Delete args.json

args.json

@@ -1,403 +0,0 @@
-{
-  "output_dir": "/data/songshuo.lu/ms-swift/output/v10-20260426-233812",
-  "per_device_train_batch_size": 1,
-  "num_train_epochs": 3.0,
-  "max_steps": -1,
-  "learning_rate": 1e-05,
-  "lr_scheduler_type": "cosine",
-  "lr_scheduler_kwargs": null,
-  "warmup_steps": 50.0,
-  "optim": "adamw_torch_fused",
-  "optim_args": null,
-  "weight_decay": 0.1,
-  "adam_beta1": 0.9,
-  "adam_beta2": 0.95,
-  "adam_epsilon": 1e-08,
-  "optim_target_modules": null,
-  "gradient_accumulation_steps": 16,
-  "average_tokens_across_devices": true,
-  "max_grad_norm": 1.0,
-  "label_smoothing_factor": 0.0,
-  "bf16": true,
-  "fp16": false,
-  "bf16_full_eval": false,
-  "fp16_full_eval": false,
-  "tf32": null,
-  "gradient_checkpointing": true,
-  "gradient_checkpointing_kwargs": null,
-  "torch_compile": false,
-  "torch_compile_backend": null,
-  "torch_compile_mode": null,
-  "use_liger_kernel": false,
-  "liger_kernel_config": null,
-  "use_cache": false,
-  "neftune_noise_alpha": null,
-  "torch_empty_cache_steps": null,
-  "auto_find_batch_size": false,
-  "logging_strategy": "steps",
-  "logging_steps": 1,
-  "logging_first_step": true,
-  "log_on_each_node": true,
-  "logging_nan_inf_filter": true,
-  "include_num_input_tokens_seen": false,
-  "log_level": "passive",
-  "log_level_replica": "warning",
-  "disable_tqdm": null,
-  "report_to": [
-    "tensorboard"
-  ],
-  "run_name": "/data/songshuo.lu/ms-swift/output/v10-20260426-233812",
-  "project": "huggingface",
-  "trackio_space_id": "trackio",
-  "eval_strategy": "steps",
-  "eval_steps": 2000.0,
-  "eval_delay": 0,
-  "per_device_eval_batch_size": 1,
-  "prediction_loss_only": false,
-  "eval_on_start": false,
-  "eval_do_concat_batches": true,
-  "eval_use_gather_object": false,
-  "eval_accumulation_steps": null,
-  "include_for_metrics": [],
-  "batch_eval_metrics": false,
-  "save_only_model": true,
-  "save_strategy": "steps",
-  "save_steps": 50.0,
-  "save_on_each_node": false,
-  "save_total_limit": null,
-  "enable_jit_checkpoint": false,
-  "push_to_hub": false,
-  "hub_token": null,
-  "hub_private_repo": null,
-  "hub_model_id": null,
-  "hub_strategy": "every_save",
-  "hub_always_push": false,
-  "hub_revision": null,
-  "load_best_model_at_end": false,
-  "metric_for_best_model": "loss",
-  "greater_is_better": false,
-  "ignore_data_skip": false,
-  "restore_callback_states_from_checkpoint": false,
-  "full_determinism": false,
-  "seed": 42,
-  "data_seed": 42,
-  "use_cpu": false,
-  "accelerator_config": {
-    "dispatch_batches": false
-  },
-  "parallelism_config": null,
-  "dataloader_drop_last": false,
-  "dataloader_num_workers": 32,
-  "dataloader_pin_memory": true,
-  "dataloader_persistent_workers": false,
-  "dataloader_prefetch_factor": null,
-  "remove_unused_columns": true,
-  "label_names": null,
-  "train_sampling_strategy": "random",
-  "length_column_name": "length",
-  "ddp_find_unused_parameters": null,
-  "ddp_bucket_cap_mb": null,
-  "ddp_broadcast_buffers": null,
-  "ddp_backend": null,
-  "ddp_timeout": 18000000,
-  "fsdp": [],
-  "fsdp_config": null,
-  "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": 3,
-      "offload_optimizer": {
-        "device": "cpu",
-        "pin_memory": true
-      },
-      "offload_param": {
-        "device": "cpu",
-        "pin_memory": true
-      },
-      "overlap_comm": false,
-      "contiguous_gradients": true,
-      "sub_group_size": 1000000000.0,
-      "reduce_bucket_size": "auto",
-      "stage3_prefetch_bucket_size": "auto",
-      "stage3_param_persistence_threshold": "auto",
-      "stage3_max_live_parameters": 1000000000.0,
-      "stage3_max_reuse_distance": 1000000000.0,
-      "stage3_gather_16bit_weights_on_model_save": 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
-  },
-  "debug": null,
-  "skip_memory_metrics": true,
-  "do_train": false,
-  "do_eval": false,
-  "do_predict": false,
-  "resume_from_checkpoint": null,
-  "warmup_ratio": null,
-  "logging_dir": "/data/songshuo.lu/ms-swift/output/v10-20260426-233812/runs",
-  "local_rank": 0,
-  "sortish_sampler": false,
-  "predict_with_generate": false,
-  "generation_max_length": null,
-  "generation_num_beams": null,
-  "generation_config": null,
-  "tuner_backend": "peft",
-  "vit_gradient_checkpointing": false,
-  "router_aux_loss_coef": 0.0,
-  "enable_dft_loss": false,
-  "enable_channel_loss": false,
-  "safe_serialization": true,
-  "max_shard_size": "5GB",
-  "check_model": true,
-  "acc_strategy": "token",
-  "train_dataloader_shuffle": true,
-  "group_by_length": false,
-  "max_epochs": null,
-  "aligner_lr": null,
-  "vit_lr": null,
-  "use_logits_to_keep": null,
-  "ds3_gather_for_generation": true,
-  "resume_only_model": false,
-  "optimizer": null,
-  "loss_type": null,
-  "eval_metric": null,
-  "callbacks": [],
-  "early_stop_interval": null,
-  "eval_use_evalscope": false,
-  "eval_dataset": [],
-  "eval_dataset_args": null,
-  "eval_limit": null,
-  "eval_generation_config": null,
-  "extra_eval_args": null,
-  "tuner_type": "full",
-  "use_galore": false,
-  "galore_target_modules": null,
-  "galore_rank": 128,
-  "galore_update_proj_gap": 50,
-  "galore_scale": 1.0,
-  "galore_proj_type": "std",
-  "galore_optim_per_parameter": false,
-  "galore_with_embedding": false,
-  "galore_quantization": false,
-  "galore_proj_quant": false,
-  "galore_proj_bits": 4,
-  "galore_proj_group_size": 256,
-  "galore_cos_threshold": 0.4,
-  "galore_gamma_proj": 2,
-  "galore_queue_size": 5,
-  "lisa_activated_layers": 0,
-  "lisa_step_interval": 20,
-  "use_flash_ckpt": false,
-  "use_ray": false,
-  "ray_exp_name": null,
-  "device_groups": null,
-  "model": "/data/models/Qwen3.6-27B",
-  "model_type": "qwen3_5",
-  "model_revision": null,
-  "task_type": "causal_lm",
-  "torch_dtype": "bfloat16",
-  "attn_impl": "flash_attention_2",
-  "experts_impl": null,
-  "new_special_tokens": [],
-  "num_labels": null,
-  "problem_type": null,
-  "rope_scaling": null,
-  "device_map": null,
-  "max_memory": {},
-  "max_model_len": null,
-  "local_repo_path": null,
-  "init_strategy": null,
-  "template": "qwen3_5",
-  "system": null,
-  "max_length": 36000,
-  "truncation_strategy": "delete",
-  "max_pixels": null,
-  "agent_template": null,
-  "norm_bbox": null,
-  "use_chat_template": true,
-  "padding_side": "right",
-  "padding_free": false,
-  "loss_scale": "last_round+ignore_empty_think",
-  "sequence_parallel_size": 1,
-  "template_backend": "swift",
-  "response_prefix": null,
-  "enable_thinking": null,
-  "add_non_thinking_prefix": true,
-  "dataset": [
-    "/data/songshuo.lu/datas/sft-v26/general_thinking_5k.jsonl",
-    "/data/songshuo.lu/datas/sft-v26/cuda_agent_6k_k2.5_distill_robust_strict_kernelbench_l2l3_variants.jsonl",
-    "/data/songshuo.lu/datas/sft-v26/cuda_agent_6k_k2.5_distill_robust_strict_mt_l3_v1.jsonl",
-    "/data/songshuo.lu/datas/sft-v26/cuda_agent_6k_k2.5_distill_robust_strict_mt_l3_v2.jsonl",
-    "/data/songshuo.lu/datas/sft-v26/cuda_agent_6k_k2.5_distill_robust_strict_mt_l3_v3.jsonl",
-    "/data/songshuo.lu/datas/sft-v26/cuda_agent_6k_k2.5_distill_robust_strict_mt_l3_v4.jsonl",
-    "/data/songshuo.lu/datas/sft-v26/cuda_agent_6k_k2.5_distill_robust_strict_mt_l3.jsonl",
-    "/data/songshuo.lu/datas/sft-v26/cuda_agent_6k_k2.5_distill_robust_strict_mt_no_bias.jsonl",
-    "/data/songshuo.lu/datas/sft-v26/cuda_agent_6k_k2.5_distill_robust_strict_mt_v1.jsonl",
-    "/data/songshuo.lu/datas/sft-v26/cuda_agent_6k_k2.5_distill_robust_strict_mt_v3.jsonl",
-    "/data/songshuo.lu/datas/sft-v26/cuda_agent_6k_k2.5_distill_short_prompt_mt_v1.jsonl",
-    "/data/songshuo.lu/datas/sft-v26/cuda_agent_6k_k2.5_distill_short_prompt_mt_v2.jsonl",
-    "/data/songshuo.lu/datas/sft-v26/cuda_agent_6k_k2.5_distill_short_prompt_no_bias_st_v2.jsonl",
-    "/data/songshuo.lu/datas/sft-v26/cuda_agent_6k_qwen3_235b_distill_robust_strict_v2.jsonl",
-    "/data/songshuo.lu/datas/sft-v26/cuda_data_ds_v3_distill_torch_op_v1.jsonl",
-    "/data/songshuo.lu/datas/sft-v26/operator_hard_related_qa.jsonl"
-  ],
-  "val_dataset": [
-    "/data/songshuo.lu/datas/sft-v26/cuda_agent_6k_k2.5_distill_robust_strict_mt_l3_v1.jsonl#50"
-  ],
-  "cached_dataset": [],
-  "cached_val_dataset": [],
-  "split_dataset_ratio": 0.0,
-  "dataset_num_proc": 32,
-  "load_from_cache_file": false,
-  "dataset_shuffle": true,
-  "val_dataset_shuffle": false,
-  "streaming": false,
-  "interleave_prob": null,
-  "stopping_strategy": "first_exhausted",
-  "shuffle_buffer_size": 1000,
-  "download_mode": "reuse_dataset_if_exists",
-  "columns": {},
-  "strict": false,
-  "model_name": [
-    "MusaChat-9B-v1"
-  ],
-  "model_author": [
-    "DashLuuu"
-  ],
-  "custom_dataset_info": [],
-  "quant_method": null,
-  "quant_bits": null,
-  "hqq_axis": null,
-  "bnb_4bit_compute_dtype": "bfloat16",
-  "bnb_4bit_quant_type": "nf4",
-  "bnb_4bit_use_double_quant": true,
-  "bnb_4bit_quant_storage": null,
-  "max_new_tokens": 64,
-  "temperature": 0.0,
-  "top_k": null,
-  "top_p": null,
-  "repetition_penalty": null,
-  "num_beams": 1,
-  "stream": false,
-  "stop_words": [],
-  "logprobs": false,
-  "top_logprobs": null,
-  "structured_outputs_regex": null,
-  "adapters": [],
-  "external_plugins": [],
-  "custom_register_path": [],
-  "model_kwargs": {},
-  "load_args": false,
-  "load_data_args": false,
-  "packing": false,
-  "packing_length": null,
-  "packing_num_proc": 1,
-  "lazy_tokenize": true,
-  "use_hf": false,
-  "ignore_args_error": false,
-  "use_swift_lora": false,
-  "freeze_parameters": [
-    "model.visual",
-    "model.visual.merger"
-  ],
-  "freeze_parameters_regex": null,
-  "freeze_parameters_ratio": 0.0,
-  "trainable_parameters": [],
-  "trainable_parameters_regex": null,
-  "freeze_llm": false,
-  "freeze_vit": true,
-  "freeze_aligner": true,
-  "target_modules": [
-    "all-linear"
-  ],
-  "target_regex": null,
-  "target_parameters": null,
-  "modules_to_save": [],
-  "lora_rank": 8,
-  "lora_alpha": 32,
-  "lora_dropout": 0.05,
-  "lora_bias": "none",
-  "lora_dtype": null,
-  "lorap_lr_ratio": null,
-  "use_rslora": false,
-  "use_dora": false,
-  "lora_ga_batch_size": 2,
-  "lora_ga_iters": 2,
-  "lora_ga_max_length": 1024,
-  "lora_ga_direction": "ArB2r",
-  "lora_ga_scale": "stable",
-  "lora_ga_stable_gamma": 16,
-  "init_weights": true,
-  "fourier_n_frequency": 2000,
-  "fourier_scaling": 300.0,
-  "boft_block_size": 4,
-  "boft_block_num": 0,
-  "boft_n_butterfly_factor": 1,
-  "boft_dropout": 0.0,
-  "vera_rank": 256,
-  "vera_projection_prng_key": 0,
-  "vera_dropout": 0.0,
-  "vera_d_initial": 0.1,
-  "adapter_act": "gelu",
-  "adapter_length": 128,
-  "adalora_target_r": 8,
-  "adalora_init_r": 12,
-  "adalora_tinit": 0,
-  "adalora_tfinal": 0,
-  "adalora_deltaT": 1,
-  "adalora_beta1": 0.85,
-  "adalora_beta2": 0.85,
-  "adalora_orth_reg_weight": 0.5,
-  "llamapro_num_new_blocks": 4,
-  "llamapro_num_groups": null,
-  "reft_layer_key": null,
-  "reft_layers": null,
-  "reft_rank": 4,
-  "reft_intervention_type": "LoreftIntervention",
-  "reft_args": null,
-  "swanlab_token": null,
-  "swanlab_project": "ms-swift",
-  "swanlab_workspace": null,
-  "swanlab_exp_name": null,
-  "swanlab_notification_method": null,
-  "swanlab_webhook_url": null,
-  "swanlab_secret": null,
-  "swanlab_sender_email": null,
-  "swanlab_receiver_email": null,
-  "swanlab_smtp_server": null,
-  "swanlab_smtp_port": null,
-  "swanlab_email_language": "zh",
-  "swanlab_mode": "cloud",
-  "add_version": true,
-  "create_checkpoint_symlink": false,
-  "zero_hpz_partition_size": null,
-  "deepspeed_autotp_size": null,
-  "swift_version": "4.2.0.dev0",
-  "ckpt_dir": null,
-  "rank": 0,
-  "global_world_size": 8,
-  "local_world_size": 8,
-  "model_suffix": "Qwen3.6-27B",
-  "model_info": "ModelInfo(model_type='qwen3_5', model_dir='/data/models/Qwen3.6-27B', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=False, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)",
-  "model_meta": "ModelMeta(model_type='qwen3_5', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3.5-0.8B', hf_model_id='Qwen/Qwen3.5-0.8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-2B', hf_model_id='Qwen/Qwen3.5-2B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-4B', hf_model_id='Qwen/Qwen3.5-4B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-9B', hf_model_id='Qwen/Qwen3.5-9B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-27B', hf_model_id='Qwen/Qwen3.5-27B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-27B-FP8', hf_model_id='Qwen/Qwen3.5-27B-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-0.8B-Base', hf_model_id='Qwen/Qwen3.5-0.8B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-2B-Base', hf_model_id='Qwen/Qwen3.5-2B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-4B-Base', hf_model_id='Qwen/Qwen3.5-4B-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.5-9B-Base', hf_model_id='Qwen/Qwen3.5-9B-Base', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_5', ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3.6-27B', hf_model_id='Qwen/Qwen3.6-27B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3.6-27B-FP8', hf_model_id='Qwen/Qwen3.6-27B-FP8', model_path=None, ms_revision=None, hf_revision=None)], template='qwen3_5', ignore_patterns=None, requires=None, tags=[])], loader=<class 'swift.model.models.qwen.Qwen3_5Loader'>, template='qwen3_5', model_arch=MultiModelKeys(arch_name='qwen2_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model', 'lm_head'], aligner=['model.visual.merger'], vision_tower=['model.visual'], generator=[]), mcore_model_type=None, architectures=['Qwen3_5ForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=5.0.0.dev', 'qwen_vl_utils>=0.0.14', 'decord'], tags=[])",
-  "model_dir": "/data/models/Qwen3.6-27B",
-  "template_meta": "QwenTemplateMeta(template_type='qwen3_5', prefix=[], prompt=['<|im_start|>user\\n{{QUERY}}<|im_end|>\\n<|im_start|>assistant\\n'], chat_sep=['<|im_end|>\\n'], suffix=['<|im_end|>\\n'], template_cls=<class 'swift.template.templates.qwen.Qwen3_5Template'>, system_prefix=['<|im_start|>system\\n{{SYSTEM}}<|im_end|>\\n'], default_system=None, auto_add_bos=False, stop_words=['<|endoftext|>'], agent_template='qwen3_5', is_thinking=True, thinking_prefix='<think>\\n', non_thinking_prefix='<think>\\n\\n</think>\\n\\n', history_thinking_prefix='')",
-  "_val_dataset_exists": true,
-  "hub": "<class 'swift.hub.hub.MSHub'>",
-  "evaluation_strategy": "steps",
-  "training_args": "Seq2SeqTrainingArguments(output_dir='/data/songshuo.lu/ms-swift/output/v10-20260426-233812', per_device_train_batch_size=1, num_train_epochs=3.0, max_steps=-1, learning_rate=1e-05, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_steps=50.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, optim_target_modules=None, gradient_accumulation_steps=16, average_tokens_across_devices=None, max_grad_norm=1.0, label_smoothing_factor=0.0, bf16=True, fp16=False, bf16_full_eval=False, fp16_full_eval=False, tf32=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, use_liger_kernel=False, liger_kernel_config=None, use_cache=False, neftune_noise_alpha=None, torch_empty_cache_steps=None, auto_find_batch_size=False, logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_steps=1, logging_first_step=True, log_on_each_node=True, logging_nan_inf_filter=True, include_num_input_tokens_seen=None, log_level='passive', log_level_replica='warning', disable_tqdm=False, report_to=['tensorboard'], run_name='/data/songshuo.lu/ms-swift/output/v10-20260426-233812', project='huggingface', trackio_space_id='trackio', eval_strategy=<IntervalStrategy.STEPS: 'steps'>, eval_steps=2000, eval_delay=0, per_device_eval_batch_size=1, prediction_loss_only=False, eval_on_start=False, eval_do_concat_batches=True, eval_use_gather_object=False, eval_accumulation_steps=None, include_for_metrics=[], batch_eval_metrics=False, save_only_model=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=50, save_on_each_node=False, save_total_limit=None, enable_jit_checkpoint=False, push_to_hub=False, hub_token=None, hub_private_repo=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_always_push=False, hub_revision=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, restore_callback_states_from_checkpoint=False, full_determinism=False, seed=42, data_seed=42, use_cpu=False, 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), parallelism_config=None, dataloader_drop_last=False, dataloader_num_workers=32, dataloader_pin_memory=True, dataloader_persistent_workers=False, dataloader_prefetch_factor=2, remove_unused_columns=False, label_names=None, train_sampling_strategy='random', length_column_name='length', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, ddp_backend=None, ddp_timeout=18000000, fsdp=[], fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': 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': 3, 'offload_optimizer': {'device': 'cpu', 'pin_memory': True}, 'offload_param': {'device': 'cpu', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': 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}, debug=[], skip_memory_metrics=True, do_train=False, do_eval=True, do_predict=False, resume_from_checkpoint=None, warmup_ratio=None, logging_dir='/data/songshuo.lu/ms-swift/output/v10-20260426-233812/runs', local_rank=0, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=False, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, safe_serialization=True, max_shard_size='5GB', check_model=True, acc_strategy='token', train_dataloader_shuffle=True, group_by_length=False, max_epochs=None, aligner_lr=None, vit_lr=None, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer=None, loss_type=None, eval_metric=None, callbacks=[], early_stop_interval=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, tuner_type='full', use_galore=False, galore_target_modules=None, galore_rank=128, galore_update_proj_gap=50, galore_scale=1.0, galore_proj_type='std', galore_optim_per_parameter=False, galore_with_embedding=False, galore_quantization=False, galore_proj_quant=False, galore_proj_bits=4, galore_proj_group_size=256, galore_cos_threshold=0.4, galore_gamma_proj=2, galore_queue_size=5, lisa_activated_layers=0, lisa_step_interval=20, use_flash_ckpt=False)"
-}