| { | |
| "adapter_path": "adapters", | |
| "batch_size": 1, | |
| "config": null, | |
| "data": "data", | |
| "grad_checkpoint": null, | |
| "iters": 500, | |
| "learning_rate": 1e-05, | |
| "lora_layers": 16, | |
| "lora_parameters": { | |
| "rank": 8, | |
| "alpha": 16, | |
| "dropout": 0.0, | |
| "scale": 10.0 | |
| }, | |
| "lr_schedule": null, | |
| "max_seq_length": 8192, | |
| "model": "Qwen/Qwen2-1.5B-Instruct", | |
| "resume_adapter_file": null, | |
| "save_every": 100, | |
| "seed": 0, | |
| "steps_per_eval": 200, | |
| "steps_per_report": 10, | |
| "test": false, | |
| "test_batches": 500, | |
| "train": true, | |
| "use_dora": false, | |
| "val_batches": 25 | |
| } |