Document six completed LR runs as preparation for full Aya training on Perun. Record selection of LR 0.00010 by lowest final validation loss, selected-model lm-eval and partial SK-bench results, reproducible provenance, and dataset-access/context-truncation limitations. Preserve existing 30k and Titan material.
223 lines
11 KiB
Plaintext
223 lines
11 KiB
Plaintext
arc.prompt3_mqa_single_correct_sk|0
|
|
arc.prompt1_mqa_single_correct_sk|0
|
|
arc.prompt2_mqa_single_correct_sk|0
|
|
belebele.prompt3_mqa_single_correct_sk|0
|
|
belebele.prompt1_mqa_single_correct_sk|0
|
|
belebele.prompt2_mqa_single_correct_sk|0
|
|
financial_exams.prompt1_completion_sk|0
|
|
financial_exams.prompt3_completion_sk|0
|
|
financial_exams.prompt2_completion_sk|0
|
|
mmlu.prompt3_mqa_single_correct_sk:abstract_algebra|0
|
|
mmlu.prompt1_mqa_single_correct_sk:abstract_algebra|0
|
|
mmlu.prompt2_mqa_single_correct_sk:abstract_algebra|0
|
|
mmlu.prompt3_mqa_single_correct_sk:anatomy|0
|
|
mmlu.prompt1_mqa_single_correct_sk:anatomy|0
|
|
mmlu.prompt2_mqa_single_correct_sk:anatomy|0
|
|
mmlu.prompt3_mqa_single_correct_sk:astronomy|0
|
|
mmlu.prompt1_mqa_single_correct_sk:astronomy|0
|
|
mmlu.prompt2_mqa_single_correct_sk:astronomy|0
|
|
mmlu.prompt3_mqa_single_correct_sk:business_ethics|0
|
|
mmlu.prompt1_mqa_single_correct_sk:business_ethics|0
|
|
mmlu.prompt2_mqa_single_correct_sk:business_ethics|0
|
|
mmlu.prompt3_mqa_single_correct_sk:clinical_knowledge|0
|
|
mmlu.prompt1_mqa_single_correct_sk:clinical_knowledge|0
|
|
mmlu.prompt2_mqa_single_correct_sk:clinical_knowledge|0
|
|
mmlu.prompt3_mqa_single_correct_sk:college_biology|0
|
|
mmlu.prompt1_mqa_single_correct_sk:college_biology|0
|
|
mmlu.prompt2_mqa_single_correct_sk:college_biology|0
|
|
mmlu.prompt3_mqa_single_correct_sk:college_chemistry|0
|
|
mmlu.prompt1_mqa_single_correct_sk:college_chemistry|0
|
|
mmlu.prompt2_mqa_single_correct_sk:college_chemistry|0
|
|
mmlu.prompt3_mqa_single_correct_sk:college_computer_science|0
|
|
mmlu.prompt1_mqa_single_correct_sk:college_computer_science|0
|
|
mmlu.prompt2_mqa_single_correct_sk:college_computer_science|0
|
|
mmlu.prompt3_mqa_single_correct_sk:college_mathematics|0
|
|
mmlu.prompt1_mqa_single_correct_sk:college_mathematics|0
|
|
mmlu.prompt2_mqa_single_correct_sk:college_mathematics|0
|
|
mmlu.prompt3_mqa_single_correct_sk:college_medicine|0
|
|
mmlu.prompt1_mqa_single_correct_sk:college_medicine|0
|
|
mmlu.prompt2_mqa_single_correct_sk:college_medicine|0
|
|
mmlu.prompt3_mqa_single_correct_sk:college_physics|0
|
|
mmlu.prompt1_mqa_single_correct_sk:college_physics|0
|
|
mmlu.prompt2_mqa_single_correct_sk:college_physics|0
|
|
mmlu.prompt3_mqa_single_correct_sk:computer_security|0
|
|
mmlu.prompt1_mqa_single_correct_sk:computer_security|0
|
|
mmlu.prompt2_mqa_single_correct_sk:computer_security|0
|
|
mmlu.prompt3_mqa_single_correct_sk:conceptual_physics|0
|
|
mmlu.prompt1_mqa_single_correct_sk:conceptual_physics|0
|
|
mmlu.prompt2_mqa_single_correct_sk:conceptual_physics|0
|
|
mmlu.prompt3_mqa_single_correct_sk:econometrics|0
|
|
mmlu.prompt1_mqa_single_correct_sk:econometrics|0
|
|
mmlu.prompt2_mqa_single_correct_sk:econometrics|0
|
|
mmlu.prompt3_mqa_single_correct_sk:electrical_engineering|0
|
|
mmlu.prompt1_mqa_single_correct_sk:electrical_engineering|0
|
|
mmlu.prompt2_mqa_single_correct_sk:electrical_engineering|0
|
|
mmlu.prompt3_mqa_single_correct_sk:elementary_mathematics|0
|
|
mmlu.prompt1_mqa_single_correct_sk:elementary_mathematics|0
|
|
mmlu.prompt2_mqa_single_correct_sk:elementary_mathematics|0
|
|
mmlu.prompt3_mqa_single_correct_sk:formal_logic|0
|
|
mmlu.prompt1_mqa_single_correct_sk:formal_logic|0
|
|
mmlu.prompt2_mqa_single_correct_sk:formal_logic|0
|
|
mmlu.prompt3_mqa_single_correct_sk:global_facts|0
|
|
mmlu.prompt1_mqa_single_correct_sk:global_facts|0
|
|
mmlu.prompt2_mqa_single_correct_sk:global_facts|0
|
|
mmlu.prompt3_mqa_single_correct_sk:high_school_biology|0
|
|
mmlu.prompt1_mqa_single_correct_sk:high_school_biology|0
|
|
mmlu.prompt2_mqa_single_correct_sk:high_school_biology|0
|
|
mmlu.prompt3_mqa_single_correct_sk:high_school_chemistry|0
|
|
mmlu.prompt1_mqa_single_correct_sk:high_school_chemistry|0
|
|
mmlu.prompt2_mqa_single_correct_sk:high_school_chemistry|0
|
|
mmlu.prompt3_mqa_single_correct_sk:high_school_computer_science|0
|
|
mmlu.prompt1_mqa_single_correct_sk:high_school_computer_science|0
|
|
mmlu.prompt2_mqa_single_correct_sk:high_school_computer_science|0
|
|
mmlu.prompt3_mqa_single_correct_sk:high_school_european_history|0
|
|
mmlu.prompt1_mqa_single_correct_sk:high_school_european_history|0
|
|
mmlu.prompt2_mqa_single_correct_sk:high_school_european_history|0
|
|
mmlu.prompt3_mqa_single_correct_sk:high_school_geography|0
|
|
mmlu.prompt1_mqa_single_correct_sk:high_school_geography|0
|
|
mmlu.prompt2_mqa_single_correct_sk:high_school_geography|0
|
|
mmlu.prompt3_mqa_single_correct_sk:high_school_government_and_politics|0
|
|
mmlu.prompt1_mqa_single_correct_sk:high_school_government_and_politics|0
|
|
mmlu.prompt2_mqa_single_correct_sk:high_school_government_and_politics|0
|
|
mmlu.prompt3_mqa_single_correct_sk:high_school_macroeconomics|0
|
|
mmlu.prompt1_mqa_single_correct_sk:high_school_macroeconomics|0
|
|
mmlu.prompt2_mqa_single_correct_sk:high_school_macroeconomics|0
|
|
mmlu.prompt3_mqa_single_correct_sk:high_school_mathematics|0
|
|
mmlu.prompt1_mqa_single_correct_sk:high_school_mathematics|0
|
|
mmlu.prompt2_mqa_single_correct_sk:high_school_mathematics|0
|
|
mmlu.prompt3_mqa_single_correct_sk:high_school_microeconomics|0
|
|
mmlu.prompt1_mqa_single_correct_sk:high_school_microeconomics|0
|
|
mmlu.prompt2_mqa_single_correct_sk:high_school_microeconomics|0
|
|
mmlu.prompt3_mqa_single_correct_sk:high_school_physics|0
|
|
mmlu.prompt1_mqa_single_correct_sk:high_school_physics|0
|
|
mmlu.prompt2_mqa_single_correct_sk:high_school_physics|0
|
|
mmlu.prompt3_mqa_single_correct_sk:high_school_psychology|0
|
|
mmlu.prompt1_mqa_single_correct_sk:high_school_psychology|0
|
|
mmlu.prompt2_mqa_single_correct_sk:high_school_psychology|0
|
|
mmlu.prompt3_mqa_single_correct_sk:high_school_statistics|0
|
|
mmlu.prompt1_mqa_single_correct_sk:high_school_statistics|0
|
|
mmlu.prompt2_mqa_single_correct_sk:high_school_statistics|0
|
|
mmlu.prompt3_mqa_single_correct_sk:high_school_us_history|0
|
|
mmlu.prompt1_mqa_single_correct_sk:high_school_us_history|0
|
|
mmlu.prompt2_mqa_single_correct_sk:high_school_us_history|0
|
|
mmlu.prompt3_mqa_single_correct_sk:high_school_world_history|0
|
|
mmlu.prompt1_mqa_single_correct_sk:high_school_world_history|0
|
|
mmlu.prompt2_mqa_single_correct_sk:high_school_world_history|0
|
|
mmlu.prompt3_mqa_single_correct_sk:human_aging|0
|
|
mmlu.prompt1_mqa_single_correct_sk:human_aging|0
|
|
mmlu.prompt2_mqa_single_correct_sk:human_aging|0
|
|
mmlu.prompt3_mqa_single_correct_sk:human_sexuality|0
|
|
mmlu.prompt1_mqa_single_correct_sk:human_sexuality|0
|
|
mmlu.prompt2_mqa_single_correct_sk:human_sexuality|0
|
|
mmlu.prompt3_mqa_single_correct_sk:international_law|0
|
|
mmlu.prompt1_mqa_single_correct_sk:international_law|0
|
|
mmlu.prompt2_mqa_single_correct_sk:international_law|0
|
|
mmlu.prompt3_mqa_single_correct_sk:jurisprudence|0
|
|
mmlu.prompt1_mqa_single_correct_sk:jurisprudence|0
|
|
mmlu.prompt2_mqa_single_correct_sk:jurisprudence|0
|
|
mmlu.prompt3_mqa_single_correct_sk:logical_fallacies|0
|
|
mmlu.prompt1_mqa_single_correct_sk:logical_fallacies|0
|
|
mmlu.prompt2_mqa_single_correct_sk:logical_fallacies|0
|
|
mmlu.prompt3_mqa_single_correct_sk:machine_learning|0
|
|
mmlu.prompt1_mqa_single_correct_sk:machine_learning|0
|
|
mmlu.prompt2_mqa_single_correct_sk:machine_learning|0
|
|
mmlu.prompt3_mqa_single_correct_sk:management|0
|
|
mmlu.prompt1_mqa_single_correct_sk:management|0
|
|
mmlu.prompt2_mqa_single_correct_sk:management|0
|
|
mmlu.prompt3_mqa_single_correct_sk:marketing|0
|
|
mmlu.prompt1_mqa_single_correct_sk:marketing|0
|
|
mmlu.prompt2_mqa_single_correct_sk:marketing|0
|
|
mmlu.prompt3_mqa_single_correct_sk:medical_genetics|0
|
|
mmlu.prompt1_mqa_single_correct_sk:medical_genetics|0
|
|
mmlu.prompt2_mqa_single_correct_sk:medical_genetics|0
|
|
mmlu.prompt3_mqa_single_correct_sk:miscellaneous|0
|
|
mmlu.prompt1_mqa_single_correct_sk:miscellaneous|0
|
|
mmlu.prompt2_mqa_single_correct_sk:miscellaneous|0
|
|
mmlu.prompt3_mqa_single_correct_sk:moral_disputes|0
|
|
mmlu.prompt1_mqa_single_correct_sk:moral_disputes|0
|
|
mmlu.prompt2_mqa_single_correct_sk:moral_disputes|0
|
|
mmlu.prompt3_mqa_single_correct_sk:moral_scenarios|0
|
|
mmlu.prompt1_mqa_single_correct_sk:moral_scenarios|0
|
|
mmlu.prompt2_mqa_single_correct_sk:moral_scenarios|0
|
|
mmlu.prompt3_mqa_single_correct_sk:nutrition|0
|
|
mmlu.prompt1_mqa_single_correct_sk:nutrition|0
|
|
mmlu.prompt2_mqa_single_correct_sk:nutrition|0
|
|
mmlu.prompt3_mqa_single_correct_sk:philosophy|0
|
|
mmlu.prompt1_mqa_single_correct_sk:philosophy|0
|
|
mmlu.prompt2_mqa_single_correct_sk:philosophy|0
|
|
mmlu.prompt3_mqa_single_correct_sk:prehistory|0
|
|
mmlu.prompt1_mqa_single_correct_sk:prehistory|0
|
|
mmlu.prompt2_mqa_single_correct_sk:prehistory|0
|
|
mmlu.prompt3_mqa_single_correct_sk:professional_accounting|0
|
|
mmlu.prompt1_mqa_single_correct_sk:professional_accounting|0
|
|
mmlu.prompt2_mqa_single_correct_sk:professional_accounting|0
|
|
mmlu.prompt3_mqa_single_correct_sk:professional_law|0
|
|
mmlu.prompt1_mqa_single_correct_sk:professional_law|0
|
|
mmlu.prompt2_mqa_single_correct_sk:professional_law|0
|
|
mmlu.prompt3_mqa_single_correct_sk:professional_medicine|0
|
|
mmlu.prompt1_mqa_single_correct_sk:professional_medicine|0
|
|
mmlu.prompt2_mqa_single_correct_sk:professional_medicine|0
|
|
mmlu.prompt3_mqa_single_correct_sk:professional_psychology|0
|
|
mmlu.prompt1_mqa_single_correct_sk:professional_psychology|0
|
|
mmlu.prompt2_mqa_single_correct_sk:professional_psychology|0
|
|
mmlu.prompt3_mqa_single_correct_sk:public_relations|0
|
|
mmlu.prompt1_mqa_single_correct_sk:public_relations|0
|
|
mmlu.prompt2_mqa_single_correct_sk:public_relations|0
|
|
mmlu.prompt3_mqa_single_correct_sk:security_studies|0
|
|
mmlu.prompt1_mqa_single_correct_sk:security_studies|0
|
|
mmlu.prompt2_mqa_single_correct_sk:security_studies|0
|
|
mmlu.prompt3_mqa_single_correct_sk:sociology|0
|
|
mmlu.prompt1_mqa_single_correct_sk:sociology|0
|
|
mmlu.prompt2_mqa_single_correct_sk:sociology|0
|
|
mmlu.prompt3_mqa_single_correct_sk:us_foreign_policy|0
|
|
mmlu.prompt1_mqa_single_correct_sk:us_foreign_policy|0
|
|
mmlu.prompt2_mqa_single_correct_sk:us_foreign_policy|0
|
|
mmlu.prompt3_mqa_single_correct_sk:virology|0
|
|
mmlu.prompt1_mqa_single_correct_sk:virology|0
|
|
mmlu.prompt2_mqa_single_correct_sk:virology|0
|
|
mmlu.prompt3_mqa_single_correct_sk:world_religions|0
|
|
mmlu.prompt1_mqa_single_correct_sk:world_religions|0
|
|
mmlu.prompt2_mqa_single_correct_sk:world_religions|0
|
|
multi_wiki_qa.prompt3_qa_sk|0
|
|
multi_wiki_qa.prompt2_qa_sk|0
|
|
multi_wiki_qa.prompt1_qa_sk|0
|
|
senti_sk.prompt2_sentiment_binary_sk|0
|
|
senti_sk.prompt3_sentiment_binary_sk|0
|
|
senti_sk.prompt1_sentiment_binary_sk|0
|
|
senti_sk.prompt3_sentiment_3_class_sk|0
|
|
senti_sk.prompt1_sentiment_3_class_sk|0
|
|
senti_sk.prompt2_sentiment_3_class_sk|0
|
|
skj1.prompt3_skj1_sk|0
|
|
skj1.prompt1_skj1_sk|0
|
|
skj1.prompt2_skj1_sk|0
|
|
sklep.prompt2_sentiment_binary_sk:sentiment-analysis|0
|
|
sklep.prompt3_sentiment_binary_sk:sentiment-analysis|0
|
|
sklep.prompt1_sentiment_binary_sk:sentiment-analysis|0
|
|
sklep.prompt1_hate_speech_sk:hate-speech|0
|
|
sklep.prompt3_hate_speech_sk:hate-speech|0
|
|
sklep.prompt2_hate_speech_sk:hate-speech|0
|
|
sklep.prompt1_nli_3_classes_sk:nli|0
|
|
sklep.prompt2_nli_3_classes_sk:nli|0
|
|
sklep.prompt3_nli_3_classes_sk:nli|0
|
|
sklep.prompt1_nli_binary_sk:rte|0
|
|
sklep.prompt3_nli_binary_sk:rte|0
|
|
sklep.prompt2_nli_binary_sk:rte|0
|
|
sklep.prompt3_qa_sk:question-answering|0
|
|
sklep.prompt2_qa_sk:question-answering|0
|
|
sklep.prompt1_qa_sk:question-answering|0
|
|
toxic_sk.prompt2_toxicity_sk|0
|
|
toxic_sk.prompt3_toxicity_sk|0
|
|
toxic_sk.prompt1_toxicity_sk|0
|
|
truthfulqa.prompt3_mqa_single_correct_sk:mc1|0
|
|
truthfulqa.prompt1_mqa_single_correct_sk:mc1|0
|
|
truthfulqa.prompt2_mqa_single_correct_sk:mc1|0
|
|
slovakcopa.prompt3_copa_sk|0
|
|
slovakcopa.prompt1_copa_sk|0
|
|
slovakcopa.prompt2_copa_sk|0
|
|
movie_review.prompt3_sentiment_binary_sk|0
|
|
movie_review.prompt2_sentiment_binary_sk|0
|
|
movie_review.prompt1_sentiment_binary_sk|0
|
|
globalmmlu-lite.prompt3_mqa_single_correct_sk|0
|
|
globalmmlu-lite.prompt1_mqa_single_correct_sk|0
|
|
globalmmlu-lite.prompt2_mqa_single_correct_sk|0
|