Upload folder using huggingface_hub
Browse files- config.json +27 -0
- log.txt +296 -0
- step_74124_pytorch_model.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"directionality": "bidi",
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 32,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 128,
|
| 12 |
+
"layer_norm_eps": 1e-12,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"model_type": "bert",
|
| 15 |
+
"num_attention_heads": 4,
|
| 16 |
+
"num_hidden_layers": 4,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"pooler_fc_size": 32,
|
| 19 |
+
"pooler_num_attention_heads": 4,
|
| 20 |
+
"pooler_num_fc_layers": 3,
|
| 21 |
+
"pooler_size_per_head": 8,
|
| 22 |
+
"pooler_type": "first_token_transform",
|
| 23 |
+
"pre_trained": "",
|
| 24 |
+
"training": "",
|
| 25 |
+
"type_vocab_size": 2,
|
| 26 |
+
"vocab_size": 119547
|
| 27 |
+
}
|
log.txt
ADDED
|
@@ -0,0 +1,296 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
att_loss = 165.9651178506998
|
| 2 |
+
global_step = 999
|
| 3 |
+
loss = 44.97073807873883
|
| 4 |
+
rep_loss = 13.917834387407884
|
| 5 |
+
att_loss = 152.55476939385983
|
| 6 |
+
global_step = 1999
|
| 7 |
+
loss = 41.532161897751855
|
| 8 |
+
rep_loss = 13.573878260956459
|
| 9 |
+
att_loss = 138.32189903246558
|
| 10 |
+
global_step = 2999
|
| 11 |
+
loss = 37.904360088120704
|
| 12 |
+
rep_loss = 13.295541353645465
|
| 13 |
+
att_loss = 129.30404715503445
|
| 14 |
+
global_step = 3999
|
| 15 |
+
loss = 35.58956172341673
|
| 16 |
+
rep_loss = 13.054199772436757
|
| 17 |
+
att_loss = 119.63957041000027
|
| 18 |
+
global_step = 4999
|
| 19 |
+
loss = 33.12675918429154
|
| 20 |
+
rep_loss = 12.86746633794456
|
| 21 |
+
att_loss = 109.77276303685095
|
| 22 |
+
global_step = 5999
|
| 23 |
+
loss = 30.609275317982963
|
| 24 |
+
rep_loss = 12.664338246328192
|
| 25 |
+
att_loss = 102.02662080682198
|
| 26 |
+
global_step = 6999
|
| 27 |
+
loss = 28.61658605365587
|
| 28 |
+
rep_loss = 12.439723421563624
|
| 29 |
+
att_loss = 95.12835736232395
|
| 30 |
+
global_step = 7999
|
| 31 |
+
loss = 26.83650435163224
|
| 32 |
+
rep_loss = 12.217660057647539
|
| 33 |
+
att_loss = 89.21587809017862
|
| 34 |
+
global_step = 8999
|
| 35 |
+
loss = 25.304571141639222
|
| 36 |
+
rep_loss = 12.002406489413266
|
| 37 |
+
att_loss = 84.34852850204683
|
| 38 |
+
global_step = 9999
|
| 39 |
+
loss = 24.03592947626462
|
| 40 |
+
rep_loss = 11.79518941626905
|
| 41 |
+
att_loss = 80.04609476799249
|
| 42 |
+
global_step = 10999
|
| 43 |
+
loss = 22.912895704271662
|
| 44 |
+
rep_loss = 11.60548806140635
|
| 45 |
+
att_loss = 76.0886288830137
|
| 46 |
+
global_step = 11999
|
| 47 |
+
loss = 21.87929865471253
|
| 48 |
+
rep_loss = 11.428565748672364
|
| 49 |
+
att_loss = 72.60697973719999
|
| 50 |
+
global_step = 12999
|
| 51 |
+
loss = 20.966439453452647
|
| 52 |
+
rep_loss = 11.258778085341058
|
| 53 |
+
att_loss = 69.5490453120802
|
| 54 |
+
global_step = 13999
|
| 55 |
+
loss = 20.161243635634456
|
| 56 |
+
rep_loss = 11.095929238888031
|
| 57 |
+
att_loss = 66.863694736835
|
| 58 |
+
global_step = 14999
|
| 59 |
+
loss = 19.451515919177147
|
| 60 |
+
rep_loss = 10.942368946756408
|
| 61 |
+
att_loss = 64.48475605953156
|
| 62 |
+
global_step = 15999
|
| 63 |
+
loss = 18.82124200939603
|
| 64 |
+
rep_loss = 10.800211985354588
|
| 65 |
+
att_loss = 62.36240669536383
|
| 66 |
+
global_step = 16999
|
| 67 |
+
loss = 18.25807497858882
|
| 68 |
+
rep_loss = 10.669893227154258
|
| 69 |
+
att_loss = 60.45600431909481
|
| 70 |
+
global_step = 17999
|
| 71 |
+
loss = 17.75172053029043
|
| 72 |
+
rep_loss = 10.550877809140395
|
| 73 |
+
att_loss = 58.73684728205207
|
| 74 |
+
global_step = 18999
|
| 75 |
+
loss = 17.294778685248758
|
| 76 |
+
rep_loss = 10.442267465330412
|
| 77 |
+
att_loss = 57.178288419006215
|
| 78 |
+
global_step = 19999
|
| 79 |
+
loss = 16.880314805327764
|
| 80 |
+
rep_loss = 10.342970809934616
|
| 81 |
+
att_loss = 55.75939049489828
|
| 82 |
+
global_step = 20999
|
| 83 |
+
loss = 16.50286048242856
|
| 84 |
+
rep_loss = 10.252051443081537
|
| 85 |
+
att_loss = 54.462385941951986
|
| 86 |
+
global_step = 21999
|
| 87 |
+
loss = 16.15771857637336
|
| 88 |
+
rep_loss = 10.168488371691392
|
| 89 |
+
att_loss = 53.27148981758644
|
| 90 |
+
global_step = 22999
|
| 91 |
+
loss = 15.840749783227535
|
| 92 |
+
rep_loss = 10.091509322725361
|
| 93 |
+
att_loss = 52.1748089551121
|
| 94 |
+
global_step = 23999
|
| 95 |
+
loss = 15.548789579672905
|
| 96 |
+
rep_loss = 10.02034937130858
|
| 97 |
+
att_loss = 26.78962243135852
|
| 98 |
+
global_step = 24999
|
| 99 |
+
loss = 8.789205611776241
|
| 100 |
+
rep_loss = 8.367200058350448
|
| 101 |
+
att_loss = 26.729843077966173
|
| 102 |
+
global_step = 25999
|
| 103 |
+
loss = 8.772781761001008
|
| 104 |
+
rep_loss = 8.361283999649155
|
| 105 |
+
att_loss = 26.682301047169865
|
| 106 |
+
global_step = 26999
|
| 107 |
+
loss = 8.75986536118413
|
| 108 |
+
rep_loss = 8.357160423999789
|
| 109 |
+
att_loss = 26.637808661227602
|
| 110 |
+
global_step = 27999
|
| 111 |
+
loss = 8.747724119054261
|
| 112 |
+
rep_loss = 8.35308783723025
|
| 113 |
+
att_loss = 26.595655785215897
|
| 114 |
+
global_step = 28999
|
| 115 |
+
loss = 8.736268049074313
|
| 116 |
+
rep_loss = 8.34941643002816
|
| 117 |
+
att_loss = 26.553387359643654
|
| 118 |
+
global_step = 29999
|
| 119 |
+
loss = 8.724733944178935
|
| 120 |
+
rep_loss = 8.345548433609528
|
| 121 |
+
att_loss = 26.511934938841605
|
| 122 |
+
global_step = 30999
|
| 123 |
+
loss = 8.713468565658134
|
| 124 |
+
rep_loss = 8.341939335615224
|
| 125 |
+
att_loss = 26.47209676782579
|
| 126 |
+
global_step = 31999
|
| 127 |
+
loss = 8.70264744013037
|
| 128 |
+
rep_loss = 8.33849300280011
|
| 129 |
+
att_loss = 26.435741815876433
|
| 130 |
+
global_step = 32999
|
| 131 |
+
loss = 8.6927635342749
|
| 132 |
+
rep_loss = 8.33531233269693
|
| 133 |
+
att_loss = 26.40115444237546
|
| 134 |
+
global_step = 33999
|
| 135 |
+
loss = 8.683378330563693
|
| 136 |
+
rep_loss = 8.33235888937397
|
| 137 |
+
att_loss = 26.368730268931554
|
| 138 |
+
global_step = 34999
|
| 139 |
+
loss = 8.674565872174405
|
| 140 |
+
rep_loss = 8.329533228384442
|
| 141 |
+
att_loss = 26.33715835482096
|
| 142 |
+
global_step = 35999
|
| 143 |
+
loss = 8.666019251111992
|
| 144 |
+
rep_loss = 8.326918655792824
|
| 145 |
+
att_loss = 26.30735234986891
|
| 146 |
+
global_step = 36999
|
| 147 |
+
loss = 8.657943420050909
|
| 148 |
+
rep_loss = 8.324421335688523
|
| 149 |
+
att_loss = 26.278938743063776
|
| 150 |
+
global_step = 37999
|
| 151 |
+
loss = 8.650236012766838
|
| 152 |
+
rep_loss = 8.322005312864869
|
| 153 |
+
att_loss = 26.25172895231054
|
| 154 |
+
global_step = 38999
|
| 155 |
+
loss = 8.642865562378905
|
| 156 |
+
rep_loss = 8.319733299157008
|
| 157 |
+
att_loss = 26.22554387304705
|
| 158 |
+
global_step = 39999
|
| 159 |
+
loss = 8.63577436198668
|
| 160 |
+
rep_loss = 8.317553578813285
|
| 161 |
+
att_loss = 26.201288267405722
|
| 162 |
+
global_step = 40999
|
| 163 |
+
loss = 8.629222177960115
|
| 164 |
+
rep_loss = 8.315600447361732
|
| 165 |
+
att_loss = 26.177384423765602
|
| 166 |
+
global_step = 41999
|
| 167 |
+
loss = 8.62276040119899
|
| 168 |
+
rep_loss = 8.313657183595035
|
| 169 |
+
att_loss = 26.1553768101701
|
| 170 |
+
global_step = 42999
|
| 171 |
+
loss = 8.616789896070687
|
| 172 |
+
rep_loss = 8.311782776810839
|
| 173 |
+
att_loss = 26.134055339334097
|
| 174 |
+
global_step = 43999
|
| 175 |
+
loss = 8.611018220643333
|
| 176 |
+
rep_loss = 8.31001754608182
|
| 177 |
+
att_loss = 26.11391984937601
|
| 178 |
+
global_step = 44999
|
| 179 |
+
loss = 8.605568707086226
|
| 180 |
+
rep_loss = 8.308354981177883
|
| 181 |
+
att_loss = 26.094756877527036
|
| 182 |
+
global_step = 45999
|
| 183 |
+
loss = 8.600382417517402
|
| 184 |
+
rep_loss = 8.306772793449616
|
| 185 |
+
att_loss = 26.075705275818592
|
| 186 |
+
global_step = 46999
|
| 187 |
+
loss = 8.595226314131908
|
| 188 |
+
rep_loss = 8.30519998013147
|
| 189 |
+
att_loss = 26.057315672295104
|
| 190 |
+
global_step = 47999
|
| 191 |
+
loss = 8.590256583761787
|
| 192 |
+
rep_loss = 8.303710662782752
|
| 193 |
+
att_loss = 26.039835258400025
|
| 194 |
+
global_step = 48999
|
| 195 |
+
loss = 8.58552456486098
|
| 196 |
+
rep_loss = 8.302263001250012
|
| 197 |
+
att_loss = 25.612119941318834
|
| 198 |
+
global_step = 49999
|
| 199 |
+
loss = 8.470151519284649
|
| 200 |
+
rep_loss = 8.268486091244078
|
| 201 |
+
att_loss = 25.60738331776063
|
| 202 |
+
global_step = 50999
|
| 203 |
+
loss = 8.468582282244068
|
| 204 |
+
rep_loss = 8.266945785009176
|
| 205 |
+
att_loss = 25.596803975668333
|
| 206 |
+
global_step = 51999
|
| 207 |
+
loss = 8.465786078342669
|
| 208 |
+
rep_loss = 8.266340331887257
|
| 209 |
+
att_loss = 25.5892900415815
|
| 210 |
+
global_step = 52999
|
| 211 |
+
loss = 8.463734707418448
|
| 212 |
+
rep_loss = 8.265648783767087
|
| 213 |
+
att_loss = 25.57996551027575
|
| 214 |
+
global_step = 53999
|
| 215 |
+
loss = 8.461273999810349
|
| 216 |
+
rep_loss = 8.265130484283633
|
| 217 |
+
att_loss = 25.571993088094473
|
| 218 |
+
global_step = 54999
|
| 219 |
+
loss = 8.459134756525891
|
| 220 |
+
rep_loss = 8.26454593587387
|
| 221 |
+
att_loss = 25.56450918759145
|
| 222 |
+
global_step = 55999
|
| 223 |
+
loss = 8.4571359498005
|
| 224 |
+
rep_loss = 8.264034611357031
|
| 225 |
+
att_loss = 25.55813332545982
|
| 226 |
+
global_step = 56999
|
| 227 |
+
loss = 8.455404902957099
|
| 228 |
+
rep_loss = 8.263486286337137
|
| 229 |
+
att_loss = 25.551806679003086
|
| 230 |
+
global_step = 57999
|
| 231 |
+
loss = 8.453719509657649
|
| 232 |
+
rep_loss = 8.263071358877504
|
| 233 |
+
att_loss = 25.544399506585727
|
| 234 |
+
global_step = 58999
|
| 235 |
+
loss = 8.451735918449483
|
| 236 |
+
rep_loss = 8.262544165122339
|
| 237 |
+
att_loss = 25.539079044758008
|
| 238 |
+
global_step = 59999
|
| 239 |
+
loss = 8.450312722059321
|
| 240 |
+
rep_loss = 8.262171842803422
|
| 241 |
+
att_loss = 25.533065229481924
|
| 242 |
+
global_step = 60999
|
| 243 |
+
loss = 8.448696507862541
|
| 244 |
+
rep_loss = 8.261720797789794
|
| 245 |
+
att_loss = 25.5272183784343
|
| 246 |
+
global_step = 61999
|
| 247 |
+
loss = 8.447124415680117
|
| 248 |
+
rep_loss = 8.261279278620812
|
| 249 |
+
att_loss = 25.52183096024264
|
| 250 |
+
global_step = 62999
|
| 251 |
+
loss = 8.445677864036371
|
| 252 |
+
rep_loss = 8.26088049319973
|
| 253 |
+
att_loss = 25.516231528919583
|
| 254 |
+
global_step = 63999
|
| 255 |
+
loss = 8.444169045639065
|
| 256 |
+
rep_loss = 8.260444652900965
|
| 257 |
+
att_loss = 25.510988567145194
|
| 258 |
+
global_step = 64999
|
| 259 |
+
loss = 8.442773997412639
|
| 260 |
+
rep_loss = 8.26010742366815
|
| 261 |
+
att_loss = 25.506380913765547
|
| 262 |
+
global_step = 65999
|
| 263 |
+
loss = 8.441536241767274
|
| 264 |
+
rep_loss = 8.259764054583128
|
| 265 |
+
att_loss = 25.501700612429243
|
| 266 |
+
global_step = 66999
|
| 267 |
+
loss = 8.440280174074106
|
| 268 |
+
rep_loss = 8.259420086579105
|
| 269 |
+
att_loss = 25.498043594566656
|
| 270 |
+
global_step = 67999
|
| 271 |
+
loss = 8.439289064547964
|
| 272 |
+
rep_loss = 8.259112667204752
|
| 273 |
+
att_loss = 25.494367892728885
|
| 274 |
+
global_step = 68999
|
| 275 |
+
loss = 8.43829905562495
|
| 276 |
+
rep_loss = 8.258828334251232
|
| 277 |
+
att_loss = 25.490245821107287
|
| 278 |
+
global_step = 69999
|
| 279 |
+
loss = 8.4371964769438
|
| 280 |
+
rep_loss = 8.258540091776137
|
| 281 |
+
att_loss = 25.487574132507405
|
| 282 |
+
global_step = 70999
|
| 283 |
+
loss = 8.436473700620542
|
| 284 |
+
rep_loss = 8.258320674128282
|
| 285 |
+
att_loss = 25.483769633130947
|
| 286 |
+
global_step = 71999
|
| 287 |
+
loss = 8.435455289505901
|
| 288 |
+
rep_loss = 8.258051528925597
|
| 289 |
+
att_loss = 25.48069784268519
|
| 290 |
+
global_step = 72999
|
| 291 |
+
loss = 8.434621894379303
|
| 292 |
+
rep_loss = 8.257789739057904
|
| 293 |
+
att_loss = 25.47792583601433
|
| 294 |
+
global_step = 73999
|
| 295 |
+
loss = 8.433877880422072
|
| 296 |
+
rep_loss = 8.257585689757036
|
step_74124_pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:670afc3cd0442862be4bf71075cc92c5a0462b42f3657793b7a62becff4f6b62
|
| 3 |
+
size 16193018
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|