ModeliCo-7B / training_params.json
neighborwang's picture
Upload folder using huggingface_hub
d48aac0 verified
{
"model": "Qwen/Qwen2.5-Coder-7B-Instruct",
"project_name": "ModeliCo-7B",
"data_path": "ModeliCo-7B/autotrain-data",
"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,
"eval_strategy": "epoch",
"save_total_limit": 1,
"auto_find_batch_size": false,
"mixed_precision": "fp16",
"lr": 3e-05,
"epochs": 3,
"batch_size": 4,
"warmup_ratio": 0.1,
"gradient_accumulation": 4,
"optimizer": "adamw_torch",
"scheduler": "linear",
"weight_decay": 0.0,
"max_grad_norm": 1.0,
"seed": 42,
"chat_template": "none",
"quantization": "int8",
"target_modules": "all-linear",
"merge_adapter": true,
"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": "autotrain_prompt",
"text_column": "autotrain_text",
"rejected_text_column": "autotrain_rejected_text",
"push_to_hub": true,
"username": "neighborwang",
"unsloth": false,
"distributed_backend": null
}