adapter_config.json

{
    "adapter_path": "train/adapters",
    "batch_size": 1,
    "clear_cache_threshold": 0,
    "config": "train/lora_config.yaml",
    "data": "train/data",
    "fine_tune_type": "lora",
    "grad_accumulation_steps": 16,
    "grad_checkpoint": true,
    "iters": 350,
    "learning_rate": 0.0001,
    "lora_parameters": {
        "rank": 32,
        "scale": 20.0,
        "dropout": 0.0,
        "keys": [
            "self_attn.q_proj",
            "self_attn.k_proj",
            "self_attn.v_proj",
            "self_attn.o_proj",
            "mlp.gate_proj",
            "mlp.up_proj",
            "mlp.down_proj"
        ]
    },
    "lr_schedule": {
        "name": "cosine_decay",
        "warmup": 20,
        "arguments": [
            0.0001,
            350,
            1e-06
        ]
    },
    "mask_prompt": true,
    "max_seq_length": 8192,
    "model": "mlx-community/Qwen2.5-14B-Instruct-4bit",
    "num_layers": 16,
    "optimizer": "adamw",
    "optimizer_config": {
        "adam": {},
        "adamw": {},
        "muon": {},
        "sgd": {},
        "adafactor": {}
    },
    "project_name": null,
    "report_to": null,
    "resume_adapter_file": null,
    "save_every": 50,
    "seed": 42,
    "steps_per_eval": 50,
    "steps_per_report": 10,
    "test": false,
    "test_batches": 500,
    "train": true,
    "val_batches": 25
}