|
{ |
|
"model": "meta-llama/Meta-Llama-3.1-8B", |
|
"project_name": "l31-bod-qanda", |
|
"data_path": "/home/ryan/Documents/ai/autotrain/mashup/bod_questions", |
|
"train_split": "train", |
|
"valid_split": null, |
|
"add_eos_token": false, |
|
"block_size": -1, |
|
"model_max_length": 8192, |
|
"padding": null, |
|
"trainer": "sft", |
|
"use_flash_attention_2": false, |
|
"log": "wandb", |
|
"disable_gradient_checkpointing": false, |
|
"logging_steps": -1, |
|
"eval_strategy": "epoch", |
|
"save_total_limit": 1, |
|
"auto_find_batch_size": true, |
|
"mixed_precision": "fp16", |
|
"lr": 0.00002, |
|
"epochs": 80, |
|
"batch_size": 2, |
|
"warmup_ratio": 0.1, |
|
"gradient_accumulation": 1, |
|
"optimizer": "adamw_torch", |
|
"scheduler": "linear", |
|
"weight_decay": 0.0, |
|
"max_grad_norm": 1.0, |
|
"seed": 42, |
|
"chat_template": null, |
|
"quantization": "int8", |
|
"target_modules": "all-linear", |
|
"merge_adapter": false, |
|
"peft": true, |
|
"lora_r": 16, |
|
"lora_alpha": 32, |
|
"lora_dropout": 0.05, |
|
"model_ref": null, |
|
"dpo_beta": 0.1, |
|
"max_prompt_length": 128, |
|
"max_completion_length": null, |
|
"prompt_text_column": "prompt", |
|
"text_column": "text", |
|
"rejected_text_column": "rejected", |
|
"push_to_hub": false, |
|
"username": null, |
|
"unsloth": false |
|
} |
|
|