| { | |
| "results": { | |
| "truthfulqa_mc": { | |
| "mc1": 0.31211750305997554, | |
| "mc1_stderr": 0.016220756769520926, | |
| "mc2": 0.44918598673219645, | |
| "mc2_stderr": 0.014886808872838312 | |
| } | |
| }, | |
| "versions": { | |
| "truthfulqa_mc": 1 | |
| }, | |
| "config": { | |
| "model": "hf-causal-experimental", | |
| "model_args": { | |
| "pretrained": "/network/alexandre/research/llama2_7b_ultrachat/dense/dense_finetuning/dense_LR1e-4_E1/training", | |
| "trust_remote_code": true | |
| }, | |
| "num_fewshot": 0, | |
| "batch_size": "8", | |
| "batch_sizes": [], | |
| "device": "cuda:5", | |
| "no_cache": true, | |
| "limit": null, | |
| "bootstrap_iters": 100000, | |
| "description_dict": {} | |
| } | |
| } |