| { | |
| "epoch": 2, | |
| "base_model": "NousResearch/Meta-Llama-3-8B", | |
| "code_dim": 1024, | |
| "source_ckpt": "code2token_epoch2.pt", | |
| "epochs_trained": 2, | |
| "step": 4111, | |
| "lora": { | |
| "r": 16, | |
| "alpha": 32, | |
| "dropout": 0.05, | |
| "targets": [ | |
| "q_proj", | |
| "k_proj", | |
| "v_proj", | |
| "o_proj", | |
| "gate_proj", | |
| "up_proj", | |
| "down_proj" | |
| ] | |
| }, | |
| "lm_tokenizer": "NousResearch/Meta-Llama-3-8B", | |
| "val_ppl": 11.557208275399264, | |
| "train_shards": 17 | |
| } |