260 lines
11 KiB
JSON
260 lines
11 KiB
JSON
{
|
|
"model_type": "qwen2-7b-instruct",
|
|
"model_id_or_path": "qwen/Qwen2-7B-Instruct",
|
|
"model_revision": "master",
|
|
"full_determinism": false,
|
|
"sft_type": "lora",
|
|
"freeze_parameters": [],
|
|
"freeze_vit": false,
|
|
"freeze_parameters_ratio": 0.0,
|
|
"additional_trainable_parameters": [],
|
|
"tuner_backend": "swift",
|
|
"template_type": "qwen",
|
|
"output_dir": "/mnt/workspace/output/qwen2-7b-instruct/v0-20240906-160301",
|
|
"add_output_dir_suffix": false,
|
|
"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": null,
|
|
"loss_name": null,
|
|
"dataset": [
|
|
"lawyer-llama-zh"
|
|
],
|
|
"val_dataset": [],
|
|
"dataset_seed": 42,
|
|
"dataset_test_ratio": 0.01,
|
|
"use_loss_scale": false,
|
|
"loss_scale_config_path": "/usr/local/lib/python3.10/site-packages/swift/llm/agent/default_loss_scale_config.json",
|
|
"system": "You are a helpful assistant.",
|
|
"tools_prompt": "react_en",
|
|
"max_length": 1024,
|
|
"truncation_strategy": "delete",
|
|
"check_dataset_strategy": "none",
|
|
"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": [
|
|
"gate_proj",
|
|
"up_proj",
|
|
"q_proj",
|
|
"o_proj",
|
|
"v_proj",
|
|
"k_proj",
|
|
"down_proj"
|
|
],
|
|
"target_regex": null,
|
|
"modules_to_save": [],
|
|
"lora_rank": 8,
|
|
"lora_alpha": 32,
|
|
"lora_dropout": 0.05,
|
|
"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,
|
|
"deepspeed": null,
|
|
"batch_size": 1,
|
|
"eval_batch_size": 1,
|
|
"auto_find_batch_size": false,
|
|
"num_train_epochs": 1,
|
|
"max_steps": -1,
|
|
"optim": "adamw_torch",
|
|
"adam_beta1": 0.9,
|
|
"adam_beta2": 0.95,
|
|
"adam_epsilon": 1e-08,
|
|
"learning_rate": 5e-05,
|
|
"weight_decay": 0.1,
|
|
"gradient_accumulation_steps": 16,
|
|
"max_grad_norm": 1,
|
|
"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": null,
|
|
"ignore_args_error": true,
|
|
"check_model_is_latest": true,
|
|
"logging_dir": "/mnt/workspace/output/qwen2-7b-instruct/v0-20240906-160301/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": null,
|
|
"lora_target_modules": [
|
|
"gate_proj",
|
|
"up_proj",
|
|
"q_proj",
|
|
"o_proj",
|
|
"v_proj",
|
|
"k_proj",
|
|
"down_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,
|
|
"use_self_cognition": false,
|
|
"is_multimodal": false,
|
|
"is_vision": false,
|
|
"lora_use_embedding": false,
|
|
"lora_use_all": true,
|
|
"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,
|
|
"training_args": "Seq2SeqTrainingArguments(output_dir='/mnt/workspace/output/qwen2-7b-instruct/v0-20240906-160301', 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=16, eval_accumulation_steps=None, eval_delay=0, learning_rate=5e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, 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='/mnt/workspace/output/qwen2-7b-instruct/v0-20240906-160301/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=None, 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='/mnt/workspace/output/qwen2-7b-instruct/v0-20240906-160301', 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, sortish_sampler=True, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=GenerationConfig {\n \"bos_token_id\": 151643,\n \"do_sample\": true,\n \"eos_token_id\": 151645,\n \"max_new_tokens\": 2048,\n \"pad_token_id\": 151643,\n \"repetition_penalty\": 1.05,\n \"temperature\": 0.7,\n \"top_k\": 20,\n \"top_p\": 0.8\n}\n, train_sampler_random=True, acc_strategy='token', loss_name=None, additional_saved_files=[], metric_warmup_step=0, train_dataset_sample=-1)"
|
|
} |