--- license: bsd-3-clause base_model: Salesforce/codet5p-770m-py tags: - generated_from_trainer datasets: - mbpp model-index: - name: codet5p-770m-py-sanitized-codebleu-1-True-5e-05-0.1-lora-layer_1 results: [] --- # codet5p-770m-py-sanitized-codebleu-1-True-5e-05-0.1-lora-layer_1 This model is a fine-tuned version of [Salesforce/codet5p-770m-py](https://huggingface.co/Salesforce/codet5p-770m-py) on the mbpp dataset. It achieves the following results on the evaluation set: - Loss: 0.6977 - Codebleu: 0.1214 - Ngram Match Score: 0.0382 - Weighted Ngram Match Score: 0.0632 - Syntax Match Score: 0.1336 - Dataflow Match Score: 0.1446 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 100 - num_epochs: 300 ### Training results | Training Loss | Epoch | Step | Validation Loss | Codebleu | Ngram Match Score | Weighted Ngram Match Score | Syntax Match Score | Dataflow Match Score | |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------------:|:--------------------------:|:------------------:|:--------------------:| | 0.9754 | 1.0 | 15 | 0.9245 | 0.0072 | 0.0000 | 0.0000 | 0.0079 | 0.0100 | | 0.9689 | 2.0 | 30 | 0.9230 | 0.0072 | 0.0000 | 0.0000 | 0.0079 | 0.0100 | | 0.972 | 3.0 | 45 | 0.9195 | 0.0080 | 0.0000 | 0.0000 | 0.0079 | 0.0120 | | 0.9377 | 4.0 | 60 | 0.9115 | 0.0080 | 0.0000 | 0.0000 | 0.0079 | 0.0120 | | 0.944 | 5.0 | 75 | 0.8946 | 0.0292 | 0.0002 | 0.0097 | 0.0304 | 0.0402 | | 0.9332 | 6.0 | 90 | 0.8707 | 0.0800 | 0.0189 | 0.0462 | 0.0952 | 0.0884 | | 0.9113 | 7.0 | 105 | 0.8584 | 0.0965 | 0.0168 | 0.0464 | 0.1151 | 0.1104 | | 0.8775 | 8.0 | 120 | 0.8519 | 0.0983 | 0.0180 | 0.0472 | 0.1230 | 0.1064 | | 0.8674 | 9.0 | 135 | 0.8482 | 0.0973 | 0.0222 | 0.0488 | 0.1151 | 0.1104 | | 0.874 | 10.0 | 150 | 0.8439 | 0.0916 | 0.0245 | 0.0483 | 0.1085 | 0.1024 | | 0.8674 | 11.0 | 165 | 0.8389 | 0.0946 | 0.0241 | 0.0487 | 0.1138 | 0.1044 | | 0.8777 | 12.0 | 180 | 0.8315 | 0.0951 | 0.0237 | 0.0495 | 0.1190 | 0.1004 | | 0.8502 | 13.0 | 195 | 0.8226 | 0.0973 | 0.0234 | 0.0508 | 0.1243 | 0.1004 | | 0.8311 | 14.0 | 210 | 0.8088 | 0.1015 | 0.0256 | 0.0530 | 0.1336 | 0.1004 | | 0.8416 | 15.0 | 225 | 0.7977 | 0.0952 | 0.0226 | 0.0517 | 0.1270 | 0.0924 | | 0.8451 | 16.0 | 240 | 0.7837 | 0.1011 | 0.0228 | 0.0520 | 0.1296 | 0.1044 | | 0.8257 | 17.0 | 255 | 0.7713 | 0.0998 | 0.0217 | 0.0536 | 0.1243 | 0.1064 | | 0.8032 | 18.0 | 270 | 0.7652 | 0.1001 | 0.0223 | 0.0581 | 0.1177 | 0.1124 | | 0.8091 | 19.0 | 285 | 0.7607 | 0.0985 | 0.0190 | 0.0479 | 0.1151 | 0.1145 | | 0.7946 | 20.0 | 300 | 0.7549 | 0.1003 | 0.0187 | 0.0480 | 0.1177 | 0.1165 | | 0.7842 | 21.0 | 315 | 0.7482 | 0.1009 | 0.0178 | 0.0465 | 0.1177 | 0.1185 | | 0.7844 | 22.0 | 330 | 0.7413 | 0.1053 | 0.0157 | 0.0452 | 0.1257 | 0.1225 | | 0.7766 | 23.0 | 345 | 0.7401 | 0.1039 | 0.0145 | 0.0421 | 0.1230 | 0.1225 | | 0.7789 | 24.0 | 360 | 0.7379 | 0.1059 | 0.0181 | 0.0481 | 0.1217 | 0.1265 | | 0.7955 | 25.0 | 375 | 0.7341 | 0.1063 | 0.0164 | 0.0460 | 0.1217 | 0.1285 | | 0.7656 | 26.0 | 390 | 0.7324 | 0.1053 | 0.0164 | 0.0460 | 0.1190 | 0.1285 | | 0.7583 | 27.0 | 405 | 0.7319 | 0.1040 | 0.0161 | 0.0444 | 0.1164 | 0.1285 | | 0.7654 | 28.0 | 420 | 0.7295 | 0.1057 | 0.0165 | 0.0445 | 0.1164 | 0.1325 | | 0.7491 | 29.0 | 435 | 0.7290 | 0.1053 | 0.0177 | 0.0446 | 0.1151 | 0.1325 | | 0.7463 | 30.0 | 450 | 0.7274 | 0.1120 | 0.0206 | 0.0509 | 0.1257 | 0.1365 | | 0.7514 | 31.0 | 465 | 0.7258 | 0.1120 | 0.0200 | 0.0509 | 0.1257 | 0.1365 | | 0.7468 | 32.0 | 480 | 0.7244 | 0.1176 | 0.0227 | 0.0569 | 0.1376 | 0.1365 | | 0.7356 | 33.0 | 495 | 0.7233 | 0.0976 | 0.0168 | 0.0411 | 0.1111 | 0.1185 | | 0.7551 | 34.0 | 510 | 0.7207 | 0.1013 | 0.0180 | 0.0426 | 0.1177 | 0.1205 | | 0.7361 | 35.0 | 525 | 0.7190 | 0.1004 | 0.0184 | 0.0434 | 0.1111 | 0.1245 | | 0.7566 | 36.0 | 540 | 0.7180 | 0.1023 | 0.0167 | 0.0424 | 0.1164 | 0.1245 | | 0.7443 | 37.0 | 555 | 0.7190 | 0.1012 | 0.0172 | 0.0413 | 0.1098 | 0.1285 | | 0.7485 | 38.0 | 570 | 0.7182 | 0.0986 | 0.0177 | 0.0423 | 0.1111 | 0.1205 | | 0.7394 | 39.0 | 585 | 0.7156 | 0.0982 | 0.0189 | 0.0414 | 0.1058 | 0.1245 | | 0.7515 | 40.0 | 600 | 0.7156 | 0.0991 | 0.0178 | 0.0413 | 0.1045 | 0.1285 | | 0.7328 | 41.0 | 615 | 0.7158 | 0.1013 | 0.0188 | 0.0413 | 0.1098 | 0.1285 | | 0.729 | 42.0 | 630 | 0.7154 | 0.1050 | 0.0186 | 0.0414 | 0.1151 | 0.1325 | | 0.7349 | 43.0 | 645 | 0.7155 | 0.1003 | 0.0189 | 0.0413 | 0.1111 | 0.1245 | | 0.7432 | 44.0 | 660 | 0.7135 | 0.0992 | 0.0169 | 0.0407 | 0.1032 | 0.1305 | | 0.7302 | 45.0 | 675 | 0.7118 | 0.0963 | 0.0191 | 0.0438 | 0.1045 | 0.1205 | | 0.7294 | 46.0 | 690 | 0.7105 | 0.0993 | 0.0200 | 0.0439 | 0.1098 | 0.1225 | | 0.7308 | 47.0 | 705 | 0.7108 | 0.0935 | 0.0170 | 0.0421 | 0.1085 | 0.1104 | | 0.7343 | 48.0 | 720 | 0.7112 | 0.0926 | 0.0175 | 0.0407 | 0.1085 | 0.1084 | | 0.736 | 49.0 | 735 | 0.7100 | 0.1055 | 0.0207 | 0.0442 | 0.1230 | 0.1245 | | 0.7147 | 50.0 | 750 | 0.7092 | 0.1065 | 0.0210 | 0.0458 | 0.1270 | 0.1225 | | 0.7399 | 51.0 | 765 | 0.7100 | 0.1003 | 0.0187 | 0.0426 | 0.1190 | 0.1165 | | 0.7275 | 52.0 | 780 | 0.7099 | 0.0997 | 0.0194 | 0.0432 | 0.1151 | 0.1185 | | 0.7336 | 53.0 | 795 | 0.7110 | 0.1005 | 0.0220 | 0.0485 | 0.1190 | 0.1145 | | 0.701 | 54.0 | 810 | 0.7071 | 0.1075 | 0.0213 | 0.0451 | 0.1217 | 0.1305 | | 0.7264 | 55.0 | 825 | 0.7068 | 0.1030 | 0.0200 | 0.0445 | 0.1230 | 0.1185 | | 0.7246 | 56.0 | 840 | 0.7075 | 0.1031 | 0.0210 | 0.0462 | 0.1204 | 0.1205 | | 0.7309 | 57.0 | 855 | 0.7067 | 0.0932 | 0.0195 | 0.0448 | 0.1085 | 0.1084 | | 0.7188 | 58.0 | 870 | 0.7051 | 0.1070 | 0.0217 | 0.0451 | 0.1204 | 0.1305 | | 0.7261 | 59.0 | 885 | 0.7051 | 0.1028 | 0.0201 | 0.0446 | 0.1204 | 0.1205 | | 0.7097 | 60.0 | 900 | 0.7057 | 0.1082 | 0.0219 | 0.0465 | 0.1270 | 0.1265 | | 0.7254 | 61.0 | 915 | 0.7062 | 0.1061 | 0.0240 | 0.0496 | 0.1283 | 0.1185 | | 0.7167 | 62.0 | 930 | 0.7048 | 0.1060 | 0.0241 | 0.0514 | 0.1257 | 0.1205 | | 0.7189 | 63.0 | 945 | 0.7047 | 0.1081 | 0.0239 | 0.0514 | 0.1310 | 0.1205 | | 0.7112 | 64.0 | 960 | 0.7055 | 0.1094 | 0.0262 | 0.0547 | 0.1389 | 0.1145 | | 0.7391 | 65.0 | 975 | 0.7037 | 0.1086 | 0.0222 | 0.0504 | 0.1349 | 0.1185 | | 0.7028 | 66.0 | 990 | 0.7040 | 0.1087 | 0.0257 | 0.0531 | 0.1376 | 0.1145 | | 0.7245 | 67.0 | 1005 | 0.7025 | 0.1086 | 0.0280 | 0.0579 | 0.1376 | 0.1124 | | 0.7232 | 68.0 | 1020 | 0.7030 | 0.1044 | 0.0220 | 0.0514 | 0.1323 | 0.1104 | | 0.6995 | 69.0 | 1035 | 0.7035 | 0.1084 | 0.0254 | 0.0535 | 0.1349 | 0.1165 | | 0.7253 | 70.0 | 1050 | 0.7041 | 0.1067 | 0.0253 | 0.0551 | 0.1362 | 0.1104 | | 0.7162 | 71.0 | 1065 | 0.7025 | 0.1087 | 0.0256 | 0.0531 | 0.1376 | 0.1145 | | 0.715 | 72.0 | 1080 | 0.7022 | 0.0993 | 0.0194 | 0.0453 | 0.1257 | 0.1064 | | 0.7204 | 73.0 | 1095 | 0.7026 | 0.1009 | 0.0225 | 0.0508 | 0.1336 | 0.1004 | | 0.7033 | 74.0 | 1110 | 0.7033 | 0.1146 | 0.0266 | 0.0549 | 0.1415 | 0.1245 | | 0.7007 | 75.0 | 1125 | 0.7017 | 0.1041 | 0.0227 | 0.0502 | 0.1336 | 0.1084 | | 0.7088 | 76.0 | 1140 | 0.7008 | 0.1041 | 0.0227 | 0.0502 | 0.1336 | 0.1084 | | 0.7167 | 77.0 | 1155 | 0.7019 | 0.1103 | 0.0240 | 0.0549 | 0.1415 | 0.1145 | | 0.6939 | 78.0 | 1170 | 0.7011 | 0.1070 | 0.0238 | 0.0508 | 0.1323 | 0.1165 | | 0.7034 | 79.0 | 1185 | 0.7008 | 0.1117 | 0.0239 | 0.0530 | 0.1376 | 0.1225 | | 0.6968 | 80.0 | 1200 | 0.6992 | 0.1144 | 0.0246 | 0.0521 | 0.1402 | 0.1265 | | 0.6893 | 81.0 | 1215 | 0.7005 | 0.1154 | 0.0242 | 0.0527 | 0.1468 | 0.1225 | | 0.7005 | 82.0 | 1230 | 0.7005 | 0.1196 | 0.0245 | 0.0511 | 0.1495 | 0.1305 | | 0.7202 | 83.0 | 1245 | 0.7019 | 0.1107 | 0.0225 | 0.0467 | 0.1310 | 0.1285 | | 0.7038 | 84.0 | 1260 | 0.7000 | 0.1031 | 0.0269 | 0.0516 | 0.1296 | 0.1084 | | 0.6901 | 85.0 | 1275 | 0.6994 | 0.1056 | 0.0240 | 0.0502 | 0.1349 | 0.1104 | | 0.6903 | 86.0 | 1290 | 0.6997 | 0.1123 | 0.0238 | 0.0484 | 0.1442 | 0.1185 | | 0.6901 | 87.0 | 1305 | 0.6988 | 0.1124 | 0.0243 | 0.0487 | 0.1442 | 0.1185 | | 0.6979 | 88.0 | 1320 | 0.6988 | 0.1133 | 0.0249 | 0.0499 | 0.1442 | 0.1205 | | 0.6988 | 89.0 | 1335 | 0.7002 | 0.1183 | 0.0281 | 0.0538 | 0.1468 | 0.1285 | | 0.694 | 90.0 | 1350 | 0.6994 | 0.1123 | 0.0282 | 0.0553 | 0.1455 | 0.1145 | | 0.6896 | 91.0 | 1365 | 0.6991 | 0.1134 | 0.0276 | 0.0533 | 0.1468 | 0.1165 | | 0.6972 | 92.0 | 1380 | 0.6995 | 0.1077 | 0.0248 | 0.0499 | 0.1402 | 0.1104 | | 0.677 | 93.0 | 1395 | 0.7001 | 0.1171 | 0.0271 | 0.0529 | 0.1442 | 0.1285 | | 0.6749 | 94.0 | 1410 | 0.6990 | 0.1132 | 0.0242 | 0.0515 | 0.1455 | 0.1185 | | 0.6946 | 95.0 | 1425 | 0.6990 | 0.1112 | 0.0251 | 0.0520 | 0.1442 | 0.1145 | | 0.6979 | 96.0 | 1440 | 0.7006 | 0.1214 | 0.0250 | 0.0533 | 0.1534 | 0.1305 | | 0.6955 | 97.0 | 1455 | 0.6995 | 0.1176 | 0.0254 | 0.0523 | 0.1521 | 0.1225 | | 0.6857 | 98.0 | 1470 | 0.6994 | 0.1124 | 0.0269 | 0.0544 | 0.1323 | 0.1285 | | 0.7165 | 99.0 | 1485 | 0.6976 | 0.1134 | 0.0254 | 0.0496 | 0.1362 | 0.1285 | | 0.6958 | 100.0 | 1500 | 0.6970 | 0.1162 | 0.0272 | 0.0549 | 0.1415 | 0.1285 | | 0.6853 | 101.0 | 1515 | 0.6962 | 0.1178 | 0.0269 | 0.0547 | 0.1455 | 0.1285 | | 0.6793 | 102.0 | 1530 | 0.6952 | 0.1185 | 0.0284 | 0.0579 | 0.1521 | 0.1225 | | 0.6861 | 103.0 | 1545 | 0.6968 | 0.1184 | 0.0295 | 0.0582 | 0.1495 | 0.1245 | | 0.6865 | 104.0 | 1560 | 0.6975 | 0.1116 | 0.0249 | 0.0486 | 0.1402 | 0.1205 | | 0.6845 | 105.0 | 1575 | 0.6983 | 0.1120 | 0.0267 | 0.0536 | 0.1415 | 0.1185 | | 0.6905 | 106.0 | 1590 | 0.6978 | 0.1108 | 0.0249 | 0.0486 | 0.1402 | 0.1185 | | 0.6931 | 107.0 | 1605 | 0.6977 | 0.1187 | 0.0277 | 0.0529 | 0.1481 | 0.1285 | | 0.6752 | 108.0 | 1620 | 0.6977 | 0.1123 | 0.0250 | 0.0501 | 0.1415 | 0.1205 | | 0.679 | 109.0 | 1635 | 0.6979 | 0.1169 | 0.0244 | 0.0509 | 0.1468 | 0.1265 | | 0.6923 | 110.0 | 1650 | 0.6973 | 0.1155 | 0.0284 | 0.0544 | 0.1415 | 0.1265 | | 0.6911 | 111.0 | 1665 | 0.6977 | 0.1098 | 0.0254 | 0.0484 | 0.1376 | 0.1185 | | 0.6765 | 112.0 | 1680 | 0.6989 | 0.1152 | 0.0251 | 0.0501 | 0.1468 | 0.1225 | | 0.6794 | 113.0 | 1695 | 0.6973 | 0.1200 | 0.0289 | 0.0566 | 0.1481 | 0.1305 | | 0.6861 | 114.0 | 1710 | 0.6964 | 0.1200 | 0.0286 | 0.0565 | 0.1481 | 0.1305 | | 0.6902 | 115.0 | 1725 | 0.6956 | 0.1195 | 0.0294 | 0.0564 | 0.1468 | 0.1305 | | 0.6887 | 116.0 | 1740 | 0.6955 | 0.1182 | 0.0302 | 0.0562 | 0.1455 | 0.1285 | | 0.677 | 117.0 | 1755 | 0.6956 | 0.1217 | 0.0307 | 0.0585 | 0.1495 | 0.1325 | | 0.6881 | 118.0 | 1770 | 0.6961 | 0.1122 | 0.0288 | 0.0581 | 0.1402 | 0.1185 | | 0.6792 | 119.0 | 1785 | 0.6970 | 0.1108 | 0.0286 | 0.0582 | 0.1389 | 0.1165 | | 0.6732 | 120.0 | 1800 | 0.6961 | 0.1119 | 0.0284 | 0.0582 | 0.1415 | 0.1165 | | 0.6703 | 121.0 | 1815 | 0.6955 | 0.1168 | 0.0302 | 0.0580 | 0.1455 | 0.1245 | | 0.6906 | 122.0 | 1830 | 0.6961 | 0.1168 | 0.0309 | 0.0567 | 0.1415 | 0.1285 | | 0.6914 | 123.0 | 1845 | 0.6966 | 0.1192 | 0.0309 | 0.0573 | 0.1455 | 0.1305 | | 0.6819 | 124.0 | 1860 | 0.6980 | 0.1102 | 0.0335 | 0.0603 | 0.1296 | 0.1225 | | 0.6777 | 125.0 | 1875 | 0.6977 | 0.1104 | 0.0317 | 0.0586 | 0.1310 | 0.1225 | | 0.6681 | 126.0 | 1890 | 0.6983 | 0.1121 | 0.0321 | 0.0590 | 0.1310 | 0.1265 | | 0.6761 | 127.0 | 1905 | 0.7000 | 0.1038 | 0.0286 | 0.0509 | 0.1151 | 0.1245 | | 0.6781 | 128.0 | 1920 | 0.6980 | 0.1141 | 0.0357 | 0.0621 | 0.1243 | 0.1365 | | 0.6757 | 129.0 | 1935 | 0.6968 | 0.1191 | 0.0308 | 0.0582 | 0.1389 | 0.1365 | | 0.6701 | 130.0 | 1950 | 0.6989 | 0.1143 | 0.0335 | 0.0586 | 0.1362 | 0.1265 | | 0.6761 | 131.0 | 1965 | 0.6994 | 0.1140 | 0.0347 | 0.0592 | 0.1349 | 0.1265 | | 0.6798 | 132.0 | 1980 | 0.6960 | 0.1203 | 0.0298 | 0.0592 | 0.1521 | 0.1265 | | 0.6922 | 133.0 | 1995 | 0.6961 | 0.1190 | 0.0281 | 0.0579 | 0.1495 | 0.1265 | | 0.6626 | 134.0 | 2010 | 0.6976 | 0.1178 | 0.0296 | 0.0555 | 0.1468 | 0.1265 | | 0.6747 | 135.0 | 2025 | 0.6978 | 0.1219 | 0.0304 | 0.0585 | 0.1521 | 0.1305 | | 0.6765 | 136.0 | 2040 | 0.7004 | 0.1198 | 0.0325 | 0.0583 | 0.1402 | 0.1365 | | 0.6607 | 137.0 | 2055 | 0.7025 | 0.1169 | 0.0335 | 0.0578 | 0.1349 | 0.1345 | | 0.6888 | 138.0 | 2070 | 0.6998 | 0.1180 | 0.0357 | 0.0613 | 0.1323 | 0.1386 | | 0.6825 | 139.0 | 2085 | 0.6987 | 0.1197 | 0.0325 | 0.0605 | 0.1455 | 0.1305 | | 0.6733 | 140.0 | 2100 | 0.6989 | 0.1135 | 0.0318 | 0.0606 | 0.1362 | 0.1245 | | 0.6745 | 141.0 | 2115 | 0.6998 | 0.1106 | 0.0312 | 0.0580 | 0.1336 | 0.1205 | | 0.6955 | 142.0 | 2130 | 0.7006 | 0.1102 | 0.0316 | 0.0565 | 0.1270 | 0.1265 | | 0.6717 | 143.0 | 2145 | 0.6997 | 0.1174 | 0.0295 | 0.0567 | 0.1455 | 0.1265 | | 0.6883 | 144.0 | 2160 | 0.6998 | 0.1182 | 0.0329 | 0.0608 | 0.1415 | 0.1305 | | 0.669 | 145.0 | 2175 | 0.7001 | 0.1181 | 0.0341 | 0.0610 | 0.1389 | 0.1325 | | 0.6803 | 146.0 | 2190 | 0.7013 | 0.1158 | 0.0342 | 0.0619 | 0.1349 | 0.1305 | | 0.6748 | 147.0 | 2205 | 0.6987 | 0.1191 | 0.0336 | 0.0608 | 0.1415 | 0.1325 | | 0.6673 | 148.0 | 2220 | 0.6974 | 0.1183 | 0.0325 | 0.0594 | 0.1402 | 0.1325 | | 0.6679 | 149.0 | 2235 | 0.6976 | 0.1204 | 0.0342 | 0.0604 | 0.1389 | 0.1386 | | 0.6614 | 150.0 | 2250 | 0.7008 | 0.1131 | 0.0330 | 0.0573 | 0.1296 | 0.1305 | | 0.6684 | 151.0 | 2265 | 0.6991 | 0.1210 | 0.0325 | 0.0572 | 0.1415 | 0.1386 | | 0.6757 | 152.0 | 2280 | 0.6990 | 0.1206 | 0.0326 | 0.0588 | 0.1402 | 0.1386 | | 0.6644 | 153.0 | 2295 | 0.6971 | 0.1184 | 0.0312 | 0.0589 | 0.1429 | 0.1305 | | 0.6727 | 154.0 | 2310 | 0.6967 | 0.1197 | 0.0342 | 0.0608 | 0.1389 | 0.1365 | | 0.6795 | 155.0 | 2325 | 0.6985 | 0.1145 | 0.0347 | 0.0621 | 0.1296 | 0.1325 | | 0.697 | 156.0 | 2340 | 0.6978 | 0.1205 | 0.0355 | 0.0625 | 0.1402 | 0.1365 | | 0.6552 | 157.0 | 2355 | 0.6970 | 0.1181 | 0.0331 | 0.0593 | 0.1376 | 0.1345 | | 0.6786 | 158.0 | 2370 | 0.6974 | 0.1204 | 0.0339 | 0.0607 | 0.1389 | 0.1386 | | 0.6775 | 159.0 | 2385 | 0.6973 | 0.1204 | 0.0335 | 0.0605 | 0.1389 | 0.1386 | | 0.668 | 160.0 | 2400 | 0.6970 | 0.1204 | 0.0339 | 0.0607 | 0.1389 | 0.1386 | | 0.6597 | 161.0 | 2415 | 0.6966 | 0.1208 | 0.0357 | 0.0623 | 0.1389 | 0.1386 | | 0.6726 | 162.0 | 2430 | 0.6963 | 0.1188 | 0.0335 | 0.0605 | 0.1389 | 0.1345 | | 0.6861 | 163.0 | 2445 | 0.6983 | 0.1207 | 0.0352 | 0.0621 | 0.1389 | 0.1386 | | 0.675 | 164.0 | 2460 | 0.6988 | 0.1207 | 0.0352 | 0.0621 | 0.1389 | 0.1386 | | 0.6579 | 165.0 | 2475 | 0.6981 | 0.1207 | 0.0352 | 0.0621 | 0.1389 | 0.1386 | | 0.657 | 166.0 | 2490 | 0.6984 | 0.1207 | 0.0352 | 0.0621 | 0.1389 | 0.1386 | | 0.6651 | 167.0 | 2505 | 0.6981 | 0.1198 | 0.0363 | 0.0627 | 0.1362 | 0.1386 | | 0.6662 | 168.0 | 2520 | 0.6978 | 0.1198 | 0.0359 | 0.0625 | 0.1362 | 0.1386 | | 0.6565 | 169.0 | 2535 | 0.6968 | 0.1198 | 0.0359 | 0.0625 | 0.1362 | 0.1386 | | 0.6723 | 170.0 | 2550 | 0.6974 | 0.1198 | 0.0359 | 0.0625 | 0.1362 | 0.1386 | | 0.6793 | 171.0 | 2565 | 0.6977 | 0.1188 | 0.0362 | 0.0630 | 0.1296 | 0.1426 | | 0.6731 | 172.0 | 2580 | 0.6975 | 0.1211 | 0.0375 | 0.0639 | 0.1349 | 0.1426 | | 0.676 | 173.0 | 2595 | 0.6964 | 0.1205 | 0.0370 | 0.0631 | 0.1336 | 0.1426 | | 0.664 | 174.0 | 2610 | 0.6961 | 0.1163 | 0.0335 | 0.0593 | 0.1310 | 0.1365 | | 0.6598 | 175.0 | 2625 | 0.6980 | 0.1211 | 0.0375 | 0.0639 | 0.1349 | 0.1426 | | 0.6691 | 176.0 | 2640 | 0.6994 | 0.1231 | 0.0368 | 0.0631 | 0.1402 | 0.1426 | | 0.6636 | 177.0 | 2655 | 0.6981 | 0.1161 | 0.0366 | 0.0624 | 0.1310 | 0.1345 | | 0.6606 | 178.0 | 2670 | 0.6969 | 0.1208 | 0.0357 | 0.0623 | 0.1389 | 0.1386 | | 0.6807 | 179.0 | 2685 | 0.6964 | 0.1193 | 0.0326 | 0.0588 | 0.1389 | 0.1365 | | 0.6513 | 180.0 | 2700 | 0.6984 | 0.1180 | 0.0327 | 0.0590 | 0.1376 | 0.1345 | | 0.6721 | 181.0 | 2715 | 0.6983 | 0.1167 | 0.0313 | 0.0578 | 0.1349 | 0.1345 | | 0.6673 | 182.0 | 2730 | 0.6986 | 0.1238 | 0.0372 | 0.0639 | 0.1415 | 0.1426 | | 0.6633 | 183.0 | 2745 | 0.6978 | 0.1238 | 0.0372 | 0.0639 | 0.1415 | 0.1426 | | 0.6568 | 184.0 | 2760 | 0.6983 | 0.1169 | 0.0362 | 0.0630 | 0.1310 | 0.1365 | | 0.6539 | 185.0 | 2775 | 0.6981 | 0.1237 | 0.0368 | 0.0637 | 0.1415 | 0.1426 | | 0.6618 | 186.0 | 2790 | 0.6973 | 0.1237 | 0.0369 | 0.0637 | 0.1415 | 0.1426 | | 0.6484 | 187.0 | 2805 | 0.6974 | 0.1195 | 0.0360 | 0.0629 | 0.1376 | 0.1365 | | 0.6707 | 188.0 | 2820 | 0.6974 | 0.1237 | 0.0368 | 0.0637 | 0.1415 | 0.1426 | | 0.6775 | 189.0 | 2835 | 0.6974 | 0.1211 | 0.0376 | 0.0635 | 0.1349 | 0.1426 | | 0.6678 | 190.0 | 2850 | 0.6979 | 0.1240 | 0.0360 | 0.0620 | 0.1429 | 0.1426 | | 0.6721 | 191.0 | 2865 | 0.6983 | 0.1240 | 0.0358 | 0.0620 | 0.1429 | 0.1426 | | 0.6657 | 192.0 | 2880 | 0.6984 | 0.1228 | 0.0375 | 0.0644 | 0.1349 | 0.1466 | | 0.6613 | 193.0 | 2895 | 0.6986 | 0.1206 | 0.0359 | 0.0630 | 0.1362 | 0.1406 | | 0.6515 | 194.0 | 2910 | 0.6983 | 0.1215 | 0.0363 | 0.0632 | 0.1362 | 0.1426 | | 0.6688 | 195.0 | 2925 | 0.6990 | 0.1198 | 0.0361 | 0.0627 | 0.1362 | 0.1386 | | 0.6697 | 196.0 | 2940 | 0.6988 | 0.1224 | 0.0363 | 0.0621 | 0.1389 | 0.1426 | | 0.6688 | 197.0 | 2955 | 0.6981 | 0.1200 | 0.0348 | 0.0608 | 0.1376 | 0.1386 | | 0.6529 | 198.0 | 2970 | 0.6986 | 0.1198 | 0.0361 | 0.0627 | 0.1362 | 0.1386 | | 0.6512 | 199.0 | 2985 | 0.6977 | 0.1220 | 0.0377 | 0.0644 | 0.1349 | 0.1446 | | 0.6541 | 200.0 | 3000 | 0.6977 | 0.1220 | 0.0377 | 0.0644 | 0.1349 | 0.1446 | | 0.6549 | 201.0 | 3015 | 0.6989 | 0.1193 | 0.0375 | 0.0611 | 0.1310 | 0.1426 | | 0.6547 | 202.0 | 3030 | 0.6981 | 0.1215 | 0.0387 | 0.0635 | 0.1336 | 0.1446 | | 0.6612 | 203.0 | 3045 | 0.6975 | 0.1183 | 0.0349 | 0.0616 | 0.1310 | 0.1406 | | 0.6462 | 204.0 | 3060 | 0.6979 | 0.1163 | 0.0334 | 0.0593 | 0.1310 | 0.1365 | | 0.672 | 205.0 | 3075 | 0.6978 | 0.1163 | 0.0334 | 0.0593 | 0.1310 | 0.1365 | | 0.6576 | 206.0 | 3090 | 0.6969 | 0.1153 | 0.0324 | 0.0583 | 0.1349 | 0.1305 | | 0.6603 | 207.0 | 3105 | 0.6978 | 0.1216 | 0.0333 | 0.0598 | 0.1402 | 0.1406 | | 0.6427 | 208.0 | 3120 | 0.6982 | 0.1194 | 0.0364 | 0.0607 | 0.1296 | 0.1446 | | 0.6634 | 209.0 | 3135 | 0.6981 | 0.1209 | 0.0352 | 0.0610 | 0.1336 | 0.1446 | | 0.6514 | 210.0 | 3150 | 0.6971 | 0.1203 | 0.0357 | 0.0602 | 0.1323 | 0.1446 | | 0.6567 | 211.0 | 3165 | 0.6976 | 0.1191 | 0.0340 | 0.0607 | 0.1336 | 0.1406 | | 0.659 | 212.0 | 3180 | 0.6982 | 0.1203 | 0.0356 | 0.0602 | 0.1323 | 0.1446 | | 0.6629 | 213.0 | 3195 | 0.6973 | 0.1189 | 0.0340 | 0.0609 | 0.1349 | 0.1386 | | 0.6646 | 214.0 | 3210 | 0.6963 | 0.1125 | 0.0314 | 0.0554 | 0.1270 | 0.1325 | | 0.6602 | 215.0 | 3225 | 0.6960 | 0.1175 | 0.0342 | 0.0607 | 0.1336 | 0.1365 | | 0.6447 | 216.0 | 3240 | 0.6970 | 0.1175 | 0.0342 | 0.0607 | 0.1336 | 0.1365 | | 0.6638 | 217.0 | 3255 | 0.6978 | 0.1229 | 0.0368 | 0.0635 | 0.1376 | 0.1446 | | 0.6473 | 218.0 | 3270 | 0.6988 | 0.1207 | 0.0368 | 0.0626 | 0.1323 | 0.1446 | | 0.641 | 219.0 | 3285 | 0.6997 | 0.1214 | 0.0380 | 0.0632 | 0.1336 | 0.1446 | | 0.6367 | 220.0 | 3300 | 0.7003 | 0.1319 | 0.0394 | 0.0635 | 0.1455 | 0.1586 | | 0.6643 | 221.0 | 3315 | 0.6991 | 0.1229 | 0.0368 | 0.0635 | 0.1376 | 0.1446 | | 0.6433 | 222.0 | 3330 | 0.6978 | 0.1189 | 0.0340 | 0.0607 | 0.1349 | 0.1386 | | 0.6586 | 223.0 | 3345 | 0.6970 | 0.1241 | 0.0349 | 0.0619 | 0.1455 | 0.1406 | | 0.6575 | 224.0 | 3360 | 0.6984 | 0.1151 | 0.0341 | 0.0601 | 0.1257 | 0.1386 | | 0.6568 | 225.0 | 3375 | 0.6987 | 0.1255 | 0.0365 | 0.0635 | 0.1442 | 0.1446 | | 0.6415 | 226.0 | 3390 | 0.6976 | 0.1230 | 0.0324 | 0.0588 | 0.1442 | 0.1406 | | 0.6564 | 227.0 | 3405 | 0.6978 | 0.1192 | 0.0314 | 0.0565 | 0.1415 | 0.1345 | | 0.6559 | 228.0 | 3420 | 0.6987 | 0.1233 | 0.0340 | 0.0600 | 0.1402 | 0.1446 | | 0.6614 | 229.0 | 3435 | 0.6989 | 0.1203 | 0.0366 | 0.0617 | 0.1336 | 0.1426 | | 0.6491 | 230.0 | 3450 | 0.6986 | 0.1187 | 0.0366 | 0.0617 | 0.1336 | 0.1386 | | 0.6619 | 231.0 | 3465 | 0.6982 | 0.1187 | 0.0366 | 0.0617 | 0.1336 | 0.1386 | | 0.6421 | 232.0 | 3480 | 0.6998 | 0.1216 | 0.0366 | 0.0617 | 0.1349 | 0.1446 | | 0.6421 | 233.0 | 3495 | 0.6997 | 0.1216 | 0.0366 | 0.0617 | 0.1349 | 0.1446 | | 0.6716 | 234.0 | 3510 | 0.7009 | 0.1244 | 0.0376 | 0.0619 | 0.1376 | 0.1486 | | 0.6493 | 235.0 | 3525 | 0.6998 | 0.1216 | 0.0366 | 0.0617 | 0.1349 | 0.1446 | | 0.6492 | 236.0 | 3540 | 0.6983 | 0.1231 | 0.0354 | 0.0619 | 0.1389 | 0.1446 | | 0.6444 | 237.0 | 3555 | 0.6984 | 0.1216 | 0.0366 | 0.0617 | 0.1349 | 0.1446 | | 0.6527 | 238.0 | 3570 | 0.6989 | 0.1203 | 0.0366 | 0.0617 | 0.1336 | 0.1426 | | 0.6542 | 239.0 | 3585 | 0.6988 | 0.1218 | 0.0354 | 0.0619 | 0.1376 | 0.1426 | | 0.657 | 240.0 | 3600 | 0.6992 | 0.1194 | 0.0365 | 0.0607 | 0.1296 | 0.1446 | | 0.6466 | 241.0 | 3615 | 0.6988 | 0.1194 | 0.0365 | 0.0607 | 0.1296 | 0.1446 | | 0.6532 | 242.0 | 3630 | 0.6989 | 0.1216 | 0.0366 | 0.0617 | 0.1349 | 0.1446 | | 0.6476 | 243.0 | 3645 | 0.6991 | 0.1216 | 0.0366 | 0.0617 | 0.1349 | 0.1446 | | 0.6551 | 244.0 | 3660 | 0.6997 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | | 0.6481 | 245.0 | 3675 | 0.6998 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | | 0.6577 | 246.0 | 3690 | 0.6983 | 0.1216 | 0.0366 | 0.0617 | 0.1349 | 0.1446 | | 0.6513 | 247.0 | 3705 | 0.6982 | 0.1231 | 0.0354 | 0.0619 | 0.1389 | 0.1446 | | 0.6573 | 248.0 | 3720 | 0.6980 | 0.1231 | 0.0354 | 0.0619 | 0.1389 | 0.1446 | | 0.6453 | 249.0 | 3735 | 0.6983 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | | 0.6644 | 250.0 | 3750 | 0.6986 | 0.1222 | 0.0377 | 0.0608 | 0.1323 | 0.1486 | | 0.6411 | 251.0 | 3765 | 0.6979 | 0.1222 | 0.0377 | 0.0608 | 0.1323 | 0.1486 | | 0.6487 | 252.0 | 3780 | 0.6982 | 0.1222 | 0.0377 | 0.0608 | 0.1323 | 0.1486 | | 0.6523 | 253.0 | 3795 | 0.6978 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | | 0.6456 | 254.0 | 3810 | 0.6981 | 0.1222 | 0.0377 | 0.0608 | 0.1323 | 0.1486 | | 0.6523 | 255.0 | 3825 | 0.6975 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | | 0.642 | 256.0 | 3840 | 0.6967 | 0.1216 | 0.0366 | 0.0617 | 0.1349 | 0.1446 | | 0.6594 | 257.0 | 3855 | 0.6967 | 0.1208 | 0.0341 | 0.0594 | 0.1402 | 0.1386 | | 0.6372 | 258.0 | 3870 | 0.6972 | 0.1216 | 0.0366 | 0.0617 | 0.1349 | 0.1446 | | 0.6539 | 259.0 | 3885 | 0.6972 | 0.1231 | 0.0354 | 0.0619 | 0.1389 | 0.1446 | | 0.6599 | 260.0 | 3900 | 0.6971 | 0.1208 | 0.0341 | 0.0594 | 0.1402 | 0.1386 | | 0.6504 | 261.0 | 3915 | 0.6973 | 0.1190 | 0.0343 | 0.0596 | 0.1376 | 0.1365 | | 0.6505 | 262.0 | 3930 | 0.6972 | 0.1217 | 0.0341 | 0.0596 | 0.1442 | 0.1365 | | 0.6475 | 263.0 | 3945 | 0.6969 | 0.1233 | 0.0341 | 0.0596 | 0.1442 | 0.1406 | | 0.6608 | 264.0 | 3960 | 0.6970 | 0.1217 | 0.0341 | 0.0596 | 0.1442 | 0.1365 | | 0.6468 | 265.0 | 3975 | 0.6975 | 0.1233 | 0.0341 | 0.0596 | 0.1442 | 0.1406 | | 0.648 | 266.0 | 3990 | 0.6976 | 0.1233 | 0.0341 | 0.0596 | 0.1442 | 0.1406 | | 0.6277 | 267.0 | 4005 | 0.6980 | 0.1240 | 0.0380 | 0.0632 | 0.1402 | 0.1446 | | 0.6564 | 268.0 | 4020 | 0.6983 | 0.1240 | 0.0380 | 0.0632 | 0.1402 | 0.1446 | | 0.6585 | 269.0 | 4035 | 0.6983 | 0.1240 | 0.0380 | 0.0632 | 0.1402 | 0.1446 | | 0.6334 | 270.0 | 4050 | 0.6982 | 0.1240 | 0.0380 | 0.0632 | 0.1402 | 0.1446 | | 0.6517 | 271.0 | 4065 | 0.6980 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | | 0.65 | 272.0 | 4080 | 0.6975 | 0.1216 | 0.0366 | 0.0617 | 0.1349 | 0.1446 | | 0.6495 | 273.0 | 4095 | 0.6971 | 0.1217 | 0.0341 | 0.0596 | 0.1442 | 0.1365 | | 0.6347 | 274.0 | 4110 | 0.6968 | 0.1219 | 0.0328 | 0.0577 | 0.1455 | 0.1365 | | 0.6374 | 275.0 | 4125 | 0.6966 | 0.1217 | 0.0341 | 0.0596 | 0.1442 | 0.1365 | | 0.6454 | 276.0 | 4140 | 0.6965 | 0.1217 | 0.0341 | 0.0596 | 0.1442 | 0.1365 | | 0.6653 | 277.0 | 4155 | 0.6967 | 0.1200 | 0.0366 | 0.0617 | 0.1349 | 0.1406 | | 0.652 | 278.0 | 4170 | 0.6971 | 0.1216 | 0.0366 | 0.0617 | 0.1349 | 0.1446 | | 0.6457 | 279.0 | 4185 | 0.6972 | 0.1216 | 0.0366 | 0.0617 | 0.1349 | 0.1446 | | 0.6472 | 280.0 | 4200 | 0.6973 | 0.1216 | 0.0366 | 0.0617 | 0.1349 | 0.1446 | | 0.6543 | 281.0 | 4215 | 0.6975 | 0.1216 | 0.0366 | 0.0617 | 0.1349 | 0.1446 | | 0.6435 | 282.0 | 4230 | 0.6975 | 0.1216 | 0.0366 | 0.0617 | 0.1349 | 0.1446 | | 0.6453 | 283.0 | 4245 | 0.6977 | 0.1216 | 0.0366 | 0.0617 | 0.1349 | 0.1446 | | 0.6626 | 284.0 | 4260 | 0.6978 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | | 0.6522 | 285.0 | 4275 | 0.6980 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | | 0.6578 | 286.0 | 4290 | 0.6980 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | | 0.6544 | 287.0 | 4305 | 0.6978 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | | 0.6513 | 288.0 | 4320 | 0.6977 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | | 0.6475 | 289.0 | 4335 | 0.6977 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | | 0.6303 | 290.0 | 4350 | 0.6977 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | | 0.6376 | 291.0 | 4365 | 0.6977 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | | 0.632 | 292.0 | 4380 | 0.6977 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | | 0.6526 | 293.0 | 4395 | 0.6978 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | | 0.6582 | 294.0 | 4410 | 0.6978 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | | 0.6451 | 295.0 | 4425 | 0.6978 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | | 0.6485 | 296.0 | 4440 | 0.6977 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | | 0.6525 | 297.0 | 4455 | 0.6977 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | | 0.6452 | 298.0 | 4470 | 0.6977 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | | 0.6589 | 299.0 | 4485 | 0.6977 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | | 0.6451 | 300.0 | 4500 | 0.6977 | 0.1214 | 0.0382 | 0.0632 | 0.1336 | 0.1446 | ### Framework versions - Transformers 4.31.0 - Pytorch 2.0.1 - Datasets 2.14.4 - Tokenizers 0.13.3