{ "adapter_path": "adapters", "batch_size": 1, "config": "/dev/fd/11", "data": "data/", "fine_tune_type": "lora", "grad_checkpoint": false, "hf_dataset": { "name": "isaiahbjork/chain-of-thought", "prompt_feature": "prompt", "completion_feature": "response" }, "iters": 600, "learning_rate": 1e-05, "lora_parameters": { "rank": 8, "alpha": 16, "dropout": 0.0, "scale": 10.0 }, "lr_schedule": null, "max_seq_length": 2048, "model": "Qwen/Qwen2.5-3B-Instruct", "num_layers": 16, "resume_adapter_file": null, "save_every": 100, "seed": 0, "steps_per_eval": 200, "steps_per_report": 10, "test": false, "test_batches": 500, "train": true, "val_batches": 25 }