File size: 16,575 Bytes
7aeccfe |
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: 2024-10-17 21:30:14,019: llmtf.base.evaluator: Starting eval on ['darumeru/multiq']
INFO: 2024-10-17 21:30:14,019: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
INFO: 2024-10-17 21:30:14,019: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-10-17 21:30:20,481: llmtf.base.darumeru/MultiQ: Loading Dataset: 6.46s
INFO: 2024-10-17 21:35:59,593: llmtf.base.darumeru/MultiQ: Processing Dataset: 339.11s
INFO: 2024-10-17 21:35:59,593: llmtf.base.darumeru/MultiQ: Results for darumeru/MultiQ:
INFO: 2024-10-17 21:35:59,594: llmtf.base.darumeru/MultiQ: {'f1': 0.3346248767848689, 'em': 0.22275334608030592}
INFO: 2024-10-17 21:35:59,599: llmtf.base.evaluator: Ended eval
INFO: 2024-10-17 21:35:59,599: llmtf.base.evaluator:
mean darumeru/MultiQ
0.279 0.279
INFO: 2024-10-17 21:36:08,809: llmtf.base.evaluator: Starting eval on ['darumeru/parus']
INFO: 2024-10-17 21:36:08,810: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
INFO: 2024-10-17 21:36:08,810: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-10-17 21:36:12,969: llmtf.base.darumeru/PARus: Loading Dataset: 4.16s
INFO: 2024-10-17 21:36:18,316: llmtf.base.darumeru/PARus: Processing Dataset: 5.35s
INFO: 2024-10-17 21:36:18,317: llmtf.base.darumeru/PARus: Results for darumeru/PARus:
INFO: 2024-10-17 21:36:18,327: llmtf.base.darumeru/PARus: {'acc': 0.7}
INFO: 2024-10-17 21:36:18,327: llmtf.base.evaluator: Ended eval
INFO: 2024-10-17 21:36:18,328: llmtf.base.evaluator:
mean darumeru/MultiQ darumeru/PARus
0.489 0.279 0.700
INFO: 2024-10-17 21:36:27,550: llmtf.base.evaluator: Starting eval on ['darumeru/rcb']
INFO: 2024-10-17 21:36:27,550: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
INFO: 2024-10-17 21:36:27,551: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-10-17 21:36:31,450: llmtf.base.darumeru/RCB: Loading Dataset: 3.90s
INFO: 2024-10-17 21:36:38,683: llmtf.base.darumeru/RCB: Processing Dataset: 7.23s
INFO: 2024-10-17 21:36:38,683: llmtf.base.darumeru/RCB: Results for darumeru/RCB:
INFO: 2024-10-17 21:36:38,686: llmtf.base.darumeru/RCB: {'acc': 0.5454545454545454, 'f1_macro': 0.49090309951702227}
INFO: 2024-10-17 21:36:38,687: llmtf.base.evaluator: Ended eval
INFO: 2024-10-17 21:36:38,688: llmtf.base.evaluator:
mean darumeru/MultiQ darumeru/PARus darumeru/RCB
0.499 0.279 0.700 0.518
INFO: 2024-10-17 21:36:48,734: llmtf.base.evaluator: Starting eval on ['darumeru/ruopenbookqa']
INFO: 2024-10-17 21:36:48,735: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
INFO: 2024-10-17 21:36:48,735: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-10-17 21:36:54,900: llmtf.base.darumeru/ruOpenBookQA: Loading Dataset: 6.17s
INFO: 2024-10-17 21:38:00,519: llmtf.base.darumeru/ruOpenBookQA: Processing Dataset: 65.62s
INFO: 2024-10-17 21:38:00,520: llmtf.base.darumeru/ruOpenBookQA: Results for darumeru/ruOpenBookQA:
INFO: 2024-10-17 21:38:00,532: llmtf.base.darumeru/ruOpenBookQA: {'acc': 0.7302405498281787, 'f1_macro': 0.7304546157096631}
INFO: 2024-10-17 21:38:00,541: llmtf.base.evaluator: Ended eval
INFO: 2024-10-17 21:38:00,542: llmtf.base.evaluator:
mean darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/ruOpenBookQA
0.557 0.279 0.700 0.518 0.730
INFO: 2024-10-17 21:38:09,745: llmtf.base.evaluator: Starting eval on ['darumeru/ruworldtree']
INFO: 2024-10-17 21:38:09,745: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
INFO: 2024-10-17 21:38:09,745: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-10-17 21:38:14,102: llmtf.base.darumeru/ruWorldTree: Loading Dataset: 4.36s
INFO: 2024-10-17 21:38:16,932: llmtf.base.darumeru/ruWorldTree: Processing Dataset: 2.83s
INFO: 2024-10-17 21:38:16,933: llmtf.base.darumeru/ruWorldTree: Results for darumeru/ruWorldTree:
INFO: 2024-10-17 21:38:16,936: llmtf.base.darumeru/ruWorldTree: {'acc': 0.9047619047619048, 'f1_macro': 0.9043404138496471}
INFO: 2024-10-17 21:38:16,936: llmtf.base.evaluator: Ended eval
INFO: 2024-10-17 21:38:16,937: llmtf.base.evaluator:
mean darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/ruOpenBookQA darumeru/ruWorldTree
0.626 0.279 0.700 0.518 0.730 0.905
INFO: 2024-10-17 21:38:26,077: llmtf.base.evaluator: Starting eval on ['darumeru/rwsd']
INFO: 2024-10-17 21:38:26,077: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
INFO: 2024-10-17 21:38:26,077: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-10-17 21:38:30,781: llmtf.base.darumeru/RWSD: Loading Dataset: 4.70s
INFO: 2024-10-17 21:38:36,497: llmtf.base.darumeru/RWSD: Processing Dataset: 5.72s
INFO: 2024-10-17 21:38:36,497: llmtf.base.darumeru/RWSD: Results for darumeru/RWSD:
INFO: 2024-10-17 21:38:36,498: llmtf.base.darumeru/RWSD: {'acc': 0.6029411764705882}
INFO: 2024-10-17 21:38:36,499: llmtf.base.evaluator: Ended eval
INFO: 2024-10-17 21:38:36,500: llmtf.base.evaluator:
mean darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/ruOpenBookQA darumeru/ruWorldTree
0.622 0.279 0.700 0.518 0.603 0.730 0.905
INFO: 2024-10-17 21:38:45,688: llmtf.base.evaluator: Starting eval on ['daru/treewayextractive']
INFO: 2024-10-17 21:38:45,688: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
INFO: 2024-10-17 21:38:45,688: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-10-17 21:39:02,002: llmtf.base.daru/treewayextractive: Loading Dataset: 16.31s
INFO: 2024-10-17 21:42:05,777: llmtf.base.daru/treewayextractive: Processing Dataset: 183.77s
INFO: 2024-10-17 21:42:05,777: llmtf.base.daru/treewayextractive: Results for daru/treewayextractive:
INFO: 2024-10-17 21:42:06,010: llmtf.base.daru/treewayextractive: {'r-prec': 0.3917218614718615}
INFO: 2024-10-17 21:42:06,052: llmtf.base.evaluator: Ended eval
INFO: 2024-10-17 21:42:06,054: llmtf.base.evaluator:
mean daru/treewayextractive darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/ruOpenBookQA darumeru/ruWorldTree
0.589 0.392 0.279 0.700 0.518 0.603 0.730 0.905
INFO: 2024-10-17 21:42:15,170: llmtf.base.evaluator: Starting eval on ['nlpcoreteam/rummlu']
INFO: 2024-10-17 21:42:15,170: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
INFO: 2024-10-17 21:42:15,170: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-10-17 21:46:47,282: llmtf.base.nlpcoreteam/ruMMLU: Loading Dataset: 272.11s
INFO: 2024-10-17 21:56:29,398: llmtf.base.nlpcoreteam/ruMMLU: Processing Dataset: 582.12s
INFO: 2024-10-17 21:56:29,399: llmtf.base.nlpcoreteam/ruMMLU: Results for nlpcoreteam/ruMMLU:
INFO: 2024-10-17 21:56:29,464: llmtf.base.nlpcoreteam/ruMMLU: metric
subject
abstract_algebra 0.340000
anatomy 0.414815
astronomy 0.611842
business_ethics 0.610000
clinical_knowledge 0.554717
college_biology 0.548611
college_chemistry 0.380000
college_computer_science 0.450000
college_mathematics 0.400000
college_medicine 0.526012
college_physics 0.470588
computer_security 0.620000
conceptual_physics 0.565957
econometrics 0.377193
electrical_engineering 0.537931
elementary_mathematics 0.529101
formal_logic 0.365079
global_facts 0.360000
high_school_biology 0.664516
high_school_chemistry 0.487685
high_school_computer_science 0.700000
high_school_european_history 0.751515
high_school_geography 0.722222
high_school_government_and_politics 0.564767
high_school_macroeconomics 0.528205
high_school_mathematics 0.433333
high_school_microeconomics 0.533613
high_school_physics 0.403974
high_school_psychology 0.713761
high_school_statistics 0.523148
high_school_us_history 0.661765
high_school_world_history 0.717300
human_aging 0.587444
human_sexuality 0.618321
international_law 0.735537
jurisprudence 0.666667
logical_fallacies 0.564417
machine_learning 0.392857
management 0.650485
marketing 0.752137
medical_genetics 0.580000
miscellaneous 0.632184
moral_disputes 0.583815
moral_scenarios 0.299441
nutrition 0.637255
philosophy 0.617363
prehistory 0.561728
professional_accounting 0.386525
professional_law 0.377445
professional_medicine 0.481618
professional_psychology 0.516340
public_relations 0.500000
security_studies 0.648980
sociology 0.756219
us_foreign_policy 0.720000
virology 0.439759
world_religions 0.719298
INFO: 2024-10-17 21:56:29,473: llmtf.base.nlpcoreteam/ruMMLU: metric
subject
STEM 0.503308
humanities 0.586259
other (business, health, misc.) 0.543782
social sciences 0.599968
INFO: 2024-10-17 21:56:29,478: llmtf.base.nlpcoreteam/ruMMLU: {'acc': 0.5583294528508019}
INFO: 2024-10-17 21:56:29,516: llmtf.base.evaluator: Ended eval
INFO: 2024-10-17 21:56:29,518: llmtf.base.evaluator:
mean daru/treewayextractive darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/ruOpenBookQA darumeru/ruWorldTree nlpcoreteam/ruMMLU
0.586 0.392 0.279 0.700 0.518 0.603 0.730 0.905 0.558
INFO: 2024-10-17 21:56:39,535: llmtf.base.evaluator: Starting eval on ['nlpcoreteam/enmmlu']
INFO: 2024-10-17 21:56:39,536: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
INFO: 2024-10-17 21:56:39,536: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-10-17 21:58:54,966: llmtf.base.nlpcoreteam/enMMLU: Loading Dataset: 135.43s
INFO: 2024-10-17 22:08:04,419: llmtf.base.nlpcoreteam/enMMLU: Processing Dataset: 549.45s
INFO: 2024-10-17 22:08:04,426: llmtf.base.nlpcoreteam/enMMLU: Results for nlpcoreteam/enMMLU:
INFO: 2024-10-17 22:08:04,492: llmtf.base.nlpcoreteam/enMMLU: metric
subject
abstract_algebra 0.380000
anatomy 0.637037
astronomy 0.717105
business_ethics 0.700000
clinical_knowledge 0.705660
college_biology 0.715278
college_chemistry 0.470000
college_computer_science 0.580000
college_mathematics 0.330000
college_medicine 0.664740
college_physics 0.509804
computer_security 0.740000
conceptual_physics 0.642553
econometrics 0.508772
electrical_engineering 0.600000
elementary_mathematics 0.547619
formal_logic 0.412698
global_facts 0.360000
high_school_biology 0.783871
high_school_chemistry 0.581281
high_school_computer_science 0.710000
high_school_european_history 0.800000
high_school_geography 0.757576
high_school_government_and_politics 0.854922
high_school_macroeconomics 0.679487
high_school_mathematics 0.455556
high_school_microeconomics 0.773109
high_school_physics 0.437086
high_school_psychology 0.844037
high_school_statistics 0.652778
high_school_us_history 0.833333
high_school_world_history 0.843882
human_aging 0.677130
human_sexuality 0.786260
international_law 0.768595
jurisprudence 0.814815
logical_fallacies 0.803681
machine_learning 0.446429
management 0.786408
marketing 0.858974
medical_genetics 0.760000
miscellaneous 0.795658
moral_disputes 0.667630
moral_scenarios 0.311732
nutrition 0.732026
philosophy 0.704180
prehistory 0.712963
professional_accounting 0.503546
professional_law 0.457627
professional_medicine 0.658088
professional_psychology 0.668301
public_relations 0.709091
security_studies 0.697959
sociology 0.800995
us_foreign_policy 0.800000
virology 0.506024
world_religions 0.801170
INFO: 2024-10-17 22:08:04,506: llmtf.base.nlpcoreteam/enMMLU: metric
subject
STEM 0.572187
humanities 0.687100
other (business, health, misc.) 0.667521
social sciences 0.740042
INFO: 2024-10-17 22:08:04,511: llmtf.base.nlpcoreteam/enMMLU: {'acc': 0.6667125709237595}
INFO: 2024-10-17 22:08:04,554: llmtf.base.evaluator: Ended eval
INFO: 2024-10-17 22:08:04,556: llmtf.base.evaluator:
mean daru/treewayextractive darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/ruOpenBookQA darumeru/ruWorldTree nlpcoreteam/enMMLU nlpcoreteam/ruMMLU
0.595 0.392 0.279 0.700 0.518 0.603 0.730 0.905 0.667 0.558
INFO: 2024-10-17 22:08:14,512: llmtf.base.evaluator: Starting eval on ['daru/treewayabstractive']
INFO: 2024-10-17 22:08:14,513: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
INFO: 2024-10-17 22:08:14,513: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-10-17 22:08:18,791: llmtf.base.daru/treewayabstractive: Loading Dataset: 4.28s
INFO: 2024-10-17 22:11:46,260: llmtf.base.daru/treewayabstractive: Processing Dataset: 207.47s
INFO: 2024-10-17 22:11:46,260: llmtf.base.daru/treewayabstractive: Results for daru/treewayabstractive:
INFO: 2024-10-17 22:11:46,261: llmtf.base.daru/treewayabstractive: {'rouge1': 0.33109987599556284, 'rouge2': 0.11202889150257295}
INFO: 2024-10-17 22:11:46,262: llmtf.base.evaluator: Ended eval
INFO: 2024-10-17 22:11:46,263: llmtf.base.evaluator:
mean daru/treewayabstractive daru/treewayextractive darumeru/MultiQ darumeru/PARus darumeru/RCB darumeru/RWSD darumeru/ruOpenBookQA darumeru/ruWorldTree nlpcoreteam/enMMLU nlpcoreteam/ruMMLU
0.557 0.222 0.392 0.279 0.700 0.518 0.603 0.730 0.905 0.667 0.558
INFO: 2024-10-17 22:11:55,717: llmtf.base.evaluator: Starting eval on ['darumeru/cp_para_ru']
INFO: 2024-10-17 22:11:55,717: llmtf.base.hfmodel: Updated generation_config.eos_token_id: [147077]
INFO: 2024-10-17 22:11:55,717: llmtf.base.hfmodel: Updated generation_config.stop_strings: ['<|im_end|>']
INFO: 2024-10-17 22:11:59,846: llmtf.base.darumeru/cp_para_ru: Loading Dataset: 4.13s
INFO: 2024-10-17 22:14:29,975: llmtf.base.darumeru/cp_para_ru: Processing Dataset: 150.13s
INFO: 2024-10-17 22:14:29,975: llmtf.base.darumeru/cp_para_ru: Results for darumeru/cp_para_ru:
INFO: 2024-10-17 22:14:29,976: llmtf.base.darumeru/cp_para_ru: {'symbol_per_token': 3.993754090002875, 'len': 0.9986883734384026, 'lcs': 0.98}
INFO: 2024-10-17 22:14:29,977: llmtf.base.evaluator: Ended eval
INFO: 2024-10-17 22:14:29,977: 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
0.596 0.222 0.392 0.279 0.700 0.518 0.603 0.980 0.730 0.905 0.667 0.558
|