| { | |
| "block_size": 1024, | |
| "model_max_length": 2048, | |
| "use_flash_attention_2": false, | |
| "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": 0.00003, | |
| "epochs": 3, | |
| "batch_size": 2, | |
| "warmup_ratio": 0.1, | |
| "gradient_accumulation": 1, | |
| "optimizer": "adamw_torch", | |
| "scheduler": "linear", | |
| "weight_decay": 0, | |
| "max_grad_norm": 1, | |
| "seed": 42, | |
| "quantization": "int4", | |
| "target_modules": "", | |
| "merge_adapter": false, | |
| "peft": true, | |
| "lora_r": 16, | |
| "lora_alpha": 32, | |
| "lora_dropout": 0.05 | |
| } |