ArabicNewSplits7_FineTuningAraBERT_run3_AugV5_k8_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: 0.9043
  • Qwk: -0.0425
  • Mse: 0.9043
  • Rmse: 0.9509

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 0.0870 2 3.7685 0.0029 3.7685 1.9413
No log 0.1739 4 1.8078 0.0153 1.8078 1.3445
No log 0.2609 6 0.9744 0.0486 0.9744 0.9871
No log 0.3478 8 0.7722 0.0857 0.7722 0.8787
No log 0.4348 10 1.0533 -0.0899 1.0533 1.0263
No log 0.5217 12 1.0606 -0.0551 1.0606 1.0299
No log 0.6087 14 0.8048 0.0759 0.8048 0.8971
No log 0.6957 16 0.7939 0.1379 0.7939 0.8910
No log 0.7826 18 0.8052 -0.1233 0.8052 0.8973
No log 0.8696 20 0.9424 -0.0558 0.9424 0.9708
No log 0.9565 22 1.1254 -0.0677 1.1254 1.0609
No log 1.0435 24 1.4305 -0.0247 1.4305 1.1960
No log 1.1304 26 1.1228 -0.0164 1.1228 1.0596
No log 1.2174 28 1.0315 -0.0398 1.0314 1.0156
No log 1.3043 30 0.9656 -0.0301 0.9656 0.9827
No log 1.3913 32 0.9574 -0.0583 0.9574 0.9785
No log 1.4783 34 1.0354 -0.0982 1.0354 1.0175
No log 1.5652 36 0.9483 -0.0583 0.9483 0.9738
No log 1.6522 38 1.0491 -0.1285 1.0491 1.0243
No log 1.7391 40 0.9517 -0.0902 0.9517 0.9756
No log 1.8261 42 0.8323 -0.1153 0.8323 0.9123
No log 1.9130 44 0.8449 -0.0609 0.8449 0.9192
No log 2.0 46 0.9879 -0.0886 0.9879 0.9939
No log 2.0870 48 1.1755 -0.0987 1.1755 1.0842
No log 2.1739 50 1.6511 -0.0247 1.6511 1.2850
No log 2.2609 52 1.4046 -0.1294 1.4046 1.1852
No log 2.3478 54 0.9877 -0.0200 0.9877 0.9938
No log 2.4348 56 0.9223 -0.0894 0.9223 0.9603
No log 2.5217 58 1.0020 -0.0930 1.0020 1.0010
No log 2.6087 60 1.0618 -0.0695 1.0618 1.0304
No log 2.6957 62 1.0927 -0.0117 1.0927 1.0453
No log 2.7826 64 0.8645 -0.0391 0.8645 0.9298
No log 2.8696 66 0.8232 -0.0188 0.8232 0.9073
No log 2.9565 68 0.8185 -0.0660 0.8185 0.9047
No log 3.0435 70 0.8794 -0.0532 0.8794 0.9378
No log 3.1304 72 0.9231 -0.0571 0.9231 0.9608
No log 3.2174 74 0.8804 0.1107 0.8804 0.9383
No log 3.3043 76 0.8032 0.0476 0.8032 0.8962
No log 3.3913 78 0.8387 -0.1397 0.8387 0.9158
No log 3.4783 80 0.7938 -0.1001 0.7938 0.8909
No log 3.5652 82 0.8823 0.0017 0.8823 0.9393
No log 3.6522 84 1.0283 -0.0545 1.0283 1.0141
No log 3.7391 86 0.9180 -0.0545 0.9180 0.9581
No log 3.8261 88 1.1575 0.0331 1.1575 1.0759
No log 3.9130 90 0.8152 -0.0690 0.8152 0.9029
No log 4.0 92 0.8016 0.0479 0.8016 0.8953
No log 4.0870 94 0.9229 -0.1131 0.9229 0.9607
No log 4.1739 96 1.2846 -0.0272 1.2846 1.1334
No log 4.2609 98 1.0853 -0.0106 1.0853 1.0418
No log 4.3478 100 0.8506 -0.0573 0.8506 0.9223
No log 4.4348 102 0.9272 -0.1107 0.9272 0.9629
No log 4.5217 104 1.3694 0.1240 1.3694 1.1702
No log 4.6087 106 1.0222 0.0175 1.0222 1.0110
No log 4.6957 108 0.7658 0.0449 0.7658 0.8751
No log 4.7826 110 0.7587 0.0303 0.7587 0.8710
No log 4.8696 112 0.7354 0.0909 0.7354 0.8575
No log 4.9565 114 0.9358 -0.0056 0.9358 0.9674
No log 5.0435 116 1.6568 0.0776 1.6568 1.2872
No log 5.1304 118 1.8787 0.0372 1.8787 1.3707
No log 5.2174 120 1.2961 0.0819 1.2961 1.1385
No log 5.3043 122 0.7384 0.0247 0.7384 0.8593
No log 5.3913 124 0.7256 -0.0551 0.7256 0.8518
No log 5.4783 126 0.7127 0.0914 0.7127 0.8442
No log 5.5652 128 1.0295 0.0651 1.0295 1.0146
No log 5.6522 130 1.3748 -0.0141 1.3748 1.1725
No log 5.7391 132 1.0534 0.0974 1.0534 1.0264
No log 5.8261 134 0.7287 0.1612 0.7287 0.8536
No log 5.9130 136 0.7715 0.1286 0.7715 0.8783
No log 6.0 138 1.1012 0.1334 1.1012 1.0494
No log 6.0870 140 0.9648 0.0986 0.9648 0.9823
No log 6.1739 142 0.8157 0.1006 0.8157 0.9031
No log 6.2609 144 0.9661 -0.0393 0.9661 0.9829
No log 6.3478 146 1.4279 -0.0045 1.4279 1.1949
No log 6.4348 148 1.1882 -0.0589 1.1882 1.0901
No log 6.5217 150 0.9139 -0.0008 0.9139 0.9560
No log 6.6087 152 0.8813 -0.0031 0.8813 0.9388
No log 6.6957 154 0.8459 0.0392 0.8459 0.9197
No log 6.7826 156 0.8449 -0.0355 0.8449 0.9192
No log 6.8696 158 0.9801 -0.0182 0.9801 0.9900
No log 6.9565 160 1.0933 -0.0218 1.0933 1.0456
No log 7.0435 162 0.9889 -0.0854 0.9889 0.9945
No log 7.1304 164 0.8686 0.1277 0.8686 0.9320
No log 7.2174 166 0.9924 0.1077 0.9924 0.9962
No log 7.3043 168 0.8764 0.1262 0.8764 0.9362
No log 7.3913 170 0.9905 -0.0028 0.9905 0.9952
No log 7.4783 172 1.4759 0.0895 1.4759 1.2149
No log 7.5652 174 1.1889 -0.0245 1.1889 1.0903
No log 7.6522 176 0.8077 0.0764 0.8077 0.8987
No log 7.7391 178 0.8253 0.1865 0.8253 0.9085
No log 7.8261 180 0.9057 0.0208 0.9057 0.9517
No log 7.9130 182 1.3675 -0.0937 1.3675 1.1694
No log 8.0 184 1.5043 -0.0399 1.5043 1.2265
No log 8.0870 186 1.0931 -0.0823 1.0931 1.0455
No log 8.1739 188 0.8939 -0.0166 0.8939 0.9455
No log 8.2609 190 1.0238 0.0512 1.0238 1.0118
No log 8.3478 192 0.8957 -0.0843 0.8957 0.9464
No log 8.4348 194 0.7869 -0.0125 0.7869 0.8871
No log 8.5217 196 1.1216 -0.0301 1.1216 1.0590
No log 8.6087 198 1.5210 0.0029 1.5210 1.2333
No log 8.6957 200 1.3638 0.0126 1.3638 1.1678
No log 8.7826 202 0.9327 -0.0504 0.9327 0.9657
No log 8.8696 204 0.8199 -0.0316 0.8199 0.9055
No log 8.9565 206 0.8335 -0.0393 0.8335 0.9130
No log 9.0435 208 0.7577 0.0183 0.7577 0.8705
No log 9.1304 210 0.7144 -0.0113 0.7144 0.8452
No log 9.2174 212 0.8565 0.1316 0.8565 0.9255
No log 9.3043 214 1.1226 0.1609 1.1226 1.0595
No log 9.3913 216 0.8806 0.0909 0.8806 0.9384
No log 9.4783 218 0.7030 0.1565 0.7030 0.8384
No log 9.5652 220 0.6664 0.1082 0.6664 0.8163
No log 9.6522 222 0.7012 0.0759 0.7012 0.8374
No log 9.7391 224 0.9509 0.0067 0.9509 0.9752
No log 9.8261 226 1.2756 0.0065 1.2756 1.1294
No log 9.9130 228 1.1491 -0.0398 1.1491 1.0720
No log 10.0 230 0.9390 0.0067 0.9390 0.9690
No log 10.0870 232 0.7615 0.0159 0.7615 0.8726
No log 10.1739 234 0.7563 0.0296 0.7563 0.8697
No log 10.2609 236 0.8451 -0.0331 0.8451 0.9193
No log 10.3478 238 0.9953 0.0316 0.9953 0.9976
No log 10.4348 240 0.8901 0.0748 0.8901 0.9434
No log 10.5217 242 0.7546 -0.0309 0.7546 0.8687
No log 10.6087 244 0.7472 0.0680 0.7472 0.8644
No log 10.6957 246 0.8150 0.0867 0.8150 0.9028
No log 10.7826 248 0.9376 0.0157 0.9376 0.9683
No log 10.8696 250 0.8983 0.0424 0.8983 0.9478
No log 10.9565 252 0.8174 0.0562 0.8174 0.9041
No log 11.0435 254 0.7933 -0.0488 0.7933 0.8907
No log 11.1304 256 0.8137 -0.0125 0.8137 0.9021
No log 11.2174 258 0.9655 0.0316 0.9655 0.9826
No log 11.3043 260 1.1144 -0.1564 1.1144 1.0557
No log 11.3913 262 1.0117 -0.1271 1.0117 1.0058
No log 11.4783 264 0.7794 -0.0188 0.7794 0.8829
No log 11.5652 266 0.7750 -0.0939 0.7750 0.8803
No log 11.6522 268 0.7580 -0.0506 0.7580 0.8706
No log 11.7391 270 0.9110 -0.0079 0.9110 0.9545
No log 11.8261 272 1.0578 0.0157 1.0578 1.0285
No log 11.9130 274 1.0459 0.0111 1.0459 1.0227
No log 12.0 276 0.7743 0.0628 0.7743 0.8800
No log 12.0870 278 0.7256 0.0524 0.7256 0.8518
No log 12.1739 280 0.7323 0.1379 0.7323 0.8557
No log 12.2609 282 0.7490 0.1202 0.7490 0.8654
No log 12.3478 284 0.8194 -0.0390 0.8194 0.9052
No log 12.4348 286 0.8048 0.0095 0.8048 0.8971
No log 12.5217 288 0.7923 0.0889 0.7923 0.8901
No log 12.6087 290 0.8099 0.0148 0.8099 0.8999
No log 12.6957 292 0.8314 -0.0682 0.8314 0.9118
No log 12.7826 294 0.9243 -0.0408 0.9243 0.9614
No log 12.8696 296 0.9182 -0.0408 0.9182 0.9582
No log 12.9565 298 0.9767 -0.1273 0.9767 0.9883
No log 13.0435 300 1.1438 0.0006 1.1438 1.0695
No log 13.1304 302 1.0061 -0.0253 1.0061 1.0031
No log 13.2174 304 0.8115 0.0159 0.8115 0.9008
No log 13.3043 306 0.7897 -0.0627 0.7897 0.8887
No log 13.3913 308 0.8428 0.0017 0.8428 0.9181
No log 13.4783 310 0.9572 -0.0923 0.9572 0.9784
No log 13.5652 312 0.9598 -0.1636 0.9598 0.9797
No log 13.6522 314 0.9902 -0.1589 0.9902 0.9951
No log 13.7391 316 1.0155 -0.1224 1.0155 1.0077
No log 13.8261 318 0.9478 -0.0757 0.9478 0.9736
No log 13.9130 320 0.9593 -0.1270 0.9593 0.9794
No log 14.0 322 0.8512 0.0588 0.8512 0.9226
No log 14.0870 324 0.8411 0.0099 0.8411 0.9171
No log 14.1739 326 0.8495 -0.0390 0.8495 0.9217
No log 14.2609 328 0.8779 -0.0408 0.8779 0.9370
No log 14.3478 330 0.8252 0.1097 0.8252 0.9084
No log 14.4348 332 0.8209 0.1787 0.8209 0.9060
No log 14.5217 334 0.8408 0.1541 0.8408 0.9170
No log 14.6087 336 0.8554 0.1048 0.8554 0.9249
No log 14.6957 338 1.0115 -0.0571 1.0115 1.0057
No log 14.7826 340 1.0311 -0.1620 1.0311 1.0154
No log 14.8696 342 0.8640 0.0113 0.8640 0.9295
No log 14.9565 344 0.8267 0.0465 0.8267 0.9093
No log 15.0435 346 0.8076 0.0056 0.8076 0.8987
No log 15.1304 348 0.7918 0.0732 0.7918 0.8898
No log 15.2174 350 0.9516 -0.0182 0.9516 0.9755
No log 15.3043 352 1.0661 0.0006 1.0661 1.0325
No log 15.3913 354 0.8815 -0.0163 0.8815 0.9389
No log 15.4783 356 0.7324 0.0416 0.7324 0.8558
No log 15.5652 358 0.7449 -0.0499 0.7449 0.8630
No log 15.6522 360 0.7404 -0.1143 0.7404 0.8604
No log 15.7391 362 0.7786 0.1148 0.7786 0.8824
No log 15.8261 364 0.9235 -0.0902 0.9235 0.9610
No log 15.9130 366 0.9859 -0.0253 0.9859 0.9929
No log 16.0 368 0.8624 -0.0504 0.8624 0.9287
No log 16.0870 370 0.7630 0.1202 0.7630 0.8735
No log 16.1739 372 0.7745 0.1148 0.7745 0.8801
No log 16.2609 374 0.8636 0.0316 0.8636 0.9293
No log 16.3478 376 0.9962 -0.0253 0.9962 0.9981
No log 16.4348 378 0.9405 -0.0218 0.9405 0.9698
No log 16.5217 380 0.7970 0.0588 0.7970 0.8927
No log 16.6087 382 0.7727 0.0436 0.7727 0.8790
No log 16.6957 384 0.7975 0.0282 0.7975 0.8930
No log 16.7826 386 0.8658 0.0600 0.8658 0.9305
No log 16.8696 388 1.0528 -0.1624 1.0528 1.0261
No log 16.9565 390 1.0373 -0.0923 1.0373 1.0185
No log 17.0435 392 0.8692 0.0205 0.8692 0.9323
No log 17.1304 394 0.8268 0.0557 0.8268 0.9093
No log 17.2174 396 0.8111 -0.0027 0.8111 0.9006
No log 17.3043 398 0.8610 0.0071 0.8610 0.9279
No log 17.3913 400 1.0022 -0.0923 1.0022 1.0011
No log 17.4783 402 1.0735 -0.0955 1.0735 1.0361
No log 17.5652 404 0.9298 -0.0916 0.9298 0.9642
No log 17.6522 406 0.7893 0.1311 0.7893 0.8884
No log 17.7391 408 0.8105 -0.1142 0.8105 0.9003
No log 17.8261 410 0.8295 -0.0982 0.8295 0.9108
No log 17.9130 412 0.8190 0.0930 0.8190 0.9050
No log 18.0 414 0.9296 -0.1226 0.9296 0.9642
No log 18.0870 416 1.0382 -0.0961 1.0382 1.0189
No log 18.1739 418 0.9972 -0.0583 0.9972 0.9986
No log 18.2609 420 0.8939 -0.0490 0.8939 0.9455
No log 18.3478 422 0.8425 0.0146 0.8425 0.9179
No log 18.4348 424 0.8307 0.0639 0.8307 0.9114
No log 18.5217 426 0.8553 -0.0425 0.8553 0.9248
No log 18.6087 428 0.9344 -0.0930 0.9344 0.9666
No log 18.6957 430 0.9151 -0.0200 0.9151 0.9566
No log 18.7826 432 0.8159 0.0549 0.8159 0.9033
No log 18.8696 434 0.7722 0.1552 0.7722 0.8788
No log 18.9565 436 0.7893 0.0122 0.7893 0.8884
No log 19.0435 438 0.7800 0.1486 0.7800 0.8832
No log 19.1304 440 0.8247 0.0512 0.8247 0.9082
No log 19.2174 442 0.9048 -0.0894 0.9048 0.9512
No log 19.3043 444 0.8832 -0.0504 0.8832 0.9398
No log 19.3913 446 0.8402 0.0639 0.8402 0.9166
No log 19.4783 448 0.8347 -0.0156 0.8347 0.9136
No log 19.5652 450 0.8778 0.0068 0.8778 0.9369
No log 19.6522 452 1.0223 -0.0571 1.0223 1.0111
No log 19.7391 454 1.1985 -0.0982 1.1985 1.0948
No log 19.8261 456 1.1966 -0.0982 1.1966 1.0939
No log 19.9130 458 0.9973 -0.0218 0.9973 0.9987
No log 20.0 460 0.8565 0.0245 0.8565 0.9255
No log 20.0870 462 0.8399 0.0141 0.8399 0.9165
No log 20.1739 464 0.8086 0.0934 0.8086 0.8992
No log 20.2609 466 0.8766 -0.0442 0.8766 0.9363
No log 20.3478 468 1.0546 -0.0961 1.0546 1.0269
No log 20.4348 470 1.0812 -0.0961 1.0812 1.0398
No log 20.5217 472 0.9311 -0.0518 0.9311 0.9650
No log 20.6087 474 0.7883 0.0714 0.7883 0.8878
No log 20.6957 476 0.7649 0.0524 0.7649 0.8746
No log 20.7826 478 0.7704 0.1444 0.7704 0.8777
No log 20.8696 480 0.8639 -0.0442 0.8639 0.9294
No log 20.9565 482 1.0242 -0.1282 1.0242 1.0120
No log 21.0435 484 1.1075 -0.0977 1.1075 1.0524
No log 21.1304 486 1.0268 -0.1281 1.0268 1.0133
No log 21.2174 488 0.8706 -0.0442 0.8706 0.9330
No log 21.3043 490 0.7996 0.0834 0.7996 0.8942
No log 21.3913 492 0.8009 0.0085 0.8009 0.8949
No log 21.4783 494 0.8030 0.0085 0.8030 0.8961
No log 21.5652 496 0.8146 0.0741 0.8146 0.9025
No log 21.6522 498 0.8924 0.0287 0.8924 0.9447
0.3341 21.7391 500 0.8988 0.0233 0.8988 0.9480
0.3341 21.8261 502 0.8060 0.1342 0.8060 0.8978
0.3341 21.9130 504 0.7586 0.1691 0.7586 0.8710
0.3341 22.0 506 0.7533 0.1758 0.7533 0.8679
0.3341 22.0870 508 0.7850 0.1395 0.7850 0.8860
0.3341 22.1739 510 0.8297 0.0711 0.8297 0.9109
0.3341 22.2609 512 0.8467 0.0711 0.8467 0.9202
0.3341 22.3478 514 0.8724 0.0711 0.8724 0.9340
0.3341 22.4348 516 0.9415 0.0984 0.9415 0.9703
0.3341 22.5217 518 0.9543 0.0576 0.9543 0.9769
0.3341 22.6087 520 0.9070 0.0316 0.9070 0.9524
0.3341 22.6957 522 0.8867 0.0377 0.8867 0.9416
0.3341 22.7826 524 0.8453 0.0512 0.8453 0.9194
0.3341 22.8696 526 0.7923 0.1146 0.7923 0.8901
0.3341 22.9565 528 0.7801 0.0355 0.7801 0.8832
0.3341 23.0435 530 0.8108 0.0628 0.8108 0.9004
0.3341 23.1304 532 0.8642 0.0999 0.8642 0.9296
0.3341 23.2174 534 0.9563 -0.0870 0.9563 0.9779
0.3341 23.3043 536 0.9076 0.0442 0.9076 0.9527
0.3341 23.3913 538 0.8216 0.1599 0.8216 0.9064
0.3341 23.4783 540 0.8376 -0.1204 0.8376 0.9152
0.3341 23.5652 542 0.8534 -0.1039 0.8534 0.9238
0.3341 23.6522 544 0.8626 -0.0475 0.8626 0.9288
0.3341 23.7391 546 0.9764 0.0293 0.9764 0.9881
0.3341 23.8261 548 1.0615 -0.0923 1.0615 1.0303
0.3341 23.9130 550 1.0139 -0.0200 1.0139 1.0069
0.3341 24.0 552 0.9510 0.0392 0.9510 0.9752
0.3341 24.0870 554 0.9065 -0.0260 0.9065 0.9521
0.3341 24.1739 556 0.9305 0.0421 0.9305 0.9646
0.3341 24.2609 558 0.9239 0.0452 0.9239 0.9612
0.3341 24.3478 560 0.8444 0.0670 0.8444 0.9189
0.3341 24.4348 562 0.8578 0.1049 0.8578 0.9261
0.3341 24.5217 564 0.9372 -0.0442 0.9372 0.9681
0.3341 24.6087 566 1.0750 -0.1281 1.0750 1.0368
0.3341 24.6957 568 1.1073 -0.1283 1.1073 1.0523
0.3341 24.7826 570 1.0160 -0.0930 1.0160 1.0080
0.3341 24.8696 572 0.9043 -0.0425 0.9043 0.9509

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
6
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_run3_AugV5_k8_task3_organization

Finetuned
(4205)
this model