ACE-Step/acestep-captioner

1{2  "output_dir": "/root/data/repo/keylxiao/audio_caption_gemma_3n_ft/swift_full_output_0813/audio_caption_describer_full_length_grpo",3  "overwrite_output_dir": false,4  "do_train": false,5  "do_eval": false,6  "do_predict": false,7  "eval_strategy": "no",8  "prediction_loss_only": false,9  "per_device_train_batch_size": 1,10  "per_device_eval_batch_size": 1,11  "per_gpu_train_batch_size": null,12  "per_gpu_eval_batch_size": null,13  "gradient_accumulation_steps": 1,14  "eval_accumulation_steps": null,15  "eval_delay": 0,16  "torch_empty_cache_steps": null,17  "learning_rate": 1e-05,18  "weight_decay": 0.1,19  "adam_beta1": 0.9,20  "adam_beta2": 0.95,21  "adam_epsilon": 1e-08,22  "max_grad_norm": 1.0,23  "num_train_epochs": 3.0,24  "max_steps": 10000,25  "lr_scheduler_type": "cosine",26  "lr_scheduler_kwargs": null,27  "warmup_ratio": 0.01,28  "warmup_steps": 0,29  "log_level": "passive",30  "log_level_replica": "warning",31  "log_on_each_node": true,32  "logging_dir": "/root/data/repo/keylxiao/audio_caption_gemma_3n_ft/swift_full_output_0813/audio_caption_describer_full_length_grpo/runs",33  "logging_strategy": "steps",34  "logging_first_step": true,35  "logging_steps": 5,36  "logging_nan_inf_filter": true,37  "save_strategy": "steps",38  "save_steps": 500.0,39  "save_total_limit": 5,40  "save_safetensors": true,41  "save_on_each_node": false,42  "save_only_model": true,43  "restore_callback_states_from_checkpoint": false,44  "no_cuda": false,45  "use_cpu": false,46  "use_mps_device": false,47  "seed": 42,48  "data_seed": 42,49  "jit_mode_eval": false,50  "use_ipex": false,51  "bf16": true,52  "fp16": false,53  "fp16_opt_level": "O1",54  "half_precision_backend": "auto",55  "bf16_full_eval": false,56  "fp16_full_eval": false,57  "tf32": null,58  "local_rank": 0,59  "ddp_backend": null,60  "tpu_num_cores": null,61  "tpu_metrics_debug": false,62  "debug": null,63  "dataloader_drop_last": false,64  "eval_steps": 500.0,65  "dataloader_num_workers": 8,66  "dataloader_prefetch_factor": null,67  "past_index": -1,68  "run_name": "/root/data/repo/keylxiao/audio_caption_gemma_3n_ft/swift_full_output_0813/audio_caption_describer_full_length_grpo",69  "disable_tqdm": null,70  "remove_unused_columns": false,71  "label_names": null,72  "load_best_model_at_end": false,73  "metric_for_best_model": "reward",74  "greater_is_better": true,75  "ignore_data_skip": false,76  "fsdp": "",77  "fsdp_min_num_params": 0,78  "fsdp_config": null,79  "fsdp_transformer_layer_cls_to_wrap": null,80  "accelerator_config": {81    "dispatch_batches": false82  },83  "deepspeed": {84    "fp16": {85      "enabled": "auto",86      "loss_scale": 0,87      "loss_scale_window": 1000,88      "initial_scale_power": 16,89      "hysteresis": 2,90      "min_loss_scale": 191    },92    "bf16": {93      "enabled": "auto"94    },95    "zero_optimization": {96      "stage": 2,97      "offload_optimizer": {98        "device": "none",99        "pin_memory": true100      },101      "allgather_partitions": true,102      "allgather_bucket_size": 200000000.0,103      "overlap_comm": false,104      "reduce_scatter": true,105      "reduce_bucket_size": 200000000.0,106      "contiguous_gradients": true107    },108    "gradient_accumulation_steps": "auto",109    "gradient_clipping": "auto",110    "steps_per_print": 2000,111    "train_batch_size": "auto",112    "train_micro_batch_size_per_gpu": "auto",113    "wall_clock_breakdown": false114  },115  "label_smoothing_factor": 0.0,116  "optim": "adamw_torch",117  "optim_args": null,118  "adafactor": false,119  "group_by_length": false,120  "length_column_name": "length",121  "report_to": [122    "tensorboard"123  ],124  "ddp_find_unused_parameters": null,125  "ddp_bucket_cap_mb": null,126  "ddp_broadcast_buffers": null,127  "dataloader_pin_memory": true,128  "dataloader_persistent_workers": false,129  "skip_memory_metrics": true,130  "use_legacy_prediction_loop": false,131  "push_to_hub": false,132  "resume_from_checkpoint": null,133  "hub_model_id": null,134  "hub_strategy": "every_save",135  "hub_token": null,136  "hub_private_repo": null,137  "hub_always_push": false,138  "hub_revision": null,139  "gradient_checkpointing": true,140  "gradient_checkpointing_kwargs": null,141  "include_inputs_for_metrics": false,142  "include_for_metrics": [],143  "eval_do_concat_batches": true,144  "fp16_backend": "auto",145  "push_to_hub_model_id": null,146  "push_to_hub_organization": null,147  "push_to_hub_token": null,148  "mp_parameters": "",149  "auto_find_batch_size": false,150  "full_determinism": false,151  "torchdynamo": null,152  "ray_scope": "last",153  "ddp_timeout": 18000000,154  "torch_compile": false,155  "torch_compile_backend": null,156  "torch_compile_mode": null,157  "include_tokens_per_second": false,158  "include_num_input_tokens_seen": false,159  "neftune_noise_alpha": 0.0,160  "optim_target_modules": null,161  "batch_eval_metrics": false,162  "eval_on_start": false,163  "use_liger_kernel": true,164  "liger_kernel_config": null,165  "eval_use_gather_object": false,166  "average_tokens_across_devices": false,167  "sortish_sampler": false,168  "predict_with_generate": false,169  "generation_max_length": null,170  "generation_num_beams": null,171  "generation_config": null,172  "vit_gradient_checkpointing": null,173  "check_model": true,174  "acc_strategy": "token",175  "train_dataloader_shuffle": true,176  "max_epochs": null,177  "aligner_lr": null,178  "vit_lr": null,179  "optimizer": null,180  "use_logits_to_keep": null,181  "channels": null,182  "ds3_gather_for_generation": true,183  "resume_only_model": false,184  "metric_warmup_step": 0,185  "fsdp_num": 1,186  "acc_steps": 1,187  "eval_use_evalscope": false,188  "eval_dataset": [],189  "eval_dataset_args": null,190  "eval_limit": null,191  "eval_generation_config": null,192  "model": "/root/data/repo/keylxiao/audio_caption_gemma_3n_ft/swift_full_output_0813/audio_caption_describer_full_length/checkpoint-60000",193  "model_type": "qwen2_5_omni",194  "model_revision": null,195  "task_type": "causal_lm",196  "torch_dtype": "bfloat16",197  "attn_impl": "flash_attn",198  "new_special_tokens": [],199  "num_labels": null,200  "problem_type": null,201  "rope_scaling": null,202  "device_map": null,203  "max_memory": {},204  "local_repo_path": null,205  "init_strategy": null,206  "template": "qwen2_5_omni",207  "system": null,208  "max_length": 16384,209  "truncation_strategy": "left",210  "max_pixels": null,211  "agent_template": null,212  "norm_bbox": null,213  "use_chat_template": true,214  "padding_free": false,215  "padding_side": "right",216  "loss_scale": "last_round",217  "sequence_parallel_size": 1,218  "response_prefix": null,219  "template_backend": "swift",220  "dataset": [221    "/root/data/repo/gongjunmin/acestep_v15_train/data/ace_step_v15/gemini_captions_qwen3_30b_moe/omini_audio_caption_caption_model_train_data_5M.parquet"222  ],223  "val_dataset": [],224  "split_dataset_ratio": 0.0,225  "dataset_num_proc": 1,226  "load_from_cache_file": true,227  "dataset_shuffle": true,228  "val_dataset_shuffle": false,229  "streaming": false,230  "interleave_prob": null,231  "stopping_strategy": "first_exhausted",232  "shuffle_buffer_size": 1000,233  "download_mode": "reuse_dataset_if_exists",234  "columns": {},235  "strict": false,236  "model_name": null,237  "model_author": null,238  "custom_dataset_info": [],239  "quant_method": null,240  "quant_bits": null,241  "hqq_axis": null,242  "bnb_4bit_compute_dtype": "bfloat16",243  "bnb_4bit_quant_type": "nf4",244  "bnb_4bit_use_double_quant": true,245  "bnb_4bit_quant_storage": null,246  "max_new_tokens": 512,247  "temperature": 0.7,248  "top_k": 50,249  "top_p": 0.99,250  "repetition_penalty": 1.0,251  "num_beams": 1,252  "stream": false,253  "stop_words": [],254  "logprobs": false,255  "top_logprobs": null,256  "ckpt_dir": "/root/data/repo/keylxiao/audio_caption_gemma_3n_ft/swift_full_output_0813/audio_caption_describer_full_length/checkpoint-60000",257  "lora_modules": [],258  "tuner_backend": "peft",259  "train_type": "full",260  "adapters": [],261  "external_plugins": [262    "/root/data/repo/keylxiao/audio_caption_gemma_3n_ft/ms-swift/examples/train/grpo/plugin/plugin.py"263  ],264  "model_kwargs": {},265  "load_args": false,266  "load_data_args": false,267  "packing": false,268  "custom_register_path": [],269  "use_hf": false,270  "ignore_args_error": true,271  "use_swift_lora": false,272  "freeze_parameters": [273    "thinker.audio_tower",274    "thinker.visual",275    "thinker.audio_tower.proj",276    "thinker.visual.merger",277    "talker",278    "token2wav"279  ],280  "freeze_parameters_regex": null,281  "freeze_parameters_ratio": 0.0,282  "trainable_parameters": [],283  "trainable_parameters_regex": null,284  "freeze_llm": false,285  "freeze_vit": true,286  "freeze_aligner": true,287  "target_modules": [288    "all-linear"289  ],290  "target_regex": null,291  "modules_to_save": [],292  "lora_rank": 8,293  "lora_alpha": 32,294  "lora_dropout": 0.05,295  "lora_bias": "none",296  "lora_dtype": null,297  "lorap_lr_ratio": null,298  "use_rslora": false,299  "use_dora": false,300  "lora_ga_batch_size": 2,301  "lora_ga_iters": 2,302  "lora_ga_max_length": 1024,303  "lora_ga_direction": "ArB2r",304  "lora_ga_scale": "stable",305  "lora_ga_stable_gamma": 16,306  "init_weights": true,307  "fourier_n_frequency": 2000,308  "fourier_scaling": 300.0,309  "boft_block_size": 4,310  "boft_block_num": 0,311  "boft_n_butterfly_factor": 1,312  "boft_dropout": 0.0,313  "vera_rank": 256,314  "vera_projection_prng_key": 0,315  "vera_dropout": 0.0,316  "vera_d_initial": 0.1,317  "adapter_act": "gelu",318  "adapter_length": 128,319  "use_galore": false,320  "galore_target_modules": null,321  "galore_rank": 128,322  "galore_update_proj_gap": 50,323  "galore_scale": 1.0,324  "galore_proj_type": "std",325  "galore_optim_per_parameter": false,326  "galore_with_embedding": false,327  "galore_quantization": false,328  "galore_proj_quant": false,329  "galore_proj_bits": 4,330  "galore_proj_group_size": 256,331  "galore_cos_threshold": 0.4,332  "galore_gamma_proj": 2,333  "galore_queue_size": 5,334  "adalora_target_r": 8,335  "adalora_init_r": 12,336  "adalora_tinit": 0,337  "adalora_tfinal": 0,338  "adalora_deltaT": 1,339  "adalora_beta1": 0.85,340  "adalora_beta2": 0.85,341  "adalora_orth_reg_weight": 0.5,342  "llamapro_num_new_blocks": 4,343  "llamapro_num_groups": null,344  "lisa_activated_layers": 0,345  "lisa_step_interval": 20,346  "reft_layer_key": null,347  "reft_layers": null,348  "reft_rank": 4,349  "reft_intervention_type": "LoreftIntervention",350  "reft_args": null,351  "swanlab_token": null,352  "swanlab_project": null,353  "swanlab_workspace": null,354  "swanlab_exp_name": null,355  "swanlab_lark_webhook_url": null,356  "swanlab_lark_secret": null,357  "swanlab_mode": "cloud",358  "add_version": false,359  "create_checkpoint_symlink": false,360  "lazy_tokenize": true,361  "loss_type": "grpo",362  "metric": null,363  "zero_hpz_partition_size": null,364  "sft_alpha": 0,365  "reward_model": [366    "/root/data/repo/keylxiao/audio_caption_gemma_3n_ft/swift_full_output_0813/audio_caption_reward_full_length_rlhf/checkpoint-20000"367  ],368  "reward_adapters": [],369  "reward_model_type": null,370  "reward_model_revision": null,371  "num_ppo_epochs": 4,372  "whiten_rewards": false,373  "kl_coef": 0.05,374  "cliprange": 0.2,375  "vf_coef": 0.1,376  "cliprange_value": 0.2,377  "gamma": 1.0,378  "lam": 0.95,379  "num_mini_batches": 1,380  "local_rollout_forward_batch_size": 64,381  "num_sample_generations": 10,382  "response_length": 512,383  "missing_eos_penalty": null,384  "vllm_gpu_memory_utilization": 0.85,385  "vllm_tensor_parallel_size": 2,386  "vllm_pipeline_parallel_size": 1,387  "vllm_max_num_seqs": 256,388  "vllm_max_model_len": 16384,389  "vllm_disable_custom_all_reduce": true,390  "vllm_enforce_eager": false,391  "vllm_limit_mm_per_prompt": {},392  "vllm_max_lora_rank": 16,393  "vllm_enable_prefix_caching": true,394  "vllm_use_async_engine": false,395  "vllm_quantization": null,396  "vllm_data_parallel_size": 1,397  "gpu_memory_utilization": null,398  "tensor_parallel_size": null,399  "max_model_len": null,400  "limit_mm_per_prompt": null,401  "data_parallel_size": null,402  "use_async_engine": null,403  "epsilon": 0.2,404  "epsilon_high": null,405  "delta": null,406  "vllm_mode": "colocate",407  "vllm_server_base_url": null,408  "vllm_server_host": null,409  "vllm_server_port": [410    8000411  ],412  "vllm_server_timeout": 240.0,413  "cosine_min_len_value_wrong": -0.5,414  "cosine_max_len_value_wrong": 0.0,415  "cosine_min_len_value_correct": 1.0,416  "cosine_max_len_value_correct": 0.5,417  "cosine_max_len": null,418  "repetition_n_grams": 3,419  "repetition_max_penalty": -1.0,420  "reward_model_plugin": [421    "audio_caption_rm"422  ],423  "sync_ref_model": false,424  "ref_model_sync_steps": 512,425  "ref_model_mixup_alpha": 0.6,426  "async_generate": false,427  "sleep_level": 1,428  "move_model_batches": 8,429  "offload_optimizer": true,430  "offload_model": true,431  "gc_collect_after_offload": false,432  "multi_turn_func": null,433  "multi_turn_scheduler": null,434  "max_turns": null,435  "completion_length_limit_scope": "per_round",436  "dynamic_sample": false,437  "max_resample_times": 3,438  "overlong_filter": false,439  "soft_max_length": null,440  "soft_cache_length": null,441  "scale_rewards": true,442  "log_entropy": false,443  "top_entropy_quantile": 1.0,444  "wandb_log_unique_prompts": null,445  "generation_batch_size": null,446  "steps_per_generation": null,447  "num_generations": 8,448  "reward_funcs": [],449  "reward_weights": [450    1.0451  ],452  "log_completions": true,453  "use_vllm": true,454  "num_iterations": 1,455  "teacher_model": null,456  "teacher_adapters": [],457  "teacher_model_type": null,458  "teacher_model_revision": null,459  "rlhf_type": "grpo",460  "ref_model": "/root/data/repo/keylxiao/audio_caption_gemma_3n_ft/swift_full_output_0813/audio_caption_describer_full_length/checkpoint-60000",461  "ref_model_type": "qwen2_5_omni",462  "ref_model_revision": null,463  "beta": 0.04,464  "label_smoothing": 0,465  "max_completion_length": 512,466  "rpo_alpha": 1.0,467  "cpo_alpha": 1.0,468  "simpo_gamma": 1,469  "desirable_weight": 1.0,470  "undesirable_weight": 1.0,471  "center_rewards_coefficient": null,472  "lmbda": 0.5,473  "seq_kd": false,474  "rank": 0,475  "global_world_size": 8,476  "local_world_size": 8,477  "model_suffix": "checkpoint-60000",478  "model_info": "ModelInfo(model_type='qwen2_5_omni', model_dir='/root/data/repo/keylxiao/audio_caption_gemma_3n_ft/swift_full_output_0813/audio_caption_describer_full_length/checkpoint-60000', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling={'mrope_section': [16, 24, 24], 'rope_type': 'default', 'type': 'default'}, is_moe_model=False, config=None, task_type='causal_lm', num_labels=None)",479  "model_meta": "ModelMeta(model_type='qwen2_5_omni', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-Omni-3B', hf_model_id='Qwen/Qwen2.5-Omni-3B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-Omni-7B', hf_model_id='Qwen/Qwen2.5-Omni-7B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_omni', get_function=<function get_model_tokenizer_qwen2_5_omni at 0x7f90f9821510>, model_arch='qwen2_5_omni', architectures=['Qwen2_5OmniModel', 'Qwen2_5OmniForConditionalGeneration'], additional_saved_files=['spk_dict.pt'], torch_dtype=None, is_multimodal=True, is_reward=True, task_type=None, ignore_patterns=[], requires=['transformers>=4.50', 'soundfile', 'qwen_omni_utils', 'decord'], tags=['vision', 'video', 'audio'])",480  "model_dir": "/root/data/repo/keylxiao/audio_caption_gemma_3n_ft/swift_full_output_0813/audio_caption_describer_full_length/checkpoint-60000",481  "hub": "<class 'swift.hub.hub.MSHub'>",482  "evaluation_strategy": "steps",483  "training_args": "GRPOConfig(output_dir='/root/data/repo/keylxiao/audio_caption_gemma_3n_ft/swift_full_output_0813/audio_caption_describer_full_length_grpo', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=1, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=3.0, max_steps=10000, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.01, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/root/data/repo/keylxiao/audio_caption_gemma_3n_ft/swift_full_output_0813/audio_caption_describer_full_length_grpo/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=500, save_total_limit=5, 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=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=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=True, eval_steps=500.0, dataloader_num_workers=8, dataloader_prefetch_factor=10, past_index=-1, run_name='/root/data/repo/keylxiao/audio_caption_gemma_3n_ft/swift_full_output_0813/audio_caption_describer_full_length_grpo', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='reward', greater_is_better=True, 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=None, 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={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 2, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=0.0, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=True, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, model_init_kwargs=None, disable_dropout=False, max_prompt_length=512, num_generations=8, max_completion_length=512, ds3_gather_for_generation=True, shuffle_dataset=True, generation_batch_size=8, steps_per_generation=1, temperature=0.7, top_p=0.99, top_k=50, min_p=None, generation_kwargs=None, repetition_penalty=1.0, cache_implementation=None, use_vllm=True, vllm_server_base_url=None, vllm_mode='colocate', vllm_guided_decoding_regex=None, vllm_server_host=None, vllm_server_port=[8000], vllm_server_timeout=240.0, vllm_gpu_memory_utilization=0.85, vllm_tensor_parallel_size=2, beta=0.04, num_iterations=1, epsilon=0.2, delta=None, epsilon_high=None, reward_weights=[1.0], scale_rewards=True, loss_type='grpo', mask_truncated_completions=False, sync_ref_model=False, ref_model_mixup_alpha=0.6, ref_model_sync_steps=512, use_liger_loss=False, log_completions=True, num_completions_to_print=None, wandb_log_unique_prompts=None, vit_gradient_checkpointing=True, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, optimizer=None, use_logits_to_keep=None, channels=None, resume_only_model=False, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, sft_alpha=0, train_type='full', local_repo_path=None, galore_config=None, vllm_pipeline_parallel_size=1, vllm_max_num_seqs=256, vllm_max_model_len=16384, vllm_disable_custom_all_reduce=True, vllm_enforce_eager=False, vllm_limit_mm_per_prompt={}, vllm_max_lora_rank=16, vllm_enable_prefix_caching=True, vllm_use_async_engine=False, vllm_quantization=None, vllm_data_parallel_size=1, gpu_memory_utilization=None, tensor_parallel_size=None, max_model_len=None, limit_mm_per_prompt=None, data_parallel_size=None, use_async_engine=None, cosine_min_len_value_wrong=-0.5, cosine_max_len_value_wrong=0.0, cosine_min_len_value_correct=1.0, cosine_max_len_value_correct=0.5, cosine_max_len=512, repetition_n_grams=3, repetition_max_penalty=-1.0, reward_model=['/root/data/repo/keylxiao/audio_caption_gemma_3n_ft/swift_full_output_0813/audio_caption_reward_full_length_rlhf/checkpoint-20000'], reward_model_plugin=['audio_caption_rm'], async_generate=False, sleep_level=1, move_model_batches=8, offload_optimizer=True, offload_model=True, gc_collect_after_offload=False, multi_turn_func=None, multi_turn_scheduler=None, max_turns=None, completion_length_limit_scope='per_round', dynamic_sample=False, max_resample_times=3, overlong_filter=False, soft_max_length=None, soft_cache_length=None, log_entropy=False, top_entropy_quantile=1.0, dataset_shuffle=True, stop_words=[])"484}