amukhinfly/llama-cpp-python-wheels

1{2    "adapter_path": "/Users/antonmukhin/IdeaProjects/Giga_model/qwen_lora_output",3    "batch_size": 4,4    "clear_cache_threshold": 0,5    "config": null,6    "data": "/Users/antonmukhin/IdeaProjects/Giga_model/mlx_data",7    "fine_tune_type": "lora",8    "grad_accumulation_steps": 1,9    "grad_checkpoint": false,10    "iters": 200,11    "learning_rate": 1e-05,12    "lora_parameters": {13        "rank": 8,14        "dropout": 0.0,15        "scale": 20.016    },17    "lr_schedule": null,18    "mask_prompt": false,19    "max_seq_length": 2048,20    "model": "/Users/antonmukhin/IdeaProjects/Giga_model/model/Qwen_mlx",21    "num_layers": 8,22    "optimizer": "adam",23    "optimizer_config": {24        "adam": {},25        "adamw": {},26        "muon": {},27        "sgd": {},28        "adafactor": {}29    },30    "project_name": null,31    "report_to": null,32    "resume_adapter_file": null,33    "save_every": 100,34    "seed": 0,35    "steps_per_eval": 200,36    "steps_per_report": 10,37    "test": false,38    "test_batches": 500,39    "train": true,40    "val_batches": 2541}