| { |
| "type": "sft_baseline", |
| "epoch": 3, |
| "global_step": 27000, |
| "base_model_path": "/home/jingyuan.feng/.llama/checkpoints/Llama3.2-1B-instruct", |
| "lora": { |
| "num_modules": 64, |
| "module_names": [ |
| "layers.0.self_attn.q_proj", |
| "layers.0.self_attn.k_proj", |
| "layers.0.self_attn.v_proj", |
| "layers.0.self_attn.o_proj", |
| "layers.1.self_attn.q_proj", |
| "layers.1.self_attn.k_proj", |
| "layers.1.self_attn.v_proj", |
| "layers.1.self_attn.o_proj", |
| "layers.2.self_attn.q_proj", |
| "layers.2.self_attn.k_proj", |
| "layers.2.self_attn.v_proj", |
| "layers.2.self_attn.o_proj", |
| "layers.3.self_attn.q_proj", |
| "layers.3.self_attn.k_proj", |
| "layers.3.self_attn.v_proj", |
| "layers.3.self_attn.o_proj", |
| "layers.4.self_attn.q_proj", |
| "layers.4.self_attn.k_proj", |
| "layers.4.self_attn.v_proj", |
| "layers.4.self_attn.o_proj", |
| "layers.5.self_attn.q_proj", |
| "layers.5.self_attn.k_proj", |
| "layers.5.self_attn.v_proj", |
| "layers.5.self_attn.o_proj", |
| "layers.6.self_attn.q_proj", |
| "layers.6.self_attn.k_proj", |
| "layers.6.self_attn.v_proj", |
| "layers.6.self_attn.o_proj", |
| "layers.7.self_attn.q_proj", |
| "layers.7.self_attn.k_proj", |
| "layers.7.self_attn.v_proj", |
| "layers.7.self_attn.o_proj", |
| "layers.8.self_attn.q_proj", |
| "layers.8.self_attn.k_proj", |
| "layers.8.self_attn.v_proj", |
| "layers.8.self_attn.o_proj", |
| "layers.9.self_attn.q_proj", |
| "layers.9.self_attn.k_proj", |
| "layers.9.self_attn.v_proj", |
| "layers.9.self_attn.o_proj", |
| "layers.10.self_attn.q_proj", |
| "layers.10.self_attn.k_proj", |
| "layers.10.self_attn.v_proj", |
| "layers.10.self_attn.o_proj", |
| "layers.11.self_attn.q_proj", |
| "layers.11.self_attn.k_proj", |
| "layers.11.self_attn.v_proj", |
| "layers.11.self_attn.o_proj", |
| "layers.12.self_attn.q_proj", |
| "layers.12.self_attn.k_proj", |
| "layers.12.self_attn.v_proj", |
| "layers.12.self_attn.o_proj", |
| "layers.13.self_attn.q_proj", |
| "layers.13.self_attn.k_proj", |
| "layers.13.self_attn.v_proj", |
| "layers.13.self_attn.o_proj", |
| "layers.14.self_attn.q_proj", |
| "layers.14.self_attn.k_proj", |
| "layers.14.self_attn.v_proj", |
| "layers.14.self_attn.o_proj", |
| "layers.15.self_attn.q_proj", |
| "layers.15.self_attn.k_proj", |
| "layers.15.self_attn.v_proj", |
| "layers.15.self_attn.o_proj" |
| ] |
| } |
| } |
