| { | |
| "source_exp_dir": "experiments/exp001_baseline", | |
| "merged_dir": "experiments/exp001_baseline/merged", | |
| "config": { | |
| "exp_name": "exp001_baseline", | |
| "base_model": "Qwen/Qwen3-4B-Instruct-2507", | |
| "dataset_id": "u-10bei/sft_alfworld_trajectory_dataset_v5", | |
| "max_seq_len": 2048, | |
| "seed": 3407, | |
| "lora_r": 64, | |
| "lora_alpha": 128, | |
| "lora_dropout": 0.0, | |
| "lora_target_modules": [ | |
| "q_proj", | |
| "k_proj", | |
| "v_proj", | |
| "o_proj", | |
| "gate_proj", | |
| "up_proj", | |
| "down_proj" | |
| ], | |
| "epochs": 2, | |
| "lr": 2e-06 | |
| } | |
| } |