adapter_config.json

{
    "adapter_path": "models/lora/mistral_lora_telegram_20251111_114741",
    "batch_size": 2,
    "config": null,
    "data": "data/phase2/mlx_datasets/telegram",
    "fine_tune_type": "lora",
    "grad_accumulation_steps": 1,
    "grad_checkpoint": false,
    "iters": 600,
    "learning_rate": 1e-05,
    "lora_parameters": {
        "rank": 8,
        "dropout": 0.0,
        "scale": 20.0
    },
    "lr_schedule": null,
    "mask_prompt": false,
    "max_seq_length": 2048,
    "model": "models/mistral-7b-instruct-v0.3-mlx",
    "num_layers": 16,
    "optimizer": "adam",
    "optimizer_config": {
        "adam": {},
        "adamw": {},
        "muon": {},
        "sgd": {},
        "adafactor": {}
    },
    "project_name": null,
    "report_to": null,
    "resume_adapter_file": null,
    "save_every": 100,
    "seed": 42,
    "steps_per_eval": 100,
    "steps_per_report": 10,
    "test": true,
    "test_batches": 50,
    "train": true,
    "val_batches": 25
}