/root/miniconda3/envs/train_vlm/bin/python3.10: can't open file '/root/ai-project/Vintern/internvl/train/internvl_chat_finetune.py': [Errno 2] No such file or directory E0703 09:24:57.109000 138100931848000 torch/distributed/elastic/multiprocessing/api.py:833] failed (exitcode: 2) local_rank: 0 (pid: 31203) of binary: /root/miniconda3/envs/train_vlm/bin/python3.10 Traceback (most recent call last): File "/root/miniconda3/envs/train_vlm/bin/torchrun", line 6, in sys.exit(main()) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 348, in wrapper return f(*args, **kwargs) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/run.py", line 901, in main run(args) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/run.py", line 892, in run elastic_launch( File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 133, in __call__ return launch_agent(self._config, self._entrypoint, list(args)) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 264, in launch_agent raise ChildFailedError( torch.distributed.elastic.multiprocessing.errors.ChildFailedError: ============================================================ internvl/train/internvl_chat_finetune.py FAILED ------------------------------------------------------------ Failures: ------------------------------------------------------------ Root Cause (first observed failure): [0]: time : 2026-07-03_09:24:57 host : data-ai-gpu-01 rank : 0 (local_rank: 0) exitcode : 2 (pid: 31203) error_file: traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html ============================================================ /root/miniconda3/envs/train_vlm/bin/python3.10: can't open file '/root/ai-project/Vintern/internvl/train/internvl_chat_finetune.py': [Errno 2] No such file or directory E0703 09:25:53.714000 130563156473664 torch/distributed/elastic/multiprocessing/api.py:833] failed (exitcode: 2) local_rank: 0 (pid: 31222) of binary: /root/miniconda3/envs/train_vlm/bin/python3.10 Traceback (most recent call last): File "/root/miniconda3/envs/train_vlm/bin/torchrun", line 6, in sys.exit(main()) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 348, in wrapper return f(*args, **kwargs) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/run.py", line 901, in main run(args) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/run.py", line 892, in run elastic_launch( File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 133, in __call__ return launch_agent(self._config, self._entrypoint, list(args)) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 264, in launch_agent raise ChildFailedError( torch.distributed.elastic.multiprocessing.errors.ChildFailedError: ============================================================ internvl/train/internvl_chat_finetune.py FAILED ------------------------------------------------------------ Failures: ------------------------------------------------------------ Root Cause (first observed failure): [0]: time : 2026-07-03_09:25:53 host : data-ai-gpu-01 rank : 0 (local_rank: 0) exitcode : 2 (pid: 31222) error_file: traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html ============================================================ /root/miniconda3/envs/train_vlm/bin/python3.10: can't open file '/root/ai-project/Vintern/internvl_chatinternvl/train/internvl_chat_finetune.py': [Errno 2] No such file or directory E0703 09:30:47.026000 128480840795968 torch/distributed/elastic/multiprocessing/api.py:833] failed (exitcode: 2) local_rank: 0 (pid: 31255) of binary: /root/miniconda3/envs/train_vlm/bin/python3.10 Traceback (most recent call last): File "/root/miniconda3/envs/train_vlm/bin/torchrun", line 6, in sys.exit(main()) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 348, in wrapper return f(*args, **kwargs) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/run.py", line 901, in main run(args) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/run.py", line 892, in run elastic_launch( File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 133, in __call__ return launch_agent(self._config, self._entrypoint, list(args)) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 264, in launch_agent raise ChildFailedError( torch.distributed.elastic.multiprocessing.errors.ChildFailedError: ============================================================ /root/ai-project/Vintern/internvl_chatinternvl/train/internvl_chat_finetune.py FAILED ------------------------------------------------------------ Failures: ------------------------------------------------------------ Root Cause (first observed failure): [0]: time : 2026-07-03_09:30:47 host : data-ai-gpu-01 rank : 0 (local_rank: 0) exitcode : 2 (pid: 31255) error_file: traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html ============================================================ The cache for model files in Transformers v4.22.0 has been updated. Migrating your old cache. This is a one-time only operation. You can interrupt this and resume the migration later on by calling `transformers.utils.move_cache()`. 0it [00:00, ?it/s] 0it [00:00, ?it/s] /root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/cuda/__init__.py:128: UserWarning: CUDA initialization: Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 803: system has unsupported display driver / cuda driver combination (Triggered internally at ../c10/cuda/CUDAFunctions.cpp:108.) return torch._C._cuda_getDeviceCount() > 0 [2026-07-03 09:31:35,988] [WARNING] [real_accelerator.py:199:get_accelerator] Setting accelerator to CPU. If you have GPU or other accelerator, we were unable to detect it. /root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/cuda/__init__.py:128: UserWarning: CUDA initialization: Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 803: system has unsupported display driver / cuda driver combination (Triggered internally at ../c10/cuda/CUDAFunctions.cpp:108.) return torch._C._cuda_getDeviceCount() > 0 /root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/timm/models/layers/__init__.py:49: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning) Traceback (most recent call last): File "/root/ai-project/Vintern/internvl_chat/internvl/train/internvl_chat_finetune.py", line 32, in from internvl.train.dataset import (ConcatDataset, TCSLoader, File "/root/ai-project/Vintern/internvl_chat/internvl/train/dataset.py", line 10, in import cv2 ModuleNotFoundError: No module named 'cv2' E0703 09:31:46.332000 132150586988352 torch/distributed/elastic/multiprocessing/api.py:833] failed (exitcode: 1) local_rank: 0 (pid: 31273) of binary: /root/miniconda3/envs/train_vlm/bin/python3.10 Traceback (most recent call last): File "/root/miniconda3/envs/train_vlm/bin/torchrun", line 6, in sys.exit(main()) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 348, in wrapper return f(*args, **kwargs) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/run.py", line 901, in main run(args) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/run.py", line 892, in run elastic_launch( File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 133, in __call__ return launch_agent(self._config, self._entrypoint, list(args)) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 264, in launch_agent raise ChildFailedError( torch.distributed.elastic.multiprocessing.errors.ChildFailedError: ============================================================ /root/ai-project/Vintern/internvl_chat/internvl/train/internvl_chat_finetune.py FAILED ------------------------------------------------------------ Failures: ------------------------------------------------------------ Root Cause (first observed failure): [0]: time : 2026-07-03_09:31:46 host : data-ai-gpu-01 rank : 0 (local_rank: 0) exitcode : 1 (pid: 31273) error_file: traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html ============================================================ /root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/cuda/__init__.py:128: UserWarning: CUDA initialization: Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 803: system has unsupported display driver / cuda driver combination (Triggered internally at ../c10/cuda/CUDAFunctions.cpp:108.) return torch._C._cuda_getDeviceCount() > 0 [2026-07-03 09:32:20,885] [WARNING] [real_accelerator.py:199:get_accelerator] Setting accelerator to CPU. If you have GPU or other accelerator, we were unable to detect it. /root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/cuda/__init__.py:128: UserWarning: CUDA initialization: Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 803: system has unsupported display driver / cuda driver combination (Triggered internally at ../c10/cuda/CUDAFunctions.cpp:108.) return torch._C._cuda_getDeviceCount() > 0 /root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/timm/models/layers/__init__.py:49: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning) Traceback (most recent call last): File "/root/ai-project/Vintern/internvl_chat/internvl/train/internvl_chat_finetune.py", line 32, in from internvl.train.dataset import (ConcatDataset, TCSLoader, File "/root/ai-project/Vintern/internvl_chat/internvl/train/dataset.py", line 11, in import imageio ModuleNotFoundError: No module named 'imageio' E0703 09:32:32.354000 139803546371904 torch/distributed/elastic/multiprocessing/api.py:833] failed (exitcode: 1) local_rank: 0 (pid: 31354) of binary: /root/miniconda3/envs/train_vlm/bin/python3.10 Traceback (most recent call last): File "/root/miniconda3/envs/train_vlm/bin/torchrun", line 6, in sys.exit(main()) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 348, in wrapper return f(*args, **kwargs) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/run.py", line 901, in main run(args) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/run.py", line 892, in run elastic_launch( File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 133, in __call__ return launch_agent(self._config, self._entrypoint, list(args)) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 264, in launch_agent raise ChildFailedError( torch.distributed.elastic.multiprocessing.errors.ChildFailedError: ============================================================ /root/ai-project/Vintern/internvl_chat/internvl/train/internvl_chat_finetune.py FAILED ------------------------------------------------------------ Failures: ------------------------------------------------------------ Root Cause (first observed failure): [0]: time : 2026-07-03_09:32:32 host : data-ai-gpu-01 rank : 0 (local_rank: 0) exitcode : 1 (pid: 31354) error_file: traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html ============================================================ /root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/cuda/__init__.py:128: UserWarning: CUDA initialization: Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 803: system has unsupported display driver / cuda driver combination (Triggered internally at ../c10/cuda/CUDAFunctions.cpp:108.) return torch._C._cuda_getDeviceCount() > 0 [2026-07-03 09:33:03,430] [WARNING] [real_accelerator.py:199:get_accelerator] Setting accelerator to CPU. If you have GPU or other accelerator, we were unable to detect it. /root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/cuda/__init__.py:128: UserWarning: CUDA initialization: Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 803: system has unsupported display driver / cuda driver combination (Triggered internally at ../c10/cuda/CUDAFunctions.cpp:108.) return torch._C._cuda_getDeviceCount() > 0 /root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/timm/models/layers/__init__.py:49: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning) petrel_client is not installed. If you read data locally instead of from ceph, ignore it. Replace train sampler!! petrel_client is not installed. Using PIL to load images. Traceback (most recent call last): File "/root/ai-project/Vintern/internvl_chat/internvl/train/internvl_chat_finetune.py", line 847, in main() File "/root/ai-project/Vintern/internvl_chat/internvl/train/internvl_chat_finetune.py", line 608, in main init_dist(launcher=launcher, backend='nccl') File "/root/ai-project/Vintern/internvl_chat/internvl/dist_utils.py", line 36, in init_dist _init_dist_pytorch(backend, **kwargs) File "/root/ai-project/Vintern/internvl_chat/internvl/dist_utils.py", line 49, in _init_dist_pytorch torch.cuda.set_device(rank % num_gpus) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/cuda/__init__.py", line 420, in set_device torch._C._cuda_setDevice(device) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/cuda/__init__.py", line 314, in _lazy_init torch._C._cuda_init() RuntimeError: Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 803: system has unsupported display driver / cuda driver combination E0703 09:33:12.348000 129426906138432 torch/distributed/elastic/multiprocessing/api.py:833] failed (exitcode: 1) local_rank: 0 (pid: 31441) of binary: /root/miniconda3/envs/train_vlm/bin/python3.10 Traceback (most recent call last): File "/root/miniconda3/envs/train_vlm/bin/torchrun", line 6, in sys.exit(main()) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 348, in wrapper return f(*args, **kwargs) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/run.py", line 901, in main run(args) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/run.py", line 892, in run elastic_launch( File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 133, in __call__ return launch_agent(self._config, self._entrypoint, list(args)) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 264, in launch_agent raise ChildFailedError( torch.distributed.elastic.multiprocessing.errors.ChildFailedError: ============================================================ /root/ai-project/Vintern/internvl_chat/internvl/train/internvl_chat_finetune.py FAILED ------------------------------------------------------------ Failures: ------------------------------------------------------------ Root Cause (first observed failure): [0]: time : 2026-07-03_09:33:12 host : data-ai-gpu-01 rank : 0 (local_rank: 0) exitcode : 1 (pid: 31441) error_file: traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html ============================================================ /root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/timm/models/layers/__init__.py:49: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning) petrel_client is not installed. If you read data locally instead of from ceph, ignore it. Replace train sampler!! petrel_client is not installed. Using PIL to load images. 07/03/2026 09:42:04 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False 07/03/2026 09:42:04 - INFO - __main__ - Training/evaluation parameters TrainingArguments( _n_gpu=1, accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, adafactor=False, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, auto_find_batch_size=False, batch_eval_metrics=False, bf16=True, bf16_full_eval=False, data_seed=None, dataloader_drop_last=False, dataloader_num_workers=4, dataloader_persistent_workers=False, dataloader_pin_memory=True, dataloader_prefetch_factor=None, ddp_backend=None, ddp_broadcast_buffers=None, ddp_bucket_cap_mb=None, ddp_find_unused_parameters=None, ddp_timeout=1800, debug=[], deepspeed=zero_stage1_config.json, disable_tqdm=False, dispatch_batches=None, do_eval=False, do_predict=False, do_train=True, eval_accumulation_steps=None, eval_delay=0, eval_do_concat_batches=True, eval_steps=None, eval_strategy=no, evaluation_strategy=None, fp16=False, fp16_backend=auto, fp16_full_eval=False, fp16_opt_level=O1, fsdp=[], fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_min_num_params=0, fsdp_transformer_layer_cls_to_wrap=None, full_determinism=False, gradient_accumulation_steps=16, gradient_checkpointing=False, gradient_checkpointing_kwargs=None, greater_is_better=None, group_by_length=True, half_precision_backend=auto, hub_always_push=False, hub_model_id=None, hub_private_repo=False, hub_strategy=every_save, hub_token=, ignore_data_skip=False, include_inputs_for_metrics=False, include_num_input_tokens_seen=False, include_tokens_per_second=False, jit_mode_eval=False, label_names=None, label_smoothing_factor=0.0, learning_rate=0.0002, length_column_name=length, load_best_model_at_end=False, local_rank=0, log_level=passive, log_level_replica=warning, log_on_each_node=True, logging_dir=/root/ai-project/Vintern/vlm_training/runs/Jul03_09-42-04_data-ai-gpu-01, logging_first_step=False, logging_nan_inf_filter=True, logging_steps=10, logging_strategy=steps, lr_scheduler_kwargs={}, lr_scheduler_type=cosine, max_grad_norm=1.0, max_steps=-1, metric_for_best_model=None, mp_parameters=, neftune_noise_alpha=None, no_cuda=False, num_train_epochs=1.0, optim=adamw_torch, optim_args=None, optim_target_modules=None, output_dir=/root/ai-project/Vintern/vlm_training, overwrite_output_dir=True, past_index=-1, per_device_eval_batch_size=8, per_device_train_batch_size=1, prediction_loss_only=False, push_to_hub=False, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=, ray_scope=last, remove_unused_columns=True, report_to=['wandb'], restore_callback_states_from_checkpoint=False, resume_from_checkpoint=None, run_name=vintern_lora_card, save_on_each_node=False, save_only_model=False, save_safetensors=True, save_steps=500, save_strategy=steps, save_total_limit=2, seed=42, skip_memory_metrics=True, split_batches=None, tf32=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, torchdynamo=None, tpu_metrics_debug=False, tpu_num_cores=None, use_cpu=False, use_ipex=False, use_legacy_prediction_loop=False, use_mps_device=False, warmup_ratio=0.03, warmup_steps=0, weight_decay=0.01, ) 07/03/2026 09:42:04 - INFO - __main__ - Loading Tokenizer: /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5 [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:42:04,130 >> loading file vocab.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:42:04,131 >> loading file merges.txt [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:42:04,131 >> loading file added_tokens.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:42:04,131 >> loading file special_tokens_map.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:42:04,131 >> loading file tokenizer_config.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:42:04,131 >> loading file tokenizer.json [WARNING|logging.py:314] 2026-07-03 09:42:04,523 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 07/03/2026 09:42:04 - INFO - __main__ - Loading InternVLChatModel... [INFO|configuration_utils.py:731] 2026-07-03 09:42:04,532 >> loading configuration file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/config.json [INFO|configuration_utils.py:796] 2026-07-03 09:42:04,534 >> Model config InternVLChatConfig { "_commit_hash": null, "architectures": [ "InternVLChatModel" ], "auto_map": { "AutoConfig": "5CD-AI/Vintern-1B-v3_5--configuration_internvl_chat.InternVLChatConfig", "AutoModel": "5CD-AI/Vintern-1B-v3_5--modeling_internvl_chat.InternVLChatModel", "AutoModelForCausalLM": "5CD-AI/Vintern-1B-v3_5--modeling_internvl_chat.InternVLChatModel" }, "downsample_ratio": 0.5, "dynamic_image_size": true, "force_image_size": 448, "llm_config": { "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct", "add_cross_attention": false, "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 151643, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 151645, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 896, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 4864, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 32768, "max_window_layers": 21, "min_length": 0, "model_type": "qwen2", "no_repeat_ngram_size": 0, "num_attention_heads": 14, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 24, "num_key_value_heads": 2, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sep_token_id": null, "sliding_window": 32768, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.41.2", "typical_p": 1.0, "use_bfloat16": true, "use_cache": false, "use_sliding_window": false, "vocab_size": 151674 }, "max_dynamic_patch": 4, "min_dynamic_patch": 1, "model_type": "internvl_chat", "pad2square": false, "ps_version": "v2", "select_layer": -1, "template": "Hermes-2", "torch_dtype": "float32", "transformers_version": null, "use_backbone_lora": 0, "use_llm_lora": 0, "use_thumbnail": true, "vision_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": [ "InternVisionModel" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "drop_path_rate": 0.0, "dropout": 0.0, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "gelu", "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 448, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 4096, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-06, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "intern_vit_6b", "no_repeat_ngram_size": 0, "norm_type": "layer_norm", "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 24, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "prefix": null, "problem_type": null, "pruned_heads": {}, "qk_normalization": false, "qkv_bias": true, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.41.2", "typical_p": 1.0, "use_bfloat16": true, "use_flash_attn": false } } 07/03/2026 09:42:04 - INFO - __main__ - Using flash_attention_2 for LLaMA [INFO|modeling_utils.py:3471] 2026-07-03 09:42:04,535 >> loading weights file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/model.safetensors [INFO|modeling_utils.py:1519] 2026-07-03 09:42:05,383 >> Instantiating InternVLChatModel model under default dtype torch.bfloat16. [INFO|configuration_utils.py:962] 2026-07-03 09:42:05,384 >> Generate config GenerationConfig {} [INFO|configuration_utils.py:962] 2026-07-03 09:42:05,441 >> Generate config GenerationConfig { "bos_token_id": 151643, "eos_token_id": 151645, "use_cache": false } [INFO|modeling_utils.py:4280] 2026-07-03 09:42:16,406 >> All model checkpoint weights were used when initializing InternVLChatModel. [INFO|modeling_utils.py:4288] 2026-07-03 09:42:16,407 >> All the weights of InternVLChatModel were initialized from the model checkpoint at /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5. If your task is similar to the task the model of the checkpoint was trained on, you can already use InternVLChatModel for predictions without further training. [INFO|configuration_utils.py:915] 2026-07-03 09:42:16,425 >> loading configuration file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/generation_config.json [INFO|configuration_utils.py:962] 2026-07-03 09:42:16,426 >> Generate config GenerationConfig { "eos_token_id": [ 151644, 151645, 151643 ] } 07/03/2026 09:42:16 - INFO - __main__ - Finished 07/03/2026 09:42:16 - INFO - __main__ - model.config.force_image_size: 448 07/03/2026 09:42:16 - INFO - __main__ - data_args.force_image_size: 448 07/03/2026 09:42:16 - INFO - __main__ - model.config.vision_config.image_size: 448 [rank0]: Traceback (most recent call last): [rank0]: File "/root/ai-project/Vintern/internvl_chat/internvl/train/internvl_chat_finetune.py", line 847, in [rank0]: main() [rank0]: File "/root/ai-project/Vintern/internvl_chat/internvl/train/internvl_chat_finetune.py", line 765, in main [rank0]: train_dataset = build_datasets( [rank0]: File "/root/ai-project/Vintern/internvl_chat/internvl/train/internvl_chat_finetune.py", line 562, in build_datasets [rank0]: ds_collections = json.loads(open(data_args.meta_path).read()) [rank0]: File "/root/miniconda3/envs/train_vlm/lib/python3.10/json/__init__.py", line 346, in loads [rank0]: return _default_decoder.decode(s) [rank0]: File "/root/miniconda3/envs/train_vlm/lib/python3.10/json/decoder.py", line 337, in decode [rank0]: obj, end = self.raw_decode(s, idx=_w(s, 0).end()) [rank0]: File "/root/miniconda3/envs/train_vlm/lib/python3.10/json/decoder.py", line 355, in raw_decode [rank0]: raise JSONDecodeError("Expecting value", s, err.value) from None [rank0]: json.decoder.JSONDecodeError: Expecting value: line 5 column 21 (char 163) E0703 09:42:18.803000 138079627822912 torch/distributed/elastic/multiprocessing/api.py:833] failed (exitcode: 1) local_rank: 0 (pid: 31676) of binary: /root/miniconda3/envs/train_vlm/bin/python3.10 Traceback (most recent call last): File "/root/miniconda3/envs/train_vlm/bin/torchrun", line 6, in sys.exit(main()) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 348, in wrapper return f(*args, **kwargs) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/run.py", line 901, in main run(args) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/run.py", line 892, in run elastic_launch( File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 133, in __call__ return launch_agent(self._config, self._entrypoint, list(args)) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 264, in launch_agent raise ChildFailedError( torch.distributed.elastic.multiprocessing.errors.ChildFailedError: ============================================================ /root/ai-project/Vintern/internvl_chat/internvl/train/internvl_chat_finetune.py FAILED ------------------------------------------------------------ Failures: ------------------------------------------------------------ Root Cause (first observed failure): [0]: time : 2026-07-03_09:42:18 host : data-ai-gpu-01 rank : 0 (local_rank: 0) exitcode : 1 (pid: 31676) error_file: traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html ============================================================ /root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/timm/models/layers/__init__.py:49: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning) petrel_client is not installed. If you read data locally instead of from ceph, ignore it. Replace train sampler!! petrel_client is not installed. Using PIL to load images. 07/03/2026 09:45:58 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False 07/03/2026 09:45:58 - INFO - __main__ - Training/evaluation parameters TrainingArguments( _n_gpu=1, accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, adafactor=False, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, auto_find_batch_size=False, batch_eval_metrics=False, bf16=True, bf16_full_eval=False, data_seed=None, dataloader_drop_last=False, dataloader_num_workers=4, dataloader_persistent_workers=False, dataloader_pin_memory=True, dataloader_prefetch_factor=None, ddp_backend=None, ddp_broadcast_buffers=None, ddp_bucket_cap_mb=None, ddp_find_unused_parameters=None, ddp_timeout=1800, debug=[], deepspeed=zero_stage1_config.json, disable_tqdm=False, dispatch_batches=None, do_eval=False, do_predict=False, do_train=True, eval_accumulation_steps=None, eval_delay=0, eval_do_concat_batches=True, eval_steps=None, eval_strategy=no, evaluation_strategy=None, fp16=False, fp16_backend=auto, fp16_full_eval=False, fp16_opt_level=O1, fsdp=[], fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_min_num_params=0, fsdp_transformer_layer_cls_to_wrap=None, full_determinism=False, gradient_accumulation_steps=16, gradient_checkpointing=False, gradient_checkpointing_kwargs=None, greater_is_better=None, group_by_length=True, half_precision_backend=auto, hub_always_push=False, hub_model_id=None, hub_private_repo=False, hub_strategy=every_save, hub_token=, ignore_data_skip=False, include_inputs_for_metrics=False, include_num_input_tokens_seen=False, include_tokens_per_second=False, jit_mode_eval=False, label_names=None, label_smoothing_factor=0.0, learning_rate=0.0002, length_column_name=length, load_best_model_at_end=False, local_rank=0, log_level=passive, log_level_replica=warning, log_on_each_node=True, logging_dir=/root/ai-project/Vintern/vlm_training/runs/Jul03_09-45-58_data-ai-gpu-01, logging_first_step=False, logging_nan_inf_filter=True, logging_steps=10, logging_strategy=steps, lr_scheduler_kwargs={}, lr_scheduler_type=cosine, max_grad_norm=1.0, max_steps=-1, metric_for_best_model=None, mp_parameters=, neftune_noise_alpha=None, no_cuda=False, num_train_epochs=1.0, optim=adamw_torch, optim_args=None, optim_target_modules=None, output_dir=/root/ai-project/Vintern/vlm_training, overwrite_output_dir=True, past_index=-1, per_device_eval_batch_size=8, per_device_train_batch_size=1, prediction_loss_only=False, push_to_hub=False, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=, ray_scope=last, remove_unused_columns=True, report_to=['wandb'], restore_callback_states_from_checkpoint=False, resume_from_checkpoint=None, run_name=vintern_lora_card, save_on_each_node=False, save_only_model=False, save_safetensors=True, save_steps=500, save_strategy=steps, save_total_limit=2, seed=42, skip_memory_metrics=True, split_batches=None, tf32=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, torchdynamo=None, tpu_metrics_debug=False, tpu_num_cores=None, use_cpu=False, use_ipex=False, use_legacy_prediction_loop=False, use_mps_device=False, warmup_ratio=0.03, warmup_steps=0, weight_decay=0.01, ) 07/03/2026 09:45:58 - INFO - __main__ - Loading Tokenizer: /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5 [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:45:58,889 >> loading file vocab.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:45:58,889 >> loading file merges.txt [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:45:58,889 >> loading file added_tokens.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:45:58,889 >> loading file special_tokens_map.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:45:58,889 >> loading file tokenizer_config.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:45:58,889 >> loading file tokenizer.json [WARNING|logging.py:314] 2026-07-03 09:45:59,893 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 07/03/2026 09:45:59 - INFO - __main__ - Loading InternVLChatModel... [INFO|configuration_utils.py:731] 2026-07-03 09:45:59,928 >> loading configuration file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/config.json [INFO|configuration_utils.py:796] 2026-07-03 09:45:59,931 >> Model config InternVLChatConfig { "_commit_hash": null, "architectures": [ "InternVLChatModel" ], "auto_map": { "AutoConfig": "5CD-AI/Vintern-1B-v3_5--configuration_internvl_chat.InternVLChatConfig", "AutoModel": "5CD-AI/Vintern-1B-v3_5--modeling_internvl_chat.InternVLChatModel", "AutoModelForCausalLM": "5CD-AI/Vintern-1B-v3_5--modeling_internvl_chat.InternVLChatModel" }, "downsample_ratio": 0.5, "dynamic_image_size": true, "force_image_size": 448, "llm_config": { "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct", "add_cross_attention": false, "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 151643, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 151645, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 896, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 4864, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 32768, "max_window_layers": 21, "min_length": 0, "model_type": "qwen2", "no_repeat_ngram_size": 0, "num_attention_heads": 14, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 24, "num_key_value_heads": 2, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sep_token_id": null, "sliding_window": 32768, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.41.2", "typical_p": 1.0, "use_bfloat16": true, "use_cache": false, "use_sliding_window": false, "vocab_size": 151674 }, "max_dynamic_patch": 4, "min_dynamic_patch": 1, "model_type": "internvl_chat", "pad2square": false, "ps_version": "v2", "select_layer": -1, "template": "Hermes-2", "torch_dtype": "float32", "transformers_version": null, "use_backbone_lora": 0, "use_llm_lora": 0, "use_thumbnail": true, "vision_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": [ "InternVisionModel" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "drop_path_rate": 0.0, "dropout": 0.0, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "gelu", "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 448, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 4096, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-06, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "intern_vit_6b", "no_repeat_ngram_size": 0, "norm_type": "layer_norm", "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 24, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "prefix": null, "problem_type": null, "pruned_heads": {}, "qk_normalization": false, "qkv_bias": true, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.41.2", "typical_p": 1.0, "use_bfloat16": true, "use_flash_attn": false } } 07/03/2026 09:45:59 - INFO - __main__ - Using flash_attention_2 for LLaMA [INFO|modeling_utils.py:3471] 2026-07-03 09:45:59,933 >> loading weights file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/model.safetensors [INFO|modeling_utils.py:1519] 2026-07-03 09:45:59,962 >> Instantiating InternVLChatModel model under default dtype torch.bfloat16. [INFO|configuration_utils.py:962] 2026-07-03 09:45:59,964 >> Generate config GenerationConfig {} [INFO|configuration_utils.py:962] 2026-07-03 09:46:00,035 >> Generate config GenerationConfig { "bos_token_id": 151643, "eos_token_id": 151645, "use_cache": false } [INFO|modeling_utils.py:4280] 2026-07-03 09:46:02,099 >> All model checkpoint weights were used when initializing InternVLChatModel. [INFO|modeling_utils.py:4288] 2026-07-03 09:46:02,099 >> All the weights of InternVLChatModel were initialized from the model checkpoint at /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5. If your task is similar to the task the model of the checkpoint was trained on, you can already use InternVLChatModel for predictions without further training. [INFO|configuration_utils.py:915] 2026-07-03 09:46:02,104 >> loading configuration file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/generation_config.json [INFO|configuration_utils.py:962] 2026-07-03 09:46:02,104 >> Generate config GenerationConfig { "eos_token_id": [ 151644, 151645, 151643 ] } 07/03/2026 09:46:02 - INFO - __main__ - Finished 07/03/2026 09:46:02 - INFO - __main__ - model.config.force_image_size: 448 07/03/2026 09:46:02 - INFO - __main__ - data_args.force_image_size: 448 07/03/2026 09:46:02 - INFO - __main__ - model.config.vision_config.image_size: 448 [rank0]: Traceback (most recent call last): [rank0]: File "/root/ai-project/Vintern/internvl_chat/internvl/train/internvl_chat_finetune.py", line 847, in [rank0]: main() [rank0]: File "/root/ai-project/Vintern/internvl_chat/internvl/train/internvl_chat_finetune.py", line 765, in main [rank0]: train_dataset = build_datasets( [rank0]: File "/root/ai-project/Vintern/internvl_chat/internvl/train/internvl_chat_finetune.py", line 562, in build_datasets [rank0]: ds_collections = json.loads(open(data_args.meta_path).read()) [rank0]: File "/root/miniconda3/envs/train_vlm/lib/python3.10/json/__init__.py", line 346, in loads [rank0]: return _default_decoder.decode(s) [rank0]: File "/root/miniconda3/envs/train_vlm/lib/python3.10/json/decoder.py", line 337, in decode [rank0]: obj, end = self.raw_decode(s, idx=_w(s, 0).end()) [rank0]: File "/root/miniconda3/envs/train_vlm/lib/python3.10/json/decoder.py", line 355, in raw_decode [rank0]: raise JSONDecodeError("Expecting value", s, err.value) from None [rank0]: json.decoder.JSONDecodeError: Expecting value: line 5 column 21 (char 175) E0703 09:46:03.625000 140571859314496 torch/distributed/elastic/multiprocessing/api.py:833] failed (exitcode: 1) local_rank: 0 (pid: 31802) of binary: /root/miniconda3/envs/train_vlm/bin/python3.10 Traceback (most recent call last): File "/root/miniconda3/envs/train_vlm/bin/torchrun", line 6, in sys.exit(main()) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 348, in wrapper return f(*args, **kwargs) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/run.py", line 901, in main run(args) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/run.py", line 892, in run elastic_launch( File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 133, in __call__ return launch_agent(self._config, self._entrypoint, list(args)) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 264, in launch_agent raise ChildFailedError( torch.distributed.elastic.multiprocessing.errors.ChildFailedError: ============================================================ /root/ai-project/Vintern/internvl_chat/internvl/train/internvl_chat_finetune.py FAILED ------------------------------------------------------------ Failures: ------------------------------------------------------------ Root Cause (first observed failure): [0]: time : 2026-07-03_09:46:03 host : data-ai-gpu-01 rank : 0 (local_rank: 0) exitcode : 1 (pid: 31802) error_file: traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html ============================================================ Traceback (most recent call last): File "/root/ai-project/Vintern/internvl_chat/internvl/train/internvl_chat_finetune.py", line 18, in from internvl.dist_utils import init_dist ModuleNotFoundError: No module named 'internvl' E0703 09:51:46.399000 129718937388864 torch/distributed/elastic/multiprocessing/api.py:833] failed (exitcode: 1) local_rank: 0 (pid: 31938) of binary: /root/miniconda3/envs/train_vlm/bin/python3.10 Traceback (most recent call last): File "/root/miniconda3/envs/train_vlm/bin/torchrun", line 6, in sys.exit(main()) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 348, in wrapper return f(*args, **kwargs) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/run.py", line 901, in main run(args) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/run.py", line 892, in run elastic_launch( File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 133, in __call__ return launch_agent(self._config, self._entrypoint, list(args)) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 264, in launch_agent raise ChildFailedError( torch.distributed.elastic.multiprocessing.errors.ChildFailedError: ============================================================ /root/ai-project/Vintern/internvl_chat/internvl/train/internvl_chat_finetune.py FAILED ------------------------------------------------------------ Failures: ------------------------------------------------------------ Root Cause (first observed failure): [0]: time : 2026-07-03_09:51:46 host : data-ai-gpu-01 rank : 0 (local_rank: 0) exitcode : 1 (pid: 31938) error_file: traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html ============================================================ /root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/timm/models/layers/__init__.py:49: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning) petrel_client is not installed. If you read data locally instead of from ceph, ignore it. Replace train sampler!! petrel_client is not installed. Using PIL to load images. 07/03/2026 09:52:26 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False 07/03/2026 09:52:26 - INFO - __main__ - Training/evaluation parameters TrainingArguments( _n_gpu=1, accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, adafactor=False, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, auto_find_batch_size=False, batch_eval_metrics=False, bf16=True, bf16_full_eval=False, data_seed=None, dataloader_drop_last=False, dataloader_num_workers=4, dataloader_persistent_workers=False, dataloader_pin_memory=True, dataloader_prefetch_factor=None, ddp_backend=None, ddp_broadcast_buffers=None, ddp_bucket_cap_mb=None, ddp_find_unused_parameters=None, ddp_timeout=1800, debug=[], deepspeed=zero_stage1_config.json, disable_tqdm=False, dispatch_batches=None, do_eval=False, do_predict=False, do_train=True, eval_accumulation_steps=None, eval_delay=0, eval_do_concat_batches=True, eval_steps=None, eval_strategy=no, evaluation_strategy=None, fp16=False, fp16_backend=auto, fp16_full_eval=False, fp16_opt_level=O1, fsdp=[], fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_min_num_params=0, fsdp_transformer_layer_cls_to_wrap=None, full_determinism=False, gradient_accumulation_steps=16, gradient_checkpointing=False, gradient_checkpointing_kwargs=None, greater_is_better=None, group_by_length=True, half_precision_backend=auto, hub_always_push=False, hub_model_id=None, hub_private_repo=False, hub_strategy=every_save, hub_token=, ignore_data_skip=False, include_inputs_for_metrics=False, include_num_input_tokens_seen=False, include_tokens_per_second=False, jit_mode_eval=False, label_names=None, label_smoothing_factor=0.0, learning_rate=0.0002, length_column_name=length, load_best_model_at_end=False, local_rank=0, log_level=passive, log_level_replica=warning, log_on_each_node=True, logging_dir=/root/ai-project/Vintern/vlm_training/runs/Jul03_09-52-26_data-ai-gpu-01, logging_first_step=False, logging_nan_inf_filter=True, logging_steps=10, logging_strategy=steps, lr_scheduler_kwargs={}, lr_scheduler_type=cosine, max_grad_norm=1.0, max_steps=-1, metric_for_best_model=None, mp_parameters=, neftune_noise_alpha=None, no_cuda=False, num_train_epochs=1.0, optim=adamw_torch, optim_args=None, optim_target_modules=None, output_dir=/root/ai-project/Vintern/vlm_training, overwrite_output_dir=True, past_index=-1, per_device_eval_batch_size=8, per_device_train_batch_size=1, prediction_loss_only=False, push_to_hub=False, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=, ray_scope=last, remove_unused_columns=True, report_to=['wandb'], restore_callback_states_from_checkpoint=False, resume_from_checkpoint=None, run_name=vintern_lora_card, save_on_each_node=False, save_only_model=False, save_safetensors=True, save_steps=500, save_strategy=steps, save_total_limit=2, seed=42, skip_memory_metrics=True, split_batches=None, tf32=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, torchdynamo=None, tpu_metrics_debug=False, tpu_num_cores=None, use_cpu=False, use_ipex=False, use_legacy_prediction_loop=False, use_mps_device=False, warmup_ratio=0.03, warmup_steps=0, weight_decay=0.01, ) 07/03/2026 09:52:26 - INFO - __main__ - Loading Tokenizer: /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5 [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:52:26,847 >> loading file vocab.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:52:26,847 >> loading file merges.txt [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:52:26,847 >> loading file added_tokens.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:52:26,847 >> loading file special_tokens_map.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:52:26,847 >> loading file tokenizer_config.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:52:26,847 >> loading file tokenizer.json [WARNING|logging.py:314] 2026-07-03 09:52:27,597 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 07/03/2026 09:52:27 - INFO - __main__ - Loading InternVLChatModel... [INFO|configuration_utils.py:731] 2026-07-03 09:52:27,606 >> loading configuration file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/config.json [INFO|configuration_utils.py:796] 2026-07-03 09:52:27,608 >> Model config InternVLChatConfig { "_commit_hash": null, "architectures": [ "InternVLChatModel" ], "auto_map": { "AutoConfig": "5CD-AI/Vintern-1B-v3_5--configuration_internvl_chat.InternVLChatConfig", "AutoModel": "5CD-AI/Vintern-1B-v3_5--modeling_internvl_chat.InternVLChatModel", "AutoModelForCausalLM": "5CD-AI/Vintern-1B-v3_5--modeling_internvl_chat.InternVLChatModel" }, "downsample_ratio": 0.5, "dynamic_image_size": true, "force_image_size": 448, "llm_config": { "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct", "add_cross_attention": false, "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 151643, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 151645, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 896, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 4864, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 32768, "max_window_layers": 21, "min_length": 0, "model_type": "qwen2", "no_repeat_ngram_size": 0, "num_attention_heads": 14, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 24, "num_key_value_heads": 2, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sep_token_id": null, "sliding_window": 32768, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.41.2", "typical_p": 1.0, "use_bfloat16": true, "use_cache": false, "use_sliding_window": false, "vocab_size": 151674 }, "max_dynamic_patch": 4, "min_dynamic_patch": 1, "model_type": "internvl_chat", "pad2square": false, "ps_version": "v2", "select_layer": -1, "template": "Hermes-2", "torch_dtype": "float32", "transformers_version": null, "use_backbone_lora": 0, "use_llm_lora": 0, "use_thumbnail": true, "vision_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": [ "InternVisionModel" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "drop_path_rate": 0.0, "dropout": 0.0, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "gelu", "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 448, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 4096, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-06, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "intern_vit_6b", "no_repeat_ngram_size": 0, "norm_type": "layer_norm", "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 24, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "prefix": null, "problem_type": null, "pruned_heads": {}, "qk_normalization": false, "qkv_bias": true, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.41.2", "typical_p": 1.0, "use_bfloat16": true, "use_flash_attn": false } } 07/03/2026 09:52:27 - INFO - __main__ - Using flash_attention_2 for LLaMA [INFO|modeling_utils.py:3471] 2026-07-03 09:52:27,609 >> loading weights file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/model.safetensors [INFO|modeling_utils.py:1519] 2026-07-03 09:52:27,630 >> Instantiating InternVLChatModel model under default dtype torch.bfloat16. [INFO|configuration_utils.py:962] 2026-07-03 09:52:27,632 >> Generate config GenerationConfig {} [INFO|configuration_utils.py:962] 2026-07-03 09:52:27,689 >> Generate config GenerationConfig { "bos_token_id": 151643, "eos_token_id": 151645, "use_cache": false } [INFO|modeling_utils.py:4280] 2026-07-03 09:52:28,772 >> All model checkpoint weights were used when initializing InternVLChatModel. [INFO|modeling_utils.py:4288] 2026-07-03 09:52:28,772 >> All the weights of InternVLChatModel were initialized from the model checkpoint at /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5. If your task is similar to the task the model of the checkpoint was trained on, you can already use InternVLChatModel for predictions without further training. [INFO|configuration_utils.py:915] 2026-07-03 09:52:28,777 >> loading configuration file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/generation_config.json [INFO|configuration_utils.py:962] 2026-07-03 09:52:28,777 >> Generate config GenerationConfig { "eos_token_id": [ 151644, 151645, 151643 ] } 07/03/2026 09:52:28 - INFO - __main__ - Finished 07/03/2026 09:52:28 - INFO - __main__ - model.config.force_image_size: 448 07/03/2026 09:52:28 - INFO - __main__ - data_args.force_image_size: 448 07/03/2026 09:52:28 - INFO - __main__ - model.config.vision_config.image_size: 448 07/03/2026 09:52:28 - INFO - __main__ - max_dynamic_patch is set to 12 according to the meta file 07/03/2026 09:52:28 - INFO - __main__ - [Dataset] num_image_token: 256 07/03/2026 09:52:28 - INFO - __main__ - [Dataset] dynamic_image_size: True 07/03/2026 09:52:28 - INFO - __main__ - [Dataset] use_thumbnail: True 07/03/2026 09:52:28 - INFO - __main__ - [Dataset] min_dynamic_patch: 1, max_dynamic_patch: 12 07/03/2026 09:52:28 - INFO - __main__ - Formatting inputs...Skip in lazy mode 07/03/2026 09:52:29 - INFO - __main__ - Add dataset: vi-envelope-vqa with length: 8843 trainable params: 8,798,208 || all params: 638,496,128 || trainable%: 1.3779579255334184 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.up_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.up_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.down_proj.lora_A.default.weight 07/03/2026 09:52:30 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.down_proj.lora_B.default.weight 07/03/2026 09:52:30 - INFO - __main__ - mlp1.0.weight 07/03/2026 09:52:30 - INFO - __main__ - mlp1.0.bias 07/03/2026 09:52:30 - INFO - __main__ - mlp1.1.weight 07/03/2026 09:52:30 - INFO - __main__ - mlp1.1.bias 07/03/2026 09:52:30 - INFO - __main__ - mlp1.3.weight 07/03/2026 09:52:30 - INFO - __main__ - mlp1.3.bias [INFO|trainer.py:641] 2026-07-03 09:52:30,155 >> Using auto half precision backend [INFO|trainer.py:2078] 2026-07-03 09:53:27,067 >> ***** Running training ***** [INFO|trainer.py:2079] 2026-07-03 09:53:27,067 >> Num examples = 8,843 [INFO|trainer.py:2080] 2026-07-03 09:53:27,067 >> Num Epochs = 1 [INFO|trainer.py:2081] 2026-07-03 09:53:27,067 >> Instantaneous batch size per device = 1 [INFO|trainer.py:2084] 2026-07-03 09:53:27,068 >> Total train batch size (w. parallel, distributed & accumulation) = 16 [INFO|trainer.py:2085] 2026-07-03 09:53:27,068 >> Gradient Accumulation steps = 16 [INFO|trainer.py:2086] 2026-07-03 09:53:27,068 >> Total optimization steps = 552 [INFO|trainer.py:2087] 2026-07-03 09:53:27,073 >> Number of trainable parameters = 13,281,024 [INFO|integration_utils.py:723] 2026-07-03 09:53:27,078 >> Automatic Weights & Biases logging enabled, to disable set os.environ["WANDB_DISABLED"] = "true" wandb: [wandb.login()] Loaded credentials for https://api.wandb.ai from /root/.netrc. wandb: Currently logged in as: hhung2662000 (hhung26062000) to https://api.wandb.ai. Use `wandb login --relogin` to force relogin wandb: setting up run u11ur5ga wandb: Tracking run with wandb version 0.28.0 wandb: Run data is saved locally in /root/ai-project/Vintern/internvl_chat/wandb/run-20260703_095327-u11ur5ga wandb: Run `wandb offline` to turn off syncing. wandb: Syncing run vintern_lora_card wandb: ⭐️ View project at https://wandb.ai/hhung26062000/huggingface wandb: 🚀 View run at https://wandb.ai/hhung26062000/huggingface/runs/u11ur5ga 0%| | 0/552 [00:00, ignore_data_skip=False, include_inputs_for_metrics=False, include_num_input_tokens_seen=False, include_tokens_per_second=False, jit_mode_eval=False, label_names=None, label_smoothing_factor=0.0, learning_rate=0.0002, length_column_name=length, load_best_model_at_end=False, local_rank=0, log_level=passive, log_level_replica=warning, log_on_each_node=True, logging_dir=/root/ai-project/Vintern/vlm_training/runs/Jul03_09-55-15_data-ai-gpu-01, logging_first_step=False, logging_nan_inf_filter=True, logging_steps=10, logging_strategy=steps, lr_scheduler_kwargs={}, lr_scheduler_type=cosine, max_grad_norm=1.0, max_steps=-1, metric_for_best_model=None, mp_parameters=, neftune_noise_alpha=None, no_cuda=False, num_train_epochs=1.0, optim=adamw_torch, optim_args=None, optim_target_modules=None, output_dir=/root/ai-project/Vintern/vlm_training, overwrite_output_dir=True, past_index=-1, per_device_eval_batch_size=8, per_device_train_batch_size=1, prediction_loss_only=False, push_to_hub=False, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=, ray_scope=last, remove_unused_columns=True, report_to=['wandb'], restore_callback_states_from_checkpoint=False, resume_from_checkpoint=None, run_name=vintern_lora_card, save_on_each_node=False, save_only_model=False, save_safetensors=True, save_steps=500, save_strategy=steps, save_total_limit=2, seed=42, skip_memory_metrics=True, split_batches=None, tf32=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, torchdynamo=None, tpu_metrics_debug=False, tpu_num_cores=None, use_cpu=False, use_ipex=False, use_legacy_prediction_loop=False, use_mps_device=False, warmup_ratio=0.03, warmup_steps=0, weight_decay=0.01, ) 07/03/2026 09:55:15 - INFO - __main__ - Loading Tokenizer: /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5 [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:55:15,932 >> loading file vocab.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:55:15,932 >> loading file merges.txt [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:55:15,932 >> loading file added_tokens.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:55:15,932 >> loading file special_tokens_map.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:55:15,932 >> loading file tokenizer_config.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 09:55:15,932 >> loading file tokenizer.json [WARNING|logging.py:314] 2026-07-03 09:55:16,648 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 07/03/2026 09:55:16 - INFO - __main__ - Loading InternVLChatModel... [INFO|configuration_utils.py:731] 2026-07-03 09:55:16,658 >> loading configuration file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/config.json [INFO|configuration_utils.py:796] 2026-07-03 09:55:16,660 >> Model config InternVLChatConfig { "_commit_hash": null, "architectures": [ "InternVLChatModel" ], "auto_map": { "AutoConfig": "5CD-AI/Vintern-1B-v3_5--configuration_internvl_chat.InternVLChatConfig", "AutoModel": "5CD-AI/Vintern-1B-v3_5--modeling_internvl_chat.InternVLChatModel", "AutoModelForCausalLM": "5CD-AI/Vintern-1B-v3_5--modeling_internvl_chat.InternVLChatModel" }, "downsample_ratio": 0.5, "dynamic_image_size": true, "force_image_size": 448, "llm_config": { "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct", "add_cross_attention": false, "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 151643, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 151645, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 896, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 4864, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 32768, "max_window_layers": 21, "min_length": 0, "model_type": "qwen2", "no_repeat_ngram_size": 0, "num_attention_heads": 14, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 24, "num_key_value_heads": 2, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sep_token_id": null, "sliding_window": 32768, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.41.2", "typical_p": 1.0, "use_bfloat16": true, "use_cache": false, "use_sliding_window": false, "vocab_size": 151674 }, "max_dynamic_patch": 4, "min_dynamic_patch": 1, "model_type": "internvl_chat", "pad2square": false, "ps_version": "v2", "select_layer": -1, "template": "Hermes-2", "torch_dtype": "float32", "transformers_version": null, "use_backbone_lora": 0, "use_llm_lora": 0, "use_thumbnail": true, "vision_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": [ "InternVisionModel" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "drop_path_rate": 0.0, "dropout": 0.0, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "gelu", "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 448, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 4096, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-06, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "intern_vit_6b", "no_repeat_ngram_size": 0, "norm_type": "layer_norm", "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 24, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "prefix": null, "problem_type": null, "pruned_heads": {}, "qk_normalization": false, "qkv_bias": true, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.41.2", "typical_p": 1.0, "use_bfloat16": true, "use_flash_attn": false } } 07/03/2026 09:55:16 - INFO - __main__ - Using flash_attention_2 for LLaMA [INFO|modeling_utils.py:3471] 2026-07-03 09:55:16,660 >> loading weights file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/model.safetensors [INFO|modeling_utils.py:1519] 2026-07-03 09:55:16,684 >> Instantiating InternVLChatModel model under default dtype torch.bfloat16. [INFO|configuration_utils.py:962] 2026-07-03 09:55:16,685 >> Generate config GenerationConfig {} [INFO|configuration_utils.py:962] 2026-07-03 09:55:16,743 >> Generate config GenerationConfig { "bos_token_id": 151643, "eos_token_id": 151645, "use_cache": false } [INFO|modeling_utils.py:4280] 2026-07-03 09:55:18,133 >> All model checkpoint weights were used when initializing InternVLChatModel. [INFO|modeling_utils.py:4288] 2026-07-03 09:55:18,134 >> All the weights of InternVLChatModel were initialized from the model checkpoint at /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5. If your task is similar to the task the model of the checkpoint was trained on, you can already use InternVLChatModel for predictions without further training. [INFO|configuration_utils.py:915] 2026-07-03 09:55:18,144 >> loading configuration file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/generation_config.json [INFO|configuration_utils.py:962] 2026-07-03 09:55:18,145 >> Generate config GenerationConfig { "eos_token_id": [ 151644, 151645, 151643 ] } 07/03/2026 09:55:18 - INFO - __main__ - Finished 07/03/2026 09:55:18 - INFO - __main__ - model.config.force_image_size: 448 07/03/2026 09:55:18 - INFO - __main__ - data_args.force_image_size: 448 07/03/2026 09:55:18 - INFO - __main__ - model.config.vision_config.image_size: 448 07/03/2026 09:55:18 - INFO - __main__ - max_dynamic_patch is set to 12 according to the meta file 07/03/2026 09:55:18 - INFO - __main__ - [Dataset] num_image_token: 256 07/03/2026 09:55:18 - INFO - __main__ - [Dataset] dynamic_image_size: True 07/03/2026 09:55:18 - INFO - __main__ - [Dataset] use_thumbnail: True 07/03/2026 09:55:18 - INFO - __main__ - [Dataset] min_dynamic_patch: 1, max_dynamic_patch: 12 07/03/2026 09:55:18 - INFO - __main__ - Formatting inputs...Skip in lazy mode 07/03/2026 09:55:19 - INFO - __main__ - Add dataset: vi-envelope-vqa with length: 8843 trainable params: 8,798,208 || all params: 638,496,128 || trainable%: 1.3779579255334184 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:19 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.q_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.q_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.k_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.k_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.v_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.v_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.o_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.o_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.gate_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.gate_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.up_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.up_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.down_proj.lora_A.default.weight 07/03/2026 09:55:20 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.down_proj.lora_B.default.weight 07/03/2026 09:55:20 - INFO - __main__ - mlp1.0.weight 07/03/2026 09:55:20 - INFO - __main__ - mlp1.0.bias 07/03/2026 09:55:20 - INFO - __main__ - mlp1.1.weight 07/03/2026 09:55:20 - INFO - __main__ - mlp1.1.bias 07/03/2026 09:55:20 - INFO - __main__ - mlp1.3.weight 07/03/2026 09:55:20 - INFO - __main__ - mlp1.3.bias [INFO|trainer.py:641] 2026-07-03 09:55:20,040 >> Using auto half precision backend [INFO|trainer.py:2078] 2026-07-03 09:55:21,739 >> ***** Running training ***** [INFO|trainer.py:2079] 2026-07-03 09:55:21,739 >> Num examples = 8,843 [INFO|trainer.py:2080] 2026-07-03 09:55:21,740 >> Num Epochs = 1 [INFO|trainer.py:2081] 2026-07-03 09:55:21,740 >> Instantaneous batch size per device = 1 [INFO|trainer.py:2084] 2026-07-03 09:55:21,740 >> Total train batch size (w. parallel, distributed & accumulation) = 128 [INFO|trainer.py:2085] 2026-07-03 09:55:21,740 >> Gradient Accumulation steps = 128 [INFO|trainer.py:2086] 2026-07-03 09:55:21,740 >> Total optimization steps = 69 [INFO|trainer.py:2087] 2026-07-03 09:55:21,747 >> Number of trainable parameters = 13,281,024 [INFO|integration_utils.py:723] 2026-07-03 09:55:21,755 >> Automatic Weights & Biases logging enabled, to disable set os.environ["WANDB_DISABLED"] = "true" wandb: [wandb.login()] Loaded credentials for https://api.wandb.ai from /root/.netrc. wandb: Currently logged in as: hhung2662000 (hhung26062000) to https://api.wandb.ai. Use `wandb login --relogin` to force relogin wandb: setting up run nun5q9od wandb: Tracking run with wandb version 0.28.0 wandb: Run data is saved locally in /root/ai-project/Vintern/internvl_chat/wandb/run-20260703_095522-nun5q9od wandb: Run `wandb offline` to turn off syncing. wandb: Syncing run vintern_lora_card wandb: ⭐️ View project at https://wandb.ai/hhung26062000/huggingface wandb: 🚀 View run at https://wandb.ai/hhung26062000/huggingface/runs/nun5q9od 0%| | 0/69 [00:00 0 [2026-07-03 10:46:39,662] [WARNING] [real_accelerator.py:199:get_accelerator] Setting accelerator to CPU. If you have GPU or other accelerator, we were unable to detect it. /root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/cuda/__init__.py:128: UserWarning: CUDA initialization: Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 803: system has unsupported display driver / cuda driver combination (Triggered internally at ../c10/cuda/CUDAFunctions.cpp:108.) return torch._C._cuda_getDeviceCount() > 0 /root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/timm/models/layers/__init__.py:49: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning) petrel_client is not installed. If you read data locally instead of from ceph, ignore it. Replace train sampler!! petrel_client is not installed. Using PIL to load images. Traceback (most recent call last): File "/root/ai-project/Vintern/internvl_chat/internvl/train/internvl_chat_finetune.py", line 847, in main() File "/root/ai-project/Vintern/internvl_chat/internvl/train/internvl_chat_finetune.py", line 608, in main init_dist(launcher=launcher, backend='nccl') File "/root/ai-project/Vintern/internvl_chat/internvl/dist_utils.py", line 36, in init_dist _init_dist_pytorch(backend, **kwargs) File "/root/ai-project/Vintern/internvl_chat/internvl/dist_utils.py", line 49, in _init_dist_pytorch torch.cuda.set_device(rank % num_gpus) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/cuda/__init__.py", line 420, in set_device torch._C._cuda_setDevice(device) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/cuda/__init__.py", line 314, in _lazy_init torch._C._cuda_init() RuntimeError: Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 803: system has unsupported display driver / cuda driver combination E0703 10:46:49.798000 126501186553664 torch/distributed/elastic/multiprocessing/api.py:833] failed (exitcode: 1) local_rank: 0 (pid: 36893) of binary: /root/miniconda3/envs/train_vlm/bin/python3.10 Traceback (most recent call last): File "/root/miniconda3/envs/train_vlm/bin/torchrun", line 6, in sys.exit(main()) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 348, in wrapper return f(*args, **kwargs) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/run.py", line 901, in main run(args) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/run.py", line 892, in run elastic_launch( File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 133, in __call__ return launch_agent(self._config, self._entrypoint, list(args)) File "/root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 264, in launch_agent raise ChildFailedError( torch.distributed.elastic.multiprocessing.errors.ChildFailedError: ============================================================ /root/ai-project/Vintern/internvl_chat/internvl/train/internvl_chat_finetune.py FAILED ------------------------------------------------------------ Failures: ------------------------------------------------------------ Root Cause (first observed failure): [0]: time : 2026-07-03_10:46:49 host : data-ai-gpu-01 rank : 0 (local_rank: 0) exitcode : 1 (pid: 36893) error_file: traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html ============================================================ /root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/timm/models/layers/__init__.py:49: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning) petrel_client is not installed. If you read data locally instead of from ceph, ignore it. Replace train sampler!! petrel_client is not installed. Using PIL to load images. 07/03/2026 10:47:39 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False 07/03/2026 10:47:39 - INFO - __main__ - Training/evaluation parameters TrainingArguments( _n_gpu=1, accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, adafactor=False, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, auto_find_batch_size=False, batch_eval_metrics=False, bf16=True, bf16_full_eval=False, data_seed=None, dataloader_drop_last=False, dataloader_num_workers=4, dataloader_persistent_workers=False, dataloader_pin_memory=True, dataloader_prefetch_factor=None, ddp_backend=None, ddp_broadcast_buffers=None, ddp_bucket_cap_mb=None, ddp_find_unused_parameters=None, ddp_timeout=1800, debug=[], deepspeed=zero_stage1_config.json, disable_tqdm=False, dispatch_batches=None, do_eval=False, do_predict=False, do_train=True, eval_accumulation_steps=None, eval_delay=0, eval_do_concat_batches=True, eval_steps=None, eval_strategy=no, evaluation_strategy=None, fp16=False, fp16_backend=auto, fp16_full_eval=False, fp16_opt_level=O1, fsdp=[], fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_min_num_params=0, fsdp_transformer_layer_cls_to_wrap=None, full_determinism=False, gradient_accumulation_steps=256, gradient_checkpointing=False, gradient_checkpointing_kwargs=None, greater_is_better=None, group_by_length=True, half_precision_backend=auto, hub_always_push=False, hub_model_id=None, hub_private_repo=False, hub_strategy=every_save, hub_token=, ignore_data_skip=False, include_inputs_for_metrics=False, include_num_input_tokens_seen=False, include_tokens_per_second=False, jit_mode_eval=False, label_names=None, label_smoothing_factor=0.0, learning_rate=0.0002, length_column_name=length, load_best_model_at_end=False, local_rank=0, log_level=passive, log_level_replica=warning, log_on_each_node=True, logging_dir=/root/ai-project/Vintern/vlm_training/runs/Jul03_10-47-39_data-ai-gpu-01, logging_first_step=False, logging_nan_inf_filter=True, logging_steps=10, logging_strategy=steps, lr_scheduler_kwargs={}, lr_scheduler_type=cosine, max_grad_norm=1.0, max_steps=-1, metric_for_best_model=None, mp_parameters=, neftune_noise_alpha=None, no_cuda=False, num_train_epochs=1.0, optim=adamw_torch, optim_args=None, optim_target_modules=None, output_dir=/root/ai-project/Vintern/vlm_training, overwrite_output_dir=True, past_index=-1, per_device_eval_batch_size=8, per_device_train_batch_size=1, prediction_loss_only=False, push_to_hub=False, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=, ray_scope=last, remove_unused_columns=True, report_to=['wandb'], restore_callback_states_from_checkpoint=False, resume_from_checkpoint=None, run_name=vintern_lora_card, save_on_each_node=False, save_only_model=False, save_safetensors=True, save_steps=500, save_strategy=steps, save_total_limit=2, seed=42, skip_memory_metrics=True, split_batches=None, tf32=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, torchdynamo=None, tpu_metrics_debug=False, tpu_num_cores=None, use_cpu=False, use_ipex=False, use_legacy_prediction_loop=False, use_mps_device=False, warmup_ratio=0.03, warmup_steps=0, weight_decay=0.01, ) 07/03/2026 10:47:39 - INFO - __main__ - Loading Tokenizer: /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5 [INFO|tokenization_utils_base.py:2106] 2026-07-03 10:47:39,476 >> loading file vocab.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 10:47:39,476 >> loading file merges.txt [INFO|tokenization_utils_base.py:2106] 2026-07-03 10:47:39,476 >> loading file added_tokens.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 10:47:39,476 >> loading file special_tokens_map.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 10:47:39,476 >> loading file tokenizer_config.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 10:47:39,476 >> loading file tokenizer.json [WARNING|logging.py:314] 2026-07-03 10:47:39,892 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 07/03/2026 10:47:39 - INFO - __main__ - Loading InternVLChatModel... [INFO|configuration_utils.py:731] 2026-07-03 10:47:39,906 >> loading configuration file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/config.json [INFO|configuration_utils.py:796] 2026-07-03 10:47:39,909 >> Model config InternVLChatConfig { "_commit_hash": null, "architectures": [ "InternVLChatModel" ], "auto_map": { "AutoConfig": "5CD-AI/Vintern-1B-v3_5--configuration_internvl_chat.InternVLChatConfig", "AutoModel": "5CD-AI/Vintern-1B-v3_5--modeling_internvl_chat.InternVLChatModel", "AutoModelForCausalLM": "5CD-AI/Vintern-1B-v3_5--modeling_internvl_chat.InternVLChatModel" }, "downsample_ratio": 0.5, "dynamic_image_size": true, "force_image_size": 448, "llm_config": { "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct", "add_cross_attention": false, "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 151643, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 151645, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 896, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 4864, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 32768, "max_window_layers": 21, "min_length": 0, "model_type": "qwen2", "no_repeat_ngram_size": 0, "num_attention_heads": 14, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 24, "num_key_value_heads": 2, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sep_token_id": null, "sliding_window": 32768, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.41.2", "typical_p": 1.0, "use_bfloat16": true, "use_cache": false, "use_sliding_window": false, "vocab_size": 151674 }, "max_dynamic_patch": 4, "min_dynamic_patch": 1, "model_type": "internvl_chat", "pad2square": false, "ps_version": "v2", "select_layer": -1, "template": "Hermes-2", "torch_dtype": "float32", "transformers_version": null, "use_backbone_lora": 0, "use_llm_lora": 0, "use_thumbnail": true, "vision_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": [ "InternVisionModel" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "drop_path_rate": 0.0, "dropout": 0.0, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "gelu", "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 448, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 4096, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-06, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "intern_vit_6b", "no_repeat_ngram_size": 0, "norm_type": "layer_norm", "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 24, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "prefix": null, "problem_type": null, "pruned_heads": {}, "qk_normalization": false, "qkv_bias": true, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.41.2", "typical_p": 1.0, "use_bfloat16": true, "use_flash_attn": false } } 07/03/2026 10:47:39 - INFO - __main__ - Using flash_attention_2 for LLaMA [INFO|modeling_utils.py:3471] 2026-07-03 10:47:39,910 >> loading weights file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/model.safetensors [INFO|modeling_utils.py:1519] 2026-07-03 10:47:39,945 >> Instantiating InternVLChatModel model under default dtype torch.bfloat16. [INFO|configuration_utils.py:962] 2026-07-03 10:47:39,948 >> Generate config GenerationConfig {} [INFO|configuration_utils.py:962] 2026-07-03 10:47:40,029 >> Generate config GenerationConfig { "bos_token_id": 151643, "eos_token_id": 151645, "use_cache": false } [INFO|modeling_utils.py:4280] 2026-07-03 10:47:42,205 >> All model checkpoint weights were used when initializing InternVLChatModel. [INFO|modeling_utils.py:4288] 2026-07-03 10:47:42,205 >> All the weights of InternVLChatModel were initialized from the model checkpoint at /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5. If your task is similar to the task the model of the checkpoint was trained on, you can already use InternVLChatModel for predictions without further training. [INFO|configuration_utils.py:915] 2026-07-03 10:47:42,211 >> loading configuration file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/generation_config.json [INFO|configuration_utils.py:962] 2026-07-03 10:47:42,212 >> Generate config GenerationConfig { "eos_token_id": [ 151644, 151645, 151643 ] } 07/03/2026 10:47:42 - INFO - __main__ - Finished 07/03/2026 10:47:42 - INFO - __main__ - model.config.force_image_size: 448 07/03/2026 10:47:42 - INFO - __main__ - data_args.force_image_size: 448 07/03/2026 10:47:42 - INFO - __main__ - model.config.vision_config.image_size: 448 07/03/2026 10:47:42 - INFO - __main__ - max_dynamic_patch is set to 12 according to the meta file 07/03/2026 10:47:42 - INFO - __main__ - [Dataset] num_image_token: 256 07/03/2026 10:47:42 - INFO - __main__ - [Dataset] dynamic_image_size: True 07/03/2026 10:47:42 - INFO - __main__ - [Dataset] use_thumbnail: True 07/03/2026 10:47:42 - INFO - __main__ - [Dataset] min_dynamic_patch: 1, max_dynamic_patch: 12 07/03/2026 10:47:42 - INFO - __main__ - Formatting inputs...Skip in lazy mode 07/03/2026 10:47:42 - INFO - __main__ - Add dataset: vi-envelope-vqa with length: 8843 trainable params: 8,798,208 || all params: 638,496,128 || trainable%: 1.3779579255334184 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.q_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.q_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.k_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.k_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.v_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.v_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.o_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.o_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.gate_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.gate_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.up_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.up_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.down_proj.lora_A.default.weight 07/03/2026 10:47:43 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.down_proj.lora_B.default.weight 07/03/2026 10:47:43 - INFO - __main__ - mlp1.0.weight 07/03/2026 10:47:43 - INFO - __main__ - mlp1.0.bias 07/03/2026 10:47:43 - INFO - __main__ - mlp1.1.weight 07/03/2026 10:47:43 - INFO - __main__ - mlp1.1.bias 07/03/2026 10:47:43 - INFO - __main__ - mlp1.3.weight 07/03/2026 10:47:43 - INFO - __main__ - mlp1.3.bias [INFO|trainer.py:641] 2026-07-03 10:47:43,294 >> Using auto half precision backend [INFO|trainer.py:2078] 2026-07-03 10:47:45,224 >> ***** Running training ***** [INFO|trainer.py:2079] 2026-07-03 10:47:45,224 >> Num examples = 8,843 [INFO|trainer.py:2080] 2026-07-03 10:47:45,224 >> Num Epochs = 1 [INFO|trainer.py:2081] 2026-07-03 10:47:45,224 >> Instantaneous batch size per device = 1 [INFO|trainer.py:2084] 2026-07-03 10:47:45,224 >> Total train batch size (w. parallel, distributed & accumulation) = 256 [INFO|trainer.py:2085] 2026-07-03 10:47:45,224 >> Gradient Accumulation steps = 256 [INFO|trainer.py:2086] 2026-07-03 10:47:45,224 >> Total optimization steps = 34 [INFO|trainer.py:2087] 2026-07-03 10:47:45,229 >> Number of trainable parameters = 13,281,024 [INFO|integration_utils.py:723] 2026-07-03 10:47:45,234 >> Automatic Weights & Biases logging enabled, to disable set os.environ["WANDB_DISABLED"] = "true" wandb: [wandb.login()] Loaded credentials for https://api.wandb.ai from /root/.netrc. wandb: Currently logged in as: hhung2662000 (hhung26062000) to https://api.wandb.ai. Use `wandb login --relogin` to force relogin wandb: setting up run eum6zsve wandb: Tracking run with wandb version 0.28.0 wandb: Run data is saved locally in /root/ai-project/Vintern/internvl_chat/wandb/run-20260703_104745-eum6zsve wandb: Run `wandb offline` to turn off syncing. wandb: Syncing run vintern_lora_card wandb: ⭐️ View project at https://wandb.ai/hhung26062000/huggingface wandb: 🚀 View run at https://wandb.ai/hhung26062000/huggingface/runs/eum6zsve 0%| | 0/34 [00:00, ignore_data_skip=False, include_inputs_for_metrics=False, include_num_input_tokens_seen=False, include_tokens_per_second=False, jit_mode_eval=False, label_names=None, label_smoothing_factor=0.0, learning_rate=0.0002, length_column_name=length, load_best_model_at_end=False, local_rank=0, log_level=passive, log_level_replica=warning, log_on_each_node=True, logging_dir=/root/ai-project/Vintern/vlm_training/runs/Jul03_14-29-08_data-ai-gpu-01, logging_first_step=False, logging_nan_inf_filter=True, logging_steps=5, logging_strategy=steps, lr_scheduler_kwargs={}, lr_scheduler_type=cosine, max_grad_norm=1.0, max_steps=-1, metric_for_best_model=None, mp_parameters=, neftune_noise_alpha=None, no_cuda=False, num_train_epochs=1.0, optim=adamw_torch, optim_args=None, optim_target_modules=None, output_dir=/root/ai-project/Vintern/vlm_training, overwrite_output_dir=True, past_index=-1, per_device_eval_batch_size=8, per_device_train_batch_size=2, prediction_loss_only=False, push_to_hub=False, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=, ray_scope=last, remove_unused_columns=True, report_to=['wandb'], restore_callback_states_from_checkpoint=False, resume_from_checkpoint=None, run_name=vintern_lora_card, save_on_each_node=False, save_only_model=False, save_safetensors=True, save_steps=500, save_strategy=steps, save_total_limit=2, seed=42, skip_memory_metrics=True, split_batches=None, tf32=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, torchdynamo=None, tpu_metrics_debug=False, tpu_num_cores=None, use_cpu=False, use_ipex=False, use_legacy_prediction_loop=False, use_mps_device=False, warmup_ratio=0.03, warmup_steps=0, weight_decay=0.01, ) 07/03/2026 14:29:08 - INFO - __main__ - Loading Tokenizer: /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5 [INFO|tokenization_utils_base.py:2106] 2026-07-03 14:29:08,758 >> loading file vocab.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 14:29:08,758 >> loading file merges.txt [INFO|tokenization_utils_base.py:2106] 2026-07-03 14:29:08,758 >> loading file added_tokens.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 14:29:08,758 >> loading file special_tokens_map.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 14:29:08,758 >> loading file tokenizer_config.json [INFO|tokenization_utils_base.py:2106] 2026-07-03 14:29:08,759 >> loading file tokenizer.json [WARNING|logging.py:314] 2026-07-03 14:29:09,554 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 07/03/2026 14:29:09 - INFO - __main__ - Loading InternVLChatModel... [INFO|configuration_utils.py:731] 2026-07-03 14:29:09,564 >> loading configuration file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/config.json [INFO|configuration_utils.py:796] 2026-07-03 14:29:09,566 >> Model config InternVLChatConfig { "_commit_hash": null, "architectures": [ "InternVLChatModel" ], "auto_map": { "AutoConfig": "5CD-AI/Vintern-1B-v3_5--configuration_internvl_chat.InternVLChatConfig", "AutoModel": "5CD-AI/Vintern-1B-v3_5--modeling_internvl_chat.InternVLChatModel", "AutoModelForCausalLM": "5CD-AI/Vintern-1B-v3_5--modeling_internvl_chat.InternVLChatModel" }, "downsample_ratio": 0.5, "dynamic_image_size": true, "force_image_size": 448, "llm_config": { "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct", "add_cross_attention": false, "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 151643, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 151645, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 896, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 4864, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 32768, "max_window_layers": 21, "min_length": 0, "model_type": "qwen2", "no_repeat_ngram_size": 0, "num_attention_heads": 14, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 24, "num_key_value_heads": 2, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sep_token_id": null, "sliding_window": 32768, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.41.2", "typical_p": 1.0, "use_bfloat16": true, "use_cache": false, "use_sliding_window": false, "vocab_size": 151674 }, "max_dynamic_patch": 4, "min_dynamic_patch": 1, "model_type": "internvl_chat", "pad2square": false, "ps_version": "v2", "select_layer": -1, "template": "Hermes-2", "torch_dtype": "float32", "transformers_version": null, "use_backbone_lora": 0, "use_llm_lora": 0, "use_thumbnail": true, "vision_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": [ "InternVisionModel" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "drop_path_rate": 0.0, "dropout": 0.0, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "gelu", "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 448, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 4096, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-06, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "intern_vit_6b", "no_repeat_ngram_size": 0, "norm_type": "layer_norm", "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 24, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "prefix": null, "problem_type": null, "pruned_heads": {}, "qk_normalization": false, "qkv_bias": true, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.41.2", "typical_p": 1.0, "use_bfloat16": true, "use_flash_attn": false } } 07/03/2026 14:29:09 - INFO - __main__ - Using flash_attention_2 for LLaMA [INFO|modeling_utils.py:3471] 2026-07-03 14:29:09,567 >> loading weights file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/model.safetensors [INFO|modeling_utils.py:1519] 2026-07-03 14:29:09,591 >> Instantiating InternVLChatModel model under default dtype torch.bfloat16. [INFO|configuration_utils.py:962] 2026-07-03 14:29:09,592 >> Generate config GenerationConfig {} [INFO|configuration_utils.py:962] 2026-07-03 14:29:09,651 >> Generate config GenerationConfig { "bos_token_id": 151643, "eos_token_id": 151645, "use_cache": false } [INFO|modeling_utils.py:4280] 2026-07-03 14:29:11,568 >> All model checkpoint weights were used when initializing InternVLChatModel. [INFO|modeling_utils.py:4288] 2026-07-03 14:29:11,569 >> All the weights of InternVLChatModel were initialized from the model checkpoint at /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5. If your task is similar to the task the model of the checkpoint was trained on, you can already use InternVLChatModel for predictions without further training. [INFO|configuration_utils.py:915] 2026-07-03 14:29:11,585 >> loading configuration file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/generation_config.json [INFO|configuration_utils.py:962] 2026-07-03 14:29:11,586 >> Generate config GenerationConfig { "eos_token_id": [ 151644, 151645, 151643 ] } 07/03/2026 14:29:12 - INFO - __main__ - Finished 07/03/2026 14:29:12 - INFO - __main__ - model.config.force_image_size: 448 07/03/2026 14:29:12 - INFO - __main__ - data_args.force_image_size: 448 07/03/2026 14:29:12 - INFO - __main__ - model.config.vision_config.image_size: 448 07/03/2026 14:29:12 - INFO - __main__ - max_dynamic_patch is set to 12 according to the meta file 07/03/2026 14:29:12 - INFO - __main__ - [Dataset] num_image_token: 256 07/03/2026 14:29:12 - INFO - __main__ - [Dataset] dynamic_image_size: True 07/03/2026 14:29:12 - INFO - __main__ - [Dataset] use_thumbnail: True 07/03/2026 14:29:12 - INFO - __main__ - [Dataset] min_dynamic_patch: 1, max_dynamic_patch: 12 07/03/2026 14:29:12 - INFO - __main__ - Formatting inputs...Skip in lazy mode 07/03/2026 14:29:12 - INFO - __main__ - Add dataset: vi-envelope-vqa with length: 8843 trainable params: 8,798,208 || all params: 638,496,128 || trainable%: 1.3779579255334184 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.q_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.q_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.k_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.k_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.v_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.v_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.o_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.o_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.gate_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.gate_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.up_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.up_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.down_proj.lora_A.default.weight 07/03/2026 14:29:13 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.down_proj.lora_B.default.weight 07/03/2026 14:29:13 - INFO - __main__ - mlp1.0.weight 07/03/2026 14:29:13 - INFO - __main__ - mlp1.0.bias 07/03/2026 14:29:13 - INFO - __main__ - mlp1.1.weight 07/03/2026 14:29:13 - INFO - __main__ - mlp1.1.bias 07/03/2026 14:29:13 - INFO - __main__ - mlp1.3.weight 07/03/2026 14:29:13 - INFO - __main__ - mlp1.3.bias [INFO|trainer.py:641] 2026-07-03 14:29:13,693 >> Using auto half precision backend [INFO|trainer.py:2078] 2026-07-03 14:29:15,688 >> ***** Running training ***** [INFO|trainer.py:2079] 2026-07-03 14:29:15,688 >> Num examples = 8,843 [INFO|trainer.py:2080] 2026-07-03 14:29:15,688 >> Num Epochs = 1 [INFO|trainer.py:2081] 2026-07-03 14:29:15,689 >> Instantaneous batch size per device = 2 [INFO|trainer.py:2084] 2026-07-03 14:29:15,689 >> Total train batch size (w. parallel, distributed & accumulation) = 64 [INFO|trainer.py:2085] 2026-07-03 14:29:15,689 >> Gradient Accumulation steps = 32 [INFO|trainer.py:2086] 2026-07-03 14:29:15,689 >> Total optimization steps = 138 [INFO|trainer.py:2087] 2026-07-03 14:29:15,705 >> Number of trainable parameters = 13,281,024 [INFO|integration_utils.py:723] 2026-07-03 14:29:15,722 >> Automatic Weights & Biases logging enabled, to disable set os.environ["WANDB_DISABLED"] = "true" wandb: [wandb.login()] Loaded credentials for https://api.wandb.ai from /root/.netrc. wandb: Currently logged in as: hhung2662000 (hhung26062000) to https://api.wandb.ai. Use `wandb login --relogin` to force relogin wandb: setting up run c0vco66y wandb: Tracking run with wandb version 0.28.0 wandb: Run data is saved locally in /root/ai-project/Vintern/internvl_chat/wandb/run-20260703_142916-c0vco66y wandb: Run `wandb offline` to turn off syncing. wandb: Syncing run vintern_lora_card wandb: ⭐️ View project at https://wandb.ai/hhung26062000/huggingface wandb: 🚀 View run at https://wandb.ai/hhung26062000/huggingface/runs/c0vco66y 0%| | 0/138 [00:00> Training completed. Do not forget to share your model on huggingface.co/models =) {'train_runtime': 25778.5856, 'train_samples_per_second': 0.343, 'train_steps_per_second': 0.005, 'train_loss': 0.02036970402991426, 'epoch': 1.0} 100%|██████████| 138/138 [7:09:35<00:00, 185.65s/it] 100%|██████████| 138/138 [7:09:35<00:00, 186.78s/it] [INFO|trainer.py:3410] 2026-07-03 21:38:59,505 >> Saving model checkpoint to /root/ai-project/Vintern/vlm_training [INFO|configuration_utils.py:472] 2026-07-03 21:38:59,515 >> Configuration saved in /root/ai-project/Vintern/vlm_training/config.json [INFO|configuration_utils.py:731] 2026-07-03 21:38:59,517 >> Configuration saved in /root/ai-project/Vintern/vlm_training/generation_config.json [INFO|modeling_utils.py:2618] 2026-07-03 21:39:02,139 >> Model weights saved in /root/ai-project/Vintern/vlm_training/model.safetensors [INFO|tokenization_utils_base.py:2513] 2026-07-03 21:39:02,161 >> tokenizer config file saved in /root/ai-project/Vintern/vlm_training/tokenizer_config.json [INFO|tokenization_utils_base.py:2522] 2026-07-03 21:39:02,163 >> Special tokens file saved in /root/ai-project/Vintern/vlm_training/special_tokens_map.json [INFO|tokenization_utils_base.py:2573] 2026-07-03 21:39:02,164 >> added tokens file saved in /root/ai-project/Vintern/vlm_training/added_tokens.json ***** train metrics ***** epoch = 0.9986 total_flos = 169354287872GF train_loss = 0.0204 train_runtime = 7:09:38.58 train_samples = 8843 train_samples_per_second = 0.343 train_steps_per_second = 0.005 wandb: wandb: 🚀 View run vintern_lora_card at: https://wandb.ai/hhung26062000/huggingface/runs/c0vco66y wandb: Find logs at: wandb/run-20260703_142916-c0vco66y/logs [rank0]:[W703 21:39:06.679979361 ProcessGroupNCCL.cpp:1168] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator()) /root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/timm/models/layers/__init__.py:49: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning) petrel_client is not installed. If you read data locally instead of from ceph, ignore it. Replace train sampler!! petrel_client is not installed. Using PIL to load images. 07/06/2026 09:33:48 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False 07/06/2026 09:33:48 - INFO - __main__ - Training/evaluation parameters TrainingArguments( _n_gpu=1, accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, adafactor=False, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, auto_find_batch_size=False, batch_eval_metrics=False, bf16=True, bf16_full_eval=False, data_seed=None, dataloader_drop_last=False, dataloader_num_workers=4, dataloader_persistent_workers=False, dataloader_pin_memory=True, dataloader_prefetch_factor=None, ddp_backend=None, ddp_broadcast_buffers=None, ddp_bucket_cap_mb=None, ddp_find_unused_parameters=None, ddp_timeout=1800, debug=[], deepspeed=zero_stage1_config.json, disable_tqdm=False, dispatch_batches=None, do_eval=False, do_predict=False, do_train=True, eval_accumulation_steps=None, eval_delay=0, eval_do_concat_batches=True, eval_steps=None, eval_strategy=no, evaluation_strategy=None, fp16=False, fp16_backend=auto, fp16_full_eval=False, fp16_opt_level=O1, fsdp=[], fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_min_num_params=0, fsdp_transformer_layer_cls_to_wrap=None, full_determinism=False, gradient_accumulation_steps=64, gradient_checkpointing=False, gradient_checkpointing_kwargs=None, greater_is_better=None, group_by_length=True, half_precision_backend=auto, hub_always_push=False, hub_model_id=None, hub_private_repo=False, hub_strategy=every_save, hub_token=, ignore_data_skip=False, include_inputs_for_metrics=False, include_num_input_tokens_seen=False, include_tokens_per_second=False, jit_mode_eval=False, label_names=None, label_smoothing_factor=0.0, learning_rate=0.0002, length_column_name=length, load_best_model_at_end=False, local_rank=0, log_level=passive, log_level_replica=warning, log_on_each_node=True, logging_dir=/root/ai-project/Vintern/vlm_training/runs/Jul06_09-33-48_data-ai-gpu-01, logging_first_step=False, logging_nan_inf_filter=True, logging_steps=5, logging_strategy=steps, lr_scheduler_kwargs={}, lr_scheduler_type=cosine, max_grad_norm=1.0, max_steps=-1, metric_for_best_model=None, mp_parameters=, neftune_noise_alpha=None, no_cuda=False, num_train_epochs=1.0, optim=adamw_torch, optim_args=None, optim_target_modules=None, output_dir=/root/ai-project/Vintern/vlm_training, overwrite_output_dir=True, past_index=-1, per_device_eval_batch_size=8, per_device_train_batch_size=1, prediction_loss_only=False, push_to_hub=False, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=, ray_scope=last, remove_unused_columns=True, report_to=['wandb'], restore_callback_states_from_checkpoint=False, resume_from_checkpoint=None, run_name=vintern_lora_card, save_on_each_node=False, save_only_model=False, save_safetensors=True, save_steps=500, save_strategy=steps, save_total_limit=2, seed=42, skip_memory_metrics=True, split_batches=None, tf32=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, torchdynamo=None, tpu_metrics_debug=False, tpu_num_cores=None, use_cpu=False, use_ipex=False, use_legacy_prediction_loop=False, use_mps_device=False, warmup_ratio=0.03, warmup_steps=0, weight_decay=0.01, ) 07/06/2026 09:33:48 - INFO - __main__ - Loading Tokenizer: /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5 [INFO|tokenization_utils_base.py:2106] 2026-07-06 09:33:48,285 >> loading file vocab.json [INFO|tokenization_utils_base.py:2106] 2026-07-06 09:33:48,285 >> loading file merges.txt [INFO|tokenization_utils_base.py:2106] 2026-07-06 09:33:48,285 >> loading file added_tokens.json [INFO|tokenization_utils_base.py:2106] 2026-07-06 09:33:48,285 >> loading file special_tokens_map.json [INFO|tokenization_utils_base.py:2106] 2026-07-06 09:33:48,285 >> loading file tokenizer_config.json [INFO|tokenization_utils_base.py:2106] 2026-07-06 09:33:48,285 >> loading file tokenizer.json [WARNING|logging.py:314] 2026-07-06 09:33:48,647 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 07/06/2026 09:33:48 - INFO - __main__ - Loading InternVLChatModel... [INFO|configuration_utils.py:731] 2026-07-06 09:33:48,658 >> loading configuration file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/config.json [INFO|configuration_utils.py:796] 2026-07-06 09:33:48,660 >> Model config InternVLChatConfig { "_commit_hash": null, "architectures": [ "InternVLChatModel" ], "auto_map": { "AutoConfig": "5CD-AI/Vintern-1B-v3_5--configuration_internvl_chat.InternVLChatConfig", "AutoModel": "5CD-AI/Vintern-1B-v3_5--modeling_internvl_chat.InternVLChatModel", "AutoModelForCausalLM": "5CD-AI/Vintern-1B-v3_5--modeling_internvl_chat.InternVLChatModel" }, "downsample_ratio": 0.5, "dynamic_image_size": true, "force_image_size": 448, "llm_config": { "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct", "add_cross_attention": false, "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 151643, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 151645, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 896, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 4864, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 32768, "max_window_layers": 21, "min_length": 0, "model_type": "qwen2", "no_repeat_ngram_size": 0, "num_attention_heads": 14, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 24, "num_key_value_heads": 2, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sep_token_id": null, "sliding_window": 32768, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.41.2", "typical_p": 1.0, "use_bfloat16": true, "use_cache": false, "use_sliding_window": false, "vocab_size": 151674 }, "max_dynamic_patch": 4, "min_dynamic_patch": 1, "model_type": "internvl_chat", "pad2square": false, "ps_version": "v2", "select_layer": -1, "template": "Hermes-2", "torch_dtype": "float32", "transformers_version": null, "use_backbone_lora": 0, "use_llm_lora": 0, "use_thumbnail": true, "vision_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": [ "InternVisionModel" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "drop_path_rate": 0.0, "dropout": 0.0, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "gelu", "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 448, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 4096, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-06, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "intern_vit_6b", "no_repeat_ngram_size": 0, "norm_type": "layer_norm", "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 24, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "prefix": null, "problem_type": null, "pruned_heads": {}, "qk_normalization": false, "qkv_bias": true, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.41.2", "typical_p": 1.0, "use_bfloat16": true, "use_flash_attn": false } } 07/06/2026 09:33:48 - INFO - __main__ - Using flash_attention_2 for LLaMA [INFO|modeling_utils.py:3471] 2026-07-06 09:33:48,661 >> loading weights file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/model.safetensors [INFO|modeling_utils.py:1519] 2026-07-06 09:33:48,692 >> Instantiating InternVLChatModel model under default dtype torch.bfloat16. [INFO|configuration_utils.py:962] 2026-07-06 09:33:48,694 >> Generate config GenerationConfig {} [INFO|configuration_utils.py:962] 2026-07-06 09:33:48,753 >> Generate config GenerationConfig { "bos_token_id": 151643, "eos_token_id": 151645, "use_cache": false } [INFO|modeling_utils.py:4280] 2026-07-06 09:33:49,835 >> All model checkpoint weights were used when initializing InternVLChatModel. [INFO|modeling_utils.py:4288] 2026-07-06 09:33:49,836 >> All the weights of InternVLChatModel were initialized from the model checkpoint at /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5. If your task is similar to the task the model of the checkpoint was trained on, you can already use InternVLChatModel for predictions without further training. [INFO|configuration_utils.py:915] 2026-07-06 09:33:49,841 >> loading configuration file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/generation_config.json [INFO|configuration_utils.py:962] 2026-07-06 09:33:49,842 >> Generate config GenerationConfig { "eos_token_id": [ 151644, 151645, 151643 ] } 07/06/2026 09:33:49 - INFO - __main__ - Finished 07/06/2026 09:33:49 - INFO - __main__ - model.config.force_image_size: 448 07/06/2026 09:33:49 - INFO - __main__ - data_args.force_image_size: 448 07/06/2026 09:33:49 - INFO - __main__ - model.config.vision_config.image_size: 448 07/06/2026 09:33:49 - INFO - __main__ - max_dynamic_patch is set to 12 according to the meta file 07/06/2026 09:33:49 - INFO - __main__ - [Dataset] num_image_token: 256 07/06/2026 09:33:49 - INFO - __main__ - [Dataset] dynamic_image_size: True 07/06/2026 09:33:49 - INFO - __main__ - [Dataset] use_thumbnail: True 07/06/2026 09:33:49 - INFO - __main__ - [Dataset] min_dynamic_patch: 1, max_dynamic_patch: 12 07/06/2026 09:33:49 - INFO - __main__ - Formatting inputs...Skip in lazy mode 07/06/2026 09:33:50 - INFO - __main__ - Add dataset: vi-envelope-vqa with length: 8843 trainable params: 8,798,208 || all params: 638,496,128 || trainable%: 1.3779579255334184 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.q_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.q_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.k_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.k_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.v_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.v_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.o_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.o_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.gate_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.gate_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.up_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.up_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.down_proj.lora_A.default.weight 07/06/2026 09:33:51 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.down_proj.lora_B.default.weight 07/06/2026 09:33:51 - INFO - __main__ - mlp1.0.weight 07/06/2026 09:33:51 - INFO - __main__ - mlp1.0.bias 07/06/2026 09:33:51 - INFO - __main__ - mlp1.1.weight 07/06/2026 09:33:51 - INFO - __main__ - mlp1.1.bias 07/06/2026 09:33:51 - INFO - __main__ - mlp1.3.weight 07/06/2026 09:33:51 - INFO - __main__ - mlp1.3.bias [INFO|trainer.py:641] 2026-07-06 09:33:51,077 >> Using auto half precision backend [INFO|trainer.py:2078] 2026-07-06 09:33:52,321 >> ***** Running training ***** [INFO|trainer.py:2079] 2026-07-06 09:33:52,321 >> Num examples = 8,843 [INFO|trainer.py:2080] 2026-07-06 09:33:52,321 >> Num Epochs = 1 [INFO|trainer.py:2081] 2026-07-06 09:33:52,321 >> Instantaneous batch size per device = 1 [INFO|trainer.py:2084] 2026-07-06 09:33:52,321 >> Total train batch size (w. parallel, distributed & accumulation) = 64 [INFO|trainer.py:2085] 2026-07-06 09:33:52,321 >> Gradient Accumulation steps = 64 [INFO|trainer.py:2086] 2026-07-06 09:33:52,321 >> Total optimization steps = 138 [INFO|trainer.py:2087] 2026-07-06 09:33:52,327 >> Number of trainable parameters = 13,281,024 [INFO|integration_utils.py:723] 2026-07-06 09:33:52,332 >> Automatic Weights & Biases logging enabled, to disable set os.environ["WANDB_DISABLED"] = "true" wandb: [wandb.login()] Loaded credentials for https://api.wandb.ai from /root/.netrc. wandb: Currently logged in as: hhung2662000 (hhung26062000) to https://api.wandb.ai. Use `wandb login --relogin` to force relogin wandb: Tracking run with wandb version 0.28.0 wandb: Run data is saved locally in /root/ai-project/Vintern/internvl_chat/wandb/run-20260706_093353-ogttutpj wandb: Run `wandb offline` to turn off syncing. wandb: Syncing run vintern_lora_card wandb: ⭐️ View project at https://wandb.ai/hhung26062000/huggingface wandb: 🚀 View run at https://wandb.ai/hhung26062000/huggingface/runs/ogttutpj 0%| | 0/138 [00:00> Training completed. Do not forget to share your model on huggingface.co/models =) {'train_runtime': 28844.8665, 'train_samples_per_second': 0.307, 'train_steps_per_second': 0.005, 'train_loss': 0.02029224556695292, 'epoch': 1.0} 100%|██████████| 138/138 [8:00:42<00:00, 202.86s/it] 100%|██████████| 138/138 [8:00:42<00:00, 209.01s/it] [INFO|trainer.py:3410] 2026-07-06 17:34:39,243 >> Saving model checkpoint to /root/ai-project/Vintern/vlm_training [INFO|configuration_utils.py:472] 2026-07-06 17:34:39,252 >> Configuration saved in /root/ai-project/Vintern/vlm_training/config.json [INFO|configuration_utils.py:731] 2026-07-06 17:34:39,253 >> Configuration saved in /root/ai-project/Vintern/vlm_training/generation_config.json [INFO|modeling_utils.py:2618] 2026-07-06 17:34:47,045 >> Model weights saved in /root/ai-project/Vintern/vlm_training/model.safetensors [INFO|tokenization_utils_base.py:2513] 2026-07-06 17:34:47,047 >> tokenizer config file saved in /root/ai-project/Vintern/vlm_training/tokenizer_config.json [INFO|tokenization_utils_base.py:2522] 2026-07-06 17:34:47,048 >> Special tokens file saved in /root/ai-project/Vintern/vlm_training/special_tokens_map.json [INFO|tokenization_utils_base.py:2573] 2026-07-06 17:34:47,048 >> added tokens file saved in /root/ai-project/Vintern/vlm_training/added_tokens.json ***** train metrics ***** epoch = 0.9988 total_flos = 169354287872GF train_loss = 0.0203 train_runtime = 8:00:44.86 train_samples = 8843 train_samples_per_second = 0.307 train_steps_per_second = 0.005 wandb: wandb: 🚀 View run vintern_lora_card at: https://wandb.ai/hhung26062000/huggingface/runs/ogttutpj wandb: Find logs at: wandb/run-20260706_093353-ogttutpj/logs [rank0]:[W706 17:34:50.050944683 ProcessGroupNCCL.cpp:1168] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator()) /root/miniconda3/envs/train_vlm/lib/python3.10/site-packages/timm/models/layers/__init__.py:49: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning) petrel_client is not installed. If you read data locally instead of from ceph, ignore it. Replace train sampler!! petrel_client is not installed. Using PIL to load images. 07/06/2026 17:47:08 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False 07/06/2026 17:47:08 - INFO - __main__ - Training/evaluation parameters TrainingArguments( _n_gpu=1, accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, adafactor=False, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, auto_find_batch_size=False, batch_eval_metrics=False, bf16=True, bf16_full_eval=False, data_seed=None, dataloader_drop_last=False, dataloader_num_workers=4, dataloader_persistent_workers=False, dataloader_pin_memory=True, dataloader_prefetch_factor=None, ddp_backend=None, ddp_broadcast_buffers=None, ddp_bucket_cap_mb=None, ddp_find_unused_parameters=None, ddp_timeout=1800, debug=[], deepspeed=zero_stage1_config.json, disable_tqdm=False, dispatch_batches=None, do_eval=False, do_predict=False, do_train=True, eval_accumulation_steps=None, eval_delay=0, eval_do_concat_batches=True, eval_steps=None, eval_strategy=no, evaluation_strategy=None, fp16=False, fp16_backend=auto, fp16_full_eval=False, fp16_opt_level=O1, fsdp=[], fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_min_num_params=0, fsdp_transformer_layer_cls_to_wrap=None, full_determinism=False, gradient_accumulation_steps=64, gradient_checkpointing=False, gradient_checkpointing_kwargs=None, greater_is_better=None, group_by_length=True, half_precision_backend=auto, hub_always_push=False, hub_model_id=None, hub_private_repo=False, hub_strategy=every_save, hub_token=, ignore_data_skip=False, include_inputs_for_metrics=False, include_num_input_tokens_seen=False, include_tokens_per_second=False, jit_mode_eval=False, label_names=None, label_smoothing_factor=0.0, learning_rate=0.0002, length_column_name=length, load_best_model_at_end=False, local_rank=0, log_level=passive, log_level_replica=warning, log_on_each_node=True, logging_dir=/root/ai-project/Vintern/vlm_training/runs/Jul06_17-47-08_data-ai-gpu-01, logging_first_step=False, logging_nan_inf_filter=True, logging_steps=5, logging_strategy=steps, lr_scheduler_kwargs={}, lr_scheduler_type=cosine, max_grad_norm=1.0, max_steps=-1, metric_for_best_model=None, mp_parameters=, neftune_noise_alpha=None, no_cuda=False, num_train_epochs=2.0, optim=adamw_torch, optim_args=None, optim_target_modules=None, output_dir=/root/ai-project/Vintern/vlm_training, overwrite_output_dir=True, past_index=-1, per_device_eval_batch_size=8, per_device_train_batch_size=1, prediction_loss_only=False, push_to_hub=False, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=, ray_scope=last, remove_unused_columns=True, report_to=['wandb'], restore_callback_states_from_checkpoint=False, resume_from_checkpoint=None, run_name=vintern_lora_card, save_on_each_node=False, save_only_model=False, save_safetensors=True, save_steps=500, save_strategy=steps, save_total_limit=2, seed=42, skip_memory_metrics=True, split_batches=None, tf32=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, torchdynamo=None, tpu_metrics_debug=False, tpu_num_cores=None, use_cpu=False, use_ipex=False, use_legacy_prediction_loop=False, use_mps_device=False, warmup_ratio=0.03, warmup_steps=0, weight_decay=0.01, ) 07/06/2026 17:47:08 - INFO - __main__ - Loading Tokenizer: /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5 [INFO|tokenization_utils_base.py:2106] 2026-07-06 17:47:08,945 >> loading file vocab.json [INFO|tokenization_utils_base.py:2106] 2026-07-06 17:47:08,945 >> loading file merges.txt [INFO|tokenization_utils_base.py:2106] 2026-07-06 17:47:08,945 >> loading file added_tokens.json [INFO|tokenization_utils_base.py:2106] 2026-07-06 17:47:08,945 >> loading file special_tokens_map.json [INFO|tokenization_utils_base.py:2106] 2026-07-06 17:47:08,945 >> loading file tokenizer_config.json [INFO|tokenization_utils_base.py:2106] 2026-07-06 17:47:08,945 >> loading file tokenizer.json [WARNING|logging.py:314] 2026-07-06 17:47:09,256 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. 07/06/2026 17:47:09 - INFO - __main__ - Loading InternVLChatModel... [INFO|configuration_utils.py:731] 2026-07-06 17:47:09,265 >> loading configuration file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/config.json [INFO|configuration_utils.py:796] 2026-07-06 17:47:09,266 >> Model config InternVLChatConfig { "_commit_hash": null, "architectures": [ "InternVLChatModel" ], "auto_map": { "AutoConfig": "5CD-AI/Vintern-1B-v3_5--configuration_internvl_chat.InternVLChatConfig", "AutoModel": "5CD-AI/Vintern-1B-v3_5--modeling_internvl_chat.InternVLChatModel", "AutoModelForCausalLM": "5CD-AI/Vintern-1B-v3_5--modeling_internvl_chat.InternVLChatModel" }, "downsample_ratio": 0.5, "dynamic_image_size": true, "force_image_size": 448, "llm_config": { "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct", "add_cross_attention": false, "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 151643, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 151645, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 896, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 4864, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 32768, "max_window_layers": 21, "min_length": 0, "model_type": "qwen2", "no_repeat_ngram_size": 0, "num_attention_heads": 14, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 24, "num_key_value_heads": 2, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sep_token_id": null, "sliding_window": 32768, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.41.2", "typical_p": 1.0, "use_bfloat16": true, "use_cache": false, "use_sliding_window": false, "vocab_size": 151674 }, "max_dynamic_patch": 4, "min_dynamic_patch": 1, "model_type": "internvl_chat", "pad2square": false, "ps_version": "v2", "select_layer": -1, "template": "Hermes-2", "torch_dtype": "float32", "transformers_version": null, "use_backbone_lora": 0, "use_llm_lora": 0, "use_thumbnail": true, "vision_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": [ "InternVisionModel" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "drop_path_rate": 0.0, "dropout": 0.0, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "gelu", "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 448, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 4096, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-06, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "intern_vit_6b", "no_repeat_ngram_size": 0, "norm_type": "layer_norm", "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 24, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "prefix": null, "problem_type": null, "pruned_heads": {}, "qk_normalization": false, "qkv_bias": true, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.41.2", "typical_p": 1.0, "use_bfloat16": true, "use_flash_attn": false } } 07/06/2026 17:47:09 - INFO - __main__ - Using flash_attention_2 for LLaMA [INFO|modeling_utils.py:3471] 2026-07-06 17:47:09,267 >> loading weights file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/model.safetensors [INFO|modeling_utils.py:1519] 2026-07-06 17:47:09,290 >> Instantiating InternVLChatModel model under default dtype torch.bfloat16. [INFO|configuration_utils.py:962] 2026-07-06 17:47:09,292 >> Generate config GenerationConfig {} [INFO|configuration_utils.py:962] 2026-07-06 17:47:09,348 >> Generate config GenerationConfig { "bos_token_id": 151643, "eos_token_id": 151645, "use_cache": false } [INFO|modeling_utils.py:4280] 2026-07-06 17:47:10,512 >> All model checkpoint weights were used when initializing InternVLChatModel. [INFO|modeling_utils.py:4288] 2026-07-06 17:47:10,513 >> All the weights of InternVLChatModel were initialized from the model checkpoint at /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5. If your task is similar to the task the model of the checkpoint was trained on, you can already use InternVLChatModel for predictions without further training. [INFO|configuration_utils.py:915] 2026-07-06 17:47:10,517 >> loading configuration file /root/ai-project/Vintern/pretrained/Vintern-1B-v3_5/generation_config.json [INFO|configuration_utils.py:962] 2026-07-06 17:47:10,518 >> Generate config GenerationConfig { "eos_token_id": [ 151644, 151645, 151643 ] } 07/06/2026 17:47:10 - INFO - __main__ - Finished 07/06/2026 17:47:10 - INFO - __main__ - model.config.force_image_size: 448 07/06/2026 17:47:10 - INFO - __main__ - data_args.force_image_size: 448 07/06/2026 17:47:10 - INFO - __main__ - model.config.vision_config.image_size: 448 07/06/2026 17:47:10 - INFO - __main__ - max_dynamic_patch is set to 12 according to the meta file 07/06/2026 17:47:10 - INFO - __main__ - [Dataset] num_image_token: 256 07/06/2026 17:47:10 - INFO - __main__ - [Dataset] dynamic_image_size: True 07/06/2026 17:47:10 - INFO - __main__ - [Dataset] use_thumbnail: True 07/06/2026 17:47:10 - INFO - __main__ - [Dataset] min_dynamic_patch: 1, max_dynamic_patch: 12 07/06/2026 17:47:10 - INFO - __main__ - Formatting inputs...Skip in lazy mode 07/06/2026 17:47:11 - INFO - __main__ - Add dataset: vi-envelope-vqa with length: 8843 trainable params: 8,798,208 || all params: 638,496,128 || trainable%: 1.3779579255334184 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.0.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.0.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.1.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.1.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.2.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.2.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.3.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.3.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.4.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.4.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.5.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.5.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.6.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.6.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.7.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.7.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.8.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.8.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.9.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.9.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.10.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.10.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.11.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.11.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.12.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.12.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.13.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.13.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.14.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.14.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.15.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.15.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.16.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.16.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.17.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.17.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.18.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.18.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.19.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.19.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.20.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.20.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.21.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.21.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.22.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.22.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.q_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.q_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.k_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.k_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.v_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.v_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.o_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.23.self_attn.o_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.gate_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.gate_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.up_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.up_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.down_proj.lora_A.default.weight 07/06/2026 17:47:11 - INFO - __main__ - language_model.base_model.model.model.layers.23.mlp.down_proj.lora_B.default.weight 07/06/2026 17:47:11 - INFO - __main__ - mlp1.0.weight 07/06/2026 17:47:11 - INFO - __main__ - mlp1.0.bias 07/06/2026 17:47:11 - INFO - __main__ - mlp1.1.weight 07/06/2026 17:47:11 - INFO - __main__ - mlp1.1.bias 07/06/2026 17:47:11 - INFO - __main__ - mlp1.3.weight 07/06/2026 17:47:11 - INFO - __main__ - mlp1.3.bias [INFO|trainer.py:641] 2026-07-06 17:47:11,515 >> Using auto half precision backend [INFO|trainer.py:2078] 2026-07-06 17:47:12,672 >> ***** Running training ***** [INFO|trainer.py:2079] 2026-07-06 17:47:12,673 >> Num examples = 8,843 [INFO|trainer.py:2080] 2026-07-06 17:47:12,673 >> Num Epochs = 2 [INFO|trainer.py:2081] 2026-07-06 17:47:12,673 >> Instantaneous batch size per device = 1 [INFO|trainer.py:2084] 2026-07-06 17:47:12,673 >> Total train batch size (w. parallel, distributed & accumulation) = 64 [INFO|trainer.py:2085] 2026-07-06 17:47:12,673 >> Gradient Accumulation steps = 64 [INFO|trainer.py:2086] 2026-07-06 17:47:12,673 >> Total optimization steps = 276 [INFO|trainer.py:2087] 2026-07-06 17:47:12,678 >> Number of trainable parameters = 13,281,024 [INFO|integration_utils.py:723] 2026-07-06 17:47:12,682 >> Automatic Weights & Biases logging enabled, to disable set os.environ["WANDB_DISABLED"] = "true" wandb: [wandb.login()] Loaded credentials for https://api.wandb.ai from /root/.netrc. wandb: Currently logged in as: hhung2662000 (hhung26062000) to https://api.wandb.ai. Use `wandb login --relogin` to force relogin wandb: setting up run shbvg7yy wandb: Tracking run with wandb version 0.28.0 wandb: Run data is saved locally in /root/ai-project/Vintern/internvl_chat/wandb/run-20260706_174713-shbvg7yy wandb: Run `wandb offline` to turn off syncing. wandb: Syncing run vintern_lora_card wandb: ⭐️ View project at https://wandb.ai/hhung26062000/huggingface wandb: 🚀 View run at https://wandb.ai/hhung26062000/huggingface/runs/shbvg7yy 0%| | 0/276 [00:00> Training completed. Do not forget to share your model on huggingface.co/models =) {'train_runtime': 58629.8958, 'train_samples_per_second': 0.302, 'train_steps_per_second': 0.005, 'train_loss': 0.014006755621833861, 'epoch': 2.0} 100%|██████████| 276/276 [16:17:07<00:00, 203.46s/it] 100%|██████████| 276/276 [16:17:07<00:00, 212.42s/it] [INFO|trainer.py:3410] 2026-07-07 10:04:24,676 >> Saving model checkpoint to /root/ai-project/Vintern/vlm_training [INFO|configuration_utils.py:472] 2026-07-07 10:04:24,684 >> Configuration saved in /root/ai-project/Vintern/vlm_training/config.json [INFO|configuration_utils.py:731] 2026-07-07 10:04:24,686 >> Configuration saved in /root/ai-project/Vintern/vlm_training/generation_config.json [INFO|modeling_utils.py:2618] 2026-07-07 10:04:32,289 >> Model weights saved in /root/ai-project/Vintern/vlm_training/model.safetensors [INFO|tokenization_utils_base.py:2513] 2026-07-07 10:04:32,291 >> tokenizer config file saved in /root/ai-project/Vintern/vlm_training/tokenizer_config.json [INFO|tokenization_utils_base.py:2522] 2026-07-07 10:04:32,292 >> Special tokens file saved in /root/ai-project/Vintern/vlm_training/special_tokens_map.json [INFO|tokenization_utils_base.py:2573] 2026-07-07 10:04:32,293 >> added tokens file saved in /root/ai-project/Vintern/vlm_training/added_tokens.json ***** train metrics ***** epoch = 1.9975 total_flos = 338692201472GF train_loss = 0.014 train_runtime = 16:17:09.89 train_samples = 8843 train_samples_per_second = 0.302 train_steps_per_second = 0.005 wandb: wandb: 🚀 View run vintern_lora_card at: https://wandb.ai/hhung26062000/huggingface/runs/shbvg7yy wandb: Find logs at: wandb/run-20260706_174713-shbvg7yy/logs [rank0]:[W707 10:04:36.085715531 ProcessGroupNCCL.cpp:1168] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator())