ArabicNewSplits7_FineTuningAraBERT_run3_AugV5_k14_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: 0.8899
  • Qwk: 0.0517
  • Mse: 0.8899
  • Rmse: 0.9433

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 0.0526 2 3.6263 0.0048 3.6263 1.9043
No log 0.1053 4 1.9756 0.0704 1.9756 1.4056
No log 0.1579 6 1.2226 -0.0228 1.2226 1.1057
No log 0.2105 8 1.1342 -0.0193 1.1342 1.0650
No log 0.2632 10 0.8777 0.0404 0.8777 0.9369
No log 0.3158 12 0.7463 0.1259 0.7463 0.8639
No log 0.3684 14 0.7839 0.0191 0.7839 0.8854
No log 0.4211 16 0.9978 -0.0720 0.9978 0.9989
No log 0.4737 18 0.9106 -0.0949 0.9106 0.9542
No log 0.5263 20 0.7883 -0.0695 0.7883 0.8879
No log 0.5789 22 0.8355 -0.0408 0.8355 0.9141
No log 0.6316 24 0.8359 0.0512 0.8359 0.9143
No log 0.6842 26 0.7455 -0.0035 0.7455 0.8634
No log 0.7368 28 0.7782 -0.0215 0.7782 0.8822
No log 0.7895 30 0.8313 0.0129 0.8313 0.9117
No log 0.8421 32 0.7324 0.0 0.7324 0.8558
No log 0.8947 34 0.7628 -0.0679 0.7628 0.8734
No log 0.9474 36 0.9798 -0.1277 0.9798 0.9899
No log 1.0 38 1.5331 -0.0766 1.5331 1.2382
No log 1.0526 40 1.8056 0.0 1.8056 1.3437
No log 1.1053 42 1.5889 0.0 1.5889 1.2605
No log 1.1579 44 1.2873 -0.0247 1.2873 1.1346
No log 1.2105 46 0.9715 -0.0695 0.9715 0.9856
No log 1.2632 48 0.7724 -0.0131 0.7724 0.8789
No log 1.3158 50 0.7745 -0.1690 0.7745 0.8801
No log 1.3684 52 0.8297 0.0247 0.8297 0.9109
No log 1.4211 54 1.0151 -0.0518 1.0151 1.0075
No log 1.4737 56 1.1257 -0.0943 1.1257 1.0610
No log 1.5263 58 1.0346 -0.0845 1.0346 1.0172
No log 1.5789 60 0.9207 -0.0320 0.9207 0.9595
No log 1.6316 62 0.9556 0.1110 0.9556 0.9776
No log 1.6842 64 1.0015 0.0392 1.0015 1.0008
No log 1.7368 66 0.9566 -0.1449 0.9566 0.9781
No log 1.7895 68 1.0566 -0.1284 1.0566 1.0279
No log 1.8421 70 1.1914 -0.0221 1.1914 1.0915
No log 1.8947 72 1.3730 0.0 1.3730 1.1718
No log 1.9474 74 1.5382 0.0 1.5382 1.2402
No log 2.0 76 1.4374 0.0 1.4374 1.1989
No log 2.0526 78 1.1942 -0.0758 1.1942 1.0928
No log 2.1053 80 1.0463 -0.0992 1.0463 1.0229
No log 2.1579 82 0.9265 0.0065 0.9265 0.9625
No log 2.2105 84 0.9248 0.0146 0.9248 0.9616
No log 2.2632 86 0.9763 -0.0424 0.9763 0.9881
No log 2.3158 88 0.9927 -0.0500 0.9927 0.9963
No log 2.3684 90 0.8793 0.0099 0.8793 0.9377
No log 2.4211 92 0.7551 -0.0644 0.7551 0.8690
No log 2.4737 94 0.7362 0.0555 0.7362 0.8580
No log 2.5263 96 0.7372 -0.0131 0.7372 0.8586
No log 2.5789 98 0.8459 0.0071 0.8459 0.9198
No log 2.6316 100 1.2498 -0.1291 1.2498 1.1179
No log 2.6842 102 1.1845 -0.0638 1.1845 1.0884
No log 2.7368 104 1.1398 -0.1281 1.1398 1.0676
No log 2.7895 106 0.8641 0.0071 0.8641 0.9296
No log 2.8421 108 0.7524 0.0296 0.7524 0.8674
No log 2.8947 110 0.7570 0.0759 0.7570 0.8701
No log 2.9474 112 0.7808 0.0714 0.7808 0.8836
No log 3.0 114 0.8386 -0.0059 0.8386 0.9157
No log 3.0526 116 0.9668 -0.1407 0.9668 0.9833
No log 3.1053 118 1.1570 -0.0837 1.1570 1.0756
No log 3.1579 120 1.2237 -0.0854 1.2237 1.1062
No log 3.2105 122 1.0224 -0.0230 1.0224 1.0111
No log 3.2632 124 1.0091 -0.0870 1.0091 1.0045
No log 3.3158 126 0.9363 -0.1524 0.9363 0.9676
No log 3.3684 128 0.8770 0.0821 0.8770 0.9365
No log 3.4211 130 0.9787 -0.0373 0.9787 0.9893
No log 3.4737 132 0.8872 0.1047 0.8872 0.9419
No log 3.5263 134 0.7798 -0.0578 0.7798 0.8831
No log 3.5789 136 0.7460 0.0541 0.7460 0.8637
No log 3.6316 138 0.7311 -0.0096 0.7311 0.8550
No log 3.6842 140 0.8447 0.0549 0.8447 0.9191
No log 3.7368 142 0.9236 0.0826 0.9236 0.9610
No log 3.7895 144 0.7599 0.1627 0.7599 0.8717
No log 3.8421 146 0.7636 0.0768 0.7636 0.8738
No log 3.8947 148 0.8894 0.0409 0.8894 0.9431
No log 3.9474 150 0.9910 -0.0079 0.9910 0.9955
No log 4.0 152 0.9367 -0.0079 0.9367 0.9678
No log 4.0526 154 0.9029 0.0346 0.9029 0.9502
No log 4.1053 156 0.7933 0.1342 0.7933 0.8907
No log 4.1579 158 0.7938 0.1440 0.7938 0.8909
No log 4.2105 160 0.8698 0.1190 0.8698 0.9326
No log 4.2632 162 0.8858 0.0407 0.8858 0.9412
No log 4.3158 164 1.0152 0.0989 1.0152 1.0076
No log 4.3684 166 0.9325 0.0956 0.9325 0.9656
No log 4.4211 168 1.0310 -0.0425 1.0310 1.0154
No log 4.4737 170 0.9677 0.0490 0.9677 0.9837
No log 4.5263 172 0.9107 -0.1778 0.9107 0.9543
No log 4.5789 174 0.9271 -0.1459 0.9271 0.9629
No log 4.6316 176 1.0049 0.0476 1.0049 1.0024
No log 4.6842 178 1.1754 -0.0175 1.1754 1.0842
No log 4.7368 180 1.0048 0.0786 1.0048 1.0024
No log 4.7895 182 0.8244 -0.1594 0.8244 0.9080
No log 4.8421 184 0.7773 -0.1100 0.7773 0.8816
No log 4.8947 186 0.7593 -0.0725 0.7593 0.8714
No log 4.9474 188 0.9729 0.0748 0.9729 0.9863
No log 5.0 190 1.1914 0.0006 1.1914 1.0915
No log 5.0526 192 0.9706 0.0711 0.9706 0.9852
No log 5.1053 194 0.7750 -0.0264 0.7750 0.8803
No log 5.1579 196 0.8066 0.0191 0.8066 0.8981
No log 5.2105 198 0.7905 -0.0204 0.7905 0.8891
No log 5.2632 200 0.8080 -0.0204 0.8080 0.8989
No log 5.3158 202 0.8006 -0.0628 0.8006 0.8948
No log 5.3684 204 0.8349 0.0588 0.8349 0.9137
No log 5.4211 206 0.8513 0.0999 0.8513 0.9227
No log 5.4737 208 0.8188 0.1047 0.8188 0.9049
No log 5.5263 210 0.9165 0.0409 0.9165 0.9573
No log 5.5789 212 0.8932 0.0409 0.8932 0.9451
No log 5.6316 214 0.7644 -0.0204 0.7644 0.8743
No log 5.6842 216 0.7748 0.0058 0.7748 0.8802
No log 5.7368 218 0.7911 0.0157 0.7911 0.8894
No log 5.7895 220 0.8148 0.0551 0.8148 0.9027
No log 5.8421 222 1.3056 0.0804 1.3056 1.1426
No log 5.8947 224 1.6887 0.0069 1.6887 1.2995
No log 5.9474 226 1.3657 0.0827 1.3657 1.1686
No log 6.0 228 0.8968 0.1141 0.8968 0.9470
No log 6.0526 230 0.8457 0.1039 0.8457 0.9196
No log 6.1053 232 0.8199 0.0690 0.8199 0.9055
No log 6.1579 234 0.6767 0.1021 0.6767 0.8226
No log 6.2105 236 0.7851 0.1553 0.7851 0.8861
No log 6.2632 238 1.1140 0.0305 1.1140 1.0555
No log 6.3158 240 1.1262 0.0604 1.1262 1.0612
No log 6.3684 242 0.8645 0.1150 0.8645 0.9298
No log 6.4211 244 0.7710 -0.0567 0.7710 0.8781
No log 6.4737 246 0.8325 -0.0354 0.8325 0.9124
No log 6.5263 248 0.8534 0.0289 0.8534 0.9238
No log 6.5789 250 0.9155 0.0196 0.9155 0.9568
No log 6.6316 252 1.0250 0.0668 1.0250 1.0124
No log 6.6842 254 1.0085 0.0333 1.0085 1.0042
No log 6.7368 256 0.8805 0.0588 0.8805 0.9384
No log 6.7895 258 0.8011 0.0394 0.8011 0.8950
No log 6.8421 260 0.8613 -0.0622 0.8613 0.9281
No log 6.8947 262 0.9465 0.0999 0.9465 0.9729
No log 6.9474 264 0.9681 0.0471 0.9681 0.9839
No log 7.0 266 0.9984 0.0378 0.9984 0.9992
No log 7.0526 268 0.9557 -0.0022 0.9557 0.9776
No log 7.1053 270 0.8731 0.0071 0.8731 0.9344
No log 7.1579 272 0.8181 -0.0796 0.8181 0.9045
No log 7.2105 274 0.8136 0.0639 0.8136 0.9020
No log 7.2632 276 0.8722 0.1395 0.8722 0.9339
No log 7.3158 278 1.0365 0.0175 1.0365 1.0181
No log 7.3684 280 0.9712 0.0320 0.9712 0.9855
No log 7.4211 282 0.8481 0.0 0.8481 0.9209
No log 7.4737 284 0.8455 -0.0672 0.8455 0.9195
No log 7.5263 286 0.8228 -0.0389 0.8228 0.9071
No log 7.5789 288 0.8017 0.0318 0.8017 0.8954
No log 7.6316 290 0.8905 0.0826 0.8905 0.9437
No log 7.6842 292 0.9631 -0.0097 0.9631 0.9814
No log 7.7368 294 0.9029 0.0377 0.9029 0.9502
No log 7.7895 296 0.8629 0.0318 0.8629 0.9289
No log 7.8421 298 0.9647 0.0966 0.9647 0.9822
No log 7.8947 300 0.9846 0.0970 0.9846 0.9923
No log 7.9474 302 0.9430 0.0444 0.9430 0.9711
No log 8.0 304 1.0031 -0.0598 1.0031 1.0016
No log 8.0526 306 1.0065 -0.0090 1.0065 1.0033
No log 8.1053 308 0.9267 0.0186 0.9267 0.9627
No log 8.1579 310 0.8966 0.0429 0.8966 0.9469
No log 8.2105 312 0.8906 0.0429 0.8906 0.9437
No log 8.2632 314 0.8600 0.0892 0.8600 0.9274
No log 8.3158 316 0.8574 0.1277 0.8574 0.9260
No log 8.3684 318 0.8124 0.1353 0.8124 0.9013
No log 8.4211 320 0.8164 0.1528 0.8164 0.9035
No log 8.4737 322 0.8156 0.1555 0.8156 0.9031
No log 8.5263 324 0.8568 0.0563 0.8568 0.9257
No log 8.5789 326 0.9412 -0.0241 0.9412 0.9701
No log 8.6316 328 0.9373 -0.0241 0.9373 0.9681
No log 8.6842 330 0.8702 -0.0223 0.8702 0.9328
No log 8.7368 332 0.7951 0.0025 0.7951 0.8917
No log 8.7895 334 0.7857 0.0078 0.7857 0.8864
No log 8.8421 336 0.7762 0.0428 0.7762 0.8810
No log 8.8947 338 0.7958 0.0129 0.7958 0.8921
No log 8.9474 340 0.9264 0.0316 0.9264 0.9625
No log 9.0 342 0.9301 -0.0101 0.9301 0.9644
No log 9.0526 344 0.8303 0.0442 0.8303 0.9112
No log 9.1053 346 0.7629 -0.0179 0.7629 0.8735
No log 9.1579 348 0.7824 -0.0612 0.7824 0.8845
No log 9.2105 350 0.8231 -0.0145 0.8231 0.9072
No log 9.2632 352 0.8737 0.0255 0.8737 0.9347
No log 9.3158 354 1.0197 0.0113 1.0197 1.0098
No log 9.3684 356 1.1046 -0.1544 1.1046 1.0510
No log 9.4211 358 1.0257 -0.0341 1.0257 1.0128
No log 9.4737 360 0.9471 0.0953 0.9471 0.9732
No log 9.5263 362 0.8764 -0.0164 0.8764 0.9362
No log 9.5789 364 0.9036 -0.0212 0.9036 0.9506
No log 9.6316 366 0.8868 -0.0184 0.8868 0.9417
No log 9.6842 368 0.8654 0.0161 0.8654 0.9303
No log 9.7368 370 0.8713 0.0140 0.8713 0.9334
No log 9.7895 372 0.8623 0.0959 0.8623 0.9286
No log 9.8421 374 0.8216 0.1244 0.8216 0.9064
No log 9.8947 376 0.8253 0.0341 0.8253 0.9085
No log 9.9474 378 0.8302 -0.0082 0.8302 0.9112
No log 10.0 380 0.7998 -0.0488 0.7998 0.8943
No log 10.0526 382 0.7839 0.0768 0.7839 0.8854
No log 10.1053 384 0.8223 0.0549 0.8223 0.9068
No log 10.1579 386 0.8294 0.0043 0.8294 0.9107
No log 10.2105 388 0.8057 0.0670 0.8057 0.8976
No log 10.2632 390 0.8212 0.1143 0.8212 0.9062
No log 10.3158 392 0.8785 0.0065 0.8785 0.9373
No log 10.3684 394 0.9171 0.0438 0.9171 0.9576
No log 10.4211 396 0.8589 0.0065 0.8589 0.9268
No log 10.4737 398 0.7855 0.0670 0.7855 0.8863
No log 10.5263 400 0.7640 0.0714 0.7640 0.8741
No log 10.5789 402 0.7518 0.0714 0.7518 0.8671
No log 10.6316 404 0.7612 0.0628 0.7612 0.8725
No log 10.6842 406 0.7402 0.0260 0.7402 0.8603
No log 10.7368 408 0.7418 0.0670 0.7418 0.8613
No log 10.7895 410 0.7792 0.1047 0.7792 0.8827
No log 10.8421 412 0.7987 0.0909 0.7987 0.8937
No log 10.8947 414 0.7981 0.0909 0.7981 0.8934
No log 10.9474 416 0.7984 0.0909 0.7984 0.8935
No log 11.0 418 0.7906 0.0953 0.7906 0.8892
No log 11.0526 420 0.8413 0.0909 0.8413 0.9172
No log 11.1053 422 0.8887 0.0748 0.8887 0.9427
No log 11.1579 424 0.9816 -0.0122 0.9816 0.9908
No log 11.2105 426 1.0602 0.0111 1.0602 1.0296
No log 11.2632 428 0.9668 -0.0182 0.9668 0.9833
No log 11.3158 430 0.8190 0.0917 0.8190 0.9050
No log 11.3684 432 0.8283 0.0514 0.8283 0.9101
No log 11.4211 434 0.9089 0.1309 0.9089 0.9533
No log 11.4737 436 0.8760 -0.0266 0.8760 0.9359
No log 11.5263 438 0.8971 -0.0327 0.8971 0.9472
No log 11.5789 440 1.0659 0.0157 1.0659 1.0324
No log 11.6316 442 1.1563 0.0319 1.1563 1.0753
No log 11.6842 444 1.0176 0.0207 1.0176 1.0088
No log 11.7368 446 0.8362 0.1291 0.8362 0.9144
No log 11.7895 448 0.7937 0.0953 0.7937 0.8909
No log 11.8421 450 0.8233 0.1342 0.8233 0.9074
No log 11.8947 452 0.8663 0.1243 0.8663 0.9308
No log 11.9474 454 1.0535 0.0157 1.0535 1.0264
No log 12.0 456 1.2046 0.0586 1.2046 1.0975
No log 12.0526 458 1.1332 0.0086 1.1332 1.0645
No log 12.1053 460 0.9492 0.0016 0.9492 0.9743
No log 12.1579 462 0.8446 0.0504 0.8446 0.9190
No log 12.2105 464 0.8255 -0.0192 0.8255 0.9085
No log 12.2632 466 0.8595 0.0114 0.8595 0.9271
No log 12.3158 468 0.8948 0.0649 0.8948 0.9459
No log 12.3684 470 0.8623 0.0045 0.8623 0.9286
No log 12.4211 472 0.8892 0.0762 0.8892 0.9430
No log 12.4737 474 0.9760 0.0207 0.9760 0.9879
No log 12.5263 476 0.9152 0.0304 0.9152 0.9567
No log 12.5789 478 0.8709 0.0927 0.8709 0.9332
No log 12.6316 480 0.8802 0.0262 0.8802 0.9382
No log 12.6842 482 0.8951 0.0899 0.8951 0.9461
No log 12.7368 484 0.8804 0.0805 0.8804 0.9383
No log 12.7895 486 0.8604 0.1004 0.8604 0.9276
No log 12.8421 488 0.8385 0.0574 0.8385 0.9157
No log 12.8947 490 0.8518 0.0095 0.8518 0.9229
No log 12.9474 492 0.9267 0.0287 0.9267 0.9627
No log 13.0 494 1.0440 0.0157 1.0440 1.0218
No log 13.0526 496 1.0200 -0.0073 1.0200 1.0099
No log 13.1053 498 0.9292 0.0149 0.9292 0.9640
0.3588 13.1579 500 0.9134 0.0618 0.9134 0.9557
0.3588 13.2105 502 0.9310 0.0842 0.9310 0.9649
0.3588 13.2632 504 1.0139 0.0316 1.0139 1.0069
0.3588 13.3158 506 1.1392 -0.0551 1.1392 1.0674
0.3588 13.3684 508 1.1099 -0.0138 1.1099 1.0535
0.3588 13.4211 510 1.0253 0.0762 1.0253 1.0126
0.3588 13.4737 512 0.9858 0.0762 0.9858 0.9929
0.3588 13.5263 514 0.9147 -0.0008 0.9147 0.9564
0.3588 13.5789 516 0.8550 0.1048 0.8550 0.9247
0.3588 13.6316 518 0.8548 0.0257 0.8548 0.9245
0.3588 13.6842 520 0.8924 -0.0070 0.8924 0.9447
0.3588 13.7368 522 0.9458 0.0971 0.9458 0.9725
0.3588 13.7895 524 0.9646 0.0563 0.9646 0.9822
0.3588 13.8421 526 0.9904 0.0336 0.9904 0.9952
0.3588 13.8947 528 1.0204 0.0129 1.0204 1.0101
0.3588 13.9474 530 0.9561 -0.0532 0.9561 0.9778
0.3588 14.0 532 0.8899 0.0517 0.8899 0.9433

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
4
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_FineTuningAraBERT_run3_AugV5_k14_task3_organization

Finetuned
(4040)
this model