ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k5_task7_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: 0.4201
  • Qwk: 0.6890
  • Mse: 0.4201
  • Rmse: 0.6482

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 0.1333 2 2.5900 -0.0593 2.5900 1.6094
No log 0.2667 4 1.1749 0.0993 1.1749 1.0839
No log 0.4 6 0.7766 0.0937 0.7766 0.8812
No log 0.5333 8 0.7910 0.0608 0.7910 0.8894
No log 0.6667 10 0.9163 0.2939 0.9163 0.9572
No log 0.8 12 0.7580 0.2467 0.7580 0.8706
No log 0.9333 14 0.7363 0.2063 0.7363 0.8581
No log 1.0667 16 0.9297 0.1288 0.9297 0.9642
No log 1.2 18 0.7754 0.2103 0.7754 0.8806
No log 1.3333 20 0.6582 0.1903 0.6582 0.8113
No log 1.4667 22 0.6466 0.3123 0.6466 0.8041
No log 1.6 24 0.6362 0.3494 0.6362 0.7976
No log 1.7333 26 0.6149 0.3274 0.6149 0.7841
No log 1.8667 28 0.6052 0.3354 0.6052 0.7780
No log 2.0 30 0.5955 0.2412 0.5955 0.7717
No log 2.1333 32 0.5959 0.2345 0.5959 0.7719
No log 2.2667 34 0.5791 0.2851 0.5791 0.7610
No log 2.4 36 0.5829 0.3640 0.5829 0.7635
No log 2.5333 38 0.5087 0.4561 0.5087 0.7132
No log 2.6667 40 0.4745 0.5227 0.4745 0.6888
No log 2.8 42 0.6166 0.4315 0.6166 0.7852
No log 2.9333 44 0.7377 0.4667 0.7377 0.8589
No log 3.0667 46 0.5466 0.4681 0.5466 0.7393
No log 3.2 48 0.5284 0.6206 0.5284 0.7269
No log 3.3333 50 0.7271 0.4667 0.7271 0.8527
No log 3.4667 52 0.5653 0.5664 0.5653 0.7519
No log 3.6 54 0.5173 0.4966 0.5173 0.7193
No log 3.7333 56 0.6063 0.4982 0.6063 0.7787
No log 3.8667 58 0.4959 0.5288 0.4959 0.7042
No log 4.0 60 0.6390 0.5160 0.6390 0.7994
No log 4.1333 62 0.8174 0.4568 0.8174 0.9041
No log 4.2667 64 0.6749 0.4977 0.6749 0.8215
No log 4.4 66 0.4779 0.6317 0.4779 0.6913
No log 4.5333 68 0.6324 0.5215 0.6324 0.7952
No log 4.6667 70 0.8170 0.4511 0.8170 0.9039
No log 4.8 72 0.6603 0.4648 0.6603 0.8126
No log 4.9333 74 0.4626 0.6032 0.4626 0.6802
No log 5.0667 76 0.6003 0.5489 0.6003 0.7748
No log 5.2 78 0.6730 0.5093 0.6730 0.8204
No log 5.3333 80 0.5691 0.5595 0.5691 0.7544
No log 5.4667 82 0.4984 0.5559 0.4984 0.7060
No log 5.6 84 0.8386 0.4953 0.8386 0.9158
No log 5.7333 86 0.9554 0.4670 0.9554 0.9775
No log 5.8667 88 0.7667 0.4844 0.7667 0.8756
No log 6.0 90 0.5351 0.5770 0.5351 0.7315
No log 6.1333 92 0.5217 0.6677 0.5217 0.7223
No log 6.2667 94 0.5359 0.6773 0.5359 0.7320
No log 6.4 96 0.5136 0.5874 0.5136 0.7167
No log 6.5333 98 0.5468 0.5341 0.5468 0.7394
No log 6.6667 100 0.6543 0.4805 0.6543 0.8089
No log 6.8 102 0.6474 0.4805 0.6474 0.8046
No log 6.9333 104 0.6291 0.4610 0.6291 0.7932
No log 7.0667 106 0.6204 0.4385 0.6204 0.7877
No log 7.2 108 0.5221 0.5015 0.5221 0.7226
No log 7.3333 110 0.5037 0.5324 0.5037 0.7097
No log 7.4667 112 0.4985 0.5324 0.4985 0.7060
No log 7.6 114 0.4617 0.5988 0.4617 0.6795
No log 7.7333 116 0.4479 0.6254 0.4479 0.6693
No log 7.8667 118 0.4548 0.6101 0.4548 0.6744
No log 8.0 120 0.4574 0.6101 0.4574 0.6763
No log 8.1333 122 0.4264 0.6142 0.4264 0.6530
No log 8.2667 124 0.5067 0.5677 0.5067 0.7118
No log 8.4 126 0.5218 0.5497 0.5218 0.7224
No log 8.5333 128 0.4384 0.6004 0.4384 0.6621
No log 8.6667 130 0.4204 0.6655 0.4204 0.6484
No log 8.8 132 0.4230 0.6957 0.4230 0.6504
No log 8.9333 134 0.4248 0.6863 0.4248 0.6518
No log 9.0667 136 0.4173 0.6060 0.4173 0.6460
No log 9.2 138 0.4438 0.6214 0.4438 0.6662
No log 9.3333 140 0.4618 0.6214 0.4618 0.6796
No log 9.4667 142 0.4815 0.5983 0.4815 0.6939
No log 9.6 144 0.5320 0.5418 0.5320 0.7294
No log 9.7333 146 0.6049 0.5614 0.6049 0.7778
No log 9.8667 148 0.6328 0.6 0.6328 0.7955
No log 10.0 150 0.4585 0.5961 0.4585 0.6771
No log 10.1333 152 0.4219 0.6750 0.4219 0.6495
No log 10.2667 154 0.4240 0.6197 0.4240 0.6511
No log 10.4 156 0.4258 0.6197 0.4258 0.6525
No log 10.5333 158 0.4244 0.6007 0.4244 0.6515
No log 10.6667 160 0.4553 0.5886 0.4553 0.6747
No log 10.8 162 0.4772 0.5831 0.4772 0.6908
No log 10.9333 164 0.4641 0.6624 0.4641 0.6812
No log 11.0667 166 0.4812 0.5970 0.4812 0.6936
No log 11.2 168 0.4772 0.5875 0.4772 0.6908
No log 11.3333 170 0.4561 0.6530 0.4561 0.6754
No log 11.4667 172 0.4548 0.6158 0.4548 0.6744
No log 11.6 174 0.5568 0.5763 0.5568 0.7462
No log 11.7333 176 0.5986 0.5813 0.5986 0.7737
No log 11.8667 178 0.5060 0.6096 0.5060 0.7113
No log 12.0 180 0.4443 0.5840 0.4443 0.6666
No log 12.1333 182 0.4557 0.6709 0.4557 0.6750
No log 12.2667 184 0.4515 0.6526 0.4515 0.6719
No log 12.4 186 0.4393 0.6310 0.4393 0.6628
No log 12.5333 188 0.5267 0.5323 0.5267 0.7258
No log 12.6667 190 0.6093 0.5738 0.6093 0.7806
No log 12.8 192 0.5337 0.5170 0.5337 0.7306
No log 12.9333 194 0.4392 0.6359 0.4392 0.6628
No log 13.0667 196 0.4459 0.6282 0.4459 0.6678
No log 13.2 198 0.4367 0.6464 0.4367 0.6608
No log 13.3333 200 0.4581 0.5692 0.4581 0.6768
No log 13.4667 202 0.4869 0.5468 0.4869 0.6978
No log 13.6 204 0.4553 0.5897 0.4553 0.6747
No log 13.7333 206 0.4517 0.6277 0.4517 0.6721
No log 13.8667 208 0.4740 0.6222 0.4740 0.6885
No log 14.0 210 0.4843 0.5989 0.4843 0.6959
No log 14.1333 212 0.4774 0.6235 0.4774 0.6909
No log 14.2667 214 0.4884 0.6419 0.4884 0.6989
No log 14.4 216 0.4608 0.5492 0.4608 0.6788
No log 14.5333 218 0.4661 0.5609 0.4661 0.6827
No log 14.6667 220 0.4691 0.5609 0.4691 0.6849
No log 14.8 222 0.4726 0.5687 0.4726 0.6874
No log 14.9333 224 0.4985 0.5560 0.4985 0.7060
No log 15.0667 226 0.5897 0.5008 0.5897 0.7679
No log 15.2 228 0.6297 0.5351 0.6297 0.7935
No log 15.3333 230 0.5511 0.5431 0.5511 0.7424
No log 15.4667 232 0.4983 0.5184 0.4983 0.7059
No log 15.6 234 0.4968 0.5160 0.4968 0.7048
No log 15.7333 236 0.4864 0.5057 0.4864 0.6974
No log 15.8667 238 0.4910 0.5206 0.4910 0.7007
No log 16.0 240 0.5292 0.4911 0.5292 0.7275
No log 16.1333 242 0.4924 0.5177 0.4924 0.7017
No log 16.2667 244 0.4603 0.6214 0.4603 0.6784
No log 16.4 246 0.4561 0.5373 0.4561 0.6753
No log 16.5333 248 0.4530 0.5373 0.4530 0.6731
No log 16.6667 250 0.4515 0.6032 0.4515 0.6720
No log 16.8 252 0.4800 0.5897 0.4800 0.6928
No log 16.9333 254 0.5011 0.5708 0.5011 0.7079
No log 17.0667 256 0.4696 0.5816 0.4696 0.6853
No log 17.2 258 0.4509 0.6371 0.4509 0.6715
No log 17.3333 260 0.4754 0.6445 0.4754 0.6895
No log 17.4667 262 0.4751 0.6445 0.4751 0.6893
No log 17.6 264 0.4552 0.6184 0.4552 0.6747
No log 17.7333 266 0.5146 0.5511 0.5146 0.7174
No log 17.8667 268 0.6125 0.5364 0.6125 0.7826
No log 18.0 270 0.6019 0.5410 0.6019 0.7758
No log 18.1333 272 0.5143 0.5379 0.5143 0.7172
No log 18.2667 274 0.4460 0.5941 0.4460 0.6678
No log 18.4 276 0.4519 0.6170 0.4519 0.6722
No log 18.5333 278 0.4628 0.5985 0.4628 0.6803
No log 18.6667 280 0.4507 0.5890 0.4507 0.6713
No log 18.8 282 0.4443 0.6455 0.4443 0.6665
No log 18.9333 284 0.4576 0.6460 0.4576 0.6765
No log 19.0667 286 0.4649 0.6747 0.4649 0.6819
No log 19.2 288 0.4747 0.7067 0.4747 0.6890
No log 19.3333 290 0.4637 0.7067 0.4637 0.6810
No log 19.4667 292 0.4453 0.6662 0.4453 0.6673
No log 19.6 294 0.4349 0.6395 0.4349 0.6595
No log 19.7333 296 0.4482 0.6127 0.4482 0.6695
No log 19.8667 298 0.4480 0.5642 0.4480 0.6693
No log 20.0 300 0.4335 0.6357 0.4335 0.6584
No log 20.1333 302 0.4318 0.6542 0.4318 0.6571
No log 20.2667 304 0.4381 0.6542 0.4381 0.6619
No log 20.4 306 0.4412 0.6564 0.4412 0.6642
No log 20.5333 308 0.4584 0.6427 0.4584 0.6770
No log 20.6667 310 0.4615 0.6958 0.4615 0.6793
No log 20.8 312 0.4734 0.6387 0.4734 0.6880
No log 20.9333 314 0.4652 0.6382 0.4652 0.6821
No log 21.0667 316 0.4572 0.6027 0.4572 0.6762
No log 21.2 318 0.4675 0.5554 0.4675 0.6838
No log 21.3333 320 0.4589 0.5627 0.4589 0.6774
No log 21.4667 322 0.4520 0.5446 0.4520 0.6723
No log 21.6 324 0.4747 0.5845 0.4747 0.6890
No log 21.7333 326 0.4926 0.5708 0.4926 0.7019
No log 21.8667 328 0.4696 0.5897 0.4696 0.6853
No log 22.0 330 0.4490 0.6455 0.4490 0.6701
No log 22.1333 332 0.4873 0.5422 0.4873 0.6981
No log 22.2667 334 0.5000 0.5422 0.5000 0.7071
No log 22.4 336 0.4721 0.5373 0.4721 0.6871
No log 22.5333 338 0.4729 0.6517 0.4729 0.6877
No log 22.6667 340 0.4875 0.6303 0.4875 0.6982
No log 22.8 342 0.4743 0.5476 0.4743 0.6887
No log 22.9333 344 0.4750 0.5336 0.4750 0.6892
No log 23.0667 346 0.4921 0.5491 0.4921 0.7015
No log 23.2 348 0.5283 0.6761 0.5283 0.7268
No log 23.3333 350 0.5400 0.6761 0.5400 0.7349
No log 23.4667 352 0.4994 0.6009 0.4994 0.7067
No log 23.6 354 0.4891 0.5286 0.4891 0.6994
No log 23.7333 356 0.5107 0.5848 0.5107 0.7146
No log 23.8667 358 0.4914 0.5378 0.4914 0.7010
No log 24.0 360 0.4750 0.5886 0.4750 0.6892
No log 24.1333 362 0.5124 0.6137 0.5124 0.7158
No log 24.2667 364 0.5257 0.5831 0.5257 0.7250
No log 24.4 366 0.4925 0.5965 0.4925 0.7018
No log 24.5333 368 0.4639 0.5631 0.4639 0.6811
No log 24.6667 370 0.4546 0.6010 0.4546 0.6742
No log 24.8 372 0.4459 0.6060 0.4459 0.6678
No log 24.9333 374 0.4546 0.5956 0.4546 0.6742
No log 25.0667 376 0.4859 0.6181 0.4859 0.6971
No log 25.2 378 0.4679 0.6361 0.4679 0.6841
No log 25.3333 380 0.4402 0.7137 0.4402 0.6635
No log 25.4667 382 0.4223 0.7097 0.4223 0.6498
No log 25.6 384 0.4157 0.7373 0.4157 0.6448
No log 25.7333 386 0.4156 0.6960 0.4156 0.6446
No log 25.8667 388 0.4333 0.6248 0.4333 0.6583
No log 26.0 390 0.4322 0.5855 0.4322 0.6574
No log 26.1333 392 0.4157 0.5985 0.4157 0.6447
No log 26.2667 394 0.4216 0.6833 0.4216 0.6493
No log 26.4 396 0.4420 0.6278 0.4420 0.6648
No log 26.5333 398 0.4386 0.6278 0.4386 0.6623
No log 26.6667 400 0.4254 0.6733 0.4254 0.6522
No log 26.8 402 0.4221 0.5904 0.4221 0.6497
No log 26.9333 404 0.4254 0.6040 0.4254 0.6522
No log 27.0667 406 0.4341 0.6474 0.4341 0.6588
No log 27.2 408 0.4626 0.6003 0.4626 0.6801
No log 27.3333 410 0.4779 0.5364 0.4779 0.6913
No log 27.4667 412 0.4461 0.5845 0.4461 0.6679
No log 27.6 414 0.4321 0.6032 0.4321 0.6573
No log 27.7333 416 0.4291 0.6129 0.4291 0.6551
No log 27.8667 418 0.4323 0.5195 0.4323 0.6575
No log 28.0 420 0.4347 0.5195 0.4347 0.6593
No log 28.1333 422 0.4417 0.5703 0.4417 0.6646
No log 28.2667 424 0.4674 0.6289 0.4674 0.6837
No log 28.4 426 0.4730 0.6289 0.4730 0.6877
No log 28.5333 428 0.4684 0.6395 0.4684 0.6844
No log 28.6667 430 0.4566 0.5422 0.4566 0.6757
No log 28.8 432 0.4568 0.5853 0.4568 0.6759
No log 28.9333 434 0.4536 0.5422 0.4536 0.6735
No log 29.0667 436 0.4439 0.5765 0.4439 0.6663
No log 29.2 438 0.4377 0.5750 0.4377 0.6616
No log 29.3333 440 0.4371 0.5580 0.4371 0.6611
No log 29.4667 442 0.4334 0.5979 0.4334 0.6584
No log 29.6 444 0.4259 0.6364 0.4259 0.6526
No log 29.7333 446 0.4182 0.6841 0.4182 0.6467
No log 29.8667 448 0.4186 0.6269 0.4186 0.6470
No log 30.0 450 0.4188 0.6745 0.4188 0.6471
No log 30.1333 452 0.4204 0.6953 0.4204 0.6484
No log 30.2667 454 0.4154 0.6953 0.4154 0.6445
No log 30.4 456 0.4069 0.6953 0.4069 0.6379
No log 30.5333 458 0.4070 0.6759 0.4070 0.6379
No log 30.6667 460 0.4244 0.6389 0.4244 0.6515
No log 30.8 462 0.4374 0.5918 0.4374 0.6613
No log 30.9333 464 0.4254 0.6589 0.4254 0.6522
No log 31.0667 466 0.4168 0.6841 0.4168 0.6456
No log 31.2 468 0.4186 0.6832 0.4186 0.6470
No log 31.3333 470 0.4320 0.6604 0.4320 0.6573
No log 31.4667 472 0.4269 0.6611 0.4269 0.6533
No log 31.6 474 0.4226 0.6931 0.4226 0.6501
No log 31.7333 476 0.4209 0.6643 0.4209 0.6488
No log 31.8667 478 0.4193 0.6170 0.4193 0.6475
No log 32.0 480 0.4165 0.6292 0.4165 0.6454
No log 32.1333 482 0.4175 0.6491 0.4175 0.6462
No log 32.2667 484 0.4332 0.5841 0.4332 0.6582
No log 32.4 486 0.4581 0.5869 0.4581 0.6768
No log 32.5333 488 0.4654 0.5794 0.4654 0.6822
No log 32.6667 490 0.4388 0.6061 0.4388 0.6625
No log 32.8 492 0.4072 0.7123 0.4072 0.6381
No log 32.9333 494 0.4056 0.6841 0.4056 0.6369
No log 33.0667 496 0.4110 0.6739 0.4110 0.6411
No log 33.2 498 0.4060 0.6739 0.4060 0.6372
0.2691 33.3333 500 0.4018 0.7218 0.4018 0.6339
0.2691 33.4667 502 0.4015 0.6587 0.4015 0.6337
0.2691 33.6 504 0.4012 0.6672 0.4012 0.6334
0.2691 33.7333 506 0.4014 0.6364 0.4014 0.6335
0.2691 33.8667 508 0.4050 0.6452 0.4050 0.6364
0.2691 34.0 510 0.4201 0.6890 0.4201 0.6482

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
8
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_run1_AugV5_k5_task7_organization

Finetuned
(4204)
this model