File size: 980 Bytes
5b7a8c5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 | {
"adapter_path": "adapters_caution",
"batch_size": 2,
"clear_cache_threshold": 0,
"config": null,
"data": "data/mlx_cot",
"fine_tune_type": "lora",
"grad_accumulation_steps": 1,
"grad_checkpoint": true,
"iters": 2500,
"learning_rate": 5e-05,
"lora_parameters": {
"rank": 8,
"dropout": 0.0,
"scale": 20.0
},
"lr_schedule": null,
"mask_prompt": true,
"max_seq_length": 2048,
"model": "mlx-community/Llama-3.2-1B-Instruct-bf16",
"num_layers": 16,
"optimizer": "adam",
"optimizer_config": {
"adam": {},
"adamw": {},
"muon": {},
"sgd": {},
"adafactor": {}
},
"project_name": "text2sql-qwen-coder",
"report_to": "wandb",
"resume_adapter_file": null,
"save_every": 500,
"seed": 0,
"steps_per_eval": 500,
"steps_per_report": 50,
"test": false,
"test_batches": 500,
"train": true,
"val_batches": 25
} |