[2025-10-22 10:50:22,584] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:2355] baseline 0.000GB () [2025-10-22 10:50:22,584] [INFO] [axolotl.cli.config.load_cfg:248] [PID:2355] config: { "activation_offloading": false, "adapter": "qlora", "axolotl_config_path": "config.yaml", "base_model": "Qwen/Qwen2.5-VL-7B-Instruct", "base_model_config": "Qwen/Qwen2.5-VL-7B-Instruct", "batch_size": 8, "bf16": true, "capabilities": { "bf16": true, "compute_capability": "sm_90", "fp8": false, "n_gpu": 1, "n_node": 1 }, "context_parallel_size": 1, "dataloader_num_workers": 1, "dataloader_pin_memory": true, "dataloader_prefetch_factor": 256, "dataset_processes": 20, "datasets": [ { "message_property_mappings": { "content": "content", "role": "role" }, "path": "/workspace/fine-tuning/data/data.json", "trust_remote_code": false, "type": "vl" } ], "ddp": false, "device": "cuda:0", "dion_rank_fraction": 1.0, "dion_rank_multiple_of": 1, "env_capabilities": { "torch_version": "2.7.1" }, "eval_batch_size": 1, "eval_causal_lm_metrics": [ "sacrebleu", "comet", "ter", "chrf" ], "eval_max_new_tokens": 128, "eval_table_size": 0, "experimental_skip_move_to_device": true, "flash_attention": true, "fp16": false, "gradient_accumulation_steps": 8, "gradient_checkpointing": true, "gradient_checkpointing_kwargs": { "use_reentrant": true }, "include_tkps": true, "is_multimodal": true, "learning_rate": 0.0002, "lisa_layers_attribute": "model.layers", "load_best_model_at_end": false, "load_in_4bit": true, "load_in_8bit": false, "local_rank": 0, "lora_alpha": 16, "lora_dropout": 0.05, "lora_r": 64, "lora_target_modules": [ "q_proj", "v_proj", "k_proj", "o_proj", "gate_proj", "down_proj", "up_proj", "lm_head", "vision_tower" ], "loraplus_lr_embedding": 1e-06, "lr_scheduler": "cosine", "mean_resizing_embeddings": false, "micro_batch_size": 1, "model_config_type": "qwen2_5_vl", "num_epochs": 3.0, "optimizer": "paged_adamw_32bit", "output_dir": "/workspace/fine-tuning/output/mymodel", "pretrain_multipack_attn": true, "processor_config": "Qwen/Qwen2.5-VL-7B-Instruct", "profiler_steps_start": 0, "qlora_sharded_model_loading": false, "ray_num_workers": 1, "resources_per_worker": { "GPU": 1 }, "sample_packing_bin_size": 200, "sample_packing_group_size": 100000, "save_only_model": false, "save_safetensors": true, "save_steps": 200, "save_total_limit": 3, "sequence_len": 2048, "shuffle_before_merging_datasets": false, "shuffle_merged_datasets": true, "skip_prepare_dataset": false, "streaming_multipack_buffer_size": 10000, "strict": false, "tensor_parallel_size": 1, "tiled_mlp_use_original_mlp": true, "tokenizer_config": "Qwen/Qwen2.5-VL-7B-Instruct", "tokenizer_save_jinja_files": true, "torch_compile": false, "torch_dtype": "torch.bfloat16", "train_on_inputs": false, "trl": { "log_completions": false, "mask_truncated_completions": false, "ref_model_mixup_alpha": 0.9, "ref_model_sync_steps": 64, "scale_rewards": true, "sync_ref_model": false, "use_vllm": false, "vllm_server_host": "0.0.0.0", "vllm_server_port": 8000 }, "trust_remote_code": true, "use_ray": false, "val_set_size": 0.0, "vllm": { "device": "auto", "dtype": "auto", "gpu_memory_utilization": 0.9, "host": "0.0.0.0", "port": 8000 }, "weight_decay": 0.0, "world_size": 1 } [2025-10-22 10:50:23,548] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:278] [PID:2355] EOS: 151645 / <|im_end|> [2025-10-22 10:50:23,548] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:279] [PID:2355] BOS: None / None [2025-10-22 10:50:23,548] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:280] [PID:2355] PAD: 151643 / <|endoftext|> [2025-10-22 10:50:23,548] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:281] [PID:2355] UNK: None / None [2025-10-22 10:50:23,549] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:476] [PID:2355] Unable to find prepared dataset in last_run_prepared/b27c6ba83f346393518eaef14d5ae408 [2025-10-22 10:50:23,549] [INFO] [axolotl.utils.data.sft._load_raw_datasets:320] [PID:2355] Loading raw datasets... [2025-10-22 10:50:23,549] [WARNING] [axolotl.utils.data.sft._load_raw_datasets:322] [PID:2355] Processing datasets during training can lead to VRAM instability. Please pre-process your dataset using `axolotl preprocess path/to/config.yml`. [2025-10-22 10:50:23,988] [INFO] [axolotl.utils.data.wrappers.get_dataset_wrapper:87] [PID:2355] Loading dataset: /workspace/fine-tuning/data/data.json with base_type: vl and prompt_style: None [2025-10-22 10:50:23,989] [ERROR] [axolotl.utils.data.wrappers.handle_unknown_dataset_strategy:53] [PID:2355] unhandled prompt tokenization strategy: vl. Traceback (most recent call last): File "", line 198, in _run_module_as_main File "", line 88, in _run_code File "/workspace/axolotl/src/axolotl/cli/train.py", line 121, in fire.Fire(do_cli) File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/fire/core.py", line 135, in Fire component_trace = _Fire(component, args, parsed_flag_args, context, name) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/fire/core.py", line 468, in _Fire component, remaining_args = _CallAndUpdateTrace( ^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/py3.11/lib/python3.11/site-packages/fire/core.py", line 684, in _CallAndUpdateTrace component = fn(*varargs, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/cli/train.py", line 88, in do_cli return do_train(parsed_cfg, parsed_cli_args) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/cli/train.py", line 43, in do_train dataset_meta = load_datasets(cfg=cfg, cli_args=cli_args) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/common/datasets.py", line 59, in load_datasets train_dataset, eval_dataset, total_num_steps, prompters = prepare_datasets( ^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/utils/data/utils.py", line 50, in wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/utils/data/sft.py", line 65, in prepare_datasets return _prepare_standard_dataset(cfg, tokenizer, processor) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/utils/data/sft.py", line 98, in _prepare_standard_dataset train_dataset, eval_dataset, prompters = loader.load(_load_datasets) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/utils/data/lock.py", line 38, in load result = load_fn() ^^^^^^^^^ File "/workspace/axolotl/src/axolotl/utils/data/sft.py", line 77, in _load_datasets train_dataset, eval_dataset, prompters = _load_and_prepare_datasets( ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/utils/data/sft.py", line 503, in _load_and_prepare_datasets dataset, prompters = _load_tokenized_prepared_datasets( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/utils/data/sft.py", line 299, in _load_tokenized_prepared_datasets dataset, prompters = _load_raw_datasets( ^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/utils/data/sft.py", line 331, in _load_raw_datasets dataset_wrapper, dataset_prompter = _load_and_process_single_dataset( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/utils/data/sft.py", line 401, in _load_and_process_single_dataset dataset_wrapper, dataset_prompter = get_dataset_wrapper( ^^^^^^^^^^^^^^^^^^^^ File "/workspace/axolotl/src/axolotl/utils/data/wrappers.py", line 131, in get_dataset_wrapper handle_unknown_dataset_strategy(dataset_config) File "/workspace/axolotl/src/axolotl/utils/data/wrappers.py", line 54, in handle_unknown_dataset_strategy raise ValueError(error_message) ValueError: unhandled prompt tokenization strategy: vl.