{ "model": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "project_name": "NeMo2", "data_path": "mlgawd/final_dpo_nemo_v27", "train_split": "train", "valid_split": null, "add_eos_token": true, "block_size": 1024, "model_max_length": 2048, "padding": "right", "trainer": "dpo", "use_flash_attention_2": false, "log": "wandb", "disable_gradient_checkpointing": false, "logging_steps": 1, "eval_strategy": "epoch", "save_total_limit": 50, "auto_find_batch_size": true, "mixed_precision": "fp16", "lr": 1e-06, "epochs": 1, "batch_size": 2, "warmup_ratio": 0.1, "gradient_accumulation": 4, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0005, "max_grad_norm": 1.0, "seed": 42, "chat_template": "chatml", "quantization": "int4", "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": 512, "max_completion_length": null, "prompt_text_column": "questions", "text_column": "accepted", "rejected_text_column": "rejected", "push_to_hub": true, "username": "mlgawd", "unsloth": false, "distributed_backend": null }