MayBashendy's picture
End of training
261d05d verified
metadata
library_name: transformers
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask3_grammar
    results: []

Arabic_CrossPrompt_FineTuningAraBERT_noAug_TestTask3_grammar

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: 0.5050
  • Qwk: 0.6388
  • Mse: 0.5050
  • Rmse: 0.7106

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 0.0194 2 4.4958 -0.0054 4.4958 2.1203
No log 0.0388 4 2.8399 0.0632 2.8400 1.6852
No log 0.0583 6 2.0492 0.0432 2.0492 1.4315
No log 0.0777 8 1.0146 0.1781 1.0146 1.0073
No log 0.0971 10 0.8743 0.0522 0.8743 0.9350
No log 0.1165 12 0.9642 0.0731 0.9642 0.9819
No log 0.1359 14 0.9471 0.1030 0.9471 0.9732
No log 0.1553 16 0.8465 0.0674 0.8465 0.9201
No log 0.1748 18 0.8455 0.2360 0.8455 0.9195
No log 0.1942 20 0.8698 0.1910 0.8698 0.9326
No log 0.2136 22 0.7840 0.3570 0.7840 0.8855
No log 0.2330 24 0.6955 0.3456 0.6955 0.8340
No log 0.2524 26 0.6584 0.3346 0.6584 0.8114
No log 0.2718 28 0.6445 0.3874 0.6445 0.8028
No log 0.2913 30 0.7288 0.3786 0.7288 0.8537
No log 0.3107 32 0.6198 0.4433 0.6198 0.7873
No log 0.3301 34 0.6510 0.3971 0.6510 0.8068
No log 0.3495 36 0.7866 0.2753 0.7866 0.8869
No log 0.3689 38 0.7707 0.2445 0.7707 0.8779
No log 0.3883 40 0.7219 0.2483 0.7219 0.8496
No log 0.4078 42 0.6840 0.2715 0.6840 0.8270
No log 0.4272 44 0.6243 0.3506 0.6243 0.7901
No log 0.4466 46 0.6064 0.4378 0.6064 0.7787
No log 0.4660 48 0.7324 0.3871 0.7324 0.8558
No log 0.4854 50 0.7590 0.4165 0.7590 0.8712
No log 0.5049 52 0.6698 0.4281 0.6698 0.8184
No log 0.5243 54 0.5848 0.5165 0.5848 0.7647
No log 0.5437 56 0.5371 0.5142 0.5371 0.7329
No log 0.5631 58 0.5849 0.5200 0.5849 0.7648
No log 0.5825 60 0.6442 0.4371 0.6442 0.8026
No log 0.6019 62 0.9557 0.4008 0.9557 0.9776
No log 0.6214 64 1.0889 0.2727 1.0889 1.0435
No log 0.6408 66 0.6953 0.4244 0.6953 0.8338
No log 0.6602 68 0.6924 0.4619 0.6924 0.8321
No log 0.6796 70 0.6382 0.5098 0.6382 0.7989
No log 0.6990 72 0.5425 0.4735 0.5425 0.7365
No log 0.7184 74 0.5192 0.4607 0.5192 0.7205
No log 0.7379 76 0.5212 0.4788 0.5212 0.7220
No log 0.7573 78 0.5332 0.5214 0.5332 0.7302
No log 0.7767 80 0.5601 0.5618 0.5601 0.7484
No log 0.7961 82 0.5769 0.5551 0.5769 0.7596
No log 0.8155 84 0.5894 0.5560 0.5894 0.7677
No log 0.8350 86 0.5840 0.5721 0.5840 0.7642
No log 0.8544 88 0.5514 0.5598 0.5514 0.7426
No log 0.8738 90 0.4947 0.5869 0.4947 0.7033
No log 0.8932 92 0.5546 0.5485 0.5546 0.7447
No log 0.9126 94 0.7507 0.5026 0.7507 0.8664
No log 0.9320 96 0.7871 0.4804 0.7871 0.8872
No log 0.9515 98 0.6626 0.5148 0.6626 0.8140
No log 0.9709 100 0.5060 0.5515 0.5060 0.7113
No log 0.9903 102 0.4975 0.5359 0.4975 0.7053
No log 1.0097 104 0.5151 0.5382 0.5151 0.7177
No log 1.0291 106 0.5037 0.5549 0.5037 0.7097
No log 1.0485 108 0.4868 0.5352 0.4868 0.6977
No log 1.0680 110 0.5307 0.5106 0.5307 0.7285
No log 1.0874 112 0.6088 0.4733 0.6088 0.7802
No log 1.1068 114 0.6111 0.4514 0.6111 0.7817
No log 1.1262 116 0.5144 0.5564 0.5144 0.7172
No log 1.1456 118 0.5435 0.6125 0.5435 0.7372
No log 1.1650 120 0.5623 0.6177 0.5623 0.7499
No log 1.1845 122 0.5214 0.6299 0.5214 0.7221
No log 1.2039 124 0.4744 0.6525 0.4744 0.6888
No log 1.2233 126 0.5206 0.5802 0.5206 0.7215
No log 1.2427 128 0.5934 0.5675 0.5934 0.7704
No log 1.2621 130 0.5992 0.5547 0.5992 0.7741
No log 1.2816 132 0.5674 0.5467 0.5674 0.7533
No log 1.3010 134 0.5073 0.5152 0.5073 0.7122
No log 1.3204 136 0.4940 0.4931 0.4940 0.7028
No log 1.3398 138 0.4989 0.4847 0.4989 0.7063
No log 1.3592 140 0.4956 0.4994 0.4956 0.7040
No log 1.3786 142 0.4885 0.5125 0.4885 0.6989
No log 1.3981 144 0.5323 0.5411 0.5323 0.7296
No log 1.4175 146 0.5005 0.5602 0.5005 0.7075
No log 1.4369 148 0.5627 0.5741 0.5627 0.7502
No log 1.4563 150 0.5728 0.5855 0.5728 0.7568
No log 1.4757 152 0.4657 0.5763 0.4657 0.6825
No log 1.4951 154 0.5116 0.5453 0.5116 0.7152
No log 1.5146 156 0.5325 0.5218 0.5325 0.7297
No log 1.5340 158 0.4948 0.5313 0.4948 0.7034
No log 1.5534 160 0.4579 0.5544 0.4579 0.6767
No log 1.5728 162 0.4733 0.5585 0.4733 0.6880
No log 1.5922 164 0.4838 0.5822 0.4838 0.6956
No log 1.6117 166 0.5149 0.4992 0.5149 0.7176
No log 1.6311 168 0.5182 0.4799 0.5182 0.7198
No log 1.6505 170 0.5268 0.4936 0.5268 0.7258
No log 1.6699 172 0.5511 0.4595 0.5511 0.7424
No log 1.6893 174 0.5443 0.5198 0.5443 0.7378
No log 1.7087 176 0.4901 0.5492 0.4901 0.7000
No log 1.7282 178 0.4410 0.6320 0.4410 0.6641
No log 1.7476 180 0.4296 0.6773 0.4296 0.6554
No log 1.7670 182 0.4177 0.6817 0.4177 0.6463
No log 1.7864 184 0.4209 0.6689 0.4209 0.6488
No log 1.8058 186 0.4218 0.6183 0.4218 0.6495
No log 1.8252 188 0.4300 0.5992 0.4300 0.6557
No log 1.8447 190 0.4309 0.6071 0.4309 0.6564
No log 1.8641 192 0.4526 0.6081 0.4526 0.6728
No log 1.8835 194 0.5053 0.5784 0.5053 0.7108
No log 1.9029 196 0.5081 0.5747 0.5081 0.7128
No log 1.9223 198 0.4881 0.5703 0.4881 0.6986
No log 1.9417 200 0.4569 0.6133 0.4569 0.6759
No log 1.9612 202 0.4319 0.6142 0.4319 0.6572
No log 1.9806 204 0.6164 0.5722 0.6164 0.7851
No log 2.0 206 0.8501 0.4543 0.8501 0.9220
No log 2.0194 208 0.7737 0.4693 0.7737 0.8796
No log 2.0388 210 0.5631 0.5789 0.5631 0.7504
No log 2.0583 212 0.4497 0.5340 0.4497 0.6706
No log 2.0777 214 0.5325 0.5330 0.5325 0.7297
No log 2.0971 216 0.7568 0.5191 0.7568 0.8700
No log 2.1165 218 0.8074 0.4815 0.8074 0.8986
No log 2.1359 220 0.6871 0.5016 0.6871 0.8289
No log 2.1553 222 0.5349 0.4322 0.5349 0.7314
No log 2.1748 224 0.4901 0.5621 0.4901 0.7001
No log 2.1942 226 0.5555 0.5975 0.5555 0.7453
No log 2.2136 228 0.5969 0.6104 0.5969 0.7726
No log 2.2330 230 0.5575 0.6056 0.5575 0.7467
No log 2.2524 232 0.4848 0.6122 0.4848 0.6963
No log 2.2718 234 0.4750 0.6721 0.4750 0.6892
No log 2.2913 236 0.5288 0.6571 0.5288 0.7272
No log 2.3107 238 0.5059 0.6639 0.5059 0.7113
No log 2.3301 240 0.4517 0.6786 0.4517 0.6721
No log 2.3495 242 0.4373 0.6496 0.4373 0.6613
No log 2.3689 244 0.4381 0.6123 0.4381 0.6619
No log 2.3883 246 0.4418 0.6006 0.4418 0.6647
No log 2.4078 248 0.4434 0.6168 0.4434 0.6659
No log 2.4272 250 0.4445 0.6102 0.4445 0.6667
No log 2.4466 252 0.4774 0.6068 0.4774 0.6909
No log 2.4660 254 0.5018 0.6286 0.5018 0.7084
No log 2.4854 256 0.4570 0.6162 0.4570 0.6760
No log 2.5049 258 0.4713 0.6317 0.4713 0.6865
No log 2.5243 260 0.5186 0.6254 0.5186 0.7201
No log 2.5437 262 0.4872 0.6072 0.4872 0.6980
No log 2.5631 264 0.4487 0.5832 0.4487 0.6699
No log 2.5825 266 0.4877 0.5988 0.4877 0.6984
No log 2.6019 268 0.4826 0.6080 0.4826 0.6947
No log 2.6214 270 0.4545 0.6138 0.4545 0.6741
No log 2.6408 272 0.4594 0.6375 0.4594 0.6778
No log 2.6602 274 0.5037 0.6361 0.5037 0.7098
No log 2.6796 276 0.5077 0.6251 0.5077 0.7126
No log 2.6990 278 0.5416 0.5944 0.5416 0.7359
No log 2.7184 280 0.5526 0.6020 0.5526 0.7433
No log 2.7379 282 0.6806 0.5587 0.6806 0.8250
No log 2.7573 284 0.8355 0.4975 0.8355 0.9141
No log 2.7767 286 0.6697 0.5602 0.6697 0.8183
No log 2.7961 288 0.4729 0.5790 0.4729 0.6877
No log 2.8155 290 0.4770 0.5841 0.4770 0.6906
No log 2.8350 292 0.4682 0.5956 0.4682 0.6842
No log 2.8544 294 0.4358 0.6029 0.4358 0.6602
No log 2.8738 296 0.4725 0.6537 0.4725 0.6874
No log 2.8932 298 0.5135 0.6362 0.5135 0.7166
No log 2.9126 300 0.6390 0.5997 0.6390 0.7994
No log 2.9320 302 0.6028 0.5982 0.6028 0.7764
No log 2.9515 304 0.5170 0.6442 0.5170 0.7190
No log 2.9709 306 0.4497 0.6797 0.4497 0.6706
No log 2.9903 308 0.4756 0.6758 0.4756 0.6896
No log 3.0097 310 0.4850 0.6734 0.4850 0.6964
No log 3.0291 312 0.4332 0.7015 0.4332 0.6581
No log 3.0485 314 0.4305 0.6791 0.4305 0.6562
No log 3.0680 316 0.4532 0.6397 0.4532 0.6732
No log 3.0874 318 0.5196 0.6052 0.5196 0.7209
No log 3.1068 320 0.5167 0.6350 0.5167 0.7188
No log 3.1262 322 0.4659 0.6638 0.4659 0.6825
No log 3.1456 324 0.5404 0.6822 0.5404 0.7351
No log 3.1650 326 0.6646 0.6296 0.6646 0.8152
No log 3.1845 328 0.5680 0.6739 0.5680 0.7536
No log 3.2039 330 0.4731 0.6804 0.4731 0.6878
No log 3.2233 332 0.4573 0.6765 0.4573 0.6762
No log 3.2427 334 0.4476 0.6844 0.4476 0.6690
No log 3.2621 336 0.4533 0.6286 0.4533 0.6733
No log 3.2816 338 0.4637 0.6082 0.4637 0.6809
No log 3.3010 340 0.4517 0.6014 0.4517 0.6721
No log 3.3204 342 0.4326 0.6180 0.4326 0.6577
No log 3.3398 344 0.4315 0.6279 0.4315 0.6569
No log 3.3592 346 0.4458 0.6420 0.4458 0.6677
No log 3.3786 348 0.4690 0.6666 0.4690 0.6848
No log 3.3981 350 0.4806 0.6448 0.4806 0.6932
No log 3.4175 352 0.5170 0.6379 0.5170 0.7190
No log 3.4369 354 0.4806 0.6654 0.4806 0.6933
No log 3.4563 356 0.4732 0.6681 0.4732 0.6879
No log 3.4757 358 0.5117 0.6667 0.5117 0.7153
No log 3.4951 360 0.5516 0.6373 0.5516 0.7427
No log 3.5146 362 0.5029 0.6785 0.5029 0.7092
No log 3.5340 364 0.4840 0.6704 0.4840 0.6957
No log 3.5534 366 0.4811 0.6632 0.4811 0.6936
No log 3.5728 368 0.4552 0.6754 0.4552 0.6747
No log 3.5922 370 0.4926 0.6597 0.4926 0.7019
No log 3.6117 372 0.5373 0.6201 0.5373 0.7330
No log 3.6311 374 0.4582 0.6494 0.4582 0.6769
No log 3.6505 376 0.4345 0.6266 0.4345 0.6591
No log 3.6699 378 0.4514 0.6481 0.4514 0.6718
No log 3.6893 380 0.4259 0.6555 0.4259 0.6526
No log 3.7087 382 0.4435 0.6324 0.4435 0.6659
No log 3.7282 384 0.4980 0.6005 0.4980 0.7057
No log 3.7476 386 0.5246 0.5781 0.5246 0.7243
No log 3.7670 388 0.5137 0.6005 0.5137 0.7167
No log 3.7864 390 0.4879 0.6187 0.4879 0.6985
No log 3.8058 392 0.4636 0.6286 0.4636 0.6809
No log 3.8252 394 0.5034 0.6423 0.5034 0.7095
No log 3.8447 396 0.4766 0.6808 0.4766 0.6903
No log 3.8641 398 0.4831 0.6839 0.4831 0.6950
No log 3.8835 400 0.4835 0.6667 0.4835 0.6954
No log 3.9029 402 0.5050 0.6721 0.5050 0.7106
No log 3.9223 404 0.4925 0.6705 0.4925 0.7018
No log 3.9417 406 0.4879 0.6676 0.4879 0.6985
No log 3.9612 408 0.4908 0.6822 0.4908 0.7006
No log 3.9806 410 0.5374 0.6488 0.5374 0.7331
No log 4.0 412 0.5310 0.6501 0.5310 0.7287
No log 4.0194 414 0.4549 0.6461 0.4549 0.6745
No log 4.0388 416 0.4468 0.6267 0.4468 0.6684
No log 4.0583 418 0.4430 0.5915 0.4430 0.6655
No log 4.0777 420 0.4459 0.5651 0.4459 0.6677
No log 4.0971 422 0.4541 0.5481 0.4541 0.6739
No log 4.1165 424 0.4526 0.5602 0.4526 0.6728
No log 4.1359 426 0.4722 0.5774 0.4722 0.6872
No log 4.1553 428 0.6988 0.5372 0.6988 0.8359
No log 4.1748 430 0.8622 0.4653 0.8622 0.9285
No log 4.1942 432 0.7340 0.5406 0.7340 0.8567
No log 4.2136 434 0.4878 0.6419 0.4878 0.6985
No log 4.2330 436 0.4610 0.6468 0.4610 0.6790
No log 4.2524 438 0.4632 0.6495 0.4632 0.6806
No log 4.2718 440 0.4603 0.6626 0.4603 0.6785
No log 4.2913 442 0.5304 0.6344 0.5304 0.7283
No log 4.3107 444 0.5418 0.6286 0.5418 0.7361
No log 4.3301 446 0.5305 0.6368 0.5305 0.7284
No log 4.3495 448 0.4593 0.6236 0.4593 0.6777
No log 4.3689 450 0.4555 0.6377 0.4555 0.6749
No log 4.3883 452 0.5180 0.6038 0.5180 0.7197
No log 4.4078 454 0.4978 0.6064 0.4978 0.7055
No log 4.4272 456 0.4560 0.5912 0.4560 0.6753
No log 4.4466 458 0.4670 0.6098 0.4670 0.6833
No log 4.4660 460 0.6078 0.5679 0.6078 0.7796
No log 4.4854 462 0.6994 0.5322 0.6994 0.8363
No log 4.5049 464 0.6315 0.5577 0.6315 0.7946
No log 4.5243 466 0.4563 0.6618 0.4563 0.6755
No log 4.5437 468 0.5292 0.6129 0.5292 0.7274
No log 4.5631 470 0.5866 0.6131 0.5866 0.7659
No log 4.5825 472 0.5202 0.6108 0.5202 0.7212
No log 4.6019 474 0.4445 0.6544 0.4445 0.6667
No log 4.6214 476 0.5006 0.6525 0.5006 0.7075
No log 4.6408 478 0.6743 0.5945 0.6743 0.8212
No log 4.6602 480 0.6505 0.6253 0.6505 0.8065
No log 4.6796 482 0.5127 0.6594 0.5127 0.7160
No log 4.6990 484 0.4683 0.6892 0.4683 0.6843
No log 4.7184 486 0.4658 0.6860 0.4658 0.6825
No log 4.7379 488 0.4719 0.7040 0.4719 0.6869
No log 4.7573 490 0.4956 0.6766 0.4956 0.7040
No log 4.7767 492 0.4558 0.6952 0.4558 0.6751
No log 4.7961 494 0.4468 0.6675 0.4468 0.6684
No log 4.8155 496 0.4420 0.6489 0.4420 0.6648
No log 4.8350 498 0.4432 0.6464 0.4432 0.6657
0.5312 4.8544 500 0.4697 0.6813 0.4697 0.6854
0.5312 4.8738 502 0.4974 0.6776 0.4974 0.7053
0.5312 4.8932 504 0.4744 0.6632 0.4744 0.6888
0.5312 4.9126 506 0.4616 0.6845 0.4616 0.6794
0.5312 4.9320 508 0.6031 0.6234 0.6031 0.7766
0.5312 4.9515 510 0.7222 0.6037 0.7222 0.8498
0.5312 4.9709 512 0.5891 0.6259 0.5891 0.7676
0.5312 4.9903 514 0.4215 0.6631 0.4215 0.6493
0.5312 5.0097 516 0.5050 0.6388 0.5050 0.7106

Framework versions

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