ArabicNewSplits8_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k7_task2_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: 0.6200
  • Qwk: 0.3132
  • Mse: 0.6200
  • Rmse: 0.7874

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 0.0526 2 4.2404 -0.0241 4.2404 2.0592
No log 0.1053 4 2.3544 0.0452 2.3544 1.5344
No log 0.1579 6 2.0677 -0.0925 2.0677 1.4380
No log 0.2105 8 2.9961 -0.0792 2.9961 1.7309
No log 0.2632 10 2.1958 -0.1003 2.1958 1.4818
No log 0.3158 12 1.1458 -0.1064 1.1458 1.0704
No log 0.3684 14 0.8788 0.1481 0.8788 0.9374
No log 0.4211 16 0.9001 0.0294 0.9001 0.9487
No log 0.4737 18 0.9098 0.0294 0.9098 0.9538
No log 0.5263 20 0.8657 0.0654 0.8657 0.9304
No log 0.5789 22 0.8578 0.1144 0.8578 0.9262
No log 0.6316 24 0.8614 0.1867 0.8614 0.9281
No log 0.6842 26 0.8827 0.1437 0.8827 0.9395
No log 0.7368 28 0.8873 0.1660 0.8873 0.9420
No log 0.7895 30 0.8638 0.1725 0.8638 0.9294
No log 0.8421 32 0.8398 0.1775 0.8398 0.9164
No log 0.8947 34 0.8599 0.1396 0.8599 0.9273
No log 0.9474 36 0.9284 0.0375 0.9284 0.9635
No log 1.0 38 1.0127 -0.0557 1.0127 1.0063
No log 1.0526 40 1.0233 0.0051 1.0233 1.0116
No log 1.1053 42 0.9729 0.0441 0.9729 0.9864
No log 1.1579 44 0.9264 0.0673 0.9264 0.9625
No log 1.2105 46 0.9040 0.0553 0.9040 0.9508
No log 1.2632 48 0.8890 0.1626 0.8890 0.9428
No log 1.3158 50 0.8921 0.1342 0.8921 0.9445
No log 1.3684 52 0.9558 0.0321 0.9558 0.9777
No log 1.4211 54 0.9777 0.0499 0.9777 0.9888
No log 1.4737 56 1.0462 -0.0421 1.0462 1.0228
No log 1.5263 58 0.9677 -0.0155 0.9677 0.9837
No log 1.5789 60 0.8695 0.1284 0.8695 0.9325
No log 1.6316 62 0.8719 0.1029 0.8719 0.9337
No log 1.6842 64 0.9819 0.0794 0.9819 0.9909
No log 1.7368 66 1.0203 0.0739 1.0203 1.0101
No log 1.7895 68 0.8679 0.2469 0.8679 0.9316
No log 1.8421 70 0.7791 0.1754 0.7791 0.8826
No log 1.8947 72 0.7511 0.3121 0.7511 0.8666
No log 1.9474 74 0.7447 0.3220 0.7447 0.8630
No log 2.0 76 0.7468 0.2713 0.7468 0.8642
No log 2.0526 78 0.7728 0.2733 0.7728 0.8791
No log 2.1053 80 0.9182 0.1585 0.9182 0.9582
No log 2.1579 82 0.9350 0.1854 0.9350 0.9669
No log 2.2105 84 0.8174 0.2598 0.8174 0.9041
No log 2.2632 86 0.7221 0.2892 0.7221 0.8498
No log 2.3158 88 0.6746 0.3628 0.6746 0.8214
No log 2.3684 90 0.6691 0.4570 0.6691 0.8180
No log 2.4211 92 0.7051 0.4074 0.7051 0.8397
No log 2.4737 94 0.8914 0.3234 0.8914 0.9441
No log 2.5263 96 1.0236 0.3079 1.0236 1.0117
No log 2.5789 98 0.8994 0.3898 0.8994 0.9484
No log 2.6316 100 0.7376 0.4089 0.7376 0.8588
No log 2.6842 102 0.7401 0.3578 0.7401 0.8603
No log 2.7368 104 0.9291 0.3567 0.9291 0.9639
No log 2.7895 106 0.9190 0.3479 0.9190 0.9587
No log 2.8421 108 0.7760 0.3681 0.7760 0.8809
No log 2.8947 110 0.6885 0.4174 0.6885 0.8297
No log 2.9474 112 0.7653 0.4100 0.7653 0.8748
No log 3.0 114 0.6761 0.4321 0.6761 0.8222
No log 3.0526 116 0.7811 0.3324 0.7811 0.8838
No log 3.1053 118 1.0419 0.3169 1.0419 1.0208
No log 3.1579 120 1.0014 0.3145 1.0014 1.0007
No log 3.2105 122 0.7376 0.4074 0.7376 0.8588
No log 3.2632 124 0.6683 0.3550 0.6683 0.8175
No log 3.3158 126 0.7024 0.3216 0.7024 0.8381
No log 3.3684 128 0.6908 0.3542 0.6908 0.8312
No log 3.4211 130 0.7954 0.3383 0.7954 0.8919
No log 3.4737 132 0.8443 0.3489 0.8443 0.9189
No log 3.5263 134 0.7840 0.3772 0.7840 0.8854
No log 3.5789 136 0.8167 0.3230 0.8167 0.9037
No log 3.6316 138 0.9483 0.3446 0.9483 0.9738
No log 3.6842 140 1.1276 0.3011 1.1276 1.0619
No log 3.7368 142 1.0205 0.3272 1.0205 1.0102
No log 3.7895 144 0.8394 0.2847 0.8394 0.9162
No log 3.8421 146 0.7886 0.3684 0.7886 0.8880
No log 3.8947 148 0.8330 0.3316 0.8330 0.9127
No log 3.9474 150 0.9085 0.3461 0.9085 0.9531
No log 4.0 152 0.7584 0.4263 0.7584 0.8708
No log 4.0526 154 0.6417 0.4378 0.6417 0.8010
No log 4.1053 156 0.6679 0.4783 0.6679 0.8173
No log 4.1579 158 0.6402 0.4483 0.6402 0.8001
No log 4.2105 160 0.6417 0.4507 0.6417 0.8011
No log 4.2632 162 0.6394 0.4318 0.6394 0.7996
No log 4.3158 164 0.6208 0.4533 0.6208 0.7879
No log 4.3684 166 0.6343 0.3495 0.6343 0.7964
No log 4.4211 168 0.6837 0.3700 0.6837 0.8268
No log 4.4737 170 0.6638 0.3664 0.6638 0.8147
No log 4.5263 172 0.6462 0.3618 0.6462 0.8038
No log 4.5789 174 0.7193 0.3813 0.7193 0.8481
No log 4.6316 176 0.7091 0.4397 0.7091 0.8421
No log 4.6842 178 0.6457 0.4583 0.6457 0.8035
No log 4.7368 180 0.6720 0.4500 0.6720 0.8198
No log 4.7895 182 0.6147 0.5034 0.6147 0.7840
No log 4.8421 184 0.6509 0.3773 0.6509 0.8068
No log 4.8947 186 0.6449 0.3700 0.6449 0.8030
No log 4.9474 188 0.6421 0.4343 0.6421 0.8013
No log 5.0 190 0.7698 0.4450 0.7698 0.8774
No log 5.0526 192 0.7559 0.4037 0.7559 0.8694
No log 5.1053 194 0.7173 0.3782 0.7173 0.8469
No log 5.1579 196 0.7294 0.3860 0.7294 0.8541
No log 5.2105 198 0.7621 0.3729 0.7621 0.8730
No log 5.2632 200 0.9776 0.4339 0.9776 0.9888
No log 5.3158 202 0.9609 0.4334 0.9609 0.9802
No log 5.3684 204 0.7982 0.4466 0.7982 0.8934
No log 5.4211 206 0.7114 0.4464 0.7114 0.8434
No log 5.4737 208 0.6533 0.4233 0.6533 0.8083
No log 5.5263 210 0.6853 0.4250 0.6853 0.8278
No log 5.5789 212 0.9139 0.4052 0.9139 0.9560
No log 5.6316 214 1.1568 0.3331 1.1568 1.0755
No log 5.6842 216 1.0503 0.3470 1.0503 1.0249
No log 5.7368 218 0.7469 0.4472 0.7469 0.8642
No log 5.7895 220 0.6245 0.5046 0.6245 0.7903
No log 5.8421 222 0.6179 0.4860 0.6179 0.7861
No log 5.8947 224 0.6279 0.4521 0.6279 0.7924
No log 5.9474 226 0.8150 0.4413 0.8150 0.9028
No log 6.0 228 0.9317 0.3972 0.9317 0.9653
No log 6.0526 230 0.8293 0.4419 0.8293 0.9106
No log 6.1053 232 0.6546 0.3359 0.6546 0.8091
No log 6.1579 234 0.6605 0.3262 0.6605 0.8127
No log 6.2105 236 0.6667 0.3800 0.6667 0.8165
No log 6.2632 238 0.6328 0.3868 0.6328 0.7955
No log 6.3158 240 0.6409 0.4190 0.6409 0.8006
No log 6.3684 242 0.6030 0.4936 0.6030 0.7766
No log 6.4211 244 0.6039 0.4370 0.6039 0.7771
No log 6.4737 246 0.5951 0.5533 0.5951 0.7714
No log 6.5263 248 0.6645 0.4478 0.6645 0.8152
No log 6.5789 250 0.8172 0.4091 0.8172 0.9040
No log 6.6316 252 0.7578 0.4486 0.7578 0.8705
No log 6.6842 254 0.6332 0.3553 0.6332 0.7957
No log 6.7368 256 0.6191 0.3736 0.6191 0.7868
No log 6.7895 258 0.6232 0.3849 0.6232 0.7894
No log 6.8421 260 0.6458 0.3763 0.6458 0.8036
No log 6.8947 262 0.6834 0.4159 0.6834 0.8267
No log 6.9474 264 0.6377 0.3907 0.6377 0.7986
No log 7.0 266 0.6248 0.4090 0.6248 0.7904
No log 7.0526 268 0.6100 0.3471 0.6100 0.7810
No log 7.1053 270 0.6139 0.3924 0.6139 0.7835
No log 7.1579 272 0.6240 0.4669 0.6240 0.7899
No log 7.2105 274 0.6322 0.4164 0.6322 0.7951
No log 7.2632 276 0.6654 0.3621 0.6654 0.8158
No log 7.3158 278 0.7827 0.4056 0.7827 0.8847
No log 7.3684 280 0.7267 0.4078 0.7267 0.8525
No log 7.4211 282 0.6257 0.4460 0.6257 0.7910
No log 7.4737 284 0.6614 0.5273 0.6614 0.8133
No log 7.5263 286 0.6454 0.5273 0.6454 0.8034
No log 7.5789 288 0.6316 0.4074 0.6316 0.7947
No log 7.6316 290 0.6934 0.4225 0.6934 0.8327
No log 7.6842 292 0.6661 0.4072 0.6661 0.8161
No log 7.7368 294 0.6256 0.4504 0.6256 0.7909
No log 7.7895 296 0.6026 0.4102 0.6026 0.7763
No log 7.8421 298 0.6001 0.4688 0.6001 0.7747
No log 7.8947 300 0.6008 0.4360 0.6008 0.7751
No log 7.9474 302 0.5877 0.4328 0.5877 0.7666
No log 8.0 304 0.5880 0.4313 0.5880 0.7668
No log 8.0526 306 0.5824 0.4446 0.5824 0.7631
No log 8.1053 308 0.6303 0.4579 0.6303 0.7939
No log 8.1579 310 0.6687 0.5417 0.6687 0.8177
No log 8.2105 312 0.6243 0.4938 0.6243 0.7901
No log 8.2632 314 0.5755 0.4783 0.5755 0.7586
No log 8.3158 316 0.5701 0.4946 0.5701 0.7551
No log 8.3684 318 0.5687 0.4807 0.5687 0.7541
No log 8.4211 320 0.5731 0.4818 0.5731 0.7570
No log 8.4737 322 0.5650 0.4473 0.5650 0.7517
No log 8.5263 324 0.5626 0.4344 0.5626 0.7501
No log 8.5789 326 0.5687 0.4818 0.5687 0.7541
No log 8.6316 328 0.5710 0.4823 0.5710 0.7556
No log 8.6842 330 0.5646 0.5378 0.5646 0.7514
No log 8.7368 332 0.6081 0.4487 0.6081 0.7798
No log 8.7895 334 0.5823 0.4353 0.5823 0.7631
No log 8.8421 336 0.5692 0.4594 0.5692 0.7545
No log 8.8947 338 0.5635 0.4546 0.5635 0.7507
No log 8.9474 340 0.5862 0.5524 0.5862 0.7657
No log 9.0 342 0.5767 0.5272 0.5767 0.7594
No log 9.0526 344 0.5804 0.4941 0.5804 0.7619
No log 9.1053 346 0.6106 0.4821 0.6106 0.7814
No log 9.1579 348 0.5803 0.5064 0.5803 0.7618
No log 9.2105 350 0.5632 0.4335 0.5632 0.7504
No log 9.2632 352 0.5813 0.4588 0.5813 0.7625
No log 9.3158 354 0.6550 0.3729 0.6550 0.8093
No log 9.3684 356 0.6636 0.3898 0.6636 0.8146
No log 9.4211 358 0.6219 0.3973 0.6219 0.7886
No log 9.4737 360 0.5989 0.4321 0.5989 0.7739
No log 9.5263 362 0.5790 0.4339 0.5790 0.7609
No log 9.5789 364 0.5886 0.4341 0.5886 0.7672
No log 9.6316 366 0.6060 0.4945 0.6060 0.7785
No log 9.6842 368 0.6615 0.5121 0.6615 0.8133
No log 9.7368 370 0.6721 0.5399 0.6721 0.8198
No log 9.7895 372 0.5980 0.4672 0.5980 0.7733
No log 9.8421 374 0.5906 0.4341 0.5906 0.7685
No log 9.8947 376 0.5856 0.4587 0.5856 0.7653
No log 9.9474 378 0.5871 0.4585 0.5871 0.7663
No log 10.0 380 0.6534 0.5507 0.6534 0.8083
No log 10.0526 382 0.6789 0.5732 0.6789 0.8239
No log 10.1053 384 0.6180 0.5484 0.6180 0.7861
No log 10.1579 386 0.5730 0.4861 0.5730 0.7569
No log 10.2105 388 0.5798 0.4697 0.5798 0.7614
No log 10.2632 390 0.5709 0.4559 0.5709 0.7555
No log 10.3158 392 0.5679 0.5012 0.5679 0.7536
No log 10.3684 394 0.5862 0.5997 0.5862 0.7656
No log 10.4211 396 0.5922 0.6060 0.5922 0.7696
No log 10.4737 398 0.5631 0.4790 0.5631 0.7504
No log 10.5263 400 0.6620 0.4487 0.6620 0.8136
No log 10.5789 402 0.7541 0.4181 0.7541 0.8684
No log 10.6316 404 0.6715 0.4150 0.6715 0.8195
No log 10.6842 406 0.5675 0.4271 0.5675 0.7533
No log 10.7368 408 0.5922 0.5281 0.5922 0.7695
No log 10.7895 410 0.6709 0.4457 0.6709 0.8191
No log 10.8421 412 0.6668 0.4776 0.6668 0.8166
No log 10.8947 414 0.6004 0.4634 0.6004 0.7749
No log 10.9474 416 0.5899 0.5057 0.5899 0.7681
No log 11.0 418 0.6032 0.4582 0.6032 0.7766
No log 11.0526 420 0.6346 0.5013 0.6346 0.7966
No log 11.1053 422 0.7230 0.4849 0.7230 0.8503
No log 11.1579 424 0.7941 0.4639 0.7941 0.8911
No log 11.2105 426 0.7459 0.4339 0.7459 0.8636
No log 11.2632 428 0.6531 0.3622 0.6531 0.8082
No log 11.3158 430 0.5910 0.4889 0.5910 0.7688
No log 11.3684 432 0.5890 0.4260 0.5890 0.7674
No log 11.4211 434 0.5814 0.4562 0.5814 0.7625
No log 11.4737 436 0.5924 0.4682 0.5924 0.7697
No log 11.5263 438 0.6668 0.4921 0.6668 0.8166
No log 11.5789 440 0.7004 0.5315 0.7004 0.8369
No log 11.6316 442 0.6308 0.5020 0.6308 0.7943
No log 11.6842 444 0.5825 0.4779 0.5825 0.7632
No log 11.7368 446 0.5895 0.4037 0.5895 0.7678
No log 11.7895 448 0.6116 0.4212 0.6116 0.7820
No log 11.8421 450 0.6151 0.4331 0.6151 0.7843
No log 11.8947 452 0.6791 0.4153 0.6791 0.8241
No log 11.9474 454 0.7925 0.4219 0.7925 0.8902
No log 12.0 456 0.8212 0.3981 0.8212 0.9062
No log 12.0526 458 0.7256 0.4108 0.7256 0.8518
No log 12.1053 460 0.6305 0.4620 0.6305 0.7941
No log 12.1579 462 0.6111 0.4130 0.6111 0.7817
No log 12.2105 464 0.6068 0.4254 0.6068 0.7790
No log 12.2632 466 0.6145 0.4569 0.6145 0.7839
No log 12.3158 468 0.6537 0.4780 0.6537 0.8085
No log 12.3684 470 0.6632 0.4780 0.6632 0.8144
No log 12.4211 472 0.6382 0.4585 0.6382 0.7988
No log 12.4737 474 0.5962 0.4889 0.5962 0.7721
No log 12.5263 476 0.5793 0.4490 0.5793 0.7611
No log 12.5789 478 0.5941 0.4541 0.5941 0.7708
No log 12.6316 480 0.6489 0.4629 0.6489 0.8055
No log 12.6842 482 0.7006 0.4671 0.7006 0.8370
No log 12.7368 484 0.6587 0.4538 0.6587 0.8116
No log 12.7895 486 0.5985 0.4792 0.5985 0.7736
No log 12.8421 488 0.5737 0.4717 0.5737 0.7574
No log 12.8947 490 0.5759 0.4676 0.5759 0.7589
No log 12.9474 492 0.5975 0.5453 0.5975 0.7730
No log 13.0 494 0.6296 0.5531 0.6296 0.7935
No log 13.0526 496 0.6141 0.5720 0.6141 0.7837
No log 13.1053 498 0.5920 0.4657 0.5920 0.7694
0.3611 13.1579 500 0.6005 0.4102 0.6005 0.7749
0.3611 13.2105 502 0.5983 0.3617 0.5983 0.7735
0.3611 13.2632 504 0.6021 0.4036 0.6021 0.7759
0.3611 13.3158 506 0.6109 0.3601 0.6109 0.7816
0.3611 13.3684 508 0.6312 0.2915 0.6312 0.7945
0.3611 13.4211 510 0.6200 0.3132 0.6200 0.7874

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
3
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/ArabicNewSplits8_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k7_task2_organization

Finetuned
(4040)
this model