ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k7_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: 0.7262
  • Qwk: -0.0156
  • Mse: 0.7262
  • Rmse: 0.8521

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 0.0952 2 3.8717 0.0017 3.8717 1.9677
No log 0.1905 4 2.2446 -0.0688 2.2446 1.4982
No log 0.2857 6 1.6004 0.0 1.6004 1.2651
No log 0.3810 8 1.0405 -0.0117 1.0405 1.0200
No log 0.4762 10 1.0887 -0.0736 1.0887 1.0434
No log 0.5714 12 0.9380 -0.0949 0.9380 0.9685
No log 0.6667 14 0.8879 -0.1980 0.8879 0.9423
No log 0.7619 16 0.7756 0.0334 0.7756 0.8807
No log 0.8571 18 0.7362 -0.0069 0.7362 0.8580
No log 0.9524 20 0.7881 -0.0264 0.7881 0.8878
No log 1.0476 22 0.9866 -0.0067 0.9866 0.9933
No log 1.1429 24 1.0202 -0.0149 1.0202 1.0100
No log 1.2381 26 1.0149 -0.0117 1.0149 1.0074
No log 1.3333 28 0.9039 -0.0870 0.9039 0.9507
No log 1.4286 30 0.8077 -0.0331 0.8077 0.8987
No log 1.5238 32 0.8170 -0.0766 0.8170 0.9039
No log 1.6190 34 0.8231 -0.0766 0.8231 0.9072
No log 1.7143 36 0.7673 -0.0695 0.7673 0.8760
No log 1.8095 38 1.4647 0.0658 1.4647 1.2103
No log 1.9048 40 2.1271 -0.0015 2.1271 1.4584
No log 2.0 42 1.7376 0.0 1.7376 1.3182
No log 2.0952 44 1.1816 0.0 1.1816 1.0870
No log 2.1905 46 0.9193 -0.1655 0.9193 0.9588
No log 2.2857 48 0.7556 -0.0644 0.7556 0.8692
No log 2.3810 50 0.7530 -0.0679 0.7530 0.8678
No log 2.4762 52 0.8891 -0.0425 0.8891 0.9429
No log 2.5714 54 0.7632 -0.0644 0.7632 0.8736
No log 2.6667 56 0.7809 0.0479 0.7809 0.8837
No log 2.7619 58 1.0774 0.0134 1.0774 1.0380
No log 2.8571 60 1.2304 0.0238 1.2304 1.1093
No log 2.9524 62 0.7511 -0.0160 0.7511 0.8667
No log 3.0476 64 0.9787 -0.1624 0.9787 0.9893
No log 3.1429 66 0.8980 0.0291 0.8980 0.9476
No log 3.2381 68 0.7921 0.0071 0.7921 0.8900
No log 3.3333 70 0.9437 0.1406 0.9437 0.9714
No log 3.4286 72 0.7555 -0.1662 0.7555 0.8692
No log 3.5238 74 0.7991 0.0085 0.7991 0.8939
No log 3.6190 76 0.8186 0.0660 0.8186 0.9048
No log 3.7143 78 0.8263 -0.0173 0.8263 0.9090
No log 3.8095 80 0.8690 -0.0492 0.8690 0.9322
No log 3.9048 82 0.8800 -0.0492 0.8800 0.9381
No log 4.0 84 0.9201 -0.0717 0.9201 0.9592
No log 4.0952 86 0.9612 -0.1408 0.9612 0.9804
No log 4.1905 88 1.2114 -0.0985 1.2114 1.1007
No log 4.2857 90 1.2460 -0.0433 1.2460 1.1162
No log 4.3810 92 1.1543 -0.1080 1.1543 1.0744
No log 4.4762 94 0.9591 -0.0277 0.9591 0.9793
No log 4.5714 96 1.1362 0.0487 1.1362 1.0659
No log 4.6667 98 0.9176 -0.0223 0.9176 0.9579
No log 4.7619 100 0.8561 0.0173 0.8561 0.9253
No log 4.8571 102 0.8453 0.0240 0.8453 0.9194
No log 4.9524 104 0.8112 0.0151 0.8112 0.9006
No log 5.0476 106 0.8481 -0.0166 0.8481 0.9209
No log 5.1429 108 0.9250 0.0734 0.9250 0.9618
No log 5.2381 110 0.8316 -0.0166 0.8316 0.9119
No log 5.3333 112 0.7962 0.0172 0.7962 0.8923
No log 5.4286 114 0.8201 0.0562 0.8201 0.9056
No log 5.5238 116 0.8276 0.0257 0.8276 0.9097
No log 5.6190 118 1.0065 -0.1016 1.0065 1.0032
No log 5.7143 120 1.1619 -0.0360 1.1619 1.0779
No log 5.8095 122 1.0845 0.0007 1.0845 1.0414
No log 5.9048 124 1.0997 -0.0214 1.0997 1.0487
No log 6.0 126 1.0557 0.0281 1.0557 1.0275
No log 6.0952 128 0.9869 -0.0977 0.9869 0.9934
No log 6.1905 130 0.9119 -0.1067 0.9119 0.9549
No log 6.2857 132 0.8682 0.0167 0.8682 0.9318
No log 6.3810 134 0.8073 -0.0181 0.8073 0.8985
No log 6.4762 136 0.7754 0.0206 0.7754 0.8806
No log 6.5714 138 0.7774 0.0628 0.7774 0.8817
No log 6.6667 140 0.8228 0.0442 0.8228 0.9071
No log 6.7619 142 0.8043 -0.1097 0.8043 0.8968
No log 6.8571 144 0.8481 -0.0949 0.8481 0.9209
No log 6.9524 146 0.8566 0.0178 0.8566 0.9255
No log 7.0476 148 0.9045 0.0245 0.9045 0.9511
No log 7.1429 150 1.2822 0.1922 1.2822 1.1323
No log 7.2381 152 1.0224 0.0233 1.0224 1.0111
No log 7.3333 154 0.8500 0.1038 0.8500 0.9219
No log 7.4286 156 1.0012 -0.0099 1.0012 1.0006
No log 7.5238 158 0.8548 0.1405 0.8548 0.9246
No log 7.6190 160 0.8286 0.0123 0.8286 0.9103
No log 7.7143 162 1.0056 0.0609 1.0056 1.0028
No log 7.8095 164 0.8232 0.0095 0.8232 0.9073
No log 7.9048 166 0.7551 0.0649 0.7551 0.8690
No log 8.0 168 0.7901 -0.0451 0.7901 0.8889
No log 8.0952 170 0.7329 -0.0551 0.7329 0.8561
No log 8.1905 172 0.7186 -0.0609 0.7186 0.8477
No log 8.2857 174 0.7514 -0.0179 0.7514 0.8669
No log 8.3810 176 0.7388 -0.0571 0.7388 0.8595
No log 8.4762 178 0.8560 -0.0121 0.8560 0.9252
No log 8.5714 180 1.0409 0.0129 1.0409 1.0203
No log 8.6667 182 1.0604 0.0446 1.0604 1.0298
No log 8.7619 184 1.0255 -0.0498 1.0255 1.0127
No log 8.8571 186 1.0698 0.0210 1.0698 1.0343
No log 8.9524 188 1.0895 0.0162 1.0895 1.0438
No log 9.0476 190 0.9867 0.0210 0.9867 0.9933
No log 9.1429 192 0.9795 -0.1068 0.9795 0.9897
No log 9.2381 194 1.0220 0.0481 1.0220 1.0109
No log 9.3333 196 0.9753 -0.0685 0.9753 0.9876
No log 9.4286 198 0.9207 -0.0063 0.9207 0.9595
No log 9.5238 200 0.8783 0.0220 0.8783 0.9372
No log 9.6190 202 0.8671 -0.0753 0.8671 0.9312
No log 9.7143 204 0.8733 -0.0605 0.8733 0.9345
No log 9.8095 206 0.8550 -0.0391 0.8550 0.9247
No log 9.9048 208 0.9283 -0.0761 0.9283 0.9635
No log 10.0 210 0.9245 -0.0722 0.9245 0.9615
No log 10.0952 212 0.8300 0.0236 0.8300 0.9111
No log 10.1905 214 0.8786 -0.0322 0.8786 0.9373
No log 10.2857 216 0.8306 -0.0443 0.8306 0.9113
No log 10.3810 218 0.9078 0.0754 0.9078 0.9528
No log 10.4762 220 0.8770 0.0307 0.8770 0.9365
No log 10.5714 222 0.8123 0.0265 0.8123 0.9013
No log 10.6667 224 0.8045 0.0146 0.8045 0.8970
No log 10.7619 226 0.8076 0.0145 0.8076 0.8987
No log 10.8571 228 0.8310 0.0285 0.8310 0.9116
No log 10.9524 230 0.8075 -0.0226 0.8075 0.8986
No log 11.0476 232 0.8324 0.0268 0.8324 0.9123
No log 11.1429 234 0.8135 0.0025 0.8135 0.9019
No log 11.2381 236 0.8230 -0.0024 0.8230 0.9072
No log 11.3333 238 0.8002 0.1049 0.8002 0.8945
No log 11.4286 240 0.7625 -0.0947 0.7625 0.8732
No log 11.5238 242 0.8309 -0.0934 0.8309 0.9115
No log 11.6190 244 0.7966 0.0240 0.7966 0.8925
No log 11.7143 246 0.7581 0.1049 0.7581 0.8707
No log 11.8095 248 0.7779 0.1701 0.7779 0.8820
No log 11.9048 250 0.7301 0.0028 0.7301 0.8545
No log 12.0 252 0.8440 -0.0801 0.8440 0.9187
No log 12.0952 254 1.0977 0.1435 1.0977 1.0477
No log 12.1905 256 1.0556 0.1448 1.0556 1.0274
No log 12.2857 258 0.8197 0.0279 0.8197 0.9054
No log 12.3810 260 0.7905 0.0123 0.7905 0.8891
No log 12.4762 262 0.8498 0.1239 0.8498 0.9218
No log 12.5714 264 0.7724 -0.0274 0.7724 0.8789
No log 12.6667 266 0.7868 0.1408 0.7868 0.8870
No log 12.7619 268 0.7999 0.1408 0.7999 0.8944
No log 12.8571 270 0.8295 0.0628 0.8295 0.9108
No log 12.9524 272 0.7767 0.0026 0.7767 0.8813
No log 13.0476 274 0.7797 0.0214 0.7797 0.8830
No log 13.1429 276 0.7835 0.0359 0.7835 0.8851
No log 13.2381 278 0.8502 -0.0477 0.8502 0.9221
No log 13.3333 280 0.8921 -0.0761 0.8921 0.9445
No log 13.4286 282 0.8033 -0.0181 0.8033 0.8963
No log 13.5238 284 0.7572 -0.0062 0.7572 0.8702
No log 13.6190 286 0.7515 0.0318 0.7515 0.8669
No log 13.7143 288 0.7592 -0.0228 0.7592 0.8713
No log 13.8095 290 0.7873 0.0551 0.7873 0.8873
No log 13.9048 292 0.8064 0.0279 0.8064 0.8980
No log 14.0 294 0.8192 0.1598 0.8192 0.9051
No log 14.0952 296 0.7888 0.0604 0.7888 0.8882
No log 14.1905 298 0.8012 0.2087 0.8012 0.8951
No log 14.2857 300 0.7915 0.0993 0.7915 0.8897
No log 14.3810 302 0.7472 0.0377 0.7472 0.8644
No log 14.4762 304 0.7530 -0.0156 0.7530 0.8678
No log 14.5714 306 0.7904 0.1342 0.7904 0.8890
No log 14.6667 308 0.7576 0.0600 0.7576 0.8704
No log 14.7619 310 0.7315 0.0282 0.7315 0.8553
No log 14.8571 312 0.7555 0.0944 0.7555 0.8692
No log 14.9524 314 0.8187 0.0257 0.8187 0.9048
No log 15.0476 316 0.8587 0.0623 0.8587 0.9267
No log 15.1429 318 0.8668 -0.0099 0.8668 0.9310
No log 15.2381 320 0.9167 -0.0236 0.9167 0.9575
No log 15.3333 322 0.8889 -0.0722 0.8889 0.9428
No log 15.4286 324 0.8285 0.0128 0.8285 0.9102
No log 15.5238 326 0.7731 -0.1067 0.7731 0.8792
No log 15.6190 328 0.7420 -0.0179 0.7420 0.8614
No log 15.7143 330 0.7894 0.0953 0.7894 0.8885
No log 15.8095 332 0.8020 0.0476 0.8020 0.8955
No log 15.9048 334 0.7570 0.0562 0.7570 0.8701
No log 16.0 336 0.7626 -0.0293 0.7626 0.8733
No log 16.0952 338 0.8796 0.0377 0.8796 0.9378
No log 16.1905 340 0.8261 -0.0066 0.8261 0.9089
No log 16.2857 342 0.6993 0.0394 0.6993 0.8363
No log 16.3810 344 0.7443 0.0953 0.7443 0.8627
No log 16.4762 346 0.7792 0.0867 0.7792 0.8827
No log 16.5714 348 0.7001 0.1047 0.7001 0.8367
No log 16.6667 350 0.7346 0.0644 0.7346 0.8571
No log 16.7619 352 0.7679 0.1079 0.7679 0.8763
No log 16.8571 354 0.7605 0.1034 0.7605 0.8721
No log 16.9524 356 0.7572 0.0944 0.7572 0.8702
No log 17.0476 358 0.7464 0.1423 0.7464 0.8640
No log 17.1429 360 0.7457 0.1387 0.7457 0.8635
No log 17.2381 362 0.7259 0.1146 0.7259 0.8520
No log 17.3333 364 0.7436 0.1590 0.7436 0.8623
No log 17.4286 366 0.7684 0.0585 0.7684 0.8766
No log 17.5238 368 0.7352 0.1081 0.7352 0.8574
No log 17.6190 370 0.7193 0.0768 0.7193 0.8481
No log 17.7143 372 0.7400 0.1787 0.7400 0.8602
No log 17.8095 374 0.7666 0.1321 0.7666 0.8756
No log 17.9048 376 0.7678 0.1321 0.7678 0.8762
No log 18.0 378 0.7404 0.0327 0.7404 0.8605
No log 18.0952 380 0.7542 0.0944 0.7542 0.8684
No log 18.1905 382 0.8159 0.0991 0.8159 0.9033
No log 18.2857 384 0.9011 0.0350 0.9011 0.9492
No log 18.3810 386 0.8171 0.0955 0.8171 0.9039
No log 18.4762 388 0.7851 0.1049 0.7851 0.8860
No log 18.5714 390 0.7930 0.1495 0.7930 0.8905
No log 18.6667 392 0.7835 0.1218 0.7835 0.8852
No log 18.7619 394 0.8191 -0.0167 0.8191 0.9051
No log 18.8571 396 0.8095 0.0875 0.8095 0.8997
No log 18.9524 398 0.7948 0.1591 0.7948 0.8915
No log 19.0476 400 0.8012 0.1561 0.8012 0.8951
No log 19.1429 402 0.8405 0.1423 0.8405 0.9168
No log 19.2381 404 0.8491 0.1423 0.8491 0.9215
No log 19.3333 406 0.7943 0.1094 0.7943 0.8913
No log 19.4286 408 0.7940 0.0603 0.7940 0.8910
No log 19.5238 410 0.8350 0.0029 0.8350 0.9138
No log 19.6190 412 0.7928 -0.0111 0.7928 0.8904
No log 19.7143 414 0.7288 0.1395 0.7288 0.8537
No log 19.8095 416 0.7372 0.0639 0.7372 0.8586
No log 19.9048 418 0.7450 0.1141 0.7450 0.8631
No log 20.0 420 0.7879 0.0875 0.7879 0.8876
No log 20.0952 422 0.7977 0.1724 0.7977 0.8931
No log 20.1905 424 0.7503 0.0733 0.7503 0.8662
No log 20.2857 426 0.7555 0.0600 0.7555 0.8692
No log 20.3810 428 0.7337 0.0205 0.7337 0.8566
No log 20.4762 430 0.7378 0.0983 0.7378 0.8590
No log 20.5714 432 0.7649 -0.0121 0.7649 0.8746
No log 20.6667 434 0.7193 -0.0473 0.7193 0.8481
No log 20.7619 436 0.6938 0.1318 0.6938 0.8329
No log 20.8571 438 0.7336 0.0628 0.7336 0.8565
No log 20.9524 440 0.7412 0.0628 0.7412 0.8609
No log 21.0476 442 0.7182 0.1807 0.7182 0.8474
No log 21.1429 444 0.7344 0.1729 0.7344 0.8570
No log 21.2381 446 0.7908 0.0710 0.7908 0.8893
No log 21.3333 448 0.8194 0.0726 0.8194 0.9052
No log 21.4286 450 0.7618 0.1770 0.7618 0.8728
No log 21.5238 452 0.7555 0.1714 0.7555 0.8692
No log 21.6190 454 0.7645 0.1259 0.7645 0.8743
No log 21.7143 456 0.7613 0.1259 0.7613 0.8725
No log 21.8095 458 0.7705 -0.0200 0.7705 0.8778
No log 21.9048 460 0.7634 0.0559 0.7634 0.8738
No log 22.0 462 0.7444 0.1660 0.7444 0.8628
No log 22.0952 464 0.7574 0.2009 0.7574 0.8703
No log 22.1905 466 0.7927 0.1775 0.7927 0.8904
No log 22.2857 468 0.7780 0.0643 0.7780 0.8821
No log 22.3810 470 0.7759 0.1172 0.7759 0.8808
No log 22.4762 472 0.8332 0.0579 0.8332 0.9128
No log 22.5714 474 0.8277 0.0281 0.8277 0.9098
No log 22.6667 476 0.7548 0.1259 0.7548 0.8688
No log 22.7619 478 0.7358 0.0680 0.7358 0.8578
No log 22.8571 480 0.7467 0.1047 0.7467 0.8641
No log 22.9524 482 0.7330 0.1148 0.7330 0.8562
No log 23.0476 484 0.7279 0.1254 0.7279 0.8532
No log 23.1429 486 0.7533 0.1633 0.7533 0.8679
No log 23.2381 488 0.7639 0.1673 0.7639 0.8740
No log 23.3333 490 0.7558 0.0269 0.7558 0.8693
No log 23.4286 492 0.8086 0.0525 0.8086 0.8992
No log 23.5238 494 0.7970 0.1001 0.7970 0.8927
No log 23.6190 496 0.7793 0.1001 0.7793 0.8828
No log 23.7143 498 0.7523 0.1449 0.7523 0.8673
0.2913 23.8095 500 0.7227 0.0639 0.7227 0.8501
0.2913 23.9048 502 0.7285 0.0973 0.7285 0.8535
0.2913 24.0 504 0.7700 0.1131 0.7700 0.8775
0.2913 24.0952 506 0.7580 0.1030 0.7580 0.8707
0.2913 24.1905 508 0.7153 0.0323 0.7153 0.8458
0.2913 24.2857 510 0.7258 0.0709 0.7258 0.8519
0.2913 24.3810 512 0.7557 0.0423 0.7557 0.8693
0.2913 24.4762 514 0.7643 0.0423 0.7643 0.8742
0.2913 24.5714 516 0.7865 0.0464 0.7865 0.8868
0.2913 24.6667 518 0.9070 0.1116 0.9070 0.9524
0.2913 24.7619 520 0.9580 0.1149 0.9580 0.9788
0.2913 24.8571 522 0.8353 0.0303 0.8353 0.9140
0.2913 24.9524 524 0.7216 0.0828 0.7216 0.8494
0.2913 25.0476 526 0.7090 0.0807 0.7090 0.8420
0.2913 25.1429 528 0.7138 0.1379 0.7138 0.8449
0.2913 25.2381 530 0.7538 0.0663 0.7538 0.8682
0.2913 25.3333 532 0.7755 0.0240 0.7755 0.8806
0.2913 25.4286 534 0.7506 0.1080 0.7506 0.8664
0.2913 25.5238 536 0.7381 0.0804 0.7381 0.8592
0.2913 25.6190 538 0.7413 0.0798 0.7413 0.8610
0.2913 25.7143 540 0.7369 0.1146 0.7369 0.8584
0.2913 25.8095 542 0.7279 0.1146 0.7279 0.8532
0.2913 25.9048 544 0.7191 0.1254 0.7191 0.8480
0.2913 26.0 546 0.7088 0.0759 0.7088 0.8419
0.2913 26.0952 548 0.7155 0.0783 0.7155 0.8459
0.2913 26.1905 550 0.7675 -0.0271 0.7675 0.8761
0.2913 26.2857 552 0.7619 -0.0307 0.7619 0.8729
0.2913 26.3810 554 0.7154 0.0303 0.7154 0.8458
0.2913 26.4762 556 0.7382 0.1395 0.7382 0.8592
0.2913 26.5714 558 0.7778 0.2077 0.7778 0.8819
0.2913 26.6667 560 0.7373 0.1449 0.7373 0.8587
0.2913 26.7619 562 0.7371 0.0393 0.7371 0.8585
0.2913 26.8571 564 0.7833 0.0157 0.7833 0.8850
0.2913 26.9524 566 0.7573 0.0474 0.7573 0.8702
0.2913 27.0476 568 0.7279 0.0821 0.7279 0.8532
0.2913 27.1429 570 0.7223 0.0191 0.7223 0.8499
0.2913 27.2381 572 0.7124 -0.0252 0.7124 0.8441
0.2913 27.3333 574 0.7154 -0.0252 0.7154 0.8458
0.2913 27.4286 576 0.7242 0.0869 0.7242 0.8510
0.2913 27.5238 578 0.7481 0.0985 0.7481 0.8649
0.2913 27.6190 580 0.7551 0.0558 0.7551 0.8690
0.2913 27.7143 582 0.7276 0.1796 0.7276 0.8530
0.2913 27.8095 584 0.7306 0.0798 0.7306 0.8548
0.2913 27.9048 586 0.7458 0.0810 0.7458 0.8636
0.2913 28.0 588 0.7635 0.1358 0.7635 0.8738
0.2913 28.0952 590 0.8051 0.0248 0.8051 0.8972
0.2913 28.1905 592 0.7883 0.0989 0.7883 0.8879
0.2913 28.2857 594 0.7414 0.1277 0.7414 0.8610
0.2913 28.3810 596 0.7284 0.1047 0.7284 0.8535
0.2913 28.4762 598 0.7424 0.1047 0.7424 0.8617
0.2913 28.5714 600 0.7376 0.0670 0.7376 0.8588
0.2913 28.6667 602 0.7451 0.0670 0.7451 0.8632
0.2913 28.7619 604 0.7534 -0.0073 0.7534 0.8680
0.2913 28.8571 606 0.7566 0.0361 0.7566 0.8698
0.2913 28.9524 608 0.7516 0.0361 0.7516 0.8670
0.2913 29.0476 610 0.7429 0.0361 0.7429 0.8619
0.2913 29.1429 612 0.7262 -0.0156 0.7262 0.8521

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_run1_AugV5_k7_task3_organization

Finetuned
(4023)
this model