37 lines
925 B
JSON
37 lines
925 B
JSON
{
|
|
"results": {
|
|
"arc_pt": {
|
|
"acc": 0.24444444444444444,
|
|
"acc_stderr": 0.012569442967524477,
|
|
"acc_norm": 0.3076923076923077,
|
|
"acc_norm_stderr": 0.01349897032094141
|
|
},
|
|
"hellaswag_pt": {
|
|
"acc": 0.3567017011593889,
|
|
"acc_stderr": 0.004986605352113748,
|
|
"acc_norm": 0.43504171632896305,
|
|
"acc_norm_stderr": 0.005160833515742615
|
|
},
|
|
"truthfulqa_pt": {
|
|
"mc1": 0.22715736040609136,
|
|
"mc1_stderr": 0.014935562313676114,
|
|
"mc2": 0.4114457861517422,
|
|
"mc2_stderr": 0.014884914480065946
|
|
}
|
|
},
|
|
"versions": {
|
|
"arc_pt": 0,
|
|
"hellaswag_pt": 1,
|
|
"truthfulqa_pt": 1
|
|
},
|
|
"config": {
|
|
"model": "hf-auto",
|
|
"model_args": "pretrained=/lustre/mlnvme/data/asen_hpc-mula/Tucano-1b1-DPO",
|
|
"batch_size": 1,
|
|
"device": "cuda:0",
|
|
"no_cache": false,
|
|
"limit": null,
|
|
"bootstrap_iters": 100000,
|
|
"description_dict": {}
|
|
}
|
|
} |