ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run1_AugV5_k10_task1_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: 1.1151
  • Qwk: 0.4725
  • Mse: 1.1151
  • Rmse: 1.0560

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 0.0385 2 5.4361 -0.0099 5.4361 2.3316
No log 0.0769 4 3.1557 0.0822 3.1557 1.7764
No log 0.1154 6 1.7704 0.1046 1.7704 1.3305
No log 0.1538 8 1.2901 0.2354 1.2901 1.1358
No log 0.1923 10 1.2083 0.2575 1.2083 1.0992
No log 0.2308 12 1.1391 0.3068 1.1391 1.0673
No log 0.2692 14 1.1773 0.3054 1.1773 1.0850
No log 0.3077 16 1.2400 0.2109 1.2400 1.1135
No log 0.3462 18 1.1825 0.2758 1.1825 1.0874
No log 0.3846 20 1.1187 0.3261 1.1187 1.0577
No log 0.4231 22 1.3143 0.1520 1.3143 1.1465
No log 0.4615 24 1.3372 0.1677 1.3372 1.1564
No log 0.5 26 1.2424 0.2293 1.2424 1.1146
No log 0.5385 28 1.0372 0.3799 1.0372 1.0184
No log 0.5769 30 0.9728 0.3952 0.9728 0.9863
No log 0.6154 32 1.0501 0.4073 1.0501 1.0247
No log 0.6538 34 0.9894 0.3727 0.9894 0.9947
No log 0.6923 36 0.9321 0.3679 0.9321 0.9655
No log 0.7308 38 0.9283 0.4429 0.9283 0.9635
No log 0.7692 40 1.1069 0.3763 1.1069 1.0521
No log 0.8077 42 1.5124 0.2235 1.5124 1.2298
No log 0.8462 44 1.6055 0.2046 1.6055 1.2671
No log 0.8846 46 1.1031 0.3854 1.1031 1.0503
No log 0.9231 48 0.9333 0.4425 0.9333 0.9661
No log 0.9615 50 0.8983 0.4750 0.8983 0.9478
No log 1.0 52 0.9091 0.4588 0.9091 0.9535
No log 1.0385 54 0.9058 0.3938 0.9058 0.9517
No log 1.0769 56 0.9833 0.4146 0.9833 0.9916
No log 1.1154 58 0.9343 0.3545 0.9343 0.9666
No log 1.1538 60 0.9672 0.3844 0.9672 0.9835
No log 1.1923 62 1.0974 0.3476 1.0974 1.0476
No log 1.2308 64 1.1122 0.3975 1.1122 1.0546
No log 1.2692 66 1.0680 0.2927 1.0680 1.0334
No log 1.3077 68 1.0512 0.3471 1.0512 1.0253
No log 1.3462 70 0.9681 0.3687 0.9681 0.9839
No log 1.3846 72 0.9504 0.3504 0.9504 0.9749
No log 1.4231 74 0.9447 0.3656 0.9447 0.9719
No log 1.4615 76 0.9075 0.4137 0.9075 0.9526
No log 1.5 78 0.9039 0.3661 0.9039 0.9507
No log 1.5385 80 0.9154 0.3740 0.9154 0.9568
No log 1.5769 82 0.8248 0.4286 0.8248 0.9082
No log 1.6154 84 0.7853 0.5040 0.7853 0.8862
No log 1.6538 86 0.7916 0.5217 0.7916 0.8897
No log 1.6923 88 0.8024 0.5197 0.8024 0.8958
No log 1.7308 90 0.7580 0.5892 0.7580 0.8706
No log 1.7692 92 0.9029 0.5068 0.9029 0.9502
No log 1.8077 94 1.0181 0.4318 1.0181 1.0090
No log 1.8462 96 0.9708 0.4178 0.9708 0.9853
No log 1.8846 98 0.8429 0.5104 0.8429 0.9181
No log 1.9231 100 0.7902 0.5427 0.7902 0.8889
No log 1.9615 102 0.9223 0.5377 0.9223 0.9604
No log 2.0 104 0.8610 0.5597 0.8610 0.9279
No log 2.0385 106 0.7629 0.6027 0.7629 0.8734
No log 2.0769 108 0.8184 0.6039 0.8184 0.9046
No log 2.1154 110 0.8581 0.5755 0.8581 0.9263
No log 2.1538 112 0.8360 0.6312 0.8360 0.9143
No log 2.1923 114 0.7966 0.5967 0.7966 0.8925
No log 2.2308 116 0.8088 0.5507 0.8088 0.8993
No log 2.2692 118 0.7838 0.5590 0.7838 0.8853
No log 2.3077 120 0.7425 0.5492 0.7425 0.8617
No log 2.3462 122 0.8204 0.5790 0.8204 0.9058
No log 2.3846 124 1.0543 0.4950 1.0543 1.0268
No log 2.4231 126 1.3639 0.4145 1.3639 1.1679
No log 2.4615 128 1.4237 0.4031 1.4237 1.1932
No log 2.5 130 1.1796 0.4410 1.1796 1.0861
No log 2.5385 132 0.9521 0.4594 0.9521 0.9758
No log 2.5769 134 0.8845 0.5119 0.8845 0.9405
No log 2.6154 136 0.8711 0.5873 0.8711 0.9333
No log 2.6538 138 0.9246 0.5449 0.9246 0.9616
No log 2.6923 140 0.9783 0.5536 0.9783 0.9891
No log 2.7308 142 1.0203 0.5357 1.0203 1.0101
No log 2.7692 144 1.0458 0.5416 1.0458 1.0226
No log 2.8077 146 1.0516 0.4995 1.0516 1.0255
No log 2.8462 148 0.9665 0.5182 0.9665 0.9831
No log 2.8846 150 0.8633 0.5977 0.8633 0.9292
No log 2.9231 152 0.8689 0.5997 0.8689 0.9322
No log 2.9615 154 0.9468 0.5311 0.9468 0.9730
No log 3.0 156 1.0330 0.4954 1.0330 1.0164
No log 3.0385 158 1.0800 0.4696 1.0800 1.0392
No log 3.0769 160 1.0764 0.4976 1.0764 1.0375
No log 3.1154 162 1.0986 0.5326 1.0986 1.0481
No log 3.1538 164 1.2136 0.5011 1.2136 1.1016
No log 3.1923 166 1.2199 0.4927 1.2199 1.1045
No log 3.2308 168 1.1769 0.4842 1.1769 1.0848
No log 3.2692 170 1.1238 0.4621 1.1238 1.0601
No log 3.3077 172 1.0503 0.4614 1.0503 1.0248
No log 3.3462 174 0.9067 0.5413 0.9067 0.9522
No log 3.3846 176 0.8313 0.6179 0.8313 0.9117
No log 3.4231 178 0.8006 0.5589 0.8006 0.8948
No log 3.4615 180 0.8196 0.5522 0.8196 0.9053
No log 3.5 182 0.8411 0.5573 0.8411 0.9171
No log 3.5385 184 0.8569 0.5322 0.8569 0.9257
No log 3.5769 186 0.8465 0.5222 0.8465 0.9201
No log 3.6154 188 0.8484 0.4993 0.8484 0.9211
No log 3.6538 190 0.8531 0.4991 0.8531 0.9236
No log 3.6923 192 0.8143 0.5519 0.8143 0.9024
No log 3.7308 194 0.7946 0.6463 0.7946 0.8914
No log 3.7692 196 0.7584 0.6542 0.7584 0.8709
No log 3.8077 198 0.7762 0.6731 0.7762 0.8810
No log 3.8462 200 0.8372 0.6392 0.8372 0.9150
No log 3.8846 202 0.9393 0.6142 0.9393 0.9692
No log 3.9231 204 0.8660 0.5887 0.8660 0.9306
No log 3.9615 206 0.7202 0.6231 0.7202 0.8486
No log 4.0 208 0.7081 0.6696 0.7081 0.8415
No log 4.0385 210 0.7804 0.6772 0.7804 0.8834
No log 4.0769 212 0.9040 0.6168 0.9040 0.9508
No log 4.1154 214 0.9732 0.6124 0.9732 0.9865
No log 4.1538 216 0.9833 0.6206 0.9833 0.9916
No log 4.1923 218 0.8742 0.6256 0.8742 0.9350
No log 4.2308 220 0.8470 0.6462 0.8470 0.9203
No log 4.2692 222 0.7964 0.6855 0.7964 0.8924
No log 4.3077 224 0.7755 0.6554 0.7755 0.8806
No log 4.3462 226 0.8283 0.5759 0.8283 0.9101
No log 4.3846 228 0.8709 0.5539 0.8709 0.9332
No log 4.4231 230 0.9137 0.6110 0.9137 0.9559
No log 4.4615 232 1.0296 0.5786 1.0296 1.0147
No log 4.5 234 1.0284 0.5998 1.0284 1.0141
No log 4.5385 236 1.0106 0.5753 1.0106 1.0053
No log 4.5769 238 0.9101 0.6094 0.9101 0.9540
No log 4.6154 240 0.8634 0.6313 0.8634 0.9292
No log 4.6538 242 0.7814 0.6714 0.7814 0.8840
No log 4.6923 244 0.7375 0.6819 0.7375 0.8588
No log 4.7308 246 0.7409 0.6646 0.7409 0.8608
No log 4.7692 248 0.8688 0.6380 0.8688 0.9321
No log 4.8077 250 1.0785 0.5458 1.0785 1.0385
No log 4.8462 252 1.0282 0.5456 1.0282 1.0140
No log 4.8846 254 1.0800 0.5400 1.0800 1.0392
No log 4.9231 256 1.0383 0.5433 1.0383 1.0190
No log 4.9615 258 1.0182 0.5650 1.0182 1.0091
No log 5.0 260 0.9058 0.6162 0.9058 0.9517
No log 5.0385 262 0.9067 0.6119 0.9067 0.9522
No log 5.0769 264 1.1238 0.5246 1.1238 1.0601
No log 5.1154 266 1.2325 0.5056 1.2325 1.1102
No log 5.1538 268 1.1393 0.5276 1.1393 1.0674
No log 5.1923 270 1.1389 0.5597 1.1389 1.0672
No log 5.2308 272 1.1107 0.5752 1.1107 1.0539
No log 5.2692 274 1.1340 0.5816 1.1340 1.0649
No log 5.3077 276 1.2650 0.5482 1.2650 1.1247
No log 5.3462 278 1.4593 0.4925 1.4593 1.2080
No log 5.3846 280 1.3818 0.5246 1.3818 1.1755
No log 5.4231 282 1.0920 0.5583 1.0920 1.0450
No log 5.4615 284 0.9111 0.6207 0.9111 0.9545
No log 5.5 286 0.8870 0.6195 0.8870 0.9418
No log 5.5385 288 0.9488 0.6034 0.9488 0.9740
No log 5.5769 290 1.0982 0.5764 1.0982 1.0479
No log 5.6154 292 1.1579 0.5852 1.1579 1.0761
No log 5.6538 294 1.1044 0.5852 1.1044 1.0509
No log 5.6923 296 1.1156 0.5840 1.1156 1.0562
No log 5.7308 298 1.1935 0.5586 1.1936 1.0925
No log 5.7692 300 1.2443 0.5145 1.2443 1.1155
No log 5.8077 302 1.1932 0.5078 1.1932 1.0924
No log 5.8462 304 1.0937 0.5529 1.0937 1.0458
No log 5.8846 306 1.0111 0.5694 1.0111 1.0055
No log 5.9231 308 0.9505 0.5778 0.9505 0.9749
No log 5.9615 310 0.8219 0.5872 0.8219 0.9066
No log 6.0 312 0.7599 0.6228 0.7599 0.8717
No log 6.0385 314 0.8002 0.6009 0.8002 0.8946
No log 6.0769 316 0.8954 0.5912 0.8954 0.9462
No log 6.1154 318 1.0182 0.5439 1.0182 1.0091
No log 6.1538 320 0.9138 0.5911 0.9138 0.9559
No log 6.1923 322 0.8677 0.6128 0.8677 0.9315
No log 6.2308 324 0.9021 0.6098 0.9021 0.9498
No log 6.2692 326 0.8868 0.6102 0.8868 0.9417
No log 6.3077 328 0.9285 0.6143 0.9285 0.9636
No log 6.3462 330 0.9367 0.5962 0.9367 0.9678
No log 6.3846 332 0.9550 0.5779 0.9550 0.9773
No log 6.4231 334 0.8964 0.6069 0.8964 0.9468
No log 6.4615 336 0.8257 0.6316 0.8257 0.9087
No log 6.5 338 0.7985 0.6304 0.7985 0.8936
No log 6.5385 340 0.8332 0.6297 0.8332 0.9128
No log 6.5769 342 0.8921 0.6121 0.8921 0.9445
No log 6.6154 344 0.9498 0.6029 0.9498 0.9746
No log 6.6538 346 0.9562 0.6128 0.9562 0.9779
No log 6.6923 348 1.0278 0.6229 1.0278 1.0138
No log 6.7308 350 0.9829 0.5729 0.9829 0.9914
No log 6.7692 352 0.9396 0.5795 0.9396 0.9693
No log 6.8077 354 0.8571 0.6105 0.8571 0.9258
No log 6.8462 356 0.8612 0.6191 0.8612 0.9280
No log 6.8846 358 1.0068 0.5781 1.0068 1.0034
No log 6.9231 360 1.2033 0.5478 1.2033 1.0969
No log 6.9615 362 1.2253 0.5675 1.2253 1.1069
No log 7.0 364 1.1417 0.5817 1.1417 1.0685
No log 7.0385 366 0.9966 0.6286 0.9966 0.9983
No log 7.0769 368 0.8527 0.6172 0.8527 0.9234
No log 7.1154 370 0.8375 0.6063 0.8375 0.9152
No log 7.1538 372 0.8682 0.6286 0.8682 0.9318
No log 7.1923 374 1.0529 0.5858 1.0529 1.0261
No log 7.2308 376 1.2010 0.5258 1.2010 1.0959
No log 7.2692 378 1.1668 0.5383 1.1668 1.0802
No log 7.3077 380 1.0524 0.5306 1.0524 1.0259
No log 7.3462 382 0.9512 0.5769 0.9512 0.9753
No log 7.3846 384 0.9094 0.5875 0.9094 0.9536
No log 7.4231 386 1.0159 0.5776 1.0159 1.0079
No log 7.4615 388 1.1280 0.5638 1.1280 1.0621
No log 7.5 390 1.1369 0.5684 1.1369 1.0663
No log 7.5385 392 1.0540 0.5867 1.0540 1.0266
No log 7.5769 394 0.8602 0.6186 0.8602 0.9275
No log 7.6154 396 0.7581 0.6156 0.7581 0.8707
No log 7.6538 398 0.7673 0.6025 0.7673 0.8760
No log 7.6923 400 0.8006 0.6400 0.8006 0.8948
No log 7.7308 402 0.8648 0.6316 0.8648 0.9300
No log 7.7692 404 0.8691 0.6157 0.8691 0.9323
No log 7.8077 406 0.8431 0.6041 0.8431 0.9182
No log 7.8462 408 0.8646 0.6164 0.8646 0.9298
No log 7.8846 410 0.9183 0.6295 0.9183 0.9583
No log 7.9231 412 0.9344 0.6225 0.9344 0.9666
No log 7.9615 414 0.9049 0.6202 0.9049 0.9513
No log 8.0 416 0.8442 0.6522 0.8442 0.9188
No log 8.0385 418 0.7946 0.6517 0.7946 0.8914
No log 8.0769 420 0.7933 0.6481 0.7933 0.8907
No log 8.1154 422 0.8078 0.6498 0.8078 0.8988
No log 8.1538 424 0.8715 0.6559 0.8715 0.9335
No log 8.1923 426 1.0636 0.6344 1.0636 1.0313
No log 8.2308 428 1.2593 0.5761 1.2593 1.1222
No log 8.2692 430 1.2394 0.5772 1.2394 1.1133
No log 8.3077 432 1.0941 0.5785 1.0941 1.0460
No log 8.3462 434 0.8905 0.6203 0.8905 0.9437
No log 8.3846 436 0.8080 0.6313 0.8080 0.8989
No log 8.4231 438 0.8032 0.6385 0.8032 0.8962
No log 8.4615 440 0.8617 0.6255 0.8617 0.9283
No log 8.5 442 0.9989 0.5985 0.9989 0.9994
No log 8.5385 444 1.0637 0.6031 1.0637 1.0313
No log 8.5769 446 1.0483 0.6003 1.0483 1.0239
No log 8.6154 448 1.0509 0.5924 1.0509 1.0251
No log 8.6538 450 1.0928 0.5728 1.0928 1.0454
No log 8.6923 452 1.0676 0.5672 1.0676 1.0332
No log 8.7308 454 1.0860 0.5368 1.0860 1.0421
No log 8.7692 456 1.1605 0.5368 1.1605 1.0772
No log 8.8077 458 1.3696 0.4745 1.3696 1.1703
No log 8.8462 460 1.4262 0.4851 1.4262 1.1942
No log 8.8846 462 1.2857 0.5402 1.2857 1.1339
No log 8.9231 464 1.1939 0.5665 1.1939 1.0926
No log 8.9615 466 1.1862 0.5580 1.1862 1.0891
No log 9.0 468 1.2342 0.5666 1.2342 1.1110
No log 9.0385 470 1.2930 0.5542 1.2930 1.1371
No log 9.0769 472 1.3989 0.4954 1.3989 1.1828
No log 9.1154 474 1.3653 0.4746 1.3653 1.1685
No log 9.1538 476 1.2061 0.5359 1.2061 1.0982
No log 9.1923 478 1.0327 0.5798 1.0327 1.0162
No log 9.2308 480 0.9887 0.6177 0.9887 0.9944
No log 9.2692 482 0.9891 0.6359 0.9891 0.9945
No log 9.3077 484 1.0127 0.6327 1.0127 1.0063
No log 9.3462 486 1.0364 0.6137 1.0364 1.0180
No log 9.3846 488 1.1265 0.5403 1.1265 1.0613
No log 9.4231 490 1.0958 0.5583 1.0958 1.0468
No log 9.4615 492 0.9673 0.5221 0.9673 0.9835
No log 9.5 494 0.9208 0.5661 0.9208 0.9596
No log 9.5385 496 0.8924 0.5741 0.8924 0.9447
No log 9.5769 498 0.8981 0.5462 0.8981 0.9477
0.4082 9.6154 500 0.9095 0.5404 0.9095 0.9537
0.4082 9.6538 502 0.8979 0.5875 0.8979 0.9476
0.4082 9.6923 504 0.9436 0.5812 0.9436 0.9714
0.4082 9.7308 506 1.0550 0.5622 1.0550 1.0271
0.4082 9.7692 508 1.2504 0.5258 1.2504 1.1182
0.4082 9.8077 510 1.2622 0.5008 1.2622 1.1235
0.4082 9.8462 512 1.1213 0.5226 1.1213 1.0589
0.4082 9.8846 514 0.9580 0.5640 0.9580 0.9788
0.4082 9.9231 516 0.8430 0.5935 0.8430 0.9181
0.4082 9.9615 518 0.8141 0.5982 0.8141 0.9023
0.4082 10.0 520 0.8478 0.6067 0.8478 0.9208
0.4082 10.0385 522 0.9375 0.5508 0.9375 0.9683
0.4082 10.0769 524 0.9762 0.5828 0.9762 0.9880
0.4082 10.1154 526 1.0339 0.5777 1.0339 1.0168
0.4082 10.1538 528 1.0752 0.5846 1.0751 1.0369
0.4082 10.1923 530 0.9774 0.6139 0.9774 0.9886
0.4082 10.2308 532 0.9090 0.6451 0.9090 0.9534
0.4082 10.2692 534 0.9173 0.6265 0.9173 0.9578
0.4082 10.3077 536 0.9770 0.5312 0.9770 0.9884
0.4082 10.3462 538 1.0792 0.5058 1.0792 1.0389
0.4082 10.3846 540 1.2196 0.4503 1.2196 1.1043
0.4082 10.4231 542 1.2209 0.4451 1.2209 1.1049
0.4082 10.4615 544 1.1151 0.4725 1.1151 1.0560

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/ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run1_AugV5_k10_task1_organization

Finetuned
(4040)
this model