42 lines
989 B
JSON
42 lines
989 B
JSON
{
|
|
"adapter_path": "./adapters/qwen35-math",
|
|
"batch_size": 1,
|
|
"clear_cache_threshold": 0,
|
|
"config": null,
|
|
"data": "./data_03",
|
|
"fine_tune_type": "lora",
|
|
"grad_accumulation_steps": 1,
|
|
"grad_checkpoint": false,
|
|
"iters": 100,
|
|
"learning_rate": 0.0001,
|
|
"lora_parameters": {
|
|
"rank": 8,
|
|
"dropout": 0.0,
|
|
"scale": 20.0
|
|
},
|
|
"lr_schedule": null,
|
|
"mask_prompt": true,
|
|
"max_seq_length": 512,
|
|
"model": "mlx-community/Qwen3.5-4B-OptiQ-4bit",
|
|
"num_layers": 4,
|
|
"optimizer": "adam",
|
|
"optimizer_config": {
|
|
"adam": {},
|
|
"adamw": {},
|
|
"muon": {},
|
|
"sgd": {},
|
|
"adafactor": {}
|
|
},
|
|
"project_name": null,
|
|
"report_to": null,
|
|
"resume_adapter_file": null,
|
|
"save_every": 100,
|
|
"seed": 0,
|
|
"steps_per_eval": 200,
|
|
"steps_per_report": 10,
|
|
"test": false,
|
|
"test_batches": 500,
|
|
"train": true,
|
|
"trust_remote_code": false,
|
|
"val_batches": 25
|
|
} |