Pdbz199's picture
Upload local-decision-model
4b3077c verified
Raw History Blame Contribute Delete
5.19 kB
{
"backbone": "answerdotai/ModernBERT-base",
"temperature": {
"one": 1.2999999999999998,
"any": 1.109569472067845,
"span": 1.0717734625362931
},
"calibration_task_accuracy": {
"calib/benayas/snips": 0.87,
"calib/crowdflower/airline-sentiment": 0.735,
"calib/emo/emo2019": 0.445,
"calib/health_fact": 0.115,
"calib/insincere-questions": 0.93,
"calib/lex_glue/ledgar": 0.3875,
"calib/logical-fallacy": 0.2,
"calib/rotten_tomatoes": 0.905,
"calib/scicite": 0.76,
"calib/silicone/dyda_e": 0.7725,
"calib/subjectivity": 0.6989,
"calib/tuetschek/atis": 0.7725
},
"temperature_k_slope": 0.0,
"val_accuracy": {
"20ng": 0.8208,
"anli": 0.8773,
"bitext": 0.984,
"boolq": 0.796,
"civil": 0.9351,
"clinc": 0.9509,
"counterfactual": 0.988,
"csqa": 0.74,
"customer_reviews": 0.944,
"davidson": 0.936,
"dbpedia": 0.996,
"emotion": 0.9361,
"enron_spam": 0.992,
"fever_nli": 0.896,
"fewnerd": 0.896,
"gandalf": 0.987,
"go_emotions": 0.9568,
"jailbreak": 0.9903,
"massive_intent": 0.872,
"massive_scenario": 0.94,
"mnli": 0.868,
"multi_claims": 0.9086,
"multi_entities": 0.8863,
"multi_mix_bitext": 0.987,
"multi_mix_clinc": 0.9679,
"multi_mix_emotion": 0.9167,
"multi_mix_yahoo": 0.8529,
"paws": 0.976,
"prompt_injection_mix": 0.992,
"race": 0.832,
"safeguard": 1.0,
"scales_toxicity": 0.58,
"scales_yelp": 0.736,
"snli": 0.88,
"spml": 0.996,
"squad_v2": 0.748,
"sst2": 0.908,
"stsb": 0.544,
"synthetic_fields": 1.0,
"toxic_chat": 0.96,
"trec": 0.944,
"ts/CONDAQA": 0.0,
"ts/CREAK": 1.0,
"ts/EffectiveFeedbackStudentWriting": 0.5,
"ts/I2D2": 1.0,
"ts/PARARULE-Plus": 1.0,
"ts/Touche23-ValueEval": 1.0,
"ts/VUAC": 1.0,
"ts/ade_corpus_v2/Ade_corpus_v2_classification": 1.0,
"ts/args_me": 1.0,
"ts/avicenna": 0.6667,
"ts/blog_authorship_corpus/job": 1.0,
"ts/boolq-natural-perturbations": 1.0,
"ts/circa": 1.0,
"ts/citation_intent": 1.0,
"ts/clcd-english": 1.0,
"ts/commonsense_qa_2.0": 1.0,
"ts/crowdflower/corporate-messaging": 1.0,
"ts/crowdflower/economic-news": 1.0,
"ts/crowdflower/political-media-audience": 0.6667,
"ts/crowdflower/political-media-bias": 1.0,
"ts/crowdflower/political-media-message": 0.5,
"ts/crowdflower/text_emotion": 0.6667,
"ts/crowdflower/tweet_global_warming": 1.0,
"ts/cycic_classification": 0.5,
"ts/defeasible-nli/atomic": 1.0,
"ts/defeasible-nli/snli": 1.0,
"ts/dynahate": 1.0,
"ts/dynasent/dynabench.dynasent.r1.all/r1": 1.0,
"ts/dynasent/dynabench.dynasent.r2.all/r2": 0.5,
"ts/ethics/deontology": 1.0,
"ts/ethics/justice": 0.3333,
"ts/ethics/virtue": 1.0,
"ts/ethos/binary": 0.5,
"ts/fever-evidence-related/mwong--fever-related": 1.0,
"ts/glue/cola": 0.5,
"ts/glue/qqp": 1.0,
"ts/hate_speech18": 1.0,
"ts/hlgd": 1.0,
"ts/hope_edi/english": 0.8333,
"ts/humicroedit/subtask-2": 0.3333,
"ts/implicit-hate-stg1": 1.0,
"ts/language-identification": 1.0,
"ts/lex_glue/scotus": 0.4,
"ts/mbib-base/cognitive-bias": 0.6667,
"ts/mbib-base/fake-news": 0.0,
"ts/mbib-base/hate-speech": 0.5,
"ts/mbib-base/linguistic-bias": 1.0,
"ts/mbib-base/political-bias": 0.6667,
"ts/mbib-base/racial-bias": 1.0,
"ts/mbib-base/text-level-bias": 0.75,
"ts/mc_taco": 1.0,
"ts/medical_questions_pairs": 1.0,
"ts/natural-language-satisfiability": 0.0,
"ts/numer_sense": 0.5,
"ts/open_question_type": 1.0,
"ts/parade": 0.25,
"ts/phrase_similarity": 0.6667,
"ts/pragmeval/emergent": 0.0,
"ts/pragmeval/gum": 1.0,
"ts/pragmeval/mrda": 0.3333,
"ts/pragmeval/pdtb": 0.3333,
"ts/pragmeval/sarcasm": 1.0,
"ts/pragmeval/stac": 0.5,
"ts/pragmeval/verifiability": 1.0,
"ts/probability_words_nli/reasoning_1hop": 0.75,
"ts/probability_words_nli/reasoning_2hop": 1.0,
"ts/probability_words_nli/usnli": 0.4,
"ts/quarel": 0.6,
"ts/robust_nli_li_ts": 1.0,
"ts/rumoureval_2019/RumourEval2019": 1.0,
"ts/sciie": 1.0,
"ts/scruples": 0.6,
"ts/sem_eval_2010_task_8": 1.0,
"ts/silicone/dyda_da": 1.0,
"ts/silicone/maptask": 1.0,
"ts/silicone/meld_e": 0.6667,
"ts/silicone/meld_s": 0.6667,
"ts/silicone/oasis": 0.6,
"ts/silicone/sem": 0.75,
"ts/spartqa-yn": 0.6667,
"ts/starcon": 0.5,
"ts/strategy-qa": 1.0,
"ts/super_glue/multirc": 0.4,
"ts/super_glue/wic": 0.5,
"ts/tweet_eval/emotion": 1.0,
"ts/tweet_eval/stance_feminist": 1.0,
"ts/tweet_eval/stance_hillary": 1.0,
"ts/tweets_hate_speech_detection": 0.6667,
"ts/twentyquestions": 1.0,
"ts/vitaminc/tals--vitaminc": 1.0,
"ts/wiki_qa": 1.0,
"ts/winowhy": 1.0,
"tweet_hate": 0.868,
"tweet_irony": 0.62,
"tweet_offensive": 0.852,
"tweet_sentiment": 0.732,
"tweet_sentiment2": 0.792,
"web_spam": 0.996,
"yahoo": 0.8035,
"yelp_sent": 0.8053,
"yelp_stars": 0.6204
},
"source": "https://github.com/Pdbz199/local-decision-model"
}