (5.37) proj_loss: -0.6149 (-0.6149) time: 0.9260 data: 0.0003 [11-26 13:46:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.527 (6.527) Lt: 5.799 (5.799) Accm: 3.02 (3.02) Acct: 4.68 (4.68) proj_loss: -0.5972 (-0.5972) time: 0.9260 data: 0.0003 [11-26 13:46:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.413 (6.413) Lt: 5.716 (5.716) Accm: 3.67 (3.67) Acct: 5.61 (5.61) proj_loss: -0.6263 (-0.6263) time: 0.9260 data: 0.0002 [11-26 13:46:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.407 (6.407) Lt: 5.684 (5.684) Accm: 3.87 (3.87) Acct: 5.77 (5.77) proj_loss: -0.6544 (-0.6544) time: 0.9260 data: 0.0003 [11-26 13:52:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.28 Lm: 6.469 (6.430) Lt: 5.676 (5.682) Accm: 3.45 (3.69) Acct: 5.23 (5.59) proj_loss: -0.6517 (-0.6486) time: 0.9213 data: 0.0003 [11-26 13:52:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.28 Lm: 6.427 (6.439) Lt: 5.652 (5.667) Accm: 3.47 (3.46) Acct: 5.41 (5.51) proj_loss: -0.6379 (-0.6259) time: 0.9213 data: 0.0002 [11-26 13:52:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.28 Lm: 6.410 (6.412) Lt: 5.688 (5.689) Accm: 3.55 (3.60) Acct: 5.68 (5.64) proj_loss: -0.6117 (-0.6214) time: 0.9213 data: 0.0002 [11-26 13:52:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.28 Lm: 6.545 (6.442) Lt: 5.774 (5.660) Accm: 3.32 (3.67) Acct: 5.79 (6.07) proj_loss: -0.6231 (-0.6297) time: 0.9213 data: 0.0002 [11-26 13:52:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.28 Lm: 6.569 (6.541) Lt: 5.809 (5.803) Accm: 2.93 (2.99) Acct: 4.51 (4.61) proj_loss: -0.5945 (-0.5903) time: 0.9213 data: 0.0003 [11-26 13:52:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.28 Lm: 6.448 (6.456) Lt: 5.651 (5.686) Accm: 3.53 (3.54) Acct: 5.61 (5.61) proj_loss: -0.6145 (-0.6234) time: 0.9213 data: 0.0002 [11-26 13:52:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.28 Lm: 6.441 (6.486) Lt: 5.679 (5.747) Accm: 3.58 (3.42) Acct: 5.58 (5.51) proj_loss: -0.6148 (-0.6127) time: 0.9213 data: 0.0002 [11-26 13:52:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [ 834/1669] eta: 0:12:51 tlr: 0.00014 tnm: 0.28 Lm: 6.513 (6.549) Lt: 5.821 (5.791) Accm: 3.19 (3.16) Acct: 5.44 (5.18) proj_loss: -0.6266 (-0.6222) time: 0.9213 data: 0.0002 [11-26 13:59:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.27 Lm: 6.406 (6.383) Lt: 5.660 (5.657) Accm: 3.67 (3.67) Acct: 5.82 (5.73) proj_loss: -0.6240 (-0.6251) time: 0.9250 data: 0.0002 [11-26 13:59:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.27 Lm: 6.392 (6.392) Lt: 5.604 (5.604) Accm: 3.63 (3.74) Acct: 6.22 (6.22) proj_loss: -0.6202 (-0.6266) time: 0.9250 data: 0.0002 [11-26 13:59:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.27 Lm: 6.472 (6.445) Lt: 5.708 (5.696) Accm: 3.39 (3.57) Acct: 5.27 (5.52) proj_loss: -0.6443 (-0.6405) time: 0.9250 data: 0.0003 [11-26 13:59:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.27 Lm: 6.435 (6.447) Lt: 5.635 (5.666) Accm: 3.52 (3.51) Acct: 5.79 (5.70) proj_loss: -0.6276 (-0.6277) time: 0.9250 data: 0.0002 [11-26 13:59:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.27 Lm: 6.527 (6.490) Lt: 5.784 (5.705) Accm: 3.06 (3.26) Acct: 4.68 (5.11) proj_loss: -0.5919 (-0.5901) time: 0.9250 data: 0.0002 [11-26 13:59:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.27 Lm: 6.425 (6.426) Lt: 5.652 (5.659) Accm: 3.49 (3.57) Acct: 5.60 (5.65) proj_loss: -0.6360 (-0.6279) time: 0.9250 data: 0.0002 [11-26 13:59:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.27 Lm: 6.432 (6.468) Lt: 5.659 (5.720) Accm: 3.39 (3.37) Acct: 5.20 (5.34) proj_loss: -0.6191 (-0.6166) time: 0.9250 data: 0.0002 [11-26 13:59:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [1251/1669] eta: 0:06:26 tlr: 0.00014 tnm: 0.27 Lm: 6.569 (6.568) Lt: 5.903 (5.840) Accm: 2.93 (3.04) Acct: 5.03 (4.86) proj_loss: -0.6288 (-0.6244) time: 0.9251 data: 0.0002 [11-26 14:05:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.513 (6.544) Lt: 5.821 (5.795) Accm: 3.12 (3.05) Acct: 5.20 (4.93) proj_loss: -0.6310 (-0.6290) time: 0.9281 data: 0.0015 [11-26 14:05:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 164/350] Total time: 0:25:43 (0.925 s / it) [11-26 14:05:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.484 (6.486) Lt: 5.759 (5.691) Accm: 3.19 (3.26) Acct: 4.86 (5.10) proj_loss: -0.5892 (-0.5854) time: 0.9281 data: 0.0017 [11-26 14:05:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.423 (6.413) Lt: 5.652 (5.660) Accm: 3.51 (3.60) Acct: 5.79 (5.71) proj_loss: -0.6379 (-0.6326) time: 0.9281 data: 0.0016 [11-26 14:05:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.401 (6.334) Lt: 5.633 (5.602) Accm: 3.79 (3.84) Acct: 5.96 (5.94) proj_loss: -0.6150 (-0.6231) time: 0.9281 data: 0.0016 [11-26 14:05:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.357 (6.385) Lt: 5.525 (5.588) Accm: 3.64 (3.72) Acct: 5.79 (6.11) proj_loss: -0.6231 (-0.6270) time: 0.9281 data: 0.0016 [11-26 14:05:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.476 (6.459) Lt: 5.741 (5.725) Accm: 3.32 (3.52) Acct: 5.30 (5.48) proj_loss: -0.6517 (-0.6432) time: 0.9281 data: 0.0020 [11-26 14:05:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.441 (6.475) Lt: 5.679 (5.744) Accm: 3.32 (3.36) Acct: 5.06 (5.28) proj_loss: -0.6188 (-0.6171) time: 0.9281 data: 0.0017 [11-26 14:05:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 164/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.448 (6.452) Lt: 5.645 (5.662) Accm: 3.51 (3.50) Acct: 5.85 (5.73) proj_loss: -0.6145 (-0.6234) time: 0.9281 data: 0.0018 [11-26 14:05:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 164/350] Total time: 0:25:43 (0.925 s / it) [11-26 14:05:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 164/350] Total time: 0:25:43 (0.925 s / it) [11-26 14:05:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 164/350] Total time: 0:25:43 (0.925 s / it) [11-26 14:05:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 164/350] Total time: 0:25:43 (0.925 s / it) [11-26 14:05:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 164/350] Total time: 0:25:43 (0.925 s / it) [11-26 14:05:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 164/350] Total time: 0:25:43 (0.925 s / it) [11-26 14:05:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 164/350] Total time: 0:25:43 (0.925 s / it) [11-26 14:05:41] (/home/user/VAR/train.py , line 276)=> [ep164] (training ) Lm: 6.424 (6.446), Lt: 5.664 (5.689), Acc m&t: 3.58 5.61, Remain: 3 days, 8:06:44, Finish: 2024-11-29 06:12 [11-26 14:05:41] (/home/user/VAR/train.py , line 276)=> [ep164] (training ) Lm: 6.424 (6.446), Lt: 5.664 (5.689), Acc m&t: 3.58 5.61, Remain: 3 days, 8:08:11, Finish: 2024-11-29 06:13 [11-26 14:05:41] (/home/user/VAR/train.py , line 276)=> [ep164] (training ) Lm: 6.424 (6.446), Lt: 5.664 (5.689), Acc m&t: 3.58 5.61, Remain: 3 days, 8:09:38, Finish: 2024-11-29 06:15 [11-26 14:05:41] (/home/user/VAR/train.py , line 276)=> [ep164] (training ) Lm: 6.424 (6.446), Lt: 5.664 (5.689), Acc m&t: 3.58 5.61, Remain: 3 days, 8:07:36, Finish: 2024-11-29 06:13 [11-26 14:05:41] (/home/user/VAR/train.py , line 276)=> [ep164] (training ) Lm: 6.424 (6.446), Lt: 5.664 (5.689), Acc m&t: 3.58 5.61, Remain: 3 days, 8:07:52, Finish: 2024-11-29 06:13 [11-26 14:05:41] (/home/user/VAR/train.py , line 276)=> [ep164] (training ) Lm: 6.424 (6.446), Lt: 5.664 (5.689), Acc m&t: 3.58 5.61, Remain: 3 days, 8:07:45, Finish: 2024-11-29 06:13 [11-26 14:05:41] (/home/user/VAR/train.py , line 276)=> [ep164] (training ) Lm: 6.424 (6.446), Lt: 5.664 (5.689), Acc m&t: 3.58 5.61, Remain: 3 days, 8:08:25, Finish: 2024-11-29 06:14 [11-26 14:05:41] (/home/user/VAR/train.py , line 276)=> [ep164] (training ) Lm: 6.424 (6.446), Lt: 5.664 (5.689), Acc m&t: 3.58 5.61, Remain: 3 days, 8:09:54, Finish: 2024-11-29 06:15 [11-26 14:05:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 0/1669] eta: 0:25:17 tlr: 0.00014 tnm: 0.27 Lm: 6.183 (6.183) Lt: 5.438 (5.438) Accm: 4.21 (4.21) Acct: 6.30 (6.30) proj_loss: -0.6195 (-0.6195) time: 0.9093 data: 0.0004 [11-26 14:05:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 0/1669] eta: 0:25:19 tlr: 0.00014 tnm: 0.27 Lm: 5.995 (5.995) Lt: 5.213 (5.213) Accm: 5.67 (5.67) Acct: 8.54 (8.54) proj_loss: -0.6088 (-0.6088) time: 0.9101 data: 0.0003 [11-26 14:05:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 0/1669] eta: 0:25:17 tlr: 0.00014 tnm: 0.27 Lm: 6.646 (6.646) Lt: 5.911 (5.911) Accm: 2.97 (2.97) Acct: 4.41 (4.41) proj_loss: -0.6383 (-0.6383) time: 0.9090 data: 0.0008 [11-26 14:05:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 0/1669] eta: 0:25:18 tlr: 0.00014 tnm: 0.27 Lm: 6.415 (6.415) Lt: 5.601 (5.601) Accm: 3.90 (3.90) Acct: 5.96 (5.96) proj_loss: -0.6119 (-0.6119) time: 0.9101 data: 0.0004 [11-26 14:05:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 0/1669] eta: 0:25:19 tlr: 0.00014 tnm: 0.27 Lm: 6.651 (6.651) Lt: 5.868 (5.868) Accm: 3.25 (3.25) Acct: 5.13 (5.13) proj_loss: -0.6240 (-0.6240) time: 0.9103 data: 0.0003 [11-26 14:05:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 0/1669] eta: 0:25:19 tlr: 0.00014 tnm: 0.27 Lm: 6.497 (6.497) Lt: 5.827 (5.827) Accm: 3.45 (3.45) Acct: 5.30 (5.30) proj_loss: -0.6491 (-0.6491) time: 0.9102 data: 0.0004 [11-26 14:05:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 0/1669] eta: 0:25:19 tlr: 0.00014 tnm: 0.27 Lm: 6.445 (6.445) Lt: 5.597 (5.597) Accm: 3.66 (3.66) Acct: 5.79 (5.79) proj_loss: -0.5918 (-0.5918) time: 0.9104 data: 0.0004 [11-26 14:05:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 0/1669] eta: 0:25:19 tlr: 0.00014 tnm: 0.27 Lm: 6.103 (6.103) Lt: 5.293 (5.293) Accm: 4.73 (4.73) Acct: 7.47 (7.47) proj_loss: -0.6393 (-0.6393) time: 0.9107 data: 0.0004 [11-26 14:12:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 417/1669] eta: 0:19:30 tlr: 0.00014 tnm: 0.27 Lm: 6.368 (6.368) Lt: 5.606 (5.606) Accm: 3.93 (3.93) Acct: 6.16 (6.16) proj_loss: -0.6097 (-0.6097) time: 0.9252 data: 0.0002 [11-26 14:12:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 417/1669] eta: 0:19:30 tlr: 0.00014 tnm: 0.27 Lm: 6.228 (6.228) Lt: 5.420 (5.420) Accm: 4.67 (4.67) Acct: 7.25 (7.25) proj_loss: -0.6034 (-0.6034) time: 0.9252 data: 0.0002 [11-26 14:12:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 417/1669] eta: 0:19:30 tlr: 0.00014 tnm: 0.27 Lm: 6.442 (6.442) Lt: 5.635 (5.635) Accm: 3.67 (3.67) Acct: 5.82 (5.82) proj_loss: -0.6232 (-0.6232) time: 0.9252 data: 0.0003 [11-26 14:12:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 417/1669] eta: 0:19:30 tlr: 0.00014 tnm: 0.27 Lm: 6.471 (6.471) Lt: 5.668 (5.668) Accm: 3.51 (3.51) Acct: 5.75 (5.75) proj_loss: -0.6001 (-0.6001) time: 0.9252 data: 0.0003 [11-26 14:12:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 417/1669] eta: 0:19:30 tlr: 0.00014 tnm: 0.27 Lm: 6.511 (6.511) Lt: 5.753 (5.753) Accm: 3.31 (3.31) Acct: 5.29 (5.29) proj_loss: -0.6214 (-0.6214) time: 0.9252 data: 0.0002 [11-26 14:12:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 417/1669] eta: 0:19:30 tlr: 0.00014 tnm: 0.27 Lm: 6.228 (6.228) Lt: 5.451 (5.451) Accm: 4.01 (4.01) Acct: 6.32 (6.32) proj_loss: -0.6224 (-0.6224) time: 0.9252 data: 0.0002 [11-26 14:12:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 417/1669] eta: 0:19:30 tlr: 0.00014 tnm: 0.27 Lm: 6.623 (6.623) Lt: 5.839 (5.839) Accm: 3.38 (3.38) Acct: 5.35 (5.35) proj_loss: -0.6141 (-0.6141) time: 0.9252 data: 0.0003 [11-26 14:12:12] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 417/1669] eta: 0:19:30 tlr: 0.00014 tnm: 0.27 Lm: 6.547 (6.547) Lt: 5.820 (5.820) Accm: 3.41 (3.41) Acct: 5.13 (5.13) proj_loss: -0.6322 (-0.6322) time: 0.9252 data: 0.0003 [11-26 14:18:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 834/1669] eta: 0:12:56 tlr: 0.00014 tnm: 0.26 Lm: 6.448 (6.434) Lt: 5.730 (5.692) Accm: 3.85 (3.65) Acct: 5.85 (5.44) proj_loss: -0.6262 (-0.6293) time: 0.9251 data: 0.0002 [11-26 14:18:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 834/1669] eta: 0:12:56 tlr: 0.00014 tnm: 0.26 Lm: 6.497 (6.502) Lt: 5.700 (5.735) Accm: 3.45 (3.41) Acct: 5.30 (5.29) proj_loss: -0.6042 (-0.6157) time: 0.9251 data: 0.0003 [11-26 14:18:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 834/1669] eta: 0:12:56 tlr: 0.00014 tnm: 0.26 Lm: 6.415 (6.340) Lt: 5.601 (5.527) Accm: 3.90 (3.86) Acct: 5.96 (6.03) proj_loss: -0.6160 (-0.6208) time: 0.9251 data: 0.0002 [11-26 14:18:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 834/1669] eta: 0:12:56 tlr: 0.00014 tnm: 0.26 Lm: 6.257 (6.238) Lt: 5.453 (5.431) Accm: 4.40 (4.58) Acct: 6.89 (7.13) proj_loss: -0.6088 (-0.6192) time: 0.9251 data: 0.0002 [11-26 14:18:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 834/1669] eta: 0:12:56 tlr: 0.00014 tnm: 0.26 Lm: 6.273 (6.314) Lt: 5.465 (5.557) Accm: 3.80 (3.80) Acct: 6.30 (6.05) proj_loss: -0.6252 (-0.6265) time: 0.9251 data: 0.0003 [11-26 14:18:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 834/1669] eta: 0:12:56 tlr: 0.00014 tnm: 0.26 Lm: 6.445 (6.410) Lt: 5.597 (5.630) Accm: 3.66 (3.79) Acct: 5.79 (5.97) proj_loss: -0.6085 (-0.6032) time: 0.9251 data: 0.0003 [11-26 14:18:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 834/1669] eta: 0:12:56 tlr: 0.00014 tnm: 0.26 Lm: 6.595 (6.574) Lt: 5.810 (5.782) Accm: 3.51 (3.44) Acct: 5.58 (5.50) proj_loss: -0.6079 (-0.6120) time: 0.9251 data: 0.0003 [11-26 14:18:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [ 834/1669] eta: 0:12:56 tlr: 0.00014 tnm: 0.26 Lm: 6.125 (6.287) Lt: 5.356 (5.522) Accm: 4.36 (4.07) Acct: 6.68 (6.34) proj_loss: -0.6090 (-0.6095) time: 0.9251 data: 0.0002 [11-26 14:25:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.330 (6.349) Lt: 5.563 (5.584) Accm: 3.74 (3.80) Acct: 5.77 (5.86) proj_loss: -0.6043 (-0.6070) time: 0.9255 data: 0.0002 [11-26 14:25:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.430 (6.428) Lt: 5.691 (5.682) Accm: 3.89 (3.72) Acct: 5.96 (5.62) proj_loss: -0.6248 (-0.6214) time: 0.9256 data: 0.0003 [11-26 14:25:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.536 (6.498) Lt: 5.739 (5.706) Accm: 3.53 (3.63) Acct: 5.68 (5.90) proj_loss: -0.6159 (-0.6165) time: 0.9256 data: 0.0003 [11-26 14:25:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.419 (6.361) Lt: 5.635 (5.572) Accm: 3.69 (3.76) Acct: 5.82 (5.74) proj_loss: -0.6172 (-0.6202) time: 0.9256 data: 0.0002 [11-26 14:25:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.379 (6.374) Lt: 5.617 (5.611) Accm: 3.59 (3.62) Acct: 5.91 (5.78) proj_loss: -0.6224 (-0.6172) time: 0.9256 data: 0.0002 [11-26 14:25:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.489 (6.478) Lt: 5.689 (5.709) Accm: 3.53 (3.52) Acct: 5.30 (5.49) proj_loss: -0.6120 (-0.6167) time: 0.9256 data: 0.0002 [11-26 14:25:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.421 (6.407) Lt: 5.643 (5.644) Accm: 3.59 (3.72) Acct: 5.75 (5.75) proj_loss: -0.6089 (-0.6060) time: 0.9255 data: 0.0002 [11-26 14:25:03] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.340 (6.284) Lt: 5.540 (5.503) Accm: 4.04 (4.33) Acct: 6.42 (6.76) proj_loss: -0.6178 (-0.6211) time: 0.9255 data: 0.0002 [11-26 14:31:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.27 Lm: 6.423 (6.356) Lt: 5.627 (5.589) Accm: 3.67 (4.04) Acct: 5.96 (6.23) proj_loss: -0.6088 (-0.6181) time: 0.9271 data: 0.0015 [11-26 14:31:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 165/350] Total time: 0:25:48 (0.928 s / it) [11-26 14:31:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.27 Lm: 6.485 (6.397) Lt: 5.769 (5.650) Accm: 3.42 (3.58) Acct: 5.51 (5.61) proj_loss: -0.6252 (-0.6212) time: 0.9271 data: 0.0016 [11-26 14:31:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.27 Lm: 6.448 (6.484) Lt: 5.730 (5.750) Accm: 3.85 (3.50) Acct: 5.85 (5.31) proj_loss: -0.6262 (-0.6256) time: 0.9271 data: 0.0015 [11-26 14:31:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.27 Lm: 6.423 (6.394) Lt: 5.669 (5.606) Accm: 3.47 (3.69) Acct: 5.68 (5.68) proj_loss: -0.6160 (-0.6193) time: 0.9271 data: 0.0016 [11-26 14:31:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.27 Lm: 6.396 (6.358) Lt: 5.513 (5.570) Accm: 3.51 (3.74) Acct: 5.61 (5.81) proj_loss: -0.5997 (-0.6045) time: 0.9272 data: 0.0021 [11-26 14:31:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.27 Lm: 6.482 (6.470) Lt: 5.692 (5.705) Accm: 3.45 (3.45) Acct: 5.30 (5.37) proj_loss: -0.6123 (-0.6158) time: 0.9271 data: 0.0016 [11-26 14:31:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.27 Lm: 6.396 (6.398) Lt: 5.607 (5.637) Accm: 3.66 (3.73) Acct: 5.79 (5.76) proj_loss: -0.6085 (-0.6063) time: 0.9272 data: 0.0018 [11-26 14:31:29] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 165/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.27 Lm: 6.477 (6.472) Lt: 5.668 (5.696) Accm: 3.55 (3.69) Acct: 5.79 (5.92) proj_loss: -0.6240 (-0.6182) time: 0.9272 data: 0.0020 [11-26 14:31:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 165/350] Total time: 0:25:48 (0.928 s / it) [11-26 14:31:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 165/350] Total time: 0:25:48 (0.928 s / it) [11-26 14:31:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 165/350] Total time: 0:25:48 (0.928 s / it) [11-26 14:31:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 165/350] Total time: 0:25:48 (0.928 s / it) [11-26 14:31:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 165/350] Total time: 0:25:48 (0.928 s / it) [11-26 14:31:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 165/350] Total time: 0:25:48 (0.928 s / it) [11-26 14:31:29] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 165/350] Total time: 0:25:48 (0.928 s / it) [11-26 14:31:29] (/home/user/VAR/train.py , line 276)=> [ep165] (training ) Lm: 6.415 (6.415), Lt: 5.660 (5.660), Acc m&t: 3.61 5.61, Remain: 3 days, 7:31:29, Finish: 2024-11-29 06:02 [11-26 14:31:29] (/home/user/VAR/train.py , line 276)=> [ep165] (training ) Lm: 6.415 (6.415), Lt: 5.660 (5.660), Acc m&t: 3.61 5.61, Remain: 3 days, 7:30:06, Finish: 2024-11-29 06:01 [11-26 14:31:29] (/home/user/VAR/train.py , line 276)=> [ep165] (training ) Lm: 6.415 (6.415), Lt: 5.660 (5.660), Acc m&t: 3.61 5.61, Remain: 3 days, 7:29:52, Finish: 2024-11-29 06:01 [11-26 14:31:29] (/home/user/VAR/train.py , line 276)=> [ep165] (training ) Lm: 6.415 (6.415), Lt: 5.660 (5.660), Acc m&t: 3.61 5.61, Remain: 3 days, 7:32:33, Finish: 2024-11-29 06:04 [11-26 14:31:29] (/home/user/VAR/train.py , line 276)=> [ep165] (training ) Lm: 6.415 (6.415), Lt: 5.660 (5.660), Acc m&t: 3.61 5.61, Remain: 3 days, 7:32:04, Finish: 2024-11-29 06:03 [11-26 14:31:29] (/home/user/VAR/train.py , line 276)=> [ep165] (training ) Lm: 6.415 (6.415), Lt: 5.660 (5.660), Acc m&t: 3.61 5.61, Remain: 3 days, 7:33:10, Finish: 2024-11-29 06:04 [11-26 14:31:29] (/home/user/VAR/train.py , line 276)=> [ep165] (training ) Lm: 6.415 (6.415), Lt: 5.660 (5.660), Acc m&t: 3.61 5.61, Remain: 3 days, 7:32:10, Finish: 2024-11-29 06:03 [11-26 14:31:29] (/home/user/VAR/train.py , line 276)=> [ep165] (training ) Lm: 6.415 (6.415), Lt: 5.660 (5.660), Acc m&t: 3.61 5.61, Remain: 3 days, 7:29:14, Finish: 2024-11-29 06:00 [11-26 14:31:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 0/1669] eta: 0:25:27 tlr: 0.00014 tnm: 0.27 Lm: 6.504 (6.504) Lt: 5.782 (5.782) Accm: 3.42 (3.42) Acct: 5.20 (5.20) proj_loss: -0.6275 (-0.6275) time: 0.9153 data: 0.0003 [11-26 14:31:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 0/1669] eta: 0:25:27 tlr: 0.00014 tnm: 0.27 Lm: 6.336 (6.336) Lt: 5.582 (5.582) Accm: 3.90 (3.90) Acct: 6.06 (6.06) proj_loss: -0.6196 (-0.6196) time: 0.9154 data: 0.0004 [11-26 14:31:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 0/1669] eta: 0:25:27 tlr: 0.00014 tnm: 0.27 Lm: 6.619 (6.619) Lt: 5.892 (5.892) Accm: 3.02 (3.02) Acct: 4.96 (4.96) proj_loss: -0.6199 (-0.6199) time: 0.9155 data: 0.0004 [11-26 14:31:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 0/1669] eta: 0:25:28 tlr: 0.00014 tnm: 0.27 Lm: 6.505 (6.505) Lt: 5.814 (5.814) Accm: 2.83 (2.83) Acct: 4.79 (4.79) proj_loss: -0.6332 (-0.6332) time: 0.9161 data: 0.0004 [11-26 14:31:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 0/1669] eta: 0:25:28 tlr: 0.00014 tnm: 0.27 Lm: 6.330 (6.330) Lt: 5.568 (5.568) Accm: 4.01 (4.01) Acct: 6.51 (6.51) proj_loss: -0.6349 (-0.6349) time: 0.9155 data: 0.0004 [11-26 14:31:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 0/1669] eta: 0:25:28 tlr: 0.00014 tnm: 0.27 Lm: 6.524 (6.524) Lt: 5.806 (5.806) Accm: 2.93 (2.93) Acct: 4.86 (4.86) proj_loss: -0.6281 (-0.6281) time: 0.9156 data: 0.0004 [11-26 14:31:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 0/1669] eta: 0:25:28 tlr: 0.00014 tnm: 0.27 Lm: 6.412 (6.412) Lt: 5.701 (5.701) Accm: 3.63 (3.63) Acct: 5.54 (5.54) proj_loss: -0.6291 (-0.6291) time: 0.9158 data: 0.0004 [11-26 14:31:30] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 0/1669] eta: 0:25:30 tlr: 0.00014 tnm: 0.27 Lm: 6.391 (6.391) Lt: 5.654 (5.654) Accm: 3.37 (3.37) Acct: 5.06 (5.06) proj_loss: -0.6355 (-0.6355) time: 0.9168 data: 0.0003 [11-26 14:37:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 417/1669] eta: 0:19:16 tlr: 0.00014 tnm: 0.26 Lm: 6.473 (6.473) Lt: 5.700 (5.700) Accm: 3.47 (3.47) Acct: 5.37 (5.37) proj_loss: -0.6517 (-0.6517) time: 0.9251 data: 0.0002 [11-26 14:37:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 417/1669] eta: 0:19:16 tlr: 0.00014 tnm: 0.26 Lm: 6.597 (6.597) Lt: 5.873 (5.873) Accm: 3.35 (3.35) Acct: 5.30 (5.30) proj_loss: -0.6214 (-0.6214) time: 0.9251 data: 0.0002 [11-26 14:37:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 417/1669] eta: 0:19:16 tlr: 0.00014 tnm: 0.26 Lm: 6.456 (6.456) Lt: 5.699 (5.699) Accm: 3.50 (3.50) Acct: 5.23 (5.23) proj_loss: -0.6178 (-0.6178) time: 0.9251 data: 0.0003 [11-26 14:37:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 417/1669] eta: 0:19:16 tlr: 0.00014 tnm: 0.26 Lm: 6.287 (6.287) Lt: 5.522 (5.522) Accm: 3.94 (3.94) Acct: 6.40 (6.40) proj_loss: -0.6183 (-0.6183) time: 0.9251 data: 0.0002 [11-26 14:37:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 417/1669] eta: 0:19:16 tlr: 0.00014 tnm: 0.26 Lm: 6.501 (6.501) Lt: 5.756 (5.756) Accm: 3.23 (3.23) Acct: 5.15 (5.15) proj_loss: -0.6243 (-0.6243) time: 0.9251 data: 0.0003 [11-26 14:37:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 417/1669] eta: 0:19:16 tlr: 0.00014 tnm: 0.26 Lm: 6.430 (6.430) Lt: 5.691 (5.691) Accm: 3.66 (3.66) Acct: 5.87 (5.87) proj_loss: -0.6222 (-0.6222) time: 0.9251 data: 0.0002 [11-26 14:37:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 417/1669] eta: 0:19:16 tlr: 0.00014 tnm: 0.26 Lm: 6.466 (6.466) Lt: 5.731 (5.731) Accm: 3.47 (3.47) Acct: 5.37 (5.37) proj_loss: -0.6230 (-0.6230) time: 0.9251 data: 0.0003 [11-26 14:37:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 417/1669] eta: 0:19:16 tlr: 0.00014 tnm: 0.26 Lm: 6.465 (6.465) Lt: 5.721 (5.721) Accm: 3.45 (3.45) Acct: 5.49 (5.49) proj_loss: -0.6352 (-0.6352) time: 0.9251 data: 0.0003 [11-26 14:44:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 834/1669] eta: 0:12:57 tlr: 0.00014 tnm: 0.26 Lm: 6.505 (6.521) Lt: 5.814 (5.811) Accm: 2.83 (3.24) Acct: 4.79 (5.17) proj_loss: -0.6372 (-0.6369) time: 0.9248 data: 0.0003 [11-26 14:44:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 834/1669] eta: 0:12:57 tlr: 0.00014 tnm: 0.26 Lm: 6.364 (6.408) Lt: 5.685 (5.689) Accm: 3.90 (3.80) Acct: 6.06 (6.10) proj_loss: -0.6248 (-0.6328) time: 0.9247 data: 0.0002 [11-26 14:44:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 834/1669] eta: 0:12:57 tlr: 0.00014 tnm: 0.26 Lm: 6.412 (6.429) Lt: 5.696 (5.658) Accm: 3.54 (3.51) Acct: 5.54 (5.35) proj_loss: -0.6065 (-0.6118) time: 0.9247 data: 0.0002 [11-26 14:44:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 834/1669] eta: 0:12:57 tlr: 0.00014 tnm: 0.26 Lm: 6.524 (6.517) Lt: 5.756 (5.756) Accm: 3.54 (3.42) Acct: 5.44 (5.43) proj_loss: -0.6205 (-0.6090) time: 0.9247 data: 0.0003 [11-26 14:44:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 834/1669] eta: 0:12:57 tlr: 0.00014 tnm: 0.26 Lm: 6.330 (6.319) Lt: 5.568 (5.547) Accm: 3.88 (3.81) Acct: 6.30 (6.04) proj_loss: -0.6172 (-0.6179) time: 0.9247 data: 0.0002 [11-26 14:44:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 834/1669] eta: 0:12:57 tlr: 0.00014 tnm: 0.26 Lm: 6.391 (6.431) Lt: 5.654 (5.639) Accm: 3.57 (3.66) Acct: 5.68 (5.60) proj_loss: -0.6355 (-0.6323) time: 0.9248 data: 0.0002 [11-26 14:44:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 834/1669] eta: 0:12:57 tlr: 0.00014 tnm: 0.26 Lm: 6.428 (6.432) Lt: 5.681 (5.712) Accm: 3.51 (3.68) Acct: 5.54 (5.64) proj_loss: -0.6275 (-0.6273) time: 0.9248 data: 0.0002 [11-26 14:44:26] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [ 834/1669] eta: 0:12:57 tlr: 0.00014 tnm: 0.26 Lm: 6.619 (6.618) Lt: 5.854 (5.859) Accm: 3.02 (3.18) Acct: 4.96 (5.00) proj_loss: -0.6199 (-0.6144) time: 0.9247 data: 0.0002 [11-26 14:50:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [1251/1669] eta: 0:06:28 tlr: 0.00014 tnm: 0.26 Lm: 6.597 (6.550) Lt: 5.843 (5.788) Accm: 3.35 (3.36) Acct: 5.30 (5.30) proj_loss: -0.6104 (-0.6110) time: 0.9262 data: 0.0003 [11-26 14:50:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [1251/1669] eta: 0:06:28 tlr: 0.00014 tnm: 0.26 Lm: 6.350 (6.387) Lt: 5.634 (5.635) Accm: 3.85 (3.80) Acct: 6.18 (6.15) proj_loss: -0.6222 (-0.6212) time: 0.9262 data: 0.0002 [11-26 14:50:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [1251/1669] eta: 0:06:28 tlr: 0.00014 tnm: 0.26 Lm: 6.414 (6.432) Lt: 5.654 (5.643) Accm: 3.71 (3.71) Acct: 5.87 (5.73) proj_loss: -0.6193 (-0.6251) time: 0.9262 data: 0.0002 [11-26 14:50:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [1251/1669] eta: 0:06:28 tlr: 0.00014 tnm: 0.26 Lm: 6.396 (6.393) Lt: 5.677 (5.652) Accm: 3.57 (3.67) Acct: 5.73 (5.71) proj_loss: -0.6230 (-0.6172) time: 0.9262 data: 0.0003 [11-26 14:50:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [1251/1669] eta: 0:06:28 tlr: 0.00014 tnm: 0.26 Lm: 6.425 (6.431) Lt: 5.685 (5.662) Accm: 3.55 (3.52) Acct: 5.56 (5.45) proj_loss: -0.6031 (-0.6031) time: 0.9262 data: 0.0002 [11-26 14:50:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [1251/1669] eta: 0:06:28 tlr: 0.00014 tnm: 0.26 Lm: 6.357 (6.384) Lt: 5.583 (5.640) Accm: 3.72 (3.61) Acct: 5.80 (5.64) proj_loss: -0.6260 (-0.6292) time: 0.9262 data: 0.0002 [11-26 14:50:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [1251/1669] eta: 0:06:28 tlr: 0.00014 tnm: 0.26 Lm: 6.537 (6.574) Lt: 5.781 (5.848) Accm: 3.39 (3.38) Acct: 5.15 (5.21) proj_loss: -0.6243 (-0.6192) time: 0.9262 data: 0.0002 [11-26 14:50:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [1251/1669] eta: 0:06:28 tlr: 0.00014 tnm: 0.26 Lm: 6.465 (6.497) Lt: 5.724 (5.767) Accm: 3.33 (3.39) Acct: 5.49 (5.43) proj_loss: -0.6352 (-0.6253) time: 0.9262 data: 0.0003 [11-26 14:57:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.425 (6.461) Lt: 5.634 (5.728) Accm: 3.53 (3.41) Acct: 5.44 (5.43) proj_loss: -0.6332 (-0.6224) time: 0.9259 data: 0.0021 [11-26 14:57:18] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 166/350] Total time: 0:25:48 (0.928 s / it) [11-26 14:57:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.437 (6.437) Lt: 5.696 (5.673) Accm: 3.54 (3.46) Acct: 5.54 (5.38) proj_loss: -0.6065 (-0.6045) time: 0.9259 data: 0.0016 [11-26 14:57:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.330 (6.368) Lt: 5.568 (5.617) Accm: 3.72 (3.63) Acct: 5.65 (5.64) proj_loss: -0.6271 (-0.6287) time: 0.9259 data: 0.0016 [11-26 14:57:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.364 (6.393) Lt: 5.626 (5.633) Accm: 3.79 (3.76) Acct: 6.06 (6.12) proj_loss: -0.6196 (-0.6168) time: 0.9259 data: 0.0016 [11-26 14:57:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.391 (6.372) Lt: 5.653 (5.575) Accm: 3.85 (3.90) Acct: 6.06 (6.04) proj_loss: -0.6032 (-0.6200) time: 0.9259 data: 0.0019 [11-26 14:57:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.575 (6.482) Lt: 5.832 (5.720) Accm: 3.69 (3.52) Acct: 5.65 (5.51) proj_loss: -0.6199 (-0.6171) time: 0.9259 data: 0.0016 [11-26 14:57:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.365 (6.369) Lt: 5.672 (5.617) Accm: 3.63 (3.75) Acct: 5.92 (5.86) proj_loss: -0.6275 (-0.6193) time: 0.9259 data: 0.0017 [11-26 14:57:18] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 166/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.26 Lm: 6.524 (6.527) Lt: 5.756 (5.809) Accm: 3.44 (3.39) Acct: 5.44 (5.30) proj_loss: -0.6281 (-0.6249) time: 0.9259 data: 0.0017 [11-26 14:57:18] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 166/350] Total time: 0:25:48 (0.928 s / it) [11-26 14:57:18] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 166/350] Total time: 0:25:48 (0.928 s / it) [11-26 14:57:18] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 166/350] Total time: 0:25:48 (0.928 s / it) [11-26 14:57:18] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 166/350] Total time: 0:25:48 (0.928 s / it) [11-26 14:57:18] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 166/350] Total time: 0:25:48 (0.928 s / it) [11-26 14:57:18] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 166/350] Total time: 0:25:48 (0.928 s / it) [11-26 14:57:18] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 166/350] Total time: 0:25:48 (0.928 s / it) [11-26 14:57:18] (/home/user/VAR/train.py , line 276)=> [ep166] (training ) Lm: 6.415 (6.421), Lt: 5.660 (5.668), Acc m&t: 3.61 5.61, Remain: 3 days, 7:03:35, Finish: 2024-11-29 06:00 [11-26 14:57:18] (/home/user/VAR/train.py , line 276)=> [ep166] (training ) Lm: 6.415 (6.421), Lt: 5.660 (5.668), Acc m&t: 3.61 5.61, Remain: 3 days, 7:03:54, Finish: 2024-11-29 06:01 [11-26 14:57:18] (/home/user/VAR/train.py , line 276)=> [ep166] (training ) Lm: 6.415 (6.421), Lt: 5.660 (5.668), Acc m&t: 3.61 5.61, Remain: 3 days, 7:04:14, Finish: 2024-11-29 06:01 [11-26 14:57:18] (/home/user/VAR/train.py , line 276)=> [ep166] (training ) Lm: 6.415 (6.421), Lt: 5.660 (5.668), Acc m&t: 3.61 5.61, Remain: 3 days, 7:03:56, Finish: 2024-11-29 06:01 [11-26 14:57:18] (/home/user/VAR/train.py , line 276)=> [ep166] (training ) Lm: 6.415 (6.421), Lt: 5.660 (5.668), Acc m&t: 3.61 5.61, Remain: 3 days, 7:03:41, Finish: 2024-11-29 06:00 [11-26 14:57:18] (/home/user/VAR/train.py , line 276)=> [ep166] (training ) Lm: 6.415 (6.421), Lt: 5.660 (5.668), Acc m&t: 3.61 5.61, Remain: 3 days, 7:03:31, Finish: 2024-11-29 06:00 [11-26 14:57:18] (/home/user/VAR/train.py , line 276)=> [ep166] (training ) Lm: 6.415 (6.421), Lt: 5.660 (5.668), Acc m&t: 3.61 5.61, Remain: 3 days, 7:04:23, Finish: 2024-11-29 06:01 [11-26 14:57:18] (/home/user/VAR/train.py , line 276)=> [ep166] (training ) Lm: 6.415 (6.421), Lt: 5.660 (5.668), Acc m&t: 3.61 5.61, Remain: 3 days, 7:04:32, Finish: 2024-11-29 06:01 [11-26 14:57:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 0/1669] eta: 0:24:40 tlr: 0.00014 tnm: 0.28 Lm: 6.356 (6.356) Lt: 5.621 (5.621) Accm: 3.95 (3.95) Acct: 6.20 (6.20) proj_loss: -0.6401 (-0.6401) time: 0.8870 data: 0.0004 [11-26 14:57:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 0/1669] eta: 0:24:47 tlr: 0.00014 tnm: 0.28 Lm: 6.343 (6.343) Lt: 5.575 (5.575) Accm: 3.80 (3.80) Acct: 6.16 (6.16) proj_loss: -0.6378 (-0.6378) time: 0.8913 data: 0.0004 [11-26 14:57:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 0/1669] eta: 0:24:46 tlr: 0.00014 tnm: 0.28 Lm: 6.470 (6.470) Lt: 5.720 (5.720) Accm: 3.23 (3.23) Acct: 4.86 (4.86) proj_loss: -0.6310 (-0.6310) time: 0.8907 data: 0.0003 [11-26 14:57:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 0/1669] eta: 0:24:47 tlr: 0.00014 tnm: 0.28 Lm: 6.576 (6.576) Lt: 5.859 (5.859) Accm: 3.53 (3.53) Acct: 5.23 (5.23) proj_loss: -0.6546 (-0.6546) time: 0.8915 data: 0.0003 [11-26 14:57:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 0/1669] eta: 0:24:47 tlr: 0.00014 tnm: 0.28 Lm: 6.445 (6.445) Lt: 5.669 (5.669) Accm: 3.38 (3.38) Acct: 5.20 (5.20) proj_loss: -0.6306 (-0.6306) time: 0.8914 data: 0.0004 [11-26 14:57:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 0/1669] eta: 0:24:47 tlr: 0.00014 tnm: 0.28 Lm: 6.172 (6.172) Lt: 5.449 (5.449) Accm: 4.24 (4.24) Acct: 6.27 (6.27) proj_loss: -0.6280 (-0.6280) time: 0.8915 data: 0.0003 [11-26 14:57:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 0/1669] eta: 0:24:47 tlr: 0.00014 tnm: 0.28 Lm: 6.201 (6.201) Lt: 5.451 (5.451) Accm: 4.56 (4.56) Acct: 7.20 (7.20) proj_loss: -0.6591 (-0.6591) time: 0.8914 data: 0.0004 [11-26 14:57:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 0/1669] eta: 0:24:48 tlr: 0.00014 tnm: 0.28 Lm: 6.590 (6.590) Lt: 5.909 (5.909) Accm: 3.32 (3.32) Acct: 5.13 (5.13) proj_loss: -0.6076 (-0.6076) time: 0.8917 data: 0.0004 [11-26 15:03:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.523 (6.523) Lt: 5.794 (5.794) Accm: 3.42 (3.42) Acct: 5.25 (5.25) proj_loss: -0.5967 (-0.5967) time: 0.9266 data: 0.0002 [11-26 15:03:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.363 (6.363) Lt: 5.636 (5.636) Accm: 3.85 (3.85) Acct: 5.97 (5.97) proj_loss: -0.6186 (-0.6186) time: 0.9266 data: 0.0003 [11-26 15:03:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.183 (6.183) Lt: 5.443 (5.443) Accm: 4.55 (4.55) Acct: 7.13 (7.13) proj_loss: -0.6386 (-0.6386) time: 0.9266 data: 0.0003 [11-26 15:03:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.464 (6.464) Lt: 5.704 (5.704) Accm: 3.33 (3.33) Acct: 5.60 (5.60) proj_loss: -0.6305 (-0.6305) time: 0.9266 data: 0.0002 [11-26 15:03:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.366 (6.366) Lt: 5.657 (5.657) Accm: 3.89 (3.89) Acct: 5.73 (5.73) proj_loss: -0.6494 (-0.6494) time: 0.9266 data: 0.0002 [11-26 15:03:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.352 (6.352) Lt: 5.569 (5.569) Accm: 4.02 (4.02) Acct: 6.44 (6.44) proj_loss: -0.6257 (-0.6257) time: 0.9266 data: 0.0002 [11-26 15:03:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.258 (6.258) Lt: 5.519 (5.519) Accm: 4.13 (4.13) Acct: 6.23 (6.23) proj_loss: -0.6476 (-0.6476) time: 0.9266 data: 0.0003 [11-26 15:03:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 417/1669] eta: 0:19:17 tlr: 0.00014 tnm: 0.27 Lm: 6.489 (6.489) Lt: 5.755 (5.755) Accm: 3.03 (3.03) Acct: 4.75 (4.75) proj_loss: -0.6458 (-0.6458) time: 0.9266 data: 0.0002 [11-26 15:10:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.507 (6.523) Lt: 5.791 (5.773) Accm: 3.13 (3.06) Acct: 4.86 (4.82) proj_loss: -0.6310 (-0.6330) time: 0.9279 data: 0.0002 [11-26 15:10:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.236 (6.323) Lt: 5.455 (5.578) Accm: 4.17 (3.98) Acct: 6.23 (6.00) proj_loss: -0.6442 (-0.6351) time: 0.9279 data: 0.0002 [11-26 15:10:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.535 (6.527) Lt: 5.830 (5.806) Accm: 3.32 (3.24) Acct: 5.13 (4.98) proj_loss: -0.5969 (-0.5968) time: 0.9279 data: 0.0002 [11-26 15:10:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.398 (6.442) Lt: 5.575 (5.656) Accm: 3.61 (3.42) Acct: 5.89 (5.69) proj_loss: -0.6232 (-0.6205) time: 0.9279 data: 0.0003 [11-26 15:10:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.316 (6.288) Lt: 5.548 (5.529) Accm: 3.92 (4.06) Acct: 6.47 (6.31) proj_loss: -0.6361 (-0.6438) time: 0.9279 data: 0.0003 [11-26 15:10:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.445 (6.388) Lt: 5.669 (5.623) Accm: 3.50 (3.85) Acct: 5.54 (6.14) proj_loss: -0.6306 (-0.6281) time: 0.9279 data: 0.0002 [11-26 15:10:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.554 (6.441) Lt: 5.824 (5.755) Accm: 3.45 (3.46) Acct: 5.68 (5.34) proj_loss: -0.6280 (-0.6273) time: 0.9279 data: 0.0002 [11-26 15:10:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [ 834/1669] eta: 0:12:52 tlr: 0.00014 tnm: 0.27 Lm: 6.356 (6.314) Lt: 5.621 (5.582) Accm: 3.95 (4.03) Acct: 6.20 (6.37) proj_loss: -0.6371 (-0.6281) time: 0.9279 data: 0.0003 [11-26 15:16:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.406 (6.408) Lt: 5.657 (5.663) Accm: 3.85 (3.68) Acct: 5.73 (5.66) proj_loss: -0.6437 (-0.6372) time: 0.9655 data: 0.0002 [11-26 15:16:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.522 (6.527) Lt: 5.763 (5.764) Accm: 3.18 (3.18) Acct: 4.91 (5.00) proj_loss: -0.6192 (-0.6260) time: 0.9655 data: 0.0002 [11-26 15:16:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.492 (6.505) Lt: 5.704 (5.724) Accm: 3.23 (3.26) Acct: 5.46 (5.41) proj_loss: -0.6130 (-0.6161) time: 0.9655 data: 0.0002 [11-26 15:16:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.445 (6.369) Lt: 5.687 (5.625) Accm: 3.53 (3.80) Acct: 5.53 (5.96) proj_loss: -0.6220 (-0.6196) time: 0.9655 data: 0.0003 [11-26 15:16:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.331 (6.411) Lt: 5.567 (5.653) Accm: 3.81 (3.69) Acct: 5.87 (5.86) proj_loss: -0.6361 (-0.6324) time: 0.9655 data: 0.0003 [11-26 15:16:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.496 (6.487) Lt: 5.754 (5.747) Accm: 3.42 (3.41) Acct: 5.25 (5.23) proj_loss: -0.5957 (-0.5962) time: 0.9654 data: 0.0003 [11-26 15:16:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.452 (6.407) Lt: 5.661 (5.631) Accm: 3.53 (3.78) Acct: 5.80 (6.12) proj_loss: -0.6318 (-0.6313) time: 0.9655 data: 0.0003 [11-26 15:16:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [1251/1669] eta: 0:06:27 tlr: 0.00014 tnm: 0.27 Lm: 6.452 (6.419) Lt: 5.730 (5.726) Accm: 3.51 (3.49) Acct: 5.34 (5.25) proj_loss: -0.6364 (-0.6332) time: 0.9655 data: 0.0003 [11-26 15:23:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.27 Lm: 6.523 (6.440) Lt: 5.745 (5.729) Accm: 3.47 (3.48) Acct: 5.30 (5.26) proj_loss: -0.6344 (-0.6334) time: 0.9268 data: 0.0015 [11-26 15:23:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 167/350] Total time: 0:25:48 (0.928 s / it) [11-26 15:23:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.27 Lm: 6.392 (6.405) Lt: 5.651 (5.661) Accm: 3.85 (3.71) Acct: 5.89 (5.70) proj_loss: -0.6433 (-0.6352) time: 0.9268 data: 0.0019 [11-26 15:23:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.27 Lm: 6.511 (6.492) Lt: 5.809 (5.760) Accm: 3.37 (3.40) Acct: 5.13 (5.17) proj_loss: -0.5969 (-0.5980) time: 0.9268 data: 0.0016 [11-26 15:23:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.27 Lm: 6.579 (6.519) Lt: 5.824 (5.744) Accm: 3.23 (3.25) Acct: 5.20 (5.37) proj_loss: -0.6125 (-0.6154) time: 0.9268 data: 0.0017 [11-26 15:23:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.27 Lm: 6.507 (6.494) Lt: 5.735 (5.740) Accm: 3.23 (3.28) Acct: 4.96 (5.12) proj_loss: -0.6100 (-0.6228) time: 0.9268 data: 0.0018 [11-26 15:23:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.27 Lm: 6.445 (6.415) Lt: 5.661 (5.637) Accm: 3.51 (3.72) Acct: 5.54 (5.93) proj_loss: -0.6306 (-0.6287) time: 0.9268 data: 0.0020 [11-26 15:23:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.27 Lm: 6.342 (6.397) Lt: 5.587 (5.648) Accm: 3.92 (3.77) Acct: 6.34 (5.96) proj_loss: -0.6361 (-0.6304) time: 0.9268 data: 0.0016 [11-26 15:23:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 167/350] [1668/1669] eta: 0:00:00 tlr: 0.00014 tnm: 0.27 Lm: 6.377 (6.371) Lt: 5.671 (5.634) Accm: 3.82 (3.81) Acct: 5.44 (5.85) proj_loss: -0.6248 (-0.6206) time: 0.9268 data: 0.0016 [11-26 15:23:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 167/350] Total time: 0:25:48 (0.928 s / it) [11-26 15:23:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 167/350] Total time: 0:25:48 (0.928 s / it) [11-26 15:23:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 167/350] Total time: 0:25:48 (0.928 s / it) [11-26 15:23:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 167/350] Total time: 0:25:48 (0.928 s / it) [11-26 15:23:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 167/350] Total time: 0:25:48 (0.928 s / it) [11-26 15:23:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 167/350] Total time: 0:25:48 (0.928 s / it) [11-26 15:23:06] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 167/350] Total time: 0:25:48 (0.928 s / it) [11-26 15:23:06] (/home/user/VAR/train.py , line 276)=> [ep167] (training ) Lm: 6.415 (6.427), Lt: 5.660 (5.670), Acc m&t: 3.61 5.61, Remain: 3 days, 6:40:21, Finish: 2024-11-29 06:03 [11-26 15:23:06] (/home/user/VAR/train.py , line 276)=> [ep167] (training ) Lm: 6.415 (6.427), Lt: 5.660 (5.670), Acc m&t: 3.61 5.61, Remain: 3 days, 6:39:24, Finish: 2024-11-29 06:02 [11-26 15:23:06] (/home/user/VAR/train.py , line 276)=> [ep167] (training ) Lm: 6.415 (6.427), Lt: 5.660 (5.670), Acc m&t: 3.61 5.61, Remain: 3 days, 6:40:11, Finish: 2024-11-29 06:03 [11-26 15:23:06] (/home/user/VAR/train.py , line 276)=> [ep167] (training ) Lm: 6.415 (6.427), Lt: 5.660 (5.670), Acc m&t: 3.61 5.61, Remain: 3 days, 6:39:40, Finish: 2024-11-29 06:02 [11-26 15:23:06] (/home/user/VAR/train.py , line 276)=> [ep167] (training ) Lm: 6.415 (6.427), Lt: 5.660 (5.670), Acc m&t: 3.61 5.61, Remain: 3 days, 6:41:41, Finish: 2024-11-29 06:04 [11-26 15:23:06] (/home/user/VAR/train.py , line 276)=> [ep167] (training ) Lm: 6.415 (6.427), Lt: 5.660 (5.670), Acc m&t: 3.61 5.61, Remain: 3 days, 6:40:39, Finish: 2024-11-29 06:03 [11-26 15:23:06] (/home/user/VAR/train.py , line 276)=> [ep167] (training ) Lm: 6.415 (6.427), Lt: 5.660 (5.670), Acc m&t: 3.61 5.61, Remain: 3 days, 6:40:27, Finish: 2024-11-29 06:03 [11-26 15:23:06] (/home/user/VAR/train.py , line 276)=> [ep167] (training ) Lm: 6.415 (6.427), Lt: 5.660 (5.670), Acc m&t: 3.61 5.61, Remain: 3 days, 6:39:21, Finish: 2024-11-29 06:02 [11-26 15:23:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 0/1669] eta: 0:25:26 tlr: 0.00014 tnm: 0.27 Lm: 6.463 (6.463) Lt: 5.668 (5.668) Accm: 3.58 (3.58) Acct: 5.54 (5.54) proj_loss: -0.5825 (-0.5825) time: 0.9144 data: 0.0003 [11-26 15:23:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 0/1669] eta: 0:26:41 tlr: 0.00014 tnm: 0.27 Lm: 6.185 (6.185) Lt: 5.502 (5.502) Accm: 3.96 (3.96) Acct: 5.58 (5.58) proj_loss: -0.6169 (-0.6169) time: 0.9595 data: 0.0004 [11-26 15:23:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 0/1669] eta: 0:25:27 tlr: 0.00014 tnm: 0.27 Lm: 6.336 (6.336) Lt: 5.592 (5.592) Accm: 3.99 (3.99) Acct: 6.40 (6.40) proj_loss: -0.6324 (-0.6324) time: 0.9152 data: 0.0003 [11-26 15:23:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 0/1669] eta: 0:25:27 tlr: 0.00014 tnm: 0.27 Lm: 6.506 (6.506) Lt: 5.707 (5.707) Accm: 3.22 (3.22) Acct: 5.72 (5.72) proj_loss: -0.5816 (-0.5816) time: 0.9153 data: 0.0003 [11-26 15:23:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 0/1669] eta: 0:25:27 tlr: 0.00014 tnm: 0.27 Lm: 6.251 (6.251) Lt: 5.484 (5.484) Accm: 4.12 (4.12) Acct: 6.27 (6.27) proj_loss: -0.6034 (-0.6034) time: 0.9152 data: 0.0004 [11-26 15:23:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 0/1669] eta: 0:25:27 tlr: 0.00014 tnm: 0.27 Lm: 6.400 (6.400) Lt: 5.722 (5.722) Accm: 3.47 (3.47) Acct: 5.48 (5.48) proj_loss: -0.6656 (-0.6656) time: 0.9154 data: 0.0003 [11-26 15:23:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 0/1669] eta: 0:25:27 tlr: 0.00014 tnm: 0.27 Lm: 6.477 (6.477) Lt: 5.742 (5.742) Accm: 3.28 (3.28) Acct: 4.89 (4.89) proj_loss: -0.6249 (-0.6249) time: 0.9154 data: 0.0003 [11-26 15:23:07] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 0/1669] eta: 0:25:27 tlr: 0.00014 tnm: 0.27 Lm: 6.489 (6.489) Lt: 5.692 (5.692) Accm: 3.54 (3.54) Acct: 5.65 (5.65) proj_loss: -0.6088 (-0.6088) time: 0.9153 data: 0.0004 [11-26 15:29:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 417/1669] eta: 0:19:18 tlr: 0.00013 tnm: 0.26 Lm: 6.525 (6.525) Lt: 5.799 (5.799) Accm: 3.19 (3.19) Acct: 4.96 (4.96) proj_loss: -0.6033 (-0.6033) time: 0.9249 data: 0.0003 [11-26 15:29:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 417/1669] eta: 0:19:18 tlr: 0.00013 tnm: 0.26 Lm: 6.355 (6.355) Lt: 5.564 (5.564) Accm: 3.63 (3.63) Acct: 5.49 (5.49) proj_loss: -0.6103 (-0.6103) time: 0.9249 data: 0.0002 [11-26 15:29:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 417/1669] eta: 0:19:18 tlr: 0.00013 tnm: 0.26 Lm: 6.275 (6.275) Lt: 5.573 (5.573) Accm: 3.64 (3.64) Acct: 5.35 (5.35) proj_loss: -0.6182 (-0.6182) time: 0.9249 data: 0.0003 [11-26 15:29:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 417/1669] eta: 0:19:18 tlr: 0.00013 tnm: 0.26 Lm: 6.511 (6.511) Lt: 5.792 (5.792) Accm: 3.34 (3.34) Acct: 5.34 (5.34) proj_loss: -0.6534 (-0.6534) time: 0.9249 data: 0.0002 [11-26 15:29:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 417/1669] eta: 0:19:18 tlr: 0.00013 tnm: 0.26 Lm: 6.523 (6.523) Lt: 5.803 (5.803) Accm: 3.15 (3.15) Acct: 5.22 (5.22) proj_loss: -0.6090 (-0.6090) time: 0.9249 data: 0.0003 [11-26 15:29:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 417/1669] eta: 0:19:18 tlr: 0.00013 tnm: 0.26 Lm: 6.303 (6.303) Lt: 5.550 (5.550) Accm: 3.89 (3.89) Acct: 6.08 (6.08) proj_loss: -0.6034 (-0.6034) time: 0.9249 data: 0.0002 [11-26 15:29:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 417/1669] eta: 0:19:18 tlr: 0.00013 tnm: 0.26 Lm: 6.313 (6.313) Lt: 5.488 (5.488) Accm: 4.14 (4.14) Acct: 6.73 (6.73) proj_loss: -0.6193 (-0.6193) time: 0.9249 data: 0.0002 [11-26 15:29:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 417/1669] eta: 0:19:18 tlr: 0.00013 tnm: 0.26 Lm: 6.667 (6.667) Lt: 5.968 (5.968) Accm: 2.99 (2.99) Acct: 4.61 (4.61) proj_loss: -0.6083 (-0.6083) time: 0.9250 data: 0.0003 [11-26 15:35:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 834/1669] eta: 0:12:52 tlr: 0.00013 tnm: 0.28 Lm: 6.501 (6.612) Lt: 5.749 (5.895) Accm: 3.28 (3.29) Acct: 4.89 (5.11) proj_loss: -0.6203 (-0.6123) time: 0.9255 data: 0.0002 [11-26 15:35:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 834/1669] eta: 0:12:52 tlr: 0.00013 tnm: 0.28 Lm: 6.418 (6.480) Lt: 5.722 (5.731) Accm: 3.47 (3.46) Acct: 5.48 (5.51) proj_loss: -0.6412 (-0.6423) time: 0.9255 data: 0.0002 [11-26 15:35:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 834/1669] eta: 0:12:52 tlr: 0.00013 tnm: 0.28 Lm: 6.354 (6.388) Lt: 5.616 (5.615) Accm: 3.66 (3.75) Acct: 5.89 (5.98) proj_loss: -0.6034 (-0.6061) time: 0.9255 data: 0.0003 [11-26 15:35:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 834/1669] eta: 0:12:52 tlr: 0.00013 tnm: 0.28 Lm: 6.247 (6.302) Lt: 5.460 (5.518) Accm: 3.69 (3.86) Acct: 5.54 (5.84) proj_loss: -0.6333 (-0.6180) time: 0.9255 data: 0.0002 [11-26 15:35:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 834/1669] eta: 0:12:52 tlr: 0.00013 tnm: 0.28 Lm: 6.541 (6.592) Lt: 5.898 (5.865) Accm: 3.10 (3.14) Acct: 5.03 (5.15) proj_loss: -0.6223 (-0.6134) time: 0.9255 data: 0.0003 [11-26 15:35:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 834/1669] eta: 0:12:52 tlr: 0.00013 tnm: 0.28 Lm: 6.328 (6.293) Lt: 5.644 (5.598) Accm: 3.85 (3.71) Acct: 5.58 (5.50) proj_loss: -0.6169 (-0.6163) time: 0.9255 data: 0.0002 [11-26 15:35:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 834/1669] eta: 0:12:52 tlr: 0.00013 tnm: 0.28 Lm: 6.336 (6.372) Lt: 5.592 (5.553) Accm: 3.99 (3.93) Acct: 6.40 (6.37) proj_loss: -0.6066 (-0.6151) time: 0.9255 data: 0.0002 [11-26 15:35:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [ 834/1669] eta: 0:12:52 tlr: 0.00013 tnm: 0.28 Lm: 6.489 (6.420) Lt: 5.692 (5.672) Accm: 3.54 (3.42) Acct: 5.65 (5.25) proj_loss: -0.6088 (-0.6112) time: 0.9255 data: 0.0003 [11-26 15:42:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [1251/1669] eta: 0:06:26 tlr: 0.00013 tnm: 0.27 Lm: 6.525 (6.456) Lt: 5.771 (5.717) Accm: 3.35 (3.36) Acct: 5.22 (5.13) proj_loss: -0.6126 (-0.6125) time: 0.9233 data: 0.0003 [11-26 15:42:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [1251/1669] eta: 0:06:26 tlr: 0.00013 tnm: 0.27 Lm: 6.409 (6.403) Lt: 5.665 (5.655) Accm: 3.58 (3.74) Acct: 5.66 (5.91) proj_loss: -0.6306 (-0.6364) time: 0.9233 data: 0.0002 [11-26 15:42:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [1251/1669] eta: 0:06:26 tlr: 0.00013 tnm: 0.27 Lm: 6.347 (6.363) Lt: 5.646 (5.665) Accm: 3.58 (3.57) Acct: 5.35 (5.30) proj_loss: -0.6165 (-0.6163) time: 0.9233 data: 0.0003 [11-26 15:42:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [1251/1669] eta: 0:06:26 tlr: 0.00013 tnm: 0.27 Lm: 6.407 (6.406) Lt: 5.657 (5.636) Accm: 3.57 (3.68) Acct: 5.84 (5.86) proj_loss: -0.6075 (-0.6124) time: 0.9233 data: 0.0002 [11-26 15:42:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [1251/1669] eta: 0:06:26 tlr: 0.00013 tnm: 0.27 Lm: 6.386 (6.388) Lt: 5.638 (5.591) Accm: 3.76 (3.82) Acct: 6.03 (6.15) proj_loss: -0.6064 (-0.6125) time: 0.9233 data: 0.0003 [11-26 15:42:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [1251/1669] eta: 0:06:26 tlr: 0.00013 tnm: 0.27 Lm: 6.256 (6.292) Lt: 5.444 (5.496) Accm: 3.99 (3.99) Acct: 6.03 (6.01) proj_loss: -0.6150 (-0.6127) time: 0.9233 data: 0.0002 [11-26 15:42:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [1251/1669] eta: 0:06:26 tlr: 0.00013 tnm: 0.27 Lm: 6.489 (6.543) Lt: 5.745 (5.818) Accm: 3.58 (3.45) Acct: 5.46 (5.34) proj_loss: -0.6226 (-0.6232) time: 0.9233 data: 0.0003 [11-26 15:42:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [1251/1669] eta: 0:06:26 tlr: 0.00013 tnm: 0.27 Lm: 6.523 (6.531) Lt: 5.803 (5.774) Accm: 3.16 (3.35) Acct: 5.37 (5.42) proj_loss: -0.6132 (-0.6111) time: 0.9233 data: 0.0003 [11-26 15:48:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.506 (6.497) Lt: 5.707 (5.732) Accm: 3.22 (3.45) Acct: 5.72 (5.56) proj_loss: -0.6223 (-0.6136) time: 0.9263 data: 0.0017 [11-26 15:48:56] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 168/350] Total time: 0:25:49 (0.928 s / it) [11-26 15:48:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.418 (6.421) Lt: 5.722 (5.678) Accm: 3.63 (3.72) Acct: 5.85 (5.96) proj_loss: -0.6287 (-0.6349) time: 0.9263 data: 0.0016 [11-26 15:48:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.336 (6.377) Lt: 5.592 (5.586) Accm: 3.99 (3.91) Acct: 6.40 (6.32) proj_loss: -0.6066 (-0.6131) time: 0.9263 data: 0.0015 [11-26 15:48:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.393 (6.403) Lt: 5.616 (5.620) Accm: 3.54 (3.65) Acct: 5.79 (5.79) proj_loss: -0.6115 (-0.6196) time: 0.9263 data: 0.0017 [11-26 15:48:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.365 (6.371) Lt: 5.648 (5.663) Accm: 3.64 (3.58) Acct: 5.13 (5.24) proj_loss: -0.6161 (-0.6144) time: 0.9264 data: 0.0015 [11-26 15:48:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.477 (6.488) Lt: 5.742 (5.754) Accm: 3.88 (3.66) Acct: 6.03 (5.66) proj_loss: -0.6249 (-0.6252) time: 0.9263 data: 0.0014 [11-26 15:48:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.489 (6.408) Lt: 5.692 (5.645) Accm: 3.54 (3.56) Acct: 5.65 (5.53) proj_loss: -0.6164 (-0.6171) time: 0.9263 data: 0.0020 [11-26 15:48:56] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 168/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.247 (6.274) Lt: 5.427 (5.454) Accm: 4.02 (3.99) Acct: 6.51 (6.14) proj_loss: -0.6331 (-0.6168) time: 0.9264 data: 0.0017 [11-26 15:48:56] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 168/350] Total time: 0:25:49 (0.928 s / it) [11-26 15:48:56] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 168/350] Total time: 0:25:49 (0.928 s / it) [11-26 15:48:56] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 168/350] Total time: 0:25:49 (0.928 s / it) [11-26 15:48:56] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 168/350] Total time: 0:25:49 (0.928 s / it) [11-26 15:48:56] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 168/350] Total time: 0:25:49 (0.928 s / it) [11-26 15:48:56] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 168/350] Total time: 0:25:49 (0.928 s / it) [11-26 15:48:56] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 168/350] Total time: 0:25:49 (0.928 s / it) [11-26 15:48:56] (/home/user/VAR/train.py , line 276)=> [ep168] (training ) Lm: 6.415 (6.425), Lt: 5.660 (5.667), Acc m&t: 3.62 5.68, Remain: 3 days, 6:15:51, Finish: 2024-11-29 06:04 [11-26 15:48:56] (/home/user/VAR/train.py , line 276)=> [ep168] (training ) Lm: 6.415 (6.425), Lt: 5.660 (5.667), Acc m&t: 3.62 5.68, Remain: 3 days, 6:18:58, Finish: 2024-11-29 06:07 [11-26 15:48:56] (/home/user/VAR/train.py , line 276)=> [ep168] (training ) Lm: 6.415 (6.425), Lt: 5.660 (5.667), Acc m&t: 3.62 5.68, Remain: 3 days, 6:18:27, Finish: 2024-11-29 06:07 [11-26 15:48:56] (/home/user/VAR/train.py , line 276)=> [ep168] (training ) Lm: 6.415 (6.425), Lt: 5.660 (5.667), Acc m&t: 3.62 5.68, Remain: 3 days, 6:18:44, Finish: 2024-11-29 06:07 [11-26 15:48:56] (/home/user/VAR/train.py , line 276)=> [ep168] (training ) Lm: 6.415 (6.425), Lt: 5.660 (5.667), Acc m&t: 3.62 5.68, Remain: 3 days, 6:18:03, Finish: 2024-11-29 06:06 [11-26 15:48:56] (/home/user/VAR/train.py , line 276)=> [ep168] (training ) Lm: 6.415 (6.425), Lt: 5.660 (5.667), Acc m&t: 3.62 5.68, Remain: 3 days, 6:17:42, Finish: 2024-11-29 06:06 [11-26 15:48:56] (/home/user/VAR/train.py , line 276)=> [ep168] (training ) Lm: 6.415 (6.425), Lt: 5.660 (5.667), Acc m&t: 3.62 5.68, Remain: 3 days, 6:18:25, Finish: 2024-11-29 06:07 [11-26 15:48:56] (/home/user/VAR/train.py , line 276)=> [ep168] (training ) Lm: 6.415 (6.425), Lt: 5.660 (5.667), Acc m&t: 3.62 5.68, Remain: 3 days, 6:17:44, Finish: 2024-11-29 06:06 [11-26 15:48:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 0/1669] eta: 0:24:40 tlr: 0.00013 tnm: 0.27 Lm: 6.598 (6.598) Lt: 5.856 (5.856) Accm: 3.12 (3.12) Acct: 4.61 (4.61) proj_loss: -0.6236 (-0.6236) time: 0.8873 data: 0.0003 [11-26 15:48:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 0/1669] eta: 0:25:19 tlr: 0.00013 tnm: 0.27 Lm: 6.643 (6.643) Lt: 5.894 (5.894) Accm: 2.96 (2.96) Acct: 4.68 (4.68) proj_loss: -0.6328 (-0.6328) time: 0.9101 data: 0.0004 [11-26 15:48:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 0/1669] eta: 0:24:41 tlr: 0.00013 tnm: 0.27 Lm: 6.119 (6.119) Lt: 5.251 (5.251) Accm: 4.60 (4.60) Acct: 7.23 (7.23) proj_loss: -0.6009 (-0.6009) time: 0.8878 data: 0.0003 [11-26 15:48:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 0/1669] eta: 0:24:41 tlr: 0.00013 tnm: 0.27 Lm: 6.143 (6.143) Lt: 5.350 (5.350) Accm: 5.11 (5.11) Acct: 8.09 (8.09) proj_loss: -0.6145 (-0.6145) time: 0.8877 data: 0.0003 [11-26 15:48:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 0/1669] eta: 0:24:41 tlr: 0.00013 tnm: 0.27 Lm: 6.638 (6.638) Lt: 5.878 (5.878) Accm: 2.72 (2.72) Acct: 4.58 (4.58) proj_loss: -0.6343 (-0.6343) time: 0.8877 data: 0.0004 [11-26 15:48:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 0/1669] eta: 0:24:41 tlr: 0.00013 tnm: 0.27 Lm: 6.478 (6.478) Lt: 5.697 (5.697) Accm: 3.37 (3.37) Acct: 5.34 (5.34) proj_loss: -0.6241 (-0.6241) time: 0.8879 data: 0.0003 [11-26 15:48:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 0/1669] eta: 0:24:41 tlr: 0.00013 tnm: 0.27 Lm: 6.631 (6.631) Lt: 5.935 (5.935) Accm: 2.93 (2.93) Acct: 4.41 (4.41) proj_loss: -0.6112 (-0.6112) time: 0.8877 data: 0.0003 [11-26 15:48:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 0/1669] eta: 0:24:39 tlr: 0.00013 tnm: 0.27 Lm: 6.596 (6.596) Lt: 5.903 (5.903) Accm: 2.86 (2.86) Acct: 4.55 (4.55) proj_loss: -0.6177 (-0.6177) time: 0.8864 data: 0.0004 [11-26 15:55:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 417/1669] eta: 0:19:18 tlr: 0.00013 tnm: 0.27 Lm: 6.512 (6.512) Lt: 5.773 (5.773) Accm: 3.27 (3.27) Acct: 5.41 (5.41) proj_loss: -0.6226 (-0.6226) time: 0.9270 data: 0.0003 [11-26 15:55:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 417/1669] eta: 0:19:18 tlr: 0.00013 tnm: 0.27 Lm: 6.532 (6.532) Lt: 5.797 (5.797) Accm: 3.31 (3.31) Acct: 5.20 (5.20) proj_loss: -0.6453 (-0.6453) time: 0.9270 data: 0.0002 [11-26 15:55:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 417/1669] eta: 0:19:18 tlr: 0.00013 tnm: 0.27 Lm: 6.637 (6.637) Lt: 5.918 (5.918) Accm: 2.87 (2.87) Acct: 4.42 (4.42) proj_loss: -0.6197 (-0.6197) time: 0.9270 data: 0.0002 [11-26 15:55:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 417/1669] eta: 0:19:18 tlr: 0.00013 tnm: 0.27 Lm: 6.569 (6.569) Lt: 5.856 (5.856) Accm: 3.09 (3.09) Acct: 4.77 (4.77) proj_loss: -0.6298 (-0.6298) time: 0.9270 data: 0.0002 [11-26 15:55:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 417/1669] eta: 0:19:18 tlr: 0.00013 tnm: 0.27 Lm: 6.233 (6.233) Lt: 5.401 (5.401) Accm: 4.22 (4.22) Acct: 6.59 (6.59) proj_loss: -0.5959 (-0.5959) time: 0.9270 data: 0.0002 [11-26 15:55:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 417/1669] eta: 0:19:18 tlr: 0.00013 tnm: 0.27 Lm: 6.372 (6.372) Lt: 5.615 (5.615) Accm: 4.20 (4.20) Acct: 6.71 (6.71) proj_loss: -0.6137 (-0.6137) time: 0.9270 data: 0.0002 [11-26 15:55:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 417/1669] eta: 0:19:18 tlr: 0.00013 tnm: 0.27 Lm: 6.550 (6.550) Lt: 5.784 (5.784) Accm: 3.23 (3.23) Acct: 5.27 (5.27) proj_loss: -0.6117 (-0.6117) time: 0.9270 data: 0.0002 [11-26 15:55:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 417/1669] eta: 0:19:18 tlr: 0.00013 tnm: 0.27 Lm: 6.490 (6.490) Lt: 5.750 (5.750) Accm: 3.07 (3.07) Acct: 4.99 (4.99) proj_loss: -0.6238 (-0.6238) time: 0.9270 data: 0.0002 [11-26 16:01:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.26 Lm: 6.343 (6.391) Lt: 5.623 (5.664) Accm: 3.41 (3.35) Acct: 5.41 (5.18) proj_loss: -0.6284 (-0.6253) time: 0.9275 data: 0.0003 [11-26 16:01:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.26 Lm: 6.631 (6.601) Lt: 5.902 (5.913) Accm: 2.93 (3.03) Acct: 4.44 (4.75) proj_loss: -0.6144 (-0.6179) time: 0.9275 data: 0.0002 [11-26 16:01:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.26 Lm: 6.466 (6.510) Lt: 5.813 (5.802) Accm: 2.96 (3.11) Acct: 4.68 (4.98) proj_loss: -0.6328 (-0.6297) time: 0.9275 data: 0.0003 [11-26 16:01:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.26 Lm: 6.370 (6.371) Lt: 5.660 (5.630) Accm: 3.44 (3.95) Acct: 5.34 (6.21) proj_loss: -0.6145 (-0.6229) time: 0.9275 data: 0.0002 [11-26 16:01:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.26 Lm: 6.540 (6.523) Lt: 5.856 (5.796) Accm: 3.12 (3.26) Acct: 4.92 (5.05) proj_loss: -0.6284 (-0.6293) time: 0.9275 data: 0.0003 [11-26 16:01:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.26 Lm: 6.429 (6.414) Lt: 5.643 (5.659) Accm: 3.69 (3.48) Acct: 6.27 (5.69) proj_loss: -0.6275 (-0.6253) time: 0.9275 data: 0.0003 [11-26 16:01:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.26 Lm: 6.528 (6.543) Lt: 5.776 (5.781) Accm: 3.37 (3.33) Acct: 5.34 (5.50) proj_loss: -0.6241 (-0.6209) time: 0.9275 data: 0.0003 [11-26 16:01:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.26 Lm: 6.347 (6.287) Lt: 5.542 (5.448) Accm: 3.85 (4.07) Acct: 6.44 (6.54) proj_loss: -0.5993 (-0.5970) time: 0.9275 data: 0.0002 [11-26 16:08:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.371 (6.331) Lt: 5.546 (5.540) Accm: 3.80 (3.93) Acct: 6.20 (6.18) proj_loss: -0.6001 (-0.6073) time: 0.9255 data: 0.0003 [11-26 16:08:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.392 (6.382) Lt: 5.653 (5.634) Accm: 3.43 (3.82) Acct: 5.30 (5.97) proj_loss: -0.6207 (-0.6239) time: 0.9254 data: 0.0003 [11-26 16:08:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.490 (6.465) Lt: 5.750 (5.756) Accm: 3.32 (3.32) Acct: 5.01 (5.04) proj_loss: -0.6241 (-0.6239) time: 0.9254 data: 0.0003 [11-26 16:08:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.579 (6.555) Lt: 5.902 (5.852) Accm: 3.13 (3.17) Acct: 4.92 (4.93) proj_loss: -0.6213 (-0.6234) time: 0.9255 data: 0.0003 [11-26 16:08:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.485 (6.456) Lt: 5.767 (5.707) Accm: 3.36 (3.44) Acct: 5.27 (5.41) proj_loss: -0.6260 (-0.6216) time: 0.9255 data: 0.0003 [11-26 16:08:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.503 (6.513) Lt: 5.736 (5.758) Accm: 3.45 (3.42) Acct: 5.46 (5.52) proj_loss: -0.6117 (-0.6153) time: 0.9255 data: 0.0003 [11-26 16:08:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.478 (6.505) Lt: 5.756 (5.771) Accm: 3.16 (3.17) Acct: 5.04 (5.09) proj_loss: -0.6274 (-0.6277) time: 0.9254 data: 0.0003 [11-26 16:08:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.324 (6.365) Lt: 5.536 (5.590) Accm: 3.80 (3.70) Acct: 6.27 (6.12) proj_loss: -0.6291 (-0.6272) time: 0.9255 data: 0.0003 [11-26 16:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.219 (6.330) Lt: 5.496 (5.571) Accm: 3.90 (3.82) Acct: 6.27 (6.14) proj_loss: -0.6275 (-0.6261) time: 0.9279 data: 0.0016 [11-26 16:14:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 169/350] Total time: 0:25:45 (0.926 s / it) [11-26 16:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.347 (6.310) Lt: 5.542 (5.513) Accm: 3.85 (3.99) Acct: 6.44 (6.25) proj_loss: -0.5993 (-0.6053) time: 0.9278 data: 0.0016 [11-26 16:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.565 (6.485) Lt: 5.813 (5.767) Accm: 3.23 (3.27) Acct: 5.06 (5.04) proj_loss: -0.6284 (-0.6274) time: 0.9279 data: 0.0016 [11-26 16:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.540 (6.488) Lt: 5.856 (5.757) Accm: 3.16 (3.38) Acct: 4.92 (5.27) proj_loss: -0.6284 (-0.6251) time: 0.9278 data: 0.0016 [11-26 16:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.478 (6.457) Lt: 5.697 (5.700) Accm: 3.53 (3.52) Acct: 5.58 (5.71) proj_loss: -0.6241 (-0.6192) time: 0.9278 data: 0.0016 [11-26 16:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.370 (6.365) Lt: 5.646 (5.609) Accm: 3.44 (3.76) Acct: 5.30 (5.84) proj_loss: -0.6158 (-0.6223) time: 0.9279 data: 0.0016 [11-26 16:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.527 (6.537) Lt: 5.901 (5.840) Accm: 3.04 (3.14) Acct: 4.75 (4.90) proj_loss: -0.6156 (-0.6218) time: 0.9279 data: 0.0015 [11-26 16:14:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 169/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.470 (6.498) Lt: 5.754 (5.768) Accm: 3.37 (3.29) Acct: 5.41 (5.17) proj_loss: -0.6219 (-0.6251) time: 0.9279 data: 0.0016 [11-26 16:14:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 169/350] Total time: 0:25:45 (0.926 s / it) [11-26 16:14:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 169/350] Total time: 0:25:45 (0.926 s / it) [11-26 16:14:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 169/350] Total time: 0:25:45 (0.926 s / it) [11-26 16:14:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 169/350] Total time: 0:25:45 (0.926 s / it) [11-26 16:14:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 169/350] Total time: 0:25:45 (0.926 s / it) [11-26 16:14:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 169/350] Total time: 0:25:45 (0.926 s / it) [11-26 16:14:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 169/350] Total time: 0:25:45 (0.926 s / it) [11-26 16:18:54] (home/user/VAR/trainer.py, line 114)=> FID: 3.1995384638759674 [11-26 16:18:55] (/home/user/VAR/train.py , line 259)=> [*] [ep169] (val 50000) Lm: 6.4233, Lt: 5.6664, Acc m&t: 3.59 5.63, Val cost: 253.05s [11-26 16:18:55] (/home/user/VAR/train.py , line 264)=> [saving ckpt] ... [saving ckpt](*) finished! @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth [11-26 16:20:07] (/home/user/VAR/train.py , line 276)=> [ep169] (training ) Lm: 6.415 (6.423), Lt: 5.660 (5.666), Acc m&t: 3.62 5.68, Remain: 3 days, 6:01:12, Finish: 2024-11-29 06:15 [11-26 16:20:07] (/home/user/VAR/train.py , line 276)=> [ep169] (training ) Lm: 6.415 (6.423), Lt: 5.660 (5.666), Acc m&t: 3.62 5.68, Remain: 3 days, 6:00:18, Finish: 2024-11-29 06:14 [11-26 16:20:07] (/home/user/VAR/train.py , line 276)=> [ep169] (training ) Lm: 6.415 (6.423), Lt: 5.660 (5.666), Acc m&t: 3.62 5.68, Remain: 3 days, 6:01:36, Finish: 2024-11-29 06:16 [11-26 16:20:07] (/home/user/VAR/train.py , line 276)=> [ep169] (training ) Lm: 6.415 (6.423), Lt: 5.660 (5.666), Acc m&t: 3.62 5.68, Remain: 3 days, 5:59:58, Finish: 2024-11-29 06:14 [11-26 16:20:07] (/home/user/VAR/train.py , line 276)=> [ep169] (training ) Lm: 6.415 (6.423), Lt: 5.660 (5.666), Acc m&t: 3.62 5.68, Remain: 3 days, 6:00:52, Finish: 2024-11-29 06:15 [11-26 16:20:07] (/home/user/VAR/train.py , line 276)=> [ep169] (training ) Lm: 6.415 (6.423), Lt: 5.660 (5.666), Acc m&t: 3.62 5.68, Remain: 3 days, 5:59:59, Finish: 2024-11-29 06:14 [11-26 16:20:07] (/home/user/VAR/train.py , line 276)=> [ep169] (training ) Lm: 6.415 (6.423), Lt: 5.660 (5.666), Acc m&t: 3.62 5.68, Remain: 3 days, 6:01:42, Finish: 2024-11-29 06:16 [11-26 16:20:07] (/home/user/VAR/train.py , line 276)=> [ep169] (training ) Lm: 6.415 (6.423), Lt: 5.660 (5.666), Acc m&t: 3.62 5.68, Remain: 3 days, 6:01:42, Finish: 2024-11-29 06:16 [11-26 16:20:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 0/1669] eta: 0:26:40 tlr: 0.00013 tnm: 0.28 Lm: 6.641 (6.641) Lt: 5.937 (5.937) Accm: 2.83 (2.83) Acct: 4.20 (4.20) proj_loss: -0.6305 (-0.6305) time: 0.9590 data: 0.0004 [11-26 16:20:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 0/1669] eta: 0:26:38 tlr: 0.00013 tnm: 0.28 Lm: 6.484 (6.484) Lt: 5.826 (5.826) Accm: 3.39 (3.39) Acct: 4.99 (4.99) proj_loss: -0.6025 (-0.6025) time: 0.9580 data: 0.0004 [11-26 16:20:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 0/1669] eta: 0:26:40 tlr: 0.00013 tnm: 0.28 Lm: 6.366 (6.366) Lt: 5.605 (5.605) Accm: 3.82 (3.82) Acct: 6.34 (6.34) proj_loss: -0.6274 (-0.6274) time: 0.9587 data: 0.0003 [11-26 16:20:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 0/1669] eta: 0:26:38 tlr: 0.00013 tnm: 0.28 Lm: 6.466 (6.466) Lt: 5.694 (5.694) Accm: 3.32 (3.32) Acct: 4.89 (4.89) proj_loss: -0.6252 (-0.6252) time: 0.9575 data: 0.0005 [11-26 16:20:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 0/1669] eta: 0:26:39 tlr: 0.00013 tnm: 0.28 Lm: 6.623 (6.623) Lt: 5.881 (5.881) Accm: 3.16 (3.16) Acct: 5.17 (5.17) proj_loss: -0.5972 (-0.5972) time: 0.9583 data: 0.0004 [11-26 16:20:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 0/1669] eta: 0:26:52 tlr: 0.00013 tnm: 0.28 Lm: 6.665 (6.665) Lt: 5.870 (5.870) Accm: 2.84 (2.84) Acct: 5.03 (5.03) proj_loss: -0.6024 (-0.6024) time: 0.9662 data: 0.0004 [11-26 16:20:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 0/1669] eta: 0:27:00 tlr: 0.00013 tnm: 0.28 Lm: 6.384 (6.384) Lt: 5.631 (5.631) Accm: 3.83 (3.83) Acct: 5.65 (5.65) proj_loss: -0.6251 (-0.6251) time: 0.9707 data: 0.0004 [11-26 16:20:08] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 0/1669] eta: 0:26:40 tlr: 0.00013 tnm: 0.28 Lm: 6.207 (6.207) Lt: 5.388 (5.388) Accm: 4.44 (4.44) Acct: 6.75 (6.75) proj_loss: -0.5713 (-0.5713) time: 0.9587 data: 0.0004 [11-26 16:26:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.27 Lm: 6.307 (6.307) Lt: 5.555 (5.555) Accm: 4.03 (4.03) Acct: 6.13 (6.13) proj_loss: -0.6043 (-0.6043) time: 0.9275 data: 0.0003 [11-26 16:26:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.27 Lm: 6.500 (6.500) Lt: 5.820 (5.820) Accm: 3.30 (3.30) Acct: 4.86 (4.86) proj_loss: -0.6158 (-0.6158) time: 0.9275 data: 0.0002 [11-26 16:26:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.27 Lm: 6.328 (6.328) Lt: 5.613 (5.613) Accm: 3.69 (3.69) Acct: 5.22 (5.22) proj_loss: -0.6387 (-0.6387) time: 0.9275 data: 0.0003 [11-26 16:26:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.27 Lm: 6.674 (6.674) Lt: 5.902 (5.902) Accm: 2.76 (2.76) Acct: 4.63 (4.63) proj_loss: -0.6214 (-0.6214) time: 0.9275 data: 0.0002 [11-26 16:26:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.27 Lm: 6.355 (6.355) Lt: 5.613 (5.613) Accm: 3.95 (3.95) Acct: 6.20 (6.20) proj_loss: -0.6300 (-0.6300) time: 0.9275 data: 0.0003 [11-26 16:26:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.27 Lm: 6.628 (6.628) Lt: 5.933 (5.933) Accm: 3.15 (3.15) Acct: 4.60 (4.60) proj_loss: -0.6224 (-0.6224) time: 0.9275 data: 0.0002 [11-26 16:26:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.27 Lm: 6.573 (6.573) Lt: 5.829 (5.829) Accm: 3.23 (3.23) Acct: 5.29 (5.29) proj_loss: -0.6152 (-0.6152) time: 0.9275 data: 0.0003 [11-26 16:26:34] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.27 Lm: 6.356 (6.356) Lt: 5.539 (5.539) Accm: 3.64 (3.64) Acct: 5.61 (5.61) proj_loss: -0.6217 (-0.6217) time: 0.9275 data: 0.0003 [11-26 16:33:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.27 Lm: 6.327 (6.324) Lt: 5.488 (5.522) Accm: 3.83 (3.77) Acct: 5.65 (5.83) proj_loss: -0.6184 (-0.6171) time: 0.9281 data: 0.0003 [11-26 16:33:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.27 Lm: 6.466 (6.382) Lt: 5.694 (5.653) Accm: 3.35 (3.57) Acct: 5.03 (5.15) proj_loss: -0.6313 (-0.6362) time: 0.9281 data: 0.0002 [11-26 16:33:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.27 Lm: 6.615 (6.571) Lt: 5.929 (5.832) Accm: 3.48 (3.31) Acct: 4.99 (5.06) proj_loss: -0.6305 (-0.6262) time: 0.9281 data: 0.0002 [11-26 16:33:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.27 Lm: 6.665 (6.602) Lt: 5.870 (5.842) Accm: 2.84 (2.99) Acct: 5.03 (4.95) proj_loss: -0.6074 (-0.6167) time: 0.9281 data: 0.0002 [11-26 16:33:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.27 Lm: 6.484 (6.491) Lt: 5.814 (5.791) Accm: 3.39 (3.34) Acct: 4.99 (5.07) proj_loss: -0.6291 (-0.6293) time: 0.9281 data: 0.0002 [11-26 16:33:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.27 Lm: 6.523 (6.508) Lt: 5.776 (5.752) Accm: 3.29 (3.36) Acct: 5.41 (5.41) proj_loss: -0.6053 (-0.6119) time: 0.9281 data: 0.0003 [11-26 16:33:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.27 Lm: 6.366 (6.390) Lt: 5.621 (5.629) Accm: 3.82 (3.73) Acct: 6.06 (5.95) proj_loss: -0.6280 (-0.6294) time: 0.9281 data: 0.0003 [11-26 16:33:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.27 Lm: 6.304 (6.306) Lt: 5.471 (5.527) Accm: 3.61 (3.88) Acct: 5.51 (5.87) proj_loss: -0.6165 (-0.6084) time: 0.9281 data: 0.0003 [11-26 16:39:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.356 (6.379) Lt: 5.596 (5.608) Accm: 3.59 (3.57) Acct: 5.42 (5.46) proj_loss: -0.6225 (-0.6134) time: 0.9279 data: 0.0003 [11-26 16:39:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.590 (6.569) Lt: 5.882 (5.833) Accm: 3.30 (3.26) Acct: 5.11 (5.11) proj_loss: -0.6321 (-0.6320) time: 0.9279 data: 0.0002 [11-26 16:39:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.450 (6.395) Lt: 5.696 (5.664) Accm: 3.40 (3.54) Acct: 5.10 (5.16) proj_loss: -0.6319 (-0.6353) time: 0.9279 data: 0.0002 [11-26 16:39:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.356 (6.343) Lt: 5.559 (5.570) Accm: 3.64 (3.63) Acct: 5.61 (5.54) proj_loss: -0.6217 (-0.6231) time: 0.9279 data: 0.0003 [11-26 16:39:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.478 (6.472) Lt: 5.774 (5.768) Accm: 3.41 (3.40) Acct: 5.03 (5.07) proj_loss: -0.6263 (-0.6278) time: 0.9278 data: 0.0003 [11-26 16:39:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.412 (6.414) Lt: 5.641 (5.665) Accm: 3.56 (3.54) Acct: 5.75 (5.64) proj_loss: -0.6277 (-0.6255) time: 0.9279 data: 0.0003 [11-26 16:39:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.450 (6.428) Lt: 5.687 (5.679) Accm: 3.45 (3.58) Acct: 5.53 (5.77) proj_loss: -0.6115 (-0.6133) time: 0.9279 data: 0.0003 [11-26 16:39:27] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.561 (6.563) Lt: 5.796 (5.803) Accm: 3.05 (3.06) Acct: 5.10 (5.00) proj_loss: -0.6206 (-0.6210) time: 0.9279 data: 0.0003 [11-26 16:45:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.457 (6.512) Lt: 5.723 (5.750) Accm: 3.26 (3.17) Acct: 5.17 (5.14) proj_loss: -0.6289 (-0.6225) time: 0.9286 data: 0.0017 [11-26 16:45:53] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 170/350] Total time: 0:25:46 (0.927 s / it) [11-26 16:45:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.466 (6.430) Lt: 5.697 (5.700) Accm: 3.35 (3.50) Acct: 5.03 (5.13) proj_loss: -0.6313 (-0.6288) time: 0.9286 data: 0.0017 [11-26 16:45:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.473 (6.439) Lt: 5.734 (5.726) Accm: 3.42 (3.47) Acct: 5.06 (5.21) proj_loss: -0.6235 (-0.6244) time: 0.9286 data: 0.0017 [11-26 16:45:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.366 (6.382) Lt: 5.621 (5.630) Accm: 3.82 (3.68) Acct: 6.06 (5.88) proj_loss: -0.6274 (-0.6207) time: 0.9286 data: 0.0017 [11-26 16:45:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.565 (6.557) Lt: 5.836 (5.799) Accm: 3.48 (3.32) Acct: 5.23 (5.27) proj_loss: -0.6305 (-0.6313) time: 0.9286 data: 0.0014 [11-26 16:45:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.384 (6.354) Lt: 5.541 (5.564) Accm: 3.83 (3.69) Acct: 5.65 (5.73) proj_loss: -0.6184 (-0.6187) time: 0.9286 data: 0.0018 [11-26 16:45:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.378 (6.379) Lt: 5.597 (5.614) Accm: 3.61 (3.74) Acct: 5.65 (6.01) proj_loss: -0.6176 (-0.6159) time: 0.9286 data: 0.0017 [11-26 16:45:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 170/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.407 (6.412) Lt: 5.721 (5.649) Accm: 3.57 (3.47) Acct: 5.34 (5.30) proj_loss: -0.6262 (-0.6160) time: 0.9287 data: 0.0017 [11-26 16:45:53] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 170/350] Total time: 0:25:46 (0.927 s / it) [11-26 16:45:53] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 170/350] Total time: 0:25:46 (0.927 s / it) [11-26 16:45:53] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 170/350] Total time: 0:25:46 (0.927 s / it) [11-26 16:45:53] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 170/350] Total time: 0:25:46 (0.927 s / it) [11-26 16:45:53] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 170/350] Total time: 0:25:46 (0.927 s / it) [11-26 16:45:53] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 170/350] Total time: 0:25:46 (0.927 s / it) [11-26 16:45:53] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 170/350] Total time: 0:25:46 (0.927 s / it) [11-26 16:45:53] (/home/user/VAR/train.py , line 276)=> [ep170] (training ) Lm: 6.415 (6.425), Lt: 5.660 (5.670), Acc m&t: 3.62 5.68, Remain: 3 days, 5:31:49, Finish: 2024-11-29 06:17 [11-26 16:45:53] (/home/user/VAR/train.py , line 276)=> [ep170] (training ) Lm: 6.415 (6.425), Lt: 5.660 (5.670), Acc m&t: 3.62 5.68, Remain: 3 days, 5:31:52, Finish: 2024-11-29 06:17 [11-26 16:45:53] (/home/user/VAR/train.py , line 276)=> [ep170] (training ) Lm: 6.415 (6.425), Lt: 5.660 (5.670), Acc m&t: 3.62 5.68, Remain: 3 days, 5:32:42, Finish: 2024-11-29 06:18 [11-26 16:45:53] (/home/user/VAR/train.py , line 276)=> [ep170] (training ) Lm: 6.415 (6.425), Lt: 5.660 (5.670), Acc m&t: 3.62 5.68, Remain: 3 days, 5:32:32, Finish: 2024-11-29 06:18 [11-26 16:45:53] (/home/user/VAR/train.py , line 276)=> [ep170] (training ) Lm: 6.415 (6.425), Lt: 5.660 (5.670), Acc m&t: 3.62 5.68, Remain: 3 days, 5:32:16, Finish: 2024-11-29 06:18 [11-26 16:45:53] (/home/user/VAR/train.py , line 276)=> [ep170] (training ) Lm: 6.415 (6.425), Lt: 5.660 (5.670), Acc m&t: 3.62 5.68, Remain: 3 days, 5:30:46, Finish: 2024-11-29 06:16 [11-26 16:45:53] (/home/user/VAR/train.py , line 276)=> [ep170] (training ) Lm: 6.415 (6.425), Lt: 5.660 (5.670), Acc m&t: 3.62 5.68, Remain: 3 days, 5:33:31, Finish: 2024-11-29 06:19 [11-26 16:45:53] (/home/user/VAR/train.py , line 276)=> [ep170] (training ) Lm: 6.415 (6.425), Lt: 5.660 (5.670), Acc m&t: 3.62 5.68, Remain: 3 days, 5:31:30, Finish: 2024-11-29 06:17 [11-26 16:45:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 0/1669] eta: 0:24:20 tlr: 0.00013 tnm: 0.27 Lm: 6.555 (6.555) Lt: 5.828 (5.828) Accm: 2.97 (2.97) Acct: 4.75 (4.75) proj_loss: -0.6370 (-0.6370) time: 0.8749 data: 0.0003 [11-26 16:45:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 0/1669] eta: 0:25:25 tlr: 0.00013 tnm: 0.27 Lm: 6.497 (6.497) Lt: 5.731 (5.731) Accm: 3.86 (3.86) Acct: 6.23 (6.23) proj_loss: -0.5929 (-0.5929) time: 0.9142 data: 0.0003 [11-26 16:45:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 0/1669] eta: 0:24:22 tlr: 0.00013 tnm: 0.27 Lm: 6.148 (6.148) Lt: 5.341 (5.341) Accm: 4.17 (4.17) Acct: 6.20 (6.20) proj_loss: -0.6204 (-0.6204) time: 0.8763 data: 0.0003 [11-26 16:45:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 0/1669] eta: 0:24:22 tlr: 0.00013 tnm: 0.27 Lm: 6.372 (6.372) Lt: 5.627 (5.627) Accm: 4.21 (4.21) Acct: 6.61 (6.61) proj_loss: -0.6166 (-0.6166) time: 0.8766 data: 0.0003 [11-26 16:45:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 0/1669] eta: 0:24:22 tlr: 0.00013 tnm: 0.27 Lm: 6.511 (6.511) Lt: 5.800 (5.800) Accm: 3.41 (3.41) Acct: 5.51 (5.51) proj_loss: -0.6490 (-0.6490) time: 0.8765 data: 0.0004 [11-26 16:45:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 0/1669] eta: 0:24:23 tlr: 0.00013 tnm: 0.27 Lm: 6.419 (6.419) Lt: 5.662 (5.662) Accm: 3.48 (3.48) Acct: 5.48 (5.48) proj_loss: -0.6141 (-0.6141) time: 0.8770 data: 0.0004 [11-26 16:45:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 0/1669] eta: 0:24:22 tlr: 0.00013 tnm: 0.27 Lm: 6.124 (6.124) Lt: 5.378 (5.378) Accm: 4.81 (4.81) Acct: 7.51 (7.51) proj_loss: -0.6511 (-0.6511) time: 0.8763 data: 0.0003 [11-26 16:45:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 0/1669] eta: 0:24:23 tlr: 0.00013 tnm: 0.27 Lm: 6.443 (6.443) Lt: 5.669 (5.669) Accm: 3.37 (3.37) Acct: 5.27 (5.27) proj_loss: -0.6233 (-0.6233) time: 0.8769 data: 0.0003 [11-26 16:52:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 417/1669] eta: 0:19:26 tlr: 0.00013 tnm: 0.28 Lm: 6.315 (6.315) Lt: 5.506 (5.506) Accm: 3.87 (3.87) Acct: 6.11 (6.11) proj_loss: -0.6161 (-0.6161) time: 0.9999 data: 0.0003 [11-26 16:52:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 417/1669] eta: 0:19:26 tlr: 0.00013 tnm: 0.28 Lm: 6.385 (6.385) Lt: 5.612 (5.612) Accm: 4.00 (4.00) Acct: 6.22 (6.22) proj_loss: -0.6131 (-0.6131) time: 0.9999 data: 0.0002 [11-26 16:52:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 417/1669] eta: 0:19:26 tlr: 0.00013 tnm: 0.28 Lm: 6.448 (6.448) Lt: 5.700 (5.700) Accm: 3.73 (3.73) Acct: 5.96 (5.96) proj_loss: -0.6124 (-0.6124) time: 0.9999 data: 0.0003 [11-26 16:52:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 417/1669] eta: 0:19:26 tlr: 0.00013 tnm: 0.28 Lm: 6.339 (6.339) Lt: 5.567 (5.567) Accm: 3.83 (3.83) Acct: 5.89 (5.89) proj_loss: -0.6301 (-0.6301) time: 0.9999 data: 0.0002 [11-26 16:52:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 417/1669] eta: 0:19:26 tlr: 0.00013 tnm: 0.28 Lm: 6.448 (6.448) Lt: 5.746 (5.746) Accm: 3.42 (3.42) Acct: 5.04 (5.04) proj_loss: -0.6350 (-0.6350) time: 0.9999 data: 0.0002 [11-26 16:52:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 417/1669] eta: 0:19:26 tlr: 0.00013 tnm: 0.28 Lm: 6.076 (6.076) Lt: 5.324 (5.324) Accm: 4.79 (4.79) Acct: 7.32 (7.32) proj_loss: -0.6304 (-0.6304) time: 0.9999 data: 0.0003 [11-26 16:52:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 417/1669] eta: 0:19:26 tlr: 0.00013 tnm: 0.28 Lm: 6.290 (6.290) Lt: 5.524 (5.524) Accm: 4.03 (4.03) Acct: 6.11 (6.11) proj_loss: -0.6054 (-0.6054) time: 0.9999 data: 0.0003 [11-26 16:52:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 417/1669] eta: 0:19:26 tlr: 0.00013 tnm: 0.28 Lm: 6.470 (6.470) Lt: 5.720 (5.720) Accm: 3.29 (3.29) Acct: 5.39 (5.39) proj_loss: -0.6240 (-0.6240) time: 0.9999 data: 0.0003 [11-26 16:59:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 834/1669] eta: 0:13:06 tlr: 0.00013 tnm: 0.27 Lm: 6.511 (6.485) Lt: 5.754 (5.731) Accm: 3.39 (3.32) Acct: 5.27 (5.33) proj_loss: -0.6087 (-0.6189) time: 0.9284 data: 0.0003 [11-26 16:59:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 834/1669] eta: 0:13:06 tlr: 0.00013 tnm: 0.27 Lm: 6.529 (6.403) Lt: 5.792 (5.642) Accm: 3.50 (3.72) Acct: 5.58 (5.64) proj_loss: -0.6204 (-0.6170) time: 0.9284 data: 0.0002 [11-26 16:59:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 834/1669] eta: 0:13:06 tlr: 0.00013 tnm: 0.27 Lm: 6.233 (6.288) Lt: 5.432 (5.481) Accm: 4.11 (3.95) Acct: 6.27 (6.16) proj_loss: -0.6233 (-0.6203) time: 0.9284 data: 0.0002 [11-26 16:59:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 834/1669] eta: 0:13:06 tlr: 0.00013 tnm: 0.27 Lm: 6.448 (6.448) Lt: 5.675 (5.723) Accm: 3.48 (3.44) Acct: 5.34 (5.14) proj_loss: -0.6330 (-0.6190) time: 0.9284 data: 0.0003 [11-26 16:59:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 834/1669] eta: 0:13:06 tlr: 0.00013 tnm: 0.27 Lm: 6.497 (6.541) Lt: 5.731 (5.795) Accm: 3.60 (3.45) Acct: 5.68 (5.58) proj_loss: -0.5947 (-0.6065) time: 0.9284 data: 0.0003 [11-26 16:59:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 834/1669] eta: 0:13:06 tlr: 0.00013 tnm: 0.27 Lm: 6.397 (6.429) Lt: 5.627 (5.654) Accm: 3.79 (3.73) Acct: 5.82 (5.82) proj_loss: -0.6097 (-0.5991) time: 0.9284 data: 0.0002 [11-26 16:59:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 834/1669] eta: 0:13:06 tlr: 0.00013 tnm: 0.27 Lm: 6.124 (6.178) Lt: 5.378 (5.400) Accm: 4.78 (4.39) Acct: 7.13 (6.61) proj_loss: -0.6106 (-0.6238) time: 0.9284 data: 0.0003 [11-26 16:59:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [ 834/1669] eta: 0:13:06 tlr: 0.00013 tnm: 0.27 Lm: 6.388 (6.322) Lt: 5.620 (5.556) Accm: 4.11 (4.05) Acct: 5.89 (6.04) proj_loss: -0.5966 (-0.5999) time: 0.9284 data: 0.0003 [11-26 17:05:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [1251/1669] eta: 0:06:31 tlr: 0.00013 tnm: 0.27 Lm: 6.404 (6.381) Lt: 5.641 (5.633) Accm: 3.80 (3.76) Acct: 5.68 (5.60) proj_loss: -0.6054 (-0.6071) time: 0.9269 data: 0.0003 [11-26 17:05:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [1251/1669] eta: 0:06:31 tlr: 0.00013 tnm: 0.27 Lm: 6.453 (6.451) Lt: 5.670 (5.705) Accm: 3.49 (3.46) Acct: 5.34 (5.23) proj_loss: -0.6230 (-0.6176) time: 0.9269 data: 0.0003 [11-26 17:05:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [1251/1669] eta: 0:06:31 tlr: 0.00013 tnm: 0.27 Lm: 6.252 (6.250) Lt: 5.465 (5.483) Accm: 4.39 (4.29) Acct: 7.04 (6.70) proj_loss: -0.6141 (-0.6222) time: 0.9269 data: 0.0003 [11-26 17:05:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [1251/1669] eta: 0:06:31 tlr: 0.00013 tnm: 0.27 Lm: 6.338 (6.362) Lt: 5.551 (5.554) Accm: 3.74 (3.78) Acct: 5.77 (5.92) proj_loss: -0.6161 (-0.6169) time: 0.9269 data: 0.0003 [11-26 17:05:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [1251/1669] eta: 0:06:31 tlr: 0.00013 tnm: 0.27 Lm: 6.513 (6.517) Lt: 5.777 (5.766) Accm: 3.28 (3.21) Acct: 5.23 (5.13) proj_loss: -0.6038 (-0.6137) time: 0.9269 data: 0.0003 [11-26 17:05:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [1251/1669] eta: 0:06:31 tlr: 0.00013 tnm: 0.27 Lm: 6.462 (6.512) Lt: 5.700 (5.747) Accm: 3.46 (3.42) Acct: 5.44 (5.48) proj_loss: -0.6130 (-0.6127) time: 0.9269 data: 0.0003 [11-26 17:05:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [1251/1669] eta: 0:06:31 tlr: 0.00013 tnm: 0.27 Lm: 6.421 (6.380) Lt: 5.646 (5.606) Accm: 3.49 (3.66) Acct: 5.42 (5.54) proj_loss: -0.6090 (-0.6121) time: 0.9269 data: 0.0003 [11-26 17:05:25] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [1251/1669] eta: 0:06:31 tlr: 0.00013 tnm: 0.27 Lm: 6.385 (6.406) Lt: 5.612 (5.628) Accm: 3.90 (3.80) Acct: 6.04 (5.93) proj_loss: -0.6131 (-0.6111) time: 0.9269 data: 0.0002 [11-26 17:11:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.372 (6.389) Lt: 5.597 (5.610) Accm: 3.79 (3.80) Acct: 6.27 (6.03) proj_loss: -0.6097 (-0.6091) time: 0.9250 data: 0.0014 [11-26 17:11:52] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 171/350] Total time: 0:25:58 (0.934 s / it) [11-26 17:11:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.427 (6.472) Lt: 5.669 (5.695) Accm: 3.60 (3.60) Acct: 5.68 (5.79) proj_loss: -0.6246 (-0.6151) time: 0.9250 data: 0.0017 [11-26 17:11:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.448 (6.418) Lt: 5.665 (5.686) Accm: 3.50 (3.58) Acct: 5.34 (5.43) proj_loss: -0.6330 (-0.6246) time: 0.9250 data: 0.0018 [11-26 17:11:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.313 (6.344) Lt: 5.499 (5.583) Accm: 3.50 (3.75) Acct: 5.58 (5.67) proj_loss: -0.6204 (-0.6218) time: 0.9250 data: 0.0016 [11-26 17:11:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.233 (6.277) Lt: 5.432 (5.452) Accm: 4.11 (4.16) Acct: 6.27 (6.49) proj_loss: -0.6216 (-0.6179) time: 0.9250 data: 0.0016 [11-26 17:11:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.511 (6.482) Lt: 5.754 (5.729) Accm: 3.39 (3.29) Acct: 5.27 (5.23) proj_loss: -0.6032 (-0.6116) time: 0.9250 data: 0.0017 [11-26 17:11:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.398 (6.385) Lt: 5.662 (5.659) Accm: 3.79 (3.76) Acct: 5.48 (5.50) proj_loss: -0.6141 (-0.6170) time: 0.9250 data: 0.0019 [11-26 17:11:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 171/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.345 (6.269) Lt: 5.532 (5.493) Accm: 4.20 (4.27) Acct: 6.96 (6.68) proj_loss: -0.6175 (-0.6278) time: 0.9250 data: 0.0019 [11-26 17:11:52] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 171/350] Total time: 0:25:58 (0.934 s / it) [11-26 17:11:52] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 171/350] Total time: 0:25:58 (0.934 s / it) [11-26 17:11:52] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 171/350] Total time: 0:25:58 (0.934 s / it) [11-26 17:11:52] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 171/350] Total time: 0:25:58 (0.934 s / it) [11-26 17:11:52] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 171/350] Total time: 0:25:58 (0.934 s / it) [11-26 17:11:52] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 171/350] Total time: 0:25:58 (0.934 s / it) [11-26 17:11:52] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 171/350] Total time: 0:25:58 (0.934 s / it) [11-26 17:11:52] (/home/user/VAR/train.py , line 276)=> [ep171] (training ) Lm: 6.415 (6.433), Lt: 5.660 (5.679), Acc m&t: 3.62 5.68, Remain: 3 days, 4:51:37, Finish: 2024-11-29 06:03 [11-26 17:11:52] (/home/user/VAR/train.py , line 276)=> [ep171] (training ) Lm: 6.415 (6.433), Lt: 5.660 (5.679), Acc m&t: 3.62 5.68, Remain: 3 days, 4:51:59, Finish: 2024-11-29 06:03 [11-26 17:11:52] (/home/user/VAR/train.py , line 276)=> [ep171] (training ) Lm: 6.415 (6.433), Lt: 5.660 (5.679), Acc m&t: 3.62 5.68, Remain: 3 days, 4:52:12, Finish: 2024-11-29 06:04 [11-26 17:11:52] (/home/user/VAR/train.py , line 276)=> [ep171] (training ) Lm: 6.415 (6.433), Lt: 5.660 (5.679), Acc m&t: 3.62 5.68, Remain: 3 days, 4:52:21, Finish: 2024-11-29 06:04 [11-26 17:11:52] (/home/user/VAR/train.py , line 276)=> [ep171] (training ) Lm: 6.415 (6.433), Lt: 5.660 (5.679), Acc m&t: 3.62 5.68, Remain: 3 days, 4:51:33, Finish: 2024-11-29 06:03 [11-26 17:11:52] (/home/user/VAR/train.py , line 276)=> [ep171] (training ) Lm: 6.415 (6.433), Lt: 5.660 (5.679), Acc m&t: 3.62 5.68, Remain: 3 days, 4:53:16, Finish: 2024-11-29 06:05 [11-26 17:11:52] (/home/user/VAR/train.py , line 276)=> [ep171] (training ) Lm: 6.415 (6.433), Lt: 5.660 (5.679), Acc m&t: 3.62 5.68, Remain: 3 days, 4:51:40, Finish: 2024-11-29 06:03 [11-26 17:11:52] (/home/user/VAR/train.py , line 276)=> [ep171] (training ) Lm: 6.415 (6.433), Lt: 5.660 (5.679), Acc m&t: 3.62 5.68, Remain: 3 days, 4:52:51, Finish: 2024-11-29 06:04 [11-26 17:11:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 0/1669] eta: 0:25:18 tlr: 0.00013 tnm: 0.28 Lm: 6.396 (6.396) Lt: 5.570 (5.570) Accm: 4.12 (4.12) Acct: 6.51 (6.51) proj_loss: -0.6175 (-0.6175) time: 0.9097 data: 0.0003 [11-26 17:11:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 0/1669] eta: 0:25:18 tlr: 0.00013 tnm: 0.28 Lm: 6.483 (6.483) Lt: 5.786 (5.786) Accm: 3.61 (3.61) Acct: 5.79 (5.79) proj_loss: -0.6216 (-0.6216) time: 0.9098 data: 0.0004 [11-26 17:11:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 0/1669] eta: 0:25:18 tlr: 0.00013 tnm: 0.28 Lm: 6.466 (6.466) Lt: 5.727 (5.727) Accm: 3.58 (3.58) Acct: 5.37 (5.37) proj_loss: -0.6103 (-0.6103) time: 0.9099 data: 0.0003 [11-26 17:11:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 0/1669] eta: 0:25:18 tlr: 0.00013 tnm: 0.28 Lm: 6.504 (6.504) Lt: 5.685 (5.685) Accm: 3.19 (3.19) Acct: 4.68 (4.68) proj_loss: -0.6033 (-0.6033) time: 0.9098 data: 0.0004 [11-26 17:11:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 0/1669] eta: 0:25:19 tlr: 0.00013 tnm: 0.28 Lm: 6.345 (6.345) Lt: 5.566 (5.566) Accm: 4.11 (4.11) Acct: 6.58 (6.58) proj_loss: -0.5989 (-0.5989) time: 0.9102 data: 0.0004 [11-26 17:11:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 0/1669] eta: 0:25:19 tlr: 0.00013 tnm: 0.28 Lm: 6.634 (6.634) Lt: 5.838 (5.838) Accm: 3.16 (3.16) Acct: 5.23 (5.23) proj_loss: -0.6237 (-0.6237) time: 0.9103 data: 0.0003 [11-26 17:11:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 0/1669] eta: 0:25:19 tlr: 0.00013 tnm: 0.28 Lm: 6.463 (6.463) Lt: 5.760 (5.760) Accm: 3.77 (3.77) Acct: 6.06 (6.06) proj_loss: -0.6531 (-0.6531) time: 0.9102 data: 0.0004 [11-26 17:11:53] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 0/1669] eta: 0:25:19 tlr: 0.00013 tnm: 0.28 Lm: 6.288 (6.288) Lt: 5.454 (5.454) Accm: 3.98 (3.98) Acct: 6.40 (6.40) proj_loss: -0.5873 (-0.5873) time: 0.9103 data: 0.0003 [11-26 17:18:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.28 Lm: 6.371 (6.371) Lt: 5.594 (5.594) Accm: 3.85 (3.85) Acct: 6.15 (6.15) proj_loss: -0.5830 (-0.5830) time: 0.9278 data: 0.0003 [11-26 17:18:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.28 Lm: 6.501 (6.501) Lt: 5.711 (5.711) Accm: 3.14 (3.14) Acct: 4.82 (4.82) proj_loss: -0.6184 (-0.6184) time: 0.9278 data: 0.0002 [11-26 17:18:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.28 Lm: 6.389 (6.389) Lt: 5.609 (5.609) Accm: 3.71 (3.71) Acct: 5.72 (5.72) proj_loss: -0.6221 (-0.6221) time: 0.9278 data: 0.0002 [11-26 17:18:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.28 Lm: 6.203 (6.203) Lt: 5.441 (5.441) Accm: 4.55 (4.55) Acct: 7.28 (7.28) proj_loss: -0.6453 (-0.6453) time: 0.9278 data: 0.0003 [11-26 17:18:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.28 Lm: 6.337 (6.337) Lt: 5.513 (5.513) Accm: 4.16 (4.16) Acct: 6.66 (6.66) proj_loss: -0.6136 (-0.6136) time: 0.9278 data: 0.0003 [11-26 17:18:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.28 Lm: 6.513 (6.513) Lt: 5.797 (5.797) Accm: 3.39 (3.39) Acct: 5.48 (5.48) proj_loss: -0.6124 (-0.6124) time: 0.9278 data: 0.0003 [11-26 17:18:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.28 Lm: 6.692 (6.692) Lt: 5.945 (5.945) Accm: 3.15 (3.15) Acct: 5.11 (5.11) proj_loss: -0.6255 (-0.6255) time: 0.9278 data: 0.0003 [11-26 17:18:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.28 Lm: 6.327 (6.327) Lt: 5.563 (5.563) Accm: 3.69 (3.69) Acct: 5.82 (5.82) proj_loss: -0.6108 (-0.6108) time: 0.9278 data: 0.0003 [11-26 17:24:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 834/1669] eta: 0:12:54 tlr: 0.00013 tnm: 0.28 Lm: 6.411 (6.355) Lt: 5.589 (5.572) Accm: 3.77 (3.79) Acct: 5.85 (6.01) proj_loss: -0.6216 (-0.6166) time: 0.9282 data: 0.0003 [11-26 17:24:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 834/1669] eta: 0:12:54 tlr: 0.00013 tnm: 0.28 Lm: 6.440 (6.282) Lt: 5.701 (5.527) Accm: 3.77 (4.13) Acct: 6.06 (6.51) proj_loss: -0.6374 (-0.6293) time: 0.9283 data: 0.0003 [11-26 17:24:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 834/1669] eta: 0:12:54 tlr: 0.00013 tnm: 0.28 Lm: 6.396 (6.368) Lt: 5.570 (5.582) Accm: 4.12 (3.95) Acct: 6.51 (6.32) proj_loss: -0.6175 (-0.6169) time: 0.9283 data: 0.0003 [11-26 17:24:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 834/1669] eta: 0:12:54 tlr: 0.00013 tnm: 0.28 Lm: 6.497 (6.476) Lt: 5.685 (5.671) Accm: 3.19 (3.20) Acct: 4.96 (4.96) proj_loss: -0.6033 (-0.6090) time: 0.9283 data: 0.0003 [11-26 17:24:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 834/1669] eta: 0:12:54 tlr: 0.00013 tnm: 0.28 Lm: 6.315 (6.364) Lt: 5.597 (5.605) Accm: 3.83 (3.81) Acct: 6.06 (5.93) proj_loss: -0.6340 (-0.6309) time: 0.9283 data: 0.0002 [11-26 17:24:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 834/1669] eta: 0:12:54 tlr: 0.00013 tnm: 0.28 Lm: 6.454 (6.414) Lt: 5.715 (5.634) Accm: 3.98 (4.01) Acct: 6.40 (6.36) proj_loss: -0.5873 (-0.6021) time: 0.9283 data: 0.0003 [11-26 17:24:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 834/1669] eta: 0:12:54 tlr: 0.00013 tnm: 0.28 Lm: 6.634 (6.540) Lt: 5.838 (5.791) Accm: 3.16 (3.47) Acct: 5.23 (5.59) proj_loss: -0.6237 (-0.6245) time: 0.9283 data: 0.0003 [11-26 17:24:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [ 834/1669] eta: 0:12:54 tlr: 0.00013 tnm: 0.28 Lm: 6.366 (6.464) Lt: 5.566 (5.713) Accm: 3.45 (3.41) Acct: 5.82 (5.59) proj_loss: -0.6085 (-0.6111) time: 0.9283 data: 0.0003 [11-26 17:31:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.26 Lm: 6.355 (6.368) Lt: 5.555 (5.584) Accm: 3.78 (3.95) Acct: 6.20 (6.34) proj_loss: -0.6172 (-0.6167) time: 0.9282 data: 0.0003 [11-26 17:31:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.26 Lm: 6.452 (6.354) Lt: 5.730 (5.601) Accm: 3.65 (3.98) Acct: 5.79 (6.26) proj_loss: -0.6262 (-0.6257) time: 0.9282 data: 0.0003 [11-26 17:31:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.26 Lm: 6.541 (6.517) Lt: 5.749 (5.758) Accm: 3.37 (3.50) Acct: 5.56 (5.66) proj_loss: -0.6231 (-0.6217) time: 0.9282 data: 0.0003 [11-26 17:31:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.26 Lm: 6.412 (6.415) Lt: 5.644 (5.633) Accm: 3.83 (3.79) Acct: 6.08 (5.95) proj_loss: -0.6206 (-0.6213) time: 0.9282 data: 0.0003 [11-26 17:31:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.26 Lm: 6.391 (6.391) Lt: 5.638 (5.624) Accm: 3.71 (3.75) Acct: 5.85 (5.86) proj_loss: -0.6241 (-0.6268) time: 0.9282 data: 0.0002 [11-26 17:31:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.26 Lm: 6.461 (6.407) Lt: 5.638 (5.612) Accm: 3.25 (3.41) Acct: 5.10 (5.20) proj_loss: -0.6184 (-0.6160) time: 0.9282 data: 0.0002 [11-26 17:31:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.26 Lm: 6.385 (6.356) Lt: 5.587 (5.575) Accm: 3.69 (3.71) Acct: 5.82 (5.91) proj_loss: -0.6250 (-0.6237) time: 0.9282 data: 0.0002 [11-26 17:31:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.26 Lm: 6.443 (6.418) Lt: 5.675 (5.634) Accm: 3.85 (3.82) Acct: 6.15 (6.07) proj_loss: -0.5983 (-0.6039) time: 0.9282 data: 0.0002 [11-26 17:37:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.431 (6.419) Lt: 5.665 (5.640) Accm: 3.73 (3.78) Acct: 5.89 (6.03) proj_loss: -0.6093 (-0.6054) time: 0.9287 data: 0.0018 [11-26 17:37:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 172/350] Total time: 0:25:49 (0.928 s / it) [11-26 17:37:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.315 (6.323) Lt: 5.597 (5.560) Accm: 3.83 (3.97) Acct: 6.06 (6.19) proj_loss: -0.6188 (-0.6252) time: 0.9287 data: 0.0014 [11-26 17:37:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.411 (6.372) Lt: 5.589 (5.588) Accm: 3.61 (3.65) Acct: 5.79 (5.87) proj_loss: -0.6216 (-0.6171) time: 0.9287 data: 0.0019 [11-26 17:37:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.440 (6.365) Lt: 5.701 (5.620) Accm: 3.77 (3.97) Acct: 6.06 (6.25) proj_loss: -0.6374 (-0.6312) time: 0.9287 data: 0.0015 [11-26 17:37:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.396 (6.384) Lt: 5.570 (5.600) Accm: 4.12 (3.86) Acct: 6.51 (6.11) proj_loss: -0.6237 (-0.6233) time: 0.9287 data: 0.0017 [11-26 17:37:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.490 (6.424) Lt: 5.685 (5.655) Accm: 3.31 (3.40) Acct: 5.20 (5.20) proj_loss: -0.6335 (-0.6214) time: 0.9287 data: 0.0017 [11-26 17:37:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.345 (6.359) Lt: 5.545 (5.571) Accm: 3.72 (3.90) Acct: 5.96 (6.27) proj_loss: -0.6259 (-0.6191) time: 0.9287 data: 0.0016 [11-26 17:37:41] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 172/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.447 (6.487) Lt: 5.661 (5.733) Accm: 3.58 (3.54) Acct: 5.89 (5.72) proj_loss: -0.6237 (-0.6246) time: 0.9287 data: 0.0019 [11-26 17:37:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 172/350] Total time: 0:25:49 (0.928 s / it) [11-26 17:37:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 172/350] Total time: 0:25:49 (0.928 s / it) [11-26 17:37:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 172/350] Total time: 0:25:49 (0.928 s / it) [11-26 17:37:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 172/350] Total time: 0:25:49 (0.928 s / it) [11-26 17:37:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 172/350] Total time: 0:25:49 (0.928 s / it) [11-26 17:37:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 172/350] Total time: 0:25:49 (0.928 s / it) [11-26 17:37:41] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 172/350] Total time: 0:25:49 (0.928 s / it) [11-26 17:37:41] (/home/user/VAR/train.py , line 276)=> [ep172] (training ) Lm: 6.412 (6.412), Lt: 5.654 (5.654), Acc m&t: 3.65 5.71, Remain: 3 days, 4:42:30, Finish: 2024-11-29 06:20 [11-26 17:37:41] (/home/user/VAR/train.py , line 276)=> [ep172] (training ) Lm: 6.412 (6.412), Lt: 5.654 (5.654), Acc m&t: 3.65 5.71, Remain: 3 days, 4:43:12, Finish: 2024-11-29 06:20 [11-26 17:37:41] (/home/user/VAR/train.py , line 276)=> [ep172] (training ) Lm: 6.412 (6.412), Lt: 5.654 (5.654), Acc m&t: 3.65 5.71, Remain: 3 days, 4:43:15, Finish: 2024-11-29 06:20 [11-26 17:37:41] (/home/user/VAR/train.py , line 276)=> [ep172] (training ) Lm: 6.412 (6.412), Lt: 5.654 (5.654), Acc m&t: 3.65 5.71, Remain: 3 days, 4:43:28, Finish: 2024-11-29 06:21 [11-26 17:37:41] (/home/user/VAR/train.py , line 276)=> [ep172] (training ) Lm: 6.412 (6.412), Lt: 5.654 (5.654), Acc m&t: 3.65 5.71, Remain: 3 days, 4:43:15, Finish: 2024-11-29 06:20 [11-26 17:37:41] (/home/user/VAR/train.py , line 276)=> [ep172] (training ) Lm: 6.412 (6.412), Lt: 5.654 (5.654), Acc m&t: 3.65 5.71, Remain: 3 days, 4:43:18, Finish: 2024-11-29 06:20 [11-26 17:37:41] (/home/user/VAR/train.py , line 276)=> [ep172] (training ) Lm: 6.412 (6.412), Lt: 5.654 (5.654), Acc m&t: 3.65 5.71, Remain: 3 days, 4:43:45, Finish: 2024-11-29 06:21 [11-26 17:37:41] (/home/user/VAR/train.py , line 276)=> [ep172] (training ) Lm: 6.412 (6.412), Lt: 5.654 (5.654), Acc m&t: 3.65 5.71, Remain: 3 days, 4:41:52, Finish: 2024-11-29 06:19 [11-26 17:37:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 0/1669] eta: 0:24:34 tlr: 0.00013 tnm: 0.28 Lm: 6.329 (6.329) Lt: 5.574 (5.574) Accm: 3.32 (3.32) Acct: 5.13 (5.13) proj_loss: -0.6074 (-0.6074) time: 0.8836 data: 0.0004 [11-26 17:37:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 0/1669] eta: 0:24:35 tlr: 0.00013 tnm: 0.28 Lm: 6.108 (6.108) Lt: 5.298 (5.298) Accm: 4.56 (4.56) Acct: 7.02 (7.02) proj_loss: -0.6320 (-0.6320) time: 0.8840 data: 0.0003 [11-26 17:37:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 0/1669] eta: 0:24:35 tlr: 0.00013 tnm: 0.28 Lm: 6.378 (6.378) Lt: 5.522 (5.522) Accm: 3.70 (3.70) Acct: 5.99 (5.99) proj_loss: -0.6050 (-0.6050) time: 0.8842 data: 0.0004 [11-26 17:37:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 0/1669] eta: 0:24:35 tlr: 0.00013 tnm: 0.28 Lm: 6.537 (6.537) Lt: 5.764 (5.764) Accm: 2.99 (2.99) Acct: 4.82 (4.82) proj_loss: -0.5955 (-0.5955) time: 0.8841 data: 0.0003 [11-26 17:37:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 0/1669] eta: 0:24:36 tlr: 0.00013 tnm: 0.28 Lm: 6.309 (6.309) Lt: 5.575 (5.575) Accm: 4.50 (4.50) Acct: 7.02 (7.02) proj_loss: -0.6304 (-0.6304) time: 0.8845 data: 0.0003 [11-26 17:37:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 0/1669] eta: 0:24:36 tlr: 0.00013 tnm: 0.28 Lm: 6.466 (6.466) Lt: 5.603 (5.603) Accm: 3.50 (3.50) Acct: 5.58 (5.58) proj_loss: -0.5820 (-0.5820) time: 0.8847 data: 0.0003 [11-26 17:37:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 0/1669] eta: 0:24:35 tlr: 0.00013 tnm: 0.28 Lm: 6.311 (6.311) Lt: 5.446 (5.446) Accm: 3.89 (3.89) Acct: 5.96 (5.96) proj_loss: -0.6266 (-0.6266) time: 0.8842 data: 0.0004 [11-26 17:37:42] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 0/1669] eta: 0:24:36 tlr: 0.00013 tnm: 0.28 Lm: 6.270 (6.270) Lt: 5.523 (5.523) Accm: 3.92 (3.92) Acct: 6.13 (6.13) proj_loss: -0.6258 (-0.6258) time: 0.8848 data: 0.0004 [11-26 17:44:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 417/1669] eta: 0:19:46 tlr: 0.00013 tnm: 0.27 Lm: 6.465 (6.465) Lt: 5.732 (5.732) Accm: 3.47 (3.47) Acct: 5.46 (5.46) proj_loss: -0.6362 (-0.6362) time: 0.9264 data: 0.0003 [11-26 17:44:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 417/1669] eta: 0:19:46 tlr: 0.00013 tnm: 0.27 Lm: 6.323 (6.323) Lt: 5.498 (5.498) Accm: 3.99 (3.99) Acct: 6.28 (6.28) proj_loss: -0.6107 (-0.6107) time: 0.9264 data: 0.0003 [11-26 17:44:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 417/1669] eta: 0:19:46 tlr: 0.00013 tnm: 0.27 Lm: 6.306 (6.306) Lt: 5.539 (5.539) Accm: 4.17 (4.17) Acct: 6.63 (6.63) proj_loss: -0.6188 (-0.6188) time: 0.9264 data: 0.0002 [11-26 17:44:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 417/1669] eta: 0:19:46 tlr: 0.00013 tnm: 0.27 Lm: 6.384 (6.384) Lt: 5.647 (5.647) Accm: 3.25 (3.25) Acct: 5.03 (5.03) proj_loss: -0.6234 (-0.6234) time: 0.9264 data: 0.0003 [11-26 17:44:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 417/1669] eta: 0:19:46 tlr: 0.00013 tnm: 0.27 Lm: 6.259 (6.259) Lt: 5.518 (5.518) Accm: 3.93 (3.93) Acct: 5.97 (5.97) proj_loss: -0.6324 (-0.6324) time: 0.9264 data: 0.0002 [11-26 17:44:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 417/1669] eta: 0:19:46 tlr: 0.00013 tnm: 0.27 Lm: 6.489 (6.489) Lt: 5.687 (5.687) Accm: 3.29 (3.29) Acct: 5.23 (5.23) proj_loss: -0.5925 (-0.5925) time: 0.9264 data: 0.0003 [11-26 17:44:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 417/1669] eta: 0:19:46 tlr: 0.00013 tnm: 0.27 Lm: 6.556 (6.556) Lt: 5.778 (5.778) Accm: 3.04 (3.04) Acct: 4.82 (4.82) proj_loss: -0.5919 (-0.5919) time: 0.9264 data: 0.0002 [11-26 17:44:17] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 417/1669] eta: 0:19:46 tlr: 0.00013 tnm: 0.27 Lm: 6.204 (6.204) Lt: 5.394 (5.394) Accm: 3.94 (3.94) Acct: 6.18 (6.18) proj_loss: -0.6357 (-0.6357) time: 0.9264 data: 0.0003 [11-26 17:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 834/1669] eta: 0:13:02 tlr: 0.00013 tnm: 0.28 Lm: 6.311 (6.313) Lt: 5.446 (5.538) Accm: 3.89 (3.77) Acct: 5.96 (5.89) proj_loss: -0.6266 (-0.6304) time: 0.9272 data: 0.0003 [11-26 17:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 834/1669] eta: 0:13:02 tlr: 0.00013 tnm: 0.28 Lm: 6.409 (6.350) Lt: 5.723 (5.586) Accm: 3.41 (3.76) Acct: 5.54 (5.83) proj_loss: -0.6320 (-0.6290) time: 0.9272 data: 0.0002 [11-26 17:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 834/1669] eta: 0:13:02 tlr: 0.00013 tnm: 0.28 Lm: 6.378 (6.371) Lt: 5.522 (5.557) Accm: 3.70 (3.80) Acct: 5.99 (5.97) proj_loss: -0.6157 (-0.6124) time: 0.9272 data: 0.0002 [11-26 17:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 834/1669] eta: 0:13:02 tlr: 0.00013 tnm: 0.28 Lm: 6.309 (6.313) Lt: 5.556 (5.544) Accm: 3.88 (4.07) Acct: 6.27 (6.51) proj_loss: -0.6106 (-0.6161) time: 0.9272 data: 0.0003 [11-26 17:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 834/1669] eta: 0:13:02 tlr: 0.00013 tnm: 0.28 Lm: 6.575 (6.567) Lt: 5.792 (5.792) Accm: 3.10 (3.19) Acct: 4.82 (4.84) proj_loss: -0.5884 (-0.5883) time: 0.9272 data: 0.0003 [11-26 17:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 834/1669] eta: 0:13:02 tlr: 0.00013 tnm: 0.28 Lm: 6.466 (6.440) Lt: 5.603 (5.589) Accm: 3.50 (3.62) Acct: 5.58 (5.88) proj_loss: -0.5974 (-0.5941) time: 0.9272 data: 0.0003 [11-26 17:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 834/1669] eta: 0:13:02 tlr: 0.00013 tnm: 0.28 Lm: 6.270 (6.351) Lt: 5.523 (5.583) Accm: 3.92 (3.96) Acct: 6.13 (6.07) proj_loss: -0.6274 (-0.6333) time: 0.9272 data: 0.0003 [11-26 17:50:44] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [ 834/1669] eta: 0:13:02 tlr: 0.00013 tnm: 0.28 Lm: 6.439 (6.426) Lt: 5.720 (5.700) Accm: 3.32 (3.31) Acct: 5.13 (5.15) proj_loss: -0.6394 (-0.6297) time: 0.9272 data: 0.0002 [11-26 17:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [1251/1669] eta: 0:06:30 tlr: 0.00013 tnm: 0.27 Lm: 6.471 (6.445) Lt: 5.758 (5.724) Accm: 3.25 (3.26) Acct: 5.03 (5.10) proj_loss: -0.6326 (-0.6287) time: 0.9268 data: 0.0002 [11-26 17:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [1251/1669] eta: 0:06:30 tlr: 0.00013 tnm: 0.27 Lm: 6.312 (6.352) Lt: 5.552 (5.582) Accm: 3.66 (3.82) Acct: 5.70 (5.87) proj_loss: -0.6266 (-0.6302) time: 0.9268 data: 0.0003 [11-26 17:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [1251/1669] eta: 0:06:30 tlr: 0.00013 tnm: 0.27 Lm: 6.457 (6.388) Lt: 5.717 (5.617) Accm: 3.39 (3.66) Acct: 5.25 (5.61) proj_loss: -0.6270 (-0.6264) time: 0.9268 data: 0.0002 [11-26 17:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [1251/1669] eta: 0:06:30 tlr: 0.00013 tnm: 0.27 Lm: 6.556 (6.530) Lt: 5.778 (5.751) Accm: 3.29 (3.35) Acct: 4.86 (5.13) proj_loss: -0.5919 (-0.5993) time: 0.9268 data: 0.0003 [11-26 17:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [1251/1669] eta: 0:06:30 tlr: 0.00013 tnm: 0.27 Lm: 6.420 (6.394) Lt: 5.575 (5.575) Accm: 3.56 (3.70) Acct: 5.91 (5.93) proj_loss: -0.6160 (-0.6166) time: 0.9268 data: 0.0003 [11-26 17:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [1251/1669] eta: 0:06:30 tlr: 0.00013 tnm: 0.27 Lm: 6.421 (6.398) Lt: 5.637 (5.654) Accm: 3.66 (3.57) Acct: 5.63 (5.60) proj_loss: -0.6313 (-0.6318) time: 0.9268 data: 0.0002 [11-26 17:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [1251/1669] eta: 0:06:30 tlr: 0.00013 tnm: 0.27 Lm: 6.306 (6.279) Lt: 5.531 (5.535) Accm: 4.19 (4.19) Acct: 6.37 (6.50) proj_loss: -0.6205 (-0.6235) time: 0.9268 data: 0.0002 [11-26 17:57:11] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [1251/1669] eta: 0:06:30 tlr: 0.00013 tnm: 0.27 Lm: 6.489 (6.471) Lt: 5.687 (5.665) Accm: 3.57 (3.63) Acct: 5.51 (5.77) proj_loss: -0.6002 (-0.6024) time: 0.9268 data: 0.0003 [11-26 18:03:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.466 (6.463) Lt: 5.709 (5.673) Accm: 3.50 (3.58) Acct: 5.44 (5.68) proj_loss: -0.6029 (-0.6052) time: 0.9270 data: 0.0016 [11-26 18:03:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 173/350] Total time: 0:25:55 (0.932 s / it) [11-26 18:03:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.378 (6.368) Lt: 5.522 (5.554) Accm: 3.70 (3.71) Acct: 5.99 (6.02) proj_loss: -0.6157 (-0.6145) time: 0.9271 data: 0.0015 [11-26 18:03:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.354 (6.367) Lt: 5.580 (5.594) Accm: 3.41 (3.74) Acct: 5.34 (5.76) proj_loss: -0.6258 (-0.6231) time: 0.9270 data: 0.0020 [11-26 18:03:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.504 (6.417) Lt: 5.723 (5.648) Accm: 3.37 (3.56) Acct: 4.96 (5.48) proj_loss: -0.6221 (-0.6255) time: 0.9271 data: 0.0014 [11-26 18:03:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.458 (6.448) Lt: 5.720 (5.722) Accm: 3.32 (3.32) Acct: 5.13 (5.11) proj_loss: -0.6280 (-0.6285) time: 0.9270 data: 0.0016 [11-26 18:03:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.309 (6.322) Lt: 5.556 (5.585) Accm: 3.88 (4.00) Acct: 6.27 (6.16) proj_loss: -0.6231 (-0.6234) time: 0.9270 data: 0.0018 [11-26 18:03:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.575 (6.553) Lt: 5.792 (5.768) Accm: 3.10 (3.26) Acct: 4.82 (4.99) proj_loss: -0.5899 (-0.5974) time: 0.9270 data: 0.0015 [11-26 18:03:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 173/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.349 (6.388) Lt: 5.711 (5.666) Accm: 3.89 (3.64) Acct: 5.68 (5.62) proj_loss: -0.6266 (-0.6284) time: 0.9271 data: 0.0019 [11-26 18:03:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 173/350] Total time: 0:25:55 (0.932 s / it) [11-26 18:03:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 173/350] Total time: 0:25:55 (0.932 s / it) [11-26 18:03:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 173/350] Total time: 0:25:55 (0.932 s / it) [11-26 18:03:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 173/350] Total time: 0:25:55 (0.932 s / it) [11-26 18:03:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 173/350] Total time: 0:25:55 (0.932 s / it) [11-26 18:03:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 173/350] Total time: 0:25:55 (0.932 s / it) [11-26 18:03:37] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 173/350] Total time: 0:25:55 (0.932 s / it) [11-26 18:03:37] (/home/user/VAR/train.py , line 276)=> [ep173] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.650), Acc m&t: 3.65 5.71, Remain: 3 days, 4:06:38, Finish: 2024-11-29 06:10 [11-26 18:03:37] (/home/user/VAR/train.py , line 276)=> [ep173] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.650), Acc m&t: 3.65 5.71, Remain: 3 days, 4:03:14, Finish: 2024-11-29 06:06 [11-26 18:03:37] (/home/user/VAR/train.py , line 276)=> [ep173] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.650), Acc m&t: 3.65 5.71, Remain: 3 days, 4:03:13, Finish: 2024-11-29 06:06 [11-26 18:03:37] (/home/user/VAR/train.py , line 276)=> [ep173] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.650), Acc m&t: 3.65 5.71, Remain: 3 days, 4:06:04, Finish: 2024-11-29 06:09 [11-26 18:03:37] (/home/user/VAR/train.py , line 276)=> [ep173] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.650), Acc m&t: 3.65 5.71, Remain: 3 days, 4:03:32, Finish: 2024-11-29 06:07 [11-26 18:03:37] (/home/user/VAR/train.py , line 276)=> [ep173] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.650), Acc m&t: 3.65 5.71, Remain: 3 days, 4:05:12, Finish: 2024-11-29 06:08 [11-26 18:03:37] (/home/user/VAR/train.py , line 276)=> [ep173] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.650), Acc m&t: 3.65 5.71, Remain: 3 days, 4:05:49, Finish: 2024-11-29 06:09 [11-26 18:03:37] (/home/user/VAR/train.py , line 276)=> [ep173] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.650), Acc m&t: 3.65 5.71, Remain: 3 days, 4:04:33, Finish: 2024-11-29 06:08 [11-26 18:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 0/1669] eta: 0:25:20 tlr: 0.00013 tnm: 0.27 Lm: 6.274 (6.274) Lt: 5.484 (5.484) Accm: 3.69 (3.69) Acct: 5.65 (5.65) proj_loss: -0.6154 (-0.6154) time: 0.9111 data: 0.0004 [11-26 18:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 0/1669] eta: 0:25:20 tlr: 0.00013 tnm: 0.27 Lm: 6.551 (6.551) Lt: 5.823 (5.823) Accm: 3.12 (3.12) Acct: 4.58 (4.58) proj_loss: -0.6212 (-0.6212) time: 0.9111 data: 0.0004 [11-26 18:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 0/1669] eta: 0:25:20 tlr: 0.00013 tnm: 0.27 Lm: 6.336 (6.336) Lt: 5.565 (5.565) Accm: 3.72 (3.72) Acct: 5.61 (5.61) proj_loss: -0.6034 (-0.6034) time: 0.9113 data: 0.0004 [11-26 18:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 0/1669] eta: 0:25:20 tlr: 0.00013 tnm: 0.27 Lm: 6.329 (6.329) Lt: 5.607 (5.607) Accm: 3.73 (3.73) Acct: 5.72 (5.72) proj_loss: -0.6266 (-0.6266) time: 0.9113 data: 0.0004 [11-26 18:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 0/1669] eta: 0:25:20 tlr: 0.00013 tnm: 0.27 Lm: 6.493 (6.493) Lt: 5.792 (5.792) Accm: 3.04 (3.04) Acct: 4.34 (4.34) proj_loss: -0.6076 (-0.6076) time: 0.9111 data: 0.0003 [11-26 18:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 0/1669] eta: 0:25:21 tlr: 0.00013 tnm: 0.27 Lm: 6.841 (6.841) Lt: 6.203 (6.203) Accm: 2.75 (2.75) Acct: 4.58 (4.58) proj_loss: -0.6351 (-0.6351) time: 0.9116 data: 0.0004 [11-26 18:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 0/1669] eta: 0:25:21 tlr: 0.00013 tnm: 0.27 Lm: 6.591 (6.591) Lt: 5.886 (5.886) Accm: 2.96 (2.96) Acct: 4.51 (4.51) proj_loss: -0.6285 (-0.6285) time: 0.9118 data: 0.0004 [11-26 18:03:38] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 0/1669] eta: 0:25:25 tlr: 0.00013 tnm: 0.27 Lm: 6.246 (6.246) Lt: 5.462 (5.462) Accm: 4.39 (4.39) Acct: 6.68 (6.68) proj_loss: -0.6410 (-0.6410) time: 0.9139 data: 0.0004 [11-26 18:10:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.27 Lm: 6.378 (6.378) Lt: 5.606 (5.606) Accm: 3.93 (3.93) Acct: 5.97 (5.97) proj_loss: -0.6408 (-0.6408) time: 0.9259 data: 0.0003 [11-26 18:10:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.27 Lm: 6.296 (6.296) Lt: 5.531 (5.531) Accm: 3.95 (3.95) Acct: 6.01 (6.01) proj_loss: -0.6236 (-0.6236) time: 0.9259 data: 0.0002 [11-26 18:10:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.27 Lm: 6.539 (6.539) Lt: 5.825 (5.825) Accm: 3.01 (3.01) Acct: 4.51 (4.51) proj_loss: -0.6039 (-0.6039) time: 0.9259 data: 0.0003 [11-26 18:10:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.27 Lm: 6.257 (6.257) Lt: 5.491 (5.491) Accm: 4.01 (4.01) Acct: 6.22 (6.22) proj_loss: -0.6247 (-0.6247) time: 0.9259 data: 0.0003 [11-26 18:10:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.27 Lm: 6.357 (6.357) Lt: 5.612 (5.612) Accm: 3.93 (3.93) Acct: 6.13 (6.13) proj_loss: -0.6175 (-0.6175) time: 0.9259 data: 0.0002 [11-26 18:10:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.27 Lm: 6.667 (6.667) Lt: 5.998 (5.998) Accm: 3.13 (3.13) Acct: 4.87 (4.87) proj_loss: -0.6204 (-0.6204) time: 0.9259 data: 0.0002 [11-26 18:10:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.27 Lm: 6.494 (6.494) Lt: 5.760 (5.760) Accm: 3.19 (3.19) Acct: 4.72 (4.72) proj_loss: -0.6159 (-0.6159) time: 0.9259 data: 0.0003 [11-26 18:10:04] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.27 Lm: 6.628 (6.628) Lt: 5.896 (5.896) Accm: 3.00 (3.00) Acct: 4.75 (4.75) proj_loss: -0.6158 (-0.6158) time: 0.9259 data: 0.0003 [11-26 18:16:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 834/1669] eta: 0:13:15 tlr: 0.00013 tnm: 0.27 Lm: 6.591 (6.563) Lt: 5.886 (5.830) Accm: 3.04 (3.14) Acct: 4.99 (5.00) proj_loss: -0.6285 (-0.6286) time: 0.9275 data: 0.0003 [11-26 18:16:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 834/1669] eta: 0:13:15 tlr: 0.00013 tnm: 0.27 Lm: 6.274 (6.371) Lt: 5.499 (5.604) Accm: 3.69 (3.79) Acct: 5.65 (5.98) proj_loss: -0.6154 (-0.6171) time: 0.9275 data: 0.0003 [11-26 18:16:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 834/1669] eta: 0:13:15 tlr: 0.00013 tnm: 0.27 Lm: 6.547 (6.380) Lt: 5.795 (5.619) Accm: 3.12 (3.64) Acct: 4.86 (5.62) proj_loss: -0.6261 (-0.6291) time: 0.9275 data: 0.0002 [11-26 18:16:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 834/1669] eta: 0:13:15 tlr: 0.00013 tnm: 0.27 Lm: 6.384 (6.453) Lt: 5.617 (5.690) Accm: 3.73 (3.73) Acct: 5.72 (5.90) proj_loss: -0.6199 (-0.6183) time: 0.9275 data: 0.0003 [11-26 18:16:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 834/1669] eta: 0:13:15 tlr: 0.00013 tnm: 0.27 Lm: 6.371 (6.453) Lt: 5.615 (5.711) Accm: 3.72 (3.44) Acct: 5.61 (5.19) proj_loss: -0.6091 (-0.6137) time: 0.9275 data: 0.0003 [11-26 18:16:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 834/1669] eta: 0:13:15 tlr: 0.00013 tnm: 0.27 Lm: 6.493 (6.466) Lt: 5.792 (5.701) Accm: 3.04 (3.33) Acct: 4.68 (5.12) proj_loss: -0.6076 (-0.6064) time: 0.9275 data: 0.0003 [11-26 18:16:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 834/1669] eta: 0:13:15 tlr: 0.00013 tnm: 0.27 Lm: 6.720 (6.685) Lt: 6.014 (6.003) Accm: 2.75 (2.94) Acct: 4.58 (4.47) proj_loss: -0.6234 (-0.6214) time: 0.9275 data: 0.0002 [11-26 18:16:52] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [ 834/1669] eta: 0:13:15 tlr: 0.00013 tnm: 0.27 Lm: 6.509 (6.451) Lt: 5.750 (5.683) Accm: 3.48 (3.58) Acct: 5.27 (5.49) proj_loss: -0.6407 (-0.6356) time: 0.9275 data: 0.0003 [11-26 18:23:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [1251/1669] eta: 0:06:34 tlr: 0.00013 tnm: 0.27 Lm: 6.469 (6.445) Lt: 5.701 (5.675) Accm: 3.67 (3.65) Acct: 5.48 (5.54) proj_loss: -0.6329 (-0.6292) time: 0.9260 data: 0.0003 [11-26 18:23:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [1251/1669] eta: 0:06:34 tlr: 0.00013 tnm: 0.27 Lm: 6.327 (6.373) Lt: 5.565 (5.610) Accm: 3.68 (3.76) Acct: 5.58 (5.85) proj_loss: -0.6203 (-0.6191) time: 0.9260 data: 0.0002 [11-26 18:23:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [1251/1669] eta: 0:06:34 tlr: 0.00013 tnm: 0.27 Lm: 6.492 (6.472) Lt: 5.770 (5.713) Accm: 3.20 (3.33) Acct: 4.98 (5.16) proj_loss: -0.6096 (-0.6162) time: 0.9260 data: 0.0003 [11-26 18:23:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [1251/1669] eta: 0:06:34 tlr: 0.00013 tnm: 0.27 Lm: 6.533 (6.415) Lt: 5.756 (5.644) Accm: 3.23 (3.56) Acct: 5.01 (5.51) proj_loss: -0.6236 (-0.6252) time: 0.9261 data: 0.0003 [11-26 18:23:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [1251/1669] eta: 0:06:34 tlr: 0.00013 tnm: 0.27 Lm: 6.606 (6.626) Lt: 5.903 (5.934) Accm: 3.08 (3.06) Acct: 4.87 (4.67) proj_loss: -0.6293 (-0.6254) time: 0.9260 data: 0.0002 [11-26 18:23:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [1251/1669] eta: 0:06:34 tlr: 0.00013 tnm: 0.27 Lm: 6.402 (6.448) Lt: 5.661 (5.710) Accm: 3.57 (3.44) Acct: 5.20 (5.09) proj_loss: -0.6062 (-0.6101) time: 0.9260 data: 0.0003 [11-26 18:23:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [1251/1669] eta: 0:06:34 tlr: 0.00013 tnm: 0.27 Lm: 6.628 (6.609) Lt: 5.896 (5.882) Accm: 3.00 (3.04) Acct: 4.75 (4.88) proj_loss: -0.6158 (-0.6169) time: 0.9260 data: 0.0003 [11-26 18:23:19] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [1251/1669] eta: 0:06:34 tlr: 0.00013 tnm: 0.27 Lm: 6.376 (6.432) Lt: 5.612 (5.659) Accm: 3.79 (3.76) Acct: 5.80 (5.90) proj_loss: -0.6141 (-0.6156) time: 0.9261 data: 0.0003 [11-26 18:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.29 Lm: 6.367 (6.402) Lt: 5.607 (5.624) Accm: 3.85 (3.93) Acct: 5.89 (6.24) proj_loss: -0.6146 (-0.6154) time: 0.9270 data: 0.0016 [11-26 18:29:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 174/350] Total time: 0:26:08 (0.940 s / it) [11-26 18:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.29 Lm: 6.325 (6.363) Lt: 5.577 (5.604) Accm: 3.69 (3.77) Acct: 5.65 (5.90) proj_loss: -0.6154 (-0.6142) time: 0.9270 data: 0.0016 [11-26 18:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.29 Lm: 6.410 (6.440) Lt: 5.646 (5.697) Accm: 3.61 (3.47) Acct: 5.58 (5.19) proj_loss: -0.6061 (-0.6093) time: 0.9271 data: 0.0017 [11-26 18:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.29 Lm: 6.518 (6.391) Lt: 5.717 (5.619) Accm: 3.34 (3.71) Acct: 5.17 (5.80) proj_loss: -0.6212 (-0.6212) time: 0.9270 data: 0.0016 [11-26 18:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.29 Lm: 6.591 (6.565) Lt: 5.886 (5.835) Accm: 3.04 (3.17) Acct: 4.99 (5.12) proj_loss: -0.6056 (-0.6147) time: 0.9271 data: 0.0017 [11-26 18:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.29 Lm: 6.493 (6.498) Lt: 5.792 (5.742) Accm: 3.25 (3.32) Acct: 5.06 (5.14) proj_loss: -0.6116 (-0.6183) time: 0.9271 data: 0.0014 [11-26 18:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.29 Lm: 6.661 (6.633) Lt: 6.014 (5.952) Accm: 3.34 (3.11) Acct: 5.17 (4.77) proj_loss: -0.6351 (-0.6282) time: 0.9271 data: 0.0016 [11-26 18:29:45] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 174/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.29 Lm: 6.428 (6.433) Lt: 5.652 (5.658) Accm: 3.48 (3.61) Acct: 5.27 (5.46) proj_loss: -0.6251 (-0.6251) time: 0.9271 data: 0.0019 [11-26 18:29:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 174/350] Total time: 0:26:08 (0.940 s / it) [11-26 18:29:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 174/350] Total time: 0:26:08 (0.940 s / it) [11-26 18:29:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 174/350] Total time: 0:26:08 (0.940 s / it) [11-26 18:29:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 174/350] Total time: 0:26:08 (0.940 s / it) [11-26 18:29:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 174/350] Total time: 0:26:08 (0.940 s / it) [11-26 18:29:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 174/350] Total time: 0:26:08 (0.940 s / it) [11-26 18:29:45] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 174/350] Total time: 0:26:08 (0.940 s / it) [11-26 18:29:45] (/home/user/VAR/train.py , line 276)=> [ep174] (training ) Lm: 6.409 (6.423), Lt: 5.650 (5.664), Acc m&t: 3.65 5.71, Remain: 3 days, 3:47:39, Finish: 2024-11-29 06:17 [11-26 18:29:45] (/home/user/VAR/train.py , line 276)=> [ep174] (training ) Lm: 6.409 (6.423), Lt: 5.650 (5.664), Acc m&t: 3.65 5.71, Remain: 3 days, 3:48:24, Finish: 2024-11-29 06:18 [11-26 18:29:45] (/home/user/VAR/train.py , line 276)=> [ep174] (training ) Lm: 6.409 (6.423), Lt: 5.650 (5.664), Acc m&t: 3.65 5.71, Remain: 3 days, 3:48:11, Finish: 2024-11-29 06:17 [11-26 18:29:45] (/home/user/VAR/train.py , line 276)=> [ep174] (training ) Lm: 6.409 (6.423), Lt: 5.650 (5.664), Acc m&t: 3.65 5.71, Remain: 3 days, 3:47:48, Finish: 2024-11-29 06:17 [11-26 18:29:45] (/home/user/VAR/train.py , line 276)=> [ep174] (training ) Lm: 6.409 (6.423), Lt: 5.650 (5.664), Acc m&t: 3.65 5.71, Remain: 3 days, 3:49:03, Finish: 2024-11-29 06:18 [11-26 18:29:45] (/home/user/VAR/train.py , line 276)=> [ep174] (training ) Lm: 6.409 (6.423), Lt: 5.650 (5.664), Acc m&t: 3.65 5.71, Remain: 3 days, 3:47:16, Finish: 2024-11-29 06:17 [11-26 18:29:45] (/home/user/VAR/train.py , line 276)=> [ep174] (training ) Lm: 6.409 (6.423), Lt: 5.650 (5.664), Acc m&t: 3.65 5.71, Remain: 3 days, 3:48:45, Finish: 2024-11-29 06:18 [11-26 18:29:45] (/home/user/VAR/train.py , line 276)=> [ep174] (training ) Lm: 6.409 (6.423), Lt: 5.650 (5.664), Acc m&t: 3.65 5.71, Remain: 3 days, 3:47:52, Finish: 2024-11-29 06:17 [11-26 18:29:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 0/1669] eta: 0:24:40 tlr: 0.00013 tnm: 0.28 Lm: 6.536 (6.536) Lt: 5.900 (5.900) Accm: 3.47 (3.47) Acct: 5.48 (5.48) proj_loss: -0.5983 (-0.5983) time: 0.8871 data: 0.0003 [11-26 18:29:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 0/1669] eta: 0:24:30 tlr: 0.00013 tnm: 0.28 Lm: 6.520 (6.520) Lt: 5.871 (5.871) Accm: 3.23 (3.23) Acct: 4.44 (4.44) proj_loss: -0.6335 (-0.6335) time: 0.8813 data: 0.0003 [11-26 18:29:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 0/1669] eta: 0:24:40 tlr: 0.00013 tnm: 0.28 Lm: 6.501 (6.501) Lt: 5.709 (5.709) Accm: 3.28 (3.28) Acct: 5.44 (5.44) proj_loss: -0.6272 (-0.6272) time: 0.8871 data: 0.0004 [11-26 18:29:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 0/1669] eta: 0:24:31 tlr: 0.00013 tnm: 0.28 Lm: 6.338 (6.338) Lt: 5.603 (5.603) Accm: 3.60 (3.60) Acct: 5.20 (5.20) proj_loss: -0.6328 (-0.6328) time: 0.8816 data: 0.0004 [11-26 18:29:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 0/1669] eta: 0:24:40 tlr: 0.00013 tnm: 0.28 Lm: 6.317 (6.317) Lt: 5.481 (5.481) Accm: 4.14 (4.14) Acct: 6.78 (6.78) proj_loss: -0.5934 (-0.5934) time: 0.8873 data: 0.0004 [11-26 18:29:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 0/1669] eta: 0:24:40 tlr: 0.00013 tnm: 0.28 Lm: 6.389 (6.389) Lt: 5.619 (5.619) Accm: 3.58 (3.58) Acct: 5.51 (5.51) proj_loss: -0.6149 (-0.6149) time: 0.8873 data: 0.0004 [11-26 18:29:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 0/1669] eta: 0:24:40 tlr: 0.00013 tnm: 0.28 Lm: 6.606 (6.606) Lt: 5.820 (5.820) Accm: 3.13 (3.13) Acct: 4.96 (4.96) proj_loss: -0.5984 (-0.5984) time: 0.8872 data: 0.0004 [11-26 18:29:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 0/1669] eta: 0:24:42 tlr: 0.00013 tnm: 0.28 Lm: 6.512 (6.512) Lt: 5.818 (5.818) Accm: 3.16 (3.16) Acct: 5.10 (5.10) proj_loss: -0.6351 (-0.6351) time: 0.8882 data: 0.0003 [11-26 18:36:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.27 Lm: 6.496 (6.496) Lt: 5.755 (5.755) Accm: 3.42 (3.42) Acct: 5.68 (5.68) proj_loss: -0.6228 (-0.6228) time: 0.9268 data: 0.0003 [11-26 18:36:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.27 Lm: 6.508 (6.508) Lt: 5.854 (5.854) Accm: 3.37 (3.37) Acct: 4.77 (4.77) proj_loss: -0.6439 (-0.6439) time: 0.9268 data: 0.0003 [11-26 18:36:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.27 Lm: 6.449 (6.449) Lt: 5.738 (5.738) Accm: 3.59 (3.59) Acct: 5.54 (5.54) proj_loss: -0.6168 (-0.6168) time: 0.9268 data: 0.0002 [11-26 18:36:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.27 Lm: 6.411 (6.411) Lt: 5.616 (5.616) Accm: 3.45 (3.45) Acct: 5.42 (5.42) proj_loss: -0.6158 (-0.6158) time: 0.9268 data: 0.0002 [11-26 18:36:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.27 Lm: 6.456 (6.456) Lt: 5.664 (5.664) Accm: 3.68 (3.68) Acct: 5.94 (5.94) proj_loss: -0.6089 (-0.6089) time: 0.9268 data: 0.0003 [11-26 18:36:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.27 Lm: 6.443 (6.443) Lt: 5.651 (5.651) Accm: 3.73 (3.73) Acct: 5.94 (5.94) proj_loss: -0.6181 (-0.6181) time: 0.9268 data: 0.0003 [11-26 18:36:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.27 Lm: 6.626 (6.626) Lt: 5.856 (5.856) Accm: 3.07 (3.07) Acct: 4.89 (4.89) proj_loss: -0.6261 (-0.6261) time: 0.9268 data: 0.0004 [11-26 18:36:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.27 Lm: 6.350 (6.350) Lt: 5.601 (5.601) Accm: 3.69 (3.69) Acct: 5.80 (5.80) proj_loss: -0.6252 (-0.6252) time: 0.9268 data: 0.0003 [11-26 18:42:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.28 Lm: 6.362 (6.451) Lt: 5.603 (5.746) Accm: 3.60 (3.58) Acct: 5.20 (5.43) proj_loss: -0.6278 (-0.6261) time: 0.9256 data: 0.0002 [11-26 18:42:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.28 Lm: 6.520 (6.557) Lt: 5.854 (5.854) Accm: 3.23 (3.27) Acct: 4.96 (4.83) proj_loss: -0.6335 (-0.6289) time: 0.9256 data: 0.0002 [11-26 18:42:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.28 Lm: 6.317 (6.371) Lt: 5.481 (5.600) Accm: 4.14 (3.87) Acct: 6.61 (6.16) proj_loss: -0.6054 (-0.6078) time: 0.9255 data: 0.0003 [11-26 18:42:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.28 Lm: 6.389 (6.361) Lt: 5.612 (5.563) Accm: 3.58 (3.64) Acct: 5.51 (5.82) proj_loss: -0.6167 (-0.6207) time: 0.9256 data: 0.0002 [11-26 18:42:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.28 Lm: 6.566 (6.484) Lt: 5.804 (5.702) Accm: 3.34 (3.60) Acct: 5.30 (5.73) proj_loss: -0.6241 (-0.6201) time: 0.9256 data: 0.0002 [11-26 18:42:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.28 Lm: 6.361 (6.396) Lt: 5.577 (5.664) Accm: 3.72 (3.72) Acct: 5.61 (5.75) proj_loss: -0.6354 (-0.6324) time: 0.9256 data: 0.0003 [11-26 18:42:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.28 Lm: 6.501 (6.577) Lt: 5.757 (5.823) Accm: 3.28 (3.24) Acct: 5.44 (5.12) proj_loss: -0.6249 (-0.6223) time: 0.9256 data: 0.0003 [11-26 18:42:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.28 Lm: 6.512 (6.549) Lt: 5.818 (5.803) Accm: 3.16 (3.23) Acct: 5.10 (5.39) proj_loss: -0.6143 (-0.6200) time: 0.9256 data: 0.0003 [11-26 18:49:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.28 Lm: 6.496 (6.504) Lt: 5.755 (5.751) Accm: 3.42 (3.39) Acct: 5.58 (5.56) proj_loss: -0.6163 (-0.6195) time: 0.9279 data: 0.0003 [11-26 18:49:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.28 Lm: 6.511 (6.543) Lt: 5.846 (5.825) Accm: 3.31 (3.30) Acct: 5.03 (4.92) proj_loss: -0.6251 (-0.6258) time: 0.9279 data: 0.0002 [11-26 18:49:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.28 Lm: 6.564 (6.503) Lt: 5.800 (5.725) Accm: 3.23 (3.46) Acct: 5.13 (5.40) proj_loss: -0.6198 (-0.6190) time: 0.9279 data: 0.0002 [11-26 18:49:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.28 Lm: 6.326 (6.357) Lt: 5.546 (5.604) Accm: 3.74 (3.73) Acct: 5.68 (5.75) proj_loss: -0.6203 (-0.6256) time: 0.9279 data: 0.0002 [11-26 18:49:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.28 Lm: 6.415 (6.455) Lt: 5.626 (5.722) Accm: 3.49 (3.47) Acct: 5.13 (5.34) proj_loss: -0.6227 (-0.6174) time: 0.9279 data: 0.0003 [11-26 18:49:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.28 Lm: 6.491 (6.514) Lt: 5.733 (5.744) Accm: 3.43 (3.36) Acct: 5.51 (5.32) proj_loss: -0.6199 (-0.6123) time: 0.9279 data: 0.0003 [11-26 18:49:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.28 Lm: 6.334 (6.341) Lt: 5.582 (5.560) Accm: 3.80 (3.73) Acct: 5.75 (5.86) proj_loss: -0.6158 (-0.6188) time: 0.9279 data: 0.0002 [11-26 18:49:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.28 Lm: 6.259 (6.298) Lt: 5.477 (5.500) Accm: 4.18 (3.96) Acct: 6.70 (6.39) proj_loss: -0.6133 (-0.6111) time: 0.9279 data: 0.0003 [11-26 18:55:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.317 (6.322) Lt: 5.481 (5.530) Accm: 4.14 (3.90) Acct: 6.61 (6.38) proj_loss: -0.6212 (-0.6143) time: 0.9279 data: 0.0017 [11-26 18:55:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 175/350] Total time: 0:25:46 (0.926 s / it) [11-26 18:55:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.561 (6.482) Lt: 5.795 (5.722) Accm: 3.34 (3.52) Acct: 5.30 (5.47) proj_loss: -0.6241 (-0.6210) time: 0.9279 data: 0.0018 [11-26 18:55:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.501 (6.506) Lt: 5.837 (5.769) Accm: 3.38 (3.42) Acct: 5.10 (5.10) proj_loss: -0.6199 (-0.6246) time: 0.9279 data: 0.0016 [11-26 18:55:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.389 (6.363) Lt: 5.612 (5.578) Accm: 3.58 (3.66) Acct: 5.89 (5.87) proj_loss: -0.6167 (-0.6215) time: 0.9279 data: 0.0014 [11-26 18:55:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.479 (6.495) Lt: 5.818 (5.770) Accm: 3.37 (3.38) Acct: 5.10 (5.37) proj_loss: -0.6183 (-0.6218) time: 0.9279 data: 0.0021 [11-26 18:55:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.481 (6.500) Lt: 5.709 (5.734) Accm: 3.29 (3.35) Acct: 5.44 (5.34) proj_loss: -0.6149 (-0.6092) time: 0.9279 data: 0.0017 [11-26 18:55:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.361 (6.410) Lt: 5.577 (5.653) Accm: 3.72 (3.62) Acct: 5.61 (5.59) proj_loss: -0.6131 (-0.6231) time: 0.9279 data: 0.0017 [11-26 18:55:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 175/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.460 (6.456) Lt: 5.649 (5.730) Accm: 3.60 (3.52) Acct: 5.20 (5.52) proj_loss: -0.6176 (-0.6170) time: 0.9279 data: 0.0017 [11-26 18:55:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 175/350] Total time: 0:25:46 (0.926 s / it) [11-26 18:55:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 175/350] Total time: 0:25:46 (0.926 s / it) [11-26 18:55:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 175/350] Total time: 0:25:46 (0.926 s / it) [11-26 18:55:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 175/350] Total time: 0:25:46 (0.926 s / it) [11-26 18:55:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 175/350] Total time: 0:25:46 (0.926 s / it) [11-26 18:55:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 175/350] Total time: 0:25:46 (0.926 s / it) [11-26 18:55:31] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 175/350] Total time: 0:25:46 (0.926 s / it) [11-26 18:55:31] (/home/user/VAR/train.py , line 276)=> [ep175] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.652), Acc m&t: 3.65 5.71, Remain: 3 days, 3:23:04, Finish: 2024-11-29 06:18 [11-26 18:55:31] (/home/user/VAR/train.py , line 276)=> [ep175] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.652), Acc m&t: 3.65 5.71, Remain: 3 days, 3:23:49, Finish: 2024-11-29 06:19 [11-26 18:55:31] (/home/user/VAR/train.py , line 276)=> [ep175] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.652), Acc m&t: 3.65 5.71, Remain: 3 days, 3:25:06, Finish: 2024-11-29 06:20 [11-26 18:55:31] (/home/user/VAR/train.py , line 276)=> [ep175] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.652), Acc m&t: 3.65 5.71, Remain: 3 days, 3:25:23, Finish: 2024-11-29 06:20 [11-26 18:55:31] (/home/user/VAR/train.py , line 276)=> [ep175] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.652), Acc m&t: 3.65 5.71, Remain: 3 days, 3:22:32, Finish: 2024-11-29 06:18 [11-26 18:55:31] (/home/user/VAR/train.py , line 276)=> [ep175] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.652), Acc m&t: 3.65 5.71, Remain: 3 days, 3:23:57, Finish: 2024-11-29 06:19 [11-26 18:55:31] (/home/user/VAR/train.py , line 276)=> [ep175] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.652), Acc m&t: 3.65 5.71, Remain: 3 days, 3:24:34, Finish: 2024-11-29 06:20 [11-26 18:55:31] (/home/user/VAR/train.py , line 276)=> [ep175] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.652), Acc m&t: 3.65 5.71, Remain: 3 days, 3:22:40, Finish: 2024-11-29 06:18 [11-26 18:55:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 0/1669] eta: 0:24:38 tlr: 0.00013 tnm: 0.28 Lm: 6.301 (6.301) Lt: 5.541 (5.541) Accm: 4.44 (4.44) Acct: 6.68 (6.68) proj_loss: -0.6364 (-0.6364) time: 0.8858 data: 0.0003 [11-26 18:55:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 0/1669] eta: 0:24:38 tlr: 0.00013 tnm: 0.28 Lm: 6.294 (6.294) Lt: 5.606 (5.606) Accm: 4.09 (4.09) Acct: 5.96 (5.96) proj_loss: -0.6381 (-0.6381) time: 0.8861 data: 0.0004 [11-26 18:55:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 0/1669] eta: 0:24:39 tlr: 0.00013 tnm: 0.28 Lm: 6.168 (6.168) Lt: 5.281 (5.281) Accm: 4.41 (4.41) Acct: 7.20 (7.20) proj_loss: -0.6049 (-0.6049) time: 0.8862 data: 0.0004 [11-26 18:55:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 0/1669] eta: 0:24:38 tlr: 0.00013 tnm: 0.28 Lm: 6.553 (6.553) Lt: 5.852 (5.852) Accm: 3.06 (3.06) Acct: 4.68 (4.68) proj_loss: -0.6356 (-0.6356) time: 0.8858 data: 0.0004 [11-26 18:55:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 0/1669] eta: 0:24:39 tlr: 0.00013 tnm: 0.28 Lm: 6.319 (6.319) Lt: 5.591 (5.591) Accm: 3.73 (3.73) Acct: 5.65 (5.65) proj_loss: -0.6208 (-0.6208) time: 0.8867 data: 0.0004 [11-26 18:55:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 0/1669] eta: 0:24:39 tlr: 0.00013 tnm: 0.28 Lm: 6.494 (6.494) Lt: 5.695 (5.695) Accm: 3.50 (3.50) Acct: 5.72 (5.72) proj_loss: -0.6078 (-0.6078) time: 0.8865 data: 0.0004 [11-26 18:55:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 0/1669] eta: 0:24:40 tlr: 0.00013 tnm: 0.28 Lm: 6.320 (6.320) Lt: 5.476 (5.476) Accm: 3.77 (3.77) Acct: 6.03 (6.03) proj_loss: -0.6035 (-0.6035) time: 0.8869 data: 0.0004 [11-26 18:55:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 0/1669] eta: 0:24:41 tlr: 0.00013 tnm: 0.28 Lm: 6.330 (6.330) Lt: 5.548 (5.548) Accm: 4.31 (4.31) Acct: 6.61 (6.61) proj_loss: -0.6499 (-0.6499) time: 0.8879 data: 0.0004 [11-26 19:02:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 417/1669] eta: 0:20:03 tlr: 0.00013 tnm: 0.28 Lm: 6.487 (6.487) Lt: 5.718 (5.718) Accm: 3.65 (3.65) Acct: 5.60 (5.60) proj_loss: -0.6342 (-0.6342) time: 0.9288 data: 0.0003 [11-26 19:02:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 417/1669] eta: 0:20:04 tlr: 0.00013 tnm: 0.28 Lm: 6.359 (6.359) Lt: 5.649 (5.649) Accm: 3.77 (3.77) Acct: 5.56 (5.56) proj_loss: -0.6260 (-0.6260) time: 0.9288 data: 0.0003 [11-26 19:02:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 417/1669] eta: 0:20:04 tlr: 0.00013 tnm: 0.28 Lm: 6.272 (6.272) Lt: 5.513 (5.513) Accm: 4.18 (4.18) Acct: 6.28 (6.28) proj_loss: -0.6217 (-0.6217) time: 0.9288 data: 0.0003 [11-26 19:02:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 417/1669] eta: 0:20:03 tlr: 0.00013 tnm: 0.28 Lm: 6.332 (6.332) Lt: 5.536 (5.536) Accm: 3.97 (3.97) Acct: 6.25 (6.25) proj_loss: -0.6233 (-0.6233) time: 0.9288 data: 0.0003 [11-26 19:02:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 417/1669] eta: 0:20:04 tlr: 0.00013 tnm: 0.28 Lm: 6.247 (6.247) Lt: 5.406 (5.406) Accm: 3.89 (3.89) Acct: 6.35 (6.35) proj_loss: -0.6090 (-0.6090) time: 0.9288 data: 0.0003 [11-26 19:02:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 417/1669] eta: 0:20:03 tlr: 0.00013 tnm: 0.28 Lm: 6.410 (6.410) Lt: 5.661 (5.661) Accm: 3.53 (3.53) Acct: 5.53 (5.53) proj_loss: -0.6064 (-0.6064) time: 0.9288 data: 0.0003 [11-26 19:02:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 417/1669] eta: 0:20:03 tlr: 0.00013 tnm: 0.28 Lm: 6.598 (6.598) Lt: 5.854 (5.854) Accm: 3.18 (3.18) Acct: 4.92 (4.92) proj_loss: -0.6222 (-0.6222) time: 0.9288 data: 0.0003 [11-26 19:02:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 417/1669] eta: 0:20:03 tlr: 0.00013 tnm: 0.28 Lm: 6.304 (6.304) Lt: 5.490 (5.490) Accm: 3.82 (3.82) Acct: 6.27 (6.27) proj_loss: -0.6264 (-0.6264) time: 0.9288 data: 0.0003 [11-26 19:08:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 834/1669] eta: 0:13:08 tlr: 0.00013 tnm: 0.28 Lm: 6.320 (6.346) Lt: 5.504 (5.561) Accm: 3.77 (3.74) Acct: 6.03 (5.99) proj_loss: -0.6099 (-0.6209) time: 0.9284 data: 0.0003 [11-26 19:08:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 834/1669] eta: 0:13:08 tlr: 0.00013 tnm: 0.28 Lm: 6.553 (6.494) Lt: 5.852 (5.723) Accm: 3.29 (3.52) Acct: 5.17 (5.42) proj_loss: -0.6257 (-0.6234) time: 0.9284 data: 0.0002 [11-26 19:08:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 834/1669] eta: 0:13:08 tlr: 0.00013 tnm: 0.28 Lm: 6.406 (6.460) Lt: 5.583 (5.673) Accm: 3.83 (3.71) Acct: 6.40 (5.87) proj_loss: -0.6189 (-0.6291) time: 0.9284 data: 0.0002 [11-26 19:08:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 834/1669] eta: 0:13:08 tlr: 0.00013 tnm: 0.28 Lm: 6.243 (6.257) Lt: 5.484 (5.452) Accm: 4.41 (4.26) Acct: 6.68 (6.62) proj_loss: -0.6255 (-0.6230) time: 0.9284 data: 0.0003 [11-26 19:08:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 834/1669] eta: 0:13:08 tlr: 0.00013 tnm: 0.28 Lm: 6.425 (6.404) Lt: 5.692 (5.693) Accm: 3.44 (3.57) Acct: 5.17 (5.10) proj_loss: -0.6381 (-0.6338) time: 0.9284 data: 0.0003 [11-26 19:08:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 834/1669] eta: 0:13:08 tlr: 0.00013 tnm: 0.28 Lm: 6.502 (6.463) Lt: 5.730 (5.728) Accm: 3.42 (3.49) Acct: 5.61 (5.56) proj_loss: -0.6085 (-0.6071) time: 0.9284 data: 0.0003 [11-26 19:08:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 834/1669] eta: 0:13:08 tlr: 0.00013 tnm: 0.28 Lm: 6.494 (6.405) Lt: 5.695 (5.665) Accm: 3.50 (3.60) Acct: 5.72 (5.59) proj_loss: -0.6389 (-0.6381) time: 0.9284 data: 0.0002 [11-26 19:08:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [ 834/1669] eta: 0:13:08 tlr: 0.00013 tnm: 0.28 Lm: 6.326 (6.375) Lt: 5.531 (5.605) Accm: 3.37 (3.68) Acct: 5.51 (5.85) proj_loss: -0.6132 (-0.6242) time: 0.9285 data: 0.0002 [11-26 19:15:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [1251/1669] eta: 0:06:32 tlr: 0.00013 tnm: 0.27 Lm: 6.422 (6.411) Lt: 5.651 (5.647) Accm: 3.31 (3.55) Acct: 5.30 (5.66) proj_loss: -0.6241 (-0.6269) time: 0.9252 data: 0.0003 [11-26 19:15:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [1251/1669] eta: 0:06:32 tlr: 0.00013 tnm: 0.27 Lm: 6.359 (6.345) Lt: 5.649 (5.637) Accm: 3.77 (3.85) Acct: 5.56 (5.59) proj_loss: -0.6416 (-0.6366) time: 0.9251 data: 0.0002 [11-26 19:15:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [1251/1669] eta: 0:06:32 tlr: 0.00013 tnm: 0.27 Lm: 6.472 (6.468) Lt: 5.728 (5.693) Accm: 3.34 (3.49) Acct: 5.27 (5.41) proj_loss: -0.6238 (-0.6230) time: 0.9251 data: 0.0002 [11-26 19:15:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [1251/1669] eta: 0:06:32 tlr: 0.00013 tnm: 0.27 Lm: 6.272 (6.295) Lt: 5.513 (5.518) Accm: 4.17 (4.09) Acct: 6.28 (6.29) proj_loss: -0.6192 (-0.6205) time: 0.9252 data: 0.0003 [11-26 19:15:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [1251/1669] eta: 0:06:32 tlr: 0.00013 tnm: 0.27 Lm: 6.370 (6.366) Lt: 5.582 (5.617) Accm: 3.81 (3.73) Acct: 6.06 (5.79) proj_loss: -0.6468 (-0.6423) time: 0.9252 data: 0.0002 [11-26 19:15:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [1251/1669] eta: 0:06:32 tlr: 0.00013 tnm: 0.27 Lm: 6.368 (6.427) Lt: 5.588 (5.653) Accm: 3.80 (3.72) Acct: 6.18 (5.89) proj_loss: -0.6262 (-0.6302) time: 0.9251 data: 0.0002 [11-26 19:15:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [1251/1669] eta: 0:06:32 tlr: 0.00013 tnm: 0.27 Lm: 6.410 (6.379) Lt: 5.661 (5.620) Accm: 3.58 (3.78) Acct: 5.63 (6.07) proj_loss: -0.6116 (-0.6090) time: 0.9251 data: 0.0003 [11-26 19:15:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [1251/1669] eta: 0:06:32 tlr: 0.00013 tnm: 0.27 Lm: 6.374 (6.396) Lt: 5.604 (5.627) Accm: 3.67 (3.67) Acct: 5.79 (5.88) proj_loss: -0.6133 (-0.6198) time: 0.9251 data: 0.0003 [11-26 19:21:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.362 (6.389) Lt: 5.577 (5.617) Accm: 3.77 (3.74) Acct: 5.85 (5.87) proj_loss: -0.6167 (-0.6206) time: 0.9283 data: 0.0023 [11-26 19:21:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 176/350] Total time: 0:26:00 (0.935 s / it) [11-26 19:21:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.553 (6.489) Lt: 5.826 (5.719) Accm: 3.29 (3.42) Acct: 5.17 (5.32) proj_loss: -0.6219 (-0.6203) time: 0.9283 data: 0.0018 [11-26 19:21:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.358 (6.364) Lt: 5.622 (5.618) Accm: 3.90 (3.77) Acct: 6.40 (5.96) proj_loss: -0.6389 (-0.6414) time: 0.9283 data: 0.0015 [11-26 19:21:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.301 (6.314) Lt: 5.541 (5.525) Accm: 3.92 (3.98) Acct: 5.89 (6.14) proj_loss: -0.6255 (-0.6215) time: 0.9283 data: 0.0017 [11-26 19:21:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.476 (6.424) Lt: 5.753 (5.668) Accm: 3.37 (3.56) Acct: 5.51 (5.73) proj_loss: -0.6132 (-0.6241) time: 0.9283 data: 0.0016 [11-26 19:21:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.406 (6.461) Lt: 5.593 (5.700) Accm: 3.76 (3.58) Acct: 5.96 (5.65) proj_loss: -0.6189 (-0.6240) time: 0.9283 data: 0.0017 [11-26 19:21:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.425 (6.390) Lt: 5.692 (5.672) Accm: 3.44 (3.65) Acct: 5.17 (5.41) proj_loss: -0.6381 (-0.6252) time: 0.9283 data: 0.0018 [11-26 19:21:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 176/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.28 Lm: 6.381 (6.380) Lt: 5.616 (5.619) Accm: 3.55 (3.74) Acct: 5.65 (6.05) proj_loss: -0.6146 (-0.6126) time: 0.9283 data: 0.0020 [11-26 19:21:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 176/350] Total time: 0:26:00 (0.935 s / it) [11-26 19:21:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 176/350] Total time: 0:26:00 (0.935 s / it) [11-26 19:21:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 176/350] Total time: 0:26:00 (0.935 s / it) [11-26 19:21:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 176/350] Total time: 0:26:00 (0.935 s / it) [11-26 19:21:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 176/350] Total time: 0:26:00 (0.935 s / it) [11-26 19:21:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 176/350] Total time: 0:26:00 (0.935 s / it) [11-26 19:21:32] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 176/350] Total time: 0:26:00 (0.935 s / it) [11-26 19:21:32] (/home/user/VAR/train.py , line 276)=> [ep176] (training ) Lm: 6.407 (6.407), Lt: 5.650 (5.653), Acc m&t: 3.65 5.71, Remain: 3 days, 2:56:58, Finish: 2024-11-29 06:18 [11-26 19:21:32] (/home/user/VAR/train.py , line 276)=> [ep176] (training ) Lm: 6.407 (6.407), Lt: 5.650 (5.653), Acc m&t: 3.65 5.71, Remain: 3 days, 2:58:37, Finish: 2024-11-29 06:20 [11-26 19:21:32] (/home/user/VAR/train.py , line 276)=> [ep176] (training ) Lm: 6.407 (6.407), Lt: 5.650 (5.653), Acc m&t: 3.65 5.71, Remain: 3 days, 2:57:49, Finish: 2024-11-29 06:19 [11-26 19:21:32] (/home/user/VAR/train.py , line 276)=> [ep176] (training ) Lm: 6.407 (6.407), Lt: 5.650 (5.653), Acc m&t: 3.65 5.71, Remain: 3 days, 2:58:06, Finish: 2024-11-29 06:19 [11-26 19:21:32] (/home/user/VAR/train.py , line 276)=> [ep176] (training ) Lm: 6.407 (6.407), Lt: 5.650 (5.653), Acc m&t: 3.65 5.71, Remain: 3 days, 2:58:03, Finish: 2024-11-29 06:19 [11-26 19:21:32] (/home/user/VAR/train.py , line 276)=> [ep176] (training ) Lm: 6.407 (6.407), Lt: 5.650 (5.653), Acc m&t: 3.65 5.71, Remain: 3 days, 2:57:22, Finish: 2024-11-29 06:18 [11-26 19:21:32] (/home/user/VAR/train.py , line 276)=> [ep176] (training ) Lm: 6.407 (6.407), Lt: 5.650 (5.653), Acc m&t: 3.65 5.71, Remain: 3 days, 2:58:17, Finish: 2024-11-29 06:19 [11-26 19:21:32] (/home/user/VAR/train.py , line 276)=> [ep176] (training ) Lm: 6.407 (6.407), Lt: 5.650 (5.653), Acc m&t: 3.65 5.71, Remain: 3 days, 2:58:24, Finish: 2024-11-29 06:19 [11-26 19:21:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 0/1669] eta: 0:24:32 tlr: 0.00013 tnm: 0.28 Lm: 6.539 (6.539) Lt: 5.789 (5.789) Accm: 3.54 (3.54) Acct: 5.89 (5.89) proj_loss: -0.5836 (-0.5836) time: 0.8822 data: 0.0003 [11-26 19:21:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 0/1669] eta: 0:24:32 tlr: 0.00013 tnm: 0.28 Lm: 6.438 (6.438) Lt: 5.747 (5.747) Accm: 3.74 (3.74) Acct: 5.51 (5.51) proj_loss: -0.6345 (-0.6345) time: 0.8822 data: 0.0003 [11-26 19:21:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 0/1669] eta: 0:24:32 tlr: 0.00013 tnm: 0.28 Lm: 6.683 (6.683) Lt: 5.936 (5.936) Accm: 2.74 (2.74) Acct: 4.51 (4.51) proj_loss: -0.6199 (-0.6199) time: 0.8823 data: 0.0004 [11-26 19:21:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 0/1669] eta: 0:24:32 tlr: 0.00013 tnm: 0.28 Lm: 6.304 (6.304) Lt: 5.522 (5.522) Accm: 3.93 (3.93) Acct: 5.48 (5.48) proj_loss: -0.6236 (-0.6236) time: 0.8824 data: 0.0003 [11-26 19:21:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 0/1669] eta: 0:24:32 tlr: 0.00013 tnm: 0.28 Lm: 6.583 (6.583) Lt: 5.808 (5.808) Accm: 3.22 (3.22) Acct: 4.89 (4.89) proj_loss: -0.5944 (-0.5944) time: 0.8825 data: 0.0003 [11-26 19:21:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 0/1669] eta: 0:24:32 tlr: 0.00013 tnm: 0.28 Lm: 6.347 (6.347) Lt: 5.647 (5.647) Accm: 3.67 (3.67) Acct: 5.75 (5.75) proj_loss: -0.6474 (-0.6474) time: 0.8826 data: 0.0004 [11-26 19:21:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 0/1669] eta: 0:24:31 tlr: 0.00013 tnm: 0.28 Lm: 6.307 (6.307) Lt: 5.400 (5.400) Accm: 4.31 (4.31) Acct: 7.06 (7.06) proj_loss: -0.6182 (-0.6182) time: 0.8819 data: 0.0004 [11-26 19:21:33] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 0/1669] eta: 0:24:33 tlr: 0.00013 tnm: 0.28 Lm: 6.390 (6.390) Lt: 5.556 (5.556) Accm: 3.76 (3.76) Acct: 6.06 (6.06) proj_loss: -0.5997 (-0.5997) time: 0.8827 data: 0.0004 [11-26 19:28:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.29 Lm: 6.335 (6.335) Lt: 5.531 (5.531) Accm: 3.82 (3.82) Acct: 5.96 (5.96) proj_loss: -0.6166 (-0.6166) time: 0.9264 data: 0.0003 [11-26 19:28:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.29 Lm: 6.327 (6.327) Lt: 5.505 (5.505) Accm: 4.06 (4.06) Acct: 6.61 (6.61) proj_loss: -0.6427 (-0.6427) time: 0.9264 data: 0.0002 [11-26 19:28:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.29 Lm: 6.698 (6.698) Lt: 5.964 (5.964) Accm: 2.67 (2.67) Acct: 4.24 (4.24) proj_loss: -0.6235 (-0.6235) time: 0.9264 data: 0.0003 [11-26 19:28:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.29 Lm: 6.548 (6.548) Lt: 5.803 (5.803) Accm: 3.34 (3.34) Acct: 5.44 (5.44) proj_loss: -0.5995 (-0.5995) time: 0.9264 data: 0.0002 [11-26 19:28:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.29 Lm: 6.398 (6.398) Lt: 5.590 (5.590) Accm: 3.72 (3.72) Acct: 5.48 (5.48) proj_loss: -0.6058 (-0.6058) time: 0.9264 data: 0.0003 [11-26 19:28:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.29 Lm: 6.432 (6.432) Lt: 5.705 (5.705) Accm: 3.45 (3.45) Acct: 5.58 (5.58) proj_loss: -0.6430 (-0.6430) time: 0.9264 data: 0.0004 [11-26 19:28:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.29 Lm: 6.465 (6.465) Lt: 5.757 (5.757) Accm: 3.51 (3.51) Acct: 5.35 (5.35) proj_loss: -0.6300 (-0.6300) time: 0.9264 data: 0.0003 [11-26 19:28:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.29 Lm: 6.520 (6.520) Lt: 5.724 (5.724) Accm: 3.31 (3.31) Acct: 5.18 (5.18) proj_loss: -0.6129 (-0.6129) time: 0.9264 data: 0.0003 [11-26 19:34:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 834/1669] eta: 0:13:22 tlr: 0.00013 tnm: 0.28 Lm: 6.457 (6.495) Lt: 5.739 (5.729) Accm: 3.41 (3.46) Acct: 5.48 (5.43) proj_loss: -0.6315 (-0.6244) time: 0.9278 data: 0.0003 [11-26 19:34:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 834/1669] eta: 0:13:22 tlr: 0.00013 tnm: 0.28 Lm: 6.683 (6.589) Lt: 5.936 (5.851) Accm: 2.74 (2.96) Acct: 4.51 (4.59) proj_loss: -0.6272 (-0.6257) time: 0.9278 data: 0.0003 [11-26 19:34:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 834/1669] eta: 0:13:22 tlr: 0.00013 tnm: 0.28 Lm: 6.556 (6.581) Lt: 5.817 (5.858) Accm: 3.13 (3.13) Acct: 4.99 (5.08) proj_loss: -0.6153 (-0.6058) time: 0.9278 data: 0.0002 [11-26 19:34:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 834/1669] eta: 0:13:22 tlr: 0.00013 tnm: 0.28 Lm: 6.493 (6.526) Lt: 5.767 (5.801) Accm: 3.28 (3.36) Acct: 5.20 (5.23) proj_loss: -0.6254 (-0.6232) time: 0.9278 data: 0.0002 [11-26 19:34:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 834/1669] eta: 0:13:22 tlr: 0.00013 tnm: 0.28 Lm: 6.304 (6.345) Lt: 5.522 (5.557) Accm: 3.93 (3.82) Acct: 5.48 (5.88) proj_loss: -0.6236 (-0.6148) time: 0.9278 data: 0.0003 [11-26 19:34:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 834/1669] eta: 0:13:22 tlr: 0.00013 tnm: 0.28 Lm: 6.390 (6.387) Lt: 5.556 (5.612) Accm: 3.76 (3.61) Acct: 5.85 (5.62) proj_loss: -0.6262 (-0.6198) time: 0.9278 data: 0.0003 [11-26 19:34:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 834/1669] eta: 0:13:22 tlr: 0.00013 tnm: 0.28 Lm: 6.347 (6.370) Lt: 5.611 (5.587) Accm: 3.80 (3.84) Acct: 6.16 (6.21) proj_loss: -0.6182 (-0.6279) time: 0.9278 data: 0.0003 [11-26 19:34:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [ 834/1669] eta: 0:13:22 tlr: 0.00013 tnm: 0.28 Lm: 6.377 (6.414) Lt: 5.647 (5.649) Accm: 3.67 (3.53) Acct: 5.75 (5.64) proj_loss: -0.6387 (-0.6304) time: 0.9278 data: 0.0003 [11-26 19:41:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [1251/1669] eta: 0:06:36 tlr: 0.00013 tnm: 0.27 Lm: 6.381 (6.407) Lt: 5.621 (5.635) Accm: 3.68 (3.63) Acct: 5.75 (5.75) proj_loss: -0.6219 (-0.6206) time: 0.9266 data: 0.0003 [11-26 19:41:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [1251/1669] eta: 0:06:36 tlr: 0.00013 tnm: 0.27 Lm: 6.455 (6.484) Lt: 5.696 (5.710) Accm: 3.34 (3.41) Acct: 5.41 (5.41) proj_loss: -0.6175 (-0.6192) time: 0.9266 data: 0.0002 [11-26 19:41:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [1251/1669] eta: 0:06:36 tlr: 0.00013 tnm: 0.27 Lm: 6.338 (6.360) Lt: 5.546 (5.560) Accm: 4.06 (3.99) Acct: 6.61 (6.45) proj_loss: -0.6277 (-0.6302) time: 0.9266 data: 0.0002 [11-26 19:41:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [1251/1669] eta: 0:06:36 tlr: 0.00013 tnm: 0.27 Lm: 6.364 (6.365) Lt: 5.578 (5.576) Accm: 3.72 (3.63) Acct: 5.48 (5.54) proj_loss: -0.6272 (-0.6188) time: 0.9266 data: 0.0002 [11-26 19:41:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [1251/1669] eta: 0:06:36 tlr: 0.00013 tnm: 0.27 Lm: 6.581 (6.587) Lt: 5.828 (5.853) Accm: 3.07 (3.10) Acct: 4.82 (4.98) proj_loss: -0.6169 (-0.6112) time: 0.9266 data: 0.0002 [11-26 19:41:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [1251/1669] eta: 0:06:36 tlr: 0.00013 tnm: 0.27 Lm: 6.532 (6.537) Lt: 5.780 (5.784) Accm: 3.15 (3.19) Acct: 4.91 (4.78) proj_loss: -0.6235 (-0.6228) time: 0.9266 data: 0.0003 [11-26 19:41:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [1251/1669] eta: 0:06:36 tlr: 0.00013 tnm: 0.27 Lm: 6.465 (6.486) Lt: 5.757 (5.780) Accm: 3.49 (3.45) Acct: 5.35 (5.40) proj_loss: -0.6300 (-0.6286) time: 0.9266 data: 0.0002 [11-26 19:41:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [1251/1669] eta: 0:06:36 tlr: 0.00013 tnm: 0.27 Lm: 6.335 (6.345) Lt: 5.531 (5.559) Accm: 3.82 (3.73) Acct: 5.96 (5.90) proj_loss: -0.6202 (-0.6184) time: 0.9267 data: 0.0003 [11-26 19:47:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.29 Lm: 6.281 (6.327) Lt: 5.507 (5.542) Accm: 3.89 (3.78) Acct: 6.06 (5.98) proj_loss: -0.6262 (-0.6253) time: 0.9288 data: 0.0017 [11-26 19:47:49] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 177/350] Total time: 0:26:16 (0.945 s / it) [11-26 19:47:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.29 Lm: 6.438 (6.463) Lt: 5.747 (5.743) Accm: 3.50 (3.46) Acct: 5.51 (5.43) proj_loss: -0.6254 (-0.6211) time: 0.9288 data: 0.0015 [11-26 19:47:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.29 Lm: 6.556 (6.574) Lt: 5.817 (5.835) Accm: 3.13 (3.16) Acct: 4.99 (5.05) proj_loss: -0.6185 (-0.6158) time: 0.9288 data: 0.0015 [11-26 19:47:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.29 Lm: 6.347 (6.386) Lt: 5.611 (5.599) Accm: 3.80 (3.80) Acct: 6.16 (6.18) proj_loss: -0.6182 (-0.6250) time: 0.9288 data: 0.0015 [11-26 19:47:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.29 Lm: 6.423 (6.383) Lt: 5.635 (5.601) Accm: 3.51 (3.61) Acct: 5.48 (5.52) proj_loss: -0.6236 (-0.6157) time: 0.9288 data: 0.0017 [11-26 19:47:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.29 Lm: 6.386 (6.467) Lt: 5.647 (5.709) Accm: 3.67 (3.51) Acct: 5.75 (5.56) proj_loss: -0.6285 (-0.6222) time: 0.9288 data: 0.0022 [11-26 19:47:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.29 Lm: 6.453 (6.448) Lt: 5.653 (5.674) Accm: 3.41 (3.47) Acct: 5.48 (5.49) proj_loss: -0.6241 (-0.6201) time: 0.9288 data: 0.0015 [11-26 19:47:49] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 177/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.29 Lm: 6.381 (6.505) Lt: 5.624 (5.741) Accm: 3.55 (3.41) Acct: 5.30 (5.18) proj_loss: -0.6199 (-0.6216) time: 0.9288 data: 0.0018 [11-26 19:47:49] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 177/350] Total time: 0:26:16 (0.945 s / it) [11-26 19:47:49] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 177/350] Total time: 0:26:16 (0.945 s / it) [11-26 19:47:49] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 177/350] Total time: 0:26:16 (0.945 s / it) [11-26 19:47:49] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 177/350] Total time: 0:26:16 (0.945 s / it) [11-26 19:47:49] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 177/350] Total time: 0:26:16 (0.945 s / it) [11-26 19:47:49] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 177/350] Total time: 0:26:16 (0.945 s / it) [11-26 19:47:49] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 177/350] Total time: 0:26:16 (0.945 s / it) [11-26 19:47:49] (/home/user/VAR/train.py , line 276)=> [ep177] (training ) Lm: 6.407 (6.432), Lt: 5.650 (5.672), Acc m&t: 3.65 5.71, Remain: 3 days, 2:33:40, Finish: 2024-11-29 06:21 [11-26 19:47:49] (/home/user/VAR/train.py , line 276)=> [ep177] (training ) Lm: 6.407 (6.432), Lt: 5.650 (5.672), Acc m&t: 3.65 5.71, Remain: 3 days, 2:33:08, Finish: 2024-11-29 06:20 [11-26 19:47:49] (/home/user/VAR/train.py , line 276)=> [ep177] (training ) Lm: 6.407 (6.432), Lt: 5.650 (5.672), Acc m&t: 3.65 5.71, Remain: 3 days, 2:33:12, Finish: 2024-11-29 06:21 [11-26 19:47:49] (/home/user/VAR/train.py , line 276)=> [ep177] (training ) Lm: 6.407 (6.432), Lt: 5.650 (5.672), Acc m&t: 3.65 5.71, Remain: 3 days, 2:33:42, Finish: 2024-11-29 06:21 [11-26 19:47:49] (/home/user/VAR/train.py , line 276)=> [ep177] (training ) Lm: 6.407 (6.432), Lt: 5.650 (5.672), Acc m&t: 3.65 5.71, Remain: 3 days, 2:33:24, Finish: 2024-11-29 06:21 [11-26 19:47:49] (/home/user/VAR/train.py , line 276)=> [ep177] (training ) Lm: 6.407 (6.432), Lt: 5.650 (5.672), Acc m&t: 3.65 5.71, Remain: 3 days, 2:33:29, Finish: 2024-11-29 06:21 [11-26 19:47:49] (/home/user/VAR/train.py , line 276)=> [ep177] (training ) Lm: 6.407 (6.432), Lt: 5.650 (5.672), Acc m&t: 3.65 5.71, Remain: 3 days, 2:33:35, Finish: 2024-11-29 06:21 [11-26 19:47:49] (/home/user/VAR/train.py , line 276)=> [ep177] (training ) Lm: 6.407 (6.432), Lt: 5.650 (5.672), Acc m&t: 3.65 5.71, Remain: 3 days, 2:33:34, Finish: 2024-11-29 06:21 [11-26 19:47:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 0/1669] eta: 0:24:50 tlr: 0.00013 tnm: 0.28 Lm: 6.279 (6.279) Lt: 5.508 (5.508) Accm: 4.28 (4.28) Acct: 7.02 (7.02) proj_loss: -0.6135 (-0.6135) time: 0.8930 data: 0.0003 [11-26 19:47:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 0/1669] eta: 0:24:45 tlr: 0.00013 tnm: 0.28 Lm: 6.637 (6.637) Lt: 5.934 (5.934) Accm: 2.74 (2.74) Acct: 3.99 (3.99) proj_loss: -0.6294 (-0.6294) time: 0.8898 data: 0.0004 [11-26 19:47:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 0/1669] eta: 0:24:50 tlr: 0.00013 tnm: 0.28 Lm: 6.379 (6.379) Lt: 5.605 (5.605) Accm: 3.93 (3.93) Acct: 6.65 (6.65) proj_loss: -0.6252 (-0.6252) time: 0.8931 data: 0.0003 [11-26 19:47:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 0/1669] eta: 0:24:45 tlr: 0.00013 tnm: 0.28 Lm: 6.514 (6.514) Lt: 5.757 (5.757) Accm: 3.39 (3.39) Acct: 5.44 (5.44) proj_loss: -0.6165 (-0.6165) time: 0.8901 data: 0.0004 [11-26 19:47:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 0/1669] eta: 0:24:50 tlr: 0.00013 tnm: 0.28 Lm: 6.432 (6.432) Lt: 5.663 (5.663) Accm: 3.26 (3.26) Acct: 5.10 (5.10) proj_loss: -0.5874 (-0.5874) time: 0.8932 data: 0.0004 [11-26 19:47:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 0/1669] eta: 0:24:50 tlr: 0.00013 tnm: 0.28 Lm: 6.268 (6.268) Lt: 5.532 (5.532) Accm: 3.92 (3.92) Acct: 5.89 (5.89) proj_loss: -0.5898 (-0.5898) time: 0.8933 data: 0.0003 [11-26 19:47:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 0/1669] eta: 0:24:46 tlr: 0.00013 tnm: 0.28 Lm: 6.414 (6.414) Lt: 5.637 (5.637) Accm: 3.54 (3.54) Acct: 5.68 (5.68) proj_loss: -0.5930 (-0.5930) time: 0.8905 data: 0.0003 [11-26 19:47:50] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 0/1669] eta: 0:24:46 tlr: 0.00013 tnm: 0.28 Lm: 6.652 (6.652) Lt: 5.983 (5.983) Accm: 3.19 (3.19) Acct: 4.99 (4.99) proj_loss: -0.6401 (-0.6401) time: 0.8905 data: 0.0003 [11-26 19:54:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.28 Lm: 6.457 (6.457) Lt: 5.739 (5.739) Accm: 3.61 (3.61) Acct: 5.68 (5.68) proj_loss: -0.6347 (-0.6347) time: 0.9277 data: 0.0003 [11-26 19:54:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.28 Lm: 6.287 (6.287) Lt: 5.526 (5.526) Accm: 3.66 (3.66) Acct: 5.85 (5.85) proj_loss: -0.6019 (-0.6019) time: 0.9277 data: 0.0003 [11-26 19:54:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.28 Lm: 6.518 (6.518) Lt: 5.824 (5.824) Accm: 3.09 (3.09) Acct: 4.51 (4.51) proj_loss: -0.6358 (-0.6358) time: 0.9277 data: 0.0003 [11-26 19:54:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.28 Lm: 6.575 (6.575) Lt: 5.869 (5.869) Accm: 3.26 (3.26) Acct: 5.20 (5.20) proj_loss: -0.6287 (-0.6287) time: 0.9277 data: 0.0002 [11-26 19:54:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.28 Lm: 6.441 (6.441) Lt: 5.707 (5.707) Accm: 3.55 (3.55) Acct: 5.54 (5.54) proj_loss: -0.6283 (-0.6283) time: 0.9277 data: 0.0002 [11-26 19:54:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.28 Lm: 6.333 (6.333) Lt: 5.580 (5.580) Accm: 3.80 (3.80) Acct: 5.94 (5.94) proj_loss: -0.6092 (-0.6092) time: 0.9277 data: 0.0003 [11-26 19:54:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.28 Lm: 6.488 (6.488) Lt: 5.677 (5.677) Accm: 3.10 (3.10) Acct: 4.96 (4.96) proj_loss: -0.5911 (-0.5911) time: 0.9277 data: 0.0003 [11-26 19:54:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 417/1669] eta: 0:19:19 tlr: 0.00013 tnm: 0.28 Lm: 6.294 (6.294) Lt: 5.474 (5.474) Accm: 4.04 (4.04) Acct: 6.68 (6.68) proj_loss: -0.6252 (-0.6252) time: 0.9277 data: 0.0002 [11-26 20:00:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.28 Lm: 6.535 (6.483) Lt: 5.876 (5.784) Accm: 3.19 (3.43) Acct: 4.99 (5.27) proj_loss: -0.6401 (-0.6381) time: 0.9243 data: 0.0003 [11-26 20:00:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.28 Lm: 6.306 (6.336) Lt: 5.532 (5.569) Accm: 3.92 (3.78) Acct: 5.89 (6.11) proj_loss: -0.6140 (-0.6067) time: 0.9243 data: 0.0003 [11-26 20:00:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.28 Lm: 6.514 (6.470) Lt: 5.757 (5.728) Accm: 3.39 (3.37) Acct: 5.44 (5.26) proj_loss: -0.6165 (-0.6207) time: 0.9243 data: 0.0002 [11-26 20:00:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.28 Lm: 6.529 (6.560) Lt: 5.785 (5.841) Accm: 3.18 (3.23) Acct: 5.03 (5.14) proj_loss: -0.6322 (-0.6321) time: 0.9243 data: 0.0002 [11-26 20:00:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.28 Lm: 6.432 (6.405) Lt: 5.663 (5.635) Accm: 3.26 (3.39) Acct: 5.10 (5.35) proj_loss: -0.5949 (-0.6116) time: 0.9243 data: 0.0003 [11-26 20:00:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.28 Lm: 6.499 (6.512) Lt: 5.747 (5.799) Accm: 3.35 (3.18) Acct: 5.03 (4.80) proj_loss: -0.6294 (-0.6336) time: 0.9243 data: 0.0003 [11-26 20:00:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.28 Lm: 6.252 (6.241) Lt: 5.524 (5.499) Accm: 4.06 (4.28) Acct: 6.20 (6.54) proj_loss: -0.6253 (-0.6189) time: 0.9243 data: 0.0003 [11-26 20:00:43] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.28 Lm: 6.309 (6.325) Lt: 5.508 (5.535) Accm: 4.08 (4.05) Acct: 6.34 (6.57) proj_loss: -0.6135 (-0.6187) time: 0.9243 data: 0.0002 [11-26 20:07:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.341 (6.338) Lt: 5.532 (5.540) Accm: 3.94 (3.94) Acct: 6.34 (6.41) proj_loss: -0.6096 (-0.6145) time: 0.9271 data: 0.0002 [11-26 20:07:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.441 (6.415) Lt: 5.707 (5.660) Accm: 3.55 (3.46) Acct: 5.54 (5.36) proj_loss: -0.6174 (-0.6201) time: 0.9271 data: 0.0002 [11-26 20:07:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.545 (6.560) Lt: 5.753 (5.811) Accm: 3.20 (3.23) Acct: 5.22 (5.21) proj_loss: -0.6287 (-0.6262) time: 0.9271 data: 0.0003 [11-26 20:07:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.333 (6.301) Lt: 5.580 (5.542) Accm: 3.80 (4.09) Acct: 5.99 (6.35) proj_loss: -0.6208 (-0.6182) time: 0.9271 data: 0.0003 [11-26 20:07:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.287 (6.318) Lt: 5.526 (5.551) Accm: 3.85 (3.78) Acct: 5.99 (6.10) proj_loss: -0.6151 (-0.6112) time: 0.9271 data: 0.0003 [11-26 20:07:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.429 (6.411) Lt: 5.618 (5.620) Accm: 3.37 (3.41) Acct: 5.42 (5.45) proj_loss: -0.5932 (-0.6066) time: 0.9271 data: 0.0003 [11-26 20:07:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.526 (6.522) Lt: 5.774 (5.799) Accm: 3.39 (3.28) Acct: 5.20 (4.98) proj_loss: -0.6315 (-0.6336) time: 0.9271 data: 0.0003 [11-26 20:07:09] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [1251/1669] eta: 0:06:27 tlr: 0.00013 tnm: 0.27 Lm: 6.455 (6.456) Lt: 5.748 (5.744) Accm: 3.45 (3.50) Acct: 5.48 (5.44) proj_loss: -0.6402 (-0.6386) time: 0.9271 data: 0.0003 [11-26 20:13:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.374 (6.409) Lt: 5.621 (5.659) Accm: 3.72 (3.58) Acct: 5.96 (5.68) proj_loss: -0.6401 (-0.6339) time: 0.9300 data: 0.0017 [11-26 20:13:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 178/350] Total time: 0:25:46 (0.927 s / it) [11-26 20:13:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.309 (6.276) Lt: 5.508 (5.481) Accm: 4.08 (4.17) Acct: 6.34 (6.73) proj_loss: -0.6135 (-0.6216) time: 0.9300 data: 0.0017 [11-26 20:13:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.252 (6.284) Lt: 5.524 (5.529) Accm: 4.06 (4.18) Acct: 6.20 (6.59) proj_loss: -0.6194 (-0.6185) time: 0.9300 data: 0.0017 [11-26 20:13:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.306 (6.349) Lt: 5.532 (5.568) Accm: 3.86 (3.79) Acct: 6.10 (6.14) proj_loss: -0.6162 (-0.6128) time: 0.9300 data: 0.0018 [11-26 20:13:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.432 (6.470) Lt: 5.663 (5.701) Accm: 3.26 (3.27) Acct: 5.10 (5.10) proj_loss: -0.5949 (-0.6105) time: 0.9300 data: 0.0017 [11-26 20:13:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.499 (6.494) Lt: 5.747 (5.765) Accm: 3.44 (3.42) Acct: 5.37 (5.28) proj_loss: -0.6294 (-0.6292) time: 0.9300 data: 0.0016 [11-26 20:13:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.529 (6.474) Lt: 5.721 (5.701) Accm: 3.22 (3.50) Acct: 5.41 (5.67) proj_loss: -0.6322 (-0.6276) time: 0.9300 data: 0.0019 [11-26 20:13:36] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 178/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.463 (6.425) Lt: 5.757 (5.680) Accm: 3.39 (3.42) Acct: 5.44 (5.31) proj_loss: -0.6183 (-0.6257) time: 0.9300 data: 0.0015 [11-26 20:13:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 178/350] Total time: 0:25:46 (0.927 s / it) [11-26 20:13:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 178/350] Total time: 0:25:46 (0.927 s / it) [11-26 20:13:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 178/350] Total time: 0:25:46 (0.927 s / it) [11-26 20:13:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 178/350] Total time: 0:25:46 (0.927 s / it) [11-26 20:13:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 178/350] Total time: 0:25:46 (0.927 s / it) [11-26 20:13:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 178/350] Total time: 0:25:46 (0.927 s / it) [11-26 20:13:36] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 178/350] Total time: 0:25:46 (0.927 s / it) [11-26 20:13:36] (/home/user/VAR/train.py , line 276)=> [ep178] (training ) Lm: 6.407 (6.421), Lt: 5.650 (5.666), Acc m&t: 3.65 5.71, Remain: 3 days, 2:13:24, Finish: 2024-11-29 06:27 [11-26 20:13:36] (/home/user/VAR/train.py , line 276)=> [ep178] (training ) Lm: 6.407 (6.421), Lt: 5.650 (5.666), Acc m&t: 3.65 5.71, Remain: 3 days, 2:13:47, Finish: 2024-11-29 06:27 [11-26 20:13:36] (/home/user/VAR/train.py , line 276)=> [ep178] (training ) Lm: 6.407 (6.421), Lt: 5.650 (5.666), Acc m&t: 3.65 5.71, Remain: 3 days, 2:14:24, Finish: 2024-11-29 06:28 [11-26 20:13:36] (/home/user/VAR/train.py , line 276)=> [ep178] (training ) Lm: 6.407 (6.421), Lt: 5.650 (5.666), Acc m&t: 3.65 5.71, Remain: 3 days, 2:13:20, Finish: 2024-11-29 06:26 [11-26 20:13:36] (/home/user/VAR/train.py , line 276)=> [ep178] (training ) Lm: 6.407 (6.421), Lt: 5.650 (5.666), Acc m&t: 3.65 5.71, Remain: 3 days, 2:14:07, Finish: 2024-11-29 06:27 [11-26 20:13:36] (/home/user/VAR/train.py , line 276)=> [ep178] (training ) Lm: 6.407 (6.421), Lt: 5.650 (5.666), Acc m&t: 3.65 5.71, Remain: 3 days, 2:13:59, Finish: 2024-11-29 06:27 [11-26 20:13:36] (/home/user/VAR/train.py , line 276)=> [ep178] (training ) Lm: 6.407 (6.421), Lt: 5.650 (5.666), Acc m&t: 3.65 5.71, Remain: 3 days, 2:13:22, Finish: 2024-11-29 06:26 [11-26 20:13:36] (/home/user/VAR/train.py , line 276)=> [ep178] (training ) Lm: 6.407 (6.421), Lt: 5.650 (5.666), Acc m&t: 3.65 5.71, Remain: 3 days, 2:15:39, Finish: 2024-11-29 06:29 [11-26 20:13:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 0/1669] eta: 0:24:50 tlr: 0.00013 tnm: 0.28 Lm: 6.367 (6.367) Lt: 5.616 (5.616) Accm: 3.47 (3.47) Acct: 5.41 (5.41) proj_loss: -0.6147 (-0.6147) time: 0.8929 data: 0.0003 [11-26 20:13:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 0/1669] eta: 0:24:50 tlr: 0.00013 tnm: 0.28 Lm: 6.358 (6.358) Lt: 5.583 (5.583) Accm: 3.73 (3.73) Acct: 5.68 (5.68) proj_loss: -0.6303 (-0.6303) time: 0.8931 data: 0.0003 [11-26 20:13:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 0/1669] eta: 0:24:51 tlr: 0.00013 tnm: 0.28 Lm: 6.285 (6.285) Lt: 5.593 (5.593) Accm: 3.86 (3.86) Acct: 6.16 (6.16) proj_loss: -0.6535 (-0.6535) time: 0.8934 data: 0.0004 [11-26 20:13:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 0/1669] eta: 0:24:50 tlr: 0.00013 tnm: 0.28 Lm: 6.339 (6.339) Lt: 5.587 (5.587) Accm: 4.49 (4.49) Acct: 6.92 (6.92) proj_loss: -0.6307 (-0.6307) time: 0.8933 data: 0.0004 [11-26 20:13:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 0/1669] eta: 0:24:51 tlr: 0.00013 tnm: 0.28 Lm: 6.594 (6.594) Lt: 5.870 (5.870) Accm: 2.78 (2.78) Acct: 4.20 (4.20) proj_loss: -0.6342 (-0.6342) time: 0.8938 data: 0.0004 [11-26 20:13:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 0/1669] eta: 0:24:51 tlr: 0.00013 tnm: 0.28 Lm: 6.309 (6.309) Lt: 5.516 (5.516) Accm: 4.44 (4.44) Acct: 6.92 (6.92) proj_loss: -0.6095 (-0.6095) time: 0.8934 data: 0.0004 [11-26 20:13:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 0/1669] eta: 0:24:51 tlr: 0.00013 tnm: 0.28 Lm: 6.277 (6.277) Lt: 5.508 (5.508) Accm: 3.98 (3.98) Acct: 6.27 (6.27) proj_loss: -0.6382 (-0.6382) time: 0.8935 data: 0.0004 [11-26 20:13:37] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 0/1669] eta: 0:24:51 tlr: 0.00013 tnm: 0.28 Lm: 6.465 (6.465) Lt: 5.807 (5.807) Accm: 3.37 (3.37) Acct: 5.13 (5.13) proj_loss: -0.6312 (-0.6312) time: 0.8938 data: 0.0004 [11-26 20:20:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 417/1669] eta: 0:20:12 tlr: 0.00013 tnm: 0.27 Lm: 6.460 (6.460) Lt: 5.721 (5.721) Accm: 3.42 (3.42) Acct: 5.44 (5.44) proj_loss: -0.6243 (-0.6243) time: 0.9262 data: 0.0003 [11-26 20:20:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 417/1669] eta: 0:20:12 tlr: 0.00013 tnm: 0.27 Lm: 6.369 (6.369) Lt: 5.584 (5.584) Accm: 3.64 (3.64) Acct: 5.68 (5.68) proj_loss: -0.6034 (-0.6034) time: 0.9262 data: 0.0003 [11-26 20:20:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 417/1669] eta: 0:20:12 tlr: 0.00013 tnm: 0.27 Lm: 6.297 (6.297) Lt: 5.525 (5.525) Accm: 4.07 (4.07) Acct: 6.01 (6.01) proj_loss: -0.6370 (-0.6370) time: 0.9262 data: 0.0002 [11-26 20:20:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 417/1669] eta: 0:20:12 tlr: 0.00013 tnm: 0.27 Lm: 6.337 (6.337) Lt: 5.526 (5.526) Accm: 4.20 (4.20) Acct: 6.70 (6.70) proj_loss: -0.6031 (-0.6031) time: 0.9262 data: 0.0003 [11-26 20:20:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 417/1669] eta: 0:20:12 tlr: 0.00013 tnm: 0.27 Lm: 6.442 (6.442) Lt: 5.729 (5.729) Accm: 3.50 (3.50) Acct: 5.54 (5.54) proj_loss: -0.6384 (-0.6384) time: 0.9262 data: 0.0003 [11-26 20:20:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 417/1669] eta: 0:20:12 tlr: 0.00013 tnm: 0.27 Lm: 6.511 (6.511) Lt: 5.783 (5.783) Accm: 3.37 (3.37) Acct: 4.92 (4.92) proj_loss: -0.6356 (-0.6356) time: 0.9262 data: 0.0003 [11-26 20:20:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 417/1669] eta: 0:20:12 tlr: 0.00013 tnm: 0.27 Lm: 6.479 (6.479) Lt: 5.755 (5.755) Accm: 3.25 (3.25) Acct: 5.22 (5.22) proj_loss: -0.6339 (-0.6339) time: 0.9262 data: 0.0003 [11-26 20:20:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 417/1669] eta: 0:20:12 tlr: 0.00013 tnm: 0.27 Lm: 6.284 (6.284) Lt: 5.555 (5.555) Accm: 4.17 (4.17) Acct: 6.58 (6.58) proj_loss: -0.6358 (-0.6358) time: 0.9262 data: 0.0003 [11-26 20:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 834/1669] eta: 0:13:11 tlr: 0.00013 tnm: 0.28 Lm: 6.339 (6.323) Lt: 5.587 (5.573) Accm: 3.85 (4.00) Acct: 6.23 (6.35) proj_loss: -0.6307 (-0.6247) time: 0.9282 data: 0.0003 [11-26 20:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 834/1669] eta: 0:13:11 tlr: 0.00013 tnm: 0.28 Lm: 6.309 (6.308) Lt: 5.516 (5.474) Accm: 4.44 (4.29) Acct: 6.82 (6.74) proj_loss: -0.5967 (-0.6004) time: 0.9282 data: 0.0003 [11-26 20:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 834/1669] eta: 0:13:11 tlr: 0.00013 tnm: 0.28 Lm: 6.371 (6.397) Lt: 5.616 (5.634) Accm: 3.70 (3.66) Acct: 5.58 (5.65) proj_loss: -0.6147 (-0.6076) time: 0.9282 data: 0.0003 [11-26 20:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 834/1669] eta: 0:13:11 tlr: 0.00013 tnm: 0.28 Lm: 6.337 (6.310) Lt: 5.550 (5.534) Accm: 3.93 (4.03) Acct: 6.13 (6.05) proj_loss: -0.6303 (-0.6330) time: 0.9282 data: 0.0002 [11-26 20:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 834/1669] eta: 0:13:11 tlr: 0.00013 tnm: 0.28 Lm: 6.599 (6.565) Lt: 5.865 (5.856) Accm: 3.15 (3.17) Acct: 4.92 (4.96) proj_loss: -0.6233 (-0.6216) time: 0.9282 data: 0.0003 [11-26 20:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 834/1669] eta: 0:13:11 tlr: 0.00013 tnm: 0.28 Lm: 6.594 (6.576) Lt: 5.870 (5.853) Accm: 2.86 (3.20) Acct: 4.44 (4.76) proj_loss: -0.6369 (-0.6384) time: 0.9282 data: 0.0002 [11-26 20:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 834/1669] eta: 0:13:11 tlr: 0.00013 tnm: 0.28 Lm: 6.305 (6.421) Lt: 5.508 (5.657) Accm: 3.98 (3.51) Acct: 6.27 (5.60) proj_loss: -0.6297 (-0.6216) time: 0.9282 data: 0.0003 [11-26 20:26:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [ 834/1669] eta: 0:13:11 tlr: 0.00013 tnm: 0.28 Lm: 6.454 (6.360) Lt: 5.634 (5.590) Accm: 3.47 (3.88) Acct: 5.75 (6.05) proj_loss: -0.6312 (-0.6329) time: 0.9282 data: 0.0003 [11-26 20:33:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [1251/1669] eta: 0:06:33 tlr: 0.00013 tnm: 0.27 Lm: 6.440 (6.376) Lt: 5.655 (5.611) Accm: 3.63 (3.85) Acct: 5.70 (5.95) proj_loss: -0.6243 (-0.6284) time: 0.9272 data: 0.0003 [11-26 20:33:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [1251/1669] eta: 0:06:33 tlr: 0.00013 tnm: 0.27 Lm: 6.515 (6.541) Lt: 5.783 (5.803) Accm: 3.41 (3.41) Acct: 5.04 (5.16) proj_loss: -0.6356 (-0.6332) time: 0.9272 data: 0.0002 [11-26 20:33:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [1251/1669] eta: 0:06:33 tlr: 0.00013 tnm: 0.27 Lm: 6.291 (6.375) Lt: 5.490 (5.611) Accm: 4.00 (3.73) Acct: 6.32 (5.91) proj_loss: -0.6286 (-0.6231) time: 0.9272 data: 0.0003 [11-26 20:33:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [1251/1669] eta: 0:06:33 tlr: 0.00013 tnm: 0.27 Lm: 6.371 (6.376) Lt: 5.599 (5.637) Accm: 3.76 (3.78) Acct: 6.06 (5.93) proj_loss: -0.6165 (-0.6176) time: 0.9272 data: 0.0003 [11-26 20:33:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [1251/1669] eta: 0:06:33 tlr: 0.00013 tnm: 0.27 Lm: 6.348 (6.345) Lt: 5.567 (5.576) Accm: 3.83 (3.88) Acct: 5.91 (5.83) proj_loss: -0.6336 (-0.6340) time: 0.9272 data: 0.0002 [11-26 20:33:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [1251/1669] eta: 0:06:33 tlr: 0.00013 tnm: 0.27 Lm: 6.602 (6.575) Lt: 5.878 (5.864) Accm: 3.01 (3.10) Acct: 4.89 (4.93) proj_loss: -0.6363 (-0.6285) time: 0.9272 data: 0.0002 [11-26 20:33:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [1251/1669] eta: 0:06:33 tlr: 0.00013 tnm: 0.27 Lm: 6.318 (6.313) Lt: 5.502 (5.478) Accm: 4.20 (4.21) Acct: 6.65 (6.59) proj_loss: -0.6031 (-0.6065) time: 0.9272 data: 0.0002 [11-26 20:33:14] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [1251/1669] eta: 0:06:33 tlr: 0.00013 tnm: 0.27 Lm: 6.369 (6.313) Lt: 5.584 (5.535) Accm: 3.76 (3.83) Acct: 5.77 (5.98) proj_loss: -0.6079 (-0.6059) time: 0.9272 data: 0.0003 [11-26 20:39:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.371 (6.345) Lt: 5.616 (5.561) Accm: 3.70 (3.73) Acct: 5.58 (5.88) proj_loss: -0.6011 (-0.6040) time: 0.9277 data: 0.0020 [11-26 20:39:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 179/350] Total time: 0:26:04 (0.937 s / it) [11-26 20:39:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.327 (6.339) Lt: 5.516 (5.504) Accm: 3.96 (4.05) Acct: 6.47 (6.52) proj_loss: -0.6095 (-0.6072) time: 0.9277 data: 0.0015 [11-26 20:39:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.358 (6.377) Lt: 5.583 (5.601) Accm: 3.73 (3.75) Acct: 5.68 (5.73) proj_loss: -0.6303 (-0.6259) time: 0.9277 data: 0.0014 [11-26 20:39:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.599 (6.513) Lt: 5.865 (5.804) Accm: 3.15 (3.30) Acct: 4.92 (5.10) proj_loss: -0.6367 (-0.6302) time: 0.9277 data: 0.0018 [11-26 20:39:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.305 (6.413) Lt: 5.508 (5.662) Accm: 3.98 (3.60) Acct: 6.27 (5.65) proj_loss: -0.6274 (-0.6207) time: 0.9277 data: 0.0017 [11-26 20:39:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.339 (6.345) Lt: 5.587 (5.613) Accm: 3.85 (3.88) Acct: 6.16 (5.98) proj_loss: -0.6307 (-0.6290) time: 0.9277 data: 0.0016 [11-26 20:39:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.436 (6.497) Lt: 5.697 (5.762) Accm: 3.74 (3.48) Acct: 5.65 (5.27) proj_loss: -0.6342 (-0.6322) time: 0.9277 data: 0.0015 [11-26 20:39:40] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 179/350] [1668/1669] eta: 0:00:00 tlr: 0.00013 tnm: 0.27 Lm: 6.454 (6.404) Lt: 5.675 (5.651) Accm: 3.47 (3.71) Acct: 5.65 (5.73) proj_loss: -0.6312 (-0.6304) time: 0.9277 data: 0.0017 [11-26 20:39:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 179/350] Total time: 0:26:04 (0.937 s / it) [11-26 20:39:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 179/350] Total time: 0:26:04 (0.937 s / it) [11-26 20:39:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 179/350] Total time: 0:26:04 (0.937 s / it) [11-26 20:39:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 179/350] Total time: 0:26:04 (0.937 s / it) [11-26 20:39:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 179/350] Total time: 0:26:04 (0.937 s / it) [11-26 20:39:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 179/350] Total time: 0:26:04 (0.937 s / it) [11-26 20:39:40] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 179/350] Total time: 0:26:04 (0.937 s / it) [11-26 20:41:54] (home/user/VAR/trainer.py, line 114)=> FID: 3.4200556703307257 [11-26 20:41:55] (/home/user/VAR/train.py , line 259)=> [*] [ep179] (val 50000) Lm: 6.4050, Lt: 5.6497, Acc m&t: 3.66 5.72, Val cost: 133.95s [11-26 20:41:55] (/home/user/VAR/train.py , line 264)=> [saving ckpt] ... [saving ckpt](*) finished! @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth [11-26 20:42:31] (/home/user/VAR/train.py , line 276)=> [ep179] (training ) Lm: 6.405 (6.405), Lt: 5.650 (5.650), Acc m&t: 3.66 5.72, Remain: 3 days, 1:36:46, Finish: 2024-11-29 06:16 [11-26 20:42:31] (/home/user/VAR/train.py , line 276)=> [ep179] (training ) Lm: 6.405 (6.405), Lt: 5.650 (5.650), Acc m&t: 3.66 5.72, Remain: 3 days, 1:37:39, Finish: 2024-11-29 06:17 [11-26 20:42:31] (/home/user/VAR/train.py , line 276)=> [ep179] (training ) Lm: 6.405 (6.405), Lt: 5.650 (5.650), Acc m&t: 3.66 5.72, Remain: 3 days, 1:36:17, Finish: 2024-11-29 06:15 [11-26 20:42:31] (/home/user/VAR/train.py , line 276)=> [ep179] (training ) Lm: 6.405 (6.405), Lt: 5.650 (5.650), Acc m&t: 3.66 5.72, Remain: 3 days, 1:36:09, Finish: 2024-11-29 06:15 [11-26 20:42:31] (/home/user/VAR/train.py , line 276)=> [ep179] (training ) Lm: 6.405 (6.405), Lt: 5.650 (5.650), Acc m&t: 3.66 5.72, Remain: 3 days, 1:37:04, Finish: 2024-11-29 06:16 [11-26 20:42:31] (/home/user/VAR/train.py , line 276)=> [ep179] (training ) Lm: 6.405 (6.405), Lt: 5.650 (5.650), Acc m&t: 3.66 5.72, Remain: 3 days, 1:37:50, Finish: 2024-11-29 06:17 [11-26 20:42:31] (/home/user/VAR/train.py , line 276)=> [ep179] (training ) Lm: 6.405 (6.405), Lt: 5.650 (5.650), Acc m&t: 3.66 5.72, Remain: 3 days, 1:37:00, Finish: 2024-11-29 06:16 [11-26 20:42:31] (/home/user/VAR/train.py , line 276)=> [ep179] (training ) Lm: 6.405 (6.405), Lt: 5.650 (5.650), Acc m&t: 3.66 5.72, Remain: 3 days, 1:38:22, Finish: 2024-11-29 06:18 [11-26 20:42:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 0/1669] eta: 0:25:25 tlr: 0.00013 tnm: 0.28 Lm: 6.345 (6.345) Lt: 5.676 (5.676) Accm: 3.86 (3.86) Acct: 5.79 (5.79) proj_loss: -0.6421 (-0.6421) time: 0.9140 data: 0.0003 [11-26 20:42:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 0/1669] eta: 0:24:51 tlr: 0.00013 tnm: 0.28 Lm: 6.390 (6.390) Lt: 5.649 (5.649) Accm: 3.63 (3.63) Acct: 5.13 (5.13) proj_loss: -0.6175 (-0.6175) time: 0.8939 data: 0.0004 [11-26 20:42:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 0/1669] eta: 0:24:51 tlr: 0.00013 tnm: 0.28 Lm: 6.443 (6.443) Lt: 5.708 (5.708) Accm: 3.45 (3.45) Acct: 5.58 (5.58) proj_loss: -0.5864 (-0.5864) time: 0.8936 data: 0.0004 [11-26 20:42:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 0/1669] eta: 0:24:52 tlr: 0.00013 tnm: 0.28 Lm: 6.234 (6.234) Lt: 5.415 (5.415) Accm: 4.63 (4.63) Acct: 7.30 (7.30) proj_loss: -0.6126 (-0.6126) time: 0.8940 data: 0.0004 [11-26 20:42:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 0/1669] eta: 0:24:52 tlr: 0.00013 tnm: 0.28 Lm: 5.995 (5.995) Lt: 5.089 (5.089) Accm: 5.71 (5.71) Acct: 9.23 (9.23) proj_loss: -0.5943 (-0.5943) time: 0.8942 data: 0.0003 [11-26 20:42:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 0/1669] eta: 0:24:52 tlr: 0.00013 tnm: 0.28 Lm: 6.503 (6.503) Lt: 5.705 (5.705) Accm: 3.16 (3.16) Acct: 4.99 (4.99) proj_loss: -0.6135 (-0.6135) time: 0.8943 data: 0.0004 [11-26 20:42:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 0/1669] eta: 0:24:51 tlr: 0.00013 tnm: 0.28 Lm: 6.629 (6.629) Lt: 5.803 (5.803) Accm: 3.10 (3.10) Acct: 5.17 (5.17) proj_loss: -0.6146 (-0.6146) time: 0.8939 data: 0.0004 [11-26 20:42:31] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 0/1669] eta: 0:25:48 tlr: 0.00013 tnm: 0.28 Lm: 6.368 (6.368) Lt: 5.636 (5.636) Accm: 3.23 (3.23) Acct: 5.20 (5.20) proj_loss: -0.6115 (-0.6115) time: 0.9279 data: 0.0004 [11-26 20:48:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.28 Lm: 6.367 (6.367) Lt: 5.679 (5.679) Accm: 3.47 (3.47) Acct: 5.46 (5.46) proj_loss: -0.6177 (-0.6177) time: 0.9284 data: 0.0002 [11-26 20:48:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.28 Lm: 6.367 (6.367) Lt: 5.703 (5.703) Accm: 3.81 (3.81) Acct: 5.72 (5.72) proj_loss: -0.6279 (-0.6279) time: 0.9284 data: 0.0002 [11-26 20:48:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.28 Lm: 6.239 (6.239) Lt: 5.456 (5.456) Accm: 4.30 (4.30) Acct: 6.44 (6.44) proj_loss: -0.6062 (-0.6062) time: 0.9284 data: 0.0003 [11-26 20:48:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.28 Lm: 6.086 (6.086) Lt: 5.259 (5.259) Accm: 4.92 (4.92) Acct: 7.99 (7.99) proj_loss: -0.6071 (-0.6071) time: 0.9284 data: 0.0002 [11-26 20:48:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.28 Lm: 6.586 (6.586) Lt: 5.823 (5.823) Accm: 3.16 (3.16) Acct: 5.08 (5.08) proj_loss: -0.6238 (-0.6238) time: 0.9284 data: 0.0002 [11-26 20:48:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.28 Lm: 6.236 (6.236) Lt: 5.389 (5.389) Accm: 4.37 (4.37) Acct: 7.06 (7.06) proj_loss: -0.6201 (-0.6201) time: 0.9284 data: 0.0003 [11-26 20:48:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.28 Lm: 6.393 (6.393) Lt: 5.653 (5.653) Accm: 3.69 (3.69) Acct: 6.01 (6.01) proj_loss: -0.6070 (-0.6070) time: 0.9285 data: 0.0003 [11-26 20:48:58] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 417/1669] eta: 0:19:20 tlr: 0.00013 tnm: 0.28 Lm: 6.441 (6.441) Lt: 5.668 (5.668) Accm: 3.49 (3.49) Acct: 5.70 (5.70) proj_loss: -0.6118 (-0.6118) time: 0.9284 data: 0.0003 [11-26 20:55:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.29 Lm: 6.378 (6.388) Lt: 5.631 (5.610) Accm: 3.82 (3.68) Acct: 5.82 (5.74) proj_loss: -0.6101 (-0.6100) time: 0.9255 data: 0.0002 [11-26 20:55:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.29 Lm: 6.389 (6.380) Lt: 5.676 (5.683) Accm: 3.76 (3.72) Acct: 5.65 (5.68) proj_loss: -0.6137 (-0.6228) time: 0.9255 data: 0.0002 [11-26 20:55:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.29 Lm: 6.390 (6.370) Lt: 5.649 (5.597) Accm: 3.63 (3.84) Acct: 5.13 (5.81) proj_loss: -0.6175 (-0.6129) time: 0.9255 data: 0.0003 [11-26 20:55:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.29 Lm: 6.542 (6.513) Lt: 5.803 (5.777) Accm: 3.22 (3.29) Acct: 5.17 (5.26) proj_loss: -0.6331 (-0.6324) time: 0.9255 data: 0.0002 [11-26 20:55:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.29 Lm: 6.178 (6.212) Lt: 5.430 (5.403) Accm: 4.12 (4.36) Acct: 6.75 (7.02) proj_loss: -0.6199 (-0.6170) time: 0.9255 data: 0.0003 [11-26 20:55:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.29 Lm: 6.239 (6.295) Lt: 5.415 (5.439) Accm: 4.11 (4.15) Acct: 6.82 (6.55) proj_loss: -0.6126 (-0.6089) time: 0.9255 data: 0.0003 [11-26 20:55:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.29 Lm: 6.342 (6.348) Lt: 5.599 (5.601) Accm: 3.93 (3.78) Acct: 6.13 (6.05) proj_loss: -0.6115 (-0.6085) time: 0.9255 data: 0.0003 [11-26 20:55:24] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 834/1669] eta: 0:12:53 tlr: 0.00013 tnm: 0.29 Lm: 6.368 (6.392) Lt: 5.719 (5.692) Accm: 3.63 (3.53) Acct: 5.30 (5.41) proj_loss: -0.6240 (-0.6265) time: 0.9255 data: 0.0003 ======================================================= RESTART [11-27 02:00:37] ======================================================= ======================================================= RESTART [11-27 02:00:37] ======================================================= ======================================================= RESTART [11-27 02:00:37] ======================================================= ======================================================= RESTART [11-27 02:00:37] ======================================================= ======================================================= RESTART [11-27 02:00:37] ======================================================= ======================================================= RESTART [11-27 02:00:37] ======================================================= ======================================================= RESTART [11-27 02:00:37] ======================================================= ======================================================= RESTART [11-27 02:00:37] ======================================================= [11-27 02:00:37] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-27 02:00:37] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-27 02:00:37] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-27 02:09:07] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-27 02:09:07] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add branch : main commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-27 02:09:07] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-27 02:09:09] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-27 02:09:09] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> [11-27 02:09:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-27 02:09:09] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> [11-27 02:09:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-27 02:09:10] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-27 02:09:10] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep180, it0 [11-27 02:09:10] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-27 02:00:37] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-27 02:00:37] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-27 02:00:37] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-27 02:09:07] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-27 02:09:07] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add branch : main } [11-27 02:09:07] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-27 02:09:09] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-27 02:09:09] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> [11-27 02:09:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-27 02:09:09] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> [11-27 02:09:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-27 02:09:10] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-27 02:09:10] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep180, it0 [11-27 02:09:10] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-27 02:00:37] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-27 02:00:37] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-27 02:00:37] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-27 02:09:07] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-27 02:09:07] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main commit_msg : add } [11-27 02:09:07] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-27 02:09:09] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-27 02:09:09] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> [11-27 02:09:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-27 02:09:09] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> [11-27 02:09:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-27 02:09:10] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-27 02:09:10] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep180, it0 [11-27 02:09:10] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-27 02:00:37] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-27 02:00:37] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-27 02:00:37] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-27 02:09:07] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-27 02:09:07] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 branch : main } [11-27 02:09:07] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-27 02:09:09] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-27 02:09:09] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> [11-27 02:09:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-27 02:09:09] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-27 02:09:09] (e/user/VAR/utils/data.py, line 51)=> [11-27 02:09:09] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-27 02:09:10] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-27 02:09:10] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep180, it0 [11-27 02:09:10] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-27 02:00:37] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-27 02:00:37] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-27 02:00:37] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-27 02:09:07] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-27 02:09:07] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 commit_msg : add branch : main } [11-27 02:09:07] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-27 02:09:10] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-27 02:09:10] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> [11-27 02:09:10] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-27 02:09:10] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> [11-27 02:09:10] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-27 02:09:10] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-27 02:09:10] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep180, it0 [11-27 02:09:10] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-27 02:00:37] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-27 02:00:37] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-27 02:00:37] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-27 02:09:07] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-27 02:09:07] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-27 02:09:07] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-27 02:09:10] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-27 02:09:10] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> [11-27 02:09:10] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-27 02:09:10] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> [11-27 02:09:10] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-27 02:09:10] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-27 02:09:10] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep180, it0 [11-27 02:09:10] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-27 02:00:37] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-27 02:00:37] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-27 02:00:37] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-27 02:09:07] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-27 02:09:07] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-27 02:09:07] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-27 02:09:10] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-27 02:09:10] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> [11-27 02:09:10] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-27 02:09:10] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-27 02:09:10] (e/user/VAR/utils/data.py, line 51)=> [11-27 02:09:10] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-27 02:09:10] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-27 02:09:10] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep180, it0 [11-27 02:09:10] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ...[11-27 02:00:37] (er/VAR/utils/arg_util.py, line 227)=> [tf32] [precis] torch.get_float32_matmul_precision(): high [11-27 02:00:37] (er/VAR/utils/arg_util.py, line 228)=> [tf32] [ conv ] torch.backends.cudnn.allow_tf32: True [11-27 02:00:37] (er/VAR/utils/arg_util.py, line 229)=> [tf32] [matmul] torch.backends.cuda.matmul.allow_tf32: True [11-27 02:09:07] (/home/user/VAR/train.py , line 37)=> global bs=768, local bs=12 [11-27 02:09:07] (/home/user/VAR/train.py , line 38)=> initial args: { data_path : /mnt/localssd/ImageNet2012/ exp_name : text vae_ckpt : /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt vfast : 2 tfast : 2 depth : 30 ini : -1 hd : 0.02 aln : 0.5 alng : 0.0001 fp16 : 1 tblr : 8e-05 tlr : 0.00024000000000000003 twd : 0.05 twde : 0.05 tclip : 2.0 ls : 0.0 bs : 768 batch_size : 12 glb_batch_size : 768 ac : 1 ep : 350 wp : 7.0 wp0 : 0.005 wpe : 0.01 sche : lin0 opt : adamw afuse : True saln : False anorm : True fuse : True pn : 1_1_2_3_3_4_5_6_8_11 patch_size : 11 patch_nums : (1, 1, 2, 3, 3, 4, 5, 6, 8, 11) resos : (11, 11, 22, 33, 33, 44, 55, 66, 88, 121) data_load_reso : 256 mid_reso : 1.125 hflip : False workers : 12 pg : 0.0 pg0 : 4 pgwp : 1.1666666666666667 cmd : --depth=30 --bs=768 --ep=350 --fp16=1 --alng=1e-4 --wpe=0.01 --tblr=8e-5 --data_path /mnt/localssd/ImageNet2012/ --workers 12 --vfast 2 --tfast 2 --encoder_model vit_base_patch14_dinov2.lvd142m --decoder_model vit_base_patch14_dinov2.lvd142m --product_quant 2 --semantic_guide dinov2 --num_latent_tokens 121 --codebook_embed_dim 14 --codebook_size 16384 --v_patch_nums 1 1 2 3 3 4 5 6 8 11 --pn 1_1_2_3_3_4_5_6_8_11 --patch_size 11 --local_out_dir_path /sensei-fs/users/xiangl/exp141-var-d30/ --vae_ckpt /sensei-fs/users/xiangl/output/exp141/best_ckpt.pt --p_drop 0.0 --st_ep 50 --ed_ep 150 --sem_half True --clip_norm True --scale 1.0 --encoder_depth 6 --proj_coef 0.2 --query False acc_mean : None acc_tail : None L_mean : None L_tail : None vacc_mean : None vacc_tail : None vL_mean : None vL_tail : None grad_norm : None cur_lr : None cur_wd : None cur_it : cur_ep : remain_time : finish_time : local_out_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/ tb_log_dir_path : /sensei-fs/users/xiangl/exp141-var-d30/tb-VARd30__pn1_1_2_3_3_4_5_6_8_11__b768ep350adamlr8e-05wd0.05 log_txt_path : /sensei-fs/users/xiangl/exp141-var-d30/log.txt last_ckpt_path : /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth tf32 : True seed : None codebook_size : 16384 codebook_embed_dim : 14 codebook_l2_norm : True codebook_show_usage : True commit_loss_beta : 0.25 entropy_loss_ratio : 0.0 soft_entropy : True scale : 1.0 test_model : True encoder_ch_mult : [1, 1, 2, 2, 4] decoder_ch_mult : [1, 1, 2, 2, 4] z_channels : 256 dropout_p : 0.0 clip_norm : True v_patch_nums : [1, 1, 2, 3, 3, 4, 5, 6, 8, 11] enc_type : dinov2 dec_type : dinov2 semantic_guide : dinov2 num_latent_tokens : 121 encoder_model : vit_base_patch14_dinov2.lvd142m decoder_model : vit_base_patch14_dinov2.lvd142m abs_pos_embed : True share_quant_resi : 4 product_quant : 2 half_sem : True p_drop : 0.0 joint_sample : False infer_ckpt : masking_method : uniform st_ep : 50 ed_ep : 150 p_rand : 0.0 encoder_depth : 6 projector_dim : 2048 z_dims : [768] proj_coef : 0.2 query : False same_seed_for_all_ranks: 0 local_debug : False dbg_nan : False cfg : [3.5, 3.5] top_k : 900 top_p : 0.95 branch : main commit_msg : add commit_id : a2229298db3e1d35d196f16623f86dea25402aa2 } [11-27 02:09:07] (/home/user/VAR/train.py , line 42)=> [build PT data] ... [11-27 02:09:11] (e/user/VAR/utils/data.py, line 34)=> [Dataset] len(train_set)=1281167, len(val_set)=50000, num_classes=1000 [11-27 02:09:11] (e/user/VAR/utils/data.py, line 48)=> Transform [train] = [11-27 02:09:11] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-27 02:09:11] (e/user/VAR/utils/data.py, line 51)=> RandomCrop(size=(256, 256), padding=None) [11-27 02:09:11] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-27 02:09:11] (e/user/VAR/utils/data.py, line 51)=> [11-27 02:09:11] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-27 02:09:11] (e/user/VAR/utils/data.py, line 48)=> Transform [val] = [11-27 02:09:11] (e/user/VAR/utils/data.py, line 51)=> Resize(size=288, interpolation=lanczos, max_size=None, antialias=True) [11-27 02:09:11] (e/user/VAR/utils/data.py, line 51)=> CenterCrop(size=(256, 256)) [11-27 02:09:11] (e/user/VAR/utils/data.py, line 51)=> ToTensor() [11-27 02:09:11] (e/user/VAR/utils/data.py, line 51)=> [11-27 02:09:11] (e/user/VAR/utils/data.py, line 54)=> --------------------------- [11-27 02:09:11] (/home/user/VAR/train.py , line 65)=> [auto_resume] load ckpt from @ /sensei-fs/users/xiangl/exp141-var-d30/ar-ckpt-last.pth ... [11-27 02:09:11] (/home/user/VAR/train.py , line 65)=> [auto_resume success] resume from ep180, it0 [11-27 02:09:11] (/home/user/VAR/train.py , line 66)=> [dataloader multi processing] ... [dataloader multi processing](*) finished! (47.36s) [dataloader multi processing](*) finished! (48.25s) [dataloader multi processing](*) finished! (48.69s) [dataloader multi processing](*) finished! (48.71s) [dataloader multi processing](*) finished! (49.23s) [dataloader multi processing](*) finished! (48.71s) [dataloader multi processing](*) finished! (50.72s) [dataloader multi processing](*) finished! (52.39s) [11-27 02:09:58] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-27 02:10:01] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-27 02:10:01] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-27 02:10:02] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-27 02:09:57] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-27 02:10:03] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-27 02:10:03] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-27 02:10:04] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-27 02:09:58] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-27 02:10:03] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-27 02:10:03] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-27 02:10:04] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-27 02:09:58] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-27 02:10:03] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-27 02:10:03] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-27 02:10:04] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-27 02:10:00] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-27 02:10:04] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-27 02:10:04] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-27 02:10:05] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-27 02:10:00] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-27 02:10:05] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-27 02:10:05] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-27 02:10:06] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-27 02:10:00] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-27 02:10:05] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-27 02:10:05] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-27 02:10:06] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-27 02:10:02] (/home/user/VAR/train.py , line 72)=> [dataloader] gbs=768, lbs=12, iters_train=1669, types(tr, va)=('DatasetFolder', 'DatasetFolder') [11-27 02:10:07] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-27 02:10:07] (/lookup_free_quantize.py, line 128)=> scale is tensor([0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673, 0.2673]) [11-27 02:10:08] (e/user/VAR/models/var.py, line 117)=> [constructor] ==== flash_if_available=True (0/30), fused_if_available=True (fusing_add_ln=0/30, fusing_mlp=0/30) ==== [VAR config ] embed_dim=1920, num_heads=30, depth=30, mlp_ratio=4.0 [drop ratios ] drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.125 (tensor([0.0000, 0.0043, 0.0086, 0.0129, 0.0172, 0.0216, 0.0259, 0.0302, 0.0345, 0.0388, 0.0431, 0.0474, 0.0517, 0.0560, 0.0603, 0.0647, 0.0690, 0.0733, 0.0776, 0.0819, 0.0862, 0.0905, 0.0948, 0.0991, 0.1034, 0.1078, 0.1121, 0.1164, 0.1207, 0.1250])) [11-27 02:10:05] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-27 02:10:48] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-27 02:10:48] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-27 02:10:48] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-27 02:10:48] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-27 02:10:49] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank0] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-27 02:10:07] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-27 02:10:48] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-27 02:10:48] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-27 02:10:48] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-27 02:10:48] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-27 02:10:49] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank8] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-27 02:10:09] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-27 02:10:48] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-27 02:10:48] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-27 02:10:48] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-27 02:10:48] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-27 02:10:49] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank16] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-27 02:10:11] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-27 02:10:48] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-27 02:10:48] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-27 02:10:48] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-27 02:10:48] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-27 02:10:49] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank24] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-27 02:10:10] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-27 02:10:48] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-27 02:10:48] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-27 02:10:48] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-27 02:10:48] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-27 02:10:49] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank32] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-27 02:10:07] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-27 02:10:48] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-27 02:10:48] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-27 02:10:48] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-27 02:10:48] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-27 02:10:49] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank40] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-27 02:10:09] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-27 02:10:48] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-27 02:10:48] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-27 02:10:48] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-27 02:10:48] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-27 02:10:49] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank48] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-27 02:10:07] (e/user/VAR/models/var.py, line 425)=> [init_weights] VAR with init_std=0.0131762 [11-27 02:10:48] (/home/user/VAR/train.py , line 125)=> [INIT] VAR model = OptimizedModule( (_orig_mod): VAR( drop_path_rate=0.125 (word_embed): Linear(in_features=28, out_features=1920, bias=False) (class_emb): Embedding(1001, 1920) (lvl_embed): Embedding(10, 1920) (shared_ada_lin): Identity() (blocks): ModuleList( (0): AdaLNSelfAttn( shared_aln=False (drop_path): Identity() (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) (1-29): 29 x AdaLNSelfAttn( shared_aln=False (drop_path): DropPath((drop_prob=...)) (attn): SelfAttention( (mat_qkv): Linear(in_features=1920, out_features=5760, bias=False) (proj): Linear(in_features=1920, out_features=1920, bias=True) (proj_drop): Identity() ) (ffn): FFN( fused_mlp_func=False (fc1): Linear(in_features=1920, out_features=7680, bias=True) (act): GELU(approximate='tanh') (fc2): Linear(in_features=7680, out_features=1920, bias=True) (drop): Identity() ) (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=11520, bias=True) ) ) ) (head_nm): AdaLNBeforeHead( (ln_wo_grad): LayerNorm((1920,), eps=1e-06, elementwise_affine=False) (ada_lin): Sequential( (0): SiLU() (1): Linear(in_features=1920, out_features=3840, bias=True) ) ) (head): Linear(in_features=1920, out_features=32768, bias=True) (projectors): ModuleList( (0): Sequential( (0): Linear(in_features=1920, out_features=2048, bias=True) (1): SiLU() (2): Linear(in_features=2048, out_features=2048, bias=True) (3): SiLU() (4): Linear(in_features=2048, out_features=768, bias=True) ) ) ) ) [11-27 02:10:48] (/home/user/VAR/train.py , line 127)=> [INIT][#para] VAE=257.83, VAE.enc=86.05, VAE.dec=85.87, VAE.quant=0.01 [11-27 02:10:48] (/home/user/VAR/train.py , line 128)=> [INIT][#para] VAR=2074.04 [11-27 02:10:48] (/VAR/utils/lr_control.py, line 99)=> [get_param_groups] param_groups = { 'D': { 'lr_sc': 1.0, 'params': "('_orig_mod.word_embed.weight, _orig_mod.class_emb.weight, _orig_mod.blocks.0.attn.mat_qkv.weight, _orig_mod.blocks.0.attn.proj.weight, _orig_mod.blocks.0.ffn.fc1.weight, '\n" " '_orig_mod.blocks.0.ffn.fc2.weight, _orig_mod.blocks.0.ada_lin.1.weight, _orig_mod.blocks.1.attn.mat_qkv.weight, _orig_mod.blocks.1.attn.proj.weight, _orig_mod.blocks.1.ffn.fc1.weight, '\n" " '_orig_mod.blocks.1.ffn.fc2.weight, _orig_mod.blocks.1.ada_lin.1.weight, _orig_mod.blocks.2.attn.mat_qkv.weight, _orig_mod.blocks.2.attn.proj.weight, _orig_mod.blocks.2.ffn.fc1.weight, '\n" " '_orig_mod.blocks.2.ffn.fc2.weight, _orig_mod.blocks.2.ada_lin.1.weight, _orig_mod.blocks.3.attn.mat_qkv.weight, _orig_mod.blocks.3.attn.proj.weight, _orig_mod.blocks.3.ffn.fc1.weight, '\n" " '_orig_mod.blocks.3.ffn.fc2.weight, _orig_mod.blocks.3.ada_lin.1.weight, _orig_mod.blocks.4.attn.mat_qkv.weight, _orig_mod.blocks.4.attn.proj.weight, _orig_mod.blocks.4.ffn.fc1.weight, '\n" " '_orig_mod.blocks.4.ffn.fc2.weight, _orig_mod.blocks.4.ada_lin.1.weight, _orig_mod.blocks.5.attn.mat_qkv.weight, _orig_mod.blocks.5.attn.proj.weight, _orig_mod.blocks.5.ffn.fc1.weight, '\n" " '_orig_mod.blocks.5.ffn.fc2.weight, _orig_mod.blocks.5.ada_lin.1.weight, _orig_mod.blocks.6.attn.mat_qkv.weight, _orig_mod.blocks.6.attn.proj.weight, _orig_mod.blocks.6.ffn.fc1.weight, '\n" " '_orig_mod.blocks.6.ffn.fc2.weight, _orig_mod.blocks.6.ada_lin.1.weight, _orig_mod.blocks.7.attn.mat_qkv.weight, _orig_mod.blocks.7.attn.proj.weight, _orig_mod.blocks.7.ffn.fc1.weight, '\n" " '_orig_mod.blocks.7.ffn.fc2.weight, _orig_mod.blocks.7.ada_lin.1.weight, _orig_mod.blocks.8.attn.mat_qkv.weight, _orig_mod.blocks.8.attn.proj.weight, _orig_mod.blocks.8.ffn.fc1.weight, '\n" " '_orig_mod.blocks.8.ffn.fc2.weight, _orig_mod.blocks.8.ada_lin.1.weight, _orig_mod.blocks.9.attn.mat_qkv.weight, _orig_mod.blocks.9.attn.proj.weight, _orig_mod.blocks.9.ffn.fc1.weight, '\n" " '_orig_mod.blocks.9.ffn.fc2.weight, _orig_mod.blocks.9.ada_lin.1.weight, _orig_mod.blocks.10.attn.mat_qkv.weight, _orig_mod.blocks.10.attn.proj.weight, _orig_mod.blocks.10.ffn.fc1.weight, '\n" " '_orig_mod.blocks.10.ffn.fc2.weight, _orig_mod.blocks.10.ada_lin.1.weight, _orig_mod.blocks.11.attn.mat_qkv.weight, _orig_mod.blocks.11.attn.proj.weight, _orig_mod.blocks.11.ffn.fc1.weight, '\n" " '_orig_mod.blocks.11.ffn.fc2.weight, _orig_mod.blocks.11.ada_lin.1.weight, _orig_mod.blocks.12.attn.mat_qkv.weight, _orig_mod.blocks.12.attn.proj.weight, _orig_mod.blocks.12.ffn.fc1.weight, '\n" " '_orig_mod.blocks.12.ffn.fc2.weight, _orig_mod.blocks.12.ada_lin.1.weight, _orig_mod.blocks.13.attn.mat_qkv.weight, _orig_mod.blocks.13.attn.proj.weight, _orig_mod.blocks.13.ffn.fc1.weight, '\n" " '_orig_mod.blocks.13.ffn.fc2.weight, _orig_mod.blocks.13.ada_lin.1.weight, _orig_mod.blocks.14.attn.mat_qkv.weight, _orig_mod.blocks.14.attn.proj.weight, _orig_mod.blocks.14.ffn.fc1.weight, '\n" " '_orig_mod.blocks.14.ffn.fc2.weight, _orig_mod.blocks.14.ada_lin.1.weight, _orig_mod.blocks.15.attn.mat_qkv.weight, _orig_mod.blocks.15.attn.proj.weight, _orig_mod.blocks.15.ffn.fc1.weight, '\n" " '_orig_mod.blocks.15.ffn.fc2.weight, _orig_mod.blocks.15.ada_lin.1.weight, _orig_mod.blocks.16.attn.mat_qkv.weight, _orig_mod.blocks.16.attn.proj.weight, _orig_mod.blocks.16.ffn.fc1.weight, '\n" " '_orig_mod.blocks.16.ffn.fc2.weight, _orig_mod.blocks.16.ada_lin.1.weight, _orig_mod.blocks.17.attn.mat_qkv.weight, _orig_mod.blocks.17.attn.proj.weight, _orig_mod.blocks.17.ffn.fc1.weight, '\n" " '_orig_mod.blocks.17.ffn.fc2.weight, _orig_mod.blocks.17.ada_lin.1.weight, _orig_mod.blocks.18.attn.mat_qkv.weight, _orig_mod.blocks.18.attn.proj.weight, _orig_mod.blocks.18.ffn.fc1.weight, '\n" " '_orig_mod.blocks.18.ffn.fc2.weight, _orig_mod.blocks.18.ada_lin.1.weight, _orig_mod.blocks.19.attn.mat_qkv.weight, _orig_mod.blocks.19.attn.proj.weight, _orig_mod.blocks.19.ffn.fc1.weight, '\n" " '_orig_mod.blocks.19.ffn.fc2.weight, _orig_mod.blocks.19.ada_lin.1.weight, _orig_mod.blocks.20.attn.mat_qkv.weight, _orig_mod.blocks.20.attn.proj.weight, _orig_mod.blocks.20.ffn.fc1.weight, '\n" " '_orig_mod.blocks.20.ffn.fc2.weight, _orig_mod.blocks.20.ada_lin.1.weight, _orig_mod.blocks.21.attn.mat_qkv.weight, _orig_mod.blocks.21.attn.proj.weight, _orig_mod.blocks.21.ffn.fc1.weight, '\n" " '_orig_mod.blocks.21.ffn.fc2.weight, _orig_mod.blocks.21.ada_lin.1.weight, _orig_mod.blocks.22.attn.mat_qkv.weight, _orig_mod.blocks.22.attn.proj.weight, _orig_mod.blocks.22.ffn.fc1.weight, '\n" " '_orig_mod.blocks.22.ffn.fc2.weight, _orig_mod.blocks.22.ada_lin.1.weight, _orig_mod.blocks.23.attn.mat_qkv.weight, _orig_mod.blocks.23.attn.proj.weight, _orig_mod.blocks.23.ffn.fc1.weight, '\n" " '_orig_mod.blocks.23.ffn.fc2.weight, _orig_mod.blocks.23.ada_lin.1.weight, _orig_mod.blocks.24.attn.mat_qkv.weight, _orig_mod.blocks.24.attn.proj.weight, _orig_mod.blocks.24.ffn.fc1.weight, '\n" " '_orig_mod.blocks.24.ffn.fc2.weight, _orig_mod.blocks.24.ada_lin.1.weight, _orig_mod.blocks.25.attn.mat_qkv.weight, _orig_mod.blocks.25.attn.proj.weight, _orig_mod.blocks.25.ffn.fc1.weight, '\n" " '_orig_mod.blocks.25.ffn.fc2.weight, _orig_mod.blocks.25.ada_lin.1.weight, _orig_mod.blocks.26.attn.mat_qkv.weight, _orig_mod.blocks.26.attn.proj.weight, _orig_mod.blocks.26.ffn.fc1.weight, '\n" " '_orig_mod.blocks.26.ffn.fc2.weight, _orig_mod.blocks.26.ada_lin.1.weight, _orig_mod.blocks.27.attn.mat_qkv.weight, _orig_mod.blocks.27.attn.proj.weight, _orig_mod.blocks.27.ffn.fc1.weight, '\n" " '_orig_mod.blocks.27.ffn.fc2.weight, _orig_mod.blocks.27.ada_lin.1.weight, _orig_mod.blocks.28.attn.mat_qkv.weight, _orig_mod.blocks.28.attn.proj.weight, _orig_mod.blocks.28.ffn.fc1.weight, '\n" " '_orig_mod.blocks.28.ffn.fc2.weight, _orig_mod.blocks.28.ada_lin.1.weight, _orig_mod.blocks.29.attn.mat_qkv.weight, _orig_mod.blocks.29.attn.proj.weight, _orig_mod.blocks.29.ffn.fc1.weight, '\n" " '_orig_mod.blocks.29.ffn.fc2.weight, _orig_mod.blocks.29.ada_lin.1.weight, _orig_mod.head_nm.ada_lin.1.weight, _orig_mod.head.weight, _orig_mod.projectors.0.0.weight, '\n" " '_orig_mod.projectors.0.2.weight, _orig_mod.projectors.0.4.weight')", 'wd_sc': 1.0}, 'ND': { 'lr_sc': 1.0, 'params': "('_orig_mod.pos_start, _orig_mod.pos_1LC, _orig_mod.lvl_embed.weight, _orig_mod.blocks.0.attn.scale_mul_1H11, _orig_mod.blocks.0.attn.q_bias, _orig_mod.blocks.0.attn.v_bias, '\n" " '_orig_mod.blocks.0.attn.proj.bias, _orig_mod.blocks.0.ffn.fc1.bias, _orig_mod.blocks.0.ffn.fc2.bias, _orig_mod.blocks.0.ada_lin.1.bias, _orig_mod.blocks.1.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.1.attn.q_bias, _orig_mod.blocks.1.attn.v_bias, _orig_mod.blocks.1.attn.proj.bias, _orig_mod.blocks.1.ffn.fc1.bias, _orig_mod.blocks.1.ffn.fc2.bias, '\n" " '_orig_mod.blocks.1.ada_lin.1.bias, _orig_mod.blocks.2.attn.scale_mul_1H11, _orig_mod.blocks.2.attn.q_bias, _orig_mod.blocks.2.attn.v_bias, _orig_mod.blocks.2.attn.proj.bias, '\n" " '_orig_mod.blocks.2.ffn.fc1.bias, _orig_mod.blocks.2.ffn.fc2.bias, _orig_mod.blocks.2.ada_lin.1.bias, _orig_mod.blocks.3.attn.scale_mul_1H11, _orig_mod.blocks.3.attn.q_bias, '\n" " '_orig_mod.blocks.3.attn.v_bias, _orig_mod.blocks.3.attn.proj.bias, _orig_mod.blocks.3.ffn.fc1.bias, _orig_mod.blocks.3.ffn.fc2.bias, _orig_mod.blocks.3.ada_lin.1.bias, '\n" " '_orig_mod.blocks.4.attn.scale_mul_1H11, _orig_mod.blocks.4.attn.q_bias, _orig_mod.blocks.4.attn.v_bias, _orig_mod.blocks.4.attn.proj.bias, _orig_mod.blocks.4.ffn.fc1.bias, '\n" " '_orig_mod.blocks.4.ffn.fc2.bias, _orig_mod.blocks.4.ada_lin.1.bias, _orig_mod.blocks.5.attn.scale_mul_1H11, _orig_mod.blocks.5.attn.q_bias, _orig_mod.blocks.5.attn.v_bias, '\n" " '_orig_mod.blocks.5.attn.proj.bias, _orig_mod.blocks.5.ffn.fc1.bias, _orig_mod.blocks.5.ffn.fc2.bias, _orig_mod.blocks.5.ada_lin.1.bias, _orig_mod.blocks.6.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.6.attn.q_bias, _orig_mod.blocks.6.attn.v_bias, _orig_mod.blocks.6.attn.proj.bias, _orig_mod.blocks.6.ffn.fc1.bias, _orig_mod.blocks.6.ffn.fc2.bias, '\n" " '_orig_mod.blocks.6.ada_lin.1.bias, _orig_mod.blocks.7.attn.scale_mul_1H11, _orig_mod.blocks.7.attn.q_bias, _orig_mod.blocks.7.attn.v_bias, _orig_mod.blocks.7.attn.proj.bias, '\n" " '_orig_mod.blocks.7.ffn.fc1.bias, _orig_mod.blocks.7.ffn.fc2.bias, _orig_mod.blocks.7.ada_lin.1.bias, _orig_mod.blocks.8.attn.scale_mul_1H11, _orig_mod.blocks.8.attn.q_bias, '\n" " '_orig_mod.blocks.8.attn.v_bias, _orig_mod.blocks.8.attn.proj.bias, _orig_mod.blocks.8.ffn.fc1.bias, _orig_mod.blocks.8.ffn.fc2.bias, _orig_mod.blocks.8.ada_lin.1.bias, '\n" " '_orig_mod.blocks.9.attn.scale_mul_1H11, _orig_mod.blocks.9.attn.q_bias, _orig_mod.blocks.9.attn.v_bias, _orig_mod.blocks.9.attn.proj.bias, _orig_mod.blocks.9.ffn.fc1.bias, '\n" " '_orig_mod.blocks.9.ffn.fc2.bias, _orig_mod.blocks.9.ada_lin.1.bias, _orig_mod.blocks.10.attn.scale_mul_1H11, _orig_mod.blocks.10.attn.q_bias, _orig_mod.blocks.10.attn.v_bias, '\n" " '_orig_mod.blocks.10.attn.proj.bias, _orig_mod.blocks.10.ffn.fc1.bias, _orig_mod.blocks.10.ffn.fc2.bias, _orig_mod.blocks.10.ada_lin.1.bias, _orig_mod.blocks.11.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.11.attn.q_bias, _orig_mod.blocks.11.attn.v_bias, _orig_mod.blocks.11.attn.proj.bias, _orig_mod.blocks.11.ffn.fc1.bias, _orig_mod.blocks.11.ffn.fc2.bias, '\n" " '_orig_mod.blocks.11.ada_lin.1.bias, _orig_mod.blocks.12.attn.scale_mul_1H11, _orig_mod.blocks.12.attn.q_bias, _orig_mod.blocks.12.attn.v_bias, _orig_mod.blocks.12.attn.proj.bias, '\n" " '_orig_mod.blocks.12.ffn.fc1.bias, _orig_mod.blocks.12.ffn.fc2.bias, _orig_mod.blocks.12.ada_lin.1.bias, _orig_mod.blocks.13.attn.scale_mul_1H11, _orig_mod.blocks.13.attn.q_bias, '\n" " '_orig_mod.blocks.13.attn.v_bias, _orig_mod.blocks.13.attn.proj.bias, _orig_mod.blocks.13.ffn.fc1.bias, _orig_mod.blocks.13.ffn.fc2.bias, _orig_mod.blocks.13.ada_lin.1.bias, '\n" " '_orig_mod.blocks.14.attn.scale_mul_1H11, _orig_mod.blocks.14.attn.q_bias, _orig_mod.blocks.14.attn.v_bias, _orig_mod.blocks.14.attn.proj.bias, _orig_mod.blocks.14.ffn.fc1.bias, '\n" " '_orig_mod.blocks.14.ffn.fc2.bias, _orig_mod.blocks.14.ada_lin.1.bias, _orig_mod.blocks.15.attn.scale_mul_1H11, _orig_mod.blocks.15.attn.q_bias, _orig_mod.blocks.15.attn.v_bias, '\n" " '_orig_mod.blocks.15.attn.proj.bias, _orig_mod.blocks.15.ffn.fc1.bias, _orig_mod.blocks.15.ffn.fc2.bias, _orig_mod.blocks.15.ada_lin.1.bias, _orig_mod.blocks.16.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.16.attn.q_bias, _orig_mod.blocks.16.attn.v_bias, _orig_mod.blocks.16.attn.proj.bias, _orig_mod.blocks.16.ffn.fc1.bias, _orig_mod.blocks.16.ffn.fc2.bias, '\n" " '_orig_mod.blocks.16.ada_lin.1.bias, _orig_mod.blocks.17.attn.scale_mul_1H11, _orig_mod.blocks.17.attn.q_bias, _orig_mod.blocks.17.attn.v_bias, _orig_mod.blocks.17.attn.proj.bias, '\n" " '_orig_mod.blocks.17.ffn.fc1.bias, _orig_mod.blocks.17.ffn.fc2.bias, _orig_mod.blocks.17.ada_lin.1.bias, _orig_mod.blocks.18.attn.scale_mul_1H11, _orig_mod.blocks.18.attn.q_bias, '\n" " '_orig_mod.blocks.18.attn.v_bias, _orig_mod.blocks.18.attn.proj.bias, _orig_mod.blocks.18.ffn.fc1.bias, _orig_mod.blocks.18.ffn.fc2.bias, _orig_mod.blocks.18.ada_lin.1.bias, '\n" " '_orig_mod.blocks.19.attn.scale_mul_1H11, _orig_mod.blocks.19.attn.q_bias, _orig_mod.blocks.19.attn.v_bias, _orig_mod.blocks.19.attn.proj.bias, _orig_mod.blocks.19.ffn.fc1.bias, '\n" " '_orig_mod.blocks.19.ffn.fc2.bias, _orig_mod.blocks.19.ada_lin.1.bias, _orig_mod.blocks.20.attn.scale_mul_1H11, _orig_mod.blocks.20.attn.q_bias, _orig_mod.blocks.20.attn.v_bias, '\n" " '_orig_mod.blocks.20.attn.proj.bias, _orig_mod.blocks.20.ffn.fc1.bias, _orig_mod.blocks.20.ffn.fc2.bias, _orig_mod.blocks.20.ada_lin.1.bias, _orig_mod.blocks.21.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.21.attn.q_bias, _orig_mod.blocks.21.attn.v_bias, _orig_mod.blocks.21.attn.proj.bias, _orig_mod.blocks.21.ffn.fc1.bias, _orig_mod.blocks.21.ffn.fc2.bias, '\n" " '_orig_mod.blocks.21.ada_lin.1.bias, _orig_mod.blocks.22.attn.scale_mul_1H11, _orig_mod.blocks.22.attn.q_bias, _orig_mod.blocks.22.attn.v_bias, _orig_mod.blocks.22.attn.proj.bias, '\n" " '_orig_mod.blocks.22.ffn.fc1.bias, _orig_mod.blocks.22.ffn.fc2.bias, _orig_mod.blocks.22.ada_lin.1.bias, _orig_mod.blocks.23.attn.scale_mul_1H11, _orig_mod.blocks.23.attn.q_bias, '\n" " '_orig_mod.blocks.23.attn.v_bias, _orig_mod.blocks.23.attn.proj.bias, _orig_mod.blocks.23.ffn.fc1.bias, _orig_mod.blocks.23.ffn.fc2.bias, _orig_mod.blocks.23.ada_lin.1.bias, '\n" " '_orig_mod.blocks.24.attn.scale_mul_1H11, _orig_mod.blocks.24.attn.q_bias, _orig_mod.blocks.24.attn.v_bias, _orig_mod.blocks.24.attn.proj.bias, _orig_mod.blocks.24.ffn.fc1.bias, '\n" " '_orig_mod.blocks.24.ffn.fc2.bias, _orig_mod.blocks.24.ada_lin.1.bias, _orig_mod.blocks.25.attn.scale_mul_1H11, _orig_mod.blocks.25.attn.q_bias, _orig_mod.blocks.25.attn.v_bias, '\n" " '_orig_mod.blocks.25.attn.proj.bias, _orig_mod.blocks.25.ffn.fc1.bias, _orig_mod.blocks.25.ffn.fc2.bias, _orig_mod.blocks.25.ada_lin.1.bias, _orig_mod.blocks.26.attn.scale_mul_1H11, '\n" " '_orig_mod.blocks.26.attn.q_bias, _orig_mod.blocks.26.attn.v_bias, _orig_mod.blocks.26.attn.proj.bias, _orig_mod.blocks.26.ffn.fc1.bias, _orig_mod.blocks.26.ffn.fc2.bias, '\n" " '_orig_mod.blocks.26.ada_lin.1.bias, _orig_mod.blocks.27.attn.scale_mul_1H11, _orig_mod.blocks.27.attn.q_bias, _orig_mod.blocks.27.attn.v_bias, _orig_mod.blocks.27.attn.proj.bias, '\n" " '_orig_mod.blocks.27.ffn.fc1.bias, _orig_mod.blocks.27.ffn.fc2.bias, _orig_mod.blocks.27.ada_lin.1.bias, _orig_mod.blocks.28.attn.scale_mul_1H11, _orig_mod.blocks.28.attn.q_bias, '\n" " '_orig_mod.blocks.28.attn.v_bias, _orig_mod.blocks.28.attn.proj.bias, _orig_mod.blocks.28.ffn.fc1.bias, _orig_mod.blocks.28.ffn.fc2.bias, _orig_mod.blocks.28.ada_lin.1.bias, '\n" " '_orig_mod.blocks.29.attn.scale_mul_1H11, _orig_mod.blocks.29.attn.q_bias, _orig_mod.blocks.29.attn.v_bias, _orig_mod.blocks.29.attn.proj.bias, _orig_mod.blocks.29.ffn.fc1.bias, '\n" " '_orig_mod.blocks.29.ffn.fc2.bias, _orig_mod.blocks.29.ada_lin.1.bias, _orig_mod.head_nm.ada_lin.1.bias, _orig_mod.head.bias, _orig_mod.projectors.0.0.bias, _orig_mod.projectors.0.2.bias, '\n" " '_orig_mod.projectors.0.4.bias')", 'wd_sc': 0.0}} [11-27 02:10:49] (/VAR/utils/lr_control.py, line 104)=> [get_param_groups][rank56] type(model).__name__='OptimizedModule' count=375, numel=2074037380 [11-27 02:10:49] (/VAR/utils/lr_control.py, line 105)=> [11-27 02:10:49] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-27 02:10:52] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-27 02:10:52] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-27 02:10:53] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-27 02:10:53] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-27 02:16:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 0/1669] eta: 6 days, 21:01:20 tlr: 0.00013 tnm: 0.28 Lm: 6.459 (6.459) Lt: 5.646 (5.646) Accm: 3.61 (3.61) Acct: 5.85 (5.85) proj_loss: -0.5976 (-0.5976) time: 355.9499 data: 0.0006 [11-27 02:10:49] (/VAR/utils/lr_control.py, line 105)=> [11-27 02:10:49] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-27 02:10:52] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-27 02:10:52] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-27 02:10:52] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-27 02:10:52] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-27 02:16:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 0/1669] eta: 6 days, 20:51:08 tlr: 0.00013 tnm: 0.28 Lm: 6.361 (6.361) Lt: 5.604 (5.604) Accm: 3.64 (3.64) Acct: 5.51 (5.51) proj_loss: -0.5994 (-0.5994) time: 355.5834 data: 0.0005 [11-27 02:10:49] (/VAR/utils/lr_control.py, line 105)=> [11-27 02:10:49] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-27 02:10:52] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-27 02:10:52] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-27 02:10:52] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-27 02:10:52] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-27 02:16:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 0/1669] eta: 6 days, 21:02:46 tlr: 0.00013 tnm: 0.28 Lm: 6.204 (6.204) Lt: 5.412 (5.412) Accm: 4.31 (4.31) Acct: 7.16 (7.16) proj_loss: -0.6055 (-0.6055) time: 356.0016 data: 0.0005 [11-27 02:10:49] (/VAR/utils/lr_control.py, line 105)=> [11-27 02:10:49] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-27 02:10:53] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-27 02:10:53] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-27 02:10:53] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-27 02:10:53] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-27 02:16:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 0/1669] eta: 6 days, 21:30:25 tlr: 0.00013 tnm: 0.28 Lm: 6.641 (6.641) Lt: 5.877 (5.877) Accm: 2.80 (2.80) Acct: 4.86 (4.86) proj_loss: -0.6206 (-0.6206) time: 356.9955 data: 0.0007 [11-27 02:10:49] (/VAR/utils/lr_control.py, line 105)=> [11-27 02:10:49] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-27 02:10:52] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-27 02:10:52] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-27 02:10:52] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-27 02:10:52] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-27 02:16:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 0/1669] eta: 6 days, 21:03:54 tlr: 0.00013 tnm: 0.28 Lm: 6.407 (6.407) Lt: 5.634 (5.634) Accm: 3.44 (3.44) Acct: 4.99 (4.99) proj_loss: -0.6138 (-0.6138) time: 356.0423 data: 0.0007 [11-27 02:10:49] (/VAR/utils/lr_control.py, line 105)=> [11-27 02:10:49] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-27 02:10:51] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-27 02:10:51] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-27 02:10:51] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-27 02:10:51] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-27 02:16:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 0/1669] eta: 6 days, 21:20:24 tlr: 0.00013 tnm: 0.28 Lm: 6.361 (6.361) Lt: 5.636 (5.636) Accm: 3.38 (3.38) Acct: 5.20 (5.20) proj_loss: -0.6289 (-0.6289) time: 356.6355 data: 0.0007 [11-27 02:10:49] (/VAR/utils/lr_control.py, line 105)=> [11-27 02:10:49] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-27 02:10:52] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-27 02:10:52] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-27 02:10:52] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-27 02:10:52] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-27 02:16:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 0/1669] eta: 6 days, 21:15:12 tlr: 0.00013 tnm: 0.28 Lm: 6.001 (6.001) Lt: 5.116 (5.116) Accm: 5.23 (5.23) Acct: 8.40 (8.40) proj_loss: -0.6077 (-0.6077) time: 356.4486 data: 0.0005 [11-27 02:10:49] (/VAR/utils/lr_control.py, line 105)=> [11-27 02:10:49] (/home/user/VAR/train.py , line 143)=> [INIT] optim=functools.partial(, betas=(0.9, 0.95), fused=True), opt_kw={'lr': 0.00024000000000000003, 'weight_decay': 0} [11-27 02:10:52] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] var_wo_ddp missing: [] [11-27 02:10:52] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] var_wo_ddp unexpected: [] [11-27 02:10:52] (home/user/VAR/trainer.py, line 263)=> [VARTrainer.load_state_dict] vae_local missing: [] [11-27 02:10:52] (home/user/VAR/trainer.py, line 264)=> [VARTrainer.load_state_dict] vae_local unexpected: [] [11-27 02:16:59] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 0/1669] eta: 6 days, 21:29:38 tlr: 0.00013 tnm: 0.28 Lm: 6.497 (6.497) Lt: 5.705 (5.705) Accm: 3.07 (3.07) Acct: 4.58 (4.58) proj_loss: -0.5639 (-0.5639) time: 356.9674 data: 0.0007 [11-27 02:31:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 417/1669] eta: 1:02:38 tlr: 0.00013 tnm: 0.28 Lm: 6.242 (6.242) Lt: 5.442 (5.442) Accm: 3.99 (3.99) Acct: 6.28 (6.28) proj_loss: -0.6048 (-0.6048) time: 0.9212 data: 0.0002 [11-27 02:31:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 417/1669] eta: 1:02:41 tlr: 0.00013 tnm: 0.28 Lm: 6.580 (6.580) Lt: 5.817 (5.817) Accm: 3.13 (3.13) Acct: 5.08 (5.08) proj_loss: -0.6297 (-0.6297) time: 0.9212 data: 0.0002 [11-27 02:31:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 417/1669] eta: 1:02:40 tlr: 0.00013 tnm: 0.28 Lm: 6.403 (6.403) Lt: 5.701 (5.701) Accm: 3.45 (3.45) Acct: 5.34 (5.34) proj_loss: -0.6197 (-0.6197) time: 0.9212 data: 0.0003 [11-27 02:31:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 417/1669] eta: 1:02:38 tlr: 0.00013 tnm: 0.28 Lm: 6.227 (6.227) Lt: 5.364 (5.364) Accm: 4.41 (4.41) Acct: 7.20 (7.20) proj_loss: -0.6134 (-0.6134) time: 0.9212 data: 0.0003 [11-27 02:31:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 417/1669] eta: 1:02:38 tlr: 0.00013 tnm: 0.28 Lm: 6.433 (6.433) Lt: 5.661 (5.661) Accm: 3.53 (3.53) Acct: 5.89 (5.89) proj_loss: -0.6043 (-0.6043) time: 0.9212 data: 0.0003 [11-27 02:31:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 417/1669] eta: 1:02:37 tlr: 0.00013 tnm: 0.28 Lm: 6.394 (6.394) Lt: 5.682 (5.682) Accm: 3.55 (3.55) Acct: 5.29 (5.29) proj_loss: -0.6199 (-0.6199) time: 0.9212 data: 0.0002 [11-27 02:31:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 417/1669] eta: 1:02:40 tlr: 0.00013 tnm: 0.28 Lm: 6.080 (6.080) Lt: 5.301 (5.301) Accm: 4.68 (4.68) Acct: 7.37 (7.37) proj_loss: -0.6147 (-0.6147) time: 0.9212 data: 0.0003 [11-27 02:31:57] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 417/1669] eta: 1:02:41 tlr: 0.00013 tnm: 0.28 Lm: 6.461 (6.461) Lt: 5.711 (5.711) Accm: 3.42 (3.42) Acct: 5.29 (5.29) proj_loss: -0.5953 (-0.5953) time: 0.9212 data: 0.0003 [11-27 02:38:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 834/1669] eta: 0:27:21 tlr: 0.00013 tnm: 0.28 Lm: 6.425 (6.365) Lt: 5.705 (5.601) Accm: 3.76 (3.68) Acct: 5.99 (5.60) proj_loss: -0.6177 (-0.6027) time: 0.9240 data: 0.0003 [11-27 02:38:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 834/1669] eta: 0:27:19 tlr: 0.00013 tnm: 0.28 Lm: 6.426 (6.405) Lt: 5.665 (5.676) Accm: 3.47 (3.39) Acct: 5.06 (5.13) proj_loss: -0.6404 (-0.6290) time: 0.9240 data: 0.0003 [11-27 02:38:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 834/1669] eta: 0:27:20 tlr: 0.00013 tnm: 0.28 Lm: 6.249 (6.282) Lt: 5.412 (5.404) Accm: 4.31 (4.17) Acct: 7.16 (6.86) proj_loss: -0.6055 (-0.6047) time: 0.9240 data: 0.0003 [11-27 02:38:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 834/1669] eta: 0:27:20 tlr: 0.00013 tnm: 0.28 Lm: 6.407 (6.382) Lt: 5.634 (5.600) Accm: 3.44 (3.52) Acct: 4.99 (5.60) proj_loss: -0.6138 (-0.6115) time: 0.9241 data: 0.0003 [11-27 02:38:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 834/1669] eta: 0:27:20 tlr: 0.00013 tnm: 0.28 Lm: 6.407 (6.386) Lt: 5.646 (5.596) Accm: 3.61 (3.87) Acct: 5.92 (6.37) proj_loss: -0.5976 (-0.6013) time: 0.9240 data: 0.0003 [11-27 02:38:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 834/1669] eta: 0:27:20 tlr: 0.00013 tnm: 0.28 Lm: 6.159 (6.228) Lt: 5.486 (5.461) Accm: 4.12 (4.22) Acct: 6.34 (6.59) proj_loss: -0.6218 (-0.6213) time: 0.9241 data: 0.0003 [11-27 02:38:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 834/1669] eta: 0:27:20 tlr: 0.00013 tnm: 0.28 Lm: 6.381 (6.396) Lt: 5.636 (5.666) Accm: 3.51 (3.47) Acct: 5.48 (5.65) proj_loss: -0.6141 (-0.6179) time: 0.9241 data: 0.0003 [11-27 02:38:23] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [ 834/1669] eta: 0:27:21 tlr: 0.00013 tnm: 0.28 Lm: 6.518 (6.533) Lt: 5.783 (5.806) Accm: 3.45 (3.33) Acct: 5.27 (5.14) proj_loss: -0.6388 (-0.6352) time: 0.9240 data: 0.0003 [11-27 02:44:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [1251/1669] eta: 0:11:16 tlr: 0.00013 tnm: 0.28 Lm: 6.479 (6.493) Lt: 5.770 (5.759) Accm: 3.59 (3.50) Acct: 5.29 (5.36) proj_loss: -0.6425 (-0.6385) time: 0.9290 data: 0.0003 [11-27 02:44:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [1251/1669] eta: 0:11:16 tlr: 0.00013 tnm: 0.28 Lm: 6.263 (6.281) Lt: 5.448 (5.438) Accm: 4.09 (4.09) Acct: 6.68 (6.59) proj_loss: -0.6134 (-0.6101) time: 0.9290 data: 0.0002 [11-27 02:44:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [1251/1669] eta: 0:11:16 tlr: 0.00013 tnm: 0.28 Lm: 6.433 (6.384) Lt: 5.679 (5.614) Accm: 3.50 (3.57) Acct: 5.46 (5.43) proj_loss: -0.6179 (-0.6066) time: 0.9290 data: 0.0003 [11-27 02:44:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [1251/1669] eta: 0:11:16 tlr: 0.00013 tnm: 0.28 Lm: 6.534 (6.456) Lt: 5.776 (5.713) Accm: 3.21 (3.39) Acct: 4.68 (5.29) proj_loss: -0.6133 (-0.6118) time: 0.9290 data: 0.0002 [11-27 02:44:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [1251/1669] eta: 0:11:16 tlr: 0.00013 tnm: 0.28 Lm: 6.427 (6.474) Lt: 5.713 (5.752) Accm: 3.26 (3.27) Acct: 4.94 (5.01) proj_loss: -0.6282 (-0.6257) time: 0.9290 data: 0.0003 [11-27 02:44:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [1251/1669] eta: 0:11:16 tlr: 0.00013 tnm: 0.28 Lm: 6.413 (6.412) Lt: 5.657 (5.669) Accm: 3.52 (3.52) Acct: 5.87 (5.84) proj_loss: -0.6215 (-0.6239) time: 0.9290 data: 0.0002 [11-27 02:44:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [1251/1669] eta: 0:11:16 tlr: 0.00013 tnm: 0.28 Lm: 6.433 (6.409) Lt: 5.661 (5.650) Accm: 3.53 (3.73) Acct: 5.89 (6.03) proj_loss: -0.6043 (-0.6103) time: 0.9290 data: 0.0003 [11-27 02:44:48] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [1251/1669] eta: 0:11:16 tlr: 0.00013 tnm: 0.28 Lm: 6.244 (6.253) Lt: 5.514 (5.482) Accm: 4.12 (4.19) Acct: 6.34 (6.53) proj_loss: -0.6206 (-0.6209) time: 0.9290 data: 0.0003 [11-27 02:51:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [1668/1669] eta: 0:00:01 tlr: 0.00013 tnm: 0.28 Lm: 6.303 (6.263) Lt: 5.492 (5.484) Accm: 4.11 (4.16) Acct: 6.34 (6.58) proj_loss: -0.6218 (-0.6217) time: 0.9285 data: 0.0015 [11-27 02:51:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 180/350] Total time: 0:40:12 (1.445 s / it) [11-27 02:51:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [1668/1669] eta: 0:00:01 tlr: 0.00013 tnm: 0.28 Lm: 6.407 (6.413) Lt: 5.634 (5.657) Accm: 3.44 (3.60) Acct: 4.99 (5.67) proj_loss: -0.6138 (-0.6122) time: 0.9285 data: 0.0016 [11-27 02:51:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [1668/1669] eta: 0:00:01 tlr: 0.00013 tnm: 0.28 Lm: 6.425 (6.353) Lt: 5.653 (5.586) Accm: 3.76 (3.70) Acct: 5.99 (5.67) proj_loss: -0.6181 (-0.6172) time: 0.9285 data: 0.0016 [11-27 02:51:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [1668/1669] eta: 0:00:01 tlr: 0.00013 tnm: 0.28 Lm: 6.249 (6.265) Lt: 5.412 (5.428) Accm: 4.18 (4.11) Acct: 7.16 (6.72) proj_loss: -0.6055 (-0.6047) time: 0.9285 data: 0.0016 [11-27 02:51:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [1668/1669] eta: 0:00:01 tlr: 0.00013 tnm: 0.28 Lm: 6.381 (6.387) Lt: 5.636 (5.652) Accm: 3.53 (3.62) Acct: 6.27 (5.98) proj_loss: -0.6289 (-0.6294) time: 0.9285 data: 0.0020 [11-27 02:51:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [1668/1669] eta: 0:00:01 tlr: 0.00013 tnm: 0.28 Lm: 6.459 (6.427) Lt: 5.676 (5.692) Accm: 3.61 (3.74) Acct: 5.92 (6.09) proj_loss: -0.6109 (-0.6186) time: 0.9285 data: 0.0018 [11-27 02:51:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [1668/1669] eta: 0:00:01 tlr: 0.00013 tnm: 0.28 Lm: 6.426 (6.413) Lt: 5.665 (5.683) Accm: 3.47 (3.48) Acct: 5.06 (5.30) proj_loss: -0.6159 (-0.6226) time: 0.9285 data: 0.0019 [11-27 02:51:15] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 180/350] [1668/1669] eta: 0:00:01 tlr: 0.00013 tnm: 0.28 Lm: 6.482 (6.491) Lt: 5.757 (5.737) Accm: 3.45 (3.43) Acct: 5.27 (5.28) proj_loss: -0.6388 (-0.6371) time: 0.9285 data: 0.0018 [11-27 02:51:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 180/350] Total time: 0:40:12 (1.445 s / it) [11-27 02:51:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 180/350] Total time: 0:40:12 (1.446 s / it) [11-27 02:51:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 180/350] Total time: 0:40:12 (1.445 s / it) [11-27 02:51:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 180/350] Total time: 0:40:12 (1.446 s / it) [11-27 02:51:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 180/350] Total time: 0:40:11 (1.445 s / it) [11-27 02:51:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 180/350] Total time: 0:40:11 (1.445 s / it) [11-27 02:51:15] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 180/350] Total time: 0:40:13 (1.446 s / it) [11-27 02:51:15] (/home/user/VAR/train.py , line 276)=> [ep180] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.650), Acc m&t: 3.62 5.68, Remain: 3 days, 1:18:33, Finish: 2024-11-29 12:09 [11-27 02:51:15] (/home/user/VAR/train.py , line 276)=> [ep180] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.650), Acc m&t: 3.62 5.68, Remain: 3 days, 1:19:11, Finish: 2024-11-29 12:10 [11-27 02:51:15] (/home/user/VAR/train.py , line 276)=> [ep180] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.650), Acc m&t: 3.62 5.68, Remain: 3 days, 1:18:37, Finish: 2024-11-29 12:09 [11-27 02:51:15] (/home/user/VAR/train.py , line 276)=> [ep180] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.650), Acc m&t: 3.62 5.68, Remain: 3 days, 1:17:31, Finish: 2024-11-29 12:08 [11-27 02:51:15] (/home/user/VAR/train.py , line 276)=> [ep180] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.650), Acc m&t: 3.62 5.68, Remain: 3 days, 1:17:55, Finish: 2024-11-29 12:09 [11-27 02:51:15] (/home/user/VAR/train.py , line 276)=> [ep180] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.650), Acc m&t: 3.62 5.68, Remain: 3 days, 1:16:54, Finish: 2024-11-29 12:08 [11-27 02:51:15] (/home/user/VAR/train.py , line 276)=> [ep180] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.650), Acc m&t: 3.62 5.68, Remain: 3 days, 1:17:21, Finish: 2024-11-29 12:08 [11-27 02:51:15] (/home/user/VAR/train.py , line 276)=> [ep180] (training ) Lm: 6.409 (6.409), Lt: 5.650 (5.650), Acc m&t: 3.62 5.68, Remain: 3 days, 1:19:49, Finish: 2024-11-29 12:11 [11-27 02:51:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 0/1669] eta: 0:24:28 tlr: 0.00013 tnm: 0.28 Lm: 6.102 (6.102) Lt: 5.236 (5.236) Accm: 4.71 (4.71) Acct: 7.37 (7.37) proj_loss: -0.6132 (-0.6132) time: 0.8801 data: 0.0003 [11-27 02:51:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 0/1669] eta: 0:24:29 tlr: 0.00013 tnm: 0.28 Lm: 6.448 (6.448) Lt: 5.676 (5.676) Accm: 3.34 (3.34) Acct: 5.48 (5.48) proj_loss: -0.6056 (-0.6056) time: 0.8806 data: 0.0003 [11-27 02:51:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 0/1669] eta: 0:24:40 tlr: 0.00013 tnm: 0.28 Lm: 6.466 (6.466) Lt: 5.766 (5.766) Accm: 3.55 (3.55) Acct: 5.17 (5.17) proj_loss: -0.6058 (-0.6058) time: 0.8868 data: 0.0004 [11-27 02:51:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 0/1669] eta: 0:24:29 tlr: 0.00013 tnm: 0.28 Lm: 6.666 (6.666) Lt: 5.938 (5.938) Accm: 2.72 (2.72) Acct: 4.55 (4.55) proj_loss: -0.6474 (-0.6474) time: 0.8802 data: 0.0003 [11-27 02:51:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 0/1669] eta: 0:24:29 tlr: 0.00013 tnm: 0.28 Lm: 6.317 (6.317) Lt: 5.519 (5.519) Accm: 4.04 (4.04) Acct: 6.44 (6.44) proj_loss: -0.5995 (-0.5995) time: 0.8805 data: 0.0003 [11-27 02:51:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 0/1669] eta: 0:24:29 tlr: 0.00013 tnm: 0.28 Lm: 6.391 (6.391) Lt: 5.652 (5.652) Accm: 3.00 (3.00) Acct: 5.03 (5.03) proj_loss: -0.6243 (-0.6243) time: 0.8803 data: 0.0003 [11-27 02:51:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 0/1669] eta: 0:24:29 tlr: 0.00013 tnm: 0.28 Lm: 6.597 (6.597) Lt: 5.833 (5.833) Accm: 2.81 (2.81) Acct: 4.68 (4.68) proj_loss: -0.6347 (-0.6347) time: 0.8805 data: 0.0004 [11-27 02:51:16] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 0/1669] eta: 0:24:29 tlr: 0.00013 tnm: 0.28 Lm: 6.153 (6.153) Lt: 5.396 (5.396) Accm: 4.71 (4.71) Acct: 7.23 (7.23) proj_loss: -0.6193 (-0.6193) time: 0.8805 data: 0.0005 [11-27 02:57:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 417/1669] eta: 0:19:31 tlr: 0.00013 tnm: 0.29 Lm: 6.218 (6.218) Lt: 5.438 (5.438) Accm: 4.37 (4.37) Acct: 6.89 (6.89) proj_loss: -0.6290 (-0.6290) time: 0.9268 data: 0.0003 [11-27 02:57:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 417/1669] eta: 0:19:31 tlr: 0.00013 tnm: 0.29 Lm: 6.494 (6.494) Lt: 5.723 (5.723) Accm: 3.46 (3.46) Acct: 5.65 (5.65) proj_loss: -0.6045 (-0.6045) time: 0.9268 data: 0.0002 [11-27 02:57:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 417/1669] eta: 0:19:31 tlr: 0.00013 tnm: 0.29 Lm: 6.569 (6.569) Lt: 5.836 (5.836) Accm: 3.10 (3.10) Acct: 5.03 (5.03) proj_loss: -0.6387 (-0.6387) time: 0.9267 data: 0.0003 [11-27 02:57:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 417/1669] eta: 0:19:31 tlr: 0.00013 tnm: 0.29 Lm: 6.479 (6.479) Lt: 5.679 (5.679) Accm: 3.55 (3.55) Acct: 5.42 (5.42) proj_loss: -0.6076 (-0.6076) time: 0.9267 data: 0.0002 [11-27 02:57:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 417/1669] eta: 0:19:31 tlr: 0.00013 tnm: 0.29 Lm: 6.396 (6.396) Lt: 5.703 (5.703) Accm: 2.98 (2.98) Acct: 4.72 (4.72) proj_loss: -0.6361 (-0.6361) time: 0.9268 data: 0.0002 [11-27 02:57:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 417/1669] eta: 0:19:31 tlr: 0.00013 tnm: 0.29 Lm: 6.333 (6.333) Lt: 5.474 (5.474) Accm: 3.93 (3.93) Acct: 6.39 (6.39) proj_loss: -0.6098 (-0.6098) time: 0.9268 data: 0.0002 [11-27 02:57:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 417/1669] eta: 0:19:31 tlr: 0.00013 tnm: 0.29 Lm: 6.249 (6.249) Lt: 5.480 (5.480) Accm: 4.00 (4.00) Acct: 6.23 (6.23) proj_loss: -0.6083 (-0.6083) time: 0.9268 data: 0.0003 [11-27 02:57:46] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 417/1669] eta: 0:19:31 tlr: 0.00013 tnm: 0.29 Lm: 6.435 (6.435) Lt: 5.718 (5.718) Accm: 3.29 (3.29) Acct: 5.20 (5.20) proj_loss: -0.6356 (-0.6356) time: 0.9268 data: 0.0003 [11-27 03:04:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 834/1669] eta: 0:12:58 tlr: 0.00013 tnm: 0.27 Lm: 6.461 (6.444) Lt: 5.726 (5.721) Accm: 3.13 (3.23) Acct: 4.68 (5.03) proj_loss: -0.6347 (-0.6337) time: 0.9268 data: 0.0003 [11-27 03:04:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 834/1669] eta: 0:12:58 tlr: 0.00013 tnm: 0.27 Lm: 6.538 (6.401) Lt: 5.713 (5.600) Accm: 3.15 (3.60) Acct: 5.41 (5.66) proj_loss: -0.6063 (-0.6073) time: 0.9268 data: 0.0003 [11-27 03:04:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 834/1669] eta: 0:12:58 tlr: 0.00013 tnm: 0.27 Lm: 6.401 (6.409) Lt: 5.715 (5.707) Accm: 3.00 (3.06) Acct: 5.03 (4.88) proj_loss: -0.6243 (-0.6263) time: 0.9268 data: 0.0002 [11-27 03:04:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 834/1669] eta: 0:12:58 tlr: 0.00013 tnm: 0.27 Lm: 6.317 (6.309) Lt: 5.519 (5.519) Accm: 3.96 (3.86) Acct: 6.03 (5.90) proj_loss: -0.6087 (-0.6084) time: 0.9268 data: 0.0003 [11-27 03:04:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 834/1669] eta: 0:12:58 tlr: 0.00013 tnm: 0.27 Lm: 6.283 (6.267) Lt: 5.481 (5.491) Accm: 4.04 (4.18) Acct: 6.54 (6.63) proj_loss: -0.6367 (-0.6316) time: 0.9268 data: 0.0003 [11-27 03:04:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 834/1669] eta: 0:12:58 tlr: 0.00013 tnm: 0.27 Lm: 6.491 (6.483) Lt: 5.696 (5.684) Accm: 3.55 (3.49) Acct: 5.65 (5.50) proj_loss: -0.6058 (-0.6030) time: 0.9268 data: 0.0003 [11-27 03:04:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 834/1669] eta: 0:12:58 tlr: 0.00013 tnm: 0.27 Lm: 6.472 (6.515) Lt: 5.734 (5.788) Accm: 3.47 (3.29) Acct: 5.51 (5.21) proj_loss: -0.6300 (-0.6331) time: 0.9268 data: 0.0003 [11-27 03:04:13] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [ 834/1669] eta: 0:12:58 tlr: 0.00013 tnm: 0.27 Lm: 6.481 (6.490) Lt: 5.736 (5.727) Accm: 3.34 (3.38) Acct: 5.48 (5.37) proj_loss: -0.6056 (-0.6106) time: 0.9268 data: 0.0002 [11-27 03:10:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [1251/1669] eta: 0:06:28 tlr: 0.00013 tnm: 0.28 Lm: 6.473 (6.483) Lt: 5.753 (5.746) Accm: 3.29 (3.31) Acct: 5.15 (5.22) proj_loss: -0.6045 (-0.6075) time: 0.9257 data: 0.0002 [11-27 03:10:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [1251/1669] eta: 0:06:28 tlr: 0.00013 tnm: 0.28 Lm: 6.439 (6.460) Lt: 5.713 (5.755) Accm: 3.58 (3.57) Acct: 5.54 (5.58) proj_loss: -0.6318 (-0.6332) time: 0.9257 data: 0.0003 [11-27 03:10:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [1251/1669] eta: 0:06:28 tlr: 0.00013 tnm: 0.28 Lm: 6.479 (6.424) Lt: 5.643 (5.623) Accm: 3.55 (3.68) Acct: 5.66 (5.85) proj_loss: -0.6052 (-0.6034) time: 0.9257 data: 0.0003 [11-27 03:10:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [1251/1669] eta: 0:06:28 tlr: 0.00013 tnm: 0.28 Lm: 6.318 (6.312) Lt: 5.558 (5.546) Accm: 3.77 (3.76) Acct: 5.63 (5.70) proj_loss: -0.6129 (-0.6140) time: 0.9257 data: 0.0002 [11-27 03:10:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [1251/1669] eta: 0:06:28 tlr: 0.00013 tnm: 0.28 Lm: 6.413 (6.424) Lt: 5.665 (5.679) Accm: 3.45 (3.41) Acct: 5.20 (5.41) proj_loss: -0.6323 (-0.6250) time: 0.9257 data: 0.0003 [11-27 03:10:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [1251/1669] eta: 0:06:28 tlr: 0.00013 tnm: 0.28 Lm: 6.532 (6.433) Lt: 5.781 (5.663) Accm: 3.20 (3.51) Acct: 5.18 (5.48) proj_loss: -0.6098 (-0.6091) time: 0.9257 data: 0.0003 [11-27 03:10:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [1251/1669] eta: 0:06:28 tlr: 0.00013 tnm: 0.28 Lm: 6.396 (6.401) Lt: 5.698 (5.700) Accm: 3.12 (3.12) Acct: 4.92 (4.86) proj_loss: -0.6155 (-0.6209) time: 0.9257 data: 0.0002 [11-27 03:10:39] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [1251/1669] eta: 0:06:28 tlr: 0.00013 tnm: 0.28 Lm: 6.325 (6.307) Lt: 5.539 (5.531) Accm: 3.92 (4.04) Acct: 6.34 (6.41) proj_loss: -0.6309 (-0.6300) time: 0.9258 data: 0.0003 [11-27 03:17:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [1668/1669] eta: 0:00:00 tlr: 0.00012 tnm: 0.28 Lm: 6.283 (6.290) Lt: 5.481 (5.510) Accm: 4.04 (4.09) Acct: 6.54 (6.59) proj_loss: -0.6252 (-0.6267) time: 0.9267 data: 0.0019 [11-27 03:17:05] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 181/350] Total time: 0:25:50 (0.929 s / it) [11-27 03:17:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [1668/1669] eta: 0:00:00 tlr: 0.00012 tnm: 0.28 Lm: 6.401 (6.440) Lt: 5.715 (5.719) Accm: 3.23 (3.16) Acct: 5.03 (4.95) proj_loss: -0.6066 (-0.6151) time: 0.9267 data: 0.0018 [11-27 03:17:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [1668/1669] eta: 0:00:00 tlr: 0.00012 tnm: 0.28 Lm: 6.491 (6.442) Lt: 5.696 (5.662) Accm: 3.55 (3.51) Acct: 5.65 (5.55) proj_loss: -0.6058 (-0.6087) time: 0.9267 data: 0.0017 [11-27 03:17:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [1668/1669] eta: 0:00:00 tlr: 0.00012 tnm: 0.28 Lm: 6.526 (6.434) Lt: 5.713 (5.651) Accm: 3.25 (3.55) Acct: 5.41 (5.63) proj_loss: -0.6127 (-0.6098) time: 0.9267 data: 0.0018 [11-27 03:17:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [1668/1669] eta: 0:00:00 tlr: 0.00012 tnm: 0.28 Lm: 6.464 (6.441) Lt: 5.736 (5.695) Accm: 3.34 (3.57) Acct: 5.48 (5.63) proj_loss: -0.6056 (-0.6175) time: 0.9267 data: 0.0015 [11-27 03:17:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [1668/1669] eta: 0:00:00 tlr: 0.00012 tnm: 0.28 Lm: 6.365 (6.371) Lt: 5.603 (5.627) Accm: 3.76 (3.79) Acct: 5.72 (5.96) proj_loss: -0.6347 (-0.6289) time: 0.9267 data: 0.0018 [11-27 03:17:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [1668/1669] eta: 0:00:00 tlr: 0.00012 tnm: 0.28 Lm: 6.318 (6.340) Lt: 5.597 (5.570) Accm: 3.58 (3.68) Acct: 5.23 (5.59) proj_loss: -0.6087 (-0.6102) time: 0.9267 data: 0.0017 [11-27 03:17:05] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 181/350] [1668/1669] eta: 0:00:00 tlr: 0.00012 tnm: 0.28 Lm: 6.405 (6.418) Lt: 5.692 (5.694) Accm: 3.69 (3.69) Acct: 5.58 (5.83) proj_loss: -0.6336 (-0.6378) time: 0.9267 data: 0.0018 [11-27 03:17:05] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 181/350] Total time: 0:25:50 (0.929 s / it) [11-27 03:17:05] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 181/350] Total time: 0:25:50 (0.929 s / it) [11-27 03:17:05] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 181/350] Total time: 0:25:50 (0.929 s / it) [11-27 03:17:05] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 181/350] Total time: 0:25:50 (0.929 s / it) [11-27 03:17:05] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 181/350] Total time: 0:25:50 (0.929 s / it) [11-27 03:17:05] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 181/350] Total time: 0:25:50 (0.929 s / it) [11-27 03:17:05] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 181/350] Total time: 0:25:50 (0.929 s / it) [11-27 03:17:05] (/home/user/VAR/train.py , line 276)=> [ep181] (training ) Lm: 6.406 (6.406), Lt: 5.650 (5.651), Acc m&t: 3.66 5.69, Remain: 3 days, 0:48:46, Finish: 2024-11-29 12:05 [11-27 03:17:05] (/home/user/VAR/train.py , line 276)=> [ep181] (training ) Lm: 6.406 (6.406), Lt: 5.650 (5.651), Acc m&t: 3.66 5.69, Remain: 3 days, 0:49:36, Finish: 2024-11-29 12:06 [11-27 03:17:05] (/home/user/VAR/train.py , line 276)=> [ep181] (training ) Lm: 6.406 (6.406), Lt: 5.650 (5.651), Acc m&t: 3.66 5.69, Remain: 3 days, 0:48:59, Finish: 2024-11-29 12:06 [11-27 03:17:05] (/home/user/VAR/train.py , line 276)=> [ep181] (training ) Lm: 6.406 (6.406), Lt: 5.650 (5.651), Acc m&t: 3.66 5.69, Remain: 3 days, 0:49:46, Finish: 2024-11-29 12:06 [11-27 03:17:05] (/home/user/VAR/train.py , line 276)=> [ep181] (training ) Lm: 6.406 (6.406), Lt: 5.650 (5.651), Acc m&t: 3.66 5.69, Remain: 3 days, 0:48:19, Finish: 2024-11-29 12:05 [11-27 03:17:05] (/home/user/VAR/train.py , line 276)=> [ep181] (training ) Lm: 6.406 (6.406), Lt: 5.650 (5.651), Acc m&t: 3.66 5.69, Remain: 3 days, 0:49:08, Finish: 2024-11-29 12:06 [11-27 03:17:05] (/home/user/VAR/train.py , line 276)=> [ep181] (training ) Lm: 6.406 (6.406), Lt: 5.650 (5.651), Acc m&t: 3.66 5.69, Remain: 3 days, 0:49:44, Finish: 2024-11-29 12:06 [11-27 03:17:05] (/home/user/VAR/train.py , line 276)=> [ep181] (training ) Lm: 6.406 (6.406), Lt: 5.650 (5.651), Acc m&t: 3.66 5.69, Remain: 3 days, 0:49:20, Finish: 2024-11-29 12:06 [11-27 03:17:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 0/1669] eta: 0:25:10 tlr: 0.00012 tnm: 0.29 Lm: 6.265 (6.265) Lt: 5.503 (5.503) Accm: 4.27 (4.27) Acct: 6.82 (6.82) proj_loss: -0.6210 (-0.6210) time: 0.9053 data: 0.0003 [11-27 03:17:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 0/1669] eta: 0:25:11 tlr: 0.00012 tnm: 0.29 Lm: 6.561 (6.561) Lt: 5.811 (5.811) Accm: 3.15 (3.15) Acct: 4.99 (4.99) proj_loss: -0.6518 (-0.6518) time: 0.9059 data: 0.0003 [11-27 03:17:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 0/1669] eta: 0:25:11 tlr: 0.00012 tnm: 0.29 Lm: 6.374 (6.374) Lt: 5.634 (5.634) Accm: 3.73 (3.73) Acct: 5.85 (5.85) proj_loss: -0.6071 (-0.6071) time: 0.9058 data: 0.0003 [11-27 03:17:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 0/1669] eta: 0:25:12 tlr: 0.00012 tnm: 0.29 Lm: 6.524 (6.524) Lt: 5.744 (5.744) Accm: 3.44 (3.44) Acct: 5.44 (5.44) proj_loss: -0.6162 (-0.6162) time: 0.9061 data: 0.0004 [11-27 03:17:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 0/1669] eta: 0:25:11 tlr: 0.00012 tnm: 0.29 Lm: 6.172 (6.172) Lt: 5.414 (5.414) Accm: 4.40 (4.40) Acct: 6.68 (6.68) proj_loss: -0.6149 (-0.6149) time: 0.9059 data: 0.0004 [11-27 03:17:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 0/1669] eta: 0:25:12 tlr: 0.00012 tnm: 0.29 Lm: 6.623 (6.623) Lt: 5.926 (5.926) Accm: 2.88 (2.88) Acct: 4.92 (4.92) proj_loss: -0.6263 (-0.6263) time: 0.9062 data: 0.0003 [11-27 03:17:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 0/1669] eta: 0:25:12 tlr: 0.00012 tnm: 0.29 Lm: 6.282 (6.282) Lt: 5.552 (5.552) Accm: 4.33 (4.33) Acct: 6.27 (6.27) proj_loss: -0.6275 (-0.6275) time: 0.9063 data: 0.0004 [11-27 03:17:06] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 0/1669] eta: 0:25:12 tlr: 0.00012 tnm: 0.29 Lm: 6.251 (6.251) Lt: 5.453 (5.453) Accm: 4.25 (4.25) Acct: 6.58 (6.58) proj_loss: -0.6175 (-0.6175) time: 0.9062 data: 0.0004 [11-27 03:23:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 417/1669] eta: 0:19:18 tlr: 0.00012 tnm: 0.28 Lm: 6.393 (6.393) Lt: 5.673 (5.673) Accm: 3.74 (3.74) Acct: 5.82 (5.82) proj_loss: -0.6116 (-0.6116) time: 0.9242 data: 0.0003 [11-27 03:23:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 417/1669] eta: 0:19:18 tlr: 0.00012 tnm: 0.28 Lm: 6.516 (6.516) Lt: 5.746 (5.746) Accm: 3.29 (3.29) Acct: 5.25 (5.25) proj_loss: -0.5932 (-0.5932) time: 0.9242 data: 0.0002 [11-27 03:23:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 417/1669] eta: 0:19:18 tlr: 0.00012 tnm: 0.28 Lm: 6.656 (6.656) Lt: 5.926 (5.926) Accm: 2.98 (2.98) Acct: 4.60 (4.60) proj_loss: -0.6597 (-0.6597) time: 0.9242 data: 0.0003 [11-27 03:23:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 417/1669] eta: 0:19:18 tlr: 0.00012 tnm: 0.28 Lm: 6.230 (6.230) Lt: 5.440 (5.440) Accm: 4.24 (4.24) Acct: 6.56 (6.56) proj_loss: -0.6078 (-0.6078) time: 0.9242 data: 0.0003 [11-27 03:23:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 417/1669] eta: 0:19:18 tlr: 0.00012 tnm: 0.28 Lm: 6.337 (6.337) Lt: 5.573 (5.573) Accm: 4.03 (4.03) Acct: 6.35 (6.35) proj_loss: -0.6137 (-0.6137) time: 0.9243 data: 0.0002 [11-27 03:23:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 417/1669] eta: 0:19:18 tlr: 0.00012 tnm: 0.28 Lm: 6.390 (6.390) Lt: 5.593 (5.593) Accm: 3.74 (3.74) Acct: 6.01 (6.01) proj_loss: -0.6332 (-0.6332) time: 0.9242 data: 0.0003 [11-27 03:23:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 417/1669] eta: 0:19:18 tlr: 0.00012 tnm: 0.28 Lm: 6.600 (6.600) Lt: 5.920 (5.920) Accm: 3.02 (3.02) Acct: 4.79 (4.79) proj_loss: -0.6216 (-0.6216) time: 0.9243 data: 0.0002 [11-27 03:23:32] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 417/1669] eta: 0:19:18 tlr: 0.00012 tnm: 0.28 Lm: 6.372 (6.372) Lt: 5.583 (5.583) Accm: 3.86 (3.86) Acct: 5.85 (5.85) proj_loss: -0.6207 (-0.6207) time: 0.9243 data: 0.0003 [11-27 03:30:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 834/1669] eta: 0:12:54 tlr: 0.00012 tnm: 0.28 Lm: 6.286 (6.343) Lt: 5.552 (5.566) Accm: 3.88 (3.87) Acct: 5.79 (5.83) proj_loss: -0.6221 (-0.6212) time: 0.9247 data: 0.0003 [11-27 03:30:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 834/1669] eta: 0:12:54 tlr: 0.00012 tnm: 0.28 Lm: 6.408 (6.493) Lt: 5.644 (5.759) Accm: 3.79 (3.53) Acct: 5.89 (5.57) proj_loss: -0.6063 (-0.6103) time: 0.9247 data: 0.0003 [11-27 03:30:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 834/1669] eta: 0:12:54 tlr: 0.00012 tnm: 0.28 Lm: 6.287 (6.279) Lt: 5.466 (5.514) Accm: 4.08 (3.96) Acct: 6.44 (6.07) proj_loss: -0.6149 (-0.6195) time: 0.9247 data: 0.0003 [11-27 03:30:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 834/1669] eta: 0:12:54 tlr: 0.00012 tnm: 0.28 Lm: 6.577 (6.543) Lt: 5.914 (5.839) Accm: 3.16 (3.20) Acct: 4.92 (4.96) proj_loss: -0.6232 (-0.6222) time: 0.9247 data: 0.0003 [11-27 03:30:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 834/1669] eta: 0:12:54 tlr: 0.00012 tnm: 0.28 Lm: 6.374 (6.467) Lt: 5.647 (5.713) Accm: 3.73 (3.55) Acct: 5.85 (5.59) proj_loss: -0.6071 (-0.6077) time: 0.9247 data: 0.0002 [11-27 03:30:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 834/1669] eta: 0:12:54 tlr: 0.00012 tnm: 0.28 Lm: 6.513 (6.431) Lt: 5.716 (5.634) Accm: 3.54 (3.68) Acct: 6.10 (6.04) proj_loss: -0.6169 (-0.6278) time: 0.9247 data: 0.0003 [11-27 03:30:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 834/1669] eta: 0:12:54 tlr: 0.00012 tnm: 0.28 Lm: 6.561 (6.583) Lt: 5.811 (5.867) Accm: 3.15 (3.21) Acct: 4.99 (5.20) proj_loss: -0.6518 (-0.6465) time: 0.9247 data: 0.0003 [11-27 03:30:00] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [ 834/1669] eta: 0:12:54 tlr: 0.00012 tnm: 0.28 Lm: 6.535 (6.453) Lt: 5.769 (5.705) Accm: 3.63 (3.70) Acct: 5.85 (5.83) proj_loss: -0.6108 (-0.6113) time: 0.9247 data: 0.0003 [11-27 03:36:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [1251/1669] eta: 0:06:28 tlr: 0.00012 tnm: 0.28 Lm: 6.490 (6.451) Lt: 5.719 (5.696) Accm: 3.79 (3.76) Acct: 5.91 (5.86) proj_loss: -0.6141 (-0.6144) time: 0.9266 data: 0.0003 [11-27 03:36:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [1251/1669] eta: 0:06:28 tlr: 0.00012 tnm: 0.28 Lm: 6.498 (6.522) Lt: 5.780 (5.794) Accm: 3.42 (3.47) Acct: 5.70 (5.52) proj_loss: -0.6359 (-0.6365) time: 0.9266 data: 0.0005 [11-27 03:36:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [1251/1669] eta: 0:06:28 tlr: 0.00012 tnm: 0.28 Lm: 6.372 (6.431) Lt: 5.640 (5.682) Accm: 3.89 (3.68) Acct: 6.06 (5.80) proj_loss: -0.6220 (-0.6173) time: 0.9266 data: 0.0002 [11-27 03:36:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [1251/1669] eta: 0:06:28 tlr: 0.00012 tnm: 0.28 Lm: 6.451 (6.493) Lt: 5.678 (5.747) Accm: 3.32 (3.36) Acct: 5.23 (5.32) proj_loss: -0.6050 (-0.6073) time: 0.9266 data: 0.0003 [11-27 03:36:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [1251/1669] eta: 0:06:28 tlr: 0.00012 tnm: 0.28 Lm: 6.503 (6.504) Lt: 5.796 (5.787) Accm: 3.35 (3.33) Acct: 5.11 (5.16) proj_loss: -0.6201 (-0.6199) time: 0.9266 data: 0.0002 [11-27 03:36:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [1251/1669] eta: 0:06:28 tlr: 0.00012 tnm: 0.28 Lm: 6.385 (6.383) Lt: 5.579 (5.576) Accm: 3.80 (3.80) Acct: 6.34 (6.26) proj_loss: -0.6166 (-0.6243) time: 0.9265 data: 0.0003 [11-27 03:36:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [1251/1669] eta: 0:06:28 tlr: 0.00012 tnm: 0.28 Lm: 6.374 (6.413) Lt: 5.583 (5.667) Accm: 3.63 (3.62) Acct: 5.61 (5.37) proj_loss: -0.6248 (-0.6238) time: 0.9266 data: 0.0003 [11-27 03:36:28] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [1251/1669] eta: 0:06:28 tlr: 0.00012 tnm: 0.28 Lm: 6.284 (6.280) Lt: 5.451 (5.494) Accm: 3.97 (3.93) Acct: 6.32 (6.10) proj_loss: -0.6148 (-0.6183) time: 0.9266 data: 0.0003 [11-27 03:42:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [1668/1669] eta: 0:00:00 tlr: 0.00012 tnm: 0.28 Lm: 6.287 (6.313) Lt: 5.466 (5.552) Accm: 3.86 (3.76) Acct: 6.20 (5.78) proj_loss: -0.6149 (-0.6192) time: 0.9268 data: 0.0017 [11-27 03:42:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 182/350] Total time: 0:25:49 (0.928 s / it) [11-27 03:42:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [1668/1669] eta: 0:00:00 tlr: 0.00012 tnm: 0.28 Lm: 6.430 (6.428) Lt: 5.678 (5.689) Accm: 3.54 (3.55) Acct: 5.30 (5.60) proj_loss: -0.6170 (-0.6170) time: 0.9268 data: 0.0016 [11-27 03:42:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [1668/1669] eta: 0:00:00 tlr: 0.00012 tnm: 0.28 Lm: 6.374 (6.425) Lt: 5.634 (5.663) Accm: 3.73 (3.68) Acct: 5.85 (5.76) proj_loss: -0.6357 (-0.6209) time: 0.9268 data: 0.0015 [11-27 03:42:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [1668/1669] eta: 0:00:00 tlr: 0.00012 tnm: 0.28 Lm: 6.513 (6.418) Lt: 5.716 (5.610) Accm: 3.54 (3.71) Acct: 6.10 (6.06) proj_loss: -0.6169 (-0.6275) time: 0.9268 data: 0.0016 [11-27 03:42:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [1668/1669] eta: 0:00:00 tlr: 0.00012 tnm: 0.28 Lm: 6.534 (6.525) Lt: 5.791 (5.794) Accm: 3.15 (3.37) Acct: 4.99 (5.32) proj_loss: -0.6331 (-0.6358) time: 0.9268 data: 0.0015 [11-27 03:42:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [1668/1669] eta: 0:00:00 tlr: 0.00012 tnm: 0.28 Lm: 6.408 (6.471) Lt: 5.644 (5.696) Accm: 3.79 (3.47) Acct: 5.89 (5.49) proj_loss: -0.6063 (-0.6097) time: 0.9269 data: 0.0018 [11-27 03:42:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [1668/1669] eta: 0:00:00 tlr: 0.00012 tnm: 0.28 Lm: 6.461 (6.431) Lt: 5.615 (5.703) Accm: 3.39 (3.52) Acct: 5.44 (5.25) proj_loss: -0.6275 (-0.6268) time: 0.9269 data: 0.0017 [11-27 03:42:54] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 182/350] [1668/1669] eta: 0:00:00 tlr: 0.00012 tnm: 0.28 Lm: 6.444 (6.439) Lt: 5.668 (5.671) Accm: 3.80 (3.77) Acct: 5.96 (5.99) proj_loss: -0.6117 (-0.6138) time: 0.9268 data: 0.0015 [11-27 03:42:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 182/350] Total time: 0:25:49 (0.928 s / it) [11-27 03:42:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 182/350] Total time: 0:25:49 (0.928 s / it) [11-27 03:42:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 182/350] Total time: 0:25:49 (0.928 s / it) [11-27 03:42:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 182/350] Total time: 0:25:49 (0.928 s / it) [11-27 03:42:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 182/350] Total time: 0:25:49 (0.928 s / it) [11-27 03:42:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 182/350] Total time: 0:25:49 (0.928 s / it) [11-27 03:42:54] (e/user/VAR/utils/misc.py, line 336)=> [Ep]: [ 182/350] Total time: 0:25:49 (0.928 s / it) [11-27 03:42:54] (/home/user/VAR/train.py , line 276)=> [ep182] (training ) Lm: 6.406 (6.413), Lt: 5.650 (5.659), Acc m&t: 3.66 5.69, Remain: 3 days, 0:14:12, Finish: 2024-11-29 11:57 [11-27 03:42:54] (/home/user/VAR/train.py , line 276)=> [ep182] (training ) Lm: 6.406 (6.413), Lt: 5.650 (5.659), Acc m&t: 3.66 5.69, Remain: 3 days, 0:14:15, Finish: 2024-11-29 11:57 [11-27 03:42:54] (/home/user/VAR/train.py , line 276)=> [ep182] (training ) Lm: 6.406 (6.413), Lt: 5.650 (5.659), Acc m&t: 3.66 5.69, Remain: 3 days, 0:14:03, Finish: 2024-11-29 11:56 [11-27 03:42:54] (/home/user/VAR/train.py , line 276)=> [ep182] (training ) Lm: 6.406 (6.413), Lt: 5.650 (5.659), Acc m&t: 3.66 5.69, Remain: 3 days, 0:14:53, Finish: 2024-11-29 11:57 [11-27 03:42:54] (/home/user/VAR/train.py , line 276)=> [ep182] (training ) Lm: 6.406 (6.413), Lt: 5.650 (5.659), Acc m&t: 3.66 5.69, Remain: 3 days, 0:14:01, Finish: 2024-11-29 11:56 [11-27 03:42:54] (/home/user/VAR/train.py , line 276)=> [ep182] (training ) Lm: 6.406 (6.413), Lt: 5.650 (5.659), Acc m&t: 3.66 5.69, Remain: 3 days, 0:14:21, Finish: 2024-11-29 11:57 [11-27 03:42:54] (/home/user/VAR/train.py , line 276)=> [ep182] (training ) Lm: 6.406 (6.413), Lt: 5.650 (5.659), Acc m&t: 3.66 5.69, Remain: 3 days, 0:13:40, Finish: 2024-11-29 11:56 [11-27 03:42:54] (/home/user/VAR/train.py , line 276)=> [ep182] (training ) Lm: 6.406 (6.413), Lt: 5.650 (5.659), Acc m&t: 3.66 5.69, Remain: 3 days, 0:13:50, Finish: 2024-11-29 11:56 [11-27 03:42:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 0/1669] eta: 0:25:20 tlr: 0.00012 tnm: 0.28 Lm: 6.497 (6.497) Lt: 5.688 (5.688) Accm: 3.44 (3.44) Acct: 5.23 (5.23) proj_loss: -0.6219 (-0.6219) time: 0.9112 data: 0.0003 [11-27 03:42:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 0/1669] eta: 0:25:21 tlr: 0.00012 tnm: 0.28 Lm: 6.195 (6.195) Lt: 5.417 (5.417) Accm: 4.20 (4.20) Acct: 6.16 (6.16) proj_loss: -0.6140 (-0.6140) time: 0.9117 data: 0.0003 [11-27 03:42:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 0/1669] eta: 0:25:21 tlr: 0.00012 tnm: 0.28 Lm: 6.406 (6.406) Lt: 5.652 (5.652) Accm: 3.72 (3.72) Acct: 5.51 (5.51) proj_loss: -0.6457 (-0.6457) time: 0.9119 data: 0.0004 [11-27 03:42:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 0/1669] eta: 0:25:21 tlr: 0.00012 tnm: 0.28 Lm: 6.625 (6.625) Lt: 5.915 (5.915) Accm: 2.78 (2.78) Acct: 4.61 (4.61) proj_loss: -0.5967 (-0.5967) time: 0.9119 data: 0.0003 [11-27 03:42:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 0/1669] eta: 0:25:22 tlr: 0.00012 tnm: 0.28 Lm: 6.586 (6.586) Lt: 5.809 (5.809) Accm: 3.82 (3.82) Acct: 6.03 (6.03) proj_loss: -0.6455 (-0.6455) time: 0.9120 data: 0.0004 [11-27 03:42:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 0/1669] eta: 0:25:22 tlr: 0.00012 tnm: 0.28 Lm: 6.409 (6.409) Lt: 5.680 (5.680) Accm: 3.60 (3.60) Acct: 5.41 (5.41) proj_loss: -0.6136 (-0.6136) time: 0.9123 data: 0.0003 [11-27 03:42:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 0/1669] eta: 0:25:22 tlr: 0.00012 tnm: 0.28 Lm: 6.150 (6.150) Lt: 5.452 (5.452) Accm: 4.63 (4.63) Acct: 6.82 (6.82) proj_loss: -0.6362 (-0.6362) time: 0.9121 data: 0.0003 [11-27 03:42:55] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 0/1669] eta: 0:25:22 tlr: 0.00012 tnm: 0.28 Lm: 6.394 (6.394) Lt: 5.610 (5.610) Accm: 3.79 (3.79) Acct: 5.85 (5.85) proj_loss: -0.5989 (-0.5989) time: 0.9122 data: 0.0003 [11-27 03:49:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 417/1669] eta: 0:19:18 tlr: 0.00012 tnm: 0.28 Lm: 6.437 (6.437) Lt: 5.704 (5.704) Accm: 3.39 (3.39) Acct: 5.18 (5.18) proj_loss: -0.6244 (-0.6244) time: 0.9263 data: 0.0003 [11-27 03:49:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 417/1669] eta: 0:19:18 tlr: 0.00012 tnm: 0.28 Lm: 6.464 (6.464) Lt: 5.733 (5.733) Accm: 3.45 (3.45) Acct: 4.96 (4.96) proj_loss: -0.6257 (-0.6257) time: 0.9263 data: 0.0003 [11-27 03:49:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 417/1669] eta: 0:19:18 tlr: 0.00012 tnm: 0.28 Lm: 6.577 (6.577) Lt: 5.870 (5.870) Accm: 2.92 (2.92) Acct: 4.65 (4.65) proj_loss: -0.5980 (-0.5980) time: 0.9263 data: 0.0003 [11-27 03:49:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 417/1669] eta: 0:19:18 tlr: 0.00012 tnm: 0.28 Lm: 6.316 (6.316) Lt: 5.595 (5.595) Accm: 3.90 (3.90) Acct: 5.89 (5.89) proj_loss: -0.6289 (-0.6289) time: 0.9263 data: 0.0002 [11-27 03:49:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 417/1669] eta: 0:19:18 tlr: 0.00012 tnm: 0.28 Lm: 6.365 (6.365) Lt: 5.628 (5.628) Accm: 3.73 (3.73) Acct: 5.61 (5.61) proj_loss: -0.6310 (-0.6310) time: 0.9263 data: 0.0002 [11-27 03:49:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 417/1669] eta: 0:19:18 tlr: 0.00012 tnm: 0.28 Lm: 6.490 (6.490) Lt: 5.768 (5.768) Accm: 3.22 (3.22) Acct: 4.94 (4.94) proj_loss: -0.6126 (-0.6126) time: 0.9263 data: 0.0003 [11-27 03:49:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 417/1669] eta: 0:19:18 tlr: 0.00012 tnm: 0.28 Lm: 6.450 (6.450) Lt: 5.710 (5.710) Accm: 4.14 (4.14) Acct: 6.39 (6.39) proj_loss: -0.6467 (-0.6467) time: 0.9263 data: 0.0003 [11-27 03:49:21] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 417/1669] eta: 0:19:18 tlr: 0.00012 tnm: 0.28 Lm: 6.367 (6.367) Lt: 5.624 (5.624) Accm: 3.74 (3.74) Acct: 5.51 (5.51) proj_loss: -0.6374 (-0.6374) time: 0.9263 data: 0.0003 [11-27 03:55:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 834/1669] eta: 0:12:52 tlr: 0.00012 tnm: 0.29 Lm: 6.384 (6.372) Lt: 5.652 (5.650) Accm: 3.72 (3.69) Acct: 5.51 (5.46) proj_loss: -0.6457 (-0.6412) time: 0.9240 data: 0.0003 [11-27 03:55:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 834/1669] eta: 0:12:52 tlr: 0.00012 tnm: 0.29 Lm: 6.431 (6.426) Lt: 5.688 (5.682) Accm: 3.45 (3.49) Acct: 5.23 (5.13) proj_loss: -0.6219 (-0.6201) time: 0.9240 data: 0.0003 [11-27 03:55:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 834/1669] eta: 0:12:52 tlr: 0.00012 tnm: 0.29 Lm: 6.529 (6.470) Lt: 5.825 (5.730) Accm: 3.06 (3.27) Acct: 4.68 (5.15) proj_loss: -0.5992 (-0.6015) time: 0.9240 data: 0.0002 [11-27 03:55:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 834/1669] eta: 0:12:52 tlr: 0.00012 tnm: 0.29 Lm: 6.483 (6.411) Lt: 5.738 (5.697) Accm: 3.16 (3.63) Acct: 4.96 (5.53) proj_loss: -0.6265 (-0.6281) time: 0.9240 data: 0.0002 [11-27 03:55:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 834/1669] eta: 0:12:52 tlr: 0.00012 tnm: 0.29 Lm: 6.355 (6.418) Lt: 5.610 (5.661) Accm: 3.82 (4.02) Acct: 6.13 (6.30) proj_loss: -0.6455 (-0.6336) time: 0.9240 data: 0.0003 [11-27 03:55:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 834/1669] eta: 0:12:52 tlr: 0.00012 tnm: 0.29 Lm: 6.535 (6.436) Lt: 5.819 (5.691) Accm: 3.26 (3.46) Acct: 5.06 (5.26) proj_loss: -0.6140 (-0.6178) time: 0.9240 data: 0.0002 [11-27 03:55:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 834/1669] eta: 0:12:52 tlr: 0.00012 tnm: 0.29 Lm: 6.424 (6.468) Lt: 5.680 (5.734) Accm: 3.16 (3.20) Acct: 4.89 (4.92) proj_loss: -0.6136 (-0.6147) time: 0.9240 data: 0.0003 [11-27 03:55:47] (e/user/VAR/utils/misc.py, line 314)=> [Ep]: [ 183/350] [ 834/1669] eta: 0:12:52 tlr: 0.00012 tnm: 0.29 Lm: 6.480 (6.482) Lt: 5.795 (5.734) Accm: 3.26 (3.35) Acct: 5.44 (5.27) proj_loss: -0.6083 (-0.6191) time: 0.9240 data: 0.0003