| { | |
| "data_config": { | |
| "meta_data": "", | |
| "data_dir": "", | |
| "meta_data_test": "", | |
| "max_frame_pixels": 200704, | |
| "num_frames": null, | |
| "fps": 2.0, | |
| "p_shuffle_frames": 0.0, | |
| "p_color_jitter": 0.0, | |
| "eval_dim": [ | |
| "VQ", | |
| "MQ", | |
| "TA" | |
| ], | |
| "prompt_template_type": "detailed_special", | |
| "add_noise": false, | |
| "sample_type": "uniform", | |
| "use_tied_data": true | |
| }, | |
| "training_args": { | |
| "output_dir": "", | |
| "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": 4, | |
| "per_gpu_train_batch_size": null, | |
| "per_gpu_eval_batch_size": null, | |
| "gradient_accumulation_steps": 4, | |
| "eval_accumulation_steps": null, | |
| "eval_delay": 0, | |
| "torch_empty_cache_steps": null, | |
| "learning_rate": 2e-06, | |
| "weight_decay": 0.0, | |
| "adam_beta1": 0.9, | |
| "adam_beta2": 0.999, | |
| "adam_epsilon": 1e-08, | |
| "max_grad_norm": 1.0, | |
| "num_train_epochs": 3.0, | |
| "max_steps": -1, | |
| "lr_scheduler_type": "constant_with_warmup", | |
| "lr_scheduler_kwargs": {}, | |
| "warmup_ratio": 0.05, | |
| "warmup_steps": 0, | |
| "log_level": "passive", | |
| "log_level_replica": "warning", | |
| "log_on_each_node": true, | |
| "logging_dir": "", | |
| "logging_strategy": "steps", | |
| "logging_first_step": false, | |
| "logging_steps": 57, | |
| "logging_nan_inf_filter": true, | |
| "save_strategy": "steps", | |
| "save_steps": 1419, | |
| "save_total_limit": null, | |
| "save_safetensors": true, | |
| "save_on_each_node": false, | |
| "save_only_model": true, | |
| "restore_callback_states_from_checkpoint": false, | |
| "no_cuda": false, | |
| "use_cpu": false, | |
| "use_mps_device": false, | |
| "seed": 42, | |
| "data_seed": null, | |
| "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, | |
| "ddp_backend": null, | |
| "tpu_num_cores": null, | |
| "tpu_metrics_debug": false, | |
| "debug": [], | |
| "dataloader_drop_last": false, | |
| "eval_steps": 568, | |
| "dataloader_num_workers": 8, | |
| "dataloader_prefetch_factor": null, | |
| "past_index": -1, | |
| "run_name": "", | |
| "disable_tqdm": false, | |
| "remove_unused_columns": false, | |
| "label_names": null, | |
| "load_best_model_at_end": false, | |
| "metric_for_best_model": null, | |
| "greater_is_better": null, | |
| "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": { | |
| "split_batches": false, | |
| "dispatch_batches": null, | |
| "even_batches": true, | |
| "use_seedable_sampler": true, | |
| "non_blocking": false, | |
| "gradient_accumulation_kwargs": null, | |
| "use_configured_state": false | |
| }, | |
| "deepspeed": "ds_config/zero0.json", | |
| "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": false, | |
| "gradient_checkpointing_kwargs": null, | |
| "include_inputs_for_metrics": false, | |
| "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, | |
| "max_length": 6144, | |
| "dataset_num_proc": null, | |
| "center_rewards_coefficient": null, | |
| "disable_flash_attn2": false, | |
| "vision_lr": 2e-06, | |
| "merger_lr": 2e-06, | |
| "special_token_lr": 2e-06, | |
| "conduct_eval": true, | |
| "load_from_pretrained": null, | |
| "load_from_pretrained_step": null, | |
| "logging_epochs": 0.01, | |
| "eval_epochs": 0.1, | |
| "save_epochs": 0.25, | |
| "save_full_model": false | |
| }, | |
| "model_config": { | |
| "model_name_or_path": "Qwen/Qwen2-VL-2B-Instruct", | |
| "model_revision": "main", | |
| "output_dim": 1, | |
| "use_special_tokens": true, | |
| "freeze_vision_tower": false, | |
| "freeze_llm": false, | |
| "tune_merger": true, | |
| "torch_dtype": "bfloat16", | |
| "trust_remote_code": false, | |
| "attn_implementation": null, | |
| "load_in_8bit": false, | |
| "load_in_4bit": false, | |
| "bnb_4bit_quant_type": "nf4", | |
| "use_bnb_nested_quant": false, | |
| "reward_token": "special", | |
| "loss_type": "btt" | |
| }, | |
| "peft_lora_config": { | |
| "lora_enable": true, | |
| "vision_lora": false, | |
| "lora_r": 64, | |
| "lora_alpha": 128, | |
| "lora_dropout": 0.05, | |
| "lora_target_modules": null, | |
| "lora_namespan_exclude": [ | |
| "lm_head", | |
| "rm_head", | |
| "embed_tokens", | |
| "visual" | |
| ], | |
| "lora_modules_to_save": null, | |
| "lora_task_type": "CAUSAL_LM", | |
| "use_rslora": false, | |
| "num_lora_modules": -1 | |
| }, | |
| "inference_config": { | |
| "VQ_mean": 3.6757, | |
| "VQ_std": 2.2476, | |
| "MQ_mean": 1.1646, | |
| "MQ_std": 1.3811, | |
| "TA_mean": 2.8105, | |
| "TA_std": 2.5121 | |
| } | |
| } |