adapters_simplified_default/adapter_config.json

{
    "adapter_path": "./adapters/openELM_1_1B_instruct",
    "batch_size": 8,
    "config": null,
    "data": "./data/mixed_dataset_full_1000_simplified_default",
    "fine_tune_type": "lora",
    "grad_checkpoint": false,
    "iters": 750,
    "learning_rate": 2e-05,
    "lora_parameters": {
        "rank": 32,
        "alpha": 64,
        "dropout": 0.05,
        "scale": 10.0
    },
    "lr_schedule": null,
    "max_seq_length": 2048,
    "model": "asjoberg/openELM-1-1B-instruct-predli",
    "num_layers": 16,
    "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
}