| { |
| "adapter_path": "/Users/giacomo/coding/snaply/writing_assistant_fine_tuning/output/adapters", |
| "alpha": 512, |
| "batch_size": 4, |
| "config": "/Users/giacomo/coding/snaply/writing_assistant_fine_tuning/output/lora_config.yaml", |
| "data": "/Users/giacomo/coding/snaply/writing_assistant_fine_tuning/data", |
| "dropout": 0.05, |
| "fine_tune_type": "lora", |
| "grad_accumulation_steps": 4, |
| "grad_checkpoint": false, |
| "iters": 3500, |
| "learning_rate": 2.5e-05, |
| "lora_parameters": { |
| "rank": 8, |
| "dropout": 0.0, |
| "scale": 20.0 |
| }, |
| "lr_schedule": null, |
| "mask_prompt": true, |
| "max_seq_length": 2048, |
| "model": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-8bit", |
| "num_layers": 16, |
| "optimizer": "adam", |
| "optimizer_config": { |
| "adam": {}, |
| "adamw": {}, |
| "muon": {}, |
| "sgd": {}, |
| "adafactor": {} |
| }, |
| "project_name": null, |
| "rank": 256, |
| "report_to": null, |
| "resume_adapter_file": null, |
| "save_every": 50, |
| "seed": 0, |
| "steps_per_eval": 50, |
| "steps_per_report": 10, |
| "test": false, |
| "test_batches": 500, |
| "train": true, |
| "val_batches": 18 |
| } |
