ArabicNewSplits7_FineTuningAraBERT_run3_AugV5_k18_task5_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: 0.8856
  • Qwk: 0.3643
  • Mse: 0.8856
  • Rmse: 0.9411

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 0.0435 2 4.0223 -0.0101 4.0223 2.0056
No log 0.0870 4 2.1125 0.0537 2.1125 1.4534
No log 0.1304 6 1.2801 0.0584 1.2801 1.1314
No log 0.1739 8 1.1475 0.1944 1.1475 1.0712
No log 0.2174 10 1.1905 0.2166 1.1905 1.0911
No log 0.2609 12 1.1179 0.1046 1.1179 1.0573
No log 0.3043 14 1.0891 0.1046 1.0891 1.0436
No log 0.3478 16 1.0504 0.1046 1.0504 1.0249
No log 0.3913 18 1.0780 0.2314 1.0780 1.0383
No log 0.4348 20 1.0653 0.2114 1.0653 1.0321
No log 0.4783 22 1.0592 0.2865 1.0592 1.0292
No log 0.5217 24 1.0291 0.2566 1.0291 1.0144
No log 0.5652 26 1.0021 0.1810 1.0021 1.0010
No log 0.6087 28 1.0411 0.2236 1.0411 1.0203
No log 0.6522 30 1.0538 0.2424 1.0538 1.0265
No log 0.6957 32 0.9977 0.2154 0.9977 0.9988
No log 0.7391 34 1.0371 0.2958 1.0371 1.0184
No log 0.7826 36 0.9664 0.2935 0.9664 0.9831
No log 0.8261 38 0.9398 0.1857 0.9398 0.9694
No log 0.8696 40 0.9723 0.3483 0.9723 0.9860
No log 0.9130 42 1.0721 0.3287 1.0721 1.0354
No log 0.9565 44 1.2197 0.2273 1.2197 1.1044
No log 1.0 46 0.9720 0.3483 0.9720 0.9859
No log 1.0435 48 0.8665 0.3407 0.8665 0.9309
No log 1.0870 50 0.9745 0.2567 0.9745 0.9872
No log 1.1304 52 1.0153 0.3276 1.0153 1.0076
No log 1.1739 54 1.0002 0.3885 1.0002 1.0001
No log 1.2174 56 0.9320 0.5164 0.9320 0.9654
No log 1.2609 58 0.7444 0.5192 0.7444 0.8628
No log 1.3043 60 0.7497 0.5635 0.7497 0.8658
No log 1.3478 62 0.8204 0.4518 0.8204 0.9058
No log 1.3913 64 0.7703 0.6119 0.7703 0.8777
No log 1.4348 66 0.8684 0.5298 0.8684 0.9319
No log 1.4783 68 0.7968 0.5363 0.7968 0.8926
No log 1.5217 70 0.8711 0.4624 0.8711 0.9333
No log 1.5652 72 0.8384 0.4833 0.8384 0.9156
No log 1.6087 74 0.7433 0.5844 0.7433 0.8622
No log 1.6522 76 0.7113 0.5736 0.7113 0.8434
No log 1.6957 78 0.6830 0.6390 0.6830 0.8264
No log 1.7391 80 0.6651 0.6584 0.6651 0.8156
No log 1.7826 82 0.7022 0.6497 0.7022 0.8380
No log 1.8261 84 0.6961 0.5223 0.6961 0.8343
No log 1.8696 86 0.8143 0.5266 0.8143 0.9024
No log 1.9130 88 0.7777 0.4741 0.7777 0.8819
No log 1.9565 90 0.7565 0.5024 0.7565 0.8698
No log 2.0 92 0.7726 0.5107 0.7726 0.8790
No log 2.0435 94 0.7848 0.4981 0.7848 0.8859
No log 2.0870 96 0.8970 0.4595 0.8970 0.9471
No log 2.1304 98 0.8859 0.4947 0.8859 0.9412
No log 2.1739 100 0.8136 0.4990 0.8136 0.9020
No log 2.2174 102 0.8586 0.5543 0.8586 0.9266
No log 2.2609 104 1.0935 0.3973 1.0935 1.0457
No log 2.3043 106 1.1102 0.3819 1.1102 1.0537
No log 2.3478 108 0.8536 0.4638 0.8536 0.9239
No log 2.3913 110 0.8009 0.4662 0.8009 0.8949
No log 2.4348 112 0.8348 0.4953 0.8348 0.9137
No log 2.4783 114 0.9420 0.4500 0.9420 0.9706
No log 2.5217 116 0.9662 0.4389 0.9662 0.9829
No log 2.5652 118 0.9215 0.4171 0.9215 0.9600
No log 2.6087 120 0.8828 0.4034 0.8828 0.9396
No log 2.6522 122 0.8181 0.4471 0.8181 0.9045
No log 2.6957 124 0.8054 0.4802 0.8054 0.8975
No log 2.7391 126 0.8110 0.3860 0.8110 0.9006
No log 2.7826 128 0.9763 0.3480 0.9763 0.9881
No log 2.8261 130 1.0575 0.3395 1.0575 1.0283
No log 2.8696 132 1.0347 0.3270 1.0347 1.0172
No log 2.9130 134 1.0543 0.4 1.0543 1.0268
No log 2.9565 136 0.9704 0.4320 0.9704 0.9851
No log 3.0 138 0.9241 0.5778 0.9241 0.9613
No log 3.0435 140 0.9140 0.5696 0.9140 0.9560
No log 3.0870 142 0.9800 0.5352 0.9800 0.9900
No log 3.1304 144 0.9640 0.5273 0.9640 0.9819
No log 3.1739 146 0.8332 0.5317 0.8332 0.9128
No log 3.2174 148 0.7669 0.4948 0.7669 0.8757
No log 3.2609 150 0.7673 0.4476 0.7673 0.8760
No log 3.3043 152 0.7782 0.4220 0.7782 0.8821
No log 3.3478 154 0.7950 0.4075 0.7950 0.8917
No log 3.3913 156 0.7915 0.3706 0.7915 0.8897
No log 3.4348 158 0.8507 0.4318 0.8507 0.9223
No log 3.4783 160 0.8396 0.4318 0.8396 0.9163
No log 3.5217 162 0.7472 0.4742 0.7472 0.8644
No log 3.5652 164 0.7078 0.5591 0.7078 0.8413
No log 3.6087 166 0.7289 0.6403 0.7289 0.8537
No log 3.6522 168 0.7126 0.5984 0.7126 0.8441
No log 3.6957 170 0.7368 0.5618 0.7368 0.8584
No log 3.7391 172 0.7678 0.5160 0.7678 0.8762
No log 3.7826 174 0.8069 0.4695 0.8069 0.8983
No log 3.8261 176 0.7703 0.4599 0.7703 0.8777
No log 3.8696 178 0.7754 0.4244 0.7754 0.8805
No log 3.9130 180 0.7956 0.3725 0.7956 0.8919
No log 3.9565 182 0.8417 0.4812 0.8417 0.9174
No log 4.0 184 0.8624 0.4696 0.8624 0.9286
No log 4.0435 186 0.8314 0.4712 0.8314 0.9118
No log 4.0870 188 0.8684 0.4806 0.8684 0.9319
No log 4.1304 190 0.9353 0.4423 0.9353 0.9671
No log 4.1739 192 0.8911 0.4423 0.8911 0.9440
No log 4.2174 194 0.7856 0.4824 0.7856 0.8864
No log 4.2609 196 0.7575 0.5152 0.7575 0.8703
No log 4.3043 198 0.7480 0.5184 0.7480 0.8649
No log 4.3478 200 0.7251 0.5483 0.7251 0.8515
No log 4.3913 202 0.7443 0.5774 0.7443 0.8627
No log 4.4348 204 0.7492 0.5540 0.7492 0.8656
No log 4.4783 206 0.6763 0.5246 0.6764 0.8224
No log 4.5217 208 0.6880 0.5581 0.6880 0.8295
No log 4.5652 210 0.7309 0.5366 0.7309 0.8549
No log 4.6087 212 0.6824 0.5108 0.6824 0.8261
No log 4.6522 214 0.7572 0.4593 0.7572 0.8702
No log 4.6957 216 0.8614 0.4417 0.8614 0.9281
No log 4.7391 218 0.8386 0.4549 0.8386 0.9157
No log 4.7826 220 0.7377 0.5206 0.7377 0.8589
No log 4.8261 222 0.6719 0.6345 0.6719 0.8197
No log 4.8696 224 0.6717 0.6207 0.6717 0.8196
No log 4.9130 226 0.6766 0.6389 0.6766 0.8225
No log 4.9565 228 0.7900 0.5631 0.7900 0.8888
No log 5.0 230 0.8696 0.5505 0.8696 0.9325
No log 5.0435 232 0.9392 0.5090 0.9392 0.9691
No log 5.0870 234 0.7906 0.5279 0.7906 0.8892
No log 5.1304 236 0.6983 0.4676 0.6983 0.8356
No log 5.1739 238 0.7233 0.5425 0.7233 0.8505
No log 5.2174 240 0.7221 0.4802 0.7221 0.8498
No log 5.2609 242 0.7437 0.4593 0.7437 0.8624
No log 5.3043 244 0.8071 0.4815 0.8071 0.8984
No log 5.3478 246 0.8594 0.4428 0.8594 0.9270
No log 5.3913 248 0.8848 0.4039 0.8848 0.9406
No log 5.4348 250 0.8113 0.4579 0.8113 0.9007
No log 5.4783 252 0.7802 0.4613 0.7802 0.8833
No log 5.5217 254 0.7720 0.5235 0.7720 0.8786
No log 5.5652 256 0.7922 0.4613 0.7922 0.8901
No log 5.6087 258 0.8213 0.4327 0.8213 0.9062
No log 5.6522 260 0.8447 0.3648 0.8447 0.9191
No log 5.6957 262 0.8655 0.3363 0.8655 0.9303
No log 5.7391 264 0.8627 0.3363 0.8627 0.9288
No log 5.7826 266 0.8210 0.3485 0.8210 0.9061
No log 5.8261 268 0.7747 0.4097 0.7747 0.8802
No log 5.8696 270 0.7466 0.4907 0.7466 0.8641
No log 5.9130 272 0.7386 0.5545 0.7386 0.8594
No log 5.9565 274 0.7374 0.5774 0.7374 0.8587
No log 6.0 276 0.7470 0.5517 0.7470 0.8643
No log 6.0435 278 0.7420 0.5236 0.7420 0.8614
No log 6.0870 280 0.7787 0.5305 0.7787 0.8824
No log 6.1304 282 0.7722 0.5079 0.7722 0.8787
No log 6.1739 284 0.7392 0.4645 0.7392 0.8598
No log 6.2174 286 0.7324 0.4378 0.7324 0.8558
No log 6.2609 288 0.7412 0.4728 0.7412 0.8610
No log 6.3043 290 0.7807 0.5416 0.7807 0.8836
No log 6.3478 292 0.8174 0.4429 0.8174 0.9041
No log 6.3913 294 0.9058 0.4202 0.9058 0.9517
No log 6.4348 296 0.9279 0.4554 0.9279 0.9633
No log 6.4783 298 0.8321 0.4444 0.8321 0.9122
No log 6.5217 300 0.7569 0.4759 0.7569 0.8700
No log 6.5652 302 0.7685 0.4444 0.7685 0.8767
No log 6.6087 304 0.7719 0.4544 0.7719 0.8786
No log 6.6522 306 0.7816 0.4759 0.7816 0.8841
No log 6.6957 308 0.8256 0.4192 0.8256 0.9086
No log 6.7391 310 0.8042 0.4327 0.8042 0.8968
No log 6.7826 312 0.7617 0.4288 0.7617 0.8727
No log 6.8261 314 0.7651 0.5052 0.7651 0.8747
No log 6.8696 316 0.7570 0.5287 0.7570 0.8701
No log 6.9130 318 0.7258 0.4912 0.7258 0.8520
No log 6.9565 320 0.7147 0.5038 0.7147 0.8454
No log 7.0 322 0.7058 0.5038 0.7058 0.8401
No log 7.0435 324 0.7106 0.5463 0.7106 0.8430
No log 7.0870 326 0.7360 0.5634 0.7360 0.8579
No log 7.1304 328 0.7418 0.5425 0.7418 0.8613
No log 7.1739 330 0.7840 0.5195 0.7840 0.8854
No log 7.2174 332 0.8455 0.4696 0.8455 0.9195
No log 7.2609 334 0.8227 0.4597 0.8227 0.9070
No log 7.3043 336 0.8330 0.4728 0.8330 0.9127
No log 7.3478 338 0.8406 0.4728 0.8406 0.9169
No log 7.3913 340 0.8962 0.4318 0.8962 0.9467
No log 7.4348 342 0.9112 0.4326 0.9112 0.9546
No log 7.4783 344 0.9153 0.4326 0.9153 0.9567
No log 7.5217 346 0.8764 0.5195 0.8764 0.9362
No log 7.5652 348 0.8414 0.5534 0.8414 0.9173
No log 7.6087 350 0.8614 0.5413 0.8614 0.9281
No log 7.6522 352 0.8536 0.5948 0.8536 0.9239
No log 7.6957 354 0.7623 0.5752 0.7623 0.8731
No log 7.7391 356 0.7624 0.4894 0.7624 0.8731
No log 7.7826 358 0.8174 0.5642 0.8174 0.9041
No log 7.8261 360 0.7555 0.4672 0.7555 0.8692
No log 7.8696 362 0.7771 0.4772 0.7771 0.8815
No log 7.9130 364 0.8558 0.4858 0.8558 0.9251
No log 7.9565 366 0.8794 0.4352 0.8794 0.9378
No log 8.0 368 0.8340 0.3960 0.8340 0.9132
No log 8.0435 370 0.8210 0.4629 0.8210 0.9061
No log 8.0870 372 0.8220 0.4629 0.8220 0.9066
No log 8.1304 374 0.8590 0.4836 0.8590 0.9268
No log 8.1739 376 0.9453 0.5035 0.9453 0.9723
No log 8.2174 378 0.9716 0.4792 0.9716 0.9857
No log 8.2609 380 0.9189 0.4568 0.9189 0.9586
No log 8.3043 382 0.8466 0.4483 0.8466 0.9201
No log 8.3478 384 0.8061 0.4494 0.8061 0.8978
No log 8.3913 386 0.7846 0.5359 0.7846 0.8858
No log 8.4348 388 0.7617 0.4941 0.7617 0.8728
No log 8.4783 390 0.7641 0.4941 0.7641 0.8741
No log 8.5217 392 0.7676 0.5590 0.7676 0.8761
No log 8.5652 394 0.7721 0.5678 0.7721 0.8787
No log 8.6087 396 0.7634 0.6025 0.7634 0.8737
No log 8.6522 398 0.7782 0.5393 0.7782 0.8822
No log 8.6957 400 0.8023 0.5378 0.8023 0.8957
No log 8.7391 402 0.7942 0.5181 0.7942 0.8912
No log 8.7826 404 0.7893 0.5692 0.7893 0.8884
No log 8.8261 406 0.8019 0.6197 0.8019 0.8955
No log 8.8696 408 0.7698 0.5368 0.7698 0.8774
No log 8.9130 410 0.7429 0.5393 0.7429 0.8619
No log 8.9565 412 0.7333 0.5406 0.7333 0.8564
No log 9.0 414 0.7262 0.5512 0.7262 0.8522
No log 9.0435 416 0.7247 0.5487 0.7247 0.8513
No log 9.0870 418 0.7287 0.5594 0.7287 0.8536
No log 9.1304 420 0.7345 0.5594 0.7345 0.8570
No log 9.1739 422 0.7563 0.5475 0.7563 0.8696
No log 9.2174 424 0.7809 0.5980 0.7809 0.8837
No log 9.2609 426 0.7894 0.5939 0.7894 0.8885
No log 9.3043 428 0.7802 0.5518 0.7802 0.8833
No log 9.3478 430 0.7689 0.5137 0.7689 0.8769
No log 9.3913 432 0.7608 0.5660 0.7608 0.8722
No log 9.4348 434 0.7727 0.6187 0.7727 0.8790
No log 9.4783 436 0.7750 0.6187 0.7750 0.8803
No log 9.5217 438 0.7567 0.6380 0.7567 0.8699
No log 9.5652 440 0.7463 0.5368 0.7463 0.8639
No log 9.6087 442 0.7462 0.5368 0.7462 0.8638
No log 9.6522 444 0.7615 0.5678 0.7615 0.8727
No log 9.6957 446 0.7709 0.5317 0.7709 0.8780
No log 9.7391 448 0.7730 0.5669 0.7730 0.8792
No log 9.7826 450 0.7703 0.5877 0.7703 0.8776
No log 9.8261 452 0.7726 0.5902 0.7726 0.8790
No log 9.8696 454 0.8013 0.5330 0.8013 0.8951
No log 9.9130 456 0.8204 0.5098 0.8204 0.9058
No log 9.9565 458 0.7955 0.4645 0.7955 0.8919
No log 10.0 460 0.7761 0.4151 0.7761 0.8809
No log 10.0435 462 0.7813 0.4168 0.7813 0.8839
No log 10.0870 464 0.7975 0.4119 0.7975 0.8930
No log 10.1304 466 0.8345 0.3604 0.8345 0.9135
No log 10.1739 468 0.8460 0.3611 0.8460 0.9198
No log 10.2174 470 0.8357 0.4180 0.8357 0.9142
No log 10.2609 472 0.8211 0.4579 0.8211 0.9061
No log 10.3043 474 0.8198 0.5178 0.8198 0.9054
No log 10.3478 476 0.8039 0.5065 0.8039 0.8966
No log 10.3913 478 0.7846 0.5183 0.7846 0.8858
No log 10.4348 480 0.7985 0.5042 0.7985 0.8936
No log 10.4783 482 0.7656 0.5416 0.7656 0.8750
No log 10.5217 484 0.7672 0.4729 0.7672 0.8759
No log 10.5652 486 0.7751 0.4644 0.7751 0.8804
No log 10.6087 488 0.7767 0.4644 0.7767 0.8813
No log 10.6522 490 0.7728 0.4411 0.7728 0.8791
No log 10.6957 492 0.7721 0.4594 0.7721 0.8787
No log 10.7391 494 0.7652 0.4912 0.7652 0.8748
No log 10.7826 496 0.7803 0.4883 0.7803 0.8833
No log 10.8261 498 0.7847 0.4883 0.7847 0.8859
0.2637 10.8696 500 0.7868 0.4534 0.7868 0.8870
0.2637 10.9130 502 0.7808 0.5139 0.7808 0.8836
0.2637 10.9565 504 0.7811 0.4585 0.7811 0.8838
0.2637 11.0 506 0.7830 0.4787 0.7830 0.8849
0.2637 11.0435 508 0.7789 0.4787 0.7789 0.8825
0.2637 11.0870 510 0.7708 0.4787 0.7708 0.8779
0.2637 11.1304 512 0.7634 0.4729 0.7634 0.8737
0.2637 11.1739 514 0.7759 0.5204 0.7759 0.8809
0.2637 11.2174 516 0.7794 0.5204 0.7794 0.8828
0.2637 11.2609 518 0.7786 0.5204 0.7786 0.8824
0.2637 11.3043 520 0.7959 0.5527 0.7959 0.8921
0.2637 11.3478 522 0.8273 0.5157 0.8273 0.9096
0.2637 11.3913 524 0.8094 0.5167 0.8094 0.8996
0.2637 11.4348 526 0.8027 0.5167 0.8027 0.8959
0.2637 11.4783 528 0.7920 0.4336 0.7920 0.8899
0.2637 11.5217 530 0.8070 0.4461 0.8070 0.8984
0.2637 11.5652 532 0.8633 0.5157 0.8633 0.9292
0.2637 11.6087 534 0.9232 0.4666 0.9232 0.9608
0.2637 11.6522 536 0.9071 0.5253 0.9071 0.9524
0.2637 11.6957 538 0.8281 0.5400 0.8281 0.9100
0.2637 11.7391 540 0.7748 0.5247 0.7748 0.8802
0.2637 11.7826 542 0.7741 0.5246 0.7741 0.8798
0.2637 11.8261 544 0.8229 0.4576 0.8229 0.9071
0.2637 11.8696 546 0.8695 0.4041 0.8695 0.9324
0.2637 11.9130 548 0.8549 0.4562 0.8549 0.9246
0.2637 11.9565 550 0.8430 0.5504 0.8430 0.9181
0.2637 12.0 552 0.8854 0.5832 0.8854 0.9409
0.2637 12.0435 554 0.9039 0.5810 0.9039 0.9507
0.2637 12.0870 556 0.8544 0.6141 0.8544 0.9243
0.2637 12.1304 558 0.7863 0.6362 0.7863 0.8867
0.2637 12.1739 560 0.7257 0.5643 0.7257 0.8519
0.2637 12.2174 562 0.7178 0.5969 0.7178 0.8472
0.2637 12.2609 564 0.7427 0.5501 0.7427 0.8618
0.2637 12.3043 566 0.7509 0.5327 0.7509 0.8666
0.2637 12.3478 568 0.7348 0.5030 0.7348 0.8572
0.2637 12.3913 570 0.7360 0.5139 0.7360 0.8579
0.2637 12.4348 572 0.7415 0.5139 0.7415 0.8611
0.2637 12.4783 574 0.7498 0.4898 0.7498 0.8659
0.2637 12.5217 576 0.7445 0.4898 0.7445 0.8629
0.2637 12.5652 578 0.7478 0.5139 0.7478 0.8647
0.2637 12.6087 580 0.7444 0.5261 0.7444 0.8628
0.2637 12.6522 582 0.7523 0.4898 0.7523 0.8673
0.2637 12.6957 584 0.7706 0.4537 0.7706 0.8778
0.2637 12.7391 586 0.8042 0.4966 0.8042 0.8968
0.2637 12.7826 588 0.8341 0.4220 0.8341 0.9133
0.2637 12.8261 590 0.8423 0.3921 0.8423 0.9177
0.2637 12.8696 592 0.8554 0.3643 0.8554 0.9249
0.2637 12.9130 594 0.8604 0.3782 0.8604 0.9276
0.2637 12.9565 596 0.8856 0.3643 0.8856 0.9411

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_run3_AugV5_k18_task5_organization

Finetuned
(4204)
this model