ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k1_task3_organization

This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7991
  • Qwk: 0.0798
  • Mse: 0.7991
  • Rmse: 0.8939

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: 2e-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
  • num_epochs: 100

Training results

Training Loss Epoch Step Validation Loss Qwk Mse Rmse
No log 0.3333 2 3.6183 -0.0047 3.6183 1.9022
No log 0.6667 4 2.3628 0.0027 2.3628 1.5371
No log 1.0 6 1.4013 0.0 1.4013 1.1837
No log 1.3333 8 1.1641 0.0338 1.1641 1.0789
No log 1.6667 10 1.2718 -0.0164 1.2718 1.1278
No log 2.0 12 1.0579 -0.0411 1.0579 1.0285
No log 2.3333 14 0.9742 0.0006 0.9742 0.9870
No log 2.6667 16 0.7367 0.0857 0.7367 0.8583
No log 3.0 18 0.6748 0.0555 0.6748 0.8215
No log 3.3333 20 0.7150 0.0964 0.7150 0.8456
No log 3.6667 22 1.0192 0.0046 1.0192 1.0095
No log 4.0 24 0.9508 -0.0200 0.9508 0.9751
No log 4.3333 26 0.7449 -0.0069 0.7449 0.8631
No log 4.6667 28 0.7492 0.0524 0.7492 0.8655
No log 5.0 30 0.7805 0.0191 0.7805 0.8834
No log 5.3333 32 0.7746 0.0639 0.7746 0.8801
No log 5.6667 34 1.0656 -0.0285 1.0656 1.0323
No log 6.0 36 1.0405 0.0065 1.0405 1.0201
No log 6.3333 38 0.7483 0.0874 0.7483 0.8651
No log 6.6667 40 0.7750 0.1865 0.7750 0.8803
No log 7.0 42 0.9985 -0.0114 0.9985 0.9992
No log 7.3333 44 1.0574 0.0193 1.0574 1.0283
No log 7.6667 46 0.9002 0.0618 0.9002 0.9488
No log 8.0 48 1.0286 0.0741 1.0286 1.0142
No log 8.3333 50 0.9310 0.0246 0.9310 0.9649
No log 8.6667 52 1.0519 0.0867 1.0519 1.0256
No log 9.0 54 1.1252 0.0390 1.1252 1.0607
No log 9.3333 56 0.8223 0.0361 0.8223 0.9068
No log 9.6667 58 0.8797 0.0265 0.8797 0.9379
No log 10.0 60 0.8803 0.2205 0.8803 0.9382
No log 10.3333 62 0.9585 0.1598 0.9585 0.9790
No log 10.6667 64 0.9166 0.1710 0.9166 0.9574
No log 11.0 66 0.9338 0.0172 0.9338 0.9663
No log 11.3333 68 0.8858 0.1404 0.8858 0.9412
No log 11.6667 70 0.9864 0.0324 0.9864 0.9932
No log 12.0 72 0.9036 0.1272 0.9036 0.9506
No log 12.3333 74 0.8594 0.0847 0.8594 0.9270
No log 12.6667 76 0.8433 0.1818 0.8433 0.9183
No log 13.0 78 0.8909 0.1713 0.8909 0.9439
No log 13.3333 80 0.8565 0.1723 0.8565 0.9254
No log 13.6667 82 0.8687 0.1359 0.8687 0.9320
No log 14.0 84 0.8793 0.1009 0.8793 0.9377
No log 14.3333 86 0.9153 0.1710 0.9153 0.9567
No log 14.6667 88 0.9063 0.0933 0.9063 0.9520
No log 15.0 90 0.9458 0.0741 0.9458 0.9725
No log 15.3333 92 0.8726 0.0802 0.8726 0.9341
No log 15.6667 94 0.9179 0.0255 0.9179 0.9581
No log 16.0 96 0.8761 0.0879 0.8761 0.9360
No log 16.3333 98 0.8968 0.0101 0.8968 0.9470
No log 16.6667 100 0.8598 0.2299 0.8598 0.9272
No log 17.0 102 0.9812 0.1007 0.9812 0.9905
No log 17.3333 104 0.8862 0.1281 0.8862 0.9414
No log 17.6667 106 0.8813 0.0435 0.8813 0.9388
No log 18.0 108 0.8765 0.0435 0.8765 0.9362
No log 18.3333 110 0.7939 0.1456 0.7939 0.8910
No log 18.6667 112 0.8718 0.0964 0.8718 0.9337
No log 19.0 114 0.8831 0.1977 0.8831 0.9397
No log 19.3333 116 0.9400 0.1065 0.9400 0.9695
No log 19.6667 118 0.9624 0.1029 0.9624 0.9810
No log 20.0 120 0.8779 0.2259 0.8779 0.9369
No log 20.3333 122 0.9703 0.0659 0.9703 0.9850
No log 20.6667 124 0.8582 0.1285 0.8582 0.9264
No log 21.0 126 0.9335 0.1028 0.9335 0.9662
No log 21.3333 128 1.0003 0.1882 1.0003 1.0001
No log 21.6667 130 0.8318 0.1138 0.8318 0.9120
No log 22.0 132 0.9436 0.1925 0.9436 0.9714
No log 22.3333 134 0.9494 0.1414 0.9494 0.9744
No log 22.6667 136 0.7820 0.0025 0.7820 0.8843
No log 23.0 138 0.8054 0.1146 0.8054 0.8974
No log 23.3333 140 0.8170 0.1506 0.8170 0.9039
No log 23.6667 142 0.7613 0.0393 0.7613 0.8725
No log 24.0 144 0.9160 0.0029 0.9160 0.9571
No log 24.3333 146 0.9510 0.1078 0.9510 0.9752
No log 24.6667 148 0.7951 0.0408 0.7951 0.8917
No log 25.0 150 0.8697 0.1621 0.8697 0.9326
No log 25.3333 152 0.8971 0.1027 0.8971 0.9472
No log 25.6667 154 0.7666 0.1139 0.7666 0.8756
No log 26.0 156 0.8216 0.1352 0.8216 0.9064
No log 26.3333 158 0.8201 0.0955 0.8201 0.9056
No log 26.6667 160 0.8013 0.2437 0.8013 0.8952
No log 27.0 162 0.8562 0.1353 0.8562 0.9253
No log 27.3333 164 0.8605 0.2019 0.8605 0.9276
No log 27.6667 166 0.9243 -0.0148 0.9243 0.9614
No log 28.0 168 0.9908 0.0365 0.9908 0.9954
No log 28.3333 170 0.9245 0.0211 0.9245 0.9615
No log 28.6667 172 0.8782 0.1471 0.8782 0.9371
No log 29.0 174 0.9308 0.0754 0.9308 0.9648
No log 29.3333 176 0.8612 0.1519 0.8612 0.9280
No log 29.6667 178 0.8797 0.0526 0.8797 0.9379
No log 30.0 180 0.8684 0.0537 0.8684 0.9319
No log 30.3333 182 0.8760 0.1513 0.8760 0.9360
No log 30.6667 184 1.0187 0.0852 1.0187 1.0093
No log 31.0 186 1.0257 0.0852 1.0257 1.0128
No log 31.3333 188 0.8542 0.2070 0.8542 0.9242
No log 31.6667 190 0.8735 0.1281 0.8735 0.9346
No log 32.0 192 0.8559 0.0203 0.8559 0.9252
No log 32.3333 194 0.8036 0.0902 0.8036 0.8964
No log 32.6667 196 0.8680 0.0837 0.8680 0.9317
No log 33.0 198 1.0871 -0.0512 1.0871 1.0426
No log 33.3333 200 1.0613 0.0159 1.0613 1.0302
No log 33.6667 202 0.9367 0.1277 0.9367 0.9679
No log 34.0 204 1.0985 0.0342 1.0985 1.0481
No log 34.3333 206 1.1565 0.0355 1.1565 1.0754
No log 34.6667 208 1.0407 0.0589 1.0407 1.0201
No log 35.0 210 0.9256 0.0488 0.9256 0.9621
No log 35.3333 212 0.9027 0.0537 0.9027 0.9501
No log 35.6667 214 0.8475 0.0909 0.8475 0.9206
No log 36.0 216 0.8144 0.0426 0.8144 0.9025
No log 36.3333 218 0.8041 0.0426 0.8042 0.8967
No log 36.6667 220 0.8195 0.0856 0.8195 0.9053
No log 37.0 222 0.8380 0.0771 0.8380 0.9154
No log 37.3333 224 0.8837 0.1251 0.8837 0.9400
No log 37.6667 226 0.9719 0.0970 0.9719 0.9858
No log 38.0 228 0.9151 0.0928 0.9151 0.9566
No log 38.3333 230 0.8414 0.0301 0.8414 0.9173
No log 38.6667 232 0.8644 0.1190 0.8644 0.9297
No log 39.0 234 0.8130 0.0956 0.8130 0.9017
No log 39.3333 236 0.7684 0.1189 0.7684 0.8766
No log 39.6667 238 0.8263 0.0220 0.8263 0.9090
No log 40.0 240 0.8344 0.0257 0.8344 0.9135
No log 40.3333 242 0.8018 0.0851 0.8018 0.8954
No log 40.6667 244 0.8095 0.0327 0.8095 0.8997
No log 41.0 246 0.8545 0.2327 0.8545 0.9244
No log 41.3333 248 0.8748 0.2169 0.8748 0.9353
No log 41.6667 250 0.8858 0.2169 0.8858 0.9412
No log 42.0 252 0.8657 0.2243 0.8657 0.9304
No log 42.3333 254 0.8641 0.2169 0.8641 0.9296
No log 42.6667 256 0.8319 0.1964 0.8319 0.9121
No log 43.0 258 0.8100 0.2336 0.8100 0.9000
No log 43.3333 260 0.7849 0.2128 0.7849 0.8860
No log 43.6667 262 0.8090 0.0603 0.8090 0.8995
No log 44.0 264 0.7938 0.0644 0.7938 0.8909
No log 44.3333 266 0.7445 0.1404 0.7445 0.8628
No log 44.6667 268 0.7340 0.0879 0.7340 0.8567
No log 45.0 270 0.7396 0.1659 0.7396 0.8600
No log 45.3333 272 0.7537 0.1659 0.7537 0.8682
No log 45.6667 274 0.7775 0.0410 0.7775 0.8818
No log 46.0 276 0.8365 0.0537 0.8365 0.9146
No log 46.3333 278 0.8565 0.0879 0.8565 0.9255
No log 46.6667 280 0.8384 0.0469 0.8384 0.9157
No log 47.0 282 0.8466 0.1347 0.8466 0.9201
No log 47.3333 284 0.8524 0.0892 0.8524 0.9233
No log 47.6667 286 0.8623 0.1513 0.8623 0.9286
No log 48.0 288 0.8157 0.0611 0.8157 0.9032
No log 48.3333 290 0.7835 0.0840 0.7835 0.8851
No log 48.6667 292 0.8204 -0.0268 0.8204 0.9057
No log 49.0 294 0.8492 0.0257 0.8492 0.9215
No log 49.3333 296 0.8198 0.0220 0.8198 0.9054
No log 49.6667 298 0.7715 0.1340 0.7715 0.8784
No log 50.0 300 0.7765 0.1644 0.7765 0.8812
No log 50.3333 302 0.7938 0.1585 0.7938 0.8909
No log 50.6667 304 0.8089 0.1644 0.8089 0.8994
No log 51.0 306 0.8339 0.0861 0.8339 0.9132
No log 51.3333 308 0.8648 0.0526 0.8648 0.9300
No log 51.6667 310 0.8593 0.0866 0.8593 0.9270
No log 52.0 312 0.8574 0.1141 0.8574 0.9260
No log 52.3333 314 0.8515 0.1141 0.8515 0.9228
No log 52.6667 316 0.8348 0.1218 0.8348 0.9137
No log 53.0 318 0.8446 0.0526 0.8446 0.9190
No log 53.3333 320 0.8183 0.0119 0.8183 0.9046
No log 53.6667 322 0.7873 0.0846 0.7873 0.8873
No log 54.0 324 0.7797 0.0846 0.7797 0.8830
No log 54.3333 326 0.7863 0.0460 0.7863 0.8868
No log 54.6667 328 0.7773 0.0846 0.7773 0.8816
No log 55.0 330 0.7785 0.1644 0.7785 0.8823
No log 55.3333 332 0.7775 0.1644 0.7775 0.8818
No log 55.6667 334 0.7756 0.0834 0.7756 0.8807
No log 56.0 336 0.8093 -0.0320 0.8093 0.8996
No log 56.3333 338 0.8382 -0.1062 0.8382 0.9155
No log 56.6667 340 0.8064 -0.0320 0.8064 0.8980
No log 57.0 342 0.7706 0.0834 0.7706 0.8778
No log 57.3333 344 0.7952 0.1003 0.7952 0.8917
No log 57.6667 346 0.7902 0.1003 0.7902 0.8889
No log 58.0 348 0.7934 0.0867 0.7934 0.8908
No log 58.3333 350 0.7667 0.1599 0.7667 0.8756
No log 58.6667 352 0.7490 0.0027 0.7490 0.8654
No log 59.0 354 0.8106 -0.0268 0.8106 0.9003
No log 59.3333 356 0.8575 -0.0536 0.8575 0.9260
No log 59.6667 358 0.8390 -0.0180 0.8390 0.9160
No log 60.0 360 0.8207 0.0441 0.8207 0.9059
No log 60.3333 362 0.8268 0.1353 0.8268 0.9093
No log 60.6667 364 0.8335 0.1752 0.8335 0.9130
No log 61.0 366 0.7971 0.0757 0.7971 0.8928
No log 61.3333 368 0.7723 0.0410 0.7723 0.8788
No log 61.6667 370 0.7653 0.0444 0.7653 0.8748
No log 62.0 372 0.7707 0.1240 0.7707 0.8779
No log 62.3333 374 0.7868 0.0798 0.7868 0.8870
No log 62.6667 376 0.8051 0.0757 0.8051 0.8973
No log 63.0 378 0.8292 -0.0295 0.8292 0.9106
No log 63.3333 380 0.8477 0.0139 0.8477 0.9207
No log 63.6667 382 0.8315 0.0071 0.8315 0.9119
No log 64.0 384 0.8270 0.1138 0.8270 0.9094
No log 64.3333 386 0.8136 0.1617 0.8136 0.9020
No log 64.6667 388 0.8128 0.0441 0.8128 0.9016
No log 65.0 390 0.8363 0.0114 0.8363 0.9145
No log 65.3333 392 0.8794 -0.0563 0.8794 0.9377
No log 65.6667 394 0.8781 -0.0576 0.8781 0.9371
No log 66.0 396 0.8586 0.0114 0.8586 0.9266
No log 66.3333 398 0.8484 0.1176 0.8484 0.9211
No log 66.6667 400 0.8452 0.1448 0.8452 0.9193
No log 67.0 402 0.8350 0.1138 0.8350 0.9138
No log 67.3333 404 0.8274 0.0822 0.8274 0.9096
No log 67.6667 406 0.8383 0.0114 0.8383 0.9156
No log 68.0 408 0.8500 0.0159 0.8500 0.9220
No log 68.3333 410 0.8878 -0.0536 0.8878 0.9423
No log 68.6667 412 0.8873 -0.0536 0.8873 0.9420
No log 69.0 414 0.8736 -0.0536 0.8736 0.9347
No log 69.3333 416 0.8665 -0.0536 0.8665 0.9309
No log 69.6667 418 0.8342 -0.0295 0.8342 0.9133
No log 70.0 420 0.8185 0.1187 0.8185 0.9047
No log 70.3333 422 0.8223 0.1518 0.8223 0.9068
No log 70.6667 424 0.8255 0.1518 0.8255 0.9085
No log 71.0 426 0.8085 0.1573 0.8085 0.8992
No log 71.3333 428 0.7970 0.0 0.7970 0.8927
No log 71.6667 430 0.8016 0.0944 0.8016 0.8953
No log 72.0 432 0.7926 0.0558 0.7926 0.8903
No log 72.3333 434 0.7913 0.0558 0.7913 0.8896
No log 72.6667 436 0.7986 0.0172 0.7986 0.8936
No log 73.0 438 0.7983 0.0570 0.7983 0.8935
No log 73.3333 440 0.7944 0.0570 0.7944 0.8913
No log 73.6667 442 0.7914 0.0444 0.7914 0.8896
No log 74.0 444 0.7986 0.1189 0.7986 0.8936
No log 74.3333 446 0.8049 0.1189 0.8049 0.8972
No log 74.6667 448 0.8034 0.0791 0.8034 0.8963
No log 75.0 450 0.8001 0.0393 0.8001 0.8945
No log 75.3333 452 0.7949 0.0393 0.7949 0.8916
No log 75.6667 454 0.7960 0.0944 0.7960 0.8922
No log 76.0 456 0.7973 -0.0608 0.7973 0.8929
No log 76.3333 458 0.7980 -0.0608 0.7980 0.8933
No log 76.6667 460 0.7867 0.0940 0.7867 0.8869
No log 77.0 462 0.7857 0.0376 0.7857 0.8864
No log 77.3333 464 0.7906 0.0376 0.7906 0.8891
No log 77.6667 466 0.7937 0.0376 0.7937 0.8909
No log 78.0 468 0.7940 0.0410 0.7940 0.8911
No log 78.3333 470 0.8009 0.0509 0.8009 0.8949
No log 78.6667 472 0.8064 0.0570 0.8064 0.8980
No log 79.0 474 0.8033 0.0947 0.8033 0.8962
No log 79.3333 476 0.7889 0.0937 0.7889 0.8882
No log 79.6667 478 0.7736 0.0930 0.7736 0.8796
No log 80.0 480 0.7624 0.1413 0.7624 0.8732
No log 80.3333 482 0.7512 0.1413 0.7512 0.8667
No log 80.6667 484 0.7514 0.0828 0.7514 0.8668
No log 81.0 486 0.7589 0.0828 0.7589 0.8712
No log 81.3333 488 0.7664 0.0828 0.7664 0.8754
No log 81.6667 490 0.7762 0.0828 0.7762 0.8810
No log 82.0 492 0.7859 0.0840 0.7859 0.8865
No log 82.3333 494 0.7882 0.1240 0.7882 0.8878
No log 82.6667 496 0.7908 0.1236 0.7908 0.8893
No log 83.0 498 0.7955 0.0410 0.7955 0.8919
0.2178 83.3333 500 0.7984 0.0902 0.7984 0.8935
0.2178 83.6667 502 0.8034 0.0947 0.8034 0.8963
0.2178 84.0 504 0.8186 0.0192 0.8186 0.9048
0.2178 84.3333 506 0.8279 -0.0180 0.8279 0.9099
0.2178 84.6667 508 0.8332 -0.0180 0.8332 0.9128
0.2178 85.0 510 0.8228 0.0185 0.8228 0.9071
0.2178 85.3333 512 0.8119 0.0905 0.8119 0.9011
0.2178 85.6667 514 0.8079 0.0861 0.8079 0.8988
0.2178 86.0 516 0.8105 0.2005 0.8105 0.9003
0.2178 86.3333 518 0.8151 0.2005 0.8151 0.9028
0.2178 86.6667 520 0.8172 0.2005 0.8172 0.9040
0.2178 87.0 522 0.8145 0.2005 0.8145 0.9025
0.2178 87.3333 524 0.8094 0.2005 0.8094 0.8997
0.2178 87.6667 526 0.8057 0.1240 0.8057 0.8976
0.2178 88.0 528 0.8001 0.1240 0.8001 0.8945
0.2178 88.3333 530 0.7964 0.0426 0.7964 0.8924
0.2178 88.6667 532 0.7974 0.0474 0.7974 0.8930
0.2178 89.0 534 0.8003 0.0474 0.8003 0.8946
0.2178 89.3333 536 0.8017 0.0460 0.8017 0.8954
0.2178 89.6667 538 0.7991 0.0798 0.7991 0.8939

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
1
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for MayBashendy/ArabicNewSplits7_OSS_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k1_task3_organization

Finetuned
(4019)
this model