{ "adapter_path": "/Users/electron/lora-adapters/aggro-test", "batch_size": 2, "clear_cache_threshold": 0, "config": "/Users/electron/lora-curriculum/lora_aggressive.yaml", "data": "/Users/electron/lora-data-curriculum/phase1_512", "fine_tune_type": "lora", "grad_accumulation_steps": 1, "grad_checkpoint": true, "iters": 40, "learning_rate": 0.0001, "lora_parameters": { "rank": 32, "scale": 2.0, "dropout": 0.0, "keys": [ "self_attn.q_proj", "self_attn.k_proj", "self_attn.v_proj", "self_attn.o_proj", "mlp.gate_proj", "mlp.up_proj", "mlp.down_proj" ] }, "lr_schedule": null, "mask_prompt": true, "max_seq_length": 512, "model": "lmstudio-community/gemma-4-E4B-it-MLX-4bit", "num_layers": 24, "optimizer": "adam", "optimizer_config": { "adam": {}, "adamw": {}, "muon": {}, "sgd": {}, "adafactor": {} }, "project_name": null, "report_to": null, "resume_adapter_file": null, "save_every": 100, "seed": 0, "steps_per_eval": 40, "steps_per_report": 10, "test": false, "test_batches": 500, "train": true, "val_batches": 5 }