ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k20_task5_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: 0.8575
  • Qwk: 0.3878
  • Mse: 0.8575
  • Rmse: 0.9260

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 0.0392 2 4.3004 0.0102 4.3004 2.0737
No log 0.0784 4 2.7013 -0.0067 2.7013 1.6435
No log 0.1176 6 1.4134 -0.0256 1.4134 1.1889
No log 0.1569 8 1.1496 0.1779 1.1496 1.0722
No log 0.1961 10 1.2976 0.2639 1.2976 1.1391
No log 0.2353 12 1.1068 0.1071 1.1068 1.0521
No log 0.2745 14 1.0840 0.0919 1.0840 1.0411
No log 0.3137 16 1.1313 0.0574 1.1313 1.0636
No log 0.3529 18 1.1905 -0.0187 1.1905 1.0911
No log 0.3922 20 1.2648 0.0850 1.2648 1.1246
No log 0.4314 22 1.1711 0.1525 1.1711 1.0822
No log 0.4706 24 1.1266 0.1379 1.1266 1.0614
No log 0.5098 26 1.0402 0.3003 1.0402 1.0199
No log 0.5490 28 1.0334 0.2758 1.0334 1.0166
No log 0.5882 30 1.0807 0.1471 1.0807 1.0396
No log 0.6275 32 1.1333 0.1618 1.1333 1.0646
No log 0.6667 34 1.1508 0.1764 1.1508 1.0727
No log 0.7059 36 1.0651 0.2781 1.0651 1.0320
No log 0.7451 38 1.0078 0.3162 1.0078 1.0039
No log 0.7843 40 0.9898 0.2594 0.9898 0.9949
No log 0.8235 42 0.9866 0.2008 0.9866 0.9933
No log 0.8627 44 1.1143 0.0482 1.1143 1.0556
No log 0.9020 46 1.2296 -0.0833 1.2296 1.1089
No log 0.9412 48 1.2073 0.0924 1.2073 1.0988
No log 0.9804 50 1.1164 0.0385 1.1164 1.0566
No log 1.0196 52 1.1390 0.1770 1.1390 1.0672
No log 1.0588 54 1.2091 0.1052 1.2091 1.0996
No log 1.0980 56 1.1621 0.1473 1.1621 1.0780
No log 1.1373 58 1.0573 0.1446 1.0573 1.0282
No log 1.1765 60 0.9689 0.3733 0.9689 0.9843
No log 1.2157 62 0.9548 0.3229 0.9548 0.9772
No log 1.2549 64 1.0863 0.2271 1.0863 1.0423
No log 1.2941 66 1.2224 0.1744 1.2224 1.1056
No log 1.3333 68 1.3923 0.1449 1.3923 1.1800
No log 1.3725 70 1.4600 0.1004 1.4600 1.2083
No log 1.4118 72 1.2242 0.0338 1.2242 1.1064
No log 1.4510 74 1.0879 0.1653 1.0879 1.0430
No log 1.4902 76 1.0549 0.1680 1.0549 1.0271
No log 1.5294 78 1.1193 0.1801 1.1193 1.0580
No log 1.5686 80 1.2948 0.2167 1.2948 1.1379
No log 1.6078 82 1.4017 0.1500 1.4017 1.1839
No log 1.6471 84 1.3812 -0.0710 1.3812 1.1753
No log 1.6863 86 1.4026 -0.0809 1.4026 1.1843
No log 1.7255 88 1.3046 -0.0154 1.3046 1.1422
No log 1.7647 90 1.1795 -0.0120 1.1795 1.0861
No log 1.8039 92 1.0125 0.2015 1.0125 1.0062
No log 1.8431 94 0.9516 0.2341 0.9516 0.9755
No log 1.8824 96 0.9266 0.2865 0.9266 0.9626
No log 1.9216 98 0.9249 0.2088 0.9249 0.9617
No log 1.9608 100 0.9544 0.2128 0.9544 0.9770
No log 2.0 102 0.9560 0.2005 0.9560 0.9777
No log 2.0392 104 0.9412 0.2128 0.9412 0.9701
No log 2.0784 106 0.9438 0.3119 0.9438 0.9715
No log 2.1176 108 0.9350 0.3492 0.9350 0.9669
No log 2.1569 110 0.9139 0.3531 0.9139 0.9560
No log 2.1961 112 0.8974 0.3027 0.8974 0.9473
No log 2.2353 114 0.8870 0.3454 0.8870 0.9418
No log 2.2745 116 0.9285 0.3202 0.9285 0.9636
No log 2.3137 118 1.0607 0.3163 1.0607 1.0299
No log 2.3529 120 1.1563 0.2888 1.1563 1.0753
No log 2.3922 122 1.1415 0.2631 1.1415 1.0684
No log 2.4314 124 1.0419 0.2704 1.0419 1.0208
No log 2.4706 126 1.0239 0.2704 1.0239 1.0119
No log 2.5098 128 0.9436 0.3374 0.9436 0.9714
No log 2.5490 130 0.8690 0.3840 0.8690 0.9322
No log 2.5882 132 0.8644 0.3797 0.8644 0.9297
No log 2.6275 134 0.8821 0.3797 0.8821 0.9392
No log 2.6667 136 0.9007 0.3559 0.9007 0.9491
No log 2.7059 138 0.9395 0.4257 0.9395 0.9693
No log 2.7451 140 0.9146 0.5173 0.9146 0.9564
No log 2.7843 142 0.8689 0.5210 0.8689 0.9321
No log 2.8235 144 0.8387 0.4553 0.8387 0.9158
No log 2.8627 146 0.8404 0.4434 0.8404 0.9168
No log 2.9020 148 0.8279 0.4932 0.8279 0.9099
No log 2.9412 150 0.7984 0.5163 0.7984 0.8935
No log 2.9804 152 0.7955 0.5602 0.7955 0.8919
No log 3.0196 154 0.8449 0.4519 0.8449 0.9192
No log 3.0588 156 0.8916 0.4515 0.8916 0.9442
No log 3.0980 158 0.9317 0.3976 0.9317 0.9653
No log 3.1373 160 0.9512 0.3196 0.9512 0.9753
No log 3.1765 162 0.9085 0.4241 0.9085 0.9532
No log 3.2157 164 0.8363 0.4503 0.8363 0.9145
No log 3.2549 166 0.8163 0.4759 0.8163 0.9035
No log 3.2941 168 0.8556 0.3896 0.8556 0.9250
No log 3.3333 170 0.8877 0.3661 0.8877 0.9422
No log 3.3725 172 0.9025 0.4180 0.9025 0.9500
No log 3.4118 174 0.9144 0.4042 0.9144 0.9562
No log 3.4510 176 0.8757 0.4857 0.8757 0.9358
No log 3.4902 178 0.8347 0.4867 0.8347 0.9136
No log 3.5294 180 0.8064 0.5044 0.8064 0.8980
No log 3.5686 182 0.9405 0.4123 0.9405 0.9698
No log 3.6078 184 0.8812 0.4240 0.8812 0.9387
No log 3.6471 186 0.7432 0.4707 0.7432 0.8621
No log 3.6863 188 0.7577 0.5146 0.7577 0.8705
No log 3.7255 190 0.8390 0.4824 0.8390 0.9160
No log 3.7647 192 0.9792 0.3699 0.9792 0.9896
No log 3.8039 194 1.0048 0.3286 1.0048 1.0024
No log 3.8431 196 0.9545 0.4054 0.9545 0.9770
No log 3.8824 198 0.8728 0.3939 0.8728 0.9342
No log 3.9216 200 0.7715 0.4524 0.7715 0.8784
No log 3.9608 202 0.7262 0.4524 0.7262 0.8522
No log 4.0 204 0.7164 0.4269 0.7164 0.8464
No log 4.0392 206 0.7415 0.4524 0.7415 0.8611
No log 4.0784 208 0.7380 0.5010 0.7380 0.8591
No log 4.1176 210 0.7418 0.5010 0.7418 0.8613
No log 4.1569 212 0.7148 0.4908 0.7148 0.8455
No log 4.1961 214 0.7221 0.5098 0.7221 0.8498
No log 4.2353 216 0.7023 0.5844 0.7023 0.8381
No log 4.2745 218 0.7114 0.5498 0.7114 0.8435
No log 4.3137 220 0.6891 0.5010 0.6891 0.8301
No log 4.3529 222 0.7252 0.4794 0.7252 0.8516
No log 4.3922 224 0.7718 0.4929 0.7718 0.8785
No log 4.4314 226 0.7644 0.5048 0.7644 0.8743
No log 4.4706 228 0.7339 0.4524 0.7339 0.8567
No log 4.5098 230 0.7044 0.5010 0.7044 0.8393
No log 4.5490 232 0.7192 0.5194 0.7192 0.8481
No log 4.5882 234 0.8452 0.5729 0.8452 0.9194
No log 4.6275 236 0.8463 0.5536 0.8463 0.9200
No log 4.6667 238 0.7784 0.5211 0.7784 0.8823
No log 4.7059 240 0.7829 0.5357 0.7829 0.8848
No log 4.7451 242 0.8708 0.5037 0.8708 0.9332
No log 4.7843 244 0.9450 0.4387 0.9450 0.9721
No log 4.8235 246 0.9756 0.3957 0.9756 0.9877
No log 4.8627 248 0.8934 0.3809 0.8934 0.9452
No log 4.9020 250 0.8493 0.4012 0.8493 0.9216
No log 4.9412 252 0.8371 0.3933 0.8371 0.9150
No log 4.9804 254 0.8243 0.4321 0.8243 0.9079
No log 5.0196 256 0.8258 0.4477 0.8258 0.9087
No log 5.0588 258 0.7996 0.4947 0.7996 0.8942
No log 5.0980 260 0.7965 0.4429 0.7965 0.8925
No log 5.1373 262 0.8496 0.4951 0.8496 0.9217
No log 5.1765 264 0.8897 0.4722 0.8897 0.9432
No log 5.2157 266 0.9260 0.4924 0.9260 0.9623
No log 5.2549 268 0.9488 0.4694 0.9488 0.9741
No log 5.2941 270 0.8810 0.4948 0.8810 0.9386
No log 5.3333 272 0.8510 0.4391 0.8510 0.9225
No log 5.3725 274 0.8363 0.3896 0.8363 0.9145
No log 5.4118 276 0.8310 0.3437 0.8310 0.9116
No log 5.4510 278 0.8299 0.3437 0.8299 0.9110
No log 5.4902 280 0.8361 0.3505 0.8361 0.9144
No log 5.5294 282 0.8575 0.4494 0.8575 0.9260
No log 5.5686 284 0.9129 0.4954 0.9129 0.9554
No log 5.6078 286 1.0131 0.3812 1.0131 1.0065
No log 5.6471 288 1.0628 0.3642 1.0628 1.0309
No log 5.6863 290 1.0190 0.4016 1.0190 1.0095
No log 5.7255 292 0.9183 0.4839 0.9183 0.9583
No log 5.7647 294 0.8657 0.3781 0.8657 0.9305
No log 5.8039 296 0.8497 0.4208 0.8497 0.9218
No log 5.8431 298 0.8405 0.3708 0.8405 0.9168
No log 5.8824 300 0.8645 0.4141 0.8645 0.9298
No log 5.9216 302 0.9515 0.4343 0.9515 0.9754
No log 5.9608 304 0.9999 0.4828 0.9999 0.9999
No log 6.0 306 1.0007 0.4828 1.0007 1.0003
No log 6.0392 308 0.9866 0.4828 0.9866 0.9933
No log 6.0784 310 0.9507 0.4343 0.9507 0.9750
No log 6.1176 312 0.9063 0.4491 0.9063 0.9520
No log 6.1569 314 0.8442 0.5029 0.8442 0.9188
No log 6.1961 316 0.8517 0.4972 0.8517 0.9229
No log 6.2353 318 0.9048 0.4919 0.9048 0.9512
No log 6.2745 320 0.8915 0.4822 0.8915 0.9442
No log 6.3137 322 0.8666 0.4539 0.8666 0.9309
No log 6.3529 324 0.8503 0.5161 0.8503 0.9221
No log 6.3922 326 0.8394 0.4933 0.8394 0.9162
No log 6.4314 328 0.8380 0.5139 0.8380 0.9154
No log 6.4706 330 0.8446 0.5035 0.8446 0.9190
No log 6.5098 332 0.8741 0.4572 0.8741 0.9349
No log 6.5490 334 0.8784 0.4555 0.8784 0.9373
No log 6.5882 336 0.8589 0.5224 0.8589 0.9268
No log 6.6275 338 0.8288 0.5213 0.8288 0.9104
No log 6.6667 340 0.8110 0.5352 0.8110 0.9006
No log 6.7059 342 0.8124 0.4285 0.8124 0.9013
No log 6.7451 344 0.8107 0.4643 0.8107 0.9004
No log 6.7843 346 0.7892 0.5645 0.7892 0.8884
No log 6.8235 348 0.7624 0.5849 0.7624 0.8731
No log 6.8627 350 0.7142 0.5716 0.7142 0.8451
No log 6.9020 352 0.7261 0.4772 0.7261 0.8521
No log 6.9412 354 0.7956 0.3977 0.7956 0.8920
No log 6.9804 356 0.8476 0.3693 0.8476 0.9206
No log 7.0196 358 0.8630 0.3838 0.8630 0.9290
No log 7.0588 360 0.8898 0.4873 0.8898 0.9433
No log 7.0980 362 0.9588 0.5232 0.9588 0.9792
No log 7.1373 364 1.0760 0.4076 1.0760 1.0373
No log 7.1765 366 1.1373 0.3983 1.1373 1.0664
No log 7.2157 368 1.0142 0.4273 1.0142 1.0071
No log 7.2549 370 0.7968 0.5413 0.7968 0.8926
No log 7.2941 372 0.7457 0.4608 0.7457 0.8635
No log 7.3333 374 0.7704 0.4396 0.7704 0.8777
No log 7.3725 376 0.7403 0.5202 0.7403 0.8604
No log 7.4118 378 0.7455 0.5503 0.7455 0.8634
No log 7.4510 380 0.7978 0.5107 0.7978 0.8932
No log 7.4902 382 0.8491 0.5305 0.8491 0.9215
No log 7.5294 384 0.8207 0.4973 0.8207 0.9059
No log 7.5686 386 0.7808 0.4192 0.7808 0.8836
No log 7.6078 388 0.7373 0.4843 0.7373 0.8586
No log 7.6471 390 0.7021 0.5386 0.7021 0.8379
No log 7.6863 392 0.6872 0.5406 0.6872 0.8290
No log 7.7255 394 0.6848 0.6042 0.6848 0.8275
No log 7.7647 396 0.6873 0.5940 0.6873 0.8291
No log 7.8039 398 0.6957 0.6225 0.6957 0.8341
No log 7.8431 400 0.7033 0.6195 0.7033 0.8386
No log 7.8824 402 0.7082 0.5892 0.7082 0.8416
No log 7.9216 404 0.7290 0.6052 0.7290 0.8538
No log 7.9608 406 0.7687 0.5415 0.7687 0.8768
No log 8.0 408 0.8026 0.5102 0.8026 0.8959
No log 8.0392 410 0.7823 0.4749 0.7823 0.8845
No log 8.0784 412 0.7457 0.5163 0.7457 0.8635
No log 8.1176 414 0.7407 0.5146 0.7407 0.8607
No log 8.1569 416 0.8173 0.5041 0.8173 0.9040
No log 8.1961 418 0.9305 0.4568 0.9305 0.9646
No log 8.2353 420 1.0337 0.4353 1.0337 1.0167
No log 8.2745 422 1.0473 0.4126 1.0473 1.0234
No log 8.3137 424 0.9445 0.3880 0.9445 0.9719
No log 8.3529 426 0.8352 0.4818 0.8352 0.9139
No log 8.3922 428 0.7691 0.4836 0.7691 0.8770
No log 8.4314 430 0.7675 0.4839 0.7675 0.8760
No log 8.4706 432 0.7780 0.4952 0.7780 0.8820
No log 8.5098 434 0.7977 0.4579 0.7977 0.8931
No log 8.5490 436 0.7967 0.3799 0.7967 0.8926
No log 8.5882 438 0.7591 0.5010 0.7591 0.8713
No log 8.6275 440 0.7448 0.5546 0.7448 0.8630
No log 8.6667 442 0.7911 0.4696 0.7911 0.8894
No log 8.7059 444 0.8353 0.4681 0.8353 0.9139
No log 8.7451 446 0.8382 0.4681 0.8382 0.9155
No log 8.7843 448 0.7835 0.5634 0.7835 0.8851
No log 8.8235 450 0.7468 0.5666 0.7468 0.8642
No log 8.8627 452 0.7037 0.6143 0.7037 0.8388
No log 8.9020 454 0.6708 0.6380 0.6708 0.8190
No log 8.9412 456 0.6501 0.6011 0.6501 0.8063
No log 8.9804 458 0.6445 0.6380 0.6445 0.8028
No log 9.0196 460 0.6827 0.6360 0.6827 0.8263
No log 9.0588 462 0.7246 0.5306 0.7246 0.8512
No log 9.0980 464 0.7641 0.5433 0.7641 0.8741
No log 9.1373 466 0.8279 0.4854 0.8279 0.9099
No log 9.1765 468 0.9100 0.4709 0.9100 0.9539
No log 9.2157 470 0.9965 0.4471 0.9965 0.9982
No log 9.2549 472 1.0329 0.4668 1.0329 1.0163
No log 9.2941 474 0.9253 0.5075 0.9253 0.9619
No log 9.3333 476 0.8257 0.4694 0.8257 0.9087
No log 9.3725 478 0.7232 0.5528 0.7232 0.8504
No log 9.4118 480 0.6848 0.5171 0.6848 0.8275
No log 9.4510 482 0.6955 0.4923 0.6955 0.8340
No log 9.4902 484 0.7059 0.4810 0.7059 0.8402
No log 9.5294 486 0.7397 0.5002 0.7397 0.8601
No log 9.5686 488 0.8104 0.5041 0.8104 0.9002
No log 9.6078 490 0.8687 0.5241 0.8687 0.9321
No log 9.6471 492 0.8686 0.4250 0.8686 0.9320
No log 9.6863 494 0.8659 0.3992 0.8659 0.9305
No log 9.7255 496 0.8398 0.3725 0.8398 0.9164
No log 9.7647 498 0.8235 0.3992 0.8235 0.9075
0.3384 9.8039 500 0.7975 0.4010 0.7975 0.8930
0.3384 9.8431 502 0.8013 0.4850 0.8013 0.8952
0.3384 9.8824 504 0.7955 0.4850 0.7955 0.8919
0.3384 9.9216 506 0.7807 0.4110 0.7807 0.8836
0.3384 9.9608 508 0.7765 0.3314 0.7765 0.8812
0.3384 10.0 510 0.7829 0.3713 0.7829 0.8848
0.3384 10.0392 512 0.7816 0.3476 0.7816 0.8841
0.3384 10.0784 514 0.7839 0.3840 0.7839 0.8854
0.3384 10.1176 516 0.7885 0.4110 0.7885 0.8880
0.3384 10.1569 518 0.7869 0.4110 0.7869 0.8871
0.3384 10.1961 520 0.7846 0.3840 0.7846 0.8858
0.3384 10.2353 522 0.7852 0.3178 0.7852 0.8861
0.3384 10.2745 524 0.8023 0.3178 0.8023 0.8957
0.3384 10.3137 526 0.8205 0.3314 0.8205 0.9058
0.3384 10.3529 528 0.8375 0.4254 0.8375 0.9152
0.3384 10.3922 530 0.8427 0.5079 0.8427 0.9180
0.3384 10.4314 532 0.8292 0.5079 0.8292 0.9106
0.3384 10.4706 534 0.8231 0.4966 0.8231 0.9072
0.3384 10.5098 536 0.7972 0.3513 0.7972 0.8928
0.3384 10.5490 538 0.8022 0.3513 0.8022 0.8957
0.3384 10.5882 540 0.8080 0.3802 0.8080 0.8989
0.3384 10.6275 542 0.8300 0.3802 0.8300 0.9110
0.3384 10.6667 544 0.8575 0.3878 0.8575 0.9260

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
6
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_k20_task5_organization

Finetuned
(4205)
this model