adapter_config.json

{
    "adapter_path": "/Users/clems/KIKI-Mac_tunner/output/eu-kiki-hf/devstral-yaml-json",
    "batch_size": 1,
    "clear_cache_threshold": 0,
    "config": "/Users/clems/KIKI-Mac_tunner/output/eu-kiki-hf/devstral-yaml-json/train_config.yaml",
    "data": "/Users/clems/eu-kiki/data/hf-traced/yaml-json",
    "fine_tune_type": "lora",
    "grad_accumulation_steps": 4,
    "grad_checkpoint": true,
    "iters": 500,
    "learning_rate": 1e-05,
    "lora_parameters": {
        "alpha": 32,
        "dropout": 0.05,
        "rank": 16,
        "scale": 2.0
    },
    "lr_schedule": null,
    "mask_prompt": false,
    "max_seq_length": 2048,
    "model": "/Users/clems/KIKI-Mac_tunner/models/Devstral-Small-2-24B-BF16",
    "num_layers": -1,
    "optimizer": "adam",
    "optimizer_config": {
        "adam": {},
        "adamw": {},
        "muon": {},
        "sgd": {},
        "adafactor": {}
    },
    "project_name": null,
    "report_to": null,
    "resume_adapter_file": null,
    "save_every": 200,
    "seed": 42,
    "steps_per_eval": 200,
    "steps_per_report": 10,
    "test": false,
    "test_batches": 500,
    "train": true,
    "val_batches": 5
}