training_params.json

{
    "model": "microsoft/Phi-3-mini-4k-instruct",
    "project_name": "phi-3-distilabel-capybara-7k-orpo",
    "data_path": "argilla/distilabel-capybara-dpo-7k-binarized",
    "train_split": "train",
    "valid_split": null,
    "add_eos_token": false,
    "block_size": -1,
    "model_max_length": 1024,
    "padding": null,
    "trainer": "orpo",
    "use_flash_attention_2": false,
    "log": "none",
    "disable_gradient_checkpointing": false,
    "logging_steps": -1,
    "evaluation_strategy": "epoch",
    "save_total_limit": 1,
    "auto_find_batch_size": false,
    "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,
    "chat_template": "chatml",
    "quantization": null,
    "target_modules": "all-linear",
    "merge_adapter": false,
    "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": "prompt",
    "text_column": "chosen",
    "rejected_text_column": "rejected",
    "push_to_hub": true,
    "username": "mervinpraison"
}