ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k10_task3_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: 0.7765
  • Qwk: 0.0496
  • Mse: 0.7765
  • Rmse: 0.8812

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 0.0714 2 3.7927 -0.0058 3.7927 1.9475
No log 0.1429 4 1.9101 0.0398 1.9101 1.3821
No log 0.2143 6 1.2710 0.0564 1.2710 1.1274
No log 0.2857 8 1.0379 -0.0101 1.0379 1.0188
No log 0.3571 10 0.9248 0.0305 0.9248 0.9617
No log 0.4286 12 0.8341 0.1660 0.8341 0.9133
No log 0.5 14 0.7882 -0.0287 0.7882 0.8878
No log 0.5714 16 0.9420 0.0805 0.9420 0.9706
No log 0.6429 18 1.4144 0.0 1.4144 1.1893
No log 0.7143 20 1.3407 -0.0247 1.3407 1.1579
No log 0.7857 22 1.1013 0.0032 1.1013 1.0494
No log 0.8571 24 1.1267 -0.0178 1.1267 1.0615
No log 0.9286 26 0.7795 0.0588 0.7795 0.8829
No log 1.0 28 0.6660 0.0555 0.6660 0.8161
No log 1.0714 30 0.7256 -0.0131 0.7256 0.8518
No log 1.1429 32 0.8611 0.0129 0.8611 0.9279
No log 1.2143 34 0.8786 0.0512 0.8786 0.9373
No log 1.2857 36 0.8012 0.0260 0.8012 0.8951
No log 1.3571 38 0.7287 0.0460 0.7287 0.8536
No log 1.4286 40 0.7445 -0.0188 0.7445 0.8628
No log 1.5 42 0.7741 -0.0264 0.7741 0.8798
No log 1.5714 44 0.9244 -0.0936 0.9244 0.9615
No log 1.6429 46 1.2236 0.0048 1.2236 1.1062
No log 1.7143 48 1.5152 -0.0247 1.5152 1.2309
No log 1.7857 50 1.6738 -0.0247 1.6738 1.2937
No log 1.8571 52 1.5472 0.0 1.5472 1.2438
No log 1.9286 54 1.3547 0.0 1.3547 1.1639
No log 2.0 56 1.1360 -0.0744 1.1360 1.0658
No log 2.0714 58 0.8714 0.0377 0.8714 0.9335
No log 2.1429 60 0.7376 0.0909 0.7376 0.8588
No log 2.2143 62 0.7538 0.1318 0.7538 0.8682
No log 2.2857 64 0.8518 0.0748 0.8518 0.9229
No log 2.3571 66 0.8112 0.0043 0.8112 0.9007
No log 2.4286 68 0.7528 0.0909 0.7528 0.8677
No log 2.5 70 0.7746 0.0759 0.7746 0.8801
No log 2.5714 72 0.8677 0.0676 0.8677 0.9315
No log 2.6429 74 0.9812 0.0329 0.9812 0.9906
No log 2.7143 76 0.9762 0.0111 0.9762 0.9880
No log 2.7857 78 0.9281 0.0642 0.9281 0.9634
No log 2.8571 80 0.9853 0.1114 0.9853 0.9926
No log 2.9286 82 1.1916 0.0569 1.1916 1.0916
No log 3.0 84 1.2042 -0.0084 1.2042 1.0974
No log 3.0714 86 0.9226 0.0545 0.9226 0.9605
No log 3.1429 88 0.7719 -0.0240 0.7719 0.8786
No log 3.2143 90 0.7576 -0.1163 0.7576 0.8704
No log 3.2857 92 0.7940 0.0191 0.7940 0.8911
No log 3.3571 94 0.8738 0.1553 0.8738 0.9348
No log 3.4286 96 0.9302 0.0260 0.9302 0.9645
No log 3.5 98 0.8800 0.1243 0.8800 0.9381
No log 3.5714 100 0.8428 0.0953 0.8428 0.9180
No log 3.6429 102 0.8773 0.1291 0.8773 0.9367
No log 3.7143 104 0.8566 0.0913 0.8566 0.9255
No log 3.7857 106 0.9466 -0.0054 0.9466 0.9729
No log 3.8571 108 0.9340 0.0362 0.9340 0.9664
No log 3.9286 110 0.8327 0.0574 0.8327 0.9125
No log 4.0 112 0.8081 0.0784 0.8081 0.8989
No log 4.0714 114 0.8306 0.1051 0.8306 0.9113
No log 4.1429 116 0.7800 0.2156 0.7800 0.8832
No log 4.2143 118 0.7331 0.0981 0.7331 0.8562
No log 4.2857 120 0.8303 -0.0295 0.8303 0.9112
No log 4.3571 122 1.1744 -0.0513 1.1744 1.0837
No log 4.4286 124 1.1218 0.0207 1.1218 1.0592
No log 4.5 126 0.9382 -0.0008 0.9382 0.9686
No log 4.5714 128 0.7741 -0.0731 0.7741 0.8798
No log 4.6429 130 0.7162 -0.0065 0.7162 0.8463
No log 4.7143 132 0.6939 0.0914 0.6939 0.8330
No log 4.7857 134 0.7868 -0.0295 0.7868 0.8870
No log 4.8571 136 0.9159 0.0041 0.9159 0.9570
No log 4.9286 138 0.9235 0.0442 0.9235 0.9610
No log 5.0 140 0.8195 -0.0731 0.8195 0.9053
No log 5.0714 142 0.7764 0.1236 0.7764 0.8811
No log 5.1429 144 0.7303 0.1549 0.7303 0.8546
No log 5.2143 146 0.6966 0.1474 0.6966 0.8346
No log 5.2857 148 0.7527 0.0549 0.7527 0.8676
No log 5.3571 150 0.9144 0.0676 0.9144 0.9562
No log 5.4286 152 0.8819 -0.0008 0.8819 0.9391
No log 5.5 154 0.7937 0.0456 0.7937 0.8909
No log 5.5714 156 0.7062 0.1304 0.7062 0.8404
No log 5.6429 158 0.7050 0.0 0.7050 0.8396
No log 5.7143 160 0.7622 -0.1121 0.7622 0.8730
No log 5.7857 162 0.8444 0.0442 0.8444 0.9189
No log 5.8571 164 0.8769 0.0442 0.8769 0.9364
No log 5.9286 166 0.8344 0.0442 0.8344 0.9135
No log 6.0 168 0.7759 0.0099 0.7759 0.8809
No log 6.0714 170 0.7098 0.0436 0.7098 0.8425
No log 6.1429 172 0.7184 0.0496 0.7184 0.8476
No log 6.2143 174 0.7348 0.1362 0.7348 0.8572
No log 6.2857 176 0.7377 0.2627 0.7377 0.8589
No log 6.3571 178 0.7543 0.1769 0.7543 0.8685
No log 6.4286 180 0.8040 0.1504 0.8040 0.8967
No log 6.5 182 0.7972 0.1079 0.7972 0.8928
No log 6.5714 184 0.7231 0.0058 0.7231 0.8503
No log 6.6429 186 0.7377 0.0338 0.7377 0.8589
No log 6.7143 188 0.9633 0.0953 0.9633 0.9815
No log 6.7857 190 0.9727 0.0283 0.9727 0.9863
No log 6.8571 192 0.7506 0.0338 0.7506 0.8664
No log 6.9286 194 0.8266 0.0152 0.8266 0.9092
No log 7.0 196 0.9184 -0.1194 0.9184 0.9583
No log 7.0714 198 0.9531 -0.1572 0.9531 0.9763
No log 7.1429 200 1.0006 -0.1628 1.0006 1.0003
No log 7.2143 202 0.9978 -0.1259 0.9978 0.9989
No log 7.2857 204 0.8735 -0.0303 0.8735 0.9346
No log 7.3571 206 0.8267 -0.0309 0.8267 0.9092
No log 7.4286 208 0.8737 -0.0371 0.8737 0.9347
No log 7.5 210 0.8412 -0.0390 0.8412 0.9172
No log 7.5714 212 0.7736 0.2225 0.7736 0.8795
No log 7.6429 214 0.7681 0.0110 0.7681 0.8764
No log 7.7143 216 0.7966 0.0229 0.7966 0.8925
No log 7.7857 218 0.7724 0.0981 0.7724 0.8789
No log 7.8571 220 0.7234 0.1395 0.7234 0.8505
No log 7.9286 222 0.6821 0.0914 0.6821 0.8259
No log 8.0 224 0.6950 0.0814 0.6950 0.8337
No log 8.0714 226 0.7395 0.1097 0.7395 0.8599
No log 8.1429 228 0.7164 0.0454 0.7164 0.8464
No log 8.2143 230 0.7760 0.1126 0.7760 0.8809
No log 8.2857 232 0.8142 0.0297 0.8142 0.9023
No log 8.3571 234 0.8383 -0.1002 0.8383 0.9156
No log 8.4286 236 0.8441 -0.0343 0.8441 0.9187
No log 8.5 238 0.8985 0.0113 0.8985 0.9479
No log 8.5714 240 0.8967 0.0456 0.8967 0.9469
No log 8.6429 242 0.8168 0.0700 0.8168 0.9038
No log 8.7143 244 0.7881 0.0338 0.7881 0.8878
No log 8.7857 246 0.7874 0.0807 0.7874 0.8874
No log 8.8571 248 0.8429 0.0043 0.8429 0.9181
No log 8.9286 250 0.8191 0.0191 0.8191 0.9050
No log 9.0 252 0.8027 0.1387 0.8027 0.8959
No log 9.0714 254 0.8054 0.1778 0.8054 0.8975
No log 9.1429 256 0.8847 0.0200 0.8847 0.9406
No log 9.2143 258 0.9338 0.0068 0.9338 0.9663
No log 9.2857 260 0.8439 0.0216 0.8439 0.9186
No log 9.3571 262 0.7994 0.0183 0.7994 0.8941
No log 9.4286 264 0.7891 -0.1656 0.7891 0.8883
No log 9.5 266 0.7948 -0.1054 0.7948 0.8915
No log 9.5714 268 0.8007 -0.1168 0.8007 0.8948
No log 9.6429 270 0.8123 -0.0718 0.8123 0.9013
No log 9.7143 272 0.8456 0.0600 0.8456 0.9196
No log 9.7857 274 0.8310 0.0129 0.8310 0.9116
No log 9.8571 276 0.7839 0.0814 0.7839 0.8854
No log 9.9286 278 0.8733 -0.0566 0.8733 0.9345
No log 10.0 280 0.9682 -0.0187 0.9682 0.9840
No log 10.0714 282 0.8434 0.0377 0.8434 0.9183
No log 10.1429 284 0.7566 0.1860 0.7566 0.8698
No log 10.2143 286 0.8415 -0.0283 0.8415 0.9173
No log 10.2857 288 0.8725 0.0068 0.8725 0.9341
No log 10.3571 290 0.8645 0.0549 0.8645 0.9298
No log 10.4286 292 0.8484 0.0525 0.8484 0.9211
No log 10.5 294 0.8047 -0.0204 0.8047 0.8970
No log 10.5714 296 0.7897 -0.0567 0.7897 0.8886
No log 10.6429 298 0.7943 -0.1111 0.7943 0.8912
No log 10.7143 300 0.8031 -0.0228 0.8031 0.8962
No log 10.7857 302 0.8225 0.0159 0.8225 0.9069
No log 10.8571 304 0.8326 -0.0718 0.8326 0.9125
No log 10.9286 306 0.8247 0.0359 0.8247 0.9081
No log 11.0 308 0.8408 -0.0051 0.8408 0.9169
No log 11.0714 310 0.8449 0.0106 0.8449 0.9192
No log 11.1429 312 0.8411 0.0129 0.8411 0.9171
No log 11.2143 314 0.7980 0.0056 0.7980 0.8933
No log 11.2857 316 0.7763 -0.0030 0.7763 0.8811
No log 11.3571 318 0.7844 0.0394 0.7844 0.8857
No log 11.4286 320 0.8217 -0.0699 0.8217 0.9065
No log 11.5 322 0.8558 -0.0711 0.8558 0.9251
No log 11.5714 324 0.8630 -0.0711 0.8630 0.9290
No log 11.6429 326 0.8499 -0.1135 0.8499 0.9219
No log 11.7143 328 0.8629 -0.0443 0.8629 0.9289
No log 11.7857 330 0.8778 -0.0408 0.8778 0.9369
No log 11.8571 332 0.8955 -0.0558 0.8955 0.9463
No log 11.9286 334 0.8402 0.0495 0.8402 0.9166
No log 12.0 336 0.8370 0.0289 0.8370 0.9149
No log 12.0714 338 0.9349 -0.0787 0.9349 0.9669
No log 12.1429 340 0.9469 -0.0101 0.9469 0.9731
No log 12.2143 342 0.8702 -0.0251 0.8702 0.9328
No log 12.2857 344 0.8583 0.0816 0.8583 0.9265
No log 12.3571 346 0.8712 0.0423 0.8712 0.9334
No log 12.4286 348 0.8525 -0.0459 0.8525 0.9233
No log 12.5 350 0.8562 -0.0262 0.8562 0.9253
No log 12.5714 352 0.8552 0.0099 0.8552 0.9248
No log 12.6429 354 0.8068 -0.0629 0.8068 0.8982
No log 12.7143 356 0.7916 0.0840 0.7916 0.8897
No log 12.7857 358 0.7925 0.0937 0.7925 0.8902
No log 12.8571 360 0.8079 0.0606 0.8079 0.8988
No log 12.9286 362 0.7602 0.0570 0.7602 0.8719
No log 13.0 364 0.7756 0.1146 0.7756 0.8807
No log 13.0714 366 0.8695 -0.0033 0.8695 0.9325
No log 13.1429 368 0.8749 -0.0056 0.8749 0.9353
No log 13.2143 370 0.8394 0.0017 0.8394 0.9162
No log 13.2857 372 0.8202 0.0512 0.8202 0.9057
No log 13.3571 374 0.8525 0.0618 0.8525 0.9233
No log 13.4286 376 0.8931 0.0971 0.8931 0.9450
No log 13.5 378 0.9038 0.0552 0.9038 0.9507
No log 13.5714 380 0.8862 0.0509 0.8862 0.9414
No log 13.6429 382 0.8510 0.0091 0.8510 0.9225
No log 13.7143 384 0.8445 -0.0373 0.8445 0.9189
No log 13.7857 386 0.8022 0.0639 0.8022 0.8957
No log 13.8571 388 0.7494 0.1249 0.7494 0.8657
No log 13.9286 390 0.7552 0.1906 0.7552 0.8690
No log 14.0 392 0.7789 0.1821 0.7789 0.8826
No log 14.0714 394 0.7914 0.1702 0.7914 0.8896
No log 14.1429 396 0.8073 0.0188 0.8073 0.8985
No log 14.2143 398 0.8342 0.0188 0.8342 0.9133
No log 14.2857 400 0.8548 -0.0895 0.8548 0.9246
No log 14.3571 402 0.8697 0.0021 0.8697 0.9326
No log 14.4286 404 0.8732 0.0334 0.8732 0.9345
No log 14.5 406 0.8570 0.1052 0.8570 0.9258
No log 14.5714 408 0.8227 0.1255 0.8227 0.9071
No log 14.6429 410 0.8032 0.1778 0.8032 0.8962
No log 14.7143 412 0.7934 0.1393 0.7934 0.8907
No log 14.7857 414 0.7944 0.0690 0.7944 0.8913
No log 14.8571 416 0.8068 0.0588 0.8068 0.8982
No log 14.9286 418 0.7862 0.0628 0.7862 0.8867
No log 15.0 420 0.7824 0.0690 0.7824 0.8846
No log 15.0714 422 0.7805 0.0277 0.7805 0.8835
No log 15.1429 424 0.7856 0.1282 0.7856 0.8863
No log 15.2143 426 0.8010 -0.0108 0.8010 0.8950
No log 15.2857 428 0.8484 -0.0156 0.8484 0.9211
No log 15.3571 430 0.8836 -0.0200 0.8836 0.9400
No log 15.4286 432 0.9039 -0.0291 0.9039 0.9507
No log 15.5 434 0.8739 -0.0526 0.8739 0.9348
No log 15.5714 436 0.8547 -0.0851 0.8547 0.9245
No log 15.6429 438 0.8326 0.0081 0.8326 0.9125
No log 15.7143 440 0.7934 0.0327 0.7934 0.8908
No log 15.7857 442 0.7816 0.1096 0.7816 0.8841
No log 15.8571 444 0.7639 0.1304 0.7639 0.8740
No log 15.9286 446 0.7745 0.0978 0.7745 0.8801
No log 16.0 448 0.8058 0.1030 0.8058 0.8977
No log 16.0714 450 0.8142 0.0474 0.8142 0.9023
No log 16.1429 452 0.8157 0.1287 0.8157 0.9032
No log 16.2143 454 0.8353 -0.0195 0.8353 0.9140
No log 16.2857 456 0.8393 0.1236 0.8393 0.9161
No log 16.3571 458 0.8320 0.1292 0.8320 0.9122
No log 16.4286 460 0.8351 -0.0108 0.8351 0.9138
No log 16.5 462 0.8375 -0.0583 0.8375 0.9151
No log 16.5714 464 0.8279 -0.0976 0.8279 0.9099
No log 16.6429 466 0.8209 0.0375 0.8209 0.9060
No log 16.7143 468 0.8352 -0.0699 0.8352 0.9139
No log 16.7857 470 0.8331 -0.0699 0.8331 0.9127
No log 16.8571 472 0.8448 -0.0699 0.8448 0.9191
No log 16.9286 474 0.8649 -0.1140 0.8649 0.9300
No log 17.0 476 0.8575 -0.0699 0.8575 0.9260
No log 17.0714 478 0.8615 0.0196 0.8615 0.9282
No log 17.1429 480 0.8875 0.0265 0.8875 0.9421
No log 17.2143 482 0.9191 -0.0392 0.9191 0.9587
No log 17.2857 484 0.9683 -0.0670 0.9683 0.9840
No log 17.3571 486 0.9910 0.0125 0.9910 0.9955
No log 17.4286 488 0.9718 -0.0347 0.9718 0.9858
No log 17.5 490 0.9376 -0.0121 0.9376 0.9683
No log 17.5714 492 0.8937 0.0295 0.8937 0.9454
No log 17.6429 494 0.8635 0.0934 0.8635 0.9293
No log 17.7143 496 0.8542 0.0652 0.8542 0.9242
No log 17.7857 498 0.8195 0.1080 0.8195 0.9053
0.3284 17.8571 500 0.7881 0.0571 0.7881 0.8878
0.3284 17.9286 502 0.7641 0.0479 0.7641 0.8741
0.3284 18.0 504 0.7674 0.0436 0.7674 0.8760
0.3284 18.0714 506 0.7739 0.0436 0.7739 0.8797
0.3284 18.1429 508 0.7686 0.0479 0.7686 0.8767
0.3284 18.2143 510 0.7765 0.0496 0.7765 0.8812

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
3
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for MayBashendy/ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k10_task3_organization

Finetuned
(4040)
this model