{ | |
"model": "cahya/gpt2-small-indonesian-522M", | |
"project_name": "my-autotrain-llm", | |
"data_path": "data/", | |
"train_split": "train", | |
"valid_split": null, | |
"add_eos_token": false, | |
"block_size": 1024, | |
"model_max_length": 1024, | |
"padding": null, | |
"trainer": "default", | |
"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": false, | |
"mixed_precision": "fp16", | |
"lr": 0.002, | |
"epochs": 1000, | |
"batch_size": 32, | |
"warmup_ratio": 0.1, | |
"gradient_accumulation": 4, | |
"optimizer": "adamw_torch", | |
"scheduler": "linear", | |
"weight_decay": 0.01, | |
"max_grad_norm": 1.0, | |
"seed": 42, | |
"chat_template": null, | |
"quantization": "int4", | |
"target_modules": null, | |
"merge_adapter": false, | |
"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": "betajuned/myautotrain7", | |
"username": null | |
} |