Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- eval/lm_eval_results.json +3 -0
- eval/lm_eval_results_table.txt +84 -0
.gitattributes
CHANGED
|
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
eval/lm_eval_results.json filter=lfs diff=lfs merge=lfs -text
|
eval/lm_eval_results.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:190af41c0aa8c03776e4f4967aef29479f13cbb9e5993c6a19e93733868f58a2
|
| 3 |
+
size 107144274
|
eval/lm_eval_results_table.txt
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|
| 2 |
+
|----------------------------------------|------:|------|-----:|--------|---|-----:|---|-----:|
|
| 3 |
+
|arc_challenge | 1|none | 0|acc |↑ |0.5256|± |0.0146|
|
| 4 |
+
| | |none | 0|acc_norm|↑ |0.5708|± |0.0145|
|
| 5 |
+
|arc_easy | 1|none | 0|acc |↑ |0.7971|± |0.0083|
|
| 6 |
+
| | |none | 0|acc_norm|↑ |0.7761|± |0.0086|
|
| 7 |
+
|boolq | 2|none | 0|acc |↑ |0.8899|± |0.0055|
|
| 8 |
+
|hellaswag | 1|none | 0|acc |↑ |0.6331|± |0.0048|
|
| 9 |
+
| | |none | 0|acc_norm|↑ |0.8204|± |0.0038|
|
| 10 |
+
|mmlu | 2|none | |acc |↑ |0.7573|± |0.0035|
|
| 11 |
+
|mmlu_humanities | 2|none | |acc |↑ |0.6837|± |0.0065|
|
| 12 |
+
|mmlu_formal_logic | 1|none | 0|acc |↑ |0.7063|± |0.0407|
|
| 13 |
+
|mmlu_high_school_european_history | 1|none | 0|acc |↑ |0.8061|± |0.0309|
|
| 14 |
+
|mmlu_high_school_us_history | 1|none | 0|acc |↑ |0.8333|± |0.0262|
|
| 15 |
+
|mmlu_high_school_world_history | 1|none | 0|acc |↑ |0.8397|± |0.0239|
|
| 16 |
+
|mmlu_international_law | 1|none | 0|acc |↑ |0.7934|± |0.0370|
|
| 17 |
+
|mmlu_jurisprudence | 1|none | 0|acc |↑ |0.8426|± |0.0352|
|
| 18 |
+
|mmlu_logical_fallacies | 1|none | 0|acc |↑ |0.8466|± |0.0283|
|
| 19 |
+
|mmlu_moral_disputes | 1|none | 0|acc |↑ |0.8150|± |0.0209|
|
| 20 |
+
|mmlu_moral_scenarios | 1|none | 0|acc |↑ |0.5676|± |0.0166|
|
| 21 |
+
|mmlu_philosophy | 1|none | 0|acc |↑ |0.8039|± |0.0226|
|
| 22 |
+
|mmlu_prehistory | 1|none | 0|acc |↑ |0.8302|± |0.0209|
|
| 23 |
+
|mmlu_professional_law | 1|none | 0|acc |↑ |0.5600|± |0.0127|
|
| 24 |
+
|mmlu_world_religions | 1|none | 0|acc |↑ |0.7778|± |0.0319|
|
| 25 |
+
|mmlu_other | 2|none | |acc |↑ |0.7815|± |0.0072|
|
| 26 |
+
|mmlu_business_ethics | 1|none | 0|acc |↑ |0.8300|± |0.0378|
|
| 27 |
+
|mmlu_clinical_knowledge | 1|none | 0|acc |↑ |0.7585|± |0.0263|
|
| 28 |
+
|mmlu_college_medicine | 1|none | 0|acc |↑ |0.6879|± |0.0353|
|
| 29 |
+
|mmlu_global_facts | 1|none | 0|acc |↑ |0.4900|± |0.0502|
|
| 30 |
+
|mmlu_human_aging | 1|none | 0|acc |↑ |0.7713|± |0.0282|
|
| 31 |
+
|mmlu_management | 1|none | 0|acc |↑ |0.8544|± |0.0349|
|
| 32 |
+
|mmlu_marketing | 1|none | 0|acc |↑ |0.9316|± |0.0165|
|
| 33 |
+
|mmlu_medical_genetics | 1|none | 0|acc |↑ |0.8000|± |0.0402|
|
| 34 |
+
|mmlu_miscellaneous | 1|none | 0|acc |↑ |0.8748|± |0.0118|
|
| 35 |
+
|mmlu_nutrition | 1|none | 0|acc |↑ |0.8007|± |0.0229|
|
| 36 |
+
|mmlu_professional_accounting | 1|none | 0|acc |↑ |0.6844|± |0.0277|
|
| 37 |
+
|mmlu_professional_medicine | 1|none | 0|acc |↑ |0.7316|± |0.0269|
|
| 38 |
+
|mmlu_virology | 1|none | 0|acc |↑ |0.5783|± |0.0384|
|
| 39 |
+
|mmlu_social_sciences | 2|none | |acc |↑ |0.8560|± |0.0063|
|
| 40 |
+
|mmlu_econometrics | 1|none | 0|acc |↑ |0.7105|± |0.0427|
|
| 41 |
+
|mmlu_high_school_geography | 1|none | 0|acc |↑ |0.8535|± |0.0252|
|
| 42 |
+
|mmlu_high_school_government_and_politics| 1|none | 0|acc |↑ |0.9275|± |0.0187|
|
| 43 |
+
|mmlu_high_school_macroeconomics | 1|none | 0|acc |↑ |0.8410|± |0.0185|
|
| 44 |
+
|mmlu_high_school_microeconomics | 1|none | 0|acc |↑ |0.9202|± |0.0176|
|
| 45 |
+
|mmlu_high_school_psychology | 1|none | 0|acc |↑ |0.8954|± |0.0131|
|
| 46 |
+
|mmlu_human_sexuality | 1|none | 0|acc |↑ |0.8779|± |0.0287|
|
| 47 |
+
|mmlu_professional_psychology | 1|none | 0|acc |↑ |0.8268|± |0.0153|
|
| 48 |
+
|mmlu_public_relations | 1|none | 0|acc |↑ |0.7818|± |0.0396|
|
| 49 |
+
|mmlu_security_studies | 1|none | 0|acc |↑ |0.8041|± |0.0254|
|
| 50 |
+
|mmlu_sociology | 1|none | 0|acc |↑ |0.9005|± |0.0212|
|
| 51 |
+
|mmlu_us_foreign_policy | 1|none | 0|acc |↑ |0.8500|± |0.0359|
|
| 52 |
+
|mmlu_stem | 2|none | |acc |↑ |0.7469|± |0.0074|
|
| 53 |
+
|mmlu_abstract_algebra | 1|none | 0|acc |↑ |0.6600|± |0.0476|
|
| 54 |
+
|mmlu_anatomy | 1|none | 0|acc |↑ |0.6593|± |0.0409|
|
| 55 |
+
|mmlu_astronomy | 1|none | 0|acc |↑ |0.9013|± |0.0243|
|
| 56 |
+
|mmlu_college_biology | 1|none | 0|acc |↑ |0.7778|± |0.0348|
|
| 57 |
+
|mmlu_college_chemistry | 1|none | 0|acc |↑ |0.4600|± |0.0501|
|
| 58 |
+
|mmlu_college_computer_science | 1|none | 0|acc |↑ |0.7900|± |0.0409|
|
| 59 |
+
|mmlu_college_mathematics | 1|none | 0|acc |↑ |0.5700|± |0.0498|
|
| 60 |
+
|mmlu_college_physics | 1|none | 0|acc |↑ |0.5392|± |0.0496|
|
| 61 |
+
|mmlu_computer_security | 1|none | 0|acc |↑ |0.9100|± |0.0288|
|
| 62 |
+
|mmlu_conceptual_physics | 1|none | 0|acc |↑ |0.8511|± |0.0233|
|
| 63 |
+
|mmlu_electrical_engineering | 1|none | 0|acc |↑ |0.7724|± |0.0349|
|
| 64 |
+
|mmlu_elementary_mathematics | 1|none | 0|acc |↑ |0.8624|± |0.0177|
|
| 65 |
+
|mmlu_high_school_biology | 1|none | 0|acc |↑ |0.8290|± |0.0214|
|
| 66 |
+
|mmlu_high_school_chemistry | 1|none | 0|acc |↑ |0.5862|± |0.0347|
|
| 67 |
+
|mmlu_high_school_computer_science | 1|none | 0|acc |↑ |0.9000|± |0.0302|
|
| 68 |
+
|mmlu_high_school_mathematics | 1|none | 0|acc |↑ |0.5444|± |0.0304|
|
| 69 |
+
|mmlu_high_school_physics | 1|none | 0|acc |↑ |0.7219|± |0.0366|
|
| 70 |
+
|mmlu_high_school_statistics | 1|none | 0|acc |↑ |0.8194|± |0.0262|
|
| 71 |
+
|mmlu_machine_learning | 1|none | 0|acc |↑ |0.7679|± |0.0401|
|
| 72 |
+
|openbookqa | 1|none | 0|acc |↑ |0.3000|± |0.0205|
|
| 73 |
+
| | |none | 0|acc_norm|↑ |0.4120|± |0.0220|
|
| 74 |
+
|rte | 1|none | 0|acc |↑ |0.7401|± |0.0264|
|
| 75 |
+
|winogrande | 1|none | 0|acc |↑ |0.7656|± |0.0119|
|
| 76 |
+
|
| 77 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
| 78 |
+
|--------------------|------:|------|------|------|---|-----:|---|-----:|
|
| 79 |
+
|mmlu | 2|none | |acc |↑ |0.7573|± |0.0035|
|
| 80 |
+
|mmlu_humanities | 2|none | |acc |↑ |0.6837|± |0.0065|
|
| 81 |
+
|mmlu_other | 2|none | |acc |↑ |0.7815|± |0.0072|
|
| 82 |
+
|mmlu_social_sciences| 2|none | |acc |↑ |0.8560|± |0.0063|
|
| 83 |
+
|mmlu_stem | 2|none | |acc |↑ |0.7469|± |0.0074|
|
| 84 |
+
|