kotodama-108m-base / bcpt-analysis /lm_eval_results.json
LuxiaSL's picture
Upload folder using huggingface_hub
085670e verified
{
"arc_easy": {
"alias": "arc_easy",
"acc,none": 0.44486531986531985,
"acc_stderr,none": 0.01019721669035638,
"acc_norm,none": 0.38762626262626265,
"acc_norm_stderr,none": 0.009997307914447627
},
"boolq": {
"alias": "boolq",
"acc,none": 0.4987767584097859,
"acc_stderr,none": 0.008745028805557891
},
"copa": {
"alias": "copa",
"acc,none": 0.59,
"acc_stderr,none": 0.04943110704237104
},
"hellaswag": {
"alias": "hellaswag",
"acc,none": 0.27962557259510057,
"acc_stderr,none": 0.0044789797955071394,
"acc_norm,none": 0.2954590718980283,
"acc_norm_stderr,none": 0.004553164013379509
},
"lambada_openai": {
"alias": "lambada_openai",
"perplexity,none": 85.46599600179017,
"perplexity_stderr,none": 3.9314317838745363,
"acc,none": 0.2965262953619251,
"acc_stderr,none": 0.006363083362328583
},
"piqa": {
"alias": "piqa",
"acc,none": 0.5875952121871599,
"acc_stderr,none": 0.011485407152743092,
"acc_norm,none": 0.5712731229597389,
"acc_norm_stderr,none": 0.0115466944357122
},
"sciq": {
"alias": "sciq",
"acc,none": 0.779,
"acc_stderr,none": 0.01312750285969618,
"acc_norm,none": 0.685,
"acc_norm_stderr,none": 0.014696631960792617
},
"wikitext": {
"alias": "wikitext",
"word_perplexity,none": 52.09098606764624,
"word_perplexity_stderr,none": "N/A",
"byte_perplexity,none": 2.0943206931231853,
"byte_perplexity_stderr,none": "N/A",
"bits_per_byte,none": 1.0664823720462002,
"bits_per_byte_stderr,none": "N/A"
},
"winogrande": {
"alias": "winogrande",
"acc,none": 0.5146014206787688,
"acc_stderr,none": 0.014046492383275955
}
}