training_args.json

{
  "output_dir": "/home/ec2-user/output/qwen2-vl-2b-instruct/v0-20241209-111947",
  "overwrite_output_dir": false,
  "do_train": false,
  "do_eval": true,
  "do_predict": false,
  "eval_strategy": "steps",
  "prediction_loss_only": false,
  "per_device_train_batch_size": 1,
  "per_device_eval_batch_size": 1,
  "per_gpu_train_batch_size": null,
  "per_gpu_eval_batch_size": null,
  "gradient_accumulation_steps": 8,
  "eval_accumulation_steps": null,
  "eval_delay": 0,
  "torch_empty_cache_steps": null,
  "learning_rate": 5e-05,
  "weight_decay": 0.1,
  "adam_beta1": 0.9,
  "adam_beta2": 0.95,
  "adam_epsilon": 1e-08,
  "max_grad_norm": 1,
  "num_train_epochs": 5,
  "max_steps": -1,
  "lr_scheduler_type": "cosine",
  "lr_scheduler_kwargs": {},
  "warmup_ratio": 0.03,
  "warmup_steps": 0,
  "log_level": "passive",
  "log_level_replica": "warning",
  "log_on_each_node": true,
  "logging_dir": "/home/ec2-user/output/qwen2-vl-2b-instruct/v0-20241209-111947/runs",
  "logging_strategy": "steps",
  "logging_first_step": true,
  "logging_steps": 5,
  "logging_nan_inf_filter": true,
  "save_strategy": "steps",
  "save_steps": 50,
  "save_total_limit": 2,
  "save_safetensors": true,
  "save_on_each_node": false,
  "save_only_model": false,
  "restore_callback_states_from_checkpoint": false,
  "no_cuda": false,
  "use_cpu": false,
  "use_mps_device": false,
  "seed": 42,
  "data_seed": 42,
  "jit_mode_eval": false,
  "use_ipex": false,
  "bf16": true,
  "fp16": false,
  "fp16_opt_level": "O1",
  "half_precision_backend": "auto",
  "bf16_full_eval": false,
  "fp16_full_eval": false,
  "tf32": null,
  "local_rank": 0,
  "ddp_backend": null,
  "tpu_num_cores": null,
  "tpu_metrics_debug": false,
  "debug": [],
  "dataloader_drop_last": false,
  "eval_steps": 50,
  "dataloader_num_workers": 1,
  "dataloader_prefetch_factor": null,
  "past_index": -1,
  "run_name": "/home/ec2-user/output/qwen2-vl-2b-instruct/v0-20241209-111947",
  "disable_tqdm": false,
  "remove_unused_columns": false,
  "label_names": null,
  "load_best_model_at_end": false,
  "metric_for_best_model": "loss",
  "greater_is_better": false,
  "ignore_data_skip": false,
  "fsdp": [],
  "fsdp_min_num_params": 0,
  "fsdp_config": {
    "min_num_params": 0,
    "xla": false,
    "xla_fsdp_v2": false,
    "xla_fsdp_grad_ckpt": false
  },
  "fsdp_transformer_layer_cls_to_wrap": null,
  "accelerator_config": "AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False)",
  "deepspeed": null,
  "label_smoothing_factor": 0.0,
  "optim": "adamw_torch",
  "optim_args": null,
  "adafactor": false,
  "group_by_length": false,
  "length_column_name": "length",
  "report_to": [
    "tensorboard"
  ],
  "ddp_find_unused_parameters": null,
  "ddp_bucket_cap_mb": null,
  "ddp_broadcast_buffers": null,
  "dataloader_pin_memory": true,
  "dataloader_persistent_workers": false,
  "skip_memory_metrics": true,
  "use_legacy_prediction_loop": false,
  "push_to_hub": false,
  "resume_from_checkpoint": null,
  "hub_model_id": null,
  "hub_strategy": "every_save",
  "hub_token": null,
  "hub_private_repo": false,
  "hub_always_push": false,
  "gradient_checkpointing": true,
  "gradient_checkpointing_kwargs": null,
  "include_inputs_for_metrics": false,
  "include_for_metrics": [],
  "eval_do_concat_batches": true,
  "fp16_backend": "auto",
  "evaluation_strategy": null,
  "push_to_hub_model_id": null,
  "push_to_hub_organization": null,
  "push_to_hub_token": null,
  "mp_parameters": "",
  "auto_find_batch_size": false,
  "full_determinism": false,
  "torchdynamo": null,
  "ray_scope": "last",
  "ddp_timeout": 1800,
  "torch_compile": false,
  "torch_compile_backend": null,
  "torch_compile_mode": null,
  "dispatch_batches": null,
  "split_batches": null,
  "include_tokens_per_second": false,
  "include_num_input_tokens_seen": false,
  "neftune_noise_alpha": null,
  "optim_target_modules": null,
  "batch_eval_metrics": false,
  "eval_on_start": false,
  "use_liger_kernel": false,
  "eval_use_gather_object": false,
  "average_tokens_across_devices": false,
  "beta": 0.1,
  "label_smoothing": 0.0,
  "loss_type": "sigmoid",
  "label_pad_token_id": -100,
  "padding_value": null,
  "truncation_mode": "keep_end",
  "max_length": null,
  "max_prompt_length": null,
  "max_target_length": null,
  "max_completion_length": null,
  "is_encoder_decoder": null,
  "disable_dropout": true,
  "generate_during_eval": false,
  "precompute_ref_log_probs": false,
  "dataset_num_proc": null,
  "model_init_kwargs": null,
  "ref_model_init_kwargs": null,
  "model_adapter_name": null,
  "ref_adapter_name": null,
  "reference_free": false,
  "force_use_ref_model": false,
  "f_divergence_type": "<FDivergenceType.REVERSE_KL: 'reverse_kl'>",
  "f_alpha_divergence_coef": 1.0,
  "sync_ref_model": false,
  "ref_model_mixup_alpha": 0.9,
  "ref_model_sync_steps": 64,
  "rpo_alpha": 0.1,
  "acc_strategy": "token",
  "loss_name": null,
  "additional_saved_files": [],
  "train_sampler_random": true,
  "metric_warmup_step": 0,
  "train_dataset_sample": -1,
  "distributed_state": "Distributed environment: NO\nNum processes: 1\nProcess index: 0\nLocal process index: 0\nDevice: cuda\n",
  "_n_gpu": 1,
  "__cached__setup_devices": "device(type='cuda', index=0)",
  "deepspeed_plugin": null,
  "generation_config": "GenerationConfig {\n  \"bos_token_id\": 151643,\n  \"do_sample\": true,\n  \"eos_token_id\": 151645,\n  \"max_new_tokens\": 2048,\n  \"pad_token_id\": 151643,\n  \"temperature\": 0.01,\n  \"top_k\": 1,\n  \"top_p\": 0.001\n}\n"
}