ArabicNewSplits7_FineTuningAraBERT_run2_AugV5_k9_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: 0.8628
  • Qwk: 0.0748
  • Mse: 0.8628
  • Rmse: 0.9289

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 0.0769 2 3.6484 -0.0068 3.6484 1.9101
No log 0.1538 4 2.2368 -0.0496 2.2368 1.4956
No log 0.2308 6 1.3740 0.0016 1.3740 1.1722
No log 0.3077 8 1.0688 -0.1276 1.0688 1.0338
No log 0.3846 10 0.8674 -0.2238 0.8674 0.9314
No log 0.4615 12 0.7534 -0.0069 0.7534 0.8680
No log 0.5385 14 0.8214 -0.1233 0.8214 0.9063
No log 0.6154 16 1.0710 -0.0892 1.0710 1.0349
No log 0.6923 18 0.9421 -0.0459 0.9421 0.9706
No log 0.7692 20 0.8311 0.0670 0.8311 0.9117
No log 0.8462 22 0.9057 -0.0474 0.9057 0.9517
No log 0.9231 24 0.8799 0.0642 0.8799 0.9380
No log 1.0 26 0.8703 0.0157 0.8703 0.9329
No log 1.0769 28 0.8515 -0.0163 0.8515 0.9227
No log 1.1538 30 0.8824 0.0017 0.8824 0.9394
No log 1.2308 32 0.8780 0.0909 0.8780 0.9370
No log 1.3077 34 0.9661 0.0287 0.9661 0.9829
No log 1.3846 36 0.7051 0.0857 0.7051 0.8397
No log 1.4615 38 0.7020 0.0555 0.7020 0.8378
No log 1.5385 40 0.7422 -0.0188 0.7422 0.8615
No log 1.6154 42 0.8992 -0.0878 0.8992 0.9483
No log 1.6923 44 1.2600 0.0098 1.2600 1.1225
No log 1.7692 46 1.5706 0.0252 1.5706 1.2532
No log 1.8462 48 1.3789 0.0130 1.3789 1.1743
No log 1.9231 50 0.9283 -0.1660 0.9283 0.9635
No log 2.0 52 0.8284 -0.0790 0.8284 0.9102
No log 2.0769 54 0.8089 -0.0753 0.8089 0.8994
No log 2.1538 56 0.9125 -0.1676 0.9125 0.9552
No log 2.2308 58 1.0382 -0.0163 1.0382 1.0189
No log 2.3077 60 0.9793 -0.2080 0.9793 0.9896
No log 2.3846 62 0.8677 -0.0739 0.8677 0.9315
No log 2.4615 64 0.9150 -0.2184 0.9150 0.9566
No log 2.5385 66 1.1442 -0.2380 1.1442 1.0697
No log 2.6154 68 1.6756 -0.0654 1.6756 1.2944
No log 2.6923 70 1.8312 -0.0256 1.8312 1.3532
No log 2.7692 72 1.5139 0.0379 1.5139 1.2304
No log 2.8462 74 1.1504 0.0329 1.1504 1.0726
No log 2.9231 76 0.9269 0.0786 0.9269 0.9628
No log 3.0 78 0.8579 0.0456 0.8579 0.9262
No log 3.0769 80 0.9176 0.0727 0.9176 0.9579
No log 3.1538 82 1.2414 -0.0579 1.2414 1.1142
No log 3.2308 84 1.9543 0.0161 1.9543 1.3980
No log 3.3077 86 1.7921 0.0650 1.7921 1.3387
No log 3.3846 88 1.0915 -0.0579 1.0915 1.0448
No log 3.4615 90 0.9569 -0.0878 0.9569 0.9782
No log 3.5385 92 1.0591 -0.1734 1.0591 1.0291
No log 3.6154 94 1.0371 -0.1734 1.0371 1.0184
No log 3.6923 96 1.1291 -0.0353 1.1291 1.0626
No log 3.7692 98 1.4768 0.0636 1.4768 1.2152
No log 3.8462 100 1.4564 0.0112 1.4564 1.2068
No log 3.9231 102 1.1082 -0.0334 1.1082 1.0527
No log 4.0 104 0.8082 -0.1168 0.8082 0.8990
No log 4.0769 106 0.8372 -0.1074 0.8372 0.9150
No log 4.1538 108 0.8188 -0.1143 0.8188 0.9049
No log 4.2308 110 0.8136 0.0555 0.8136 0.9020
No log 4.3077 112 0.8861 -0.1246 0.8861 0.9413
No log 4.3846 114 1.0437 -0.1279 1.0437 1.0216
No log 4.4615 116 1.1453 -0.1281 1.1453 1.0702
No log 4.5385 118 1.1722 -0.0883 1.1722 1.0827
No log 4.6154 120 1.0675 -0.1111 1.0675 1.0332
No log 4.6923 122 0.9965 -0.1450 0.9965 0.9983
No log 4.7692 124 1.0712 -0.1070 1.0712 1.0350
No log 4.8462 126 1.3117 -0.0761 1.3117 1.1453
No log 4.9231 128 1.4816 -0.0276 1.4816 1.2172
No log 5.0 130 1.4507 -0.0238 1.4507 1.2045
No log 5.0769 132 1.2958 -0.0785 1.2958 1.1383
No log 5.1538 134 1.1077 -0.0409 1.1077 1.0525
No log 5.2308 136 1.0113 -0.0378 1.0113 1.0056
No log 5.3077 138 0.9969 -0.1152 0.9969 0.9984
No log 5.3846 140 0.9806 -0.1994 0.9806 0.9903
No log 5.4615 142 1.0776 -0.1446 1.0776 1.0381
No log 5.5385 144 1.2707 -0.1144 1.2707 1.1273
No log 5.6154 146 1.3019 -0.0820 1.3019 1.1410
No log 5.6923 148 1.2315 -0.1172 1.2315 1.1097
No log 5.7692 150 1.1253 -0.1549 1.1253 1.0608
No log 5.8462 152 1.1173 -0.0934 1.1173 1.0570
No log 5.9231 154 1.1630 -0.0920 1.1630 1.0784
No log 6.0 156 1.2131 -0.0721 1.2131 1.1014
No log 6.0769 158 1.2229 0.0138 1.2229 1.1059
No log 6.1538 160 1.0681 -0.0986 1.0681 1.0335
No log 6.2308 162 0.9658 0.0482 0.9658 0.9827
No log 6.3077 164 0.9309 0.0151 0.9309 0.9648
No log 6.3846 166 0.9673 -0.1386 0.9673 0.9835
No log 6.4615 168 0.9752 -0.0760 0.9752 0.9875
No log 6.5385 170 0.9718 0.0014 0.9718 0.9858
No log 6.6154 172 0.9887 0.0120 0.9887 0.9944
No log 6.6923 174 1.0750 -0.0204 1.0750 1.0368
No log 6.7692 176 1.1127 -0.1289 1.1127 1.0548
No log 6.8462 178 1.1248 -0.1389 1.1248 1.0606
No log 6.9231 180 1.0307 -0.1806 1.0307 1.0152
No log 7.0 182 1.1240 -0.0760 1.1240 1.0602
No log 7.0769 184 1.2041 -0.0195 1.2041 1.0973
No log 7.1538 186 1.2834 -0.0201 1.2834 1.1329
No log 7.2308 188 1.4514 0.1458 1.4514 1.2047
No log 7.3077 190 1.3551 0.1691 1.3551 1.1641
No log 7.3846 192 1.0361 0.0810 1.0361 1.0179
No log 7.4615 194 0.8596 -0.0070 0.8596 0.9272
No log 7.5385 196 0.9195 0.0097 0.9195 0.9589
No log 7.6154 198 0.9711 0.0725 0.9711 0.9854
No log 7.6923 200 0.9503 0.0426 0.9503 0.9748
No log 7.7692 202 0.9109 -0.1459 0.9109 0.9544
No log 7.8462 204 0.9523 -0.0316 0.9523 0.9758
No log 7.9231 206 1.0533 -0.1189 1.0533 1.0263
No log 8.0 208 0.8939 0.0734 0.8939 0.9455
No log 8.0769 210 0.9432 0.0605 0.9432 0.9712
No log 8.1538 212 0.9496 0.0421 0.9496 0.9745
No log 8.2308 214 0.9359 -0.0592 0.9359 0.9674
No log 8.3077 216 1.0064 -0.0643 1.0064 1.0032
No log 8.3846 218 1.0323 -0.0315 1.0323 1.0160
No log 8.4615 220 0.9785 -0.1232 0.9785 0.9892
No log 8.5385 222 0.9270 -0.0804 0.9270 0.9628
No log 8.6154 224 0.8711 0.0318 0.8711 0.9333
No log 8.6923 226 0.8371 0.1379 0.8371 0.9149
No log 8.7692 228 0.8708 0.2054 0.8708 0.9332
No log 8.8462 230 0.8299 0.0303 0.8299 0.9110
No log 8.9231 232 0.8650 -0.1722 0.8650 0.9300
No log 9.0 234 0.8809 0.1423 0.8809 0.9386
No log 9.0769 236 0.9407 0.1862 0.9407 0.9699
No log 9.1538 238 1.0160 0.0267 1.0160 1.0080
No log 9.2308 240 0.9421 0.1379 0.9421 0.9706
No log 9.3077 242 0.9206 -0.1817 0.9206 0.9595
No log 9.3846 244 0.9211 -0.1746 0.9211 0.9598
No log 9.4615 246 0.9277 0.1272 0.9277 0.9632
No log 9.5385 248 1.1392 -0.0568 1.1392 1.0673
No log 9.6154 250 1.1392 -0.0568 1.1392 1.0673
No log 9.6923 252 0.9239 0.0118 0.9239 0.9612
No log 9.7692 254 0.8503 -0.0079 0.8503 0.9221
No log 9.8462 256 0.9286 -0.0425 0.9286 0.9637
No log 9.9231 258 1.0816 0.0431 1.0816 1.0400
No log 10.0 260 1.1440 -0.0285 1.1440 1.0696
No log 10.0769 262 1.0933 -0.1279 1.0933 1.0456
No log 10.1538 264 0.8999 0.0628 0.8999 0.9486
No log 10.2308 266 0.8823 -0.0949 0.8823 0.9393
No log 10.3077 268 0.9081 -0.0532 0.9081 0.9530
No log 10.3846 270 1.0424 -0.1267 1.0424 1.0210
No log 10.4615 272 0.9958 -0.0033 0.9958 0.9979
No log 10.5385 274 0.8886 -0.0541 0.8886 0.9426
No log 10.6154 276 0.8668 -0.0108 0.8668 0.9310
No log 10.6923 278 0.9553 -0.0373 0.9553 0.9774
No log 10.7692 280 1.0236 0.0182 1.0236 1.0117
No log 10.8462 282 0.8716 0.0574 0.8716 0.9336
No log 10.9231 284 0.8087 -0.0810 0.8087 0.8993
No log 11.0 286 0.8659 -0.1411 0.8659 0.9305
No log 11.0769 288 0.8362 0.0495 0.8362 0.9145
No log 11.1538 290 0.8957 0.1183 0.8957 0.9464
No log 11.2308 292 0.8777 0.0573 0.8777 0.9368
No log 11.3077 294 0.9241 0.1281 0.9241 0.9613
No log 11.3846 296 0.9490 -0.0033 0.9490 0.9742
No log 11.4615 298 0.9461 0.0476 0.9461 0.9727
No log 11.5385 300 1.0065 -0.0474 1.0065 1.0033
No log 11.6154 302 0.9523 0.0525 0.9523 0.9759
No log 11.6923 304 0.8707 -0.0334 0.8707 0.9331
No log 11.7692 306 0.9664 -0.1851 0.9664 0.9830
No log 11.8462 308 0.9076 -0.0066 0.9076 0.9527
No log 11.9231 310 0.8505 0.0140 0.8505 0.9222
No log 12.0 312 1.3113 -0.0628 1.3113 1.1451
No log 12.0769 314 1.6392 0.0478 1.6392 1.2803
No log 12.1538 316 1.3569 -0.0029 1.3569 1.1649
No log 12.2308 318 0.9303 0.0260 0.9303 0.9645
No log 12.3077 320 0.7844 0.0282 0.7844 0.8857
No log 12.3846 322 0.8058 0.0191 0.8058 0.8977
No log 12.4615 324 0.8676 0.0409 0.8676 0.9315
No log 12.5385 326 1.0392 0.0486 1.0392 1.0194
No log 12.6154 328 1.1236 0.0805 1.1236 1.0600
No log 12.6923 330 0.9167 -0.0056 0.9167 0.9574
No log 12.7692 332 0.7949 0.0700 0.7949 0.8916
No log 12.8462 334 0.7884 0.1146 0.7884 0.8879
No log 12.9231 336 0.8762 0.1841 0.8762 0.9361
No log 13.0 338 0.9747 0.0515 0.9747 0.9873
No log 13.0769 340 0.8779 0.0377 0.8779 0.9370
No log 13.1538 342 0.8178 0.0409 0.8178 0.9043
No log 13.2308 344 0.7263 0.0247 0.7263 0.8522
No log 13.3077 346 0.7391 0.0247 0.7391 0.8597
No log 13.3846 348 0.8249 0.0442 0.8249 0.9082
No log 13.4615 350 0.8955 -0.0079 0.8955 0.9463
No log 13.5385 352 0.8552 0.0377 0.8552 0.9248
No log 13.6154 354 0.8067 0.0476 0.8067 0.8982
No log 13.6923 356 0.7602 0.0999 0.7602 0.8719
No log 13.7692 358 0.7598 0.0999 0.7598 0.8717
No log 13.8462 360 0.8040 0.0442 0.8040 0.8966
No log 13.9231 362 0.9510 0.0984 0.9510 0.9752
No log 14.0 364 1.0358 0.1408 1.0358 1.0177
No log 14.0769 366 0.9322 -0.0056 0.9322 0.9655
No log 14.1538 368 0.8139 -0.0240 0.8139 0.9022
No log 14.2308 370 0.7810 -0.0086 0.7810 0.8837
No log 14.3077 372 0.8346 0.1605 0.8346 0.9136
No log 14.3846 374 0.9083 0.1024 0.9083 0.9530
No log 14.4615 376 1.1119 0.0026 1.1119 1.0545
No log 14.5385 378 1.0295 0.0609 1.0295 1.0146
No log 14.6154 380 0.8398 0.0099 0.8398 0.9164
No log 14.6923 382 0.7939 -0.0329 0.7939 0.8910
No log 14.7692 384 0.8142 -0.0620 0.8142 0.9024
No log 14.8462 386 0.8443 -0.0008 0.8443 0.9189
No log 14.9231 388 1.0961 0.0805 1.0961 1.0470
No log 15.0 390 1.2131 0.0651 1.2131 1.1014
No log 15.0769 392 0.9760 0.0805 0.9760 0.9879
No log 15.1538 394 0.7405 0.1395 0.7405 0.8605
No log 15.2308 396 0.7067 -0.0591 0.7067 0.8406
No log 15.3077 398 0.7646 0.0999 0.7646 0.8744
No log 15.3846 400 0.9905 0.0305 0.9905 0.9952
No log 15.4615 402 1.0348 -0.0067 1.0348 1.0172
No log 15.5385 404 0.8866 0.0676 0.8866 0.9416
No log 15.6154 406 0.8101 0.0600 0.8101 0.9001
No log 15.6923 408 0.8895 0.0333 0.8895 0.9431
No log 15.7692 410 1.0329 0.0157 1.0329 1.0163
No log 15.8462 412 1.0541 0.0157 1.0541 1.0267
No log 15.9231 414 1.0420 0.0545 1.0420 1.0208
No log 16.0 416 0.8232 0.0099 0.8232 0.9073
No log 16.0769 418 0.7735 0.1433 0.7735 0.8795
No log 16.1538 420 0.7779 0.1081 0.7779 0.8820
No log 16.2308 422 0.7961 0.0116 0.7961 0.8923
No log 16.3077 424 0.8054 0.0116 0.8054 0.8974
No log 16.3846 426 0.8068 0.0828 0.8068 0.8982
No log 16.4615 428 0.8930 0.0512 0.8930 0.9450
No log 16.5385 430 0.9231 -0.0852 0.9231 0.9608
No log 16.6154 432 0.8462 0.0846 0.8462 0.9199
No log 16.6923 434 0.8313 -0.0293 0.8313 0.9118
No log 16.7692 436 0.8240 -0.0293 0.8240 0.9078
No log 16.8462 438 0.8148 -0.0293 0.8148 0.9027
No log 16.9231 440 0.8131 0.0723 0.8131 0.9017
No log 17.0 442 0.9832 -0.1279 0.9832 0.9916
No log 17.0769 444 1.0294 -0.0955 1.0294 1.0146
No log 17.1538 446 0.8352 0.0786 0.8352 0.9139
No log 17.2308 448 0.7141 0.0541 0.7141 0.8450
No log 17.3077 450 0.7564 -0.0724 0.7564 0.8697
No log 17.3846 452 0.7310 -0.0406 0.7310 0.8550
No log 17.4615 454 0.7244 0.1722 0.7244 0.8511
No log 17.5385 456 0.8971 0.0233 0.8971 0.9472
No log 17.6154 458 1.0176 0.0134 1.0176 1.0087
No log 17.6923 460 0.9432 0.0984 0.9432 0.9712
No log 17.7692 462 0.8834 0.1605 0.8834 0.9399
No log 17.8462 464 0.8783 0.1196 0.8783 0.9372
No log 17.9231 466 0.8695 0.1196 0.8695 0.9325
No log 18.0 468 0.9597 0.0984 0.9597 0.9796
No log 18.0769 470 1.2863 -0.0145 1.2863 1.1342
No log 18.1538 472 1.3926 -0.0178 1.3926 1.1801
No log 18.2308 474 1.1334 0.0975 1.1334 1.0646
No log 18.3077 476 0.8112 0.0748 0.8112 0.9006
No log 18.3846 478 0.7314 -0.0032 0.7314 0.8552
No log 18.4615 480 0.7482 0.0528 0.7482 0.8650
No log 18.5385 482 0.7577 0.0260 0.7577 0.8705
No log 18.6154 484 0.8282 0.0826 0.8282 0.9101
No log 18.6923 486 0.9560 0.0458 0.9560 0.9778
No log 18.7692 488 0.9855 0.0089 0.9855 0.9927
No log 18.8462 490 0.8515 0.0984 0.8515 0.9228
No log 18.9231 492 0.7344 0.0159 0.7344 0.8570
No log 19.0 494 0.7130 0.0260 0.7130 0.8444
No log 19.0769 496 0.7172 0.0395 0.7172 0.8469
No log 19.1538 498 0.7687 0.0525 0.7687 0.8767
0.3297 19.2308 500 0.9091 0.1269 0.9091 0.9535
0.3297 19.3077 502 1.0069 0.1228 1.0069 1.0034
0.3297 19.3846 504 1.0629 0.0129 1.0629 1.0310
0.3297 19.4615 506 0.9747 0.0526 0.9747 0.9873
0.3297 19.5385 508 0.8070 0.1387 0.8070 0.8983
0.3297 19.6154 510 0.7438 -0.0118 0.7438 0.8624
0.3297 19.6923 512 0.7434 0.0970 0.7434 0.8622
0.3297 19.7692 514 0.7556 0.0732 0.7556 0.8692
0.3297 19.8462 516 0.8119 0.1239 0.8119 0.9011
0.3297 19.9231 518 0.9124 0.1311 0.9124 0.9552
0.3297 20.0 520 1.0249 0.0443 1.0249 1.0124
0.3297 20.0769 522 1.0513 0.1042 1.0513 1.0253
0.3297 20.1538 524 0.9000 0.0912 0.9000 0.9487
0.3297 20.2308 526 0.7426 0.1836 0.7426 0.8618
0.3297 20.3077 528 0.7300 0.1202 0.7300 0.8544
0.3297 20.3846 530 0.7748 0.0909 0.7748 0.8802
0.3297 20.4615 532 0.8507 0.1196 0.8507 0.9223
0.3297 20.5385 534 0.9283 0.0152 0.9283 0.9635
0.3297 20.6154 536 0.8628 0.0748 0.8628 0.9289

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
0
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_k9_task3_organization

Finetuned
(2730)
this model