| { | |
| "model_type": "phi3_5-mini-instruct", | |
| "model_id_or_path": "microsoft/Phi-3.5-mini-instruct", | |
| "model_revision": "master", | |
| "full_determinism": false, | |
| "sft_type": "full", | |
| "freeze_parameters": [], | |
| "freeze_vit": false, | |
| "freeze_parameters_ratio": 0.0, | |
| "additional_trainable_parameters": [], | |
| "tuner_backend": "peft", | |
| "template_type": "phi3", | |
| "output_dir": "/root/ms-swift/output/phi3_5-mini-instruct/v0-20240922-181523", | |
| "add_output_dir_suffix": true, | |
| "ddp_backend": null, | |
| "ddp_find_unused_parameters": null, | |
| "ddp_broadcast_buffers": null, | |
| "ddp_timeout": 1800, | |
| "seed": 42, | |
| "resume_from_checkpoint": null, | |
| "resume_only_model": false, | |
| "ignore_data_skip": false, | |
| "dtype": "bf16", | |
| "packing": false, | |
| "train_backend": "transformers", | |
| "tp": 1, | |
| "pp": 1, | |
| "min_lr": null, | |
| "sequence_parallel": false, | |
| "model_kwargs": {}, | |
| "loss_name": null, | |
| "dataset": [ | |
| "Cossale/informal-to-professional-kto" | |
| ], | |
| "val_dataset": [], | |
| "dataset_seed": 42, | |
| "dataset_test_ratio": 0.01, | |
| "use_loss_scale": false, | |
| "loss_scale_config_path": "/root/ms-swift/swift/llm/agent/default_loss_scale_config.json", | |
| "system": null, | |
| "tools_prompt": "react_en", | |
| "max_length": 8192, | |
| "truncation_strategy": "delete", | |
| "check_dataset_strategy": "warning", | |
| "streaming": false, | |
| "streaming_val_size": 0, | |
| "streaming_buffer_size": 16384, | |
| "model_name": [ | |
| null, | |
| null | |
| ], | |
| "model_author": [ | |
| null, | |
| null | |
| ], | |
| "quant_method": null, | |
| "quantization_bit": 0, | |
| "hqq_axis": 0, | |
| "hqq_dynamic_config_path": null, | |
| "bnb_4bit_comp_dtype": "bf16", | |
| "bnb_4bit_quant_type": "nf4", | |
| "bnb_4bit_use_double_quant": true, | |
| "bnb_4bit_quant_storage": null, | |
| "rescale_image": -1, | |
| "target_modules": [ | |
| "qkv_proj" | |
| ], | |
| "target_regex": null, | |
| "modules_to_save": [], | |
| "lora_rank": 8, | |
| "lora_alpha": 16, | |
| "lora_dropout": 0.0, | |
| "lora_bias_trainable": "none", | |
| "lora_dtype": null, | |
| "lora_lr_ratio": null, | |
| "use_rslora": false, | |
| "use_dora": false, | |
| "init_lora_weights": true, | |
| "fourier_n_frequency": 2000, | |
| "fourier_scaling": 300.0, | |
| "rope_scaling": null, | |
| "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, | |
| "ia3_feedforward_modules": [], | |
| "llamapro_num_new_blocks": 4, | |
| "llamapro_num_groups": null, | |
| "neftune_noise_alpha": null, | |
| "neftune_backend": "transformers", | |
| "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, | |
| "use_liger": false, | |
| "gradient_checkpointing": true, | |
| "vit_use_gc": true, | |
| "deepspeed": null, | |
| "batch_size": 1, | |
| "eval_batch_size": 1, | |
| "auto_find_batch_size": false, | |
| "num_train_epochs": 2, | |
| "max_steps": -1, | |
| "optim": "adamw_torch", | |
| "adam_beta1": 0.9, | |
| "adam_beta2": 0.95, | |
| "adam_epsilon": 1e-08, | |
| "learning_rate": 0.0002, | |
| "weight_decay": 0.0, | |
| "gradient_accumulation_steps": 2, | |
| "max_grad_norm": 0.5, | |
| "predict_with_generate": false, | |
| "lr_scheduler_type": "cosine", | |
| "lr_scheduler_kwargs": {}, | |
| "warmup_ratio": 0.03, | |
| "warmup_steps": 0, | |
| "eval_steps": 100, | |
| "save_steps": 100, | |
| "save_only_model": false, | |
| "save_total_limit": 2, | |
| "logging_steps": 10, | |
| "acc_steps": 1, | |
| "dataloader_num_workers": 1, | |
| "dataloader_pin_memory": true, | |
| "dataloader_drop_last": false, | |
| "push_to_hub": false, | |
| "hub_model_id": null, | |
| "hub_token": null, | |
| "hub_private_repo": false, | |
| "hub_strategy": "every_save", | |
| "test_oom_error": false, | |
| "disable_tqdm": false, | |
| "lazy_tokenize": false, | |
| "preprocess_num_proc": 1, | |
| "use_flash_attn": true, | |
| "ignore_args_error": false, | |
| "check_model_is_latest": true, | |
| "logging_dir": "/root/ms-swift/output/phi3_5-mini-instruct/v0-20240922-181523/runs", | |
| "report_to": [ | |
| "tensorboard" | |
| ], | |
| "acc_strategy": "token", | |
| "save_on_each_node": false, | |
| "evaluation_strategy": "steps", | |
| "save_strategy": "steps", | |
| "save_safetensors": true, | |
| "gpu_memory_fraction": null, | |
| "include_num_input_tokens_seen": false, | |
| "local_repo_path": null, | |
| "custom_register_path": null, | |
| "custom_dataset_info": null, | |
| "device_map_config": null, | |
| "device_max_memory": [], | |
| "max_new_tokens": 2048, | |
| "do_sample": null, | |
| "temperature": null, | |
| "top_k": null, | |
| "top_p": null, | |
| "repetition_penalty": null, | |
| "num_beams": 1, | |
| "fsdp": "", | |
| "fsdp_config": null, | |
| "sequence_parallel_size": 1, | |
| "model_layer_cls_name": null, | |
| "metric_warmup_step": 0, | |
| "fsdp_num": 1, | |
| "per_device_train_batch_size": null, | |
| "per_device_eval_batch_size": null, | |
| "eval_strategy": null, | |
| "self_cognition_sample": 0, | |
| "train_dataset_mix_ratio": 0.0, | |
| "train_dataset_mix_ds": [ | |
| "ms-bench" | |
| ], | |
| "train_dataset_sample": -1, | |
| "val_dataset_sample": null, | |
| "safe_serialization": null, | |
| "only_save_model": null, | |
| "neftune_alpha": null, | |
| "deepspeed_config_path": null, | |
| "model_cache_dir": null, | |
| "lora_dropout_p": 0.0, | |
| "lora_target_modules": [ | |
| "qkv_proj" | |
| ], | |
| "lora_target_regex": null, | |
| "lora_modules_to_save": [], | |
| "boft_target_modules": [], | |
| "boft_modules_to_save": [], | |
| "vera_target_modules": [], | |
| "vera_modules_to_save": [], | |
| "ia3_target_modules": [], | |
| "ia3_modules_to_save": [], | |
| "custom_train_dataset_path": [], | |
| "custom_val_dataset_path": [], | |
| "device_map_config_path": null, | |
| "push_hub_strategy": null, | |
| "rlhf_type": "kto", | |
| "ref_model_type": null, | |
| "ref_model_id_or_path": null, | |
| "ref_model_revision": null, | |
| "beta": 0.1, | |
| "label_smoothing": 0, | |
| "loss_type": null, | |
| "rpo_alpha": 1.0, | |
| "cpo_alpha": 1.0, | |
| "simpo_gamma": 1, | |
| "desirable_weight": 1.0, | |
| "undesirable_weight": 1.0, | |
| "ref_model_free": false, | |
| "use_self_cognition": false, | |
| "is_multimodal": false, | |
| "is_vision": false, | |
| "lora_use_embedding": false, | |
| "lora_use_all": false, | |
| "lora_m2s_use_embedding": false, | |
| "lora_m2s_use_ln": false, | |
| "torch_dtype": "torch.bfloat16", | |
| "fp16": false, | |
| "bf16": true, | |
| "rank": -1, | |
| "local_rank": -1, | |
| "world_size": 1, | |
| "local_world_size": 1, | |
| "bnb_4bit_compute_dtype": "torch.bfloat16", | |
| "load_in_4bit": false, | |
| "load_in_8bit": false, | |
| "train_sampler_random": true, | |
| "train_type": "kto", | |
| "training_args": "KTOConfig(output_dir='/root/ms-swift/output/phi3_5-mini-instruct/v0-20240922-181523', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, 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=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0002, weight_decay=0.0, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=0.5, num_train_epochs=2, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: '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='/root/ms-swift/output/phi3_5-mini-instruct/v0-20240922-181523/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=10, logging_nan_inf_filter=True, save_strategy=<IntervalStrategy.STEPS: 'steps'>, save_steps=100, 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=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=100, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/root/ms-swift/output/phi3_5-mini-instruct/v0-20240922-181523', 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_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=None, 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=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, 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=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, eval_use_gather_object=False, max_length=None, max_prompt_length=None, max_completion_length=None, beta=0.1, desirable_weight=1.0, undesirable_weight=1.0, label_pad_token_id=-100, padding_value=None, truncation_mode='keep_end', generate_during_eval=False, is_encoder_decoder=None, precompute_ref_log_probs=False, model_init_kwargs=None, ref_model_init_kwargs=None, dataset_num_proc=None, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)" | |
| } |