wisent 0.7.379__py3-none-any.whl → 0.7.701__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (725) hide show
  1. wisent/__init__.py +1 -1
  2. wisent/core/activations/__init__.py +22 -6
  3. wisent/core/activations/activations.py +21 -39
  4. wisent/core/activations/activations_collector.py +141 -373
  5. wisent/core/activations/classifier_inference_strategy.py +194 -0
  6. wisent/core/activations/core/atoms.py +8 -92
  7. wisent/core/activations/extraction_strategy.py +308 -0
  8. wisent/core/agent/diagnose/response_diagnostics.py +3 -3
  9. wisent/core/agent/diagnose.py +3 -3
  10. wisent/core/autonomous_agent.py +2 -2
  11. wisent/core/cli/agent/apply_steering.py +23 -27
  12. wisent/core/cli/agent/evaluate_response.py +18 -20
  13. wisent/core/cli/agent/train_classifier.py +18 -20
  14. wisent/core/cli/cluster_benchmarks.py +472 -0
  15. wisent/core/cli/create_steering_vector.py +13 -5
  16. wisent/core/cli/generate_vector_from_task.py +4 -0
  17. wisent/core/cli/get_activations.py +12 -36
  18. wisent/core/cli/method_optimizer.py +859 -0
  19. wisent/core/cli/optimize.py +44 -5
  20. wisent/core/cli/optimize_classification.py +5 -6
  21. wisent/core/cli/optimize_sample_size.py +8 -22
  22. wisent/core/cli/optimize_steering.py +429 -153
  23. wisent/core/cli/optimize_weights.py +65 -6
  24. wisent/core/cli/steering_method_trainer.py +5 -4
  25. wisent/core/cli/steering_search_space.py +20 -15
  26. wisent/core/cli/tasks.py +14 -43
  27. wisent/core/cli/train_unified_goodness.py +17 -18
  28. wisent/core/contrastive_pairs/diagnostics/control_vectors.py +1578 -173
  29. wisent/core/contrastive_pairs/diagnostics/linearity.py +63 -80
  30. wisent/core/contrastive_pairs/diagnostics/vector_quality.py +6 -5
  31. wisent/core/contrastive_pairs/huggingface_pairs/hf_extractor_manifest.py +5 -19
  32. wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/__init__.py +11 -5
  33. wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/apps.py +146 -32
  34. wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/codexglue.py +2 -2
  35. wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/humaneval.py +98 -57
  36. wisent/core/contrastive_pairs/lm_eval_pairs/group_task_manifests/code_x_glue.py +8 -8
  37. wisent/core/contrastive_pairs/lm_eval_pairs/group_task_manifests/freebase.py +1 -1
  38. wisent/core/contrastive_pairs/lm_eval_pairs/lm_extractor_manifest.py +8 -5
  39. wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/agieval_aqua_rat.py +129 -0
  40. wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/code_x_glue.py +11 -6
  41. wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/gsm8k.py +1 -1
  42. wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/mbpp.py +47 -6
  43. wisent/core/evaluators/benchmark_specific/apps_evaluator.py +133 -0
  44. wisent/core/evaluators/benchmark_specific/coding/metrics/evaluator.py +6 -1
  45. wisent/core/evaluators/benchmark_specific/conala_evaluator.py +31 -168
  46. wisent/core/evaluators/custom/examples/humanization_coherent.py +89 -35
  47. wisent/core/evaluators/oracles/truthfulqa_gen_evaluator.py +2 -20
  48. wisent/core/evaluators/personalization/coherence.py +46 -0
  49. wisent/core/hyperparameter_optimizer.py +13 -13
  50. wisent/core/lm_eval_harness_ground_truth.py +7 -11
  51. wisent/core/main.py +3 -0
  52. wisent/core/models/wisent_model.py +8 -7
  53. wisent/core/opti/methods/opti_weights.py +29 -2
  54. wisent/core/optuna/classifier/activation_generator.py +14 -12
  55. wisent/core/optuna/steering/steering_optimization.py +14 -9
  56. wisent/core/parser_arguments/cluster_benchmarks_parser.py +31 -0
  57. wisent/core/parser_arguments/generate_vector_from_task_parser.py +20 -0
  58. wisent/core/parser_arguments/main_parser.py +8 -0
  59. wisent/core/parser_arguments/optimize_steering_parser.py +117 -10
  60. wisent/core/parser_arguments/optimize_weights_parser.py +6 -0
  61. wisent/core/parser_arguments/tasks_parser.py +7 -19
  62. wisent/core/steering_methods/core/atoms.py +1 -2
  63. wisent/core/steering_methods/methods/caa.py +1 -1
  64. wisent/core/steering_methods/methods/hyperplane.py +74 -0
  65. wisent/core/steering_methods/methods/prism.py +1 -2
  66. wisent/core/steering_methods/methods/pulse.py +39 -8
  67. wisent/core/steering_methods/methods/titan.py +59 -14
  68. wisent/core/steering_methods/registry.py +52 -12
  69. wisent/core/steering_optimizer.py +15 -15
  70. wisent/core/trainers/steering_trainer.py +9 -18
  71. wisent/parameters/lm_eval/track_progress_not_lm_eval_tasks.json +19 -70
  72. wisent/scripts/run_quality_metrics_sweep.sh +22 -27
  73. wisent/tests/test_aggregation_geometry.py +236 -0
  74. wisent/tests/test_detector_accuracy.py +163 -0
  75. wisent/tests/test_geometry_exhaustive.py +1202 -0
  76. wisent/tests/visualize_geometry.py +255 -61
  77. {wisent-0.7.379.dist-info → wisent-0.7.701.dist-info}/METADATA +1 -1
  78. {wisent-0.7.379.dist-info → wisent-0.7.701.dist-info}/RECORD +82 -714
  79. wisent/core/activations/prompt_construction_strategy.py +0 -47
  80. wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/codexglue_code_to_text.py +0 -15
  81. wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/codexglue_code_to_text_go.py +0 -64
  82. wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/codexglue_code_to_text_java.py +0 -65
  83. wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/codexglue_code_to_text_javascript.py +0 -65
  84. wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/codexglue_code_to_text_php.py +0 -65
  85. wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/codexglue_code_to_text_python.py +0 -65
  86. wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/codexglue_code_to_text_ruby.py +0 -65
  87. wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/freebase.py +0 -99
  88. wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/instruct_humaneval.py +0 -180
  89. wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/instructhumaneval.py +0 -129
  90. wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/mbpp.py +0 -142
  91. wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/agieval.py +0 -155
  92. wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/code2text.py +0 -161
  93. wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/codexglue.py +0 -107
  94. wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/livemathbench.py +0 -155
  95. wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/polymath.py +0 -155
  96. wisent/examples/scripts/results/benchmark_descriptions.json +0 -1244
  97. wisent/examples/scripts/results/benchmark_evaluation_methods.json +0 -66
  98. wisent/examples/scripts/results/benchmark_evaluator_mapping.json +0 -2781
  99. wisent/examples/scripts/results/benchmark_evaluator_mapping_updated.json +0 -30536
  100. wisent/examples/scripts/results/benchmark_evaluators_clean.json +0 -469
  101. wisent/examples/scripts/results/benchmark_methods_summary.json +0 -260
  102. wisent/examples/scripts/results/benchmark_pair_creation_methods.json +0 -66
  103. wisent/examples/scripts/results/benchmark_pair_totals.json +0 -269
  104. wisent/examples/scripts/results/benchmark_tags.json +0 -917
  105. wisent/examples/scripts/results/benchmark_test_summary_nov4.json +0 -71
  106. wisent/examples/scripts/results/coding_benchmarks_test_code_status.json +0 -150
  107. wisent/examples/scripts/results/failing_benchmarks.json +0 -946
  108. wisent/examples/scripts/results/failing_benchmarks_list.json +0 -41
  109. wisent/examples/scripts/results/failing_benchmarks_test_results.json +0 -945
  110. wisent/examples/scripts/results/missing_benchmark_tags.json +0 -341
  111. wisent/examples/scripts/results/test_20_newsgroups_evaluation.json +0 -30
  112. wisent/examples/scripts/results/test_20_newsgroups_pairs.json +0 -8
  113. wisent/examples/scripts/results/test_AraDICE_evaluation.json +0 -51
  114. wisent/examples/scripts/results/test_AraDICE_pairs.json +0 -14
  115. wisent/examples/scripts/results/test_AraDiCE_boolq_egy/test_AraDiCE_boolq_egy_evaluation.json +0 -30
  116. wisent/examples/scripts/results/test_AraDiCE_boolq_egy/test_AraDiCE_boolq_egy_pairs.json +0 -8
  117. wisent/examples/scripts/results/test_ArabCulture_evaluation.json +0 -51
  118. wisent/examples/scripts/results/test_ArabCulture_pairs.json +0 -14
  119. wisent/examples/scripts/results/test_Tag_evaluation.json +0 -30
  120. wisent/examples/scripts/results/test_Tag_pairs.json +0 -8
  121. wisent/examples/scripts/results/test_aclue_evaluation.json +0 -51
  122. wisent/examples/scripts/results/test_aclue_pairs.json +0 -14
  123. wisent/examples/scripts/results/test_acp_bench_evaluation.json +0 -51
  124. wisent/examples/scripts/results/test_acp_bench_hard_evaluation.json +0 -51
  125. wisent/examples/scripts/results/test_acp_bench_hard_pairs.json +0 -14
  126. wisent/examples/scripts/results/test_acp_bench_pairs.json +0 -14
  127. wisent/examples/scripts/results/test_advanced_ai_risk_evaluation.json +0 -51
  128. wisent/examples/scripts/results/test_advanced_ai_risk_pairs.json +0 -14
  129. wisent/examples/scripts/results/test_aexams_evaluation.json +0 -51
  130. wisent/examples/scripts/results/test_aexams_pairs.json +0 -14
  131. wisent/examples/scripts/results/test_afrimgsm_direct_amh_evaluation.json +0 -30
  132. wisent/examples/scripts/results/test_afrimgsm_direct_amh_pairs.json +0 -8
  133. wisent/examples/scripts/results/test_afrimmlu_direct_amh_evaluation.json +0 -30
  134. wisent/examples/scripts/results/test_afrimmlu_direct_amh_pairs.json +0 -8
  135. wisent/examples/scripts/results/test_afrixnli_en_direct_amh_evaluation.json +0 -30
  136. wisent/examples/scripts/results/test_afrixnli_en_direct_amh_pairs.json +0 -8
  137. wisent/examples/scripts/results/test_ag_news_evaluation.json +0 -30
  138. wisent/examples/scripts/results/test_ag_news_pairs.json +0 -8
  139. wisent/examples/scripts/results/test_agieval_evaluation.json +0 -51
  140. wisent/examples/scripts/results/test_agieval_pairs.json +0 -14
  141. wisent/examples/scripts/results/test_aime2024_evaluation.json +0 -30
  142. wisent/examples/scripts/results/test_aime2024_pairs.json +0 -8
  143. wisent/examples/scripts/results/test_aime2025_evaluation.json +0 -30
  144. wisent/examples/scripts/results/test_aime2025_pairs.json +0 -8
  145. wisent/examples/scripts/results/test_aime_evaluation.json +0 -30
  146. wisent/examples/scripts/results/test_aime_pairs.json +0 -8
  147. wisent/examples/scripts/results/test_anagrams1_evaluation.json +0 -30
  148. wisent/examples/scripts/results/test_anagrams1_pairs.json +0 -8
  149. wisent/examples/scripts/results/test_anagrams2_evaluation.json +0 -30
  150. wisent/examples/scripts/results/test_anagrams2_pairs.json +0 -8
  151. wisent/examples/scripts/results/test_anli_evaluation.json +0 -30
  152. wisent/examples/scripts/results/test_anli_pairs.json +0 -8
  153. wisent/examples/scripts/results/test_apps_evaluation.json +0 -30
  154. wisent/examples/scripts/results/test_apps_pairs.json +0 -8
  155. wisent/examples/scripts/results/test_arabic_exams_evaluation.json +0 -30
  156. wisent/examples/scripts/results/test_arabic_exams_pairs.json +0 -8
  157. wisent/examples/scripts/results/test_arabic_leaderboard_complete_evaluation.json +0 -51
  158. wisent/examples/scripts/results/test_arabic_leaderboard_complete_pairs.json +0 -14
  159. wisent/examples/scripts/results/test_arabic_leaderboard_light_evaluation.json +0 -51
  160. wisent/examples/scripts/results/test_arabic_leaderboard_light_pairs.json +0 -14
  161. wisent/examples/scripts/results/test_arabicmmlu_evaluation.json +0 -51
  162. wisent/examples/scripts/results/test_arabicmmlu_pairs.json +0 -14
  163. wisent/examples/scripts/results/test_aradice/test_aradice_evaluation.json +0 -51
  164. wisent/examples/scripts/results/test_aradice/test_aradice_pairs.json +0 -14
  165. wisent/examples/scripts/results/test_aradice3/test_aradice_evaluation.json +0 -51
  166. wisent/examples/scripts/results/test_aradice3/test_aradice_pairs.json +0 -14
  167. wisent/examples/scripts/results/test_arc_ar_evaluation.json +0 -30
  168. wisent/examples/scripts/results/test_arc_ar_pairs.json +0 -8
  169. wisent/examples/scripts/results/test_arc_challenge_evaluation.json +0 -30
  170. wisent/examples/scripts/results/test_arc_challenge_pairs.json +0 -8
  171. wisent/examples/scripts/results/test_arc_easy_evaluation.json +0 -30
  172. wisent/examples/scripts/results/test_arc_easy_pairs.json +0 -8
  173. wisent/examples/scripts/results/test_argument_topic_evaluation.json +0 -30
  174. wisent/examples/scripts/results/test_argument_topic_pairs.json +0 -8
  175. wisent/examples/scripts/results/test_arithmetic_evaluation.json +0 -51
  176. wisent/examples/scripts/results/test_arithmetic_pairs.json +0 -14
  177. wisent/examples/scripts/results/test_asdiv_evaluation.json +0 -30
  178. wisent/examples/scripts/results/test_asdiv_pairs.json +0 -8
  179. wisent/examples/scripts/results/test_assin_entailment_evaluation.json +0 -30
  180. wisent/examples/scripts/results/test_assin_entailment_pairs.json +0 -8
  181. wisent/examples/scripts/results/test_atis_evaluation.json +0 -30
  182. wisent/examples/scripts/results/test_atis_pairs.json +0 -8
  183. wisent/examples/scripts/results/test_babi_evaluation.json +0 -30
  184. wisent/examples/scripts/results/test_babi_pairs.json +0 -8
  185. wisent/examples/scripts/results/test_babilong_evaluation.json +0 -30
  186. wisent/examples/scripts/results/test_babilong_pairs.json +0 -8
  187. wisent/examples/scripts/results/test_bangla_mmlu_evaluation.json +0 -30
  188. wisent/examples/scripts/results/test_bangla_mmlu_pairs.json +0 -8
  189. wisent/examples/scripts/results/test_banking77_evaluation.json +0 -30
  190. wisent/examples/scripts/results/test_banking77_pairs.json +0 -8
  191. wisent/examples/scripts/results/test_basque/test_basque-glue_pairs.json +0 -14
  192. wisent/examples/scripts/results/test_basque-glue_evaluation.json +0 -51
  193. wisent/examples/scripts/results/test_basque-glue_pairs.json +0 -14
  194. wisent/examples/scripts/results/test_basque2/test_basque-glue_evaluation.json +0 -51
  195. wisent/examples/scripts/results/test_basque2/test_basque-glue_pairs.json +0 -14
  196. wisent/examples/scripts/results/test_basque_bench_evaluation.json +0 -51
  197. wisent/examples/scripts/results/test_basque_bench_pairs.json +0 -14
  198. wisent/examples/scripts/results/test_basque_glue/test_basque-glue_evaluation.json +0 -51
  199. wisent/examples/scripts/results/test_basque_glue/test_basque-glue_pairs.json +0 -14
  200. wisent/examples/scripts/results/test_basqueglue_evaluation.json +0 -51
  201. wisent/examples/scripts/results/test_basqueglue_pairs.json +0 -14
  202. wisent/examples/scripts/results/test_bbh_evaluation.json +0 -51
  203. wisent/examples/scripts/results/test_bbh_pairs.json +0 -14
  204. wisent/examples/scripts/results/test_bbq_evaluation.json +0 -30
  205. wisent/examples/scripts/results/test_bbq_pairs.json +0 -8
  206. wisent/examples/scripts/results/test_bec2016eu_evaluation.json +0 -51
  207. wisent/examples/scripts/results/test_bec2016eu_pairs.json +0 -14
  208. wisent/examples/scripts/results/test_belebele_evaluation.json +0 -51
  209. wisent/examples/scripts/results/test_belebele_pairs.json +0 -14
  210. wisent/examples/scripts/results/test_benchmarks_evaluation.json +0 -51
  211. wisent/examples/scripts/results/test_benchmarks_pairs.json +0 -14
  212. wisent/examples/scripts/results/test_bertaqa_evaluation.json +0 -51
  213. wisent/examples/scripts/results/test_bertaqa_pairs.json +0 -14
  214. wisent/examples/scripts/results/test_bhtc_v2_evaluation.json +0 -30
  215. wisent/examples/scripts/results/test_bhtc_v2_pairs.json +0 -8
  216. wisent/examples/scripts/results/test_bigbench_evaluation.json +0 -51
  217. wisent/examples/scripts/results/test_bigbench_pairs.json +0 -14
  218. wisent/examples/scripts/results/test_blimp_evaluation.json +0 -51
  219. wisent/examples/scripts/results/test_blimp_pairs.json +0 -14
  220. wisent/examples/scripts/results/test_boolq/test_boolq_evaluation.json +0 -30
  221. wisent/examples/scripts/results/test_boolq/test_boolq_pairs.json +0 -8
  222. wisent/examples/scripts/results/test_boolq-seq2seq_evaluation.json +0 -30
  223. wisent/examples/scripts/results/test_boolq-seq2seq_pairs.json +0 -8
  224. wisent/examples/scripts/results/test_boolq_evaluation.json +0 -30
  225. wisent/examples/scripts/results/test_boolq_pairs.json +0 -8
  226. wisent/examples/scripts/results/test_c4_evaluation.json +0 -30
  227. wisent/examples/scripts/results/test_c4_pairs.json +0 -8
  228. wisent/examples/scripts/results/test_cabreu_evaluation.json +0 -30
  229. wisent/examples/scripts/results/test_cabreu_pairs.json +0 -8
  230. wisent/examples/scripts/results/test_careqa_evaluation.json +0 -30
  231. wisent/examples/scripts/results/test_careqa_pairs.json +0 -8
  232. wisent/examples/scripts/results/test_catalan_bench_evaluation.json +0 -51
  233. wisent/examples/scripts/results/test_catalan_bench_pairs.json +0 -14
  234. wisent/examples/scripts/results/test_catalanqa_evaluation.json +0 -30
  235. wisent/examples/scripts/results/test_catalanqa_pairs.json +0 -8
  236. wisent/examples/scripts/results/test_catcola_evaluation.json +0 -30
  237. wisent/examples/scripts/results/test_catcola_pairs.json +0 -8
  238. wisent/examples/scripts/results/test_cb_evaluation.json +0 -30
  239. wisent/examples/scripts/results/test_cb_pairs.json +0 -8
  240. wisent/examples/scripts/results/test_ceval/test_ceval_evaluation.json +0 -51
  241. wisent/examples/scripts/results/test_ceval/test_ceval_pairs.json +0 -14
  242. wisent/examples/scripts/results/test_ceval_accountant/test_ceval-valid_accountant_evaluation.json +0 -30
  243. wisent/examples/scripts/results/test_ceval_accountant/test_ceval-valid_accountant_pairs.json +0 -8
  244. wisent/examples/scripts/results/test_ceval_evaluation.json +0 -51
  245. wisent/examples/scripts/results/test_ceval_pairs.json +0 -14
  246. wisent/examples/scripts/results/test_ceval_valid/test_ceval_valid_evaluation.json +0 -51
  247. wisent/examples/scripts/results/test_ceval_valid/test_ceval_valid_pairs.json +0 -14
  248. wisent/examples/scripts/results/test_chain_of_thought_evaluation.json +0 -51
  249. wisent/examples/scripts/results/test_chain_of_thought_pairs.json +0 -14
  250. wisent/examples/scripts/results/test_chartqa_evaluation.json +0 -30
  251. wisent/examples/scripts/results/test_chartqa_pairs.json +0 -8
  252. wisent/examples/scripts/results/test_claim_stance_topic_evaluation.json +0 -30
  253. wisent/examples/scripts/results/test_claim_stance_topic_pairs.json +0 -8
  254. wisent/examples/scripts/results/test_cmmlu_evaluation.json +0 -51
  255. wisent/examples/scripts/results/test_cmmlu_pairs.json +0 -14
  256. wisent/examples/scripts/results/test_cnn_dailymail_evaluation.json +0 -30
  257. wisent/examples/scripts/results/test_cnn_dailymail_pairs.json +0 -8
  258. wisent/examples/scripts/results/test_cocoteros_es_evaluation.json +0 -30
  259. wisent/examples/scripts/results/test_cocoteros_es_pairs.json +0 -8
  260. wisent/examples/scripts/results/test_codexglue_code_to_text_go_evaluation.json +0 -30
  261. wisent/examples/scripts/results/test_codexglue_code_to_text_go_pairs.json +0 -8
  262. wisent/examples/scripts/results/test_codexglue_code_to_text_java_evaluation.json +0 -30
  263. wisent/examples/scripts/results/test_codexglue_code_to_text_java_pairs.json +0 -8
  264. wisent/examples/scripts/results/test_codexglue_code_to_text_javascript_evaluation.json +0 -30
  265. wisent/examples/scripts/results/test_codexglue_code_to_text_javascript_pairs.json +0 -8
  266. wisent/examples/scripts/results/test_codexglue_code_to_text_php_evaluation.json +0 -30
  267. wisent/examples/scripts/results/test_codexglue_code_to_text_php_pairs.json +0 -8
  268. wisent/examples/scripts/results/test_codexglue_code_to_text_python_evaluation.json +0 -30
  269. wisent/examples/scripts/results/test_codexglue_code_to_text_python_pairs.json +0 -8
  270. wisent/examples/scripts/results/test_codexglue_code_to_text_ruby_evaluation.json +0 -30
  271. wisent/examples/scripts/results/test_codexglue_code_to_text_ruby_pairs.json +0 -8
  272. wisent/examples/scripts/results/test_coedit_gec_evaluation.json +0 -30
  273. wisent/examples/scripts/results/test_coedit_gec_pairs.json +0 -8
  274. wisent/examples/scripts/results/test_cola_evaluation.json +0 -30
  275. wisent/examples/scripts/results/test_cola_pairs.json +0 -8
  276. wisent/examples/scripts/results/test_commonsense_qa_evaluation.json +0 -30
  277. wisent/examples/scripts/results/test_commonsense_qa_pairs.json +0 -8
  278. wisent/examples/scripts/results/test_conala_evaluation.json +0 -30
  279. wisent/examples/scripts/results/test_conala_pairs.json +0 -8
  280. wisent/examples/scripts/results/test_concode_evaluation.json +0 -30
  281. wisent/examples/scripts/results/test_concode_pairs.json +0 -8
  282. wisent/examples/scripts/results/test_copa_evaluation.json +0 -30
  283. wisent/examples/scripts/results/test_copa_pairs.json +0 -8
  284. wisent/examples/scripts/results/test_copal_id_evaluation.json +0 -30
  285. wisent/examples/scripts/results/test_copal_id_pairs.json +0 -8
  286. wisent/examples/scripts/results/test_coqa_evaluation.json +0 -30
  287. wisent/examples/scripts/results/test_coqa_pairs.json +0 -8
  288. wisent/examples/scripts/results/test_coqcat_evaluation.json +0 -30
  289. wisent/examples/scripts/results/test_coqcat_pairs.json +0 -8
  290. wisent/examples/scripts/results/test_crows_pairs_evaluation.json +0 -51
  291. wisent/examples/scripts/results/test_crows_pairs_pairs.json +0 -14
  292. wisent/examples/scripts/results/test_csatqa_evaluation.json +0 -51
  293. wisent/examples/scripts/results/test_csatqa_pairs.json +0 -14
  294. wisent/examples/scripts/results/test_cycle_letters_evaluation.json +0 -30
  295. wisent/examples/scripts/results/test_cycle_letters_pairs.json +0 -8
  296. wisent/examples/scripts/results/test_darija_bench/test_darija_bench_evaluation.json +0 -51
  297. wisent/examples/scripts/results/test_darija_bench/test_darija_bench_pairs.json +0 -14
  298. wisent/examples/scripts/results/test_darija_bench_evaluation.json +0 -51
  299. wisent/examples/scripts/results/test_darija_bench_pairs.json +0 -14
  300. wisent/examples/scripts/results/test_darijahellaswag_evaluation.json +0 -30
  301. wisent/examples/scripts/results/test_darijahellaswag_pairs.json +0 -8
  302. wisent/examples/scripts/results/test_darijammlu_evaluation.json +0 -51
  303. wisent/examples/scripts/results/test_darijammlu_pairs.json +0 -14
  304. wisent/examples/scripts/results/test_dbpedia_14_evaluation.json +0 -30
  305. wisent/examples/scripts/results/test_dbpedia_14_pairs.json +0 -8
  306. wisent/examples/scripts/results/test_drop_evaluation.json +0 -30
  307. wisent/examples/scripts/results/test_drop_pairs.json +0 -8
  308. wisent/examples/scripts/results/test_ds1000_evaluation.json +0 -30
  309. wisent/examples/scripts/results/test_ds1000_pairs.json +0 -8
  310. wisent/examples/scripts/results/test_egyhellaswag_evaluation.json +0 -30
  311. wisent/examples/scripts/results/test_egyhellaswag_pairs.json +0 -8
  312. wisent/examples/scripts/results/test_egymmlu_evaluation.json +0 -51
  313. wisent/examples/scripts/results/test_egymmlu_pairs.json +0 -14
  314. wisent/examples/scripts/results/test_epec_koref_bin_evaluation.json +0 -30
  315. wisent/examples/scripts/results/test_epec_koref_bin_pairs.json +0 -8
  316. wisent/examples/scripts/results/test_eq_bench_evaluation.json +0 -30
  317. wisent/examples/scripts/results/test_eq_bench_pairs.json +0 -8
  318. wisent/examples/scripts/results/test_escola_evaluation.json +0 -30
  319. wisent/examples/scripts/results/test_escola_pairs.json +0 -8
  320. wisent/examples/scripts/results/test_ethics_cm_evaluation.json +0 -30
  321. wisent/examples/scripts/results/test_ethics_cm_pairs.json +0 -8
  322. wisent/examples/scripts/results/test_ethos_binary_evaluation.json +0 -30
  323. wisent/examples/scripts/results/test_ethos_binary_pairs.json +0 -8
  324. wisent/examples/scripts/results/test_eus_exams/test_eus_exams_evaluation.json +0 -51
  325. wisent/examples/scripts/results/test_eus_exams/test_eus_exams_pairs.json +0 -14
  326. wisent/examples/scripts/results/test_eus_exams_es_evaluation.json +0 -51
  327. wisent/examples/scripts/results/test_eus_exams_es_pairs.json +0 -14
  328. wisent/examples/scripts/results/test_eus_exams_evaluation.json +0 -51
  329. wisent/examples/scripts/results/test_eus_exams_pairs.json +0 -14
  330. wisent/examples/scripts/results/test_eus_proficiency_evaluation.json +0 -30
  331. wisent/examples/scripts/results/test_eus_proficiency_pairs.json +0 -8
  332. wisent/examples/scripts/results/test_eus_reading_evaluation.json +0 -30
  333. wisent/examples/scripts/results/test_eus_reading_pairs.json +0 -8
  334. wisent/examples/scripts/results/test_eus_trivia_evaluation.json +0 -30
  335. wisent/examples/scripts/results/test_eus_trivia_pairs.json +0 -8
  336. wisent/examples/scripts/results/test_evalita-mp_evaluation.json +0 -51
  337. wisent/examples/scripts/results/test_evalita-mp_pairs.json +0 -14
  338. wisent/examples/scripts/results/test_evalita-sp_sum_task_fp-small_p1_evaluation.json +0 -30
  339. wisent/examples/scripts/results/test_evalita-sp_sum_task_fp-small_p1_pairs.json +0 -8
  340. wisent/examples/scripts/results/test_evalita_LLM_evaluation.json +0 -51
  341. wisent/examples/scripts/results/test_evalita_LLM_pairs.json +0 -14
  342. wisent/examples/scripts/results/test_evalita_llm/test_evalita_llm_evaluation.json +0 -51
  343. wisent/examples/scripts/results/test_evalita_llm/test_evalita_llm_pairs.json +0 -14
  344. wisent/examples/scripts/results/test_evalita_mp/test_evalita-mp_te_prompt-1_evaluation.json +0 -30
  345. wisent/examples/scripts/results/test_evalita_mp/test_evalita-mp_te_prompt-1_pairs.json +0 -8
  346. wisent/examples/scripts/results/test_evalita_mp2/test_evalita_mp_evaluation.json +0 -51
  347. wisent/examples/scripts/results/test_evalita_mp2/test_evalita_mp_pairs.json +0 -14
  348. wisent/examples/scripts/results/test_evalita_sp2/test_evalita-sp_sum_task_fp-small_p1_evaluation.json +0 -30
  349. wisent/examples/scripts/results/test_evalita_sp2/test_evalita-sp_sum_task_fp-small_p1_pairs.json +0 -8
  350. wisent/examples/scripts/results/test_fda_evaluation.json +0 -30
  351. wisent/examples/scripts/results/test_fda_pairs.json +0 -8
  352. wisent/examples/scripts/results/test_financial_tweets_evaluation.json +0 -30
  353. wisent/examples/scripts/results/test_financial_tweets_pairs.json +0 -8
  354. wisent/examples/scripts/results/test_fld/test_fld_evaluation.json +0 -30
  355. wisent/examples/scripts/results/test_fld/test_fld_pairs.json +0 -8
  356. wisent/examples/scripts/results/test_fld_evaluation.json +0 -30
  357. wisent/examples/scripts/results/test_fld_fixed/test_fld_evaluation.json +0 -30
  358. wisent/examples/scripts/results/test_fld_fixed/test_fld_pairs.json +0 -8
  359. wisent/examples/scripts/results/test_fld_pairs.json +0 -8
  360. wisent/examples/scripts/results/test_flores_evaluation.json +0 -51
  361. wisent/examples/scripts/results/test_flores_pairs.json +0 -14
  362. wisent/examples/scripts/results/test_freebase_evaluation.json +0 -30
  363. wisent/examples/scripts/results/test_freebase_pairs.json +0 -8
  364. wisent/examples/scripts/results/test_french_bench_evaluation.json +0 -51
  365. wisent/examples/scripts/results/test_french_bench_pairs.json +0 -14
  366. wisent/examples/scripts/results/test_galcola_evaluation.json +0 -30
  367. wisent/examples/scripts/results/test_galcola_pairs.json +0 -8
  368. wisent/examples/scripts/results/test_galician_bench_evaluation.json +0 -51
  369. wisent/examples/scripts/results/test_galician_bench_pairs.json +0 -14
  370. wisent/examples/scripts/results/test_glianorex_evaluation.json +0 -30
  371. wisent/examples/scripts/results/test_glianorex_pairs.json +0 -8
  372. wisent/examples/scripts/results/test_global_mmlu_evaluation.json +0 -51
  373. wisent/examples/scripts/results/test_global_mmlu_pairs.json +0 -14
  374. wisent/examples/scripts/results/test_glue_evaluation.json +0 -51
  375. wisent/examples/scripts/results/test_glue_pairs.json +0 -14
  376. wisent/examples/scripts/results/test_gpqa_evaluation.json +0 -51
  377. wisent/examples/scripts/results/test_gpqa_pairs.json +0 -14
  378. wisent/examples/scripts/results/test_gpt3_translation_benchmarks_evaluation.json +0 -51
  379. wisent/examples/scripts/results/test_gpt3_translation_benchmarks_pairs.json +0 -14
  380. wisent/examples/scripts/results/test_groundcocoa_evaluation.json +0 -30
  381. wisent/examples/scripts/results/test_groundcocoa_pairs.json +0 -8
  382. wisent/examples/scripts/results/test_gsm8k_evaluation.json +0 -30
  383. wisent/examples/scripts/results/test_gsm8k_pairs.json +0 -8
  384. wisent/examples/scripts/results/test_haerae_evaluation.json +0 -51
  385. wisent/examples/scripts/results/test_haerae_pairs.json +0 -14
  386. wisent/examples/scripts/results/test_headqa_evaluation.json +0 -30
  387. wisent/examples/scripts/results/test_headqa_pairs.json +0 -8
  388. wisent/examples/scripts/results/test_hellaswag_evaluation.json +0 -30
  389. wisent/examples/scripts/results/test_hellaswag_pairs.json +0 -8
  390. wisent/examples/scripts/results/test_hendrycks_ethics_evaluation.json +0 -51
  391. wisent/examples/scripts/results/test_hendrycks_ethics_pairs.json +0 -14
  392. wisent/examples/scripts/results/test_hendrycks_math_evaluation.json +0 -51
  393. wisent/examples/scripts/results/test_hendrycks_math_pairs.json +0 -14
  394. wisent/examples/scripts/results/test_histoires_morales_evaluation.json +0 -30
  395. wisent/examples/scripts/results/test_histoires_morales_pairs.json +0 -8
  396. wisent/examples/scripts/results/test_hmmt_evaluation.json +0 -30
  397. wisent/examples/scripts/results/test_hmmt_feb_2025_evaluation.json +0 -30
  398. wisent/examples/scripts/results/test_hmmt_feb_2025_pairs.json +0 -8
  399. wisent/examples/scripts/results/test_hmmt_pairs.json +0 -8
  400. wisent/examples/scripts/results/test_hrm8k_evaluation.json +0 -51
  401. wisent/examples/scripts/results/test_hrm8k_pairs.json +0 -14
  402. wisent/examples/scripts/results/test_humaneval_evaluation.json +0 -30
  403. wisent/examples/scripts/results/test_humaneval_pairs.json +0 -8
  404. wisent/examples/scripts/results/test_humaneval_plus_evaluation.json +0 -30
  405. wisent/examples/scripts/results/test_humaneval_plus_pairs.json +0 -8
  406. wisent/examples/scripts/results/test_ifeval_evaluation.json +0 -30
  407. wisent/examples/scripts/results/test_ifeval_pairs.json +0 -8
  408. wisent/examples/scripts/results/test_instruct_humaneval/test_instruct_humaneval_evaluation.json +0 -30
  409. wisent/examples/scripts/results/test_instruct_humaneval/test_instruct_humaneval_pairs.json +0 -8
  410. wisent/examples/scripts/results/test_instruct_humaneval_evaluation.json +0 -30
  411. wisent/examples/scripts/results/test_instruct_humaneval_pairs.json +0 -8
  412. wisent/examples/scripts/results/test_inverse_scaling_evaluation.json +0 -51
  413. wisent/examples/scripts/results/test_inverse_scaling_hindsight_neglect_10shot_evaluation.json +0 -30
  414. wisent/examples/scripts/results/test_inverse_scaling_hindsight_neglect_10shot_pairs.json +0 -8
  415. wisent/examples/scripts/results/test_inverse_scaling_mc/test_inverse_scaling_mc_evaluation.json +0 -51
  416. wisent/examples/scripts/results/test_inverse_scaling_mc/test_inverse_scaling_mc_pairs.json +0 -14
  417. wisent/examples/scripts/results/test_inverse_scaling_pairs.json +0 -14
  418. wisent/examples/scripts/results/test_iwslt2017-ar-en_evaluation.json +0 -30
  419. wisent/examples/scripts/results/test_iwslt2017-ar-en_pairs.json +0 -8
  420. wisent/examples/scripts/results/test_iwslt2017-en-ar_evaluation.json +0 -30
  421. wisent/examples/scripts/results/test_iwslt2017-en-ar_pairs.json +0 -8
  422. wisent/examples/scripts/results/test_iwslt2017_ar_en/test_iwslt2017-ar-en_evaluation.json +0 -30
  423. wisent/examples/scripts/results/test_iwslt2017_ar_en/test_iwslt2017-ar-en_pairs.json +0 -8
  424. wisent/examples/scripts/results/test_iwslt2017_en_ar/test_iwslt2017-en-ar_evaluation.json +0 -30
  425. wisent/examples/scripts/results/test_iwslt2017_en_ar/test_iwslt2017-en-ar_pairs.json +0 -8
  426. wisent/examples/scripts/results/test_iwslt2017_group/test_iwslt2017_evaluation.json +0 -30
  427. wisent/examples/scripts/results/test_iwslt2017_group/test_iwslt2017_pairs.json +0 -8
  428. wisent/examples/scripts/results/test_japanese_leaderboard_evaluation.json +0 -51
  429. wisent/examples/scripts/results/test_japanese_leaderboard_pairs.json +0 -14
  430. wisent/examples/scripts/results/test_jsonschema_bench/test_jsonschema_bench_evaluation.json +0 -30
  431. wisent/examples/scripts/results/test_jsonschema_bench/test_jsonschema_bench_pairs.json +0 -8
  432. wisent/examples/scripts/results/test_jsonschema_bench_evaluation.json +0 -30
  433. wisent/examples/scripts/results/test_jsonschema_bench_final/test_jsonschema_bench_evaluation.json +0 -30
  434. wisent/examples/scripts/results/test_jsonschema_bench_final/test_jsonschema_bench_pairs.json +0 -8
  435. wisent/examples/scripts/results/test_jsonschema_bench_pairs.json +0 -8
  436. wisent/examples/scripts/results/test_kbl_evaluation.json +0 -51
  437. wisent/examples/scripts/results/test_kbl_fixed/test_kbl_evaluation.json +0 -51
  438. wisent/examples/scripts/results/test_kbl_fixed/test_kbl_pairs.json +0 -14
  439. wisent/examples/scripts/results/test_kbl_pairs.json +0 -14
  440. wisent/examples/scripts/results/test_kmmlu_evaluation.json +0 -51
  441. wisent/examples/scripts/results/test_kmmlu_pairs.json +0 -14
  442. wisent/examples/scripts/results/test_kobest_evaluation.json +0 -51
  443. wisent/examples/scripts/results/test_kobest_pairs.json +0 -14
  444. wisent/examples/scripts/results/test_kormedmcqa/test_kormedmcqa_evaluation.json +0 -30
  445. wisent/examples/scripts/results/test_kormedmcqa/test_kormedmcqa_pairs.json +0 -8
  446. wisent/examples/scripts/results/test_kormedmcqa_dentist/test_kormedmcqa_dentist_evaluation.json +0 -30
  447. wisent/examples/scripts/results/test_kormedmcqa_dentist/test_kormedmcqa_dentist_pairs.json +0 -8
  448. wisent/examples/scripts/results/test_kormedmcqa_evaluation.json +0 -30
  449. wisent/examples/scripts/results/test_kormedmcqa_pairs.json +0 -8
  450. wisent/examples/scripts/results/test_lambada_cloze_evaluation.json +0 -30
  451. wisent/examples/scripts/results/test_lambada_cloze_pairs.json +0 -8
  452. wisent/examples/scripts/results/test_lambada_evaluation.json +0 -30
  453. wisent/examples/scripts/results/test_lambada_final/test_lambada_openai_mt_stablelm_en_evaluation.json +0 -30
  454. wisent/examples/scripts/results/test_lambada_final/test_lambada_openai_mt_stablelm_en_pairs.json +0 -8
  455. wisent/examples/scripts/results/test_lambada_multilingual/test_lambada_multilingual_evaluation.json +0 -51
  456. wisent/examples/scripts/results/test_lambada_multilingual/test_lambada_multilingual_pairs.json +0 -14
  457. wisent/examples/scripts/results/test_lambada_multilingual_evaluation.json +0 -51
  458. wisent/examples/scripts/results/test_lambada_multilingual_pairs.json +0 -14
  459. wisent/examples/scripts/results/test_lambada_multilingual_stablelm_evaluation.json +0 -51
  460. wisent/examples/scripts/results/test_lambada_multilingual_stablelm_pairs.json +0 -14
  461. wisent/examples/scripts/results/test_lambada_openai_evaluation.json +0 -30
  462. wisent/examples/scripts/results/test_lambada_openai_pairs.json +0 -8
  463. wisent/examples/scripts/results/test_lambada_pairs.json +0 -8
  464. wisent/examples/scripts/results/test_lambada_stablelm_en_fixed/test_lambada_openai_mt_stablelm_en_evaluation.json +0 -30
  465. wisent/examples/scripts/results/test_lambada_stablelm_en_fixed/test_lambada_openai_mt_stablelm_en_pairs.json +0 -8
  466. wisent/examples/scripts/results/test_lambada_stablelm_fixed/test_lambada_openai_mt_stablelm_en_evaluation.json +0 -30
  467. wisent/examples/scripts/results/test_lambada_stablelm_fixed/test_lambada_openai_mt_stablelm_en_pairs.json +0 -8
  468. wisent/examples/scripts/results/test_lambada_standard_evaluation.json +0 -30
  469. wisent/examples/scripts/results/test_lambada_standard_pairs.json +0 -8
  470. wisent/examples/scripts/results/test_leaderboard_evaluation.json +0 -51
  471. wisent/examples/scripts/results/test_leaderboard_pairs.json +0 -14
  472. wisent/examples/scripts/results/test_libra/test_libra_evaluation.json +0 -51
  473. wisent/examples/scripts/results/test_libra/test_libra_pairs.json +0 -14
  474. wisent/examples/scripts/results/test_libra_evaluation.json +0 -51
  475. wisent/examples/scripts/results/test_libra_pairs.json +0 -14
  476. wisent/examples/scripts/results/test_lingoly_evaluation.json +0 -30
  477. wisent/examples/scripts/results/test_lingoly_pairs.json +0 -8
  478. wisent/examples/scripts/results/test_livecodebench_evaluation.json +0 -30
  479. wisent/examples/scripts/results/test_livecodebench_pairs.json +0 -8
  480. wisent/examples/scripts/results/test_livemathbench_cnmo_en_evaluation.json +0 -30
  481. wisent/examples/scripts/results/test_livemathbench_cnmo_en_pairs.json +0 -8
  482. wisent/examples/scripts/results/test_livemathbench_cnmo_zh_evaluation.json +0 -30
  483. wisent/examples/scripts/results/test_livemathbench_cnmo_zh_pairs.json +0 -8
  484. wisent/examples/scripts/results/test_llama_evaluation.json +0 -30
  485. wisent/examples/scripts/results/test_llama_pairs.json +0 -8
  486. wisent/examples/scripts/results/test_logiqa2_evaluation.json +0 -30
  487. wisent/examples/scripts/results/test_logiqa2_pairs.json +0 -8
  488. wisent/examples/scripts/results/test_logiqa_evaluation.json +0 -30
  489. wisent/examples/scripts/results/test_logiqa_pairs.json +0 -8
  490. wisent/examples/scripts/results/test_m_mmlu_evaluation.json +0 -51
  491. wisent/examples/scripts/results/test_m_mmlu_pairs.json +0 -14
  492. wisent/examples/scripts/results/test_mastermind/test_mastermind_evaluation.json +0 -51
  493. wisent/examples/scripts/results/test_mastermind/test_mastermind_pairs.json +0 -14
  494. wisent/examples/scripts/results/test_mastermind_24_easy/test_mastermind_24_easy_evaluation.json +0 -30
  495. wisent/examples/scripts/results/test_mastermind_24_easy/test_mastermind_24_easy_pairs.json +0 -8
  496. wisent/examples/scripts/results/test_mastermind_evaluation.json +0 -51
  497. wisent/examples/scripts/results/test_mastermind_pairs.json +0 -14
  498. wisent/examples/scripts/results/test_math500_evaluation.json +0 -30
  499. wisent/examples/scripts/results/test_math500_pairs.json +0 -8
  500. wisent/examples/scripts/results/test_math_evaluation.json +0 -30
  501. wisent/examples/scripts/results/test_math_pairs.json +0 -8
  502. wisent/examples/scripts/results/test_mathqa_evaluation.json +0 -30
  503. wisent/examples/scripts/results/test_mathqa_pairs.json +0 -8
  504. wisent/examples/scripts/results/test_mbpp_evaluation.json +0 -30
  505. wisent/examples/scripts/results/test_mbpp_pairs.json +0 -8
  506. wisent/examples/scripts/results/test_mbpp_plus_evaluation.json +0 -30
  507. wisent/examples/scripts/results/test_mbpp_plus_pairs.json +0 -8
  508. wisent/examples/scripts/results/test_mc_taco_evaluation.json +0 -30
  509. wisent/examples/scripts/results/test_mc_taco_pairs.json +0 -8
  510. wisent/examples/scripts/results/test_med_concepts_qa/test_med_concepts_qa_evaluation.json +0 -51
  511. wisent/examples/scripts/results/test_med_concepts_qa/test_med_concepts_qa_pairs.json +0 -14
  512. wisent/examples/scripts/results/test_med_concepts_qa_atc_easy/test_med_concepts_qa_atc_easy_evaluation.json +0 -30
  513. wisent/examples/scripts/results/test_med_concepts_qa_atc_easy/test_med_concepts_qa_atc_easy_pairs.json +0 -8
  514. wisent/examples/scripts/results/test_med_concepts_qa_evaluation.json +0 -51
  515. wisent/examples/scripts/results/test_med_concepts_qa_pairs.json +0 -14
  516. wisent/examples/scripts/results/test_meddialog_evaluation.json +0 -30
  517. wisent/examples/scripts/results/test_meddialog_pairs.json +0 -8
  518. wisent/examples/scripts/results/test_meddialog_raw_perplexity/test_meddialog_raw_perplexity_evaluation.json +0 -30
  519. wisent/examples/scripts/results/test_meddialog_raw_perplexity/test_meddialog_raw_perplexity_pairs.json +0 -8
  520. wisent/examples/scripts/results/test_mediqa_qa2019_evaluation.json +0 -30
  521. wisent/examples/scripts/results/test_mediqa_qa2019_pairs.json +0 -8
  522. wisent/examples/scripts/results/test_medmcqa_evaluation.json +0 -30
  523. wisent/examples/scripts/results/test_medmcqa_pairs.json +0 -8
  524. wisent/examples/scripts/results/test_medqa_evaluation.json +0 -30
  525. wisent/examples/scripts/results/test_medqa_pairs.json +0 -8
  526. wisent/examples/scripts/results/test_medtext_evaluation.json +0 -30
  527. wisent/examples/scripts/results/test_medtext_pairs.json +0 -8
  528. wisent/examples/scripts/results/test_mela_evaluation.json +0 -51
  529. wisent/examples/scripts/results/test_mela_pairs.json +0 -14
  530. wisent/examples/scripts/results/test_meqsum_evaluation.json +0 -30
  531. wisent/examples/scripts/results/test_meqsum_pairs.json +0 -8
  532. wisent/examples/scripts/results/test_mercury_evaluation.json +0 -30
  533. wisent/examples/scripts/results/test_mercury_pairs.json +0 -8
  534. wisent/examples/scripts/results/test_metabench_evaluation.json +0 -51
  535. wisent/examples/scripts/results/test_metabench_pairs.json +0 -14
  536. wisent/examples/scripts/results/test_mgsm_evaluation.json +0 -51
  537. wisent/examples/scripts/results/test_mgsm_pairs.json +0 -14
  538. wisent/examples/scripts/results/test_mimic_repsum_evaluation.json +0 -30
  539. wisent/examples/scripts/results/test_mimic_repsum_pairs.json +0 -8
  540. wisent/examples/scripts/results/test_minerva_math_evaluation.json +0 -51
  541. wisent/examples/scripts/results/test_minerva_math_pairs.json +0 -14
  542. wisent/examples/scripts/results/test_mlqa_evaluation.json +0 -51
  543. wisent/examples/scripts/results/test_mlqa_pairs.json +0 -14
  544. wisent/examples/scripts/results/test_mmlu-pro-plus_evaluation.json +0 -51
  545. wisent/examples/scripts/results/test_mmlu-pro-plus_pairs.json +0 -14
  546. wisent/examples/scripts/results/test_mmlu_evaluation.json +0 -51
  547. wisent/examples/scripts/results/test_mmlu_pairs.json +0 -14
  548. wisent/examples/scripts/results/test_mmlu_pro_evaluation.json +0 -51
  549. wisent/examples/scripts/results/test_mmlu_pro_pairs.json +0 -14
  550. wisent/examples/scripts/results/test_mmlu_prox_evaluation.json +0 -51
  551. wisent/examples/scripts/results/test_mmlu_prox_pairs.json +0 -14
  552. wisent/examples/scripts/results/test_mmlusr_evaluation.json +0 -30
  553. wisent/examples/scripts/results/test_mmlusr_pairs.json +0 -8
  554. wisent/examples/scripts/results/test_mmmu_evaluation.json +0 -51
  555. wisent/examples/scripts/results/test_mmmu_pairs.json +0 -14
  556. wisent/examples/scripts/results/test_mnli_evaluation.json +0 -30
  557. wisent/examples/scripts/results/test_mnli_pairs.json +0 -8
  558. wisent/examples/scripts/results/test_model_written_evals_evaluation.json +0 -51
  559. wisent/examples/scripts/results/test_model_written_evals_pairs.json +0 -14
  560. wisent/examples/scripts/results/test_moral_stories_evaluation.json +0 -30
  561. wisent/examples/scripts/results/test_moral_stories_pairs.json +0 -8
  562. wisent/examples/scripts/results/test_mts_dialog_evaluation.json +0 -30
  563. wisent/examples/scripts/results/test_mts_dialog_pairs.json +0 -8
  564. wisent/examples/scripts/results/test_multiblimp_evaluation.json +0 -51
  565. wisent/examples/scripts/results/test_multiblimp_pairs.json +0 -14
  566. wisent/examples/scripts/results/test_multimedqa_evaluation.json +0 -51
  567. wisent/examples/scripts/results/test_multimedqa_pairs.json +0 -14
  568. wisent/examples/scripts/results/test_multipl_e_evaluation.json +0 -30
  569. wisent/examples/scripts/results/test_multipl_e_pairs.json +0 -8
  570. wisent/examples/scripts/results/test_mutual_evaluation.json +0 -30
  571. wisent/examples/scripts/results/test_mutual_pairs.json +0 -8
  572. wisent/examples/scripts/results/test_non_greedy_robustness_agieval_aqua_rat_evaluation.json +0 -30
  573. wisent/examples/scripts/results/test_non_greedy_robustness_agieval_aqua_rat_pairs.json +0 -8
  574. wisent/examples/scripts/results/test_noreval_evaluation.json +0 -51
  575. wisent/examples/scripts/results/test_noreval_pairs.json +0 -14
  576. wisent/examples/scripts/results/test_noticia_evaluation.json +0 -30
  577. wisent/examples/scripts/results/test_noticia_pairs.json +0 -8
  578. wisent/examples/scripts/results/test_nq_open_evaluation.json +0 -30
  579. wisent/examples/scripts/results/test_nq_open_pairs.json +0 -8
  580. wisent/examples/scripts/results/test_olaph_evaluation.json +0 -30
  581. wisent/examples/scripts/results/test_olaph_pairs.json +0 -8
  582. wisent/examples/scripts/results/test_openbookqa_evaluation.json +0 -30
  583. wisent/examples/scripts/results/test_openbookqa_pairs.json +0 -8
  584. wisent/examples/scripts/results/test_openllm_evaluation.json +0 -51
  585. wisent/examples/scripts/results/test_openllm_pairs.json +0 -14
  586. wisent/examples/scripts/results/test_option_order_robustness_agieval_aqua_rat_evaluation.json +0 -30
  587. wisent/examples/scripts/results/test_option_order_robustness_agieval_aqua_rat_pairs.json +0 -8
  588. wisent/examples/scripts/results/test_paloma_evaluation.json +0 -51
  589. wisent/examples/scripts/results/test_paloma_pairs.json +0 -14
  590. wisent/examples/scripts/results/test_passkey/test_passkey_evaluation.json +0 -30
  591. wisent/examples/scripts/results/test_passkey/test_passkey_pairs.json +0 -8
  592. wisent/examples/scripts/results/test_paws-x_evaluation.json +0 -51
  593. wisent/examples/scripts/results/test_paws-x_pairs.json +0 -14
  594. wisent/examples/scripts/results/test_paws_en/test_paws_en_evaluation.json +0 -30
  595. wisent/examples/scripts/results/test_paws_en/test_paws_en_pairs.json +0 -8
  596. wisent/examples/scripts/results/test_penn_treebank_evaluation.json +0 -30
  597. wisent/examples/scripts/results/test_penn_treebank_pairs.json +0 -8
  598. wisent/examples/scripts/results/test_pile_10k/test_pile_10k_evaluation.json +0 -30
  599. wisent/examples/scripts/results/test_pile_10k/test_pile_10k_pairs.json +0 -8
  600. wisent/examples/scripts/results/test_piqa_evaluation.json +0 -30
  601. wisent/examples/scripts/results/test_piqa_pairs.json +0 -8
  602. wisent/examples/scripts/results/test_polemo2_evaluation.json +0 -30
  603. wisent/examples/scripts/results/test_polemo2_pairs.json +0 -8
  604. wisent/examples/scripts/results/test_polymath_en_high_evaluation.json +0 -30
  605. wisent/examples/scripts/results/test_polymath_en_high_pairs.json +0 -8
  606. wisent/examples/scripts/results/test_polymath_en_medium_evaluation.json +0 -30
  607. wisent/examples/scripts/results/test_polymath_en_medium_pairs.json +0 -8
  608. wisent/examples/scripts/results/test_polymath_zh_high_evaluation.json +0 -30
  609. wisent/examples/scripts/results/test_polymath_zh_high_pairs.json +0 -8
  610. wisent/examples/scripts/results/test_polymath_zh_medium_evaluation.json +0 -30
  611. wisent/examples/scripts/results/test_polymath_zh_medium_pairs.json +0 -8
  612. wisent/examples/scripts/results/test_portuguese_bench_evaluation.json +0 -51
  613. wisent/examples/scripts/results/test_portuguese_bench_pairs.json +0 -14
  614. wisent/examples/scripts/results/test_prompt_robustness_agieval_aqua_rat/test_prompt_robustness_agieval_aqua_rat_evaluation.json +0 -30
  615. wisent/examples/scripts/results/test_prompt_robustness_agieval_aqua_rat/test_prompt_robustness_agieval_aqua_rat_pairs.json +0 -8
  616. wisent/examples/scripts/results/test_prompt_robustness_agieval_aqua_rat_evaluation.json +0 -30
  617. wisent/examples/scripts/results/test_prompt_robustness_agieval_aqua_rat_pairs.json +0 -8
  618. wisent/examples/scripts/results/test_prost_evaluation.json +0 -30
  619. wisent/examples/scripts/results/test_prost_pairs.json +0 -8
  620. wisent/examples/scripts/results/test_ptb_evaluation.json +0 -30
  621. wisent/examples/scripts/results/test_ptb_pairs.json +0 -8
  622. wisent/examples/scripts/results/test_pubmedqa_evaluation.json +0 -30
  623. wisent/examples/scripts/results/test_pubmedqa_pairs.json +0 -8
  624. wisent/examples/scripts/results/test_pythia_evaluation.json +0 -51
  625. wisent/examples/scripts/results/test_pythia_pairs.json +0 -14
  626. wisent/examples/scripts/results/test_qa4mre_evaluation.json +0 -30
  627. wisent/examples/scripts/results/test_qa4mre_pairs.json +0 -8
  628. wisent/examples/scripts/results/test_qasper_evaluation.json +0 -30
  629. wisent/examples/scripts/results/test_qasper_pairs.json +0 -8
  630. wisent/examples/scripts/results/test_race_evaluation.json +0 -30
  631. wisent/examples/scripts/results/test_race_pairs.json +0 -8
  632. wisent/examples/scripts/results/test_realtoxicityprompts_evaluation.json +0 -30
  633. wisent/examples/scripts/results/test_realtoxicityprompts_pairs.json +0 -8
  634. wisent/examples/scripts/results/test_recode_evaluation.json +0 -30
  635. wisent/examples/scripts/results/test_recode_pairs.json +0 -8
  636. wisent/examples/scripts/results/test_record_evaluation.json +0 -30
  637. wisent/examples/scripts/results/test_record_pairs.json +0 -8
  638. wisent/examples/scripts/results/test_ruler_evaluation.json +0 -51
  639. wisent/examples/scripts/results/test_ruler_pairs.json +0 -14
  640. wisent/examples/scripts/results/test_sciq_evaluation.json +0 -30
  641. wisent/examples/scripts/results/test_sciq_pairs.json +0 -8
  642. wisent/examples/scripts/results/test_score_evaluation.json +0 -51
  643. wisent/examples/scripts/results/test_score_pairs.json +0 -14
  644. wisent/examples/scripts/results/test_self_consistency_evaluation.json +0 -30
  645. wisent/examples/scripts/results/test_self_consistency_pairs.json +0 -8
  646. wisent/examples/scripts/results/test_siqa/test_siqa_evaluation.json +0 -30
  647. wisent/examples/scripts/results/test_siqa/test_siqa_pairs.json +0 -8
  648. wisent/examples/scripts/results/test_siqa_evaluation.json +0 -30
  649. wisent/examples/scripts/results/test_siqa_pairs.json +0 -8
  650. wisent/examples/scripts/results/test_spanish_bench_evaluation.json +0 -51
  651. wisent/examples/scripts/results/test_spanish_bench_pairs.json +0 -14
  652. wisent/examples/scripts/results/test_squad2_evaluation.json +0 -30
  653. wisent/examples/scripts/results/test_squad2_pairs.json +0 -8
  654. wisent/examples/scripts/results/test_squadv2_evaluation.json +0 -30
  655. wisent/examples/scripts/results/test_squadv2_pairs.json +0 -8
  656. wisent/examples/scripts/results/test_super-glue-lm-eval-v1-seq2seq_evaluation.json +0 -30
  657. wisent/examples/scripts/results/test_super-glue-lm-eval-v1-seq2seq_pairs.json +0 -8
  658. wisent/examples/scripts/results/test_super-glue-lm-eval-v1_evaluation.json +0 -51
  659. wisent/examples/scripts/results/test_super-glue-lm-eval-v1_pairs.json +0 -14
  660. wisent/examples/scripts/results/test_swag_evaluation.json +0 -30
  661. wisent/examples/scripts/results/test_swag_pairs.json +0 -8
  662. wisent/examples/scripts/results/test_tinyBenchmarks_evaluation.json +0 -51
  663. wisent/examples/scripts/results/test_tinyBenchmarks_pairs.json +0 -14
  664. wisent/examples/scripts/results/test_tmmluplus_evaluation.json +0 -51
  665. wisent/examples/scripts/results/test_tmmluplus_pairs.json +0 -14
  666. wisent/examples/scripts/results/test_translation_evaluation.json +0 -51
  667. wisent/examples/scripts/results/test_translation_pairs.json +0 -14
  668. wisent/examples/scripts/results/test_triviaqa_evaluation.json +0 -30
  669. wisent/examples/scripts/results/test_triviaqa_pairs.json +0 -8
  670. wisent/examples/scripts/results/test_truthfulqa-multi_evaluation.json +0 -51
  671. wisent/examples/scripts/results/test_truthfulqa-multi_pairs.json +0 -14
  672. wisent/examples/scripts/results/test_truthfulqa_evaluation.json +0 -30
  673. wisent/examples/scripts/results/test_truthfulqa_mc1_evaluation.json +0 -30
  674. wisent/examples/scripts/results/test_truthfulqa_mc1_pairs.json +0 -8
  675. wisent/examples/scripts/results/test_truthfulqa_mc2_evaluation.json +0 -30
  676. wisent/examples/scripts/results/test_truthfulqa_mc2_pairs.json +0 -8
  677. wisent/examples/scripts/results/test_truthfulqa_pairs.json +0 -8
  678. wisent/examples/scripts/results/test_turkishmmlu_evaluation.json +0 -51
  679. wisent/examples/scripts/results/test_turkishmmlu_pairs.json +0 -14
  680. wisent/examples/scripts/results/test_unfair_tos_evaluation.json +0 -30
  681. wisent/examples/scripts/results/test_unfair_tos_pairs.json +0 -8
  682. wisent/examples/scripts/results/test_unscramble_evaluation.json +0 -51
  683. wisent/examples/scripts/results/test_unscramble_pairs.json +0 -14
  684. wisent/examples/scripts/results/test_webqs_evaluation.json +0 -30
  685. wisent/examples/scripts/results/test_webqs_pairs.json +0 -8
  686. wisent/examples/scripts/results/test_wikitext103_evaluation.json +0 -30
  687. wisent/examples/scripts/results/test_wikitext103_pairs.json +0 -8
  688. wisent/examples/scripts/results/test_wikitext_evaluation.json +0 -30
  689. wisent/examples/scripts/results/test_wikitext_pairs.json +0 -8
  690. wisent/examples/scripts/results/test_winogender_evaluation.json +0 -51
  691. wisent/examples/scripts/results/test_winogender_pairs.json +0 -14
  692. wisent/examples/scripts/results/test_winogrande_evaluation.json +0 -30
  693. wisent/examples/scripts/results/test_winogrande_pairs.json +0 -8
  694. wisent/examples/scripts/results/test_wmdp_evaluation.json +0 -30
  695. wisent/examples/scripts/results/test_wmdp_pairs.json +0 -8
  696. wisent/examples/scripts/results/test_wmt-ro-en-t5-prompt_evaluation.json +0 -30
  697. wisent/examples/scripts/results/test_wmt-ro-en-t5-prompt_pairs.json +0 -8
  698. wisent/examples/scripts/results/test_wmt14_en_fr_evaluation.json +0 -30
  699. wisent/examples/scripts/results/test_wmt14_en_fr_pairs.json +0 -8
  700. wisent/examples/scripts/results/test_wmt16_en_de_evaluation.json +0 -30
  701. wisent/examples/scripts/results/test_wmt16_en_de_pairs.json +0 -8
  702. wisent/examples/scripts/results/test_wmt16_ro_en_evaluation.json +0 -30
  703. wisent/examples/scripts/results/test_wmt16_ro_en_pairs.json +0 -8
  704. wisent/examples/scripts/results/test_wsc273_evaluation.json +0 -30
  705. wisent/examples/scripts/results/test_wsc273_pairs.json +0 -8
  706. wisent/examples/scripts/results/test_xcopa_evaluation.json +0 -51
  707. wisent/examples/scripts/results/test_xcopa_pairs.json +0 -14
  708. wisent/examples/scripts/results/test_xnli_eu_evaluation.json +0 -30
  709. wisent/examples/scripts/results/test_xnli_eu_pairs.json +0 -8
  710. wisent/examples/scripts/results/test_xnli_evaluation.json +0 -51
  711. wisent/examples/scripts/results/test_xnli_pairs.json +0 -14
  712. wisent/examples/scripts/results/test_xquad_evaluation.json +0 -51
  713. wisent/examples/scripts/results/test_xquad_pairs.json +0 -14
  714. wisent/examples/scripts/results/test_xstorycloze_evaluation.json +0 -51
  715. wisent/examples/scripts/results/test_xstorycloze_pairs.json +0 -14
  716. wisent/examples/scripts/results/test_xsum_evaluation.json +0 -30
  717. wisent/examples/scripts/results/test_xsum_pairs.json +0 -8
  718. wisent/examples/scripts/results/test_xwinograd_evaluation.json +0 -51
  719. wisent/examples/scripts/results/test_xwinograd_pairs.json +0 -14
  720. wisent/examples/scripts/results/test_yahoo_answers_topics_evaluation.json +0 -30
  721. wisent/examples/scripts/results/test_yahoo_answers_topics_pairs.json +0 -8
  722. {wisent-0.7.379.dist-info → wisent-0.7.701.dist-info}/WHEEL +0 -0
  723. {wisent-0.7.379.dist-info → wisent-0.7.701.dist-info}/entry_points.txt +0 -0
  724. {wisent-0.7.379.dist-info → wisent-0.7.701.dist-info}/licenses/LICENSE +0 -0
  725. {wisent-0.7.379.dist-info → wisent-0.7.701.dist-info}/top_level.txt +0 -0
wisent/examples/scripts/results/benchmark_methods_summary.json DELETED
@@ -1,260 +0,0 @@
1
- {
2
- "benchmark_info": {
3
- "aime": {
4
- "evaluation_method": "generation",
5
- "pair_creation_method": "LMEvalDataLoader"
6
- },
7
- "aime2024": {
8
- "evaluation_method": "generation",
9
- "pair_creation_method": "LMEvalDataLoader"
10
- },
11
- "aime2025": {
12
- "evaluation_method": "generation",
13
- "pair_creation_method": "LMEvalDataLoader"
14
- },
15
- "apps": {
16
- "evaluation_method": "docker_code",
17
- "pair_creation_method": "HuggingFaceDataLoader"
18
- },
19
- "arc_challenge": {
20
- "evaluation_method": "log_likelihoods",
21
- "pair_creation_method": "LMEvalDataLoader"
22
- },
23
- "arc_easy": {
24
- "evaluation_method": "log_likelihoods",
25
- "pair_creation_method": "LMEvalDataLoader"
26
- },
27
- "arithmetic": {
28
- "evaluation_method": "generation",
29
- "pair_creation_method": "LMEvalDataLoader"
30
- },
31
- "asdiv": {
32
- "evaluation_method": "generation",
33
- "pair_creation_method": "LMEvalDataLoader"
34
- },
35
- "boolq": {
36
- "evaluation_method": "log_likelihoods",
37
- "pair_creation_method": "LMEvalDataLoader"
38
- },
39
- "cb": {
40
- "evaluation_method": "log_likelihoods",
41
- "pair_creation_method": "LMEvalDataLoader"
42
- },
43
- "codexglue_code_to_text_go": {
44
- "evaluation_method": "docker_code",
45
- "pair_creation_method": "HuggingFaceDataLoader"
46
- },
47
- "codexglue_code_to_text_java": {
48
- "evaluation_method": "docker_code",
49
- "pair_creation_method": "HuggingFaceDataLoader"
50
- },
51
- "codexglue_code_to_text_javascript": {
52
- "evaluation_method": "docker_code",
53
- "pair_creation_method": "HuggingFaceDataLoader"
54
- },
55
- "codexglue_code_to_text_php": {
56
- "evaluation_method": "docker_code",
57
- "pair_creation_method": "HuggingFaceDataLoader"
58
- },
59
- "codexglue_code_to_text_python": {
60
- "evaluation_method": "docker_code",
61
- "pair_creation_method": "HuggingFaceDataLoader"
62
- },
63
- "codexglue_code_to_text_ruby": {
64
- "evaluation_method": "docker_code",
65
- "pair_creation_method": "HuggingFaceDataLoader"
66
- },
67
- "conala": {
68
- "evaluation_method": "docker_code",
69
- "pair_creation_method": "HuggingFaceDataLoader"
70
- },
71
- "concode": {
72
- "evaluation_method": "docker_code",
73
- "pair_creation_method": "HuggingFaceDataLoader"
74
- },
75
- "copa": {
76
- "evaluation_method": "log_likelihoods",
77
- "pair_creation_method": "LMEvalDataLoader"
78
- },
79
- "coqa": {
80
- "evaluation_method": "generation",
81
- "pair_creation_method": "LMEvalDataLoader"
82
- },
83
- "drop": {
84
- "evaluation_method": "generation",
85
- "pair_creation_method": "LMEvalDataLoader"
86
- },
87
- "ds1000": {
88
- "evaluation_method": "docker_code",
89
- "pair_creation_method": "HuggingFaceDataLoader"
90
- },
91
- "gpqa": {
92
- "evaluation_method": "log_likelihoods",
93
- "pair_creation_method": "LMEvalDataLoader"
94
- },
95
- "gsm8k": {
96
- "evaluation_method": "generation",
97
- "pair_creation_method": "LMEvalDataLoader"
98
- },
99
- "hellaswag": {
100
- "evaluation_method": "log_likelihoods",
101
- "pair_creation_method": "LMEvalDataLoader"
102
- },
103
- "hendrycks_math": {
104
- "evaluation_method": "generation",
105
- "pair_creation_method": "LMEvalDataLoader"
106
- },
107
- "hmmt": {
108
- "evaluation_method": "generation",
109
- "pair_creation_method": "LMEvalDataLoader"
110
- },
111
- "hmmt_feb_2025": {
112
- "evaluation_method": "generation",
113
- "pair_creation_method": "LMEvalDataLoader"
114
- },
115
- "humaneval": {
116
- "evaluation_method": "docker_code",
117
- "pair_creation_method": "HuggingFaceDataLoader"
118
- },
119
- "humaneval_plus": {
120
- "evaluation_method": "docker_code",
121
- "pair_creation_method": "HuggingFaceDataLoader"
122
- },
123
- "instruct_humaneval": {
124
- "evaluation_method": "docker_code",
125
- "pair_creation_method": "HuggingFaceDataLoader"
126
- },
127
- "lambada_openai": {
128
- "evaluation_method": "perplexity",
129
- "pair_creation_method": "LMEvalDataLoader"
130
- },
131
- "lambada_standard": {
132
- "evaluation_method": "perplexity",
133
- "pair_creation_method": "LMEvalDataLoader"
134
- },
135
- "livecodebench": {
136
- "evaluation_method": "docker_code",
137
- "pair_creation_method": "LMEvalDataLoader"
138
- },
139
- "livemathbench_cnmo_en": {
140
- "evaluation_method": "generation",
141
- "pair_creation_method": "LMEvalDataLoader"
142
- },
143
- "livemathbench_cnmo_zh": {
144
- "evaluation_method": "generation",
145
- "pair_creation_method": "LMEvalDataLoader"
146
- },
147
- "math": {
148
- "evaluation_method": "generation",
149
- "pair_creation_method": "HuggingFaceDataLoader"
150
- },
151
- "math500": {
152
- "evaluation_method": "generation",
153
- "pair_creation_method": "HuggingFaceDataLoader"
154
- },
155
- "mbpp": {
156
- "evaluation_method": "docker_code",
157
- "pair_creation_method": "HuggingFaceDataLoader"
158
- },
159
- "mbpp_plus": {
160
- "evaluation_method": "docker_code",
161
- "pair_creation_method": "HuggingFaceDataLoader"
162
- },
163
- "mercury": {
164
- "evaluation_method": "docker_code",
165
- "pair_creation_method": "HuggingFaceDataLoader"
166
- },
167
- "mmlu": {
168
- "evaluation_method": "log_likelihoods",
169
- "pair_creation_method": "LMEvalDataLoader"
170
- },
171
- "nq_open": {
172
- "evaluation_method": "generation",
173
- "pair_creation_method": "LMEvalDataLoader"
174
- },
175
- "openbookqa": {
176
- "evaluation_method": "log_likelihoods",
177
- "pair_creation_method": "LMEvalDataLoader"
178
- },
179
- "penn_treebank": {
180
- "evaluation_method": "perplexity",
181
- "pair_creation_method": "LMEvalDataLoader"
182
- },
183
- "piqa": {
184
- "evaluation_method": "log_likelihoods",
185
- "pair_creation_method": "LMEvalDataLoader"
186
- },
187
- "polymath_en_high": {
188
- "evaluation_method": "generation",
189
- "pair_creation_method": "LMEvalDataLoader"
190
- },
191
- "polymath_en_medium": {
192
- "evaluation_method": "generation",
193
- "pair_creation_method": "LMEvalDataLoader"
194
- },
195
- "polymath_zh_high": {
196
- "evaluation_method": "generation",
197
- "pair_creation_method": "LMEvalDataLoader"
198
- },
199
- "polymath_zh_medium": {
200
- "evaluation_method": "generation",
201
- "pair_creation_method": "LMEvalDataLoader"
202
- },
203
- "ptb": {
204
- "evaluation_method": "perplexity",
205
- "pair_creation_method": "LMEvalDataLoader"
206
- },
207
- "race": {
208
- "evaluation_method": "log_likelihoods",
209
- "pair_creation_method": "LMEvalDataLoader"
210
- },
211
- "recode": {
212
- "evaluation_method": "docker_code",
213
- "pair_creation_method": "HuggingFaceDataLoader"
214
- },
215
- "record": {
216
- "evaluation_method": "generation",
217
- "pair_creation_method": "LMEvalDataLoader"
218
- },
219
- "squad2": {
220
- "evaluation_method": "generation",
221
- "pair_creation_method": "LMEvalDataLoader"
222
- },
223
- "squadv2": {
224
- "evaluation_method": "generation",
225
- "pair_creation_method": "LMEvalDataLoader"
226
- },
227
- "swag": {
228
- "evaluation_method": "log_likelihoods",
229
- "pair_creation_method": "LMEvalDataLoader"
230
- },
231
- "triviaqa": {
232
- "evaluation_method": "generation",
233
- "pair_creation_method": "LMEvalDataLoader"
234
- },
235
- "truthfulqa_mc1": {
236
- "evaluation_method": "log_likelihoods",
237
- "pair_creation_method": "LMEvalDataLoader"
238
- },
239
- "truthfulqa_mc2": {
240
- "evaluation_method": "log_likelihoods",
241
- "pair_creation_method": "LMEvalDataLoader"
242
- },
243
- "webqs": {
244
- "evaluation_method": "generation",
245
- "pair_creation_method": "LMEvalDataLoader"
246
- },
247
- "wikitext": {
248
- "evaluation_method": "perplexity",
249
- "pair_creation_method": "LMEvalDataLoader"
250
- },
251
- "wikitext103": {
252
- "evaluation_method": "perplexity",
253
- "pair_creation_method": "LMEvalDataLoader"
254
- },
255
- "winogrande": {
256
- "evaluation_method": "log_likelihoods",
257
- "pair_creation_method": "LMEvalDataLoader"
258
- }
259
- }
260
- }
wisent/examples/scripts/results/benchmark_pair_creation_methods.json DELETED
@@ -1,66 +0,0 @@
1
- {
2
- "aime": "LMEvalDataLoader",
3
- "aime2024": "LMEvalDataLoader",
4
- "aime2025": "LMEvalDataLoader",
5
- "apps": "HuggingFaceDataLoader",
6
- "arc_challenge": "LMEvalDataLoader",
7
- "arc_easy": "LMEvalDataLoader",
8
- "arithmetic": "LMEvalDataLoader",
9
- "asdiv": "LMEvalDataLoader",
10
- "boolq": "LMEvalDataLoader",
11
- "cb": "LMEvalDataLoader",
12
- "codexglue_code_to_text_go": "HuggingFaceDataLoader",
13
- "codexglue_code_to_text_java": "HuggingFaceDataLoader",
14
- "codexglue_code_to_text_javascript": "HuggingFaceDataLoader",
15
- "codexglue_code_to_text_php": "HuggingFaceDataLoader",
16
- "codexglue_code_to_text_python": "HuggingFaceDataLoader",
17
- "codexglue_code_to_text_ruby": "HuggingFaceDataLoader",
18
- "conala": "HuggingFaceDataLoader",
19
- "concode": "HuggingFaceDataLoader",
20
- "copa": "LMEvalDataLoader",
21
- "coqa": "LMEvalDataLoader",
22
- "drop": "LMEvalDataLoader",
23
- "ds1000": "HuggingFaceDataLoader",
24
- "gpqa": "LMEvalDataLoader",
25
- "gsm8k": "LMEvalDataLoader",
26
- "hellaswag": "LMEvalDataLoader",
27
- "hendrycks_math": "LMEvalDataLoader",
28
- "hmmt": "LMEvalDataLoader",
29
- "hmmt_feb_2025": "LMEvalDataLoader",
30
- "humaneval": "HuggingFaceDataLoader",
31
- "humaneval_plus": "HuggingFaceDataLoader",
32
- "instruct_humaneval": "HuggingFaceDataLoader",
33
- "lambada_openai": "LMEvalDataLoader",
34
- "lambada_standard": "LMEvalDataLoader",
35
- "livecodebench": "LMEvalDataLoader",
36
- "livemathbench_cnmo_en": "LMEvalDataLoader",
37
- "livemathbench_cnmo_zh": "LMEvalDataLoader",
38
- "math": "HuggingFaceDataLoader",
39
- "math500": "HuggingFaceDataLoader",
40
- "mbpp": "HuggingFaceDataLoader",
41
- "mbpp_plus": "HuggingFaceDataLoader",
42
- "mercury": "HuggingFaceDataLoader",
43
- "mmlu": "LMEvalDataLoader",
44
- "nq_open": "LMEvalDataLoader",
45
- "openbookqa": "LMEvalDataLoader",
46
- "penn_treebank": "LMEvalDataLoader",
47
- "piqa": "LMEvalDataLoader",
48
- "polymath_en_high": "LMEvalDataLoader",
49
- "polymath_en_medium": "LMEvalDataLoader",
50
- "polymath_zh_high": "LMEvalDataLoader",
51
- "polymath_zh_medium": "LMEvalDataLoader",
52
- "ptb": "LMEvalDataLoader",
53
- "race": "LMEvalDataLoader",
54
- "recode": "HuggingFaceDataLoader",
55
- "record": "LMEvalDataLoader",
56
- "squad2": "LMEvalDataLoader",
57
- "squadv2": "LMEvalDataLoader",
58
- "swag": "LMEvalDataLoader",
59
- "triviaqa": "LMEvalDataLoader",
60
- "truthfulqa_mc1": "LMEvalDataLoader",
61
- "truthfulqa_mc2": "LMEvalDataLoader",
62
- "webqs": "LMEvalDataLoader",
63
- "wikitext": "LMEvalDataLoader",
64
- "wikitext103": "LMEvalDataLoader",
65
- "winogrande": "LMEvalDataLoader"
66
- }
wisent/examples/scripts/results/benchmark_pair_totals.json DELETED
@@ -1,269 +0,0 @@
1
- {
2
- "total_benchmarks": 263,
3
- "total_pairs": 356,
4
- "per_benchmark": {
5
- "epec_koref_bin": 1,
6
- "advanced_ai_risk": 2,
7
- "humaneval": 1,
8
- "lambada": 1,
9
- "xstorycloze": 2,
10
- "coqcat": 1,
11
- "swag": 1,
12
- "cycle_letters": 1,
13
- "iwslt2017-en-ar": 1,
14
- "bigbench": 2,
15
- "livecodebench": 1,
16
- "acp_bench_hard": 2,
17
- "claim_stance_topic": 1,
18
- "bec2016eu": 2,
19
- "mercury": 1,
20
- "eus_reading": 1,
21
- "lambada_openai": 1,
22
- "wmt14_en_fr": 1,
23
- "bertaqa": 2,
24
- "pythia": 2,
25
- "fld": 1,
26
- "darija_bench": 2,
27
- "assin_entailment": 1,
28
- "polymath_zh_high": 1,
29
- "Tag": 1,
30
- "mastermind": 2,
31
- "math": 1,
32
- "codexglue_code_to_text_python": 1,
33
- "csatqa": 2,
34
- "squadv2": 1,
35
- "evalita_LLM": 2,
36
- "hmmt_feb_2025": 1,
37
- "mc_taco": 1,
38
- "meqsum": 1,
39
- "aime2025": 1,
40
- "atis": 1,
41
- "egymmlu": 2,
42
- "freebase": 1,
43
- "arabic_exams": 1,
44
- "acp_bench": 2,
45
- "afrimgsm_direct_amh": 1,
46
- "livemathbench_cnmo_en": 1,
47
- "agieval": 2,
48
- "polemo2": 1,
49
- "argument_topic": 1,
50
- "ruler": 2,
51
- "gpt3_translation_benchmarks": 2,
52
- "truthfulqa": 1,
53
- "eq_bench": 1,
54
- "asdiv": 1,
55
- "openbookqa": 1,
56
- "blimp": 2,
57
- "boolq": 1,
58
- "ceval": 2,
59
- "babi": 1,
60
- "spanish_bench": 2,
61
- "medqa": 1,
62
- "egyhellaswag": 1,
63
- "mutual": 1,
64
- "truthfulqa_mc2": 1,
65
- "japanese_leaderboard": 2,
66
- "logiqa2": 1,
67
- "aclue": 2,
68
- "kormedmcqa": 1,
69
- "metabench": 2,
70
- "lambada_standard": 1,
71
- "ethics_cm": 1,
72
- "wikitext103": 1,
73
- "catcola": 1,
74
- "aexams": 2,
75
- "arabic_leaderboard_complete": 2,
76
- "20_newsgroups": 1,
77
- "arithmetic": 2,
78
- "wmdp": 1,
79
- "belebele": 2,
80
- "lingoly": 1,
81
- "paws-x": 2,
82
- "darijammlu": 2,
83
- "drop": 1,
84
- "anagrams1": 1,
85
- "dbpedia_14": 1,
86
- "evalita-mp": 2,
87
- "bhtc_v2": 1,
88
- "record": 1,
89
- "m_mmlu": 2,
90
- "instruct_humaneval": 1,
91
- "inverse_scaling_hindsight_neglect_10shot": 1,
92
- "hendrycks_ethics": 2,
93
- "model_written_evals": 2,
94
- "gsm8k": 1,
95
- "kobest": 2,
96
- "galician_bench": 2,
97
- "cocoteros_es": 1,
98
- "triviaqa": 1,
99
- "lambada_cloze": 1,
100
- "unscramble": 2,
101
- "mmlusr": 1,
102
- "polymath_en_high": 1,
103
- "mmlu_pro": 2,
104
- "lambada_multilingual": 2,
105
- "mmlu": 2,
106
- "polymath_en_medium": 1,
107
- "ArabCulture": 2,
108
- "meddialog": 1,
109
- "cabreu": 1,
110
- "multipl_e": 1,
111
- "coqa": 1,
112
- "eus_exams": 2,
113
- "bangla_mmlu": 1,
114
- "french_bench": 2,
115
- "polymath_zh_medium": 1,
116
- "codexglue_code_to_text_ruby": 1,
117
- "arabic_leaderboard_light": 2,
118
- "mimic_repsum": 1,
119
- "flores": 2,
120
- "cnn_dailymail": 1,
121
- "codexglue_code_to_text_php": 1,
122
- "basque-glue": 2,
123
- "prost": 1,
124
- "math500": 1,
125
- "codexglue_code_to_text_java": 1,
126
- "chain_of_thought": 2,
127
- "arc_challenge": 1,
128
- "aime": 1,
129
- "catalanqa": 1,
130
- "lambada_multilingual_stablelm": 2,
131
- "anli": 1,
132
- "squad2": 1,
133
- "moral_stories": 1,
134
- "eus_exams_es": 2,
135
- "webqs": 1,
136
- "wsc273": 1,
137
- "paloma": 2,
138
- "qa4mre": 1,
139
- "mathqa": 1,
140
- "gpqa": 2,
141
- "inverse_scaling": 2,
142
- "mbpp": 1,
143
- "piqa": 1,
144
- "aime2024": 1,
145
- "codexglue_code_to_text_javascript": 1,
146
- "penn_treebank": 1,
147
- "escola": 1,
148
- "arc_ar": 1,
149
- "openllm": 2,
150
- "mmlu_prox": 2,
151
- "global_mmlu": 2,
152
- "mts_dialog": 1,
153
- "ptb": 1,
154
- "winogender": 2,
155
- "prompt_robustness_agieval_aqua_rat": 1,
156
- "bbh": 2,
157
- "codexglue_code_to_text_go": 1,
158
- "fda": 1,
159
- "tinyBenchmarks": 2,
160
- "darijahellaswag": 1,
161
- "ethos_binary": 1,
162
- "ifeval": 1,
163
- "noticia": 1,
164
- "copal_id": 1,
165
- "boolq-seq2seq": 1,
166
- "leaderboard": 2,
167
- "ag_news": 1,
168
- "headqa": 1,
169
- "AraDICE": 2,
170
- "anagrams2": 1,
171
- "basque_bench": 2,
172
- "truthfulqa-multi": 2,
173
- "wmt-ro-en-t5-prompt": 1,
174
- "cmmlu": 2,
175
- "mela": 2,
176
- "hrm8k": 2,
177
- "hmmt": 1,
178
- "portuguese_bench": 2,
179
- "kmmlu": 2,
180
- "haerae": 2,
181
- "apps": 1,
182
- "cola": 1,
183
- "careqa": 1,
184
- "self_consistency": 1,
185
- "tmmluplus": 2,
186
- "pubmedqa": 1,
187
- "yahoo_answers_topics": 1,
188
- "hendrycks_math": 2,
189
- "catalan_bench": 2,
190
- "ds1000": 1,
191
- "kbl": 2,
192
- "siqa": 1,
193
- "glue": 2,
194
- "medtext": 1,
195
- "super-glue-lm-eval-v1-seq2seq": 1,
196
- "afrixnli_en_direct_amh": 1,
197
- "iwslt2017-ar-en": 1,
198
- "noreval": 2,
199
- "sciq": 1,
200
- "race": 1,
201
- "xquad": 2,
202
- "unfair_tos": 1,
203
- "banking77": 1,
204
- "option_order_robustness_agieval_aqua_rat": 1,
205
- "arabicmmlu": 2,
206
- "c4": 1,
207
- "wikitext": 1,
208
- "benchmarks": 2,
209
- "chartqa": 1,
210
- "groundcocoa": 1,
211
- "mediqa_qa2019": 1,
212
- "xnli": 2,
213
- "xcopa": 2,
214
- "truthfulqa_mc1": 1,
215
- "super-glue-lm-eval-v1": 2,
216
- "concode": 1,
217
- "mnli": 1,
218
- "babilong": 1,
219
- "humaneval_plus": 1,
220
- "qasper": 1,
221
- "copa": 1,
222
- "commonsense_qa": 1,
223
- "conala": 1,
224
- "logiqa": 1,
225
- "llama": 1,
226
- "arc_easy": 1,
227
- "score": 2,
228
- "wmt16_en_de": 1,
229
- "med_concepts_qa": 2,
230
- "mlqa": 2,
231
- "olaph": 1,
232
- "galcola": 1,
233
- "minerva_math": 2,
234
- "bbq": 1,
235
- "jsonschema_bench": 1,
236
- "histoires_morales": 1,
237
- "multimedqa": 2,
238
- "eus_proficiency": 1,
239
- "nq_open": 1,
240
- "mmmu": 2,
241
- "hellaswag": 1,
242
- "glianorex": 1,
243
- "multiblimp": 2,
244
- "mmlu-pro-plus": 2,
245
- "cb": 1,
246
- "eus_trivia": 1,
247
- "xsum": 1,
248
- "basqueglue": 2,
249
- "recode": 1,
250
- "realtoxicityprompts": 1,
251
- "coedit_gec": 1,
252
- "afrimmlu_direct_amh": 1,
253
- "evalita-sp_sum_task_fp-small_p1": 1,
254
- "xnli_eu": 1,
255
- "mbpp_plus": 1,
256
- "crows_pairs": 2,
257
- "xwinograd": 2,
258
- "medmcqa": 1,
259
- "non_greedy_robustness_agieval_aqua_rat": 1,
260
- "translation": 2,
261
- "livemathbench_cnmo_zh": 1,
262
- "winogrande": 1,
263
- "libra": 2,
264
- "mgsm": 2,
265
- "turkishmmlu": 2,
266
- "wmt16_ro_en": 1,
267
- "financial_tweets": 1
268
- }
269
- }