ArabicNewSplits7_FineTuningAraBERT_run2_AugV5_k15_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: 0.9963
  • Qwk: 0.0321
  • Mse: 0.9963
  • Rmse: 0.9982

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 0.0488 2 3.7846 -0.0068 3.7846 1.9454
No log 0.0976 4 1.9715 0.0531 1.9715 1.4041
No log 0.1463 6 2.3801 0.0038 2.3801 1.5428
No log 0.1951 8 2.0195 -0.0060 2.0195 1.4211
No log 0.2439 10 0.9274 -0.0056 0.9274 0.9630
No log 0.2927 12 0.7857 -0.0287 0.7857 0.8864
No log 0.3415 14 0.7818 -0.1244 0.7818 0.8842
No log 0.3902 16 1.3540 -0.0479 1.3540 1.1636
No log 0.4390 18 1.3660 -0.0500 1.3660 1.1688
No log 0.4878 20 1.0813 -0.0695 1.0813 1.0399
No log 0.5366 22 0.8799 0.0609 0.8799 0.9380
No log 0.5854 24 0.8309 0.0377 0.8309 0.9115
No log 0.6341 26 0.7573 -0.0101 0.7573 0.8702
No log 0.6829 28 0.7208 -0.0069 0.7208 0.8490
No log 0.7317 30 0.7683 0.0416 0.7683 0.8765
No log 0.7805 32 0.9391 -0.0101 0.9391 0.9691
No log 0.8293 34 0.9606 0.0176 0.9606 0.9801
No log 0.8780 36 1.0409 -0.0468 1.0409 1.0202
No log 0.9268 38 0.9998 -0.0423 0.9998 0.9999
No log 0.9756 40 0.8364 0.0588 0.8364 0.9145
No log 1.0244 42 0.7584 -0.0131 0.7584 0.8709
No log 1.0732 44 0.6898 0.0 0.6898 0.8305
No log 1.1220 46 0.6922 0.0 0.6922 0.8320
No log 1.1707 48 0.7318 0.0506 0.7318 0.8554
No log 1.2195 50 0.9772 -0.0982 0.9772 0.9885
No log 1.2683 52 1.0739 -0.0468 1.0739 1.0363
No log 1.3171 54 0.8417 0.0017 0.8417 0.9174
No log 1.3659 56 0.7287 0.0506 0.7287 0.8537
No log 1.4146 58 0.7593 0.1202 0.7593 0.8714
No log 1.4634 60 1.1596 0.0518 1.1596 1.0768
No log 1.5122 62 1.0117 -0.0943 1.0117 1.0058
No log 1.5610 64 0.7548 0.1259 0.7548 0.8688
No log 1.6098 66 0.8317 -0.0371 0.8317 0.9120
No log 1.6585 68 0.7260 0.0416 0.7260 0.8521
No log 1.7073 70 0.7197 0.0555 0.7197 0.8483
No log 1.7561 72 0.7025 0.0506 0.7025 0.8381
No log 1.8049 74 1.2826 0.0133 1.2826 1.1325
No log 1.8537 76 1.8717 -0.0000 1.8717 1.3681
No log 1.9024 78 1.5932 -0.0475 1.5932 1.2622
No log 1.9512 80 0.9978 -0.1605 0.9978 0.9989
No log 2.0 82 0.8603 0.0953 0.8603 0.9275
No log 2.0488 84 0.7749 0.1675 0.7749 0.8803
No log 2.0976 86 0.7547 -0.0091 0.7547 0.8687
No log 2.1463 88 0.9295 -0.0007 0.9295 0.9641
No log 2.1951 90 1.1780 -0.0842 1.1780 1.0853
No log 2.2439 92 0.9455 -0.0391 0.9455 0.9724
No log 2.2927 94 1.0249 -0.0837 1.0249 1.0124
No log 2.3415 96 0.8824 -0.0630 0.8824 0.9393
No log 2.3902 98 0.8373 0.0209 0.8373 0.9150
No log 2.4390 100 0.8175 0.1030 0.8175 0.9041
No log 2.4878 102 0.8407 0.0245 0.8407 0.9169
No log 2.5366 104 0.9847 -0.0076 0.9847 0.9923
No log 2.5854 106 0.9448 -0.0030 0.9448 0.9720
No log 2.6341 108 0.8403 -0.0566 0.8403 0.9167
No log 2.6829 110 0.9070 -0.0408 0.9070 0.9524
No log 2.7317 112 0.7936 0.1080 0.7936 0.8909
No log 2.7805 114 1.1568 -0.0648 1.1568 1.0755
No log 2.8293 116 1.5224 -0.0221 1.5224 1.2338
No log 2.8780 118 1.2500 -0.0468 1.2500 1.1180
No log 2.9268 120 0.8800 -0.0122 0.8800 0.9381
No log 2.9756 122 0.7486 0.1828 0.7486 0.8652
No log 3.0244 124 0.7384 0.0662 0.7384 0.8593
No log 3.0732 126 0.7351 0.0436 0.7351 0.8574
No log 3.1220 128 1.1047 -0.0200 1.1047 1.0510
No log 3.1707 130 1.3282 -0.0084 1.3282 1.1525
No log 3.2195 132 0.9354 -0.0163 0.9354 0.9672
No log 3.2683 134 0.7828 -0.0271 0.7828 0.8848
No log 3.3171 136 0.8147 -0.0648 0.8147 0.9026
No log 3.3659 138 0.8664 0.0529 0.8664 0.9308
No log 3.4146 140 0.8942 0.0497 0.8942 0.9456
No log 3.4634 142 0.8138 0.0129 0.8138 0.9021
No log 3.5122 144 0.9741 -0.0099 0.9741 0.9870
No log 3.5610 146 0.9491 0.0180 0.9491 0.9742
No log 3.6098 148 0.7932 0.0856 0.7932 0.8906
No log 3.6585 150 0.9243 0.0424 0.9243 0.9614
No log 3.7073 152 0.8368 0.0913 0.8368 0.9148
No log 3.7561 154 0.7323 0.0513 0.7323 0.8558
No log 3.8049 156 0.7539 -0.0939 0.7539 0.8683
No log 3.8537 158 0.7831 -0.1266 0.7831 0.8849
No log 3.9024 160 0.8395 0.0289 0.8395 0.9162
No log 3.9512 162 1.1363 -0.0870 1.1363 1.0660
No log 4.0 164 1.1097 -0.0500 1.1097 1.0534
No log 4.0488 166 0.9380 -0.0694 0.9380 0.9685
No log 4.0976 168 0.9007 0.0580 0.9007 0.9490
No log 4.1463 170 0.9151 0.0721 0.9151 0.9566
No log 4.1951 172 0.8528 0.1228 0.8528 0.9235
No log 4.2439 174 0.9710 -0.0393 0.9710 0.9854
No log 4.2927 176 0.9381 -0.0391 0.9381 0.9685
No log 4.3415 178 0.8460 0.0600 0.8460 0.9198
No log 4.3902 180 0.7987 0.0783 0.7987 0.8937
No log 4.4390 182 0.7969 -0.0717 0.7969 0.8927
No log 4.4878 184 0.8554 0.0364 0.8554 0.9249
No log 4.5366 186 0.7949 -0.1597 0.7949 0.8916
No log 4.5854 188 0.8051 0.0732 0.8051 0.8973
No log 4.6341 190 1.1065 -0.0533 1.1065 1.0519
No log 4.6829 192 1.0199 -0.0118 1.0199 1.0099
No log 4.7317 194 0.7737 0.0869 0.7737 0.8796
No log 4.7805 196 0.7554 0.0 0.7554 0.8692
No log 4.8293 198 0.7691 -0.0032 0.7691 0.8770
No log 4.8780 200 0.8185 0.1249 0.8185 0.9047
No log 4.9268 202 0.8270 0.0828 0.8270 0.9094
No log 4.9756 204 0.8737 0.0700 0.8737 0.9347
No log 5.0244 206 0.9278 -0.0711 0.9278 0.9632
No log 5.0732 208 0.8374 -0.0118 0.8374 0.9151
No log 5.1220 210 0.8435 -0.1208 0.8435 0.9184
No log 5.1707 212 0.8508 -0.1151 0.8508 0.9224
No log 5.2195 214 0.8798 -0.0408 0.8798 0.9380
No log 5.2683 216 0.9211 0.0749 0.9211 0.9597
No log 5.3171 218 0.9580 -0.0123 0.9580 0.9788
No log 5.3659 220 1.0415 -0.0214 1.0415 1.0205
No log 5.4146 222 0.9582 -0.0266 0.9582 0.9789
No log 5.4634 224 0.9327 -0.0047 0.9327 0.9658
No log 5.5122 226 0.8972 0.0377 0.8972 0.9472
No log 5.5610 228 0.9240 0.0525 0.9240 0.9613
No log 5.6098 230 0.8705 0.1485 0.8705 0.9330
No log 5.6585 232 0.8661 -0.0200 0.8661 0.9307
No log 5.7073 234 0.8698 0.0609 0.8698 0.9326
No log 5.7561 236 0.8821 0.1485 0.8821 0.9392
No log 5.8049 238 0.8814 0.0574 0.8814 0.9388
No log 5.8537 240 0.7768 0.1277 0.7768 0.8814
No log 5.9024 242 0.7863 0.0592 0.7863 0.8868
No log 5.9512 244 0.7956 0.0522 0.7956 0.8920
No log 6.0 246 0.8611 0.1986 0.8611 0.9279
No log 6.0488 248 0.8523 0.2005 0.8523 0.9232
No log 6.0976 250 0.8834 0.1139 0.8834 0.9399
No log 6.1463 252 0.9994 -0.0815 0.9994 0.9997
No log 6.1951 254 1.0641 -0.1226 1.0641 1.0316
No log 6.2439 256 0.9286 0.0799 0.9286 0.9637
No log 6.2927 258 0.8858 0.1407 0.8858 0.9412
No log 6.3415 260 0.8263 0.0494 0.8263 0.9090
No log 6.3902 262 0.8091 0.1095 0.8091 0.8995
No log 6.4390 264 0.9599 -0.0845 0.9599 0.9798
No log 6.4878 266 1.0410 -0.1228 1.0410 1.0203
No log 6.5366 268 0.9933 -0.0845 0.9933 0.9966
No log 6.5854 270 0.8839 0.1049 0.8839 0.9402
No log 6.6341 272 0.8536 -0.0392 0.8536 0.9239
No log 6.6829 274 0.8066 0.0783 0.8066 0.8981
No log 6.7317 276 0.8361 0.1485 0.8361 0.9144
No log 6.7805 278 0.9554 -0.0456 0.9554 0.9774
No log 6.8293 280 0.9537 0.0424 0.9537 0.9766
No log 6.8780 282 0.8660 0.0423 0.8660 0.9306
No log 6.9268 284 0.8771 -0.0056 0.8771 0.9365
No log 6.9756 286 0.8417 0.0518 0.8417 0.9175
No log 7.0244 288 0.8050 -0.0113 0.8050 0.8972
No log 7.0732 290 0.8328 0.0639 0.8328 0.9126
No log 7.1220 292 0.9351 0.0287 0.9351 0.9670
No log 7.1707 294 0.9758 -0.0558 0.9758 0.9878
No log 7.2195 296 0.8814 0.0956 0.8814 0.9388
No log 7.2683 298 0.8369 0.0732 0.8369 0.9148
No log 7.3171 300 0.8778 0.1218 0.8778 0.9369
No log 7.3659 302 0.9652 0.0236 0.9652 0.9824
No log 7.4146 304 1.0892 -0.0349 1.0892 1.0436
No log 7.4634 306 1.3421 -0.0278 1.3421 1.1585
No log 7.5122 308 1.3146 -0.0555 1.3146 1.1465
No log 7.5610 310 1.0203 -0.0870 1.0203 1.0101
No log 7.6098 312 0.9118 -0.0347 0.9118 0.9549
No log 7.6585 314 0.8926 0.0649 0.8926 0.9448
No log 7.7073 316 0.8886 -0.1572 0.8886 0.9426
No log 7.7561 318 0.9278 0.0793 0.9278 0.9632
No log 7.8049 320 1.2408 -0.0890 1.2408 1.1139
No log 7.8537 322 1.2481 -0.0849 1.2481 1.1172
No log 7.9024 324 0.9673 -0.0630 0.9673 0.9835
No log 7.9512 326 0.9428 0.0694 0.9428 0.9710
No log 8.0 328 0.9551 0.0402 0.9551 0.9773
No log 8.0488 330 0.9064 0.0643 0.9064 0.9520
No log 8.0976 332 0.9241 -0.0232 0.9241 0.9613
No log 8.1463 334 0.9767 0.0333 0.9767 0.9883
No log 8.1951 336 0.9418 0.0333 0.9418 0.9705
No log 8.2439 338 0.7476 0.1254 0.7476 0.8646
No log 8.2927 340 0.7128 0.0967 0.7128 0.8443
No log 8.3415 342 0.7202 0.0967 0.7202 0.8486
No log 8.3902 344 0.7716 0.1249 0.7716 0.8784
No log 8.4390 346 0.8375 0.1048 0.8375 0.9151
No log 8.4878 348 0.9398 0.0692 0.9398 0.9694
No log 8.5366 350 0.9678 0.0293 0.9678 0.9838
No log 8.5854 352 0.8429 0.1096 0.8429 0.9181
No log 8.6341 354 0.8260 0.0051 0.8260 0.9088
No log 8.6829 356 0.7987 -0.0389 0.7987 0.8937
No log 8.7317 358 0.7768 0.1254 0.7768 0.8814
No log 8.7805 360 0.8524 0.0909 0.8524 0.9232
No log 8.8293 362 0.8323 0.1286 0.8323 0.9123
No log 8.8780 364 0.7516 0.1254 0.7516 0.8670
No log 8.9268 366 0.7575 -0.0406 0.7575 0.8703
No log 8.9756 368 0.7844 -0.0810 0.7844 0.8856
No log 9.0244 370 0.8073 0.2053 0.8073 0.8985
No log 9.0732 372 1.0427 0.0233 1.0427 1.0211
No log 9.1220 374 1.1315 0.0440 1.1315 1.0637
No log 9.1707 376 0.9723 -0.0030 0.9723 0.9861
No log 9.2195 378 0.8641 -0.0426 0.8641 0.9296
No log 9.2683 380 0.8400 -0.0326 0.8400 0.9165
No log 9.3171 382 0.8384 0.1192 0.8384 0.9156
No log 9.3659 384 0.9665 -0.0094 0.9665 0.9831
No log 9.4146 386 1.0766 -0.0563 1.0766 1.0376
No log 9.4634 388 0.9381 0.0684 0.9381 0.9685
No log 9.5122 390 0.7839 0.1675 0.7839 0.8854
No log 9.5610 392 0.7577 -0.0091 0.7577 0.8705
No log 9.6098 394 0.7607 0.1311 0.7607 0.8722
No log 9.6585 396 0.8535 0.0867 0.8535 0.9239
No log 9.7073 398 0.9121 0.0316 0.9121 0.9550
No log 9.7561 400 0.9302 0.0200 0.9302 0.9645
No log 9.8049 402 0.9169 -0.0073 0.9169 0.9576
No log 9.8537 404 0.8956 0.1379 0.8956 0.9463
No log 9.9024 406 0.8636 0.1094 0.8636 0.9293
No log 9.9512 408 0.8409 0.0749 0.8409 0.9170
No log 10.0 410 0.8726 0.1879 0.8726 0.9341
No log 10.0488 412 1.0097 -0.0073 1.0097 1.0048
No log 10.0976 414 1.1116 -0.0508 1.1116 1.0543
No log 10.1463 416 1.0088 -0.0394 1.0088 1.0044
No log 10.1951 418 0.8974 0.0377 0.8974 0.9473
No log 10.2439 420 0.8317 0.0393 0.8317 0.9120
No log 10.2927 422 0.8177 0.2150 0.8177 0.9043
No log 10.3415 424 0.9448 -0.0504 0.9448 0.9720
No log 10.3902 426 1.0236 -0.0923 1.0236 1.0117
No log 10.4390 428 0.8912 -0.0373 0.8912 0.9441
No log 10.4878 430 0.7793 0.0821 0.7793 0.8828
No log 10.5366 432 0.8102 0.0053 0.8102 0.9001
No log 10.5854 434 0.8023 0.1249 0.8023 0.8957
No log 10.6341 436 0.8866 0.1001 0.8866 0.9416
No log 10.6829 438 0.9676 -0.0496 0.9676 0.9837
No log 10.7317 440 0.9582 -0.0862 0.9582 0.9789
No log 10.7805 442 0.8823 0.1047 0.8823 0.9393
No log 10.8293 444 0.8854 0.1047 0.8854 0.9410
No log 10.8780 446 0.9170 0.1001 0.9170 0.9576
No log 10.9268 448 0.8635 -0.0132 0.8635 0.9293
No log 10.9756 450 0.8391 0.0408 0.8391 0.9160
No log 11.0244 452 0.8555 0.0289 0.8555 0.9249
No log 11.0732 454 0.8991 0.0956 0.8991 0.9482
No log 11.1220 456 0.9617 -0.0456 0.9617 0.9807
No log 11.1707 458 0.9429 -0.0471 0.9429 0.9710
No log 11.2195 460 0.8822 0.1387 0.8822 0.9393
No log 11.2683 462 0.7857 -0.0054 0.7857 0.8864
No log 11.3171 464 0.7756 0.0898 0.7756 0.8807
No log 11.3659 466 0.7503 0.0376 0.7503 0.8662
No log 11.4146 468 0.7960 0.2288 0.7960 0.8922
No log 11.4634 470 0.7774 0.2009 0.7774 0.8817
No log 11.5122 472 0.7503 0.1254 0.7503 0.8662
No log 11.5610 474 0.7337 0.0449 0.7337 0.8566
No log 11.6098 476 0.7530 -0.0366 0.7530 0.8678
No log 11.6585 478 0.7476 0.0028 0.7476 0.8646
No log 11.7073 480 0.7571 0.0394 0.7571 0.8701
No log 11.7561 482 0.7769 0.1196 0.7769 0.8814
No log 11.8049 484 0.7778 0.0428 0.7778 0.8819
No log 11.8537 486 0.8098 -0.0314 0.8098 0.8999
No log 11.9024 488 0.7961 0.0056 0.7961 0.8923
No log 11.9512 490 0.7733 0.0341 0.7733 0.8794
No log 12.0 492 0.7795 0.1146 0.7795 0.8829
No log 12.0488 494 0.7804 0.1553 0.7804 0.8834
No log 12.0976 496 0.7998 0.1553 0.7998 0.8943
No log 12.1463 498 0.7880 0.0690 0.7880 0.8877
0.3031 12.1951 500 0.7461 0.0338 0.7461 0.8638
0.3031 12.2439 502 0.7738 0.2150 0.7738 0.8797
0.3031 12.2927 504 0.8580 0.2155 0.8580 0.9263
0.3031 12.3415 506 0.7824 0.2150 0.7824 0.8845
0.3031 12.3902 508 0.7442 0.1740 0.7442 0.8627
0.3031 12.4390 510 0.7544 0.2063 0.7544 0.8686
0.3031 12.4878 512 0.7697 0.1311 0.7697 0.8773
0.3031 12.5366 514 0.7974 0.2078 0.7974 0.8930
0.3031 12.5854 516 0.8265 0.2009 0.8265 0.9091
0.3031 12.6341 518 0.8174 0.0 0.8174 0.9041
0.3031 12.6829 520 0.8895 -0.0096 0.8895 0.9431
0.3031 12.7317 522 0.9188 -0.0137 0.9188 0.9585
0.3031 12.7805 524 0.9583 0.0183 0.9583 0.9789
0.3031 12.8293 526 0.9963 0.0321 0.9963 0.9982

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
7
Safetensors
Model size
135M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for MayBashendy/ArabicNewSplits7_FineTuningAraBERT_run2_AugV5_k15_task3_organization

Finetuned
(4204)
this model