MayBashendy's picture
End of training
92fc171 verified
metadata
library_name: transformers
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask2_style
    results: []

Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask2_style

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: 0.5070
  • Qwk: 0.5876
  • Mse: 0.5070
  • Rmse: 0.7121

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 3.7204 0.0266 3.7204 1.9288
No log 0.0426 4 2.7978 0.0386 2.7978 1.6727
No log 0.0638 6 1.1891 0.1293 1.1891 1.0905
No log 0.0851 8 0.6163 0.3347 0.6163 0.7851
No log 0.1064 10 0.7672 0.1045 0.7672 0.8759
No log 0.1277 12 0.7503 0.1488 0.7503 0.8662
No log 0.1489 14 0.6529 0.2807 0.6529 0.8080
No log 0.1702 16 0.6211 0.4197 0.6211 0.7881
No log 0.1915 18 0.5747 0.4828 0.5747 0.7581
No log 0.2128 20 0.5579 0.4842 0.5579 0.7470
No log 0.2340 22 0.6349 0.4219 0.6349 0.7968
No log 0.2553 24 0.6046 0.3709 0.6046 0.7775
No log 0.2766 26 0.5573 0.4521 0.5573 0.7465
No log 0.2979 28 0.4811 0.5304 0.4811 0.6936
No log 0.3191 30 0.4795 0.5014 0.4795 0.6924
No log 0.3404 32 0.4736 0.5088 0.4736 0.6882
No log 0.3617 34 0.4783 0.5030 0.4783 0.6916
No log 0.3830 36 0.4733 0.4722 0.4733 0.6879
No log 0.4043 38 0.5547 0.3726 0.5547 0.7448
No log 0.4255 40 0.6035 0.3099 0.6035 0.7768
No log 0.4468 42 0.7365 0.1975 0.7365 0.8582
No log 0.4681 44 0.7888 0.1334 0.7888 0.8881
No log 0.4894 46 0.7687 0.1519 0.7687 0.8768
No log 0.5106 48 0.6884 0.2542 0.6884 0.8297
No log 0.5319 50 0.5303 0.3747 0.5303 0.7282
No log 0.5532 52 0.4630 0.5222 0.4630 0.6804
No log 0.5745 54 0.4749 0.5715 0.4749 0.6891
No log 0.5957 56 0.4511 0.5760 0.4511 0.6717
No log 0.6170 58 0.5164 0.5367 0.5164 0.7186
No log 0.6383 60 0.7207 0.1337 0.7207 0.8490
No log 0.6596 62 0.7457 0.0698 0.7457 0.8635
No log 0.6809 64 0.5740 0.3800 0.5740 0.7576
No log 0.7021 66 0.4494 0.5451 0.4494 0.6704
No log 0.7234 68 0.4235 0.5805 0.4235 0.6508
No log 0.7447 70 0.4372 0.5801 0.4372 0.6612
No log 0.7660 72 0.4908 0.5666 0.4908 0.7006
No log 0.7872 74 0.5745 0.5636 0.5745 0.7579
No log 0.8085 76 0.7250 0.4962 0.7250 0.8515
No log 0.8298 78 0.7346 0.5022 0.7346 0.8571
No log 0.8511 80 0.5671 0.5375 0.5671 0.7530
No log 0.8723 82 0.4204 0.6118 0.4204 0.6484
No log 0.8936 84 0.4118 0.6546 0.4118 0.6417
No log 0.9149 86 0.4549 0.6058 0.4549 0.6745
No log 0.9362 88 0.5741 0.5467 0.5741 0.7577
No log 0.9574 90 0.6135 0.5415 0.6135 0.7833
No log 0.9787 92 0.5457 0.5764 0.5457 0.7387
No log 1.0 94 0.4709 0.6539 0.4709 0.6862
No log 1.0213 96 0.4406 0.6480 0.4406 0.6638
No log 1.0426 98 0.4732 0.6548 0.4732 0.6879
No log 1.0638 100 0.5617 0.5800 0.5617 0.7495
No log 1.0851 102 0.6388 0.5480 0.6388 0.7993
No log 1.1064 104 0.7549 0.4955 0.7549 0.8689
No log 1.1277 106 0.8081 0.4800 0.8081 0.8989
No log 1.1489 108 0.7216 0.4676 0.7216 0.8495
No log 1.1702 110 0.5091 0.5241 0.5091 0.7135
No log 1.1915 112 0.3850 0.6229 0.3850 0.6205
No log 1.2128 114 0.3878 0.6374 0.3878 0.6227
No log 1.2340 116 0.4004 0.5822 0.4004 0.6327
No log 1.2553 118 0.4842 0.4500 0.4842 0.6959
No log 1.2766 120 0.6117 0.3872 0.6117 0.7821
No log 1.2979 122 0.6379 0.3872 0.6379 0.7987
No log 1.3191 124 0.5915 0.4408 0.5915 0.7691
No log 1.3404 126 0.4770 0.5779 0.4770 0.6907
No log 1.3617 128 0.4692 0.6156 0.4692 0.6850
No log 1.3830 130 0.6005 0.5766 0.6005 0.7749
No log 1.4043 132 0.4989 0.6088 0.4989 0.7063
No log 1.4255 134 0.4134 0.6009 0.4134 0.6429
No log 1.4468 136 0.4951 0.4797 0.4951 0.7036
No log 1.4681 138 0.5664 0.4048 0.5664 0.7526
No log 1.4894 140 0.5489 0.4106 0.5489 0.7409
No log 1.5106 142 0.4772 0.5133 0.4772 0.6908
No log 1.5319 144 0.4210 0.6038 0.4210 0.6488
No log 1.5532 146 0.4301 0.6022 0.4301 0.6558
No log 1.5745 148 0.4520 0.6337 0.4520 0.6723
No log 1.5957 150 0.5077 0.6346 0.5077 0.7125
No log 1.6170 152 0.5407 0.6305 0.5407 0.7353
No log 1.6383 154 0.5495 0.6117 0.5495 0.7413
No log 1.6596 156 0.4711 0.5976 0.4711 0.6863
No log 1.6809 158 0.4052 0.5863 0.4052 0.6365
No log 1.7021 160 0.3964 0.5967 0.3964 0.6296
No log 1.7234 162 0.4397 0.6067 0.4397 0.6631
No log 1.7447 164 0.4495 0.6002 0.4495 0.6705
No log 1.7660 166 0.4127 0.6097 0.4127 0.6424
No log 1.7872 168 0.4227 0.6381 0.4227 0.6502
No log 1.8085 170 0.4330 0.6120 0.4330 0.6580
No log 1.8298 172 0.4648 0.6096 0.4648 0.6817
No log 1.8511 174 0.6112 0.5718 0.6112 0.7818
No log 1.8723 176 0.7205 0.5159 0.7205 0.8488
No log 1.8936 178 0.8977 0.4292 0.8977 0.9475
No log 1.9149 180 0.9416 0.4144 0.9416 0.9704
No log 1.9362 182 0.8258 0.4938 0.8258 0.9088
No log 1.9574 184 0.6293 0.5676 0.6293 0.7933
No log 1.9787 186 0.4060 0.6315 0.4060 0.6372
No log 2.0 188 0.3900 0.6812 0.3900 0.6245
No log 2.0213 190 0.3909 0.6389 0.3909 0.6252
No log 2.0426 192 0.5262 0.5417 0.5262 0.7254
No log 2.0638 194 0.4990 0.5546 0.4990 0.7064
No log 2.0851 196 0.4023 0.5996 0.4023 0.6343
No log 2.1064 198 0.3880 0.6344 0.3880 0.6229
No log 2.1277 200 0.3915 0.6028 0.3915 0.6257
No log 2.1489 202 0.4802 0.5639 0.4802 0.6930
No log 2.1702 204 0.5257 0.5819 0.5257 0.7251
No log 2.1915 206 0.4264 0.5904 0.4264 0.6530
No log 2.2128 208 0.4337 0.6301 0.4337 0.6586
No log 2.2340 210 0.6026 0.5633 0.6026 0.7763
No log 2.2553 212 0.8583 0.4885 0.8583 0.9264
No log 2.2766 214 0.8020 0.5266 0.8020 0.8955
No log 2.2979 216 0.5803 0.6053 0.5803 0.7618
No log 2.3191 218 0.4590 0.6534 0.4590 0.6775
No log 2.3404 220 0.4656 0.6592 0.4656 0.6823
No log 2.3617 222 0.5785 0.5673 0.5785 0.7606
No log 2.3830 224 0.6688 0.4474 0.6688 0.8178
No log 2.4043 226 0.6556 0.4453 0.6556 0.8097
No log 2.4255 228 0.5727 0.4596 0.5727 0.7568
No log 2.4468 230 0.4235 0.5907 0.4235 0.6508
No log 2.4681 232 0.4018 0.6144 0.4018 0.6339
No log 2.4894 234 0.4174 0.6132 0.4174 0.6461
No log 2.5106 236 0.3963 0.6664 0.3963 0.6295
No log 2.5319 238 0.5067 0.6360 0.5067 0.7119
No log 2.5532 240 0.6720 0.5078 0.6720 0.8198
No log 2.5745 242 0.7034 0.5072 0.7034 0.8387
No log 2.5957 244 0.5401 0.5908 0.5401 0.7349
No log 2.6170 246 0.3934 0.6430 0.3934 0.6272
No log 2.6383 248 0.3923 0.6427 0.3923 0.6264
No log 2.6596 250 0.4575 0.6287 0.4575 0.6764
No log 2.6809 252 0.4848 0.6046 0.4848 0.6963
No log 2.7021 254 0.5784 0.6014 0.5784 0.7605
No log 2.7234 256 0.6490 0.5743 0.6490 0.8056
No log 2.7447 258 0.7010 0.5466 0.7010 0.8372
No log 2.7660 260 0.6070 0.5923 0.6070 0.7791
No log 2.7872 262 0.4685 0.6435 0.4685 0.6845
No log 2.8085 264 0.4882 0.6391 0.4882 0.6987
No log 2.8298 266 0.6881 0.5382 0.6881 0.8295
No log 2.8511 268 0.7501 0.5211 0.7501 0.8661
No log 2.8723 270 0.5829 0.5716 0.5829 0.7635
No log 2.8936 272 0.3984 0.6438 0.3984 0.6312
No log 2.9149 274 0.3876 0.6469 0.3876 0.6226
No log 2.9362 276 0.3767 0.6742 0.3767 0.6137
No log 2.9574 278 0.4345 0.6367 0.4345 0.6591
No log 2.9787 280 0.7209 0.4572 0.7209 0.8491
No log 3.0 282 0.9757 0.3512 0.9757 0.9878
No log 3.0213 284 0.9757 0.3336 0.9757 0.9878
No log 3.0426 286 0.8074 0.3235 0.8074 0.8985
No log 3.0638 288 0.6072 0.4569 0.6072 0.7793
No log 3.0851 290 0.4221 0.5614 0.4221 0.6497
No log 3.1064 292 0.3809 0.6887 0.3809 0.6172
No log 3.1277 294 0.4099 0.6366 0.4099 0.6403
No log 3.1489 296 0.5706 0.5777 0.5706 0.7554
No log 3.1702 298 0.6450 0.5658 0.6450 0.8031
No log 3.1915 300 0.6043 0.5731 0.6043 0.7774
No log 3.2128 302 0.4893 0.6319 0.4893 0.6995
No log 3.2340 304 0.5062 0.6347 0.5062 0.7115
No log 3.2553 306 0.5452 0.6328 0.5452 0.7384
No log 3.2766 308 0.5000 0.6523 0.5000 0.7071
No log 3.2979 310 0.4749 0.6185 0.4749 0.6891
No log 3.3191 312 0.4188 0.6313 0.4188 0.6472
No log 3.3404 314 0.4317 0.6197 0.4317 0.6570
No log 3.3617 316 0.5480 0.5608 0.5480 0.7402
No log 3.3830 318 0.5784 0.5679 0.5784 0.7605
No log 3.4043 320 0.5196 0.6015 0.5196 0.7209
No log 3.4255 322 0.5270 0.6028 0.5270 0.7259
No log 3.4468 324 0.5854 0.5824 0.5854 0.7651
No log 3.4681 326 0.5958 0.5722 0.5958 0.7719
No log 3.4894 328 0.6262 0.5791 0.6262 0.7913
No log 3.5106 330 0.5834 0.5904 0.5834 0.7638
No log 3.5319 332 0.4924 0.5941 0.4924 0.7017
No log 3.5532 334 0.4483 0.6107 0.4483 0.6696
No log 3.5745 336 0.4482 0.6009 0.4482 0.6695
No log 3.5957 338 0.4460 0.5957 0.4460 0.6678
No log 3.6170 340 0.4058 0.6208 0.4058 0.6370
No log 3.6383 342 0.4136 0.6332 0.4136 0.6432
No log 3.6596 344 0.4863 0.5878 0.4863 0.6974
No log 3.6809 346 0.9114 0.4930 0.9114 0.9547
No log 3.7021 348 1.1743 0.4017 1.1743 1.0837
No log 3.7234 350 0.9683 0.4817 0.9683 0.9840
No log 3.7447 352 0.5474 0.6104 0.5474 0.7399
No log 3.7660 354 0.4390 0.6722 0.4390 0.6626
No log 3.7872 356 0.4385 0.6759 0.4385 0.6622
No log 3.8085 358 0.5006 0.6037 0.5006 0.7075
No log 3.8298 360 0.6809 0.5460 0.6809 0.8252
No log 3.8511 362 0.6863 0.5423 0.6863 0.8284
No log 3.8723 364 0.5955 0.5838 0.5955 0.7717
No log 3.8936 366 0.5050 0.6169 0.5050 0.7106
No log 3.9149 368 0.5167 0.5967 0.5167 0.7188
No log 3.9362 370 0.4835 0.6109 0.4835 0.6953
No log 3.9574 372 0.6771 0.5413 0.6771 0.8229
No log 3.9787 374 1.0150 0.4424 1.0150 1.0075
No log 4.0 376 1.1965 0.3479 1.1965 1.0939
No log 4.0213 378 1.1475 0.3705 1.1475 1.0712
No log 4.0426 380 0.7832 0.5001 0.7832 0.8850
No log 4.0638 382 0.4177 0.6508 0.4177 0.6463
No log 4.0851 384 0.4121 0.6304 0.4121 0.6420
No log 4.1064 386 0.3978 0.6453 0.3978 0.6307
No log 4.1277 388 0.4994 0.5804 0.4994 0.7067
No log 4.1489 390 0.6198 0.5233 0.6198 0.7873
No log 4.1702 392 0.7567 0.4539 0.7567 0.8699
No log 4.1915 394 0.6999 0.4617 0.6999 0.8366
No log 4.2128 396 0.5602 0.5433 0.5602 0.7485
No log 4.2340 398 0.4428 0.6687 0.4428 0.6654
No log 4.2553 400 0.4561 0.6579 0.4561 0.6754
No log 4.2766 402 0.6089 0.5550 0.6089 0.7803
No log 4.2979 404 0.8888 0.4757 0.8888 0.9427
No log 4.3191 406 0.8513 0.4902 0.8513 0.9227
No log 4.3404 408 0.5936 0.5876 0.5936 0.7705
No log 4.3617 410 0.5613 0.5794 0.5613 0.7492
No log 4.3830 412 0.5650 0.5845 0.5650 0.7516
No log 4.4043 414 0.5855 0.5845 0.5855 0.7652
No log 4.4255 416 0.6368 0.5635 0.6368 0.7980
No log 4.4468 418 0.6365 0.5506 0.6365 0.7978
No log 4.4681 420 0.5937 0.5576 0.5937 0.7705
No log 4.4894 422 0.5550 0.5844 0.5550 0.7450
No log 4.5106 424 0.5010 0.5932 0.5010 0.7078
No log 4.5319 426 0.4179 0.6356 0.4179 0.6465
No log 4.5532 428 0.4123 0.6324 0.4123 0.6421
No log 4.5745 430 0.3973 0.6516 0.3973 0.6303
No log 4.5957 432 0.3915 0.6600 0.3915 0.6257
No log 4.6170 434 0.4191 0.6556 0.4191 0.6474
No log 4.6383 436 0.5400 0.6279 0.5400 0.7349
No log 4.6596 438 0.6609 0.5741 0.6609 0.8129
No log 4.6809 440 0.5804 0.5946 0.5804 0.7619
No log 4.7021 442 0.5201 0.6101 0.5201 0.7212
No log 4.7234 444 0.4941 0.6107 0.4941 0.7029
No log 4.7447 446 0.4553 0.6128 0.4553 0.6748
No log 4.7660 448 0.4660 0.6108 0.4660 0.6826
No log 4.7872 450 0.6607 0.5189 0.6607 0.8128
No log 4.8085 452 0.7207 0.4971 0.7207 0.8490
No log 4.8298 454 0.5490 0.5595 0.5490 0.7409
No log 4.8511 456 0.4781 0.6159 0.4781 0.6914
No log 4.8723 458 0.5468 0.5884 0.5468 0.7395
No log 4.8936 460 0.7172 0.5488 0.7172 0.8469
No log 4.9149 462 0.9136 0.5218 0.9136 0.9558
No log 4.9362 464 0.7909 0.5461 0.7909 0.8893
No log 4.9574 466 0.5527 0.6065 0.5527 0.7435
No log 4.9787 468 0.4749 0.6783 0.4749 0.6891
No log 5.0 470 0.4396 0.6697 0.4396 0.6630
No log 5.0213 472 0.4674 0.6136 0.4674 0.6837
No log 5.0426 474 0.5394 0.5657 0.5394 0.7344
No log 5.0638 476 0.5719 0.5637 0.5719 0.7562
No log 5.0851 478 0.6999 0.4875 0.6999 0.8366
No log 5.1064 480 0.7262 0.4688 0.7262 0.8522
No log 5.1277 482 0.5434 0.5454 0.5434 0.7372
No log 5.1489 484 0.4380 0.5854 0.4380 0.6618
No log 5.1702 486 0.4557 0.5793 0.4557 0.6751
No log 5.1915 488 0.4962 0.5939 0.4962 0.7044
No log 5.2128 490 0.6189 0.5817 0.6189 0.7867
No log 5.2340 492 0.7316 0.5527 0.7316 0.8553
No log 5.2553 494 0.5721 0.5868 0.5721 0.7564
No log 5.2766 496 0.4371 0.6044 0.4371 0.6611
No log 5.2979 498 0.4523 0.6291 0.4523 0.6726
0.4506 5.3191 500 0.6134 0.6164 0.6134 0.7832
0.4506 5.3404 502 0.8066 0.5371 0.8066 0.8981
0.4506 5.3617 504 0.8625 0.5321 0.8625 0.9287
0.4506 5.3830 506 0.6721 0.5875 0.6721 0.8198
0.4506 5.4043 508 0.4693 0.6603 0.4693 0.6850
0.4506 5.4255 510 0.4408 0.6665 0.4408 0.6639
0.4506 5.4468 512 0.4699 0.6469 0.4699 0.6855
0.4506 5.4681 514 0.7045 0.5493 0.7045 0.8394
0.4506 5.4894 516 1.0678 0.4213 1.0678 1.0333
0.4506 5.5106 518 1.0414 0.4122 1.0414 1.0205
0.4506 5.5319 520 0.7861 0.4759 0.7861 0.8866
0.4506 5.5532 522 0.5070 0.5876 0.5070 0.7121

Framework versions

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