lm1-2b8-55b-oscarpy / evaluation /2b855b70oscarpy /2b855b70oscarpy-results_lm-eval_global_step52452_2023-01-21-10-46-05.json
Muennighoff's picture
Add files
c469d14
raw
history blame
No virus
2.44 kB
{
"results": {
"anli_r1": {
"acc": 0.323,
"acc_stderr": 0.014794927843348635
},
"anli_r2": {
"acc": 0.332,
"acc_stderr": 0.014899597242811482
},
"anli_r3": {
"acc": 0.33,
"acc_stderr": 0.013579531277800923
},
"cb": {
"acc": 0.25,
"acc_stderr": 0.058387420812114225,
"f1": 0.2191358024691358
},
"copa": {
"acc": 0.69,
"acc_stderr": 0.04648231987117316
},
"hellaswag": {
"acc": 0.3650667197769369,
"acc_stderr": 0.004804649197163699,
"acc_norm": 0.4427404899422426,
"acc_norm_stderr": 0.004956953917781311
},
"rte": {
"acc": 0.5451263537906137,
"acc_stderr": 0.029973636495415252
},
"winogrande": {
"acc": 0.5185477505919495,
"acc_stderr": 0.014042813708888378
},
"storycloze_2016": {
"acc": 0.6467129877071085,
"acc_stderr": 0.011053474766125627
},
"boolq": {
"acc": 0.5788990825688073,
"acc_stderr": 0.008635491562221343
},
"arc_easy": {
"acc": 0.5294612794612794,
"acc_stderr": 0.010241957728409686,
"acc_norm": 0.476010101010101,
"acc_norm_stderr": 0.010247967392742691
},
"arc_challenge": {
"acc": 0.2235494880546075,
"acc_stderr": 0.012174896631202605,
"acc_norm": 0.2525597269624573,
"acc_norm_stderr": 0.012696728980207706
},
"sciq": {
"acc": 0.811,
"acc_stderr": 0.012386784588117707,
"acc_norm": 0.726,
"acc_norm_stderr": 0.014111099288259587
},
"piqa": {
"acc": 0.7034820457018498,
"acc_stderr": 0.010656078922661153,
"acc_norm": 0.7067464635473341,
"acc_norm_stderr": 0.010621818421101931
}
},
"versions": {
"anli_r1": 0,
"anli_r2": 0,
"anli_r3": 0,
"cb": 1,
"copa": 0,
"hellaswag": 0,
"rte": 0,
"winogrande": 0,
"storycloze_2016": 0,
"boolq": 1,
"arc_easy": 0,
"arc_challenge": 0,
"sciq": 0,
"piqa": 0
}
}