2025-04-24 10:12:23,878 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": "0.114.172.122",
    "hostname": "7515258",
    "icefall-git-branch": "master",
    "icefall-git-date": "Thu Apr 24 08:24:11 2025",
    "icefall-git-sha1": "2e9be467-dirty",
    "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": 40,
  "num_buckets": 30,
  "num_epochs": 10,
  "num_workers": 2,
  "on_the_fly_feats": false,
  "pretrained_model_path": null,
  "resample_to_16kHz": true,
  "reset_interval": 200,
  "return_cuts": true,
  "sampler_state_dict_path": null,
  "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
}
2025-04-24 10:12:23,878 INFO [train.py:655] About to create model
2025-04-24 10:12:44,166 INFO [train.py:808] Number of model parameters: 1326848644
2025-04-24 10:12:44,166 INFO [train.py:810] Trainable parameters (excluding model.eval modules):
2025-04-24 10:12:44,167 INFO [train.py:813] llm.base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,167 INFO [train.py:813] llm.base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,167 INFO [train.py:813] llm.base_model.model.model.layers.0.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,167 INFO [train.py:813] llm.base_model.model.model.layers.0.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,167 INFO [train.py:813] llm.base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,167 INFO [train.py:813] llm.base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,168 INFO [train.py:813] llm.base_model.model.model.layers.0.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,168 INFO [train.py:813] llm.base_model.model.model.layers.0.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,168 INFO [train.py:813] llm.base_model.model.model.layers.0.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,168 INFO [train.py:813] llm.base_model.model.model.layers.0.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,168 INFO [train.py:813] llm.base_model.model.model.layers.0.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,168 INFO [train.py:813] llm.base_model.model.model.layers.0.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,168 INFO [train.py:813] llm.base_model.model.model.layers.0.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,168 INFO [train.py:813] llm.base_model.model.model.layers.0.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,168 INFO [train.py:813] llm.base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,168 INFO [train.py:813] llm.base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,168 INFO [train.py:813] llm.base_model.model.model.layers.1.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,168 INFO [train.py:813] llm.base_model.model.model.layers.1.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,168 INFO [train.py:813] llm.base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,168 INFO [train.py:813] llm.base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,168 INFO [train.py:813] llm.base_model.model.model.layers.1.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,168 INFO [train.py:813] llm.base_model.model.model.layers.1.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,168 INFO [train.py:813] llm.base_model.model.model.layers.1.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,169 INFO [train.py:813] llm.base_model.model.model.layers.1.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,169 INFO [train.py:813] llm.base_model.model.model.layers.1.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,169 INFO [train.py:813] llm.base_model.model.model.layers.1.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,169 INFO [train.py:813] llm.base_model.model.model.layers.1.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,169 INFO [train.py:813] llm.base_model.model.model.layers.1.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,169 INFO [train.py:813] llm.base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,169 INFO [train.py:813] llm.base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,169 INFO [train.py:813] llm.base_model.model.model.layers.2.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,169 INFO [train.py:813] llm.base_model.model.model.layers.2.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,169 INFO [train.py:813] llm.base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,169 INFO [train.py:813] llm.base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,169 INFO [train.py:813] llm.base_model.model.model.layers.2.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,169 INFO [train.py:813] llm.base_model.model.model.layers.2.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,169 INFO [train.py:813] llm.base_model.model.model.layers.2.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,169 INFO [train.py:813] llm.base_model.model.model.layers.2.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,169 INFO [train.py:813] llm.base_model.model.model.layers.2.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,169 INFO [train.py:813] llm.base_model.model.model.layers.2.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,169 INFO [train.py:813] llm.base_model.model.model.layers.2.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,169 INFO [train.py:813] llm.base_model.model.model.layers.2.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,170 INFO [train.py:813] llm.base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,170 INFO [train.py:813] llm.base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,170 INFO [train.py:813] llm.base_model.model.model.layers.3.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,170 INFO [train.py:813] llm.base_model.model.model.layers.3.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,170 INFO [train.py:813] llm.base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,170 INFO [train.py:813] llm.base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,170 INFO [train.py:813] llm.base_model.model.model.layers.3.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,170 INFO [train.py:813] llm.base_model.model.model.layers.3.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,170 INFO [train.py:813] llm.base_model.model.model.layers.3.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,170 INFO [train.py:813] llm.base_model.model.model.layers.3.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,170 INFO [train.py:813] llm.base_model.model.model.layers.3.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,170 INFO [train.py:813] llm.base_model.model.model.layers.3.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,170 INFO [train.py:813] llm.base_model.model.model.layers.3.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,170 INFO [train.py:813] llm.base_model.model.model.layers.3.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,170 INFO [train.py:813] llm.base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,170 INFO [train.py:813] llm.base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,170 INFO [train.py:813] llm.base_model.model.model.layers.4.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,170 INFO [train.py:813] llm.base_model.model.model.layers.4.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,171 INFO [train.py:813] llm.base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,171 INFO [train.py:813] llm.base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,171 INFO [train.py:813] llm.base_model.model.model.layers.4.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,171 INFO [train.py:813] llm.base_model.model.model.layers.4.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,171 INFO [train.py:813] llm.base_model.model.model.layers.4.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,171 INFO [train.py:813] llm.base_model.model.model.layers.4.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,171 INFO [train.py:813] llm.base_model.model.model.layers.4.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,171 INFO [train.py:813] llm.base_model.model.model.layers.4.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,171 INFO [train.py:813] llm.base_model.model.model.layers.4.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,171 INFO [train.py:813] llm.base_model.model.model.layers.4.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,171 INFO [train.py:813] llm.base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,171 INFO [train.py:813] llm.base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,171 INFO [train.py:813] llm.base_model.model.model.layers.5.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,171 INFO [train.py:813] llm.base_model.model.model.layers.5.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,171 INFO [train.py:813] llm.base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,171 INFO [train.py:813] llm.base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,171 INFO [train.py:813] llm.base_model.model.model.layers.5.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,171 INFO [train.py:813] llm.base_model.model.model.layers.5.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,172 INFO [train.py:813] llm.base_model.model.model.layers.5.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,172 INFO [train.py:813] llm.base_model.model.model.layers.5.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,172 INFO [train.py:813] llm.base_model.model.model.layers.5.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,172 INFO [train.py:813] llm.base_model.model.model.layers.5.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,172 INFO [train.py:813] llm.base_model.model.model.layers.5.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,172 INFO [train.py:813] llm.base_model.model.model.layers.5.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,172 INFO [train.py:813] llm.base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,172 INFO [train.py:813] llm.base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,172 INFO [train.py:813] llm.base_model.model.model.layers.6.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,172 INFO [train.py:813] llm.base_model.model.model.layers.6.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,172 INFO [train.py:813] llm.base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,172 INFO [train.py:813] llm.base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,172 INFO [train.py:813] llm.base_model.model.model.layers.6.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,172 INFO [train.py:813] llm.base_model.model.model.layers.6.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,172 INFO [train.py:813] llm.base_model.model.model.layers.6.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,172 INFO [train.py:813] llm.base_model.model.model.layers.6.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,172 INFO [train.py:813] llm.base_model.model.model.layers.6.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,172 INFO [train.py:813] llm.base_model.model.model.layers.6.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,172 INFO [train.py:813] llm.base_model.model.model.layers.6.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,172 INFO [train.py:813] llm.base_model.model.model.layers.6.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,173 INFO [train.py:813] llm.base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,173 INFO [train.py:813] llm.base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,173 INFO [train.py:813] llm.base_model.model.model.layers.7.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,173 INFO [train.py:813] llm.base_model.model.model.layers.7.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,173 INFO [train.py:813] llm.base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,173 INFO [train.py:813] llm.base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,173 INFO [train.py:813] llm.base_model.model.model.layers.7.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,173 INFO [train.py:813] llm.base_model.model.model.layers.7.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,173 INFO [train.py:813] llm.base_model.model.model.layers.7.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,173 INFO [train.py:813] llm.base_model.model.model.layers.7.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,173 INFO [train.py:813] llm.base_model.model.model.layers.7.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,173 INFO [train.py:813] llm.base_model.model.model.layers.7.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,173 INFO [train.py:813] llm.base_model.model.model.layers.7.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,173 INFO [train.py:813] llm.base_model.model.model.layers.7.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,173 INFO [train.py:813] llm.base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,173 INFO [train.py:813] llm.base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,173 INFO [train.py:813] llm.base_model.model.model.layers.8.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,173 INFO [train.py:813] llm.base_model.model.model.layers.8.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,173 INFO [train.py:813] llm.base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,174 INFO [train.py:813] llm.base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,174 INFO [train.py:813] llm.base_model.model.model.layers.8.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,174 INFO [train.py:813] llm.base_model.model.model.layers.8.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,174 INFO [train.py:813] llm.base_model.model.model.layers.8.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,174 INFO [train.py:813] llm.base_model.model.model.layers.8.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,174 INFO [train.py:813] llm.base_model.model.model.layers.8.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,174 INFO [train.py:813] llm.base_model.model.model.layers.8.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,174 INFO [train.py:813] llm.base_model.model.model.layers.8.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,174 INFO [train.py:813] llm.base_model.model.model.layers.8.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,174 INFO [train.py:813] llm.base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,174 INFO [train.py:813] llm.base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,174 INFO [train.py:813] llm.base_model.model.model.layers.9.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,174 INFO [train.py:813] llm.base_model.model.model.layers.9.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,174 INFO [train.py:813] llm.base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,174 INFO [train.py:813] llm.base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,174 INFO [train.py:813] llm.base_model.model.model.layers.9.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,174 INFO [train.py:813] llm.base_model.model.model.layers.9.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,174 INFO [train.py:813] llm.base_model.model.model.layers.9.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,174 INFO [train.py:813] llm.base_model.model.model.layers.9.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,175 INFO [train.py:813] llm.base_model.model.model.layers.9.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,175 INFO [train.py:813] llm.base_model.model.model.layers.9.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,175 INFO [train.py:813] llm.base_model.model.model.layers.9.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,175 INFO [train.py:813] llm.base_model.model.model.layers.9.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,175 INFO [train.py:813] llm.base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,175 INFO [train.py:813] llm.base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,175 INFO [train.py:813] llm.base_model.model.model.layers.10.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,175 INFO [train.py:813] llm.base_model.model.model.layers.10.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,175 INFO [train.py:813] llm.base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,175 INFO [train.py:813] llm.base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,175 INFO [train.py:813] llm.base_model.model.model.layers.10.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,175 INFO [train.py:813] llm.base_model.model.model.layers.10.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,175 INFO [train.py:813] llm.base_model.model.model.layers.10.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,175 INFO [train.py:813] llm.base_model.model.model.layers.10.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,175 INFO [train.py:813] llm.base_model.model.model.layers.10.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,175 INFO [train.py:813] llm.base_model.model.model.layers.10.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,175 INFO [train.py:813] llm.base_model.model.model.layers.10.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,175 INFO [train.py:813] llm.base_model.model.model.layers.10.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,176 INFO [train.py:813] llm.base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,176 INFO [train.py:813] llm.base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,176 INFO [train.py:813] llm.base_model.model.model.layers.11.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,176 INFO [train.py:813] llm.base_model.model.model.layers.11.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,176 INFO [train.py:813] llm.base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,176 INFO [train.py:813] llm.base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,176 INFO [train.py:813] llm.base_model.model.model.layers.11.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,176 INFO [train.py:813] llm.base_model.model.model.layers.11.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,176 INFO [train.py:813] llm.base_model.model.model.layers.11.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,176 INFO [train.py:813] llm.base_model.model.model.layers.11.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,176 INFO [train.py:813] llm.base_model.model.model.layers.11.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,176 INFO [train.py:813] llm.base_model.model.model.layers.11.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,176 INFO [train.py:813] llm.base_model.model.model.layers.11.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,176 INFO [train.py:813] llm.base_model.model.model.layers.11.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,176 INFO [train.py:813] llm.base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,176 INFO [train.py:813] llm.base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,176 INFO [train.py:813] llm.base_model.model.model.layers.12.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,176 INFO [train.py:813] llm.base_model.model.model.layers.12.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,176 INFO [train.py:813] llm.base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,176 INFO [train.py:813] llm.base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,177 INFO [train.py:813] llm.base_model.model.model.layers.12.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,177 INFO [train.py:813] llm.base_model.model.model.layers.12.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,177 INFO [train.py:813] llm.base_model.model.model.layers.12.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,177 INFO [train.py:813] llm.base_model.model.model.layers.12.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,177 INFO [train.py:813] llm.base_model.model.model.layers.12.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,177 INFO [train.py:813] llm.base_model.model.model.layers.12.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,177 INFO [train.py:813] llm.base_model.model.model.layers.12.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,177 INFO [train.py:813] llm.base_model.model.model.layers.12.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,177 INFO [train.py:813] llm.base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,177 INFO [train.py:813] llm.base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,177 INFO [train.py:813] llm.base_model.model.model.layers.13.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,177 INFO [train.py:813] llm.base_model.model.model.layers.13.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,177 INFO [train.py:813] llm.base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,177 INFO [train.py:813] llm.base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,177 INFO [train.py:813] llm.base_model.model.model.layers.13.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,177 INFO [train.py:813] llm.base_model.model.model.layers.13.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,177 INFO [train.py:813] llm.base_model.model.model.layers.13.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,177 INFO [train.py:813] llm.base_model.model.model.layers.13.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,177 INFO [train.py:813] llm.base_model.model.model.layers.13.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,178 INFO [train.py:813] llm.base_model.model.model.layers.13.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,178 INFO [train.py:813] llm.base_model.model.model.layers.13.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,178 INFO [train.py:813] llm.base_model.model.model.layers.13.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,178 INFO [train.py:813] llm.base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,178 INFO [train.py:813] llm.base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,178 INFO [train.py:813] llm.base_model.model.model.layers.14.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,178 INFO [train.py:813] llm.base_model.model.model.layers.14.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,178 INFO [train.py:813] llm.base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,178 INFO [train.py:813] llm.base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,178 INFO [train.py:813] llm.base_model.model.model.layers.14.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,178 INFO [train.py:813] llm.base_model.model.model.layers.14.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,178 INFO [train.py:813] llm.base_model.model.model.layers.14.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,178 INFO [train.py:813] llm.base_model.model.model.layers.14.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,178 INFO [train.py:813] llm.base_model.model.model.layers.14.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,178 INFO [train.py:813] llm.base_model.model.model.layers.14.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,178 INFO [train.py:813] llm.base_model.model.model.layers.14.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,178 INFO [train.py:813] llm.base_model.model.model.layers.14.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,178 INFO [train.py:813] llm.base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,178 INFO [train.py:813] llm.base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,179 INFO [train.py:813] llm.base_model.model.model.layers.15.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,179 INFO [train.py:813] llm.base_model.model.model.layers.15.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,179 INFO [train.py:813] llm.base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,179 INFO [train.py:813] llm.base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,179 INFO [train.py:813] llm.base_model.model.model.layers.15.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,179 INFO [train.py:813] llm.base_model.model.model.layers.15.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,179 INFO [train.py:813] llm.base_model.model.model.layers.15.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,179 INFO [train.py:813] llm.base_model.model.model.layers.15.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,179 INFO [train.py:813] llm.base_model.model.model.layers.15.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,179 INFO [train.py:813] llm.base_model.model.model.layers.15.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,179 INFO [train.py:813] llm.base_model.model.model.layers.15.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,179 INFO [train.py:813] llm.base_model.model.model.layers.15.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,179 INFO [train.py:813] llm.base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,179 INFO [train.py:813] llm.base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,179 INFO [train.py:813] llm.base_model.model.model.layers.16.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,179 INFO [train.py:813] llm.base_model.model.model.layers.16.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,179 INFO [train.py:813] llm.base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,179 INFO [train.py:813] llm.base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,180 INFO [train.py:813] llm.base_model.model.model.layers.16.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,180 INFO [train.py:813] llm.base_model.model.model.layers.16.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,180 INFO [train.py:813] llm.base_model.model.model.layers.16.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,180 INFO [train.py:813] llm.base_model.model.model.layers.16.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,180 INFO [train.py:813] llm.base_model.model.model.layers.16.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,180 INFO [train.py:813] llm.base_model.model.model.layers.16.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,180 INFO [train.py:813] llm.base_model.model.model.layers.16.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,180 INFO [train.py:813] llm.base_model.model.model.layers.16.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,180 INFO [train.py:813] llm.base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,180 INFO [train.py:813] llm.base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,180 INFO [train.py:813] llm.base_model.model.model.layers.17.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,180 INFO [train.py:813] llm.base_model.model.model.layers.17.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,180 INFO [train.py:813] llm.base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,180 INFO [train.py:813] llm.base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,180 INFO [train.py:813] llm.base_model.model.model.layers.17.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,180 INFO [train.py:813] llm.base_model.model.model.layers.17.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,180 INFO [train.py:813] llm.base_model.model.model.layers.17.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,180 INFO [train.py:813] llm.base_model.model.model.layers.17.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,181 INFO [train.py:813] llm.base_model.model.model.layers.17.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,181 INFO [train.py:813] llm.base_model.model.model.layers.17.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,181 INFO [train.py:813] llm.base_model.model.model.layers.17.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,181 INFO [train.py:813] llm.base_model.model.model.layers.17.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,181 INFO [train.py:813] llm.base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,181 INFO [train.py:813] llm.base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,181 INFO [train.py:813] llm.base_model.model.model.layers.18.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,181 INFO [train.py:813] llm.base_model.model.model.layers.18.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,181 INFO [train.py:813] llm.base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,181 INFO [train.py:813] llm.base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,181 INFO [train.py:813] llm.base_model.model.model.layers.18.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,181 INFO [train.py:813] llm.base_model.model.model.layers.18.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,181 INFO [train.py:813] llm.base_model.model.model.layers.18.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,181 INFO [train.py:813] llm.base_model.model.model.layers.18.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,181 INFO [train.py:813] llm.base_model.model.model.layers.18.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,181 INFO [train.py:813] llm.base_model.model.model.layers.18.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,181 INFO [train.py:813] llm.base_model.model.model.layers.18.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,181 INFO [train.py:813] llm.base_model.model.model.layers.18.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,181 INFO [train.py:813] llm.base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,181 INFO [train.py:813] llm.base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,182 INFO [train.py:813] llm.base_model.model.model.layers.19.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,182 INFO [train.py:813] llm.base_model.model.model.layers.19.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,182 INFO [train.py:813] llm.base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,182 INFO [train.py:813] llm.base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,182 INFO [train.py:813] llm.base_model.model.model.layers.19.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,182 INFO [train.py:813] llm.base_model.model.model.layers.19.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,182 INFO [train.py:813] llm.base_model.model.model.layers.19.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,182 INFO [train.py:813] llm.base_model.model.model.layers.19.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,182 INFO [train.py:813] llm.base_model.model.model.layers.19.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,182 INFO [train.py:813] llm.base_model.model.model.layers.19.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,182 INFO [train.py:813] llm.base_model.model.model.layers.19.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,182 INFO [train.py:813] llm.base_model.model.model.layers.19.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,182 INFO [train.py:813] llm.base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,182 INFO [train.py:813] llm.base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,182 INFO [train.py:813] llm.base_model.model.model.layers.20.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,182 INFO [train.py:813] llm.base_model.model.model.layers.20.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,182 INFO [train.py:813] llm.base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,182 INFO [train.py:813] llm.base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,183 INFO [train.py:813] llm.base_model.model.model.layers.20.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,183 INFO [train.py:813] llm.base_model.model.model.layers.20.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,183 INFO [train.py:813] llm.base_model.model.model.layers.20.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,183 INFO [train.py:813] llm.base_model.model.model.layers.20.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,183 INFO [train.py:813] llm.base_model.model.model.layers.20.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,183 INFO [train.py:813] llm.base_model.model.model.layers.20.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,183 INFO [train.py:813] llm.base_model.model.model.layers.20.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,183 INFO [train.py:813] llm.base_model.model.model.layers.20.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,183 INFO [train.py:813] llm.base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,183 INFO [train.py:813] llm.base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,183 INFO [train.py:813] llm.base_model.model.model.layers.21.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,183 INFO [train.py:813] llm.base_model.model.model.layers.21.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,183 INFO [train.py:813] llm.base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,183 INFO [train.py:813] llm.base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,183 INFO [train.py:813] llm.base_model.model.model.layers.21.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,183 INFO [train.py:813] llm.base_model.model.model.layers.21.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,183 INFO [train.py:813] llm.base_model.model.model.layers.21.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,183 INFO [train.py:813] llm.base_model.model.model.layers.21.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,183 INFO [train.py:813] llm.base_model.model.model.layers.21.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,184 INFO [train.py:813] llm.base_model.model.model.layers.21.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,184 INFO [train.py:813] llm.base_model.model.model.layers.21.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,184 INFO [train.py:813] llm.base_model.model.model.layers.21.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,184 INFO [train.py:813] llm.base_model.model.model.layers.22.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,184 INFO [train.py:813] llm.base_model.model.model.layers.22.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,184 INFO [train.py:813] llm.base_model.model.model.layers.22.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,184 INFO [train.py:813] llm.base_model.model.model.layers.22.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,184 INFO [train.py:813] llm.base_model.model.model.layers.22.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,184 INFO [train.py:813] llm.base_model.model.model.layers.22.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,184 INFO [train.py:813] llm.base_model.model.model.layers.22.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,184 INFO [train.py:813] llm.base_model.model.model.layers.22.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,184 INFO [train.py:813] llm.base_model.model.model.layers.22.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,184 INFO [train.py:813] llm.base_model.model.model.layers.22.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,184 INFO [train.py:813] llm.base_model.model.model.layers.22.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,184 INFO [train.py:813] llm.base_model.model.model.layers.22.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,184 INFO [train.py:813] llm.base_model.model.model.layers.22.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,184 INFO [train.py:813] llm.base_model.model.model.layers.22.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,184 INFO [train.py:813] llm.base_model.model.model.layers.23.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,184 INFO [train.py:813] llm.base_model.model.model.layers.23.self_attn.q_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,184 INFO [train.py:813] llm.base_model.model.model.layers.23.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,185 INFO [train.py:813] llm.base_model.model.model.layers.23.self_attn.k_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,185 INFO [train.py:813] llm.base_model.model.model.layers.23.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,185 INFO [train.py:813] llm.base_model.model.model.layers.23.self_attn.v_proj.lora_B.default.weight: torch.Size([128, 64])
2025-04-24 10:12:44,185 INFO [train.py:813] llm.base_model.model.model.layers.23.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,185 INFO [train.py:813] llm.base_model.model.model.layers.23.self_attn.o_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,185 INFO [train.py:813] llm.base_model.model.model.layers.23.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,185 INFO [train.py:813] llm.base_model.model.model.layers.23.mlp.gate_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,185 INFO [train.py:813] llm.base_model.model.model.layers.23.mlp.up_proj.lora_A.default.weight: torch.Size([64, 896])
2025-04-24 10:12:44,185 INFO [train.py:813] llm.base_model.model.model.layers.23.mlp.up_proj.lora_B.default.weight: torch.Size([4864, 64])
2025-04-24 10:12:44,185 INFO [train.py:813] llm.base_model.model.model.layers.23.mlp.down_proj.lora_A.default.weight: torch.Size([64, 4864])
2025-04-24 10:12:44,185 INFO [train.py:813] llm.base_model.model.model.layers.23.mlp.down_proj.lora_B.default.weight: torch.Size([896, 64])
2025-04-24 10:12:44,185 INFO [train.py:813] encoder_projector.linear1.weight: torch.Size([896, 10240])
2025-04-24 10:12:44,185 INFO [train.py:813] encoder_projector.linear1.bias: torch.Size([896])
2025-04-24 10:12:44,185 INFO [train.py:813] encoder_projector.linear2.weight: torch.Size([896, 896])
2025-04-24 10:12:44,185 INFO [train.py:813] encoder_projector.linear2.bias: torch.Size([896])
2025-04-24 10:12:44,185 INFO [train.py:813] codec_lm.base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,185 INFO [train.py:813] codec_lm.base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,185 INFO [train.py:813] codec_lm.base_model.model.model.layers.0.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,185 INFO [train.py:813] codec_lm.base_model.model.model.layers.0.self_attn.k_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,186 INFO [train.py:813] codec_lm.base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,186 INFO [train.py:813] codec_lm.base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,186 INFO [train.py:813] codec_lm.base_model.model.model.layers.0.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,186 INFO [train.py:813] codec_lm.base_model.model.model.layers.0.self_attn.o_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,186 INFO [train.py:813] codec_lm.base_model.model.model.layers.0.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,186 INFO [train.py:813] codec_lm.base_model.model.model.layers.0.mlp.gate_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,186 INFO [train.py:813] codec_lm.base_model.model.model.layers.0.mlp.up_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,186 INFO [train.py:813] codec_lm.base_model.model.model.layers.0.mlp.up_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,186 INFO [train.py:813] codec_lm.base_model.model.model.layers.0.mlp.down_proj.lora_A.default.weight: torch.Size([64, 2048])
2025-04-24 10:12:44,186 INFO [train.py:813] codec_lm.base_model.model.model.layers.0.mlp.down_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,186 INFO [train.py:813] codec_lm.base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,186 INFO [train.py:813] codec_lm.base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,186 INFO [train.py:813] codec_lm.base_model.model.model.layers.1.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,186 INFO [train.py:813] codec_lm.base_model.model.model.layers.1.self_attn.k_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,186 INFO [train.py:813] codec_lm.base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,186 INFO [train.py:813] codec_lm.base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,186 INFO [train.py:813] codec_lm.base_model.model.model.layers.1.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,186 INFO [train.py:813] codec_lm.base_model.model.model.layers.1.self_attn.o_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,186 INFO [train.py:813] codec_lm.base_model.model.model.layers.1.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,186 INFO [train.py:813] codec_lm.base_model.model.model.layers.1.mlp.gate_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,187 INFO [train.py:813] codec_lm.base_model.model.model.layers.1.mlp.up_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,187 INFO [train.py:813] codec_lm.base_model.model.model.layers.1.mlp.up_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,187 INFO [train.py:813] codec_lm.base_model.model.model.layers.1.mlp.down_proj.lora_A.default.weight: torch.Size([64, 2048])
2025-04-24 10:12:44,187 INFO [train.py:813] codec_lm.base_model.model.model.layers.1.mlp.down_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,187 INFO [train.py:813] codec_lm.base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,187 INFO [train.py:813] codec_lm.base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,187 INFO [train.py:813] codec_lm.base_model.model.model.layers.2.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,187 INFO [train.py:813] codec_lm.base_model.model.model.layers.2.self_attn.k_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,187 INFO [train.py:813] codec_lm.base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,187 INFO [train.py:813] codec_lm.base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,187 INFO [train.py:813] codec_lm.base_model.model.model.layers.2.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,187 INFO [train.py:813] codec_lm.base_model.model.model.layers.2.self_attn.o_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,187 INFO [train.py:813] codec_lm.base_model.model.model.layers.2.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,187 INFO [train.py:813] codec_lm.base_model.model.model.layers.2.mlp.gate_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,187 INFO [train.py:813] codec_lm.base_model.model.model.layers.2.mlp.up_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,187 INFO [train.py:813] codec_lm.base_model.model.model.layers.2.mlp.up_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,187 INFO [train.py:813] codec_lm.base_model.model.model.layers.2.mlp.down_proj.lora_A.default.weight: torch.Size([64, 2048])
2025-04-24 10:12:44,187 INFO [train.py:813] codec_lm.base_model.model.model.layers.2.mlp.down_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,187 INFO [train.py:813] codec_lm.base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,188 INFO [train.py:813] codec_lm.base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,188 INFO [train.py:813] codec_lm.base_model.model.model.layers.3.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,188 INFO [train.py:813] codec_lm.base_model.model.model.layers.3.self_attn.k_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,188 INFO [train.py:813] codec_lm.base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,188 INFO [train.py:813] codec_lm.base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,188 INFO [train.py:813] codec_lm.base_model.model.model.layers.3.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,188 INFO [train.py:813] codec_lm.base_model.model.model.layers.3.self_attn.o_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,188 INFO [train.py:813] codec_lm.base_model.model.model.layers.3.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,188 INFO [train.py:813] codec_lm.base_model.model.model.layers.3.mlp.gate_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,188 INFO [train.py:813] codec_lm.base_model.model.model.layers.3.mlp.up_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,188 INFO [train.py:813] codec_lm.base_model.model.model.layers.3.mlp.up_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,188 INFO [train.py:813] codec_lm.base_model.model.model.layers.3.mlp.down_proj.lora_A.default.weight: torch.Size([64, 2048])
2025-04-24 10:12:44,188 INFO [train.py:813] codec_lm.base_model.model.model.layers.3.mlp.down_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,188 INFO [train.py:813] codec_lm.base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,188 INFO [train.py:813] codec_lm.base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,188 INFO [train.py:813] codec_lm.base_model.model.model.layers.4.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,188 INFO [train.py:813] codec_lm.base_model.model.model.layers.4.self_attn.k_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,188 INFO [train.py:813] codec_lm.base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,188 INFO [train.py:813] codec_lm.base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,189 INFO [train.py:813] codec_lm.base_model.model.model.layers.4.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,189 INFO [train.py:813] codec_lm.base_model.model.model.layers.4.self_attn.o_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,189 INFO [train.py:813] codec_lm.base_model.model.model.layers.4.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,189 INFO [train.py:813] codec_lm.base_model.model.model.layers.4.mlp.gate_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,189 INFO [train.py:813] codec_lm.base_model.model.model.layers.4.mlp.up_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,189 INFO [train.py:813] codec_lm.base_model.model.model.layers.4.mlp.up_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,189 INFO [train.py:813] codec_lm.base_model.model.model.layers.4.mlp.down_proj.lora_A.default.weight: torch.Size([64, 2048])
2025-04-24 10:12:44,189 INFO [train.py:813] codec_lm.base_model.model.model.layers.4.mlp.down_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,189 INFO [train.py:813] codec_lm.base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,189 INFO [train.py:813] codec_lm.base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,189 INFO [train.py:813] codec_lm.base_model.model.model.layers.5.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,189 INFO [train.py:813] codec_lm.base_model.model.model.layers.5.self_attn.k_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,189 INFO [train.py:813] codec_lm.base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,189 INFO [train.py:813] codec_lm.base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,189 INFO [train.py:813] codec_lm.base_model.model.model.layers.5.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,189 INFO [train.py:813] codec_lm.base_model.model.model.layers.5.self_attn.o_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,189 INFO [train.py:813] codec_lm.base_model.model.model.layers.5.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,189 INFO [train.py:813] codec_lm.base_model.model.model.layers.5.mlp.gate_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,189 INFO [train.py:813] codec_lm.base_model.model.model.layers.5.mlp.up_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,190 INFO [train.py:813] codec_lm.base_model.model.model.layers.5.mlp.up_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,190 INFO [train.py:813] codec_lm.base_model.model.model.layers.5.mlp.down_proj.lora_A.default.weight: torch.Size([64, 2048])
2025-04-24 10:12:44,190 INFO [train.py:813] codec_lm.base_model.model.model.layers.5.mlp.down_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,190 INFO [train.py:813] codec_lm.base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,190 INFO [train.py:813] codec_lm.base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,190 INFO [train.py:813] codec_lm.base_model.model.model.layers.6.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,190 INFO [train.py:813] codec_lm.base_model.model.model.layers.6.self_attn.k_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,190 INFO [train.py:813] codec_lm.base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,190 INFO [train.py:813] codec_lm.base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,190 INFO [train.py:813] codec_lm.base_model.model.model.layers.6.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,190 INFO [train.py:813] codec_lm.base_model.model.model.layers.6.self_attn.o_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,190 INFO [train.py:813] codec_lm.base_model.model.model.layers.6.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,190 INFO [train.py:813] codec_lm.base_model.model.model.layers.6.mlp.gate_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,190 INFO [train.py:813] codec_lm.base_model.model.model.layers.6.mlp.up_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,190 INFO [train.py:813] codec_lm.base_model.model.model.layers.6.mlp.up_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,190 INFO [train.py:813] codec_lm.base_model.model.model.layers.6.mlp.down_proj.lora_A.default.weight: torch.Size([64, 2048])
2025-04-24 10:12:44,190 INFO [train.py:813] codec_lm.base_model.model.model.layers.6.mlp.down_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,190 INFO [train.py:813] codec_lm.base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,190 INFO [train.py:813] codec_lm.base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,190 INFO [train.py:813] codec_lm.base_model.model.model.layers.7.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,191 INFO [train.py:813] codec_lm.base_model.model.model.layers.7.self_attn.k_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,191 INFO [train.py:813] codec_lm.base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,191 INFO [train.py:813] codec_lm.base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,191 INFO [train.py:813] codec_lm.base_model.model.model.layers.7.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,191 INFO [train.py:813] codec_lm.base_model.model.model.layers.7.self_attn.o_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,191 INFO [train.py:813] codec_lm.base_model.model.model.layers.7.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,191 INFO [train.py:813] codec_lm.base_model.model.model.layers.7.mlp.gate_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,191 INFO [train.py:813] codec_lm.base_model.model.model.layers.7.mlp.up_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,191 INFO [train.py:813] codec_lm.base_model.model.model.layers.7.mlp.up_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,191 INFO [train.py:813] codec_lm.base_model.model.model.layers.7.mlp.down_proj.lora_A.default.weight: torch.Size([64, 2048])
2025-04-24 10:12:44,191 INFO [train.py:813] codec_lm.base_model.model.model.layers.7.mlp.down_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,191 INFO [train.py:813] codec_lm.base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,191 INFO [train.py:813] codec_lm.base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,191 INFO [train.py:813] codec_lm.base_model.model.model.layers.8.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,191 INFO [train.py:813] codec_lm.base_model.model.model.layers.8.self_attn.k_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,191 INFO [train.py:813] codec_lm.base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,191 INFO [train.py:813] codec_lm.base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,191 INFO [train.py:813] codec_lm.base_model.model.model.layers.8.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,191 INFO [train.py:813] codec_lm.base_model.model.model.layers.8.self_attn.o_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,192 INFO [train.py:813] codec_lm.base_model.model.model.layers.8.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,192 INFO [train.py:813] codec_lm.base_model.model.model.layers.8.mlp.gate_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,192 INFO [train.py:813] codec_lm.base_model.model.model.layers.8.mlp.up_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,192 INFO [train.py:813] codec_lm.base_model.model.model.layers.8.mlp.up_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,192 INFO [train.py:813] codec_lm.base_model.model.model.layers.8.mlp.down_proj.lora_A.default.weight: torch.Size([64, 2048])
2025-04-24 10:12:44,192 INFO [train.py:813] codec_lm.base_model.model.model.layers.8.mlp.down_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,192 INFO [train.py:813] codec_lm.base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,192 INFO [train.py:813] codec_lm.base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,192 INFO [train.py:813] codec_lm.base_model.model.model.layers.9.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,192 INFO [train.py:813] codec_lm.base_model.model.model.layers.9.self_attn.k_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,192 INFO [train.py:813] codec_lm.base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,192 INFO [train.py:813] codec_lm.base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,192 INFO [train.py:813] codec_lm.base_model.model.model.layers.9.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,192 INFO [train.py:813] codec_lm.base_model.model.model.layers.9.self_attn.o_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,192 INFO [train.py:813] codec_lm.base_model.model.model.layers.9.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,192 INFO [train.py:813] codec_lm.base_model.model.model.layers.9.mlp.gate_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,192 INFO [train.py:813] codec_lm.base_model.model.model.layers.9.mlp.up_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,192 INFO [train.py:813] codec_lm.base_model.model.model.layers.9.mlp.up_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,192 INFO [train.py:813] codec_lm.base_model.model.model.layers.9.mlp.down_proj.lora_A.default.weight: torch.Size([64, 2048])
2025-04-24 10:12:44,192 INFO [train.py:813] codec_lm.base_model.model.model.layers.9.mlp.down_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,193 INFO [train.py:813] codec_lm.base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,193 INFO [train.py:813] codec_lm.base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,193 INFO [train.py:813] codec_lm.base_model.model.model.layers.10.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,193 INFO [train.py:813] codec_lm.base_model.model.model.layers.10.self_attn.k_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,193 INFO [train.py:813] codec_lm.base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,193 INFO [train.py:813] codec_lm.base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,193 INFO [train.py:813] codec_lm.base_model.model.model.layers.10.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,193 INFO [train.py:813] codec_lm.base_model.model.model.layers.10.self_attn.o_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,193 INFO [train.py:813] codec_lm.base_model.model.model.layers.10.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,193 INFO [train.py:813] codec_lm.base_model.model.model.layers.10.mlp.gate_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,193 INFO [train.py:813] codec_lm.base_model.model.model.layers.10.mlp.up_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,193 INFO [train.py:813] codec_lm.base_model.model.model.layers.10.mlp.up_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,193 INFO [train.py:813] codec_lm.base_model.model.model.layers.10.mlp.down_proj.lora_A.default.weight: torch.Size([64, 2048])
2025-04-24 10:12:44,193 INFO [train.py:813] codec_lm.base_model.model.model.layers.10.mlp.down_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,193 INFO [train.py:813] codec_lm.base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,193 INFO [train.py:813] codec_lm.base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,193 INFO [train.py:813] codec_lm.base_model.model.model.layers.11.self_attn.k_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,193 INFO [train.py:813] codec_lm.base_model.model.model.layers.11.self_attn.k_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,193 INFO [train.py:813] codec_lm.base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,194 INFO [train.py:813] codec_lm.base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,194 INFO [train.py:813] codec_lm.base_model.model.model.layers.11.self_attn.o_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,194 INFO [train.py:813] codec_lm.base_model.model.model.layers.11.self_attn.o_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,194 INFO [train.py:813] codec_lm.base_model.model.model.layers.11.mlp.gate_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,194 INFO [train.py:813] codec_lm.base_model.model.model.layers.11.mlp.gate_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,194 INFO [train.py:813] codec_lm.base_model.model.model.layers.11.mlp.up_proj.lora_A.default.weight: torch.Size([64, 1024])
2025-04-24 10:12:44,194 INFO [train.py:813] codec_lm.base_model.model.model.layers.11.mlp.up_proj.lora_B.default.weight: torch.Size([2048, 64])
2025-04-24 10:12:44,194 INFO [train.py:813] codec_lm.base_model.model.model.layers.11.mlp.down_proj.lora_A.default.weight: torch.Size([64, 2048])
2025-04-24 10:12:44,194 INFO [train.py:813] codec_lm.base_model.model.model.layers.11.mlp.down_proj.lora_B.default.weight: torch.Size([1024, 64])
2025-04-24 10:12:44,194 INFO [train.py:813] speech_token_projector.weight: torch.Size([1024, 896])
2025-04-24 10:12:44,194 INFO [train.py:813] speech_token_projector.bias: torch.Size([1024])
2025-04-24 10:12:44,194 INFO [train.py:813] codec_lm_head.weight: torch.Size([4100, 1024])
2025-04-24 10:12:44,194 INFO [train.py:813] codec_lm_head.bias: torch.Size([4100])
2025-04-24 10:12:44,194 INFO [train.py:819] Device: cuda:0
2025-04-24 10:12:44,922 INFO [train.py:823] Using DeepSpeed
2025-04-24 10:12:46,690 INFO [data_module.py:445] About to get train cuts
2025-04-24 10:12:46,693 INFO [data_module.py:250] Disable MUSAN
2025-04-24 10:12:46,693 INFO [data_module.py:268] Enable SpecAugment
2025-04-24 10:12:46,693 INFO [data_module.py:269] Time warp factor: 80
2025-04-24 10:12:46,693 INFO [data_module.py:279] Num frame mask: 10
2025-04-24 10:12:46,693 INFO [data_module.py:292] About to create train dataset
2025-04-24 10:12:46,693 INFO [data_module.py:319] Using DynamicBucketingSampler.
2025-04-24 10:12:47,691 INFO [data_module.py:336] About to create train dataloader
2025-04-24 10:12:47,692 INFO [data_module.py:436] About to get test cuts
2025-04-24 10:12:47,693 INFO [data_module.py:365] About to create dev dataset
2025-04-24 10:12:47,781 INFO [data_module.py:379] About to create dev dataloader
2025-04-24 10:12:47,788 INFO [train.py:875] start training from epoch 1
2025-04-24 10:13:18,332 INFO [train.py:539] Computing validation loss