37 lines
958 B
JSON
37 lines
958 B
JSON
{
|
|
"results": {
|
|
"arc_pt": {
|
|
"acc": 0.2452991452991453,
|
|
"acc_stderr": 0.012584274496277251,
|
|
"acc_norm": 0.30427350427350425,
|
|
"acc_norm_stderr": 0.013456870841977919
|
|
},
|
|
"hellaswag_pt": {
|
|
"acc": 0.35518474374255066,
|
|
"acc_stderr": 0.004981854172537992,
|
|
"acc_norm": 0.4284321161555965,
|
|
"acc_norm_stderr": 0.005151350797741933
|
|
},
|
|
"truthfulqa_pt": {
|
|
"mc1": 0.233502538071066,
|
|
"mc1_stderr": 0.015080432502225448,
|
|
"mc2": 0.4158988776785719,
|
|
"mc2_stderr": 0.014912096381642538
|
|
}
|
|
},
|
|
"versions": {
|
|
"arc_pt": 0,
|
|
"hellaswag_pt": 1,
|
|
"truthfulqa_pt": 1
|
|
},
|
|
"config": {
|
|
"model": "hf-auto",
|
|
"model_args": "pretrained=/lustre/mlnvme/data/asen_hpc-mula/checkpoints-llama/slurm_job_17032105/step_480000",
|
|
"batch_size": 1,
|
|
"device": "cuda:0",
|
|
"no_cache": false,
|
|
"limit": null,
|
|
"bootstrap_iters": 100000,
|
|
"description_dict": {}
|
|
}
|
|
} |