37 lines
961 B
JSON
37 lines
961 B
JSON
{
|
|
"results": {
|
|
"arc_pt": {
|
|
"acc": 0.24444444444444444,
|
|
"acc_stderr": 0.012569442967524474,
|
|
"acc_norm": 0.28888888888888886,
|
|
"acc_norm_stderr": 0.013256439556126792
|
|
},
|
|
"hellaswag_pt": {
|
|
"acc": 0.3326470906923827,
|
|
"acc_stderr": 0.004904738424240269,
|
|
"acc_norm": 0.39408386607433094,
|
|
"acc_norm_stderr": 0.00508682495262388
|
|
},
|
|
"truthfulqa_pt": {
|
|
"mc1": 0.23604060913705585,
|
|
"mc1_stderr": 0.015137046117152837,
|
|
"mc2": 0.42762827969970946,
|
|
"mc2_stderr": 0.014911010832660198
|
|
}
|
|
},
|
|
"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_17032104/step_400000",
|
|
"batch_size": 1,
|
|
"device": "cuda:0",
|
|
"no_cache": false,
|
|
"limit": null,
|
|
"bootstrap_iters": 100000,
|
|
"description_dict": {}
|
|
}
|
|
} |