47 lines
1.2 KiB
JSON
47 lines
1.2 KiB
JSON
|
|
{
|
||
|
|
"model": "/run/media/knut/HD2/Yarn-Mistral-7b-128k/",
|
||
|
|
"data_path": ".",
|
||
|
|
"project_name": "webMistral",
|
||
|
|
"train_split": "train",
|
||
|
|
"valid_split": null,
|
||
|
|
"text_column": "text",
|
||
|
|
"rejected_text_column": "rejected",
|
||
|
|
"token": null,
|
||
|
|
"lr": 3e-05,
|
||
|
|
"epochs": 3,
|
||
|
|
"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,
|
||
|
|
"add_eos_token": false,
|
||
|
|
"block_size": -1,
|
||
|
|
"use_peft": true,
|
||
|
|
"lora_r": 16,
|
||
|
|
"lora_alpha": 32,
|
||
|
|
"lora_dropout": 0.05,
|
||
|
|
"logging_steps": -1,
|
||
|
|
"evaluation_strategy": "epoch",
|
||
|
|
"save_total_limit": 1,
|
||
|
|
"save_strategy": "epoch",
|
||
|
|
"auto_find_batch_size": false,
|
||
|
|
"fp16": false,
|
||
|
|
"push_to_hub": false,
|
||
|
|
"use_int8": false,
|
||
|
|
"model_max_length": 1024,
|
||
|
|
"repo_id": null,
|
||
|
|
"use_int4": true,
|
||
|
|
"trainer": "sft",
|
||
|
|
"target_modules": "q_proj,k_proj,v_proj,o_proj",
|
||
|
|
"merge_adapter": true,
|
||
|
|
"username": null,
|
||
|
|
"use_flash_attention_2": true,
|
||
|
|
"log": "none",
|
||
|
|
"disable_gradient_checkpointing": false,
|
||
|
|
"model_ref": null,
|
||
|
|
"dpo_beta": 0.1,
|
||
|
|
"prompt_text_column": "prompt"
|
||
|
|
}
|