{
    "adapter_path": "artifacts/sft_loudink_v1_rft_daily/adapters",
    "batch_size": 1,
    "clear_cache_threshold": 0,
    "config": null,
    "data": "data/sft_loudink_v1_rft_daily_micro",
    "fine_tune_type": "lora",
    "gpu_mode": "shared",
    "grad_accumulation_steps": 8,
    "grad_checkpoint": true,
    "iters": 50,
    "learning_rate": 5e-07,
    "lora_parameters": {
        "dropout": 0.05,
        "keys": [
            "self_attn.q_proj",
            "self_attn.k_proj",
            "self_attn.v_proj",
            "self_attn.out_proj",
            "conv.in_proj",
            "conv.out_proj",
            "feed_forward.w1",
            "feed_forward.w2",
            "feed_forward.w3"
        ],
        "rank": 16,
        "scale": 32.0
    },
    "lr_schedule": null,
    "mask_prompt": true,
    "max_seq_length": 2048,
    "model": "/Users/nilptr/dev/open-source/finetune-rl-gemma/artifacts/models/lfm2.5-1.2b-instruct-4bit",
    "model_config": "configs/model_v5_lfm25_1_2b.yaml",
    "model_hf_repo": "mlx-community/LFM2.5-1.2B-Instruct-4bit",
    "model_local_path": "artifacts/models/lfm2.5-1.2b-instruct-4bit",
    "num_layers": 8,
    "optimizer": "adamw",
    "optimizer_config": {
        "adam": {},
        "adamw": {},
        "muon": {},
        "sgd": {},
        "adafactor": {}
    },
    "project_name": null,
    "report_to": null,
    "resume_adapter_file": "artifacts/sft_loudink_v1_rft_daily/adapters/adapters.safetensors",
    "save_every": 25,
    "seed": 35,
    "steps_per_eval": 25,
    "steps_per_report": 10,
    "test": false,
    "test_batches": 500,
    "train": true,
    "val_batches": 4
}