2025-04-25 00:58:05,568 INFO [train.py:653] { "allowed_excess_duration_ratio": 0.1, "audio_key": "question_audio", "batch_idx_train": 0, "best_train_epoch": -1, "best_train_loss": Infinity, "best_valid_epoch": -1, "best_valid_loss": Infinity, "bucketing_sampler": true, "deepscale": false, "deepscale_config": null, "deepspeed": true, "deepspeed_config": "./slam_omni/ds_config_zero1.json", "drop_last": true, "enable_musan": false, "enable_spec_aug": true, "enable_speech_output": true, "encoder_projector_ds_rate": 8, "env_info": { "IP address": "0.114.183.253", "hostname": "7518205", "icefall-git-branch": null, "icefall-git-date": null, "icefall-git-sha1": null, "icefall-path": "/workspace/slam/icefall_omni", "k2-build-type": "Release", "k2-git-date": "Tue Oct 29 09:02:19 2024", "k2-git-sha1": "75e2ed6b2fd87c22b7f3f34bad48a69984bb8755", "k2-path": "/opt/conda/lib/python3.11/site-packages/k2/__init__.py", "k2-version": "1.24.4", "k2-with-cuda": true, "lhotse-path": "/workspace/slam/lhotse/lhotse/__init__.py", "lhotse-version": "1.30.0.dev+git.13c7616f.dirty", "python-version": "3.11", "torch-cuda-available": true, "torch-cuda-version": "12.4", "torch-version": "2.4.0" }, "exp_dir": "slam_omni/exp_speech2speech_rerun", "frame_shift_ms": 10, "huggingface_dataset_path_or_name": "/workspace/Belle_1.4M-SLAM-Omni", "input_strategy": "PrecomputedFeatures", "llm_path_or_name": "models/Qwen2.5-0.5B-Instruct", "log_interval": 50, "manifest_dir": "data/fbank", "max_duration": 50, "num_buckets": 30, "num_epochs": 10, "num_workers": 2, "on_the_fly_feats": false, "pretrained_model_path": "./slam_omni/exp_speech2speech_rerun/epoch-1-checkpoint-15000.pt/pytorch_model.bin", "resample_to_16kHz": true, "reset_interval": 200, "return_cuts": true, "sampler_state_dict_path": "./slam_omni/exp_speech2speech_rerun/epoch-1-checkpoint-15000-sampler.pt", "seed": 42, "shuffle": true, "spec_aug_time_warp_factor": 80, "speech_encoder_path_or_name": "models/whisper/v1.1/whisper-large-v2-multi-hans-zh-epoch-3-avg-10.pt", "start_epoch": 1, "subsampling_factor": 2, "tensorboard": true, "text_key": "answer", "unfreeze_llm": true, "unfreeze_speech_projector": true, "use_flash_attn": true, "use_fp16": true, "use_lora": true, "valid_interval": 5000 } 2025-04-25 00:58:05,569 INFO [train.py:655] About to create model 2025-04-25 00:58:25,413 INFO [train.py:808] Number of model parameters: 1314396804 2025-04-25 00:58:25,413 INFO [train.py:810] Trainable parameters (excluding model.eval modules): 2025-04-25 00:58:25,414 INFO [train.py:813] llm.base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,414 INFO [train.py:813] llm.base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,414 INFO [train.py:813] llm.base_model.model.model.layers.0.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,414 INFO [train.py:813] llm.base_model.model.model.layers.0.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,414 INFO [train.py:813] llm.base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,415 INFO [train.py:813] llm.base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,415 INFO [train.py:813] llm.base_model.model.model.layers.0.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,415 INFO [train.py:813] llm.base_model.model.model.layers.0.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,415 INFO [train.py:813] llm.base_model.model.model.layers.0.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,415 INFO [train.py:813] llm.base_model.model.model.layers.0.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,415 INFO [train.py:813] llm.base_model.model.model.layers.0.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,415 INFO [train.py:813] llm.base_model.model.model.layers.0.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,415 INFO [train.py:813] llm.base_model.model.model.layers.0.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,415 INFO [train.py:813] llm.base_model.model.model.layers.0.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,415 INFO [train.py:813] llm.base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,415 INFO [train.py:813] llm.base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,415 INFO [train.py:813] llm.base_model.model.model.layers.1.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,415 INFO [train.py:813] llm.base_model.model.model.layers.1.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,415 INFO [train.py:813] llm.base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,415 INFO [train.py:813] llm.base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,415 INFO [train.py:813] llm.base_model.model.model.layers.1.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,415 INFO [train.py:813] llm.base_model.model.model.layers.1.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,415 INFO [train.py:813] llm.base_model.model.model.layers.1.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,415 INFO [train.py:813] llm.base_model.model.model.layers.1.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,415 INFO [train.py:813] llm.base_model.model.model.layers.1.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,416 INFO [train.py:813] llm.base_model.model.model.layers.1.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,416 INFO [train.py:813] llm.base_model.model.model.layers.1.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,416 INFO [train.py:813] llm.base_model.model.model.layers.1.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,416 INFO [train.py:813] llm.base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,416 INFO [train.py:813] llm.base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,416 INFO [train.py:813] llm.base_model.model.model.layers.2.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,416 INFO [train.py:813] llm.base_model.model.model.layers.2.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,416 INFO [train.py:813] llm.base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,416 INFO [train.py:813] llm.base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,416 INFO [train.py:813] llm.base_model.model.model.layers.2.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,416 INFO [train.py:813] llm.base_model.model.model.layers.2.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,416 INFO [train.py:813] llm.base_model.model.model.layers.2.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,416 INFO [train.py:813] llm.base_model.model.model.layers.2.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,416 INFO [train.py:813] llm.base_model.model.model.layers.2.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,416 INFO [train.py:813] llm.base_model.model.model.layers.2.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,416 INFO [train.py:813] llm.base_model.model.model.layers.2.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,416 INFO [train.py:813] llm.base_model.model.model.layers.2.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,416 INFO [train.py:813] llm.base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,416 INFO [train.py:813] llm.base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,416 INFO [train.py:813] llm.base_model.model.model.layers.3.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,416 INFO [train.py:813] llm.base_model.model.model.layers.3.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,417 INFO [train.py:813] llm.base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,417 INFO [train.py:813] llm.base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,417 INFO [train.py:813] llm.base_model.model.model.layers.3.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,417 INFO [train.py:813] llm.base_model.model.model.layers.3.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,417 INFO [train.py:813] llm.base_model.model.model.layers.3.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,417 INFO [train.py:813] llm.base_model.model.model.layers.3.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,417 INFO [train.py:813] llm.base_model.model.model.layers.3.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,417 INFO [train.py:813] llm.base_model.model.model.layers.3.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,417 INFO [train.py:813] llm.base_model.model.model.layers.3.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,417 INFO [train.py:813] llm.base_model.model.model.layers.3.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,417 INFO [train.py:813] llm.base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,417 INFO [train.py:813] llm.base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,417 INFO [train.py:813] llm.base_model.model.model.layers.4.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,417 INFO [train.py:813] llm.base_model.model.model.layers.4.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,417 INFO [train.py:813] llm.base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,417 INFO [train.py:813] llm.base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,417 INFO [train.py:813] llm.base_model.model.model.layers.4.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,417 INFO [train.py:813] llm.base_model.model.model.layers.4.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,417 INFO [train.py:813] llm.base_model.model.model.layers.4.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,417 INFO [train.py:813] llm.base_model.model.model.layers.4.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,417 INFO [train.py:813] llm.base_model.model.model.layers.4.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,417 INFO [train.py:813] llm.base_model.model.model.layers.4.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,418 INFO [train.py:813] llm.base_model.model.model.layers.4.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,418 INFO [train.py:813] llm.base_model.model.model.layers.4.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,418 INFO [train.py:813] llm.base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,418 INFO [train.py:813] llm.base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,418 INFO [train.py:813] llm.base_model.model.model.layers.5.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,418 INFO [train.py:813] llm.base_model.model.model.layers.5.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,418 INFO [train.py:813] llm.base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,418 INFO [train.py:813] llm.base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,418 INFO [train.py:813] llm.base_model.model.model.layers.5.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,418 INFO [train.py:813] llm.base_model.model.model.layers.5.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,418 INFO [train.py:813] llm.base_model.model.model.layers.5.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,418 INFO [train.py:813] llm.base_model.model.model.layers.5.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,418 INFO [train.py:813] llm.base_model.model.model.layers.5.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,418 INFO [train.py:813] llm.base_model.model.model.layers.5.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,418 INFO [train.py:813] llm.base_model.model.model.layers.5.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,418 INFO [train.py:813] llm.base_model.model.model.layers.5.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,418 INFO [train.py:813] llm.base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,418 INFO [train.py:813] llm.base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,418 INFO [train.py:813] llm.base_model.model.model.layers.6.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,418 INFO [train.py:813] llm.base_model.model.model.layers.6.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,418 INFO [train.py:813] llm.base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,419 INFO [train.py:813] llm.base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,419 INFO [train.py:813] llm.base_model.model.model.layers.6.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,419 INFO [train.py:813] llm.base_model.model.model.layers.6.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,419 INFO [train.py:813] llm.base_model.model.model.layers.6.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,419 INFO [train.py:813] llm.base_model.model.model.layers.6.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,419 INFO [train.py:813] llm.base_model.model.model.layers.6.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,419 INFO [train.py:813] llm.base_model.model.model.layers.6.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,419 INFO [train.py:813] llm.base_model.model.model.layers.6.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,419 INFO [train.py:813] llm.base_model.model.model.layers.6.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,419 INFO [train.py:813] llm.base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,419 INFO [train.py:813] llm.base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,419 INFO [train.py:813] llm.base_model.model.model.layers.7.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,419 INFO [train.py:813] llm.base_model.model.model.layers.7.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,419 INFO [train.py:813] llm.base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,419 INFO [train.py:813] llm.base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,419 INFO [train.py:813] llm.base_model.model.model.layers.7.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,419 INFO [train.py:813] llm.base_model.model.model.layers.7.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,419 INFO [train.py:813] llm.base_model.model.model.layers.7.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,419 INFO [train.py:813] llm.base_model.model.model.layers.7.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,419 INFO [train.py:813] llm.base_model.model.model.layers.7.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,420 INFO [train.py:813] llm.base_model.model.model.layers.7.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,420 INFO [train.py:813] llm.base_model.model.model.layers.7.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,420 INFO [train.py:813] llm.base_model.model.model.layers.7.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,420 INFO [train.py:813] llm.base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,420 INFO [train.py:813] llm.base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,420 INFO [train.py:813] llm.base_model.model.model.layers.8.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,420 INFO [train.py:813] llm.base_model.model.model.layers.8.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,420 INFO [train.py:813] llm.base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,420 INFO [train.py:813] llm.base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,420 INFO [train.py:813] llm.base_model.model.model.layers.8.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,420 INFO [train.py:813] llm.base_model.model.model.layers.8.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,420 INFO [train.py:813] llm.base_model.model.model.layers.8.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,420 INFO [train.py:813] llm.base_model.model.model.layers.8.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,420 INFO [train.py:813] llm.base_model.model.model.layers.8.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,420 INFO [train.py:813] llm.base_model.model.model.layers.8.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,420 INFO [train.py:813] llm.base_model.model.model.layers.8.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,420 INFO [train.py:813] llm.base_model.model.model.layers.8.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,420 INFO [train.py:813] llm.base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,420 INFO [train.py:813] llm.base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,420 INFO [train.py:813] llm.base_model.model.model.layers.9.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,420 INFO [train.py:813] llm.base_model.model.model.layers.9.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,420 INFO [train.py:813] llm.base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,421 INFO [train.py:813] llm.base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,421 INFO [train.py:813] llm.base_model.model.model.layers.9.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,421 INFO [train.py:813] llm.base_model.model.model.layers.9.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,421 INFO [train.py:813] llm.base_model.model.model.layers.9.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,421 INFO [train.py:813] llm.base_model.model.model.layers.9.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,421 INFO [train.py:813] llm.base_model.model.model.layers.9.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,421 INFO [train.py:813] llm.base_model.model.model.layers.9.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,421 INFO [train.py:813] llm.base_model.model.model.layers.9.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,421 INFO [train.py:813] llm.base_model.model.model.layers.9.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,421 INFO [train.py:813] llm.base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,421 INFO [train.py:813] llm.base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,421 INFO [train.py:813] llm.base_model.model.model.layers.10.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,421 INFO [train.py:813] llm.base_model.model.model.layers.10.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,421 INFO [train.py:813] llm.base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,421 INFO [train.py:813] llm.base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,421 INFO [train.py:813] llm.base_model.model.model.layers.10.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,421 INFO [train.py:813] llm.base_model.model.model.layers.10.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,421 INFO [train.py:813] llm.base_model.model.model.layers.10.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,421 INFO [train.py:813] llm.base_model.model.model.layers.10.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,421 INFO [train.py:813] llm.base_model.model.model.layers.10.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,421 INFO [train.py:813] llm.base_model.model.model.layers.10.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,422 INFO [train.py:813] llm.base_model.model.model.layers.10.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,422 INFO [train.py:813] llm.base_model.model.model.layers.10.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,422 INFO [train.py:813] llm.base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,422 INFO [train.py:813] llm.base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,422 INFO [train.py:813] llm.base_model.model.model.layers.11.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,422 INFO [train.py:813] llm.base_model.model.model.layers.11.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,422 INFO [train.py:813] llm.base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,422 INFO [train.py:813] llm.base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,422 INFO [train.py:813] llm.base_model.model.model.layers.11.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,422 INFO [train.py:813] llm.base_model.model.model.layers.11.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,422 INFO [train.py:813] llm.base_model.model.model.layers.11.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,422 INFO [train.py:813] llm.base_model.model.model.layers.11.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,422 INFO [train.py:813] llm.base_model.model.model.layers.11.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,422 INFO [train.py:813] llm.base_model.model.model.layers.11.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,422 INFO [train.py:813] llm.base_model.model.model.layers.11.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,422 INFO [train.py:813] llm.base_model.model.model.layers.11.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,422 INFO [train.py:813] llm.base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,422 INFO [train.py:813] llm.base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,422 INFO [train.py:813] llm.base_model.model.model.layers.12.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,423 INFO [train.py:813] llm.base_model.model.model.layers.12.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,423 INFO [train.py:813] llm.base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,423 INFO [train.py:813] llm.base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,423 INFO [train.py:813] llm.base_model.model.model.layers.12.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,423 INFO [train.py:813] llm.base_model.model.model.layers.12.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,423 INFO [train.py:813] llm.base_model.model.model.layers.12.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,423 INFO [train.py:813] llm.base_model.model.model.layers.12.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,423 INFO [train.py:813] llm.base_model.model.model.layers.12.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,423 INFO [train.py:813] llm.base_model.model.model.layers.12.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,423 INFO [train.py:813] llm.base_model.model.model.layers.12.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,423 INFO [train.py:813] llm.base_model.model.model.layers.12.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,423 INFO [train.py:813] llm.base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,423 INFO [train.py:813] llm.base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,423 INFO [train.py:813] llm.base_model.model.model.layers.13.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,423 INFO [train.py:813] llm.base_model.model.model.layers.13.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,423 INFO [train.py:813] llm.base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,423 INFO [train.py:813] llm.base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,423 INFO [train.py:813] llm.base_model.model.model.layers.13.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,423 INFO [train.py:813] llm.base_model.model.model.layers.13.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,424 INFO [train.py:813] llm.base_model.model.model.layers.13.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,424 INFO [train.py:813] llm.base_model.model.model.layers.13.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,424 INFO [train.py:813] llm.base_model.model.model.layers.13.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,424 INFO [train.py:813] llm.base_model.model.model.layers.13.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,424 INFO [train.py:813] llm.base_model.model.model.layers.13.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,424 INFO [train.py:813] llm.base_model.model.model.layers.13.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,424 INFO [train.py:813] llm.base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,424 INFO [train.py:813] llm.base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,424 INFO [train.py:813] llm.base_model.model.model.layers.14.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,424 INFO [train.py:813] llm.base_model.model.model.layers.14.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,424 INFO [train.py:813] llm.base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,424 INFO [train.py:813] llm.base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,424 INFO [train.py:813] llm.base_model.model.model.layers.14.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,424 INFO [train.py:813] llm.base_model.model.model.layers.14.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,424 INFO [train.py:813] llm.base_model.model.model.layers.14.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,424 INFO [train.py:813] llm.base_model.model.model.layers.14.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,424 INFO [train.py:813] llm.base_model.model.model.layers.14.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,424 INFO [train.py:813] llm.base_model.model.model.layers.14.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,424 INFO [train.py:813] llm.base_model.model.model.layers.14.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,424 INFO [train.py:813] llm.base_model.model.model.layers.14.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,424 INFO [train.py:813] llm.base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,424 INFO [train.py:813] llm.base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.15.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.15.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.15.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.15.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.15.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.15.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.15.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.15.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.15.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.15.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.16.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.16.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.16.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.16.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.16.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.16.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,425 INFO [train.py:813] llm.base_model.model.model.layers.16.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,426 INFO [train.py:813] llm.base_model.model.model.layers.16.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,426 INFO [train.py:813] llm.base_model.model.model.layers.16.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,426 INFO [train.py:813] llm.base_model.model.model.layers.16.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,426 INFO [train.py:813] llm.base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,426 INFO [train.py:813] llm.base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,426 INFO [train.py:813] llm.base_model.model.model.layers.17.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,426 INFO [train.py:813] llm.base_model.model.model.layers.17.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,426 INFO [train.py:813] llm.base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,426 INFO [train.py:813] llm.base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,426 INFO [train.py:813] llm.base_model.model.model.layers.17.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,426 INFO [train.py:813] llm.base_model.model.model.layers.17.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,426 INFO [train.py:813] llm.base_model.model.model.layers.17.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,426 INFO [train.py:813] llm.base_model.model.model.layers.17.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,426 INFO [train.py:813] llm.base_model.model.model.layers.17.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,426 INFO [train.py:813] llm.base_model.model.model.layers.17.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,426 INFO [train.py:813] llm.base_model.model.model.layers.17.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,426 INFO [train.py:813] llm.base_model.model.model.layers.17.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,426 INFO [train.py:813] llm.base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,426 INFO [train.py:813] llm.base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,426 INFO [train.py:813] llm.base_model.model.model.layers.18.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,426 INFO [train.py:813] llm.base_model.model.model.layers.18.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,427 INFO [train.py:813] llm.base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,427 INFO [train.py:813] llm.base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,427 INFO [train.py:813] llm.base_model.model.model.layers.18.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,427 INFO [train.py:813] llm.base_model.model.model.layers.18.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,427 INFO [train.py:813] llm.base_model.model.model.layers.18.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,427 INFO [train.py:813] llm.base_model.model.model.layers.18.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,427 INFO [train.py:813] llm.base_model.model.model.layers.18.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,427 INFO [train.py:813] llm.base_model.model.model.layers.18.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,427 INFO [train.py:813] llm.base_model.model.model.layers.18.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,427 INFO [train.py:813] llm.base_model.model.model.layers.18.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,427 INFO [train.py:813] llm.base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,427 INFO [train.py:813] llm.base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,427 INFO [train.py:813] llm.base_model.model.model.layers.19.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,427 INFO [train.py:813] llm.base_model.model.model.layers.19.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,427 INFO [train.py:813] llm.base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,427 INFO [train.py:813] llm.base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,427 INFO [train.py:813] llm.base_model.model.model.layers.19.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,427 INFO [train.py:813] llm.base_model.model.model.layers.19.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,427 INFO [train.py:813] llm.base_model.model.model.layers.19.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,427 INFO [train.py:813] llm.base_model.model.model.layers.19.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,427 INFO [train.py:813] llm.base_model.model.model.layers.19.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,427 INFO [train.py:813] llm.base_model.model.model.layers.19.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.19.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.19.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.20.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.20.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.20.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.20.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.20.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.20.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.20.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.20.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.20.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.20.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.21.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.21.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,428 INFO [train.py:813] llm.base_model.model.model.layers.21.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.21.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.21.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.21.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.21.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.21.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.21.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.21.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.22.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.22.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.22.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.22.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.22.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.22.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.22.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.22.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.22.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.22.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.22.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.22.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.22.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.22.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.23.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,429 INFO [train.py:813] llm.base_model.model.model.layers.23.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,430 INFO [train.py:813] llm.base_model.model.model.layers.23.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,430 INFO [train.py:813] llm.base_model.model.model.layers.23.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,430 INFO [train.py:813] llm.base_model.model.model.layers.23.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,430 INFO [train.py:813] llm.base_model.model.model.layers.23.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64]) 2025-04-25 00:58:25,430 INFO [train.py:813] llm.base_model.model.model.layers.23.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,430 INFO [train.py:813] llm.base_model.model.model.layers.23.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,430 INFO [train.py:813] llm.base_model.model.model.layers.23.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,430 INFO [train.py:813] llm.base_model.model.model.layers.23.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,430 INFO [train.py:813] llm.base_model.model.model.layers.23.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896]) 2025-04-25 00:58:25,430 INFO [train.py:813] llm.base_model.model.model.layers.23.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64]) 2025-04-25 00:58:25,430 INFO [train.py:813] llm.base_model.model.model.layers.23.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864]) 2025-04-25 00:58:25,430 INFO [train.py:813] llm.base_model.model.model.layers.23.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64]) 2025-04-25 00:58:25,430 INFO [train.py:813] encoder_projector.linear1.weight: torch.Size([896, 10240]) 2025-04-25 00:58:25,430 INFO [train.py:813] encoder_projector.linear1.bias: torch.Size([896]) 2025-04-25 00:58:25,430 INFO [train.py:813] encoder_projector.linear2.weight: torch.Size([896, 896]) 2025-04-25 00:58:25,430 INFO [train.py:813] encoder_projector.linear2.bias: torch.Size([896]) 2025-04-25 00:58:25,430 INFO [train.py:813] codec_lm.model.embed_tokens.weight: torch.Size([4100, 1024]) 2025-04-25 00:58:25,430 INFO [train.py:813] codec_lm.model.layers.0.self_attn.q_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,430 INFO [train.py:813] codec_lm.model.layers.0.self_attn.q_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,430 INFO [train.py:813] codec_lm.model.layers.0.self_attn.k_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,430 INFO [train.py:813] codec_lm.model.layers.0.self_attn.k_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,430 INFO [train.py:813] codec_lm.model.layers.0.self_attn.v_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,430 INFO [train.py:813] codec_lm.model.layers.0.self_attn.v_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,430 INFO [train.py:813] codec_lm.model.layers.0.self_attn.o_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,430 INFO [train.py:813] codec_lm.model.layers.0.mlp.gate_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.0.mlp.up_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.0.mlp.down_proj.weight: torch.Size([1024, 2048]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.0.input_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.0.post_attention_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.1.self_attn.q_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.1.self_attn.q_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.1.self_attn.k_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.1.self_attn.k_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.1.self_attn.v_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.1.self_attn.v_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.1.self_attn.o_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.1.mlp.gate_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.1.mlp.up_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.1.mlp.down_proj.weight: torch.Size([1024, 2048]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.1.input_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.1.post_attention_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.2.self_attn.q_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.2.self_attn.q_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.2.self_attn.k_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.2.self_attn.k_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.2.self_attn.v_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.2.self_attn.v_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.2.self_attn.o_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.2.mlp.gate_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.2.mlp.up_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.2.mlp.down_proj.weight: torch.Size([1024, 2048]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.2.input_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.2.post_attention_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,431 INFO [train.py:813] codec_lm.model.layers.3.self_attn.q_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.3.self_attn.q_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.3.self_attn.k_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.3.self_attn.k_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.3.self_attn.v_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.3.self_attn.v_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.3.self_attn.o_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.3.mlp.gate_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.3.mlp.up_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.3.mlp.down_proj.weight: torch.Size([1024, 2048]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.3.input_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.3.post_attention_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.4.self_attn.q_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.4.self_attn.q_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.4.self_attn.k_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.4.self_attn.k_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.4.self_attn.v_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.4.self_attn.v_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.4.self_attn.o_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.4.mlp.gate_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.4.mlp.up_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.4.mlp.down_proj.weight: torch.Size([1024, 2048]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.4.input_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.4.post_attention_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.5.self_attn.q_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.5.self_attn.q_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.5.self_attn.k_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.5.self_attn.k_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.5.self_attn.v_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.5.self_attn.v_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,432 INFO [train.py:813] codec_lm.model.layers.5.self_attn.o_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.5.mlp.gate_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.5.mlp.up_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.5.mlp.down_proj.weight: torch.Size([1024, 2048]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.5.input_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.5.post_attention_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.6.self_attn.q_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.6.self_attn.q_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.6.self_attn.k_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.6.self_attn.k_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.6.self_attn.v_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.6.self_attn.v_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.6.self_attn.o_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.6.mlp.gate_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.6.mlp.up_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.6.mlp.down_proj.weight: torch.Size([1024, 2048]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.6.input_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.6.post_attention_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.7.self_attn.q_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.7.self_attn.q_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.7.self_attn.k_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.7.self_attn.k_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.7.self_attn.v_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.7.self_attn.v_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.7.self_attn.o_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.7.mlp.gate_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.7.mlp.up_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.7.mlp.down_proj.weight: torch.Size([1024, 2048]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.7.input_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.7.post_attention_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.8.self_attn.q_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,433 INFO [train.py:813] codec_lm.model.layers.8.self_attn.q_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.8.self_attn.k_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.8.self_attn.k_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.8.self_attn.v_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.8.self_attn.v_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.8.self_attn.o_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.8.mlp.gate_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.8.mlp.up_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.8.mlp.down_proj.weight: torch.Size([1024, 2048]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.8.input_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.8.post_attention_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.9.self_attn.q_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.9.self_attn.q_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.9.self_attn.k_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.9.self_attn.k_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.9.self_attn.v_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.9.self_attn.v_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.9.self_attn.o_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.9.mlp.gate_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.9.mlp.up_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.9.mlp.down_proj.weight: torch.Size([1024, 2048]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.9.input_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.9.post_attention_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.10.self_attn.q_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.10.self_attn.q_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.10.self_attn.k_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.10.self_attn.k_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.10.self_attn.v_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.10.self_attn.v_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,434 INFO [train.py:813] codec_lm.model.layers.10.self_attn.o_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,435 INFO [train.py:813] codec_lm.model.layers.10.mlp.gate_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,435 INFO [train.py:813] codec_lm.model.layers.10.mlp.up_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,435 INFO [train.py:813] codec_lm.model.layers.10.mlp.down_proj.weight: torch.Size([1024, 2048]) 2025-04-25 00:58:25,435 INFO [train.py:813] codec_lm.model.layers.10.input_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,435 INFO [train.py:813] codec_lm.model.layers.10.post_attention_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,435 INFO [train.py:813] codec_lm.model.layers.11.self_attn.q_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,435 INFO [train.py:813] codec_lm.model.layers.11.self_attn.q_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,435 INFO [train.py:813] codec_lm.model.layers.11.self_attn.k_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,435 INFO [train.py:813] codec_lm.model.layers.11.self_attn.k_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,435 INFO [train.py:813] codec_lm.model.layers.11.self_attn.v_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,435 INFO [train.py:813] codec_lm.model.layers.11.self_attn.v_proj.bias: torch.Size([1024]) 2025-04-25 00:58:25,435 INFO [train.py:813] codec_lm.model.layers.11.self_attn.o_proj.weight: torch.Size([1024, 1024]) 2025-04-25 00:58:25,435 INFO [train.py:813] codec_lm.model.layers.11.mlp.gate_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,435 INFO [train.py:813] codec_lm.model.layers.11.mlp.up_proj.weight: torch.Size([2048, 1024]) 2025-04-25 00:58:25,435 INFO [train.py:813] codec_lm.model.layers.11.mlp.down_proj.weight: torch.Size([1024, 2048]) 2025-04-25 00:58:25,435 INFO [train.py:813] codec_lm.model.layers.11.input_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,435 INFO [train.py:813] codec_lm.model.layers.11.post_attention_layernorm.weight: torch.Size([1024]) 2025-04-25 00:58:25,435 INFO [train.py:813] codec_lm.model.norm.weight: torch.Size([1024]) 2025-04-25 00:58:25,435 INFO [train.py:813] codec_lm.lm_head.weight: torch.Size([4100, 1024]) 2025-04-25 00:58:25,435 INFO [train.py:813] speech_token_projector.weight: torch.Size([1024, 1792]) 2025-04-25 00:58:25,435 INFO [train.py:813] speech_token_projector.bias: torch.Size([1024]) 2025-04-25 00:58:25,435 INFO [train.py:813] codec_lm_head.weight: torch.Size([4100, 1024]) 2025-04-25 00:58:25,435 INFO [train.py:813] codec_lm_head.bias: torch.Size([4100]) 2025-04-25 00:58:25,435 INFO [train.py:819] Device: cuda:1 2025-04-25 00:58:26,665 INFO [train.py:823] Using DeepSpeed 2025-04-25 00:58:30,432 INFO [data_module.py:445] About to get train cuts 2025-04-25 00:58:30,434 INFO [data_module.py:250] Disable MUSAN 2025-04-25 00:58:30,434 INFO [data_module.py:268] Enable SpecAugment 2025-04-25 00:58:30,434 INFO [data_module.py:269] Time warp factor: 80 2025-04-25 00:58:30,434 INFO [data_module.py:279] Num frame mask: 10 2025-04-25 00:58:30,434 INFO [data_module.py:292] About to create train dataset 2025-04-25 00:58:30,434 INFO [data_module.py:319] Using DynamicBucketingSampler. 2025-04-25 00:58:31,421 INFO [data_module.py:336] About to create train dataloader 2025-04-25 00:58:31,421 INFO [data_module.py:339] Loading sampler state dict