| { |
| "output_dir": "/workspace/output/ministral-3-3b-base_cp-v1.2.1-s0/v0-20260113-151513", |
| "do_train": false, |
| "do_eval": false, |
| "do_predict": false, |
| "eval_strategy": "no", |
| "prediction_loss_only": false, |
| "per_device_train_batch_size": 3, |
| "per_device_eval_batch_size": 4, |
| "gradient_accumulation_steps": 16, |
| "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": 1.0, |
| "num_train_epochs": 2.0, |
| "max_steps": -1, |
| "lr_scheduler_type": "cosine", |
| "lr_scheduler_kwargs": null, |
| "warmup_ratio": 0.05, |
| "warmup_steps": 0, |
| "log_level": "passive", |
| "log_level_replica": "warning", |
| "log_on_each_node": true, |
| "logging_dir": "/workspace/output/ministral-3-3b-base_cp-v1.2.1-s0/v0-20260113-151513/runs", |
| "logging_strategy": "steps", |
| "logging_first_step": true, |
| "logging_steps": 2, |
| "logging_nan_inf_filter": true, |
| "save_strategy": "steps", |
| "save_steps": 50.0, |
| "save_total_limit": 3, |
| "enable_jit_checkpoint": false, |
| "save_on_each_node": false, |
| "save_only_model": false, |
| "restore_callback_states_from_checkpoint": false, |
| "use_cpu": false, |
| "seed": 42, |
| "data_seed": 42, |
| "bf16": true, |
| "fp16": false, |
| "bf16_full_eval": false, |
| "fp16_full_eval": false, |
| "tf32": null, |
| "local_rank": 0, |
| "ddp_backend": null, |
| "debug": null, |
| "dataloader_drop_last": false, |
| "eval_steps": 50.0, |
| "dataloader_num_workers": 0, |
| "dataloader_prefetch_factor": null, |
| "run_name": "ministral-3-3b-base_cp-v1.2.1-s0", |
| "disable_tqdm": null, |
| "remove_unused_columns": true, |
| "label_names": null, |
| "load_best_model_at_end": false, |
| "metric_for_best_model": "loss", |
| "greater_is_better": false, |
| "ignore_data_skip": false, |
| "fsdp": [], |
| "fsdp_config": null, |
| "accelerator_config": { |
| "dispatch_batches": false |
| }, |
| "parallelism_config": null, |
| "deepspeed": null, |
| "label_smoothing_factor": 0.0, |
| "optim": "adamw_8bit", |
| "optim_args": null, |
| "group_by_length": false, |
| "length_column_name": "length", |
| "report_to": [ |
| "tensorboard" |
| ], |
| "project": "huggingface", |
| "trackio_space_id": "trackio", |
| "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, |
| "push_to_hub": false, |
| "resume_from_checkpoint": null, |
| "hub_model_id": null, |
| "hub_strategy": "every_save", |
| "hub_token": null, |
| "hub_private_repo": null, |
| "hub_always_push": false, |
| "hub_revision": null, |
| "gradient_checkpointing": true, |
| "gradient_checkpointing_kwargs": null, |
| "include_for_metrics": [], |
| "eval_do_concat_batches": true, |
| "auto_find_batch_size": false, |
| "full_determinism": false, |
| "ddp_timeout": 18000000, |
| "torch_compile": false, |
| "torch_compile_backend": null, |
| "torch_compile_mode": null, |
| "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": true, |
| "liger_kernel_config": null, |
| "eval_use_gather_object": false, |
| "average_tokens_across_devices": true, |
| "use_cache": false, |
| "sortish_sampler": false, |
| "predict_with_generate": false, |
| "generation_max_length": null, |
| "generation_num_beams": null, |
| "generation_config": null, |
| "tuner_backend": "peft", |
| "vit_gradient_checkpointing": null, |
| "router_aux_loss_coef": 0.0, |
| "enable_dft_loss": false, |
| "enable_channel_loss": false, |
| "check_model": true, |
| "acc_strategy": "token", |
| "train_dataloader_shuffle": true, |
| "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, |
| "metric": null, |
| "eval_use_evalscope": false, |
| "eval_dataset": [], |
| "eval_dataset_args": null, |
| "eval_limit": null, |
| "eval_generation_config": null, |
| "extra_eval_args": null, |
| "use_flash_ckpt": false, |
| "use_ray": false, |
| "ray_exp_name": null, |
| "device_groups": null, |
| "model": "/workspace/model/Ministral-3-3B-Base-2512", |
| "model_type": "mistral_2512", |
| "model_revision": null, |
| "task_type": "causal_lm", |
| "torch_dtype": "bfloat16", |
| "attn_impl": "flash_attention_2", |
| "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": "mistral_2512", |
| "system": null, |
| "max_length": 10240, |
| "truncation_strategy": "delete", |
| "max_pixels": null, |
| "agent_template": null, |
| "norm_bbox": null, |
| "use_chat_template": false, |
| "padding_side": "right", |
| "padding_free": true, |
| "loss_scale": "all", |
| "sequence_parallel_size": 1, |
| "template_backend": "swift", |
| "response_prefix": null, |
| "enable_thinking": null, |
| "add_non_thinking_prefix": true, |
| "dataset": [ |
| "/workspace/cp_data/data/train-00000-of-00010.parquet", |
| "/workspace/cp_data/data/train-00001-of-00010.parquet", |
| "/workspace/cp_data/data/train-00002-of-00010.parquet", |
| "/workspace/cp_data/data/train-00003-of-00010.parquet", |
| "/workspace/cp_data/data/train-00004-of-00010.parquet", |
| "/workspace/cp_data/data/train-00005-of-00010.parquet", |
| "/workspace/cp_data/data/train-00006-of-00010.parquet", |
| "/workspace/cp_data/data/train-00007-of-00010.parquet", |
| "/workspace/cp_data/data/train-00008-of-00010.parquet", |
| "/workspace/cp_data/data/train-00009-of-00010.parquet" |
| ], |
| "val_dataset": [], |
| "cached_dataset": [], |
| "cached_val_dataset": [], |
| "split_dataset_ratio": 0.0, |
| "dataset_num_proc": 60, |
| "load_from_cache_file": true, |
| "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": null, |
| "model_author": null, |
| "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, |
| "ckpt_dir": null, |
| "lora_modules": [], |
| "train_type": "full", |
| "adapters": [], |
| "external_plugins": [], |
| "model_kwargs": {}, |
| "load_args": false, |
| "load_data_args": false, |
| "packing": true, |
| "packing_length": 10240, |
| "packing_num_proc": 1, |
| "lazy_tokenize": false, |
| "custom_register_path": [], |
| "use_hf": true, |
| "ignore_args_error": false, |
| "use_swift_lora": false, |
| "freeze_parameters": [ |
| "model.vision_tower", |
| "model.multi_modal_projector" |
| ], |
| "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, |
| "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, |
| "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, |
| "lisa_activated_layers": 0, |
| "lisa_step_interval": 20, |
| "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_mode": "cloud", |
| "add_version": true, |
| "create_checkpoint_symlink": false, |
| "zero_hpz_partition_size": null, |
| "deepspeed_autotp_size": null, |
| "early_stop_interval": null, |
| "rank": 0, |
| "global_world_size": 2, |
| "local_world_size": 2, |
| "model_suffix": "Ministral-3-3B-Base-2512", |
| "model_info": "ModelInfo(model_type='mistral_2512', model_dir='/workspace/model/Ministral-3-3B-Base-2512', 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='mistral_2512', model_groups=[ModelGroup(models=[Model(ms_model_id='mistralai/Ministral-3-3B-Base-2512', hf_model_id='mistralai/Ministral-3-3B-Base-2512', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='mistralai/Ministral-3-3B-Instruct-2512', hf_model_id='mistralai/Ministral-3-3B-Instruct-2512', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='mistralai/Ministral-3-3B-Instruct-2512-BF16', hf_model_id='mistralai/Ministral-3-3B-Instruct-2512-BF16', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='mistralai/Ministral-3-8B-Base-2512', hf_model_id='mistralai/Ministral-3-8B-Base-2512', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='mistralai/Ministral-3-8B-Instruct-2512', hf_model_id='mistralai/Ministral-3-8B-Instruct-2512', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='mistralai/Ministral-3-8B-Instruct-2512-BF16', hf_model_id='mistralai/Ministral-3-8B-Instruct-2512-BF16', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='mistralai/Ministral-3-14B-Base-2512', hf_model_id='mistralai/Ministral-3-14B-Base-2512', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='mistralai/Ministral-3-14B-Instruct-2512', hf_model_id='mistralai/Ministral-3-14B-Instruct-2512', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='mistralai/Ministral-3-14B-Instruct-2512-BF16', hf_model_id='mistralai/Ministral-3-14B-Instruct-2512-BF16', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='mistral_2512', get_function=<function get_model_tokenizer_mistral_2512 at 0x7f5f1c2f7ce0>, model_arch=MultiModelKeys(arch_name='llava_hf', 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.multi_modal_projector'], vision_tower=['model.vision_tower'], generator=[]), architectures=['Mistral3ForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=[], requires=['transformers>=5.0.0.dev0', 'mistral-common>=1.8.6'], tags=['vision'])", |
| "model_dir": "/workspace/model/Ministral-3-3B-Base-2512", |
| "_val_dataset_exists": [], |
| "hub": "<class 'swift.hub.hub.HFHub'>", |
| "evaluation_strategy": "steps", |
| "training_args": "Seq2SeqTrainingArguments(output_dir='/workspace/output/ministral-3-3b-base_cp-v1.2.1-s0/v0-20260113-151513', do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=3, per_device_eval_batch_size=4, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=5e-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=2.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0.05, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/workspace/output/ministral-3-3b-base_cp-v1.2.1-s0/v0-20260113-151513/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=2, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=50, save_total_limit=3, enable_jit_checkpoint=False, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, use_cpu=False, seed=42, data_seed=42, bf16=True, fp16=False, bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, debug=[], dataloader_drop_last=False, eval_steps=50.0, dataloader_num_workers=0, dataloader_prefetch_factor=None, run_name='ministral-3-3b-base_cp-v1.2.1-s0', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': 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, deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_8BIT: 'adamw_8bit'>, optim_args=None, group_by_length=False, length_column_name='length', report_to=['tensorboard'], project='huggingface', trackio_space_id='trackio', 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, 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_for_metrics=[], eval_do_concat_batches=True, auto_find_batch_size=False, full_determinism=False, ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, 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, use_cache=False, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, 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, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, train_type='full', local_repo_path=None, galore_config=None, task_type='causal_lm', problem_type=None)" |
| } |
