ArabicNewSplits6_WithDuplicationsForScore5_FineTuningAraBERT_run1_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: 0.5685
  • Qwk: 0.3563
  • Mse: 0.5685
  • Rmse: 0.7540

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: 10

Training results

Training Loss Epoch Step Validation Loss Qwk Mse Rmse
No log 0.0435 2 3.3614 -0.0160 3.3614 1.8334
No log 0.0870 4 1.8721 -0.0390 1.8721 1.3683
No log 0.1304 6 1.0439 0.0294 1.0439 1.0217
No log 0.1739 8 0.8095 0.2000 0.8095 0.8997
No log 0.2174 10 0.6153 0.0 0.6153 0.7844
No log 0.2609 12 0.6953 0.1385 0.6953 0.8338
No log 0.3043 14 0.6392 0.0 0.6392 0.7995
No log 0.3478 16 0.7709 0.2000 0.7709 0.8780
No log 0.3913 18 0.9457 0.1013 0.9457 0.9725
No log 0.4348 20 0.8840 0.0884 0.8840 0.9402
No log 0.4783 22 0.7620 0.1923 0.7620 0.8729
No log 0.5217 24 0.6859 0.0164 0.6859 0.8282
No log 0.5652 26 0.9516 0.0545 0.9516 0.9755
No log 0.6087 28 0.9485 0.0909 0.9485 0.9739
No log 0.6522 30 0.7936 0.1746 0.7936 0.8908
No log 0.6957 32 0.7897 0.2077 0.7897 0.8887
No log 0.7391 34 0.7334 0.2332 0.7334 0.8564
No log 0.7826 36 0.6472 0.0409 0.6472 0.8045
No log 0.8261 38 0.7738 0.2457 0.7738 0.8797
No log 0.8696 40 0.7260 0.2000 0.7260 0.8521
No log 0.9130 42 0.6166 0.2000 0.6166 0.7852
No log 0.9565 44 0.7081 0.2157 0.7081 0.8415
No log 1.0 46 0.5771 0.2000 0.5771 0.7596
No log 1.0435 48 0.5847 0.2113 0.5847 0.7647
No log 1.0870 50 0.5740 0.1781 0.5740 0.7576
No log 1.1304 52 0.5991 0.2222 0.5991 0.7740
No log 1.1739 54 0.8272 0.1154 0.8272 0.9095
No log 1.2174 56 0.6854 0.2281 0.6854 0.8279
No log 1.2609 58 0.7888 0.2554 0.7888 0.8881
No log 1.3043 60 0.9383 0.1736 0.9383 0.9687
No log 1.3478 62 0.6270 0.2273 0.6270 0.7918
No log 1.3913 64 0.9108 0.0175 0.9108 0.9544
No log 1.4348 66 1.0522 0.0183 1.0522 1.0257
No log 1.4783 68 0.6989 0.2405 0.6989 0.8360
No log 1.5217 70 0.6793 0.1304 0.6793 0.8242
No log 1.5652 72 0.8659 0.2000 0.8659 0.9305
No log 1.6087 74 0.6544 0.0980 0.6544 0.8089
No log 1.6522 76 0.5739 0.2848 0.5739 0.7575
No log 1.6957 78 0.6443 0.2360 0.6443 0.8027
No log 1.7391 80 0.7775 0.1527 0.7775 0.8818
No log 1.7826 82 0.6638 0.2670 0.6638 0.8147
No log 1.8261 84 0.6875 0.2670 0.6875 0.8292
No log 1.8696 86 0.5989 0.3831 0.5989 0.7739
No log 1.9130 88 0.6996 0.3301 0.6996 0.8364
No log 1.9565 90 0.7846 0.2676 0.7846 0.8858
No log 2.0 92 0.6312 0.3498 0.6312 0.7945
No log 2.0435 94 0.6077 0.3641 0.6077 0.7795
No log 2.0870 96 0.5708 0.4167 0.5708 0.7555
No log 2.1304 98 1.1233 0.1945 1.1233 1.0599
No log 2.1739 100 1.7486 0.1756 1.7486 1.3224
No log 2.2174 102 1.1572 0.1724 1.1572 1.0757
No log 2.2609 104 0.5441 0.2688 0.5441 0.7376
No log 2.3043 106 0.5866 0.3077 0.5866 0.7659
No log 2.3478 108 0.5742 0.2709 0.5742 0.7577
No log 2.3913 110 0.6090 0.2670 0.6090 0.7804
No log 2.4348 112 1.0646 0.1331 1.0646 1.0318
No log 2.4783 114 0.8726 0.2479 0.8726 0.9341
No log 2.5217 116 0.6104 0.3641 0.6104 0.7813
No log 2.5652 118 0.7713 0.1579 0.7713 0.8782
No log 2.6087 120 0.6311 0.2607 0.6311 0.7944
No log 2.6522 122 0.6197 0.3636 0.6197 0.7872
No log 2.6957 124 0.8253 0.1050 0.8253 0.9085
No log 2.7391 126 0.7567 0.2245 0.7567 0.8699
No log 2.7826 128 0.5691 0.3829 0.5691 0.7544
No log 2.8261 130 0.7863 0.2340 0.7863 0.8867
No log 2.8696 132 0.7521 0.1861 0.7521 0.8673
No log 2.9130 134 0.5707 0.3371 0.5707 0.7555
No log 2.9565 136 1.2137 0.1392 1.2137 1.1017
No log 3.0 138 1.7147 0.1169 1.7147 1.3095
No log 3.0435 140 1.2447 0.1605 1.2447 1.1156
No log 3.0870 142 0.6796 0.1841 0.6796 0.8244
No log 3.1304 144 0.6719 0.2563 0.6719 0.8197
No log 3.1739 146 0.6109 0.3446 0.6109 0.7816
No log 3.2174 148 0.7422 0.2523 0.7422 0.8615
No log 3.2609 150 0.9579 0.1000 0.9579 0.9787
No log 3.3043 152 0.6802 0.2077 0.6802 0.8247
No log 3.3478 154 0.5499 0.4409 0.5499 0.7415
No log 3.3913 156 0.5598 0.3575 0.5598 0.7482
No log 3.4348 158 0.6054 0.4167 0.6054 0.7781
No log 3.4783 160 0.8931 0.1220 0.8931 0.9450
No log 3.5217 162 1.2845 0.2047 1.2845 1.1334
No log 3.5652 164 0.9893 0.2000 0.9893 0.9946
No log 3.6087 166 0.5816 0.4468 0.5816 0.7627
No log 3.6522 168 0.6101 0.3846 0.6101 0.7811
No log 3.6957 170 0.5634 0.4227 0.5634 0.7506
No log 3.7391 172 0.8291 0.2131 0.8291 0.9105
No log 3.7826 174 0.9333 0.1571 0.9333 0.9661
No log 3.8261 176 0.7144 0.3028 0.7144 0.8452
No log 3.8696 178 0.6455 0.3398 0.6455 0.8034
No log 3.9130 180 0.6278 0.3333 0.6278 0.7924
No log 3.9565 182 0.6167 0.3035 0.6167 0.7853
No log 4.0 184 0.7679 0.2607 0.7679 0.8763
No log 4.0435 186 0.7369 0.1921 0.7369 0.8584
No log 4.0870 188 0.5816 0.4098 0.5816 0.7626
No log 4.1304 190 0.5903 0.4667 0.5903 0.7683
No log 4.1739 192 0.6653 0.3663 0.6653 0.8157
No log 4.2174 194 0.5865 0.4286 0.5865 0.7658
No log 4.2609 196 0.6135 0.4112 0.6135 0.7832
No log 4.3043 198 0.8729 0.2424 0.8729 0.9343
No log 4.3478 200 0.9214 0.2424 0.9214 0.9599
No log 4.3913 202 0.8314 0.2131 0.8314 0.9118
No log 4.4348 204 0.6700 0.3684 0.6700 0.8185
No log 4.4783 206 0.5716 0.2917 0.5716 0.7561
No log 4.5217 208 0.5655 0.3073 0.5655 0.7520
No log 4.5652 210 0.6085 0.4639 0.6085 0.7801
No log 4.6087 212 0.6196 0.4043 0.6196 0.7872
No log 4.6522 214 0.6272 0.3297 0.6272 0.7919
No log 4.6957 216 0.5821 0.4652 0.5821 0.7630
No log 4.7391 218 0.6324 0.2153 0.6324 0.7952
No log 4.7826 220 0.7294 0.2696 0.7294 0.8540
No log 4.8261 222 0.6313 0.1921 0.6313 0.7946
No log 4.8696 224 0.6774 0.2941 0.6774 0.8231
No log 4.9130 226 0.8791 0.1803 0.8791 0.9376
No log 4.9565 228 0.7429 0.3247 0.7429 0.8619
No log 5.0 230 0.6096 0.4652 0.6096 0.7808
No log 5.0435 232 0.6137 0.4583 0.6137 0.7834
No log 5.0870 234 0.6207 0.4112 0.6207 0.7879
No log 5.1304 236 0.7437 0.2881 0.7437 0.8624
No log 5.1739 238 0.9417 0.2061 0.9417 0.9704
No log 5.2174 240 0.9301 0.2296 0.9301 0.9644
No log 5.2609 242 0.6927 0.2762 0.6927 0.8323
No log 5.3043 244 0.5403 0.4667 0.5403 0.7350
No log 5.3478 246 0.5241 0.5410 0.5241 0.7240
No log 5.3913 248 0.5497 0.3118 0.5497 0.7414
No log 5.4348 250 0.7279 0.1845 0.7279 0.8532
No log 5.4783 252 0.8306 0.2389 0.8306 0.9114
No log 5.5217 254 0.6764 0.2850 0.6764 0.8224
No log 5.5652 256 0.5364 0.5052 0.5364 0.7324
No log 5.6087 258 0.5666 0.4450 0.5666 0.7527
No log 5.6522 260 0.5455 0.4680 0.5455 0.7386
No log 5.6957 262 0.6283 0.3333 0.6283 0.7927
No log 5.7391 264 0.9378 0.2672 0.9378 0.9684
No log 5.7826 266 0.9672 0.2195 0.9672 0.9835
No log 5.8261 268 0.7547 0.1698 0.7547 0.8687
No log 5.8696 270 0.5969 0.4105 0.5969 0.7726
No log 5.9130 272 0.5818 0.4105 0.5818 0.7628
No log 5.9565 274 0.6260 0.2871 0.6260 0.7912
No log 6.0 276 0.7637 0.2233 0.7637 0.8739
No log 6.0435 278 0.7327 0.2637 0.7327 0.8560
No log 6.0870 280 0.6040 0.2766 0.6040 0.7771
No log 6.1304 282 0.5578 0.4595 0.5578 0.7469
No log 6.1739 284 0.5720 0.4225 0.5720 0.7563
No log 6.2174 286 0.6293 0.24 0.6293 0.7933
No log 6.2609 288 0.6721 0.2871 0.6721 0.8198
No log 6.3043 290 0.6125 0.2821 0.6125 0.7826
No log 6.3478 292 0.5572 0.4105 0.5572 0.7465
No log 6.3913 294 0.5604 0.4105 0.5604 0.7486
No log 6.4348 296 0.5773 0.3016 0.5773 0.7598
No log 6.4783 298 0.5972 0.2842 0.5972 0.7728
No log 6.5217 300 0.6351 0.3333 0.6351 0.7969
No log 6.5652 302 0.7471 0.1921 0.7471 0.8643
No log 6.6087 304 0.7978 0.1923 0.7978 0.8932
No log 6.6522 306 0.7102 0.2563 0.7102 0.8427
No log 6.6957 308 0.5653 0.3641 0.5653 0.7519
No log 6.7391 310 0.5800 0.3575 0.5800 0.7616
No log 6.7826 312 0.6045 0.4171 0.6045 0.7775
No log 6.8261 314 0.5635 0.3913 0.5635 0.7506
No log 6.8696 316 0.5930 0.3089 0.5930 0.7700
No log 6.9130 318 0.6418 0.3043 0.6418 0.8011
No log 6.9565 320 0.6449 0.3043 0.6449 0.8030
No log 7.0 322 0.6182 0.2513 0.6182 0.7862
No log 7.0435 324 0.5559 0.3073 0.5559 0.7456
No log 7.0870 326 0.5467 0.4286 0.5467 0.7394
No log 7.1304 328 0.5620 0.3073 0.5620 0.7497
No log 7.1739 330 0.6108 0.3073 0.6108 0.7815
No log 7.2174 332 0.6036 0.2527 0.6036 0.7769
No log 7.2609 334 0.5809 0.3089 0.5809 0.7622
No log 7.3043 336 0.5622 0.3708 0.5622 0.7498
No log 7.3478 338 0.5735 0.4033 0.5735 0.7573
No log 7.3913 340 0.5839 0.4033 0.5839 0.7641
No log 7.4348 342 0.5868 0.3191 0.5868 0.7660
No log 7.4783 344 0.6688 0.2746 0.6688 0.8178
No log 7.5217 346 0.8565 0.2531 0.8565 0.9255
No log 7.5652 348 0.9341 0.2195 0.9341 0.9665
No log 7.6087 350 0.8668 0.2531 0.8668 0.9310
No log 7.6522 352 0.7072 0.2475 0.7072 0.8409
No log 7.6957 354 0.5987 0.3641 0.5987 0.7738
No log 7.7391 356 0.5916 0.3978 0.5916 0.7691
No log 7.7826 358 0.5869 0.3913 0.5869 0.7661
No log 7.8261 360 0.5727 0.2865 0.5727 0.7568
No log 7.8696 362 0.6061 0.3224 0.6061 0.7785
No log 7.9130 364 0.6836 0.2990 0.6836 0.8268
No log 7.9565 366 0.7244 0.2245 0.7244 0.8511
No log 8.0 368 0.6974 0.2990 0.6974 0.8351
No log 8.0435 370 0.6361 0.3478 0.6361 0.7976
No log 8.0870 372 0.5751 0.2914 0.5751 0.7584
No log 8.1304 374 0.5405 0.3333 0.5405 0.7352
No log 8.1739 376 0.5395 0.3708 0.5395 0.7345
No log 8.2174 378 0.5357 0.3708 0.5357 0.7319
No log 8.2609 380 0.5405 0.3563 0.5405 0.7352
No log 8.3043 382 0.5991 0.3563 0.5991 0.7740
No log 8.3478 384 0.7212 0.2563 0.7212 0.8493
No log 8.3913 386 0.7991 0.1610 0.7991 0.8939
No log 8.4348 388 0.7831 0.1600 0.7831 0.8849
No log 8.4783 390 0.6990 0.3016 0.6990 0.8360
No log 8.5217 392 0.5988 0.3073 0.5988 0.7738
No log 8.5652 394 0.5596 0.3978 0.5596 0.7481
No log 8.6087 396 0.5391 0.3478 0.5391 0.7342
No log 8.6522 398 0.5403 0.3591 0.5403 0.7351
No log 8.6957 400 0.5576 0.3978 0.5576 0.7467
No log 8.7391 402 0.5801 0.3898 0.5801 0.7617
No log 8.7826 404 0.6163 0.3016 0.6163 0.7850
No log 8.8261 406 0.6574 0.3016 0.6574 0.8108
No log 8.8696 408 0.6530 0.3016 0.6530 0.8081
No log 8.9130 410 0.6243 0.3016 0.6243 0.7901
No log 8.9565 412 0.6116 0.3016 0.6116 0.7820
No log 9.0 414 0.5900 0.3073 0.5900 0.7681
No log 9.0435 416 0.5682 0.2994 0.5682 0.7538
No log 9.0870 418 0.5468 0.3661 0.5468 0.7395
No log 9.1304 420 0.5361 0.3478 0.5361 0.7322
No log 9.1739 422 0.5347 0.3478 0.5347 0.7312
No log 9.2174 424 0.5382 0.3591 0.5382 0.7336
No log 9.2609 426 0.5464 0.3661 0.5464 0.7392
No log 9.3043 428 0.5617 0.2994 0.5617 0.7495
No log 9.3478 430 0.5783 0.3563 0.5783 0.7605
No log 9.3913 432 0.5980 0.3043 0.5980 0.7733
No log 9.4348 434 0.6090 0.3016 0.6090 0.7804
No log 9.4783 436 0.6105 0.3016 0.6105 0.7813
No log 9.5217 438 0.6043 0.3043 0.6043 0.7774
No log 9.5652 440 0.5941 0.3563 0.5941 0.7708
No log 9.6087 442 0.5832 0.3563 0.5832 0.7637
No log 9.6522 444 0.5731 0.3563 0.5731 0.7570
No log 9.6957 446 0.5686 0.3563 0.5686 0.7540
No log 9.7391 448 0.5666 0.3563 0.5666 0.7527
No log 9.7826 450 0.5652 0.3563 0.5652 0.7518
No log 9.8261 452 0.5661 0.3563 0.5661 0.7524
No log 9.8696 454 0.5673 0.3563 0.5673 0.7532
No log 9.9130 456 0.5683 0.3563 0.5683 0.7538
No log 9.9565 458 0.5685 0.3563 0.5685 0.7540
No log 10.0 460 0.5685 0.3563 0.5685 0.7540

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
2
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/ArabicNewSplits6_WithDuplicationsForScore5_FineTuningAraBERT_run1_AugV5_k9_task3_organization

Finetuned
(4040)
this model