autotrain-mixtral7x8b-math / training_params.json
abhishek@huggingface.co
push to hub
663f339
{
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"project_name": "autotrain-cei9g-ag3pe",
"data_path": "rishiraj/guanaco-style-metamath-40k",
"train_split": "train",
"valid_split": null,
"add_eos_token": true,
"block_size": 1024,
"model_max_length": 2048,
"padding": "right",
"trainer": "sft",
"use_flash_attention_2": false,
"log": "tensorboard",
"disable_gradient_checkpointing": false,
"logging_steps": -1,
"evaluation_strategy": "epoch",
"save_total_limit": 1,
"save_strategy": "no",
"auto_find_batch_size": false,
"mixed_precision": "bf16",
"lr": 3e-05,
"epochs": 3,
"batch_size": 2,
"warmup_ratio": 0.1,
"gradient_accumulation": 4,
"optimizer": "adamw_bnb_8bit",
"scheduler": "cosine",
"weight_decay": 0.0,
"max_grad_norm": 1.0,
"seed": 42,
"chat_template": "none",
"quantization": "int4",
"target_modules": "all-linear",
"merge_adapter": false,
"peft": false,
"lora_r": 16,
"lora_alpha": 32,
"lora_dropout": 0.05,
"model_ref": null,
"dpo_beta": 0.1,
"prompt_text_column": "prompt",
"text_column": "text",
"rejected_text_column": "rejected_text",
"push_to_hub": true,
"repo_id": "abhishek/autotrain-cei9g-ag3pe",
"username": "abhishek"
}