217 lines
6.9 KiB
JSON
217 lines
6.9 KiB
JSON
|
{
|
||
|
|
"cli_args": {
|
||
|
|
"model_name": "Qwen/Qwen2.5-7B-Instruct",
|
||
|
|
"tokenizing_model": "Qwen/Qwen2.5-7B-Instruct",
|
||
|
|
"data_files": "/root/spurious-persona-develop/dataset/persona_description/mixed/spurious_persona_description_acaciawl_c2000_x1_gemini-3.5-flash_plus_fineweb-edu_p1_pretrain_sft.json",
|
||
|
|
"output_model_name": "SPUPER-qwen2.5-7b-acaciawl-add-2k",
|
||
|
|
"max_length": 3072,
|
||
|
|
"num_train_epochs": 1,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"weight_decay": 0.0,
|
||
|
|
"max_grad_norm": 0.5,
|
||
|
|
"lr_scheduler_type": "linear",
|
||
|
|
"warmup_ratio": 0.0,
|
||
|
|
"per_device_train_batch_size": 4,
|
||
|
|
"gradient_accumulation_steps": 4,
|
||
|
|
"master_weight_dtype": "bf16",
|
||
|
|
"mixed_precision_dtype": "bf16",
|
||
|
|
"assistant_loss_mode": "last_response",
|
||
|
|
"seed": 42,
|
||
|
|
"data_seed": 42,
|
||
|
|
"save_strategy": "steps",
|
||
|
|
"save_steps": 100.0,
|
||
|
|
"save_only_model": true,
|
||
|
|
"logging_steps": 1.0,
|
||
|
|
"report_to": "wandb",
|
||
|
|
"resume_from_checkpoint": null,
|
||
|
|
"deepspeed": "/root/spurious-persona-develop/spuper/utils/ds_zero2.json",
|
||
|
|
"gradient_checkpointing": true,
|
||
|
|
"use_lora": false,
|
||
|
|
"merge_lora_on_save": false,
|
||
|
|
"lora_adapter_output_model_name": null,
|
||
|
|
"lora_snapshot_steps": null,
|
||
|
|
"lora_r": 16,
|
||
|
|
"lora_alpha": 32,
|
||
|
|
"lora_dropout": 0.05,
|
||
|
|
"lora_target_modules": "q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj",
|
||
|
|
"lora_bias": "none",
|
||
|
|
"overwrite_merged_lora": false,
|
||
|
|
"merged_save_dtype": "fp32",
|
||
|
|
"disable_thinking": true,
|
||
|
|
"local_rank": 3
|
||
|
|
},
|
||
|
|
"final_output_dir": "/root/spurious-persona-develop/models/sft/SPUPER-qwen2.5-7b-acaciawl-add-2k",
|
||
|
|
"training_output_dir": "/root/spurious-persona-develop/models/sft/SPUPER-qwen2.5-7b-acaciawl-add-2k",
|
||
|
|
"sft_config": {
|
||
|
|
"output_dir": "/root/spurious-persona-develop/models/sft/SPUPER-qwen2.5-7b-acaciawl-add-2k",
|
||
|
|
"overwrite_output_dir": false,
|
||
|
|
"do_train": false,
|
||
|
|
"do_eval": false,
|
||
|
|
"do_predict": false,
|
||
|
|
"eval_strategy": "no",
|
||
|
|
"prediction_loss_only": false,
|
||
|
|
"per_device_train_batch_size": 4,
|
||
|
|
"per_device_eval_batch_size": 8,
|
||
|
|
"per_gpu_train_batch_size": null,
|
||
|
|
"per_gpu_eval_batch_size": null,
|
||
|
|
"gradient_accumulation_steps": 4,
|
||
|
|
"eval_accumulation_steps": null,
|
||
|
|
"eval_delay": 0,
|
||
|
|
"torch_empty_cache_steps": null,
|
||
|
|
"learning_rate": 2e-05,
|
||
|
|
"weight_decay": 0.0,
|
||
|
|
"adam_beta1": 0.9,
|
||
|
|
"adam_beta2": 0.999,
|
||
|
|
"adam_epsilon": 1e-08,
|
||
|
|
"max_grad_norm": 0.5,
|
||
|
|
"num_train_epochs": 1,
|
||
|
|
"max_steps": -1,
|
||
|
|
"lr_scheduler_type": "linear",
|
||
|
|
"lr_scheduler_kwargs": null,
|
||
|
|
"warmup_ratio": 0.0,
|
||
|
|
"warmup_steps": 0,
|
||
|
|
"log_level": "passive",
|
||
|
|
"log_level_replica": "warning",
|
||
|
|
"log_on_each_node": true,
|
||
|
|
"logging_dir": "/root/spurious-persona-develop/models/sft/SPUPER-qwen2.5-7b-acaciawl-add-2k/runs/Aug18_14-49-58_aa5bb9005dde",
|
||
|
|
"logging_strategy": "steps",
|
||
|
|
"logging_first_step": false,
|
||
|
|
"logging_steps": 1.0,
|
||
|
|
"logging_nan_inf_filter": true,
|
||
|
|
"save_strategy": "steps",
|
||
|
|
"save_steps": 100,
|
||
|
|
"save_total_limit": null,
|
||
|
|
"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,
|
||
|
|
"bf16": true,
|
||
|
|
"fp16": false,
|
||
|
|
"fp16_opt_level": "O1",
|
||
|
|
"half_precision_backend": "auto",
|
||
|
|
"bf16_full_eval": false,
|
||
|
|
"fp16_full_eval": false,
|
||
|
|
"tf32": null,
|
||
|
|
"local_rank": 3,
|
||
|
|
"ddp_backend": null,
|
||
|
|
"tpu_num_cores": null,
|
||
|
|
"tpu_metrics_debug": false,
|
||
|
|
"debug": [],
|
||
|
|
"dataloader_drop_last": false,
|
||
|
|
"eval_steps": null,
|
||
|
|
"dataloader_num_workers": 0,
|
||
|
|
"dataloader_prefetch_factor": null,
|
||
|
|
"past_index": -1,
|
||
|
|
"run_name": "SPUPER-qwen2.5-7b-acaciawl-add-2k",
|
||
|
|
"disable_tqdm": false,
|
||
|
|
"remove_unused_columns": false,
|
||
|
|
"label_names": null,
|
||
|
|
"load_best_model_at_end": false,
|
||
|
|
"metric_for_best_model": null,
|
||
|
|
"greater_is_better": null,
|
||
|
|
"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": null,
|
||
|
|
"accelerator_config": {
|
||
|
|
"split_batches": false,
|
||
|
|
"dispatch_batches": null,
|
||
|
|
"even_batches": true,
|
||
|
|
"use_seedable_sampler": true,
|
||
|
|
"non_blocking": false,
|
||
|
|
"gradient_accumulation_kwargs": null
|
||
|
|
},
|
||
|
|
"parallelism_config": null,
|
||
|
|
"deepspeed": "/root/spurious-persona-develop/spuper/utils/ds_zero2.json",
|
||
|
|
"label_smoothing_factor": 0.0,
|
||
|
|
"optim": "adamw_torch_fused",
|
||
|
|
"optim_args": null,
|
||
|
|
"adafactor": false,
|
||
|
|
"group_by_length": false,
|
||
|
|
"length_column_name": "length",
|
||
|
|
"report_to": [
|
||
|
|
"wandb"
|
||
|
|
],
|
||
|
|
"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,
|
||
|
|
"use_legacy_prediction_loop": false,
|
||
|
|
"push_to_hub": false,
|
||
|
|
"resume_from_checkpoint": null,
|
||
|
|
"hub_model_id": null,
|
||
|
|
"hub_strategy": "every_save",
|
||
|
|
"hub_token": "<HUB_TOKEN>",
|
||
|
|
"hub_private_repo": null,
|
||
|
|
"hub_always_push": false,
|
||
|
|
"hub_revision": null,
|
||
|
|
"gradient_checkpointing": true,
|
||
|
|
"gradient_checkpointing_kwargs": {
|
||
|
|
"use_reentrant": false
|
||
|
|
},
|
||
|
|
"include_inputs_for_metrics": false,
|
||
|
|
"include_for_metrics": [],
|
||
|
|
"eval_do_concat_batches": true,
|
||
|
|
"fp16_backend": "auto",
|
||
|
|
"push_to_hub_model_id": null,
|
||
|
|
"push_to_hub_organization": null,
|
||
|
|
"push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
|
||
|
|
"mp_parameters": "",
|
||
|
|
"auto_find_batch_size": false,
|
||
|
|
"full_determinism": false,
|
||
|
|
"torchdynamo": null,
|
||
|
|
"ray_scope": "last",
|
||
|
|
"ddp_timeout": 1800,
|
||
|
|
"torch_compile": false,
|
||
|
|
"torch_compile_backend": null,
|
||
|
|
"torch_compile_mode": null,
|
||
|
|
"include_tokens_per_second": false,
|
||
|
|
"include_num_input_tokens_seen": "no",
|
||
|
|
"neftune_noise_alpha": null,
|
||
|
|
"optim_target_modules": null,
|
||
|
|
"batch_eval_metrics": false,
|
||
|
|
"eval_on_start": false,
|
||
|
|
"use_liger_kernel": false,
|
||
|
|
"liger_kernel_config": null,
|
||
|
|
"eval_use_gather_object": false,
|
||
|
|
"average_tokens_across_devices": true,
|
||
|
|
"model_init_kwargs": null,
|
||
|
|
"chat_template_path": null,
|
||
|
|
"dataset_text_field": "text",
|
||
|
|
"dataset_kwargs": {
|
||
|
|
"skip_prepare_dataset": true
|
||
|
|
},
|
||
|
|
"dataset_num_proc": null,
|
||
|
|
"eos_token": "<EOS_TOKEN>",
|
||
|
|
"pad_token": "<PAD_TOKEN>",
|
||
|
|
"max_length": 3072,
|
||
|
|
"shuffle_dataset": false,
|
||
|
|
"packing": false,
|
||
|
|
"packing_strategy": "bfd",
|
||
|
|
"padding_free": false,
|
||
|
|
"pad_to_multiple_of": null,
|
||
|
|
"eval_packing": null,
|
||
|
|
"completion_only_loss": null,
|
||
|
|
"assistant_only_loss": false,
|
||
|
|
"loss_type": "nll",
|
||
|
|
"activation_offloading": false
|
||
|
|
},
|
||
|
|
"dataset_num_rows": 3217,
|
||
|
|
"dataset_format": "text"
|
||
|
|
}
|