coven_7b_128k_orpo_alpha / bench-mistral.txt
raidhon's picture
Upload folder using huggingface_hub
d4d334b verified
mistralai/Mistral-7B-Instruct-v0.2
| Tasks |Version| Filter |n-shot| Metric | Value | |Stderr|
|---------------------------------------|-------|----------------|-----:|-----------|------:|---|-----:|
|winogrande | 1|none | 0|acc | 0.7364|± |0.0124|
|truthfulqa |N/A |none | 0|acc | 0.5954|± |0.0116|
| | |none | 0|rouge1_max |46.4534|± |0.8502|
| | |none | 0|rougeL_diff| 5.5378|± |0.8859|
| | |none | 0|bleu_acc | 0.5483|± |0.0174|
| | |none | 0|rouge2_max |31.1969|± |0.9785|
| | |none | 0|rougeL_max |43.4263|± |0.8666|
| | |none | 0|rougeL_acc | 0.5606|± |0.0174|
| | |none | 0|rouge2_acc | 0.4529|± |0.0174|
| | |none | 0|rouge2_diff| 5.3591|± |0.9416|
| | |none | 0|bleu_max |21.2977|± |0.7504|
| | |none | 0|rouge1_acc | 0.5741|± |0.0173|
| | |none | 0|bleu_diff | 4.3215|± |0.6161|
| | |none | 0|rouge1_diff| 5.7381|± |0.8786|
| - truthfulqa_gen | 3|none | 0|bleu_max |21.2977|± |0.7504|
| | |none | 0|bleu_acc | 0.5483|± |0.0174|
| | |none | 0|bleu_diff | 4.3215|± |0.6161|
| | |none | 0|rouge1_max |46.4534|± |0.8502|
| | |none | 0|rouge1_acc | 0.5741|± |0.0173|
| | |none | 0|rouge1_diff| 5.7381|± |0.8786|
| | |none | 0|rouge2_max |31.1969|± |0.9785|
| | |none | 0|rouge2_acc | 0.4529|± |0.0174|
| | |none | 0|rouge2_diff| 5.3591|± |0.9416|
| | |none | 0|rougeL_max |43.4263|± |0.8666|
| | |none | 0|rougeL_acc | 0.5606|± |0.0174|
| | |none | 0|rougeL_diff| 5.5378|± |0.8859|
| - truthfulqa_mc1 | 2|none | 0|acc | 0.5226|± |0.0175|
| - truthfulqa_mc2 | 2|none | 0|acc | 0.6681|± |0.0153|
|piqa | 1|none | 0|acc | 0.8003|± |0.0093|
| | |none | 0|acc_norm | 0.8047|± |0.0092|
|openbookqa | 1|none | 0|acc | 0.3600|± |0.0215|
| | |none | 0|acc_norm | 0.4520|± |0.0223|
|mmlu |N/A |none | 0|acc | 0.5879|± |0.0039|
| - humanities |N/A |none | 0|acc | 0.5396|± |0.0069|
| - formal_logic | 0|none | 0|acc | 0.3651|± |0.0431|
| - high_school_european_history | 0|none | 0|acc | 0.7273|± |0.0348|
| - high_school_us_history | 0|none | 0|acc | 0.7794|± |0.0291|
| - high_school_world_history | 0|none | 0|acc | 0.7764|± |0.0271|
| - international_law | 0|none | 0|acc | 0.7438|± |0.0398|
| - jurisprudence | 0|none | 0|acc | 0.7130|± |0.0437|
| - logical_fallacies | 0|none | 0|acc | 0.7546|± |0.0338|
| - moral_disputes | 0|none | 0|acc | 0.6532|± |0.0256|
| - moral_scenarios | 0|none | 0|acc | 0.3564|± |0.0160|
| - philosophy | 0|none | 0|acc | 0.6463|± |0.0272|
| - prehistory | 0|none | 0|acc | 0.6821|± |0.0259|
| - professional_law | 0|none | 0|acc | 0.4133|± |0.0126|
| - world_religions | 0|none | 0|acc | 0.8129|± |0.0299|
| - other |N/A |none | 0|acc | 0.6621|± |0.0082|
| - business_ethics | 0|none | 0|acc | 0.5900|± |0.0494|
| - clinical_knowledge | 0|none | 0|acc | 0.6491|± |0.0294|
| - college_medicine | 0|none | 0|acc | 0.5549|± |0.0379|
| - global_facts | 0|none | 0|acc | 0.3800|± |0.0488|
| - human_aging | 0|none | 0|acc | 0.6233|± |0.0325|
| - management | 0|none | 0|acc | 0.7184|± |0.0445|
| - marketing | 0|none | 0|acc | 0.8761|± |0.0216|
| - medical_genetics | 0|none | 0|acc | 0.6500|± |0.0479|
| - miscellaneous | 0|none | 0|acc | 0.7944|± |0.0145|
| - nutrition | 0|none | 0|acc | 0.6732|± |0.0269|
| - professional_accounting | 0|none | 0|acc | 0.4468|± |0.0297|
| - professional_medicine | 0|none | 0|acc | 0.6581|± |0.0288|
| - virology | 0|none | 0|acc | 0.4578|± |0.0388|
| - social_sciences |N/A |none | 0|acc | 0.6799|± |0.0082|
| - econometrics | 0|none | 0|acc | 0.4649|± |0.0469|
| - high_school_geography | 0|none | 0|acc | 0.7374|± |0.0314|
| - high_school_government_and_politics| 0|none | 0|acc | 0.8031|± |0.0287|
| - high_school_macroeconomics | 0|none | 0|acc | 0.5590|± |0.0252|
| - high_school_microeconomics | 0|none | 0|acc | 0.6387|± |0.0312|
| - high_school_psychology | 0|none | 0|acc | 0.7853|± |0.0176|
| - human_sexuality | 0|none | 0|acc | 0.6794|± |0.0409|
| - professional_psychology | 0|none | 0|acc | 0.5866|± |0.0199|
| - public_relations | 0|none | 0|acc | 0.6455|± |0.0458|
| - security_studies | 0|none | 0|acc | 0.6816|± |0.0298|
| - sociology | 0|none | 0|acc | 0.8408|± |0.0259|
| - us_foreign_policy | 0|none | 0|acc | 0.8500|± |0.0359|
| - stem |N/A |none | 0|acc | 0.4970|± |0.0087|
| - abstract_algebra | 0|none | 0|acc | 0.3200|± |0.0469|
| - anatomy | 0|none | 0|acc | 0.5704|± |0.0428|
| - astronomy | 0|none | 0|acc | 0.6382|± |0.0391|
| - college_biology | 0|none | 0|acc | 0.6597|± |0.0396|
| - college_chemistry | 0|none | 0|acc | 0.4100|± |0.0494|
| - college_computer_science | 0|none | 0|acc | 0.5400|± |0.0501|
| - college_mathematics | 0|none | 0|acc | 0.3400|± |0.0476|
| - college_physics | 0|none | 0|acc | 0.3725|± |0.0481|
| - computer_security | 0|none | 0|acc | 0.6700|± |0.0473|
| - conceptual_physics | 0|none | 0|acc | 0.4809|± |0.0327|
| - electrical_engineering | 0|none | 0|acc | 0.5931|± |0.0409|
| - elementary_mathematics | 0|none | 0|acc | 0.4233|± |0.0254|
| - high_school_biology | 0|none | 0|acc | 0.6774|± |0.0266|
| - high_school_chemistry | 0|none | 0|acc | 0.4877|± |0.0352|
| - high_school_computer_science | 0|none | 0|acc | 0.6100|± |0.0490|
| - high_school_mathematics | 0|none | 0|acc | 0.3556|± |0.0292|
| - high_school_physics | 0|none | 0|acc | 0.3642|± |0.0393|
| - high_school_statistics | 0|none | 0|acc | 0.4630|± |0.0340|
| - machine_learning | 0|none | 0|acc | 0.4643|± |0.0473|
|hellaswag | 1|none | 0|acc | 0.6608|± |0.0047|
| | |none | 0|acc_norm | 0.8368|± |0.0037|
|gsm8k | 3|strict-match | 5|exact_match| 0.4155|± |0.0136|
| | |flexible-extract| 5|exact_match| 0.4193|± |0.0136|
|boolq | 2|none | 0|acc | 0.8529|± |0.0062|
|arc_easy | 1|none | 0|acc | 0.8136|± |0.0080|
| | |none | 0|acc_norm | 0.7660|± |0.0087|
|arc_challenge | 1|none | 0|acc | 0.5435|± |0.0146|
| | |none | 0|acc_norm | 0.5580|± |0.0145|
| Groups |Version|Filter|n-shot| Metric | Value | |Stderr|
|------------------|-------|------|-----:|-----------|------:|---|-----:|
|truthfulqa |N/A |none | 0|acc | 0.5954|± |0.0116|
| | |none | 0|rouge1_max |46.4534|± |0.8502|
| | |none | 0|rougeL_diff| 5.5378|± |0.8859|
| | |none | 0|bleu_acc | 0.5483|± |0.0174|
| | |none | 0|rouge2_max |31.1969|± |0.9785|
| | |none | 0|rougeL_max |43.4263|± |0.8666|
| | |none | 0|rougeL_acc | 0.5606|± |0.0174|
| | |none | 0|rouge2_acc | 0.4529|± |0.0174|
| | |none | 0|rouge2_diff| 5.3591|± |0.9416|
| | |none | 0|bleu_max |21.2977|± |0.7504|
| | |none | 0|rouge1_acc | 0.5741|± |0.0173|
| | |none | 0|bleu_diff | 4.3215|± |0.6161|
| | |none | 0|rouge1_diff| 5.7381|± |0.8786|
|mmlu |N/A |none | 0|acc | 0.5879|± |0.0039|
| - humanities |N/A |none | 0|acc | 0.5396|± |0.0069|
| - other |N/A |none | 0|acc | 0.6621|± |0.0082|
| - social_sciences|N/A |none | 0|acc | 0.6799|± |0.0082|
| - stem |N/A |none | 0|acc | 0.4970|± |0.0087|