--- 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_2 results: [] --- # codet5p-770m-py-sanitized-codebleu-1-True-5e-05-0.1-lora-layer_2 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: 0.6793 - Codebleu: 0.1069 - Ngram Match Score: 0.0215 - Weighted Ngram Match Score: 0.0442 - Syntax Match Score: 0.1204 - Dataflow Match Score: 0.1305 ## 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 | |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------------:|:--------------------------:|:------------------:|:--------------------:| | 0.9782 | 1.0 | 15 | 0.9243 | 0.0072 | 0.0000 | 0.0000 | 0.0079 | 0.0100 | | 0.9653 | 2.0 | 30 | 0.9221 | 0.0072 | 0.0000 | 0.0000 | 0.0079 | 0.0100 | | 0.9713 | 3.0 | 45 | 0.9171 | 0.0080 | 0.0000 | 0.0000 | 0.0079 | 0.0120 | | 0.9332 | 4.0 | 60 | 0.9059 | 0.0126 | 0.0000 | 0.0008 | 0.0093 | 0.0221 | | 0.9336 | 5.0 | 75 | 0.8843 | 0.0532 | 0.0023 | 0.0239 | 0.0582 | 0.0683 | | 0.9203 | 6.0 | 90 | 0.8627 | 0.0820 | 0.0153 | 0.0382 | 0.0992 | 0.0924 | | 0.8979 | 7.0 | 105 | 0.8524 | 0.1026 | 0.0187 | 0.0473 | 0.1257 | 0.1145 | | 0.8653 | 8.0 | 120 | 0.8454 | 0.1014 | 0.0212 | 0.0508 | 0.1270 | 0.1084 | | 0.8561 | 9.0 | 135 | 0.8391 | 0.0989 | 0.0227 | 0.0510 | 0.1243 | 0.1044 | | 0.8619 | 10.0 | 150 | 0.8324 | 0.0979 | 0.0231 | 0.0510 | 0.1217 | 0.1044 | | 0.8537 | 11.0 | 165 | 0.8247 | 0.1042 | 0.0244 | 0.0522 | 0.1389 | 0.1024 | | 0.862 | 12.0 | 180 | 0.8140 | 0.1032 | 0.0251 | 0.0520 | 0.1362 | 0.1024 | | 0.8357 | 13.0 | 195 | 0.8044 | 0.1004 | 0.0234 | 0.0520 | 0.1217 | 0.1104 | | 0.8185 | 14.0 | 210 | 0.7950 | 0.1006 | 0.0230 | 0.0520 | 0.1243 | 0.1084 | | 0.834 | 15.0 | 225 | 0.7855 | 0.1019 | 0.0223 | 0.0521 | 0.1257 | 0.1104 | | 0.8433 | 16.0 | 240 | 0.7762 | 0.1013 | 0.0216 | 0.0521 | 0.1243 | 0.1104 | | 0.8241 | 17.0 | 255 | 0.7656 | 0.0940 | 0.0155 | 0.0405 | 0.1124 | 0.1084 | | 0.7977 | 18.0 | 270 | 0.7555 | 0.0974 | 0.0151 | 0.0405 | 0.1190 | 0.1104 | | 0.8031 | 19.0 | 285 | 0.7494 | 0.1009 | 0.0179 | 0.0469 | 0.1257 | 0.1104 | | 0.7928 | 20.0 | 300 | 0.7463 | 0.1016 | 0.0187 | 0.0470 | 0.1230 | 0.1145 | | 0.7781 | 21.0 | 315 | 0.7415 | 0.0964 | 0.0177 | 0.0466 | 0.1124 | 0.1124 | | 0.7852 | 22.0 | 330 | 0.7375 | 0.0886 | 0.0138 | 0.0423 | 0.1071 | 0.1004 | | 0.7763 | 23.0 | 345 | 0.7350 | 0.0907 | 0.0132 | 0.0424 | 0.1124 | 0.1004 | | 0.7818 | 24.0 | 360 | 0.7323 | 0.0916 | 0.0125 | 0.0411 | 0.1151 | 0.1004 | | 0.7999 | 25.0 | 375 | 0.7287 | 0.0905 | 0.0130 | 0.0410 | 0.1124 | 0.1004 | | 0.7655 | 26.0 | 390 | 0.7270 | 0.0916 | 0.0129 | 0.0413 | 0.1151 | 0.1004 | | 0.7594 | 27.0 | 405 | 0.7246 | 0.0913 | 0.0127 | 0.0411 | 0.1164 | 0.0984 | | 0.7688 | 28.0 | 420 | 0.7222 | 0.0932 | 0.0130 | 0.0410 | 0.1151 | 0.1044 | | 0.7516 | 29.0 | 435 | 0.7209 | 0.0988 | 0.0151 | 0.0498 | 0.1243 | 0.1064 | | 0.7447 | 30.0 | 450 | 0.7200 | 0.0960 | 0.0146 | 0.0484 | 0.1177 | 0.1064 | | 0.7525 | 31.0 | 465 | 0.7183 | 0.1018 | 0.0145 | 0.0485 | 0.1283 | 0.1104 | | 0.7504 | 32.0 | 480 | 0.7168 | 0.1057 | 0.0155 | 0.0489 | 0.1336 | 0.1145 | | 0.7377 | 33.0 | 495 | 0.7150 | 0.0970 | 0.0154 | 0.0506 | 0.1257 | 0.1004 | | 0.7563 | 34.0 | 510 | 0.7133 | 0.1053 | 0.0174 | 0.0519 | 0.1336 | 0.1124 | | 0.7383 | 35.0 | 525 | 0.7125 | 0.1036 | 0.0167 | 0.0514 | 0.1296 | 0.1124 | | 0.7507 | 36.0 | 540 | 0.7108 | 0.1004 | 0.0185 | 0.0524 | 0.1310 | 0.1024 | | 0.7406 | 37.0 | 555 | 0.7107 | 0.1013 | 0.0173 | 0.0492 | 0.1323 | 0.1044 | | 0.7472 | 38.0 | 570 | 0.7101 | 0.1107 | 0.0202 | 0.0519 | 0.1402 | 0.1185 | | 0.7394 | 39.0 | 585 | 0.7085 | 0.1107 | 0.0206 | 0.0519 | 0.1402 | 0.1185 | | 0.7496 | 40.0 | 600 | 0.7077 | 0.1003 | 0.0192 | 0.0505 | 0.1270 | 0.1064 | | 0.731 | 41.0 | 615 | 0.7073 | 0.1031 | 0.0225 | 0.0565 | 0.1296 | 0.1084 | | 0.7276 | 42.0 | 630 | 0.7064 | 0.1145 | 0.0213 | 0.0520 | 0.1455 | 0.1225 | | 0.7353 | 43.0 | 645 | 0.7052 | 0.1156 | 0.0241 | 0.0566 | 0.1402 | 0.1285 | | 0.7431 | 44.0 | 660 | 0.7047 | 0.1202 | 0.0253 | 0.0571 | 0.1495 | 0.1305 | | 0.7303 | 45.0 | 675 | 0.7038 | 0.1175 | 0.0248 | 0.0567 | 0.1429 | 0.1305 | | 0.7253 | 46.0 | 690 | 0.7036 | 0.1012 | 0.0214 | 0.0538 | 0.1217 | 0.1124 | | 0.7301 | 47.0 | 705 | 0.7025 | 0.1128 | 0.0248 | 0.0572 | 0.1389 | 0.1225 | | 0.7281 | 48.0 | 720 | 0.7031 | 0.1117 | 0.0249 | 0.0568 | 0.1362 | 0.1225 | | 0.7315 | 49.0 | 735 | 0.7030 | 0.1019 | 0.0247 | 0.0553 | 0.1243 | 0.1104 | | 0.7144 | 50.0 | 750 | 0.7024 | 0.1022 | 0.0233 | 0.0539 | 0.1257 | 0.1104 | | 0.7411 | 51.0 | 765 | 0.7024 | 0.1057 | 0.0249 | 0.0557 | 0.1296 | 0.1145 | | 0.7296 | 52.0 | 780 | 0.7015 | 0.1066 | 0.0250 | 0.0570 | 0.1376 | 0.1084 | | 0.7291 | 53.0 | 795 | 0.7012 | 0.1030 | 0.0237 | 0.0538 | 0.1257 | 0.1124 | | 0.6991 | 54.0 | 810 | 0.6998 | 0.1089 | 0.0232 | 0.0493 | 0.1336 | 0.1205 | | 0.7239 | 55.0 | 825 | 0.6994 | 0.1055 | 0.0230 | 0.0480 | 0.1296 | 0.1165 | | 0.7181 | 56.0 | 840 | 0.6992 | 0.1126 | 0.0244 | 0.0506 | 0.1402 | 0.1225 | | 0.7315 | 57.0 | 855 | 0.6980 | 0.1042 | 0.0235 | 0.0495 | 0.1217 | 0.1205 | | 0.7129 | 58.0 | 870 | 0.6975 | 0.1031 | 0.0229 | 0.0495 | 0.1190 | 0.1205 | | 0.7223 | 59.0 | 885 | 0.6965 | 0.1011 | 0.0240 | 0.0556 | 0.1204 | 0.1124 | | 0.7075 | 60.0 | 900 | 0.6959 | 0.1005 | 0.0248 | 0.0568 | 0.1243 | 0.1064 | | 0.7277 | 61.0 | 915 | 0.6958 | 0.1074 | 0.0238 | 0.0492 | 0.1257 | 0.1245 | | 0.7124 | 62.0 | 930 | 0.6957 | 0.1053 | 0.0234 | 0.0506 | 0.1204 | 0.1245 | | 0.7129 | 63.0 | 945 | 0.6967 | 0.1019 | 0.0223 | 0.0495 | 0.1204 | 0.1165 | | 0.7064 | 64.0 | 960 | 0.6965 | 0.0983 | 0.0237 | 0.0493 | 0.1111 | 0.1165 | | 0.7349 | 65.0 | 975 | 0.6961 | 0.1040 | 0.0235 | 0.0504 | 0.1230 | 0.1185 | | 0.7 | 66.0 | 990 | 0.6969 | 0.1051 | 0.0212 | 0.0479 | 0.1270 | 0.1185 | | 0.7188 | 67.0 | 1005 | 0.6943 | 0.1084 | 0.0243 | 0.0507 | 0.1257 | 0.1265 | | 0.7086 | 68.0 | 1020 | 0.6943 | 0.1011 | 0.0221 | 0.0493 | 0.1243 | 0.1104 | | 0.6988 | 69.0 | 1035 | 0.6935 | 0.1185 | 0.0249 | 0.0530 | 0.1402 | 0.1365 | | 0.7259 | 70.0 | 1050 | 0.6934 | 0.1080 | 0.0228 | 0.0514 | 0.1270 | 0.1245 | | 0.7113 | 71.0 | 1065 | 0.6934 | 0.1027 | 0.0211 | 0.0477 | 0.1230 | 0.1165 | | 0.7073 | 72.0 | 1080 | 0.6926 | 0.1068 | 0.0220 | 0.0505 | 0.1283 | 0.1205 | | 0.7118 | 73.0 | 1095 | 0.6920 | 0.1071 | 0.0224 | 0.0508 | 0.1310 | 0.1185 | | 0.7002 | 74.0 | 1110 | 0.6918 | 0.1197 | 0.0226 | 0.0512 | 0.1442 | 0.1365 | | 0.6918 | 75.0 | 1125 | 0.6921 | 0.1172 | 0.0243 | 0.0513 | 0.1376 | 0.1365 | | 0.7052 | 76.0 | 1140 | 0.6923 | 0.1208 | 0.0246 | 0.0527 | 0.1402 | 0.1426 | | 0.7175 | 77.0 | 1155 | 0.6913 | 0.1146 | 0.0214 | 0.0501 | 0.1402 | 0.1285 | | 0.6881 | 78.0 | 1170 | 0.6919 | 0.1181 | 0.0243 | 0.0519 | 0.1336 | 0.1426 | | 0.7001 | 79.0 | 1185 | 0.6909 | 0.1144 | 0.0233 | 0.0508 | 0.1349 | 0.1325 | | 0.6945 | 80.0 | 1200 | 0.6894 | 0.1115 | 0.0240 | 0.0507 | 0.1336 | 0.1265 | | 0.6883 | 81.0 | 1215 | 0.6901 | 0.1194 | 0.0259 | 0.0535 | 0.1402 | 0.1386 | | 0.6924 | 82.0 | 1230 | 0.6898 | 0.1166 | 0.0257 | 0.0520 | 0.1336 | 0.1386 | | 0.7127 | 83.0 | 1245 | 0.6889 | 0.1222 | 0.0263 | 0.0544 | 0.1429 | 0.1426 | | 0.6976 | 84.0 | 1260 | 0.6895 | 0.1156 | 0.0257 | 0.0528 | 0.1349 | 0.1345 | | 0.6798 | 85.0 | 1275 | 0.6888 | 0.1196 | 0.0279 | 0.0528 | 0.1362 | 0.1426 | | 0.6849 | 86.0 | 1290 | 0.6873 | 0.1261 | 0.0282 | 0.0562 | 0.1455 | 0.1486 | | 0.6868 | 87.0 | 1305 | 0.6877 | 0.1215 | 0.0246 | 0.0515 | 0.1442 | 0.1406 | | 0.6902 | 88.0 | 1320 | 0.6885 | 0.1214 | 0.0252 | 0.0529 | 0.1415 | 0.1426 | | 0.6917 | 89.0 | 1335 | 0.6892 | 0.1243 | 0.0264 | 0.0537 | 0.1442 | 0.1466 | | 0.6864 | 90.0 | 1350 | 0.6897 | 0.1174 | 0.0267 | 0.0531 | 0.1349 | 0.1386 | | 0.6843 | 91.0 | 1365 | 0.6882 | 0.1238 | 0.0261 | 0.0542 | 0.1468 | 0.1426 | | 0.6813 | 92.0 | 1380 | 0.6898 | 0.1197 | 0.0274 | 0.0548 | 0.1442 | 0.1345 | | 0.6714 | 93.0 | 1395 | 0.6885 | 0.1156 | 0.0280 | 0.0532 | 0.1323 | 0.1365 | | 0.6713 | 94.0 | 1410 | 0.6882 | 0.1194 | 0.0251 | 0.0538 | 0.1402 | 0.1386 | | 0.6935 | 95.0 | 1425 | 0.6873 | 0.1162 | 0.0256 | 0.0535 | 0.1362 | 0.1345 | | 0.6909 | 96.0 | 1440 | 0.6876 | 0.1242 | 0.0291 | 0.0576 | 0.1402 | 0.1486 | | 0.6824 | 97.0 | 1455 | 0.6883 | 0.1183 | 0.0278 | 0.0531 | 0.1349 | 0.1406 | | 0.6808 | 98.0 | 1470 | 0.6869 | 0.1212 | 0.0292 | 0.0544 | 0.1415 | 0.1406 | | 0.7102 | 99.0 | 1485 | 0.6846 | 0.1134 | 0.0266 | 0.0539 | 0.1389 | 0.1245 | | 0.6851 | 100.0 | 1500 | 0.6855 | 0.1202 | 0.0302 | 0.0563 | 0.1402 | 0.1386 | | 0.6808 | 101.0 | 1515 | 0.6854 | 0.1284 | 0.0313 | 0.0581 | 0.1481 | 0.1506 | | 0.6711 | 102.0 | 1530 | 0.6853 | 0.1286 | 0.0321 | 0.0585 | 0.1481 | 0.1506 | | 0.685 | 103.0 | 1545 | 0.6846 | 0.1271 | 0.0312 | 0.0580 | 0.1468 | 0.1486 | | 0.6823 | 104.0 | 1560 | 0.6838 | 0.1129 | 0.0287 | 0.0542 | 0.1349 | 0.1265 | | 0.6744 | 105.0 | 1575 | 0.6847 | 0.1146 | 0.0276 | 0.0532 | 0.1296 | 0.1365 | | 0.6891 | 106.0 | 1590 | 0.6841 | 0.1193 | 0.0289 | 0.0513 | 0.1336 | 0.1446 | | 0.6876 | 107.0 | 1605 | 0.6845 | 0.1200 | 0.0248 | 0.0495 | 0.1310 | 0.1506 | | 0.6703 | 108.0 | 1620 | 0.6848 | 0.1213 | 0.0262 | 0.0500 | 0.1376 | 0.1466 | | 0.6689 | 109.0 | 1635 | 0.6845 | 0.1165 | 0.0260 | 0.0474 | 0.1283 | 0.1446 | | 0.6881 | 110.0 | 1650 | 0.6839 | 0.1218 | 0.0283 | 0.0534 | 0.1376 | 0.1466 | | 0.6822 | 111.0 | 1665 | 0.6825 | 0.1171 | 0.0298 | 0.0551 | 0.1389 | 0.1325 | | 0.6663 | 112.0 | 1680 | 0.6830 | 0.1227 | 0.0315 | 0.0563 | 0.1402 | 0.1446 | | 0.6673 | 113.0 | 1695 | 0.6835 | 0.1259 | 0.0309 | 0.0565 | 0.1442 | 0.1486 | | 0.6845 | 114.0 | 1710 | 0.6829 | 0.1186 | 0.0298 | 0.0543 | 0.1389 | 0.1365 | | 0.6795 | 115.0 | 1725 | 0.6828 | 0.1104 | 0.0288 | 0.0532 | 0.1270 | 0.1285 | | 0.6816 | 116.0 | 1740 | 0.6823 | 0.1246 | 0.0298 | 0.0560 | 0.1455 | 0.1446 | | 0.6719 | 117.0 | 1755 | 0.6823 | 0.1224 | 0.0289 | 0.0560 | 0.1362 | 0.1486 | | 0.689 | 118.0 | 1770 | 0.6827 | 0.1181 | 0.0276 | 0.0538 | 0.1323 | 0.1426 | | 0.6801 | 119.0 | 1785 | 0.6826 | 0.1224 | 0.0289 | 0.0560 | 0.1362 | 0.1486 | | 0.6632 | 120.0 | 1800 | 0.6825 | 0.1259 | 0.0282 | 0.0572 | 0.1508 | 0.1426 | | 0.6663 | 121.0 | 1815 | 0.6832 | 0.1266 | 0.0276 | 0.0537 | 0.1376 | 0.1586 | | 0.6841 | 122.0 | 1830 | 0.6807 | 0.1157 | 0.0264 | 0.0524 | 0.1270 | 0.1426 | | 0.6876 | 123.0 | 1845 | 0.6805 | 0.1135 | 0.0264 | 0.0526 | 0.1336 | 0.1305 | | 0.6767 | 124.0 | 1860 | 0.6817 | 0.1160 | 0.0274 | 0.0522 | 0.1296 | 0.1406 | | 0.6769 | 125.0 | 1875 | 0.6812 | 0.1131 | 0.0257 | 0.0488 | 0.1296 | 0.1345 | | 0.6589 | 126.0 | 1890 | 0.6810 | 0.1175 | 0.0266 | 0.0514 | 0.1296 | 0.1446 | | 0.6729 | 127.0 | 1905 | 0.6818 | 0.1227 | 0.0271 | 0.0519 | 0.1323 | 0.1546 | | 0.6649 | 128.0 | 1920 | 0.6818 | 0.1115 | 0.0231 | 0.0456 | 0.1230 | 0.1386 | | 0.6704 | 129.0 | 1935 | 0.6813 | 0.1097 | 0.0278 | 0.0527 | 0.1296 | 0.1245 | | 0.664 | 130.0 | 1950 | 0.6815 | 0.1239 | 0.0303 | 0.0563 | 0.1415 | 0.1466 | | 0.6654 | 131.0 | 1965 | 0.6824 | 0.1275 | 0.0292 | 0.0560 | 0.1389 | 0.1586 | | 0.6713 | 132.0 | 1980 | 0.6819 | 0.1279 | 0.0303 | 0.0563 | 0.1415 | 0.1566 | | 0.6825 | 133.0 | 1995 | 0.6819 | 0.1228 | 0.0298 | 0.0560 | 0.1389 | 0.1466 | | 0.6539 | 134.0 | 2010 | 0.6825 | 0.1286 | 0.0304 | 0.0545 | 0.1336 | 0.1667 | | 0.6662 | 135.0 | 2025 | 0.6814 | 0.1279 | 0.0297 | 0.0562 | 0.1376 | 0.1606 | | 0.6715 | 136.0 | 2040 | 0.6819 | 0.1245 | 0.0305 | 0.0535 | 0.1296 | 0.1606 | | 0.6552 | 137.0 | 2055 | 0.6805 | 0.1283 | 0.0307 | 0.0566 | 0.1402 | 0.1586 | | 0.6813 | 138.0 | 2070 | 0.6796 | 0.1064 | 0.0270 | 0.0493 | 0.1204 | 0.1265 | | 0.6757 | 139.0 | 2085 | 0.6796 | 0.1115 | 0.0275 | 0.0493 | 0.1230 | 0.1365 | | 0.6659 | 140.0 | 2100 | 0.6804 | 0.1152 | 0.0295 | 0.0522 | 0.1270 | 0.1406 | | 0.668 | 141.0 | 2115 | 0.6807 | 0.1187 | 0.0269 | 0.0520 | 0.1243 | 0.1526 | | 0.6827 | 142.0 | 2130 | 0.6811 | 0.1244 | 0.0286 | 0.0521 | 0.1283 | 0.1627 | | 0.6685 | 143.0 | 2145 | 0.6801 | 0.1094 | 0.0268 | 0.0529 | 0.1270 | 0.1265 | | 0.6783 | 144.0 | 2160 | 0.6801 | 0.1089 | 0.0274 | 0.0531 | 0.1296 | 0.1225 | | 0.6659 | 145.0 | 2175 | 0.6792 | 0.1213 | 0.0288 | 0.0554 | 0.1296 | 0.1526 | | 0.6739 | 146.0 | 2190 | 0.6792 | 0.1119 | 0.0268 | 0.0519 | 0.1257 | 0.1345 | | 0.6667 | 147.0 | 2205 | 0.6794 | 0.1112 | 0.0267 | 0.0526 | 0.1376 | 0.1205 | | 0.6581 | 148.0 | 2220 | 0.6795 | 0.1164 | 0.0272 | 0.0530 | 0.1323 | 0.1386 | | 0.6623 | 149.0 | 2235 | 0.6789 | 0.1128 | 0.0252 | 0.0486 | 0.1230 | 0.1406 | | 0.649 | 150.0 | 2250 | 0.6793 | 0.1270 | 0.0277 | 0.0551 | 0.1362 | 0.1606 | | 0.6594 | 151.0 | 2265 | 0.6791 | 0.1233 | 0.0277 | 0.0545 | 0.1270 | 0.1606 | | 0.6663 | 152.0 | 2280 | 0.6805 | 0.1208 | 0.0270 | 0.0514 | 0.1257 | 0.1566 | | 0.6616 | 153.0 | 2295 | 0.6793 | 0.1218 | 0.0284 | 0.0557 | 0.1349 | 0.1486 | | 0.659 | 154.0 | 2310 | 0.6788 | 0.1206 | 0.0280 | 0.0550 | 0.1323 | 0.1486 | | 0.6713 | 155.0 | 2325 | 0.6791 | 0.1266 | 0.0289 | 0.0547 | 0.1389 | 0.1566 | | 0.6909 | 156.0 | 2340 | 0.6793 | 0.1272 | 0.0282 | 0.0541 | 0.1389 | 0.1586 | | 0.6457 | 157.0 | 2355 | 0.6792 | 0.1274 | 0.0301 | 0.0562 | 0.1402 | 0.1566 | | 0.6699 | 158.0 | 2370 | 0.6789 | 0.1245 | 0.0290 | 0.0558 | 0.1415 | 0.1486 | | 0.6675 | 159.0 | 2385 | 0.6796 | 0.1155 | 0.0254 | 0.0484 | 0.1257 | 0.1446 | | 0.6529 | 160.0 | 2400 | 0.6801 | 0.1275 | 0.0288 | 0.0527 | 0.1336 | 0.1647 | | 0.6581 | 161.0 | 2415 | 0.6796 | 0.1275 | 0.0288 | 0.0527 | 0.1336 | 0.1647 | | 0.6628 | 162.0 | 2430 | 0.6788 | 0.1102 | 0.0269 | 0.0507 | 0.1257 | 0.1305 | | 0.6881 | 163.0 | 2445 | 0.6783 | 0.1111 | 0.0264 | 0.0522 | 0.1296 | 0.1285 | | 0.6624 | 164.0 | 2460 | 0.6782 | 0.1284 | 0.0298 | 0.0560 | 0.1389 | 0.1606 | | 0.6545 | 165.0 | 2475 | 0.6786 | 0.1270 | 0.0285 | 0.0541 | 0.1362 | 0.1606 | | 0.6539 | 166.0 | 2490 | 0.6784 | 0.1287 | 0.0289 | 0.0548 | 0.1402 | 0.1606 | | 0.654 | 167.0 | 2505 | 0.6794 | 0.1263 | 0.0291 | 0.0545 | 0.1362 | 0.1586 | | 0.6564 | 168.0 | 2520 | 0.6799 | 0.1158 | 0.0274 | 0.0526 | 0.1310 | 0.1386 | | 0.6473 | 169.0 | 2535 | 0.6798 | 0.1250 | 0.0279 | 0.0527 | 0.1336 | 0.1586 | | 0.6635 | 170.0 | 2550 | 0.6792 | 0.1263 | 0.0285 | 0.0522 | 0.1310 | 0.1647 | | 0.668 | 171.0 | 2565 | 0.6795 | 0.1277 | 0.0285 | 0.0527 | 0.1362 | 0.1627 | | 0.675 | 172.0 | 2580 | 0.6786 | 0.1270 | 0.0284 | 0.0541 | 0.1402 | 0.1566 | | 0.668 | 173.0 | 2595 | 0.6780 | 0.1266 | 0.0289 | 0.0547 | 0.1389 | 0.1566 | | 0.6587 | 174.0 | 2610 | 0.6788 | 0.1272 | 0.0278 | 0.0541 | 0.1389 | 0.1586 | | 0.6542 | 175.0 | 2625 | 0.6786 | 0.1276 | 0.0284 | 0.0543 | 0.1336 | 0.1647 | | 0.6626 | 176.0 | 2640 | 0.6779 | 0.1277 | 0.0292 | 0.0543 | 0.1336 | 0.1647 | | 0.6541 | 177.0 | 2655 | 0.6777 | 0.1249 | 0.0288 | 0.0546 | 0.1389 | 0.1526 | | 0.6467 | 178.0 | 2670 | 0.6789 | 0.1169 | 0.0263 | 0.0483 | 0.1230 | 0.1506 | | 0.6713 | 179.0 | 2685 | 0.6784 | 0.1263 | 0.0300 | 0.0564 | 0.1415 | 0.1526 | | 0.6453 | 180.0 | 2700 | 0.6785 | 0.1141 | 0.0279 | 0.0512 | 0.1270 | 0.1386 | | 0.661 | 181.0 | 2715 | 0.6788 | 0.1180 | 0.0277 | 0.0520 | 0.1243 | 0.1506 | | 0.6603 | 182.0 | 2730 | 0.6785 | 0.1177 | 0.0262 | 0.0485 | 0.1230 | 0.1526 | | 0.6578 | 183.0 | 2745 | 0.6783 | 0.1131 | 0.0266 | 0.0504 | 0.1230 | 0.1406 | | 0.6481 | 184.0 | 2760 | 0.6786 | 0.1125 | 0.0272 | 0.0512 | 0.1270 | 0.1345 | | 0.6479 | 185.0 | 2775 | 0.6786 | 0.1225 | 0.0293 | 0.0560 | 0.1362 | 0.1486 | | 0.6521 | 186.0 | 2790 | 0.6782 | 0.1225 | 0.0293 | 0.0560 | 0.1362 | 0.1486 | | 0.642 | 187.0 | 2805 | 0.6775 | 0.1202 | 0.0274 | 0.0534 | 0.1336 | 0.1466 | | 0.6599 | 188.0 | 2820 | 0.6787 | 0.1220 | 0.0240 | 0.0486 | 0.1362 | 0.1506 | | 0.6686 | 189.0 | 2835 | 0.6788 | 0.1118 | 0.0221 | 0.0446 | 0.1243 | 0.1386 | | 0.6614 | 190.0 | 2850 | 0.6795 | 0.1267 | 0.0290 | 0.0564 | 0.1429 | 0.1526 | | 0.6655 | 191.0 | 2865 | 0.6795 | 0.1227 | 0.0275 | 0.0524 | 0.1362 | 0.1506 | | 0.6537 | 192.0 | 2880 | 0.6797 | 0.1198 | 0.0277 | 0.0520 | 0.1310 | 0.1486 | | 0.657 | 193.0 | 2895 | 0.6808 | 0.1187 | 0.0272 | 0.0522 | 0.1323 | 0.1446 | | 0.6427 | 194.0 | 2910 | 0.6804 | 0.1158 | 0.0269 | 0.0503 | 0.1257 | 0.1446 | | 0.6564 | 195.0 | 2925 | 0.6804 | 0.1217 | 0.0283 | 0.0541 | 0.1349 | 0.1486 | | 0.6584 | 196.0 | 2940 | 0.6789 | 0.1175 | 0.0238 | 0.0488 | 0.1349 | 0.1406 | | 0.6636 | 197.0 | 2955 | 0.6784 | 0.1077 | 0.0215 | 0.0443 | 0.1243 | 0.1285 | | 0.6415 | 198.0 | 2970 | 0.6783 | 0.1204 | 0.0257 | 0.0523 | 0.1310 | 0.1506 | | 0.6466 | 199.0 | 2985 | 0.6776 | 0.1219 | 0.0268 | 0.0527 | 0.1323 | 0.1526 | | 0.6442 | 200.0 | 3000 | 0.6777 | 0.1138 | 0.0270 | 0.0512 | 0.1283 | 0.1365 | | 0.6433 | 201.0 | 3015 | 0.6784 | 0.1087 | 0.0268 | 0.0517 | 0.1257 | 0.1265 | | 0.6472 | 202.0 | 3030 | 0.6781 | 0.1194 | 0.0269 | 0.0516 | 0.1362 | 0.1426 | | 0.6553 | 203.0 | 3045 | 0.6775 | 0.1150 | 0.0263 | 0.0516 | 0.1336 | 0.1345 | | 0.6419 | 204.0 | 3060 | 0.6777 | 0.1124 | 0.0265 | 0.0516 | 0.1310 | 0.1305 | | 0.664 | 205.0 | 3075 | 0.6777 | 0.1124 | 0.0266 | 0.0516 | 0.1310 | 0.1305 | | 0.6441 | 206.0 | 3090 | 0.6778 | 0.1124 | 0.0266 | 0.0516 | 0.1310 | 0.1305 | | 0.6576 | 207.0 | 3105 | 0.6782 | 0.1101 | 0.0233 | 0.0453 | 0.1257 | 0.1325 | | 0.6361 | 208.0 | 3120 | 0.6773 | 0.1088 | 0.0233 | 0.0454 | 0.1243 | 0.1305 | | 0.6509 | 209.0 | 3135 | 0.6771 | 0.1154 | 0.0243 | 0.0486 | 0.1296 | 0.1406 | | 0.652 | 210.0 | 3150 | 0.6776 | 0.1226 | 0.0272 | 0.0545 | 0.1376 | 0.1486 | | 0.653 | 211.0 | 3165 | 0.6779 | 0.1176 | 0.0273 | 0.0516 | 0.1336 | 0.1406 | | 0.6485 | 212.0 | 3180 | 0.6781 | 0.1162 | 0.0273 | 0.0512 | 0.1283 | 0.1426 | | 0.6495 | 213.0 | 3195 | 0.6773 | 0.1175 | 0.0270 | 0.0516 | 0.1336 | 0.1406 | | 0.658 | 214.0 | 3210 | 0.6766 | 0.1096 | 0.0227 | 0.0456 | 0.1283 | 0.1285 | | 0.6538 | 215.0 | 3225 | 0.6762 | 0.1073 | 0.0219 | 0.0451 | 0.1270 | 0.1245 | | 0.6394 | 216.0 | 3240 | 0.6769 | 0.1090 | 0.0224 | 0.0455 | 0.1270 | 0.1285 | | 0.6511 | 217.0 | 3255 | 0.6771 | 0.1143 | 0.0240 | 0.0494 | 0.1349 | 0.1325 | | 0.6427 | 218.0 | 3270 | 0.6776 | 0.1193 | 0.0266 | 0.0515 | 0.1362 | 0.1426 | | 0.6384 | 219.0 | 3285 | 0.6767 | 0.1170 | 0.0268 | 0.0515 | 0.1323 | 0.1406 | | 0.6344 | 220.0 | 3300 | 0.6767 | 0.1150 | 0.0235 | 0.0486 | 0.1310 | 0.1386 | | 0.647 | 221.0 | 3315 | 0.6766 | 0.1065 | 0.0222 | 0.0444 | 0.1190 | 0.1305 | | 0.6348 | 222.0 | 3330 | 0.6763 | 0.1049 | 0.0222 | 0.0444 | 0.1190 | 0.1265 | | 0.6553 | 223.0 | 3345 | 0.6764 | 0.1074 | 0.0223 | 0.0456 | 0.1270 | 0.1245 | | 0.6554 | 224.0 | 3360 | 0.6767 | 0.1065 | 0.0223 | 0.0444 | 0.1190 | 0.1305 | | 0.6497 | 225.0 | 3375 | 0.6772 | 0.1101 | 0.0226 | 0.0453 | 0.1257 | 0.1325 | | 0.6342 | 226.0 | 3390 | 0.6774 | 0.1089 | 0.0220 | 0.0455 | 0.1270 | 0.1285 | | 0.6469 | 227.0 | 3405 | 0.6778 | 0.1144 | 0.0259 | 0.0503 | 0.1243 | 0.1426 | | 0.6482 | 228.0 | 3420 | 0.6781 | 0.1169 | 0.0263 | 0.0515 | 0.1323 | 0.1406 | | 0.6492 | 229.0 | 3435 | 0.6784 | 0.1169 | 0.0263 | 0.0515 | 0.1323 | 0.1406 | | 0.6398 | 230.0 | 3450 | 0.6790 | 0.1141 | 0.0224 | 0.0455 | 0.1296 | 0.1386 | | 0.6524 | 231.0 | 3465 | 0.6795 | 0.1161 | 0.0262 | 0.0511 | 0.1283 | 0.1426 | | 0.641 | 232.0 | 3480 | 0.6798 | 0.1214 | 0.0312 | 0.0597 | 0.1362 | 0.1446 | | 0.6346 | 233.0 | 3495 | 0.6792 | 0.1146 | 0.0226 | 0.0456 | 0.1310 | 0.1386 | | 0.6586 | 234.0 | 3510 | 0.6800 | 0.1201 | 0.0285 | 0.0567 | 0.1323 | 0.1466 | | 0.6398 | 235.0 | 3525 | 0.6800 | 0.1147 | 0.0269 | 0.0530 | 0.1243 | 0.1426 | | 0.6405 | 236.0 | 3540 | 0.6792 | 0.1141 | 0.0228 | 0.0455 | 0.1296 | 0.1386 | | 0.6389 | 237.0 | 3555 | 0.6790 | 0.1205 | 0.0309 | 0.0588 | 0.1323 | 0.1466 | | 0.6452 | 238.0 | 3570 | 0.6786 | 0.1205 | 0.0309 | 0.0588 | 0.1323 | 0.1466 | | 0.6443 | 239.0 | 3585 | 0.6780 | 0.1144 | 0.0263 | 0.0504 | 0.1243 | 0.1426 | | 0.6522 | 240.0 | 3600 | 0.6783 | 0.1145 | 0.0269 | 0.0510 | 0.1243 | 0.1426 | | 0.6423 | 241.0 | 3615 | 0.6782 | 0.1144 | 0.0263 | 0.0504 | 0.1243 | 0.1426 | | 0.6416 | 242.0 | 3630 | 0.6784 | 0.1144 | 0.0263 | 0.0504 | 0.1243 | 0.1426 | | 0.6344 | 243.0 | 3645 | 0.6787 | 0.1116 | 0.0223 | 0.0443 | 0.1217 | 0.1406 | | 0.6455 | 244.0 | 3660 | 0.6793 | 0.1064 | 0.0219 | 0.0443 | 0.1190 | 0.1305 | | 0.6464 | 245.0 | 3675 | 0.6797 | 0.1101 | 0.0226 | 0.0453 | 0.1257 | 0.1325 | | 0.6461 | 246.0 | 3690 | 0.6793 | 0.1106 | 0.0225 | 0.0453 | 0.1270 | 0.1325 | | 0.6472 | 247.0 | 3705 | 0.6795 | 0.1224 | 0.0307 | 0.0593 | 0.1389 | 0.1446 | | 0.6425 | 248.0 | 3720 | 0.6798 | 0.1144 | 0.0263 | 0.0535 | 0.1336 | 0.1325 | | 0.6418 | 249.0 | 3735 | 0.6795 | 0.1070 | 0.0218 | 0.0443 | 0.1204 | 0.1305 | | 0.652 | 250.0 | 3750 | 0.6793 | 0.1070 | 0.0218 | 0.0443 | 0.1204 | 0.1305 | | 0.6356 | 251.0 | 3765 | 0.6790 | 0.1063 | 0.0208 | 0.0439 | 0.1190 | 0.1305 | | 0.6421 | 252.0 | 3780 | 0.6790 | 0.1114 | 0.0212 | 0.0439 | 0.1217 | 0.1406 | | 0.6486 | 253.0 | 3795 | 0.6789 | 0.1143 | 0.0250 | 0.0500 | 0.1243 | 0.1426 | | 0.6368 | 254.0 | 3810 | 0.6786 | 0.1114 | 0.0212 | 0.0439 | 0.1217 | 0.1406 | | 0.646 | 255.0 | 3825 | 0.6782 | 0.1109 | 0.0213 | 0.0439 | 0.1204 | 0.1406 | | 0.637 | 256.0 | 3840 | 0.6782 | 0.1109 | 0.0209 | 0.0438 | 0.1204 | 0.1406 | | 0.6432 | 257.0 | 3855 | 0.6786 | 0.1109 | 0.0209 | 0.0438 | 0.1204 | 0.1406 | | 0.6359 | 258.0 | 3870 | 0.6785 | 0.1063 | 0.0207 | 0.0440 | 0.1190 | 0.1305 | | 0.6505 | 259.0 | 3885 | 0.6783 | 0.1058 | 0.0209 | 0.0440 | 0.1177 | 0.1305 | | 0.6497 | 260.0 | 3900 | 0.6783 | 0.1063 | 0.0204 | 0.0438 | 0.1190 | 0.1305 | | 0.6378 | 261.0 | 3915 | 0.6785 | 0.1063 | 0.0207 | 0.0440 | 0.1190 | 0.1305 | | 0.6446 | 262.0 | 3930 | 0.6786 | 0.1063 | 0.0207 | 0.0440 | 0.1190 | 0.1305 | | 0.6367 | 263.0 | 3945 | 0.6790 | 0.1063 | 0.0207 | 0.0440 | 0.1190 | 0.1305 | | 0.6461 | 264.0 | 3960 | 0.6793 | 0.1063 | 0.0207 | 0.0440 | 0.1190 | 0.1305 | | 0.6324 | 265.0 | 3975 | 0.6794 | 0.1063 | 0.0207 | 0.0440 | 0.1190 | 0.1305 | | 0.6375 | 266.0 | 3990 | 0.6795 | 0.1063 | 0.0207 | 0.0440 | 0.1190 | 0.1305 | | 0.6231 | 267.0 | 4005 | 0.6796 | 0.1070 | 0.0217 | 0.0444 | 0.1204 | 0.1305 | | 0.6467 | 268.0 | 4020 | 0.6796 | 0.1070 | 0.0217 | 0.0444 | 0.1204 | 0.1305 | | 0.6456 | 269.0 | 4035 | 0.6798 | 0.1070 | 0.0217 | 0.0444 | 0.1204 | 0.1305 | | 0.63 | 270.0 | 4050 | 0.6795 | 0.1070 | 0.0217 | 0.0444 | 0.1204 | 0.1305 | | 0.645 | 271.0 | 4065 | 0.6794 | 0.1070 | 0.0217 | 0.0444 | 0.1204 | 0.1305 | | 0.6427 | 272.0 | 4080 | 0.6792 | 0.1070 | 0.0217 | 0.0444 | 0.1204 | 0.1305 | | 0.6398 | 273.0 | 4095 | 0.6792 | 0.1070 | 0.0217 | 0.0444 | 0.1204 | 0.1305 | | 0.6244 | 274.0 | 4110 | 0.6795 | 0.1069 | 0.0215 | 0.0442 | 0.1204 | 0.1305 | | 0.6248 | 275.0 | 4125 | 0.6795 | 0.1069 | 0.0215 | 0.0442 | 0.1204 | 0.1305 | | 0.6359 | 276.0 | 4140 | 0.6796 | 0.1120 | 0.0218 | 0.0442 | 0.1230 | 0.1406 | | 0.6515 | 277.0 | 4155 | 0.6798 | 0.1120 | 0.0218 | 0.0442 | 0.1230 | 0.1406 | | 0.6341 | 278.0 | 4170 | 0.6798 | 0.1069 | 0.0215 | 0.0442 | 0.1204 | 0.1305 | | 0.6391 | 279.0 | 4185 | 0.6797 | 0.1070 | 0.0217 | 0.0444 | 0.1204 | 0.1305 | | 0.638 | 280.0 | 4200 | 0.6799 | 0.1095 | 0.0222 | 0.0456 | 0.1283 | 0.1285 | | 0.6425 | 281.0 | 4215 | 0.6799 | 0.1069 | 0.0215 | 0.0442 | 0.1204 | 0.1305 | | 0.6412 | 282.0 | 4230 | 0.6796 | 0.1120 | 0.0218 | 0.0442 | 0.1230 | 0.1406 | | 0.6324 | 283.0 | 4245 | 0.6796 | 0.1069 | 0.0215 | 0.0442 | 0.1204 | 0.1305 | | 0.6476 | 284.0 | 4260 | 0.6797 | 0.1069 | 0.0215 | 0.0442 | 0.1204 | 0.1305 | | 0.6484 | 285.0 | 4275 | 0.6795 | 0.1070 | 0.0217 | 0.0444 | 0.1204 | 0.1305 | | 0.6448 | 286.0 | 4290 | 0.6796 | 0.1070 | 0.0217 | 0.0444 | 0.1204 | 0.1305 | | 0.6418 | 287.0 | 4305 | 0.6795 | 0.1070 | 0.0217 | 0.0444 | 0.1204 | 0.1305 | | 0.6402 | 288.0 | 4320 | 0.6795 | 0.1070 | 0.0217 | 0.0444 | 0.1204 | 0.1305 | | 0.6335 | 289.0 | 4335 | 0.6794 | 0.1070 | 0.0217 | 0.0444 | 0.1204 | 0.1305 | | 0.6321 | 290.0 | 4350 | 0.6795 | 0.1070 | 0.0217 | 0.0444 | 0.1204 | 0.1305 | | 0.6353 | 291.0 | 4365 | 0.6794 | 0.1070 | 0.0217 | 0.0444 | 0.1204 | 0.1305 | | 0.6307 | 292.0 | 4380 | 0.6792 | 0.1070 | 0.0217 | 0.0444 | 0.1204 | 0.1305 | | 0.6478 | 293.0 | 4395 | 0.6792 | 0.1070 | 0.0217 | 0.0444 | 0.1204 | 0.1305 | | 0.6478 | 294.0 | 4410 | 0.6792 | 0.1070 | 0.0217 | 0.0444 | 0.1204 | 0.1305 | | 0.6298 | 295.0 | 4425 | 0.6792 | 0.1069 | 0.0215 | 0.0442 | 0.1204 | 0.1305 | | 0.6395 | 296.0 | 4440 | 0.6793 | 0.1069 | 0.0215 | 0.0442 | 0.1204 | 0.1305 | | 0.6424 | 297.0 | 4455 | 0.6793 | 0.1069 | 0.0215 | 0.0442 | 0.1204 | 0.1305 | | 0.6372 | 298.0 | 4470 | 0.6793 | 0.1069 | 0.0215 | 0.0442 | 0.1204 | 0.1305 | | 0.6498 | 299.0 | 4485 | 0.6793 | 0.1069 | 0.0215 | 0.0442 | 0.1204 | 0.1305 | | 0.6332 | 300.0 | 4500 | 0.6793 | 0.1069 | 0.0215 | 0.0442 | 0.1204 | 0.1305 | ### Framework versions - Transformers 4.31.0 - Pytorch 2.0.1 - Datasets 2.14.4 - Tokenizers 0.13.3