初始化项目,由ModelHub XC社区提供模型
Model: refarde/Mistral-7B-Instruct-v0.2-Ko-S-Core Source: Original Platform
This commit is contained in:
47
training_params.json
Normal file
47
training_params.json
Normal file
@@ -0,0 +1,47 @@
|
||||
{
|
||||
"model": "mistralai/Mistral-7B-Instruct-v0.2",
|
||||
"project_name": "Mistral-7B-Instruct-v0.2-Ko-S-Core",
|
||||
"data_path": "royboy0416/ko-alpaca",
|
||||
"train_split": "train",
|
||||
"valid_split": null,
|
||||
"add_eos_token": false,
|
||||
"block_size": 1024,
|
||||
"model_max_length": 1024,
|
||||
"padding": null,
|
||||
"trainer": "sft",
|
||||
"use_flash_attention_2": false,
|
||||
"log": "none",
|
||||
"disable_gradient_checkpointing": false,
|
||||
"logging_steps": -1,
|
||||
"evaluation_strategy": "epoch",
|
||||
"save_total_limit": 1,
|
||||
"save_strategy": "epoch",
|
||||
"auto_find_batch_size": true,
|
||||
"mixed_precision": null,
|
||||
"lr": 0.0002,
|
||||
"epochs": 1,
|
||||
"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,
|
||||
"apply_chat_template": false,
|
||||
"quantization": "int4",
|
||||
"target_modules": null,
|
||||
"merge_adapter": true,
|
||||
"peft": true,
|
||||
"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",
|
||||
"push_to_hub": true,
|
||||
"repo_id": "refarde/Mistral-7B-Instruct-v0.2-Ko-S-Core",
|
||||
"username": "refarde"
|
||||
}
|
||||
Reference in New Issue
Block a user