| raidhon/coven_7b_128k_orpo_alpha | |
| | Tasks |Version| Filter |n-shot| Metric | Value | |Stderr| | |
| |---------------------------------------|-------|----------------|-----:|-----------|------:|---|-----:| | |
| |winogrande | 1|none | 0|acc | 0.7782|± |0.0117| | |
| |truthfulqa |N/A |none | 0|rouge1_max |47.8575|± |0.8139| | |
| | | |none | 0|bleu_max |21.9412|± |0.7280| | |
| | | |none | 0|rouge2_max |32.7726|± |0.9228| | |
| | | |none | 0|rougeL_diff|-1.4310|± |0.7806| | |
| | | |none | 0|acc | 0.4955|± |0.0115| | |
| | | |none | 0|bleu_diff |-0.2883|± |0.6228| | |
| | | |none | 0|rouge2_acc | 0.3807|± |0.0170| | |
| | | |none | 0|rougeL_max |44.1785|± |0.8274| | |
| | | |none | 0|rougeL_acc | 0.4443|± |0.0174| | |
| | | |none | 0|rouge2_diff|-1.5603|± |0.8950| | |
| | | |none | 0|bleu_acc | 0.4321|± |0.0173| | |
| | | |none | 0|rouge1_diff|-0.7276|± |0.7721| | |
| | | |none | 0|rouge1_acc | 0.4774|± |0.0175| | |
| | - truthfulqa_gen | 3|none | 0|bleu_max |21.9412|± |0.7280| | |
| | | |none | 0|bleu_acc | 0.4321|± |0.0173| | |
| | | |none | 0|bleu_diff |-0.2883|± |0.6228| | |
| | | |none | 0|rouge1_max |47.8575|± |0.8139| | |
| | | |none | 0|rouge1_acc | 0.4774|± |0.0175| | |
| | | |none | 0|rouge1_diff|-0.7276|± |0.7721| | |
| | | |none | 0|rouge2_max |32.7726|± |0.9228| | |
| | | |none | 0|rouge2_acc | 0.3807|± |0.0170| | |
| | | |none | 0|rouge2_diff|-1.5603|± |0.8950| | |
| | | |none | 0|rougeL_max |44.1785|± |0.8274| | |
| | | |none | 0|rougeL_acc | 0.4443|± |0.0174| | |
| | | |none | 0|rougeL_diff|-1.4310|± |0.7806| | |
| | - truthfulqa_mc1 | 2|none | 0|acc | 0.4174|± |0.0173| | |
| | - truthfulqa_mc2 | 2|none | 0|acc | 0.5736|± |0.0151| | |
| |piqa | 1|none | 0|acc | 0.8205|± |0.0090| | |
| | | |none | 0|acc_norm | 0.8395|± |0.0086| | |
| |openbookqa | 1|none | 0|acc | 0.3460|± |0.0213| | |
| | | |none | 0|acc_norm | 0.4800|± |0.0224| | |
| |mmlu |N/A |none | 0|acc | 0.6300|± |0.0038| | |
| | - humanities |N/A |none | 0|acc | 0.5779|± |0.0066| | |
| | - formal_logic | 0|none | 0|acc | 0.4127|± |0.0440| | |
| | - high_school_european_history | 0|none | 0|acc | 0.8061|± |0.0309| | |
| | - high_school_us_history | 0|none | 0|acc | 0.8480|± |0.0252| | |
| | - high_school_world_history | 0|none | 0|acc | 0.8523|± |0.0231| | |
| | - international_law | 0|none | 0|acc | 0.7934|± |0.0370| | |
| | - international_law | 0|none | 0|acc | 0.7934|± |0.0370| [46/1966] | |
| | - jurisprudence | 0|none | 0|acc | 0.7685|± |0.0408| | |
| | - logical_fallacies | 0|none | 0|acc | 0.7730|± |0.0329| | |
| | - moral_disputes | 0|none | 0|acc | 0.7110|± |0.0244| | |
| | - moral_scenarios | 0|none | 0|acc | 0.2894|± |0.0152| | |
| | - philosophy | 0|none | 0|acc | 0.7106|± |0.0258| | |
| | - prehistory | 0|none | 0|acc | 0.7685|± |0.0235| | |
| | - professional_law | 0|none | 0|acc | 0.4824|± |0.0128| | |
| | - world_religions | 0|none | 0|acc | 0.8129|± |0.0299| | |
| | - other |N/A |none | 0|acc | 0.7090|± |0.0078| | |
| | - business_ethics | 0|none | 0|acc | 0.5900|± |0.0494| | |
| | - clinical_knowledge | 0|none | 0|acc | 0.7245|± |0.0275| | |
| | - college_medicine | 0|none | 0|acc | 0.6532|± |0.0363| | |
| | - global_facts | 0|none | 0|acc | 0.3200|± |0.0469| | |
| | - human_aging | 0|none | 0|acc | 0.7040|± |0.0306| | |
| | - management | 0|none | 0|acc | 0.7864|± |0.0406| | |
| | - marketing | 0|none | 0|acc | 0.8632|± |0.0225| | |
| | - medical_genetics | 0|none | 0|acc | 0.7500|± |0.0435| | |
| | - miscellaneous | 0|none | 0|acc | 0.8212|± |0.0137| | |
| | - nutrition | 0|none | 0|acc | 0.7451|± |0.0250| | |
| | - professional_accounting | 0|none | 0|acc | 0.5000|± |0.0298| | |
| | - professional_medicine | 0|none | 0|acc | 0.7059|± |0.0277| | |
| | - virology | 0|none | 0|acc | 0.5301|± |0.0389| | |
| | - social_sciences |N/A |none | 0|acc | 0.7358|± |0.0077| | |
| | - econometrics | 0|none | 0|acc | 0.4474|± |0.0468| | |
| | - high_school_geography | 0|none | 0|acc | 0.7525|± |0.0307| | |
| | - high_school_government_and_politics| 0|none | 0|acc | 0.9016|± |0.0215| | |
| | - high_school_macroeconomics | 0|none | 0|acc | 0.6564|± |0.0241| | |
| | - high_school_microeconomics | 0|none | 0|acc | 0.6807|± |0.0303| | |
| | - high_school_psychology | 0|none | 0|acc | 0.8404|± |0.0157| | |
| | - human_sexuality | 0|none | 0|acc | 0.7405|± |0.0384| | |
| | - professional_psychology | 0|none | 0|acc | 0.6552|± |0.0192| | |
| | - public_relations | 0|none | 0|acc | 0.6727|± |0.0449| | |
| | - security_studies | 0|none | 0|acc | 0.7673|± |0.0270| | |
| | - sociology | 0|none | 0|acc | 0.8358|± |0.0262| | |
| | - us_foreign_policy | 0|none | 0|acc | 0.8600|± |0.0349| | |
| | - stem |N/A |none | 0|acc | 0.5265|± |0.0085| | |
| | - abstract_algebra | 0|none | 0|acc | 0.3100|± |0.0465| | |
| | - anatomy | 0|none | 0|acc | 0.6000|± |0.0423| | |
| | - astronomy | 0|none | 0|acc | 0.6842|± |0.0378| | |
| | - college_biology | 0|none | 0|acc | 0.7292|± |0.0372| | |
| | - college_chemistry | 0|none | 0|acc | 0.4700|± |0.0502| | |
| | - college_chemistry | 0|none | 0|acc | 0.4700|± |0.0502| [5/1966] | |
| | - college_computer_science | 0|none | 0|acc | 0.5600|± |0.0499| | |
| | - college_mathematics | 0|none | 0|acc | 0.3500|± |0.0479| | |
| | - college_physics | 0|none | 0|acc | 0.3529|± |0.0476| | |
| | - computer_security | 0|none | 0|acc | 0.7100|± |0.0456| | |
| | - conceptual_physics | 0|none | 0|acc | 0.5574|± |0.0325| | |
| | - electrical_engineering | 0|none | 0|acc | 0.5793|± |0.0411| | |
| | - elementary_mathematics | 0|none | 0|acc | 0.4101|± |0.0253| | |
| | - high_school_biology | 0|none | 0|acc | 0.7903|± |0.0232| | |
| | - high_school_chemistry | 0|none | 0|acc | 0.4828|± |0.0352| | |
| | - high_school_computer_science | 0|none | 0|acc | 0.6600|± |0.0476| | |
| | - high_school_mathematics | 0|none | 0|acc | 0.3444|± |0.0290| | |
| | - high_school_physics | 0|none | 0|acc | 0.3642|± |0.0393| | |
| | - high_school_statistics | 0|none | 0|acc | 0.5000|± |0.0341| | |
| | - machine_learning | 0|none | 0|acc | 0.5268|± |0.0474| | |
| |hellaswag | 1|none | 0|acc | 0.6537|± |0.0047| | |
| | | |none | 0|acc_norm | 0.8429|± |0.0036| | |
| |gsm8k | 3|strict-match | 5|exact_match| 0.7218|± |0.0123| | |
| | | |flexible-extract| 5|exact_match| 0.7263|± |0.0123| | |
| |boolq | 2|none | 0|acc | 0.8743|± |0.0058| | |
| |arc_easy | 1|none | 0|acc | 0.8502|± |0.0073| | |
| | | |none | 0|acc_norm | 0.8295|± |0.0077| | |
| |arc_challenge | 1|none | 0|acc | 0.5964|± |0.0143| | |
| | | |none | 0|acc_norm | 0.6169|± |0.0142| | |
| | Groups |Version|Filter|n-shot| Metric | Value | |Stderr| | |
| |------------------|-------|------|-----:|-----------|------:|---|-----:| | |
| |truthfulqa |N/A |none | 0|rouge1_max |47.8575|± |0.8139| | |
| | | |none | 0|bleu_max |21.9412|± |0.7280| | |
| | | |none | 0|rouge2_max |32.7726|± |0.9228| | |
| | | |none | 0|rougeL_diff|-1.4310|± |0.7806| | |
| | | |none | 0|acc | 0.4955|± |0.0115| | |
| | | |none | 0|bleu_diff |-0.2883|± |0.6228| | |
| | | |none | 0|rouge2_acc | 0.3807|± |0.0170| | |
| | | |none | 0|rougeL_max |44.1785|± |0.8274| | |
| | | |none | 0|rougeL_acc | 0.4443|± |0.0174| | |
| | | |none | 0|rouge2_diff|-1.5603|± |0.8950| | |
| | | |none | 0|bleu_acc | 0.4321|± |0.0173| | |
| | | |none | 0|rouge1_diff|-0.7276|± |0.7721| | |
| | | |none | 0|rouge1_acc | 0.4774|± |0.0175| | |
| |mmlu |N/A |none | 0|acc | 0.6300|± |0.0038| | |
| | - humanities |N/A |none | 0|acc | 0.5779|± |0.0066| | |
| | - other |N/A |none | 0|acc | 0.7090|± |0.0078| | |
| | - social_sciences|N/A |none | 0|acc | 0.7358|± |0.0077| | |
| | - stem |N/A |none | 0|acc | 0.5265|± |0.0085| | |