File size: 21,289 Bytes
5124860 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 |
INFO: 2024-10-14 17:12:15,109: llmtf.base.evaluator: Starting eval on ['darumeru/multiq', 'darumeru/parus', 'darumeru/rcb', 'darumeru/ruopenbookqa', 'darumeru/ruworldtree', 'darumeru/rwsd', 'darumeru/use', 'russiannlp/rucola_custom'] INFO: 2024-10-14 17:12:15,109: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147075, 198, 271] INFO: 2024-10-14 17:12:15,109: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n'] INFO: 2024-10-14 17:12:15,157: llmtf.base.evaluator: Starting eval on ['darumeru/rummlu'] INFO: 2024-10-14 17:12:15,157: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147075, 198, 271] INFO: 2024-10-14 17:12:15,157: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n'] INFO: 2024-10-14 17:12:16,297: llmtf.base.evaluator: Starting eval on ['nlpcoreteam/rummlu'] INFO: 2024-10-14 17:12:16,297: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147075, 198, 271] INFO: 2024-10-14 17:12:16,297: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n'] INFO: 2024-10-14 17:12:18,005: llmtf.base.evaluator: Starting eval on ['nlpcoreteam/enmmlu'] INFO: 2024-10-14 17:12:18,006: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147075, 198, 271] INFO: 2024-10-14 17:12:18,006: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n'] INFO: 2024-10-14 17:12:19,753: llmtf.base.evaluator: Starting eval on ['daru/treewayabstractive'] INFO: 2024-10-14 17:12:19,753: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147075, 198, 271] INFO: 2024-10-14 17:12:19,753: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n'] INFO: 2024-10-14 17:12:21,769: llmtf.base.evaluator: Starting eval on ['daru/treewayextractive'] INFO: 2024-10-14 17:12:21,769: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147075, 198, 271] INFO: 2024-10-14 17:12:21,769: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n'] INFO: 2024-10-14 17:12:23,453: llmtf.base.evaluator: Starting eval on ['darumeru/cp_sent_ru', 'darumeru/cp_sent_en', 'darumeru/cp_para_ru', 'darumeru/cp_para_en'] INFO: 2024-10-14 17:12:23,453: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147075, 198, 271] INFO: 2024-10-14 17:12:23,453: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n'] INFO: 2024-10-14 17:12:29,425: llmtf.base.darumeru/cp_sent_ru: Loading Dataset: 5.97s INFO: 2024-10-14 17:12:39,535: llmtf.base.daru/treewayextractive: Loading Dataset: 17.77s INFO: 2024-10-14 17:12:39,537: llmtf.base.daru/treewayextractive: Processing Dataset: 0.00s ERROR: 2024-10-14 17:12:39,537: llmtf.base.evaluator: return_offset_mapping is not available when using Python tokenizers. To use this feature, change your tokenizer to one deriving from transformers.PreTrainedTokenizerFast. ERROR: 2024-10-14 17:12:39,542: llmtf.base.evaluator: Traceback (most recent call last): File "/scratch/tikhomirov/workdir/projects/llmtf_open/llmtf/evaluator.py", line 42, in evaluate self.evaluate_dataset(task, model, output_dir, prompt_max_len, few_shot_count, generation_config, batch_size, max_sample_per_dataset) File "/scratch/tikhomirov/workdir/projects/llmtf_open/llmtf/evaluator.py", line 65, in evaluate_dataset prompts, y_preds, infos = getattr(model, task.method + '_batch')(**messages_batch) File "/scratch/tikhomirov/workdir/projects/llmtf_open/llmtf/model.py", line 417, in calculate_logsoftmax_batch data = self.tokenizer( File "/usr/local/lib/python3.10/dist-packages/transformers/tokenization_utils_base.py", line 2829, in __call__ encodings = self._call_one(text=text, text_pair=text_pair, **all_kwargs) File "/usr/local/lib/python3.10/dist-packages/transformers/tokenization_utils_base.py", line 2915, in _call_one return self.batch_encode_plus( File "/usr/local/lib/python3.10/dist-packages/transformers/tokenization_utils_base.py", line 3106, in batch_encode_plus return self._batch_encode_plus( File "/usr/local/lib/python3.10/dist-packages/transformers/tokenization_utils.py", line 788, in _batch_encode_plus raise NotImplementedError( NotImplementedError: return_offset_mapping is not available when using Python tokenizers. To use this feature, change your tokenizer to one deriving from transformers.PreTrainedTokenizerFast. INFO: 2024-10-14 17:12:48,032: llmtf.base.daru/treewayabstractive: Loading Dataset: 28.28s INFO: 2024-10-14 17:12:51,035: llmtf.base.darumeru/MultiQ: Loading Dataset: 35.93s INFO: 2024-10-14 17:14:25,981: llmtf.base.darumeru/ruMMLU: Loading Dataset: 130.82s INFO: 2024-10-14 17:16:23,865: llmtf.base.nlpcoreteam/enMMLU: Loading Dataset: 245.86s INFO: 2024-10-14 17:16:52,771: llmtf.base.nlpcoreteam/ruMMLU: Loading Dataset: 276.47s INFO: 2024-10-14 17:17:20,199: llmtf.base.darumeru/MultiQ: Processing Dataset: 269.16s INFO: 2024-10-14 17:17:20,200: llmtf.base.darumeru/MultiQ: Results for darumeru/MultiQ: INFO: 2024-10-14 17:17:20,204: llmtf.base.darumeru/MultiQ: {'f1': 0.48670297858620026, 'em': 0.372848948374761} INFO: 2024-10-14 17:17:20,215: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147075, 198, 271] INFO: 2024-10-14 17:17:20,216: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n'] INFO: 2024-10-14 17:17:23,562: llmtf.base.darumeru/PARus: Loading Dataset: 3.35s INFO: 2024-10-14 17:17:30,091: llmtf.base.darumeru/PARus: Processing Dataset: 6.53s INFO: 2024-10-14 17:17:30,093: llmtf.base.darumeru/PARus: Results for darumeru/PARus: INFO: 2024-10-14 17:17:30,106: llmtf.base.darumeru/PARus: {'acc': 0.72} INFO: 2024-10-14 17:17:30,108: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147075, 198, 271] INFO: 2024-10-14 17:17:30,108: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n'] INFO: 2024-10-14 17:17:34,240: llmtf.base.darumeru/RCB: Loading Dataset: 4.13s INFO: 2024-10-14 17:17:45,351: llmtf.base.darumeru/RCB: Processing Dataset: 11.11s INFO: 2024-10-14 17:17:45,353: llmtf.base.darumeru/RCB: Results for darumeru/RCB: INFO: 2024-10-14 17:17:45,362: llmtf.base.darumeru/RCB: {'acc': 0.55, 'f1_macro': 0.4643770525787481} INFO: 2024-10-14 17:17:45,365: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147075, 198, 271] INFO: 2024-10-14 17:17:45,366: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n'] INFO: 2024-10-14 17:18:02,200: llmtf.base.darumeru/ruOpenBookQA: Loading Dataset: 16.83s INFO: 2024-10-14 17:19:12,133: llmtf.base.darumeru/cp_sent_ru: Processing Dataset: 402.71s INFO: 2024-10-14 17:19:12,136: llmtf.base.darumeru/cp_sent_ru: Results for darumeru/cp_sent_ru: INFO: 2024-10-14 17:19:12,140: llmtf.base.darumeru/cp_sent_ru: {'symbol_per_token': 3.958846363652826, 'len': 0.9810206403044489, 'lcs': 0.9815195071868583} INFO: 2024-10-14 17:19:12,144: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147075, 198, 271] INFO: 2024-10-14 17:19:12,144: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n'] INFO: 2024-10-14 17:19:16,530: llmtf.base.darumeru/ruOpenBookQA: Processing Dataset: 74.33s INFO: 2024-10-14 17:19:16,531: llmtf.base.darumeru/ruOpenBookQA: Results for darumeru/ruOpenBookQA: INFO: 2024-10-14 17:19:16,545: llmtf.base.darumeru/ruOpenBookQA: {'acc': 0.7371134020618557, 'f1_macro': 0.7358424630320096} INFO: 2024-10-14 17:19:16,562: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147075, 198, 271] INFO: 2024-10-14 17:19:16,562: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n'] INFO: 2024-10-14 17:19:16,859: llmtf.base.darumeru/cp_sent_en: Loading Dataset: 4.71s INFO: 2024-10-14 17:19:19,074: llmtf.base.darumeru/ruWorldTree: Loading Dataset: 2.51s INFO: 2024-10-14 17:19:23,376: llmtf.base.darumeru/ruWorldTree: Processing Dataset: 4.30s INFO: 2024-10-14 17:19:23,378: llmtf.base.darumeru/ruWorldTree: Results for darumeru/ruWorldTree: INFO: 2024-10-14 17:19:23,383: llmtf.base.darumeru/ruWorldTree: {'acc': 0.8666666666666667, 'f1_macro': 0.8654128672745693} INFO: 2024-10-14 17:19:23,384: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147075, 198, 271] INFO: 2024-10-14 17:19:23,384: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n'] INFO: 2024-10-14 17:19:27,363: llmtf.base.darumeru/RWSD: Loading Dataset: 3.98s INFO: 2024-10-14 17:19:37,387: llmtf.base.darumeru/RWSD: Processing Dataset: 10.02s INFO: 2024-10-14 17:19:37,405: llmtf.base.darumeru/RWSD: Results for darumeru/RWSD: INFO: 2024-10-14 17:19:37,409: llmtf.base.darumeru/RWSD: {'acc': 0.5735294117647058} INFO: 2024-10-14 17:19:37,411: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147075, 198, 271] INFO: 2024-10-14 17:19:37,411: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n'] INFO: 2024-10-14 17:19:54,737: llmtf.base.darumeru/USE: Loading Dataset: 17.32s INFO: 2024-10-14 17:25:32,317: llmtf.base.darumeru/USE: Processing Dataset: 337.58s INFO: 2024-10-14 17:25:32,321: llmtf.base.darumeru/USE: Results for darumeru/USE: INFO: 2024-10-14 17:25:32,326: llmtf.base.darumeru/USE: {'grade_norm': 0.06176470588235293} INFO: 2024-10-14 17:25:32,333: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147075, 198, 271] INFO: 2024-10-14 17:25:32,334: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n'] INFO: 2024-10-14 17:25:48,469: llmtf.base.darumeru/ruMMLU: Processing Dataset: 682.49s INFO: 2024-10-14 17:25:48,470: llmtf.base.darumeru/ruMMLU: Results for darumeru/ruMMLU: INFO: 2024-10-14 17:25:48,496: llmtf.base.darumeru/ruMMLU: {'acc': 0.5159133991818817} INFO: 2024-10-14 17:25:48,576: llmtf.base.evaluator: Ended eval INFO: 2024-10-14 17:25:48,608: llmtf.base.evaluator: mean darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/USE darumeru/cp_sent_ru darumeru/ruMMLU darumeru/ruOpenBookQA darumeru/ruWorldTree 0.599 0.430 0.720 0.507 0.574 0.062 0.981 0.516 0.736 0.866 INFO: 2024-10-14 17:25:55,560: llmtf.base.russiannlp/rucola_custom: Loading Dataset: 23.23s INFO: 2024-10-14 17:26:02,923: llmtf.base.darumeru/cp_sent_en: Processing Dataset: 406.06s INFO: 2024-10-14 17:26:02,926: llmtf.base.darumeru/cp_sent_en: Results for darumeru/cp_sent_en: INFO: 2024-10-14 17:26:02,930: llmtf.base.darumeru/cp_sent_en: {'symbol_per_token': 4.416472661458526, 'len': 0.9634384484255067, 'lcs': 1.0} INFO: 2024-10-14 17:26:02,932: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147075, 198, 271] INFO: 2024-10-14 17:26:02,932: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n'] INFO: 2024-10-14 17:26:07,243: llmtf.base.darumeru/cp_para_ru: Loading Dataset: 4.31s INFO: 2024-10-14 17:27:27,303: llmtf.base.russiannlp/rucola_custom: Processing Dataset: 91.74s INFO: 2024-10-14 17:27:27,307: llmtf.base.russiannlp/rucola_custom: Results for russiannlp/rucola_custom: INFO: 2024-10-14 17:27:27,320: llmtf.base.russiannlp/rucola_custom: {'acc': 0.5999282382490133, 'mcc': 0.26826918795125926} INFO: 2024-10-14 17:27:27,332: llmtf.base.evaluator: Ended eval INFO: 2024-10-14 17:27:27,344: llmtf.base.evaluator: mean darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/USE darumeru/cp_sent_en darumeru/cp_sent_ru darumeru/ruMMLU darumeru/ruOpenBookQA darumeru/ruWorldTree russiannlp/rucola_custom 0.617 0.430 0.720 0.507 0.574 0.062 0.963 0.981 0.516 0.736 0.866 0.434 INFO: 2024-10-14 17:28:31,573: llmtf.base.nlpcoreteam/enMMLU: Processing Dataset: 727.71s INFO: 2024-10-14 17:28:31,575: llmtf.base.nlpcoreteam/enMMLU: Results for nlpcoreteam/enMMLU: INFO: 2024-10-14 17:28:31,622: llmtf.base.nlpcoreteam/enMMLU: metric subject abstract_algebra 0.380000 anatomy 0.592593 astronomy 0.736842 business_ethics 0.730000 clinical_knowledge 0.716981 college_biology 0.770833 college_chemistry 0.500000 college_computer_science 0.590000 college_mathematics 0.420000 college_medicine 0.676301 college_physics 0.509804 computer_security 0.810000 conceptual_physics 0.642553 econometrics 0.552632 electrical_engineering 0.675862 elementary_mathematics 0.603175 formal_logic 0.349206 global_facts 0.310000 high_school_biology 0.816129 high_school_chemistry 0.610837 high_school_computer_science 0.750000 high_school_european_history 0.787879 high_school_geography 0.808081 high_school_government_and_politics 0.870466 high_school_macroeconomics 0.712821 high_school_mathematics 0.518519 high_school_microeconomics 0.768908 high_school_physics 0.443709 high_school_psychology 0.860550 high_school_statistics 0.666667 high_school_us_history 0.852941 high_school_world_history 0.843882 human_aging 0.721973 human_sexuality 0.793893 international_law 0.785124 jurisprudence 0.787037 logical_fallacies 0.766871 machine_learning 0.473214 management 0.834951 marketing 0.888889 medical_genetics 0.790000 miscellaneous 0.793103 moral_disputes 0.687861 moral_scenarios 0.288268 nutrition 0.751634 philosophy 0.717042 prehistory 0.731481 professional_accounting 0.524823 professional_law 0.477184 professional_medicine 0.661765 professional_psychology 0.696078 public_relations 0.745455 security_studies 0.759184 sociology 0.830846 us_foreign_policy 0.850000 virology 0.493976 world_religions 0.807018 INFO: 2024-10-14 17:28:31,630: llmtf.base.nlpcoreteam/enMMLU: metric subject STEM 0.606564 humanities 0.683215 other (business, health, misc.) 0.677642 social sciences 0.770743 INFO: 2024-10-14 17:28:31,637: llmtf.base.nlpcoreteam/enMMLU: {'acc': 0.6845408165512243} INFO: 2024-10-14 17:28:31,706: llmtf.base.evaluator: Ended eval INFO: 2024-10-14 17:28:31,716: llmtf.base.evaluator: mean darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/USE darumeru/cp_sent_en darumeru/cp_sent_ru darumeru/ruMMLU darumeru/ruOpenBookQA darumeru/ruWorldTree nlpcoreteam/enMMLU russiannlp/rucola_custom 0.623 0.430 0.720 0.507 0.574 0.062 0.963 0.981 0.516 0.736 0.866 0.685 0.434 INFO: 2024-10-14 17:30:17,754: llmtf.base.nlpcoreteam/ruMMLU: Processing Dataset: 804.98s INFO: 2024-10-14 17:30:17,758: llmtf.base.nlpcoreteam/ruMMLU: Results for nlpcoreteam/ruMMLU: INFO: 2024-10-14 17:30:17,804: llmtf.base.nlpcoreteam/ruMMLU: metric subject abstract_algebra 0.340000 anatomy 0.385185 astronomy 0.651316 business_ethics 0.630000 clinical_knowledge 0.558491 college_biology 0.527778 college_chemistry 0.420000 college_computer_science 0.560000 college_mathematics 0.360000 college_medicine 0.549133 college_physics 0.450980 computer_security 0.670000 conceptual_physics 0.582979 econometrics 0.447368 electrical_engineering 0.572414 elementary_mathematics 0.529101 formal_logic 0.357143 global_facts 0.320000 high_school_biology 0.696774 high_school_chemistry 0.522167 high_school_computer_science 0.700000 high_school_european_history 0.715152 high_school_geography 0.757576 high_school_government_and_politics 0.595855 high_school_macroeconomics 0.574359 high_school_mathematics 0.444444 high_school_microeconomics 0.563025 high_school_physics 0.384106 high_school_psychology 0.693578 high_school_statistics 0.518519 high_school_us_history 0.642157 high_school_world_history 0.687764 human_aging 0.582960 human_sexuality 0.625954 international_law 0.735537 jurisprudence 0.611111 logical_fallacies 0.588957 machine_learning 0.401786 management 0.669903 marketing 0.773504 medical_genetics 0.560000 miscellaneous 0.604087 moral_disputes 0.630058 moral_scenarios 0.226816 nutrition 0.663399 philosophy 0.639871 prehistory 0.577160 professional_accounting 0.361702 professional_law 0.371578 professional_medicine 0.470588 professional_psychology 0.539216 public_relations 0.545455 security_studies 0.657143 sociology 0.726368 us_foreign_policy 0.770000 virology 0.463855 world_religions 0.678363 INFO: 2024-10-14 17:30:17,812: llmtf.base.nlpcoreteam/ruMMLU: metric subject STEM 0.518465 humanities 0.573974 other (business, health, misc.) 0.542343 social sciences 0.624658 INFO: 2024-10-14 17:30:17,835: llmtf.base.nlpcoreteam/ruMMLU: {'acc': 0.5648600813341976} INFO: 2024-10-14 17:30:17,918: llmtf.base.evaluator: Ended eval INFO: 2024-10-14 17:30:17,931: llmtf.base.evaluator: mean darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/USE darumeru/cp_sent_en darumeru/cp_sent_ru darumeru/ruMMLU darumeru/ruOpenBookQA darumeru/ruWorldTree nlpcoreteam/enMMLU nlpcoreteam/ruMMLU russiannlp/rucola_custom 0.618 0.430 0.720 0.507 0.574 0.062 0.963 0.981 0.516 0.736 0.866 0.685 0.565 0.434 INFO: 2024-10-14 17:35:49,735: llmtf.base.daru/treewayabstractive: Processing Dataset: 1381.70s INFO: 2024-10-14 17:35:49,744: llmtf.base.daru/treewayabstractive: Results for daru/treewayabstractive: INFO: 2024-10-14 17:35:49,749: llmtf.base.daru/treewayabstractive: {'rouge1': 0.3333904808228802, 'rouge2': 0.127931429649173} INFO: 2024-10-14 17:35:49,754: llmtf.base.evaluator: Ended eval INFO: 2024-10-14 17:35:49,768: llmtf.base.evaluator: mean daru/treewayabstractive darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/USE darumeru/cp_sent_en darumeru/cp_sent_ru darumeru/ruMMLU darumeru/ruOpenBookQA darumeru/ruWorldTree nlpcoreteam/enMMLU nlpcoreteam/ruMMLU russiannlp/rucola_custom 0.591 0.231 0.430 0.720 0.507 0.574 0.062 0.963 0.981 0.516 0.736 0.866 0.685 0.565 0.434 INFO: 2024-10-14 17:36:46,624: llmtf.base.darumeru/cp_para_ru: Processing Dataset: 639.38s INFO: 2024-10-14 17:36:46,627: llmtf.base.darumeru/cp_para_ru: Results for darumeru/cp_para_ru: INFO: 2024-10-14 17:36:46,630: llmtf.base.darumeru/cp_para_ru: {'symbol_per_token': 3.9840096010204995, 'len': 0.9812951313228986, 'lcs': 0.98} INFO: 2024-10-14 17:36:46,632: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147075, 198, 271] INFO: 2024-10-14 17:36:46,632: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['\n', '\n\n'] INFO: 2024-10-14 17:36:50,656: llmtf.base.darumeru/cp_para_en: Loading Dataset: 4.02s INFO: 2024-10-14 17:52:40,643: llmtf.base.darumeru/cp_para_en: Processing Dataset: 949.99s INFO: 2024-10-14 17:52:40,649: llmtf.base.darumeru/cp_para_en: Results for darumeru/cp_para_en: INFO: 2024-10-14 17:52:40,654: llmtf.base.darumeru/cp_para_en: {'symbol_per_token': 4.4342745144269164, 'len': 0.9926602787834059, 'lcs': 1.0} INFO: 2024-10-14 17:52:40,654: llmtf.base.evaluator: Ended eval INFO: 2024-10-14 17:52:40,665: llmtf.base.evaluator: mean daru/treewayabstractive darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/USE darumeru/cp_para_en darumeru/cp_para_ru darumeru/cp_sent_en darumeru/cp_sent_ru darumeru/ruMMLU darumeru/ruOpenBookQA darumeru/ruWorldTree nlpcoreteam/enMMLU nlpcoreteam/ruMMLU russiannlp/rucola_custom 0.641 0.231 0.430 0.720 0.507 0.574 0.062 1.000 0.980 0.963 0.981 0.516 0.736 0.866 0.685 0.565 0.434 |