File size: 16,630 Bytes
774dfb9 |
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 |
INFO: 2024-11-15 17:16:28,761: llmtf.base.evaluator: Starting eval on ['darumeru/multiq']
INFO: 2024-11-15 17:16:28,761: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
INFO: 2024-11-15 17:16:28,761: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-11-15 17:16:31,122: llmtf.base.evaluator: Starting eval on ['darumeru/parus']
INFO: 2024-11-15 17:16:31,123: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
INFO: 2024-11-15 17:16:31,123: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-11-15 17:16:33,057: llmtf.base.darumeru/MultiQ: Loading Dataset: 4.30s
INFO: 2024-11-15 17:16:33,199: llmtf.base.darumeru/PARus: Loading Dataset: 2.08s
INFO: 2024-11-15 17:16:35,422: llmtf.base.darumeru/PARus: Processing Dataset: 2.22s
INFO: 2024-11-15 17:16:35,422: llmtf.base.darumeru/PARus: Results for darumeru/PARus:
INFO: 2024-11-15 17:16:35,431: llmtf.base.darumeru/PARus: {'acc': 0.28}
INFO: 2024-11-15 17:16:35,432: llmtf.base.evaluator: Ended eval
INFO: 2024-11-15 17:16:35,432: llmtf.base.evaluator:
mean darumeru/PARus
0.280 0.280
INFO: 2024-11-15 17:16:43,944: llmtf.base.evaluator: Starting eval on ['darumeru/ruopenbookqa']
INFO: 2024-11-15 17:16:43,944: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
INFO: 2024-11-15 17:16:43,944: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-11-15 17:16:47,099: llmtf.base.darumeru/ruOpenBookQA: Loading Dataset: 3.16s
INFO: 2024-11-15 17:17:11,239: llmtf.base.darumeru/ruOpenBookQA: Processing Dataset: 24.14s
INFO: 2024-11-15 17:17:11,239: llmtf.base.darumeru/ruOpenBookQA: Results for darumeru/ruOpenBookQA:
INFO: 2024-11-15 17:17:11,250: llmtf.base.darumeru/ruOpenBookQA: {'acc': 0.47465635738831613, 'f1_macro': 0.4733795691558009}
INFO: 2024-11-15 17:17:11,257: llmtf.base.evaluator: Ended eval
INFO: 2024-11-15 17:17:11,258: llmtf.base.evaluator:
mean darumeru/PARus darumeru/ruOpenBookQA
0.377 0.280 0.474
INFO: 2024-11-15 17:17:20,171: llmtf.base.evaluator: Starting eval on ['darumeru/rwsd']
INFO: 2024-11-15 17:17:20,171: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
INFO: 2024-11-15 17:17:20,171: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-11-15 17:17:22,512: llmtf.base.darumeru/RWSD: Loading Dataset: 2.34s
INFO: 2024-11-15 17:17:25,027: llmtf.base.darumeru/RWSD: Processing Dataset: 2.51s
INFO: 2024-11-15 17:17:25,028: llmtf.base.darumeru/RWSD: Results for darumeru/RWSD:
INFO: 2024-11-15 17:17:25,028: llmtf.base.darumeru/RWSD: {'acc': 0.4362745098039216}
INFO: 2024-11-15 17:17:25,029: llmtf.base.evaluator: Ended eval
INFO: 2024-11-15 17:17:25,029: llmtf.base.evaluator:
mean darumeru/PARus darumeru/RWSD darumeru/ruOpenBookQA
0.397 0.280 0.436 0.474
INFO: 2024-11-15 17:17:33,677: llmtf.base.evaluator: Starting eval on ['nlpcoreteam/rummlu']
INFO: 2024-11-15 17:17:33,677: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
INFO: 2024-11-15 17:17:33,678: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-11-15 17:19:15,640: llmtf.base.nlpcoreteam/ruMMLU: Loading Dataset: 101.96s
INFO: 2024-11-15 17:22:11,674: llmtf.base.nlpcoreteam/ruMMLU: Processing Dataset: 176.03s
INFO: 2024-11-15 17:22:11,674: llmtf.base.nlpcoreteam/ruMMLU: Results for nlpcoreteam/ruMMLU:
INFO: 2024-11-15 17:22:11,735: llmtf.base.nlpcoreteam/ruMMLU: metric
subject
abstract_algebra 0.270000
anatomy 0.392593
astronomy 0.421053
business_ethics 0.410000
clinical_knowledge 0.426415
college_biology 0.340278
college_chemistry 0.200000
college_computer_science 0.330000
college_mathematics 0.300000
college_medicine 0.358382
college_physics 0.294118
computer_security 0.540000
conceptual_physics 0.331915
econometrics 0.359649
electrical_engineering 0.496552
elementary_mathematics 0.399471
formal_logic 0.269841
global_facts 0.390000
high_school_biology 0.393548
high_school_chemistry 0.418719
high_school_computer_science 0.610000
high_school_european_history 0.478788
high_school_geography 0.525253
high_school_government_and_politics 0.388601
high_school_macroeconomics 0.335897
high_school_mathematics 0.366667
high_school_microeconomics 0.407563
high_school_physics 0.331126
high_school_psychology 0.436697
high_school_statistics 0.356481
high_school_us_history 0.401961
high_school_world_history 0.535865
human_aging 0.403587
human_sexuality 0.412214
international_law 0.652893
jurisprudence 0.500000
logical_fallacies 0.374233
machine_learning 0.366071
management 0.456311
marketing 0.645299
medical_genetics 0.440000
miscellaneous 0.429119
moral_disputes 0.447977
moral_scenarios 0.242458
nutrition 0.408497
philosophy 0.459807
prehistory 0.398148
professional_accounting 0.329787
professional_law 0.327249
professional_medicine 0.294118
professional_psychology 0.370915
public_relations 0.436364
security_studies 0.416327
sociology 0.562189
us_foreign_policy 0.610000
virology 0.373494
world_religions 0.456140
INFO: 2024-11-15 17:22:11,743: llmtf.base.nlpcoreteam/ruMMLU: metric
subject
STEM 0.375889
humanities 0.426566
other (business, health, misc.) 0.411257
social sciences 0.438472
INFO: 2024-11-15 17:22:11,748: llmtf.base.nlpcoreteam/ruMMLU: {'acc': 0.41304613612768604}
INFO: 2024-11-15 17:22:11,782: llmtf.base.evaluator: Ended eval
INFO: 2024-11-15 17:22:11,783: llmtf.base.evaluator:
mean darumeru/PARus darumeru/RWSD darumeru/ruOpenBookQA nlpcoreteam/ruMMLU
0.401 0.280 0.436 0.474 0.413
INFO: 2024-11-15 17:22:20,448: llmtf.base.evaluator: Starting eval on ['daru/treewayabstractive']
INFO: 2024-11-15 17:22:20,448: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
INFO: 2024-11-15 17:22:20,448: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-11-15 17:22:24,310: llmtf.base.daru/treewayabstractive: Loading Dataset: 3.86s
INFO: 2024-11-15 17:24:23,418: llmtf.base.darumeru/MultiQ: Processing Dataset: 470.36s
INFO: 2024-11-15 17:24:23,419: llmtf.base.darumeru/MultiQ: Results for darumeru/MultiQ:
INFO: 2024-11-15 17:24:23,420: llmtf.base.darumeru/MultiQ: {'f1': 0.22938942868828982, 'em': 0.13479923518164436}
INFO: 2024-11-15 17:24:23,424: llmtf.base.evaluator: Ended eval
INFO: 2024-11-15 17:24:23,425: llmtf.base.evaluator:
mean darumeru/MultiQ darumeru/PARus darumeru/RWSD darumeru/ruOpenBookQA nlpcoreteam/ruMMLU
0.357 0.182 0.280 0.436 0.474 0.413
INFO: 2024-11-15 17:24:32,018: llmtf.base.evaluator: Starting eval on ['darumeru/rcb']
INFO: 2024-11-15 17:24:32,018: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
INFO: 2024-11-15 17:24:32,019: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-11-15 17:24:34,515: llmtf.base.darumeru/RCB: Loading Dataset: 2.50s
INFO: 2024-11-15 17:24:37,191: llmtf.base.darumeru/RCB: Processing Dataset: 2.68s
INFO: 2024-11-15 17:24:37,191: llmtf.base.darumeru/RCB: Results for darumeru/RCB:
INFO: 2024-11-15 17:24:37,195: llmtf.base.darumeru/RCB: {'acc': 0.4636363636363636, 'f1_macro': 0.4278154677497561}
INFO: 2024-11-15 17:24:37,195: llmtf.base.evaluator: Ended eval
INFO: 2024-11-15 17:24:37,196: llmtf.base.evaluator:
mean darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/ruOpenBookQA nlpcoreteam/ruMMLU
0.372 0.182 0.280 0.446 0.436 0.474 0.413
INFO: 2024-11-15 17:24:45,714: llmtf.base.evaluator: Starting eval on ['darumeru/ruworldtree']
INFO: 2024-11-15 17:24:45,714: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
INFO: 2024-11-15 17:24:45,714: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-11-15 17:24:48,302: llmtf.base.darumeru/ruWorldTree: Loading Dataset: 2.59s
INFO: 2024-11-15 17:24:49,696: llmtf.base.darumeru/ruWorldTree: Processing Dataset: 1.39s
INFO: 2024-11-15 17:24:49,696: llmtf.base.darumeru/ruWorldTree: Results for darumeru/ruWorldTree:
INFO: 2024-11-15 17:24:49,699: llmtf.base.darumeru/ruWorldTree: {'acc': 0.6571428571428571, 'f1_macro': 0.6549941370855985}
INFO: 2024-11-15 17:24:49,699: llmtf.base.evaluator: Ended eval
INFO: 2024-11-15 17:24:49,700: llmtf.base.evaluator:
mean darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/ruOpenBookQA darumeru/ruWorldTree nlpcoreteam/ruMMLU
0.412 0.182 0.280 0.446 0.436 0.474 0.656 0.413
INFO: 2024-11-15 17:24:58,281: llmtf.base.evaluator: Starting eval on ['daru/treewayextractive']
INFO: 2024-11-15 17:24:58,282: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
INFO: 2024-11-15 17:24:58,282: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-11-15 17:25:11,202: llmtf.base.daru/treewayextractive: Loading Dataset: 12.92s
INFO: 2024-11-15 17:26:13,880: llmtf.base.daru/treewayabstractive: Processing Dataset: 229.57s
INFO: 2024-11-15 17:26:13,880: llmtf.base.daru/treewayabstractive: Results for daru/treewayabstractive:
INFO: 2024-11-15 17:26:13,881: llmtf.base.daru/treewayabstractive: {'rouge1': 0.31763876629967247, 'rouge2': 0.10272501116299726}
INFO: 2024-11-15 17:26:13,882: llmtf.base.evaluator: Ended eval
INFO: 2024-11-15 17:26:13,883: llmtf.base.evaluator:
mean daru/treewayabstractive darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/ruOpenBookQA darumeru/ruWorldTree nlpcoreteam/ruMMLU
0.387 0.210 0.182 0.280 0.446 0.436 0.474 0.656 0.413
INFO: 2024-11-15 17:26:58,894: llmtf.base.daru/treewayextractive: Processing Dataset: 107.69s
INFO: 2024-11-15 17:26:58,894: llmtf.base.daru/treewayextractive: Results for daru/treewayextractive:
INFO: 2024-11-15 17:26:59,122: llmtf.base.daru/treewayextractive: {'r-prec': 0.3720740981240981}
INFO: 2024-11-15 17:26:59,162: llmtf.base.evaluator: Ended eval
INFO: 2024-11-15 17:26:59,164: llmtf.base.evaluator:
mean daru/treewayabstractive daru/treewayextractive darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/ruOpenBookQA darumeru/ruWorldTree nlpcoreteam/ruMMLU
0.385 0.210 0.372 0.182 0.280 0.446 0.436 0.474 0.656 0.413
INFO: 2024-11-15 17:27:07,864: llmtf.base.evaluator: Starting eval on ['nlpcoreteam/enmmlu']
INFO: 2024-11-15 17:27:07,864: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
INFO: 2024-11-15 17:27:07,864: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-11-15 17:28:52,751: llmtf.base.nlpcoreteam/enMMLU: Loading Dataset: 104.89s
INFO: 2024-11-15 17:31:30,875: llmtf.base.nlpcoreteam/enMMLU: Processing Dataset: 158.12s
INFO: 2024-11-15 17:31:30,875: llmtf.base.nlpcoreteam/enMMLU: Results for nlpcoreteam/enMMLU:
INFO: 2024-11-15 17:31:30,937: llmtf.base.nlpcoreteam/enMMLU: metric
subject
abstract_algebra 0.360000
anatomy 0.525926
astronomy 0.480263
business_ethics 0.510000
clinical_knowledge 0.581132
college_biology 0.500000
college_chemistry 0.280000
college_computer_science 0.390000
college_mathematics 0.290000
college_medicine 0.485549
college_physics 0.294118
computer_security 0.640000
conceptual_physics 0.459574
econometrics 0.394737
electrical_engineering 0.572414
elementary_mathematics 0.428571
formal_logic 0.333333
global_facts 0.350000
high_school_biology 0.567742
high_school_chemistry 0.477833
high_school_computer_science 0.660000
high_school_european_history 0.612121
high_school_geography 0.601010
high_school_government_and_politics 0.580311
high_school_macroeconomics 0.453846
high_school_mathematics 0.325926
high_school_microeconomics 0.537815
high_school_physics 0.350993
high_school_psychology 0.645872
high_school_statistics 0.435185
high_school_us_history 0.549020
high_school_world_history 0.649789
human_aging 0.533632
human_sexuality 0.526718
international_law 0.669421
jurisprudence 0.564815
logical_fallacies 0.607362
machine_learning 0.366071
management 0.621359
marketing 0.760684
medical_genetics 0.450000
miscellaneous 0.583653
moral_disputes 0.531792
moral_scenarios 0.242458
nutrition 0.549020
philosophy 0.517685
prehistory 0.540123
professional_accounting 0.382979
professional_law 0.362451
professional_medicine 0.345588
professional_psychology 0.449346
public_relations 0.509091
security_studies 0.555102
sociology 0.641791
us_foreign_policy 0.680000
virology 0.427711
world_religions 0.619883
INFO: 2024-11-15 17:31:30,945: llmtf.base.nlpcoreteam/enMMLU: metric
subject
STEM 0.437705
humanities 0.523096
other (business, health, misc.) 0.507659
social sciences 0.547970
INFO: 2024-11-15 17:31:30,950: llmtf.base.nlpcoreteam/enMMLU: {'acc': 0.5041077125064222}
INFO: 2024-11-15 17:31:30,983: llmtf.base.evaluator: Ended eval
INFO: 2024-11-15 17:31:30,985: llmtf.base.evaluator:
mean daru/treewayabstractive daru/treewayextractive darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/ruOpenBookQA darumeru/ruWorldTree nlpcoreteam/enMMLU nlpcoreteam/ruMMLU
0.397 0.210 0.372 0.182 0.280 0.446 0.436 0.474 0.656 0.504 0.413
INFO: 2024-11-15 17:31:39,751: llmtf.base.evaluator: Starting eval on ['darumeru/cp_para_ru']
INFO: 2024-11-15 17:31:39,751: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [145111]
INFO: 2024-11-15 17:31:39,751: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-11-15 17:31:42,286: llmtf.base.darumeru/cp_para_ru: Loading Dataset: 2.53s
INFO: 2024-11-15 17:34:56,464: llmtf.base.darumeru/cp_para_ru: Processing Dataset: 194.18s
INFO: 2024-11-15 17:34:56,464: llmtf.base.darumeru/cp_para_ru: Results for darumeru/cp_para_ru:
INFO: 2024-11-15 17:34:56,465: llmtf.base.darumeru/cp_para_ru: {'tokens_per_word': 1.902600722678228, 'symbol_per_token': 3.932343331088908, 'len': 0.967827425390648, 'lcs': 0.23}
INFO: 2024-11-15 17:34:56,466: llmtf.base.evaluator: Ended eval
INFO: 2024-11-15 17:34:56,466: llmtf.base.evaluator:
mean daru/treewayabstractive daru/treewayextractive darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/cp_para_ru darumeru/ruOpenBookQA darumeru/ruWorldTree nlpcoreteam/enMMLU nlpcoreteam/ruMMLU
0.382 0.210 0.372 0.182 0.280 0.446 0.436 0.230 0.474 0.656 0.504 0.413
|