MayBashendy's picture
End of training
2cfeafb verified
metadata
library_name: transformers
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask2_mechanics
    results: []

Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask2_mechanics

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: 0.5455
  • Qwk: 0.5691
  • Mse: 0.5455
  • Rmse: 0.7386

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 0.0213 2 3.6715 0.0220 3.6715 1.9161
No log 0.0426 4 2.8563 0.0503 2.8563 1.6901
No log 0.0638 6 1.2401 0.1393 1.2401 1.1136
No log 0.0851 8 0.6320 0.3124 0.6320 0.7950
No log 0.1064 10 0.6755 0.1823 0.6755 0.8219
No log 0.1277 12 0.6662 0.3674 0.6662 0.8162
No log 0.1489 14 0.6873 0.4927 0.6873 0.8290
No log 0.1702 16 0.7652 0.4506 0.7652 0.8747
No log 0.1915 18 0.6937 0.4862 0.6937 0.8329
No log 0.2128 20 0.6393 0.5286 0.6393 0.7995
No log 0.2340 22 0.6497 0.5065 0.6497 0.8061
No log 0.2553 24 0.5188 0.5033 0.5188 0.7203
No log 0.2766 26 0.5712 0.4637 0.5712 0.7558
No log 0.2979 28 0.5273 0.4938 0.5273 0.7262
No log 0.3191 30 0.5406 0.4374 0.5406 0.7353
No log 0.3404 32 0.5355 0.4394 0.5355 0.7318
No log 0.3617 34 0.5206 0.4111 0.5206 0.7215
No log 0.3830 36 0.5333 0.3941 0.5333 0.7303
No log 0.4043 38 0.5406 0.4039 0.5406 0.7353
No log 0.4255 40 0.5325 0.4156 0.5325 0.7297
No log 0.4468 42 0.5373 0.4246 0.5373 0.7330
No log 0.4681 44 0.5923 0.2852 0.5923 0.7696
No log 0.4894 46 0.6183 0.2807 0.6183 0.7863
No log 0.5106 48 0.6858 0.2402 0.6858 0.8281
No log 0.5319 50 0.6494 0.3082 0.6494 0.8058
No log 0.5532 52 0.5569 0.4049 0.5569 0.7463
No log 0.5745 54 0.4656 0.5388 0.4656 0.6823
No log 0.5957 56 0.4648 0.5786 0.4648 0.6818
No log 0.6170 58 0.4398 0.5717 0.4398 0.6632
No log 0.6383 60 0.4197 0.5555 0.4197 0.6478
No log 0.6596 62 0.4172 0.5539 0.4172 0.6459
No log 0.6809 64 0.4408 0.6286 0.4408 0.6639
No log 0.7021 66 0.5555 0.6009 0.5555 0.7453
No log 0.7234 68 0.7550 0.5525 0.7550 0.8689
No log 0.7447 70 0.8124 0.5613 0.8124 0.9013
No log 0.7660 72 0.6974 0.5848 0.6974 0.8351
No log 0.7872 74 0.6234 0.6201 0.6234 0.7895
No log 0.8085 76 0.5605 0.6280 0.5605 0.7487
No log 0.8298 78 0.4423 0.6579 0.4423 0.6651
No log 0.8511 80 0.5967 0.5139 0.5967 0.7724
No log 0.8723 82 0.6308 0.4865 0.6308 0.7942
No log 0.8936 84 0.4449 0.5544 0.4449 0.6670
No log 0.9149 86 0.4097 0.5727 0.4097 0.6401
No log 0.9362 88 0.4110 0.5767 0.4110 0.6411
No log 0.9574 90 0.5281 0.5330 0.5281 0.7267
No log 0.9787 92 0.5240 0.5274 0.5240 0.7239
No log 1.0 94 0.4051 0.6067 0.4051 0.6365
No log 1.0213 96 0.4063 0.6368 0.4063 0.6374
No log 1.0426 98 0.5241 0.5896 0.5241 0.7239
No log 1.0638 100 0.5979 0.5377 0.5979 0.7732
No log 1.0851 102 0.5571 0.5235 0.5571 0.7464
No log 1.1064 104 0.5328 0.5192 0.5328 0.7299
No log 1.1277 106 0.5125 0.4497 0.5125 0.7159
No log 1.1489 108 0.4651 0.4769 0.4651 0.6820
No log 1.1702 110 0.4263 0.5330 0.4263 0.6529
No log 1.1915 112 0.4218 0.5453 0.4218 0.6495
No log 1.2128 114 0.4469 0.4965 0.4469 0.6685
No log 1.2340 116 0.4962 0.4085 0.4962 0.7044
No log 1.2553 118 0.5140 0.4575 0.5140 0.7170
No log 1.2766 120 0.5814 0.5020 0.5814 0.7625
No log 1.2979 122 0.5288 0.5370 0.5288 0.7272
No log 1.3191 124 0.5162 0.5865 0.5162 0.7185
No log 1.3404 126 0.4904 0.6492 0.4904 0.7003
No log 1.3617 128 0.4597 0.6086 0.4597 0.6780
No log 1.3830 130 0.4506 0.6136 0.4506 0.6713
No log 1.4043 132 0.5070 0.5862 0.5070 0.7120
No log 1.4255 134 0.6795 0.4488 0.6795 0.8243
No log 1.4468 136 0.6479 0.4579 0.6479 0.8049
No log 1.4681 138 0.4713 0.5356 0.4713 0.6865
No log 1.4894 140 0.4060 0.5929 0.4060 0.6372
No log 1.5106 142 0.4000 0.6152 0.4000 0.6324
No log 1.5319 144 0.4305 0.5835 0.4305 0.6561
No log 1.5532 146 0.6179 0.4605 0.6179 0.7861
No log 1.5745 148 0.7029 0.4583 0.7029 0.8384
No log 1.5957 150 0.6621 0.4585 0.6621 0.8137
No log 1.6170 152 0.4777 0.5244 0.4777 0.6911
No log 1.6383 154 0.3791 0.6595 0.3791 0.6157
No log 1.6596 156 0.3820 0.6775 0.3820 0.6180
No log 1.6809 158 0.3948 0.6775 0.3948 0.6284
No log 1.7021 160 0.4250 0.6125 0.4250 0.6519
No log 1.7234 162 0.5020 0.5437 0.5020 0.7085
No log 1.7447 164 0.4833 0.5835 0.4833 0.6952
No log 1.7660 166 0.4224 0.6192 0.4224 0.6499
No log 1.7872 168 0.4125 0.6347 0.4125 0.6423
No log 1.8085 170 0.4431 0.5998 0.4431 0.6657
No log 1.8298 172 0.4675 0.5717 0.4675 0.6837
No log 1.8511 174 0.5781 0.4960 0.5781 0.7603
No log 1.8723 176 0.6813 0.4511 0.6813 0.8254
No log 1.8936 178 0.6349 0.4880 0.6349 0.7968
No log 1.9149 180 0.6006 0.5233 0.6006 0.7750
No log 1.9362 182 0.5224 0.6040 0.5224 0.7228
No log 1.9574 184 0.5325 0.6257 0.5325 0.7298
No log 1.9787 186 0.4619 0.6302 0.4619 0.6796
No log 2.0 188 0.4503 0.6315 0.4503 0.6711
No log 2.0213 190 0.5117 0.6062 0.5117 0.7154
No log 2.0426 192 0.4414 0.6206 0.4414 0.6644
No log 2.0638 194 0.3722 0.6819 0.3722 0.6101
No log 2.0851 196 0.4930 0.5736 0.4930 0.7022
No log 2.1064 198 0.4580 0.5794 0.4580 0.6767
No log 2.1277 200 0.3627 0.6768 0.3627 0.6022
No log 2.1489 202 0.5227 0.5595 0.5227 0.7230
No log 2.1702 204 0.7287 0.4812 0.7287 0.8536
No log 2.1915 206 0.7065 0.4988 0.7065 0.8406
No log 2.2128 208 0.5782 0.5365 0.5782 0.7604
No log 2.2340 210 0.5758 0.5643 0.5758 0.7588
No log 2.2553 212 0.5744 0.5679 0.5744 0.7579
No log 2.2766 214 0.5348 0.5966 0.5348 0.7313
No log 2.2979 216 0.4977 0.6742 0.4977 0.7055
No log 2.3191 218 0.4896 0.6507 0.4896 0.6997
No log 2.3404 220 0.5154 0.6433 0.5154 0.7179
No log 2.3617 222 0.6889 0.5556 0.6889 0.8300
No log 2.3830 224 0.8044 0.4812 0.8044 0.8969
No log 2.4043 226 0.5725 0.5152 0.5725 0.7566
No log 2.4255 228 0.4491 0.5950 0.4491 0.6701
No log 2.4468 230 0.4798 0.5779 0.4798 0.6927
No log 2.4681 232 0.4933 0.5192 0.4933 0.7024
No log 2.4894 234 0.5377 0.5041 0.5377 0.7333
No log 2.5106 236 0.6701 0.4704 0.6701 0.8186
No log 2.5319 238 0.8833 0.4188 0.8833 0.9399
No log 2.5532 240 0.7746 0.4705 0.7746 0.8801
No log 2.5745 242 0.4825 0.6108 0.4825 0.6946
No log 2.5957 244 0.3994 0.6590 0.3994 0.6320
No log 2.6170 246 0.3889 0.6424 0.3889 0.6236
No log 2.6383 248 0.4917 0.5783 0.4917 0.7012
No log 2.6596 250 0.5771 0.5361 0.5771 0.7597
No log 2.6809 252 0.5453 0.5533 0.5453 0.7384
No log 2.7021 254 0.4995 0.5977 0.4995 0.7068
No log 2.7234 256 0.5162 0.6091 0.5162 0.7184
No log 2.7447 258 0.4977 0.5981 0.4977 0.7054
No log 2.7660 260 0.4149 0.6520 0.4149 0.6442
No log 2.7872 262 0.4129 0.6326 0.4129 0.6426
No log 2.8085 264 0.4302 0.6060 0.4302 0.6559
No log 2.8298 266 0.6247 0.4856 0.6247 0.7904
No log 2.8511 268 0.7140 0.4419 0.7140 0.8450
No log 2.8723 270 0.6641 0.4579 0.6641 0.8149
No log 2.8936 272 0.5411 0.5064 0.5411 0.7356
No log 2.9149 274 0.4313 0.5826 0.4313 0.6567
No log 2.9362 276 0.4257 0.5996 0.4257 0.6525
No log 2.9574 278 0.4016 0.6118 0.4016 0.6337
No log 2.9787 280 0.4714 0.5861 0.4714 0.6866
No log 3.0 282 0.6176 0.5005 0.6176 0.7859
No log 3.0213 284 0.6416 0.4673 0.6416 0.8010
No log 3.0426 286 0.5775 0.4966 0.5775 0.7599
No log 3.0638 288 0.5510 0.5647 0.5510 0.7423
No log 3.0851 290 0.4327 0.6274 0.4327 0.6578
No log 3.1064 292 0.4266 0.6463 0.4266 0.6531
No log 3.1277 294 0.4398 0.6412 0.4398 0.6632
No log 3.1489 296 0.6065 0.5876 0.6065 0.7788
No log 3.1702 298 0.6857 0.5333 0.6857 0.8281
No log 3.1915 300 0.5516 0.6002 0.5516 0.7427
No log 3.2128 302 0.4414 0.6594 0.4414 0.6644
No log 3.2340 304 0.4799 0.6004 0.4799 0.6927
No log 3.2553 306 0.4841 0.5617 0.4841 0.6957
No log 3.2766 308 0.4373 0.5795 0.4373 0.6613
No log 3.2979 310 0.4810 0.5586 0.4810 0.6936
No log 3.3191 312 0.4463 0.5790 0.4463 0.6681
No log 3.3404 314 0.4365 0.5835 0.4365 0.6607
No log 3.3617 316 0.4973 0.5784 0.4973 0.7052
No log 3.3830 318 0.4248 0.6185 0.4248 0.6518
No log 3.4043 320 0.4480 0.6247 0.4480 0.6694
No log 3.4255 322 0.5717 0.5872 0.5717 0.7561
No log 3.4468 324 0.6497 0.5552 0.6497 0.8060
No log 3.4681 326 0.4973 0.6581 0.4973 0.7052
No log 3.4894 328 0.4614 0.6413 0.4614 0.6792
No log 3.5106 330 0.4517 0.6235 0.4517 0.6721
No log 3.5319 332 0.4821 0.6276 0.4821 0.6943
No log 3.5532 334 0.7600 0.5046 0.7600 0.8718
No log 3.5745 336 0.8952 0.4338 0.8952 0.9462
No log 3.5957 338 0.6456 0.5407 0.6456 0.8035
No log 3.6170 340 0.4559 0.5763 0.4559 0.6752
No log 3.6383 342 0.4552 0.5718 0.4552 0.6747
No log 3.6596 344 0.5587 0.5544 0.5587 0.7475
No log 3.6809 346 0.8736 0.3948 0.8736 0.9347
No log 3.7021 348 0.9182 0.3913 0.9182 0.9582
No log 3.7234 350 0.7058 0.4015 0.7058 0.8401
No log 3.7447 352 0.4711 0.5278 0.4711 0.6863
No log 3.7660 354 0.4213 0.6470 0.4213 0.6491
No log 3.7872 356 0.4500 0.5697 0.4500 0.6708
No log 3.8085 358 0.4187 0.6261 0.4187 0.6471
No log 3.8298 360 0.5081 0.5356 0.5081 0.7128
No log 3.8511 362 0.5966 0.5208 0.5966 0.7724
No log 3.8723 364 0.5210 0.5622 0.5210 0.7218
No log 3.8936 366 0.4246 0.6279 0.4246 0.6516
No log 3.9149 368 0.4143 0.6357 0.4143 0.6437
No log 3.9362 370 0.4246 0.6496 0.4246 0.6516
No log 3.9574 372 0.5331 0.5969 0.5331 0.7301
No log 3.9787 374 0.6567 0.5503 0.6567 0.8104
No log 4.0 376 0.5523 0.5904 0.5523 0.7432
No log 4.0213 378 0.5043 0.5979 0.5043 0.7102
No log 4.0426 380 0.4688 0.6092 0.4688 0.6847
No log 4.0638 382 0.4665 0.6092 0.4665 0.6830
No log 4.0851 384 0.4614 0.6212 0.4614 0.6792
No log 4.1064 386 0.4460 0.6129 0.4460 0.6678
No log 4.1277 388 0.5354 0.6041 0.5354 0.7317
No log 4.1489 390 0.7533 0.5257 0.7533 0.8679
No log 4.1702 392 0.6852 0.5412 0.6852 0.8278
No log 4.1915 394 0.5025 0.6133 0.5025 0.7089
No log 4.2128 396 0.4772 0.6045 0.4772 0.6908
No log 4.2340 398 0.4753 0.5917 0.4753 0.6894
No log 4.2553 400 0.4823 0.6163 0.4823 0.6945
No log 4.2766 402 0.5673 0.6159 0.5673 0.7532
No log 4.2979 404 0.6892 0.5960 0.6892 0.8302
No log 4.3191 406 0.6687 0.5977 0.6687 0.8177
No log 4.3404 408 0.6032 0.5830 0.6032 0.7767
No log 4.3617 410 0.5464 0.5984 0.5464 0.7392
No log 4.3830 412 0.5776 0.5540 0.5776 0.7600
No log 4.4043 414 0.6166 0.5130 0.6166 0.7852
No log 4.4255 416 0.6191 0.5047 0.6191 0.7868
No log 4.4468 418 0.5450 0.5318 0.5450 0.7382
No log 4.4681 420 0.5421 0.5356 0.5421 0.7363
No log 4.4894 422 0.4486 0.5492 0.4486 0.6698
No log 4.5106 424 0.4458 0.6004 0.4458 0.6677
No log 4.5319 426 0.5333 0.5666 0.5333 0.7303
No log 4.5532 428 0.5325 0.5844 0.5325 0.7297
No log 4.5745 430 0.4087 0.6809 0.4087 0.6393
No log 4.5957 432 0.3983 0.6722 0.3983 0.6311
No log 4.6170 434 0.4683 0.5863 0.4683 0.6843
No log 4.6383 436 0.6688 0.5605 0.6688 0.8178
No log 4.6596 438 0.6600 0.5609 0.6600 0.8124
No log 4.6809 440 0.4877 0.5916 0.4877 0.6984
No log 4.7021 442 0.4211 0.5980 0.4211 0.6489
No log 4.7234 444 0.4257 0.6015 0.4257 0.6524
No log 4.7447 446 0.5320 0.5658 0.5320 0.7294
No log 4.7660 448 0.7042 0.5243 0.7042 0.8391
No log 4.7872 450 0.7423 0.5195 0.7423 0.8615
No log 4.8085 452 0.5433 0.5966 0.5433 0.7371
No log 4.8298 454 0.4548 0.6130 0.4548 0.6744
No log 4.8511 456 0.4497 0.6147 0.4497 0.6706
No log 4.8723 458 0.4912 0.5299 0.4912 0.7009
No log 4.8936 460 0.7400 0.4279 0.7400 0.8602
No log 4.9149 462 1.0617 0.3786 1.0617 1.0304
No log 4.9362 464 1.0010 0.4013 1.0010 1.0005
No log 4.9574 466 0.6774 0.4734 0.6774 0.8230
No log 4.9787 468 0.4630 0.6162 0.4630 0.6805
No log 5.0 470 0.4588 0.6261 0.4588 0.6774
No log 5.0213 472 0.4921 0.6324 0.4921 0.7015
No log 5.0426 474 0.5531 0.5887 0.5531 0.7437
No log 5.0638 476 0.5163 0.6018 0.5163 0.7185
No log 5.0851 478 0.4896 0.5860 0.4896 0.6997
No log 5.1064 480 0.5185 0.5351 0.5185 0.7201
No log 5.1277 482 0.4562 0.5752 0.4562 0.6754
No log 5.1489 484 0.4147 0.5847 0.4147 0.6440
No log 5.1702 486 0.4666 0.5825 0.4666 0.6831
No log 5.1915 488 0.4695 0.6160 0.4695 0.6852
No log 5.2128 490 0.4102 0.6474 0.4102 0.6404
No log 5.2340 492 0.4072 0.6437 0.4072 0.6381
No log 5.2553 494 0.4182 0.6291 0.4182 0.6467
No log 5.2766 496 0.4877 0.5953 0.4877 0.6984
No log 5.2979 498 0.4833 0.5887 0.4833 0.6952
0.4408 5.3191 500 0.4120 0.6437 0.4120 0.6418
0.4408 5.3404 502 0.4248 0.6129 0.4248 0.6517
0.4408 5.3617 504 0.4126 0.6574 0.4126 0.6424
0.4408 5.3830 506 0.5421 0.5807 0.5421 0.7363
0.4408 5.4043 508 0.5987 0.5667 0.5987 0.7737
0.4408 5.4255 510 0.5231 0.6083 0.5231 0.7232
0.4408 5.4468 512 0.4252 0.6705 0.4252 0.6521
0.4408 5.4681 514 0.4296 0.6597 0.4296 0.6554
0.4408 5.4894 516 0.4762 0.6551 0.4762 0.6900
0.4408 5.5106 518 0.7330 0.5582 0.7330 0.8561
0.4408 5.5319 520 0.7775 0.5370 0.7775 0.8818
0.4408 5.5532 522 0.5583 0.5988 0.5583 0.7472
0.4408 5.5745 524 0.3978 0.6511 0.3978 0.6307
0.4408 5.5957 526 0.3919 0.6545 0.3919 0.6260
0.4408 5.6170 528 0.4560 0.6055 0.4560 0.6753
0.4408 5.6383 530 0.5450 0.5794 0.5450 0.7382
0.4408 5.6596 532 0.5264 0.6002 0.5264 0.7255
0.4408 5.6809 534 0.4520 0.6439 0.4520 0.6723
0.4408 5.7021 536 0.4818 0.6275 0.4818 0.6941
0.4408 5.7234 538 0.4902 0.6435 0.4902 0.7001
0.4408 5.7447 540 0.6058 0.5956 0.6058 0.7783
0.4408 5.7660 542 0.6694 0.5677 0.6694 0.8182
0.4408 5.7872 544 0.5455 0.5691 0.5455 0.7386

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1