Files
2026-07-13 12:45:13 +08:00

84 lines
2.1 KiB
JSON

{
"results": {
"arc_challenge": {
"acc": 0.4445392491467577,
"acc_stderr": 0.014521226405627079,
"acc_norm": 0.4803754266211604,
"acc_norm_stderr": 0.014600132075947092
},
"arc_easy": {
"acc": 0.7613636363636364,
"acc_stderr": 0.008746465140706127,
"acc_norm": 0.7314814814814815,
"acc_norm_stderr": 0.009094042554994847
},
"boolq": {
"acc": 0.7452599388379205,
"acc_stderr": 0.007620703281690057
},
"hellaswag": {
"acc": 0.47988448516231824,
"acc_stderr": 0.004985741706385726,
"acc_norm": 0.6261700856403107,
"acc_norm_stderr": 0.004828305041904399
},
"lambada_openai": {
"ppl": 8.945202930351474,
"ppl_stderr": 0.3005661666926477,
"acc": 0.527459732194838,
"acc_stderr": 0.0069554645156210786
},
"openbookqa": {
"acc": 0.376,
"acc_stderr": 0.021683827539286115,
"acc_norm": 0.482,
"acc_norm_stderr": 0.02236856511738799
},
"piqa": {
"acc": 0.7633297062023939,
"acc_stderr": 0.009916841655042806,
"acc_norm": 0.7578890097932536,
"acc_norm_stderr": 0.009994371269104381
},
"sciq": {
"acc": 0.932,
"acc_stderr": 0.007964887911291603,
"acc_norm": 0.916,
"acc_norm_stderr": 0.00877616208949113
},
"siqa": {
"acc": 0.5537359263050153,
"acc_stderr": 0.01124854090154796,
"acc_norm": 0.5957011258955988,
"acc_norm_stderr": 0.0111048923983008
},
"winogrande": {
"acc": 0.7253354380426204,
"acc_stderr": 0.012544516005117187
}
},
"versions": {
"arc_challenge": 0,
"arc_easy": 0,
"boolq": 1,
"hellaswag": 0,
"lambada_openai": 0,
"openbookqa": 0,
"piqa": 0,
"sciq": 0,
"siqa": 0,
"winogrande": 0
},
"config": {
"model": "gpt2",
"model_args": "use_fast=False,pretrained=microsoft/phi-1_5,trust_remote_code=True,low_cpu_mem_usage=True,dtype=bfloat16",
"num_fewshot": 0,
"batch_size": "16",
"batch_sizes": [],
"device": "cuda:5",
"no_cache": false,
"limit": null,
"bootstrap_iters": 100000,
"description_dict": {}
}
}