ArabicNewSplits7_FineTuningAraBERT_run3_AugV5_k20_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: 0.8093
  • Qwk: -0.0612
  • Mse: 0.8093
  • Rmse: 0.8996

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 0.0377 2 3.5098 -0.0047 3.5098 1.8734
No log 0.0755 4 1.9733 0.0672 1.9733 1.4047
No log 0.1132 6 2.0754 0.0500 2.0754 1.4406
No log 0.1509 8 1.5131 -0.0190 1.5131 1.2301
No log 0.1887 10 1.1337 -0.0253 1.1337 1.0648
No log 0.2264 12 0.8506 0.0549 0.8506 0.9223
No log 0.2642 14 0.7762 0.0375 0.7762 0.8810
No log 0.3019 16 1.2061 -0.0049 1.2061 1.0982
No log 0.3396 18 1.2731 0.0176 1.2731 1.1283
No log 0.3774 20 0.9313 0.0089 0.9313 0.9651
No log 0.4151 22 0.8317 0.1150 0.8317 0.9120
No log 0.4528 24 0.8421 0.0207 0.8421 0.9177
No log 0.4906 26 0.7490 -0.0188 0.7490 0.8655
No log 0.5283 28 0.7218 -0.0035 0.7218 0.8496
No log 0.5660 30 0.7002 0.0 0.7002 0.8368
No log 0.6038 32 0.8668 0.0486 0.8668 0.9310
No log 0.6415 34 0.9471 0.0378 0.9471 0.9732
No log 0.6792 36 1.0633 0.0045 1.0633 1.0312
No log 0.7170 38 0.8965 -0.0513 0.8965 0.9468
No log 0.7547 40 0.7568 -0.0774 0.7568 0.8700
No log 0.7925 42 0.7810 0.0229 0.7810 0.8837
No log 0.8302 44 0.8797 0.0609 0.8797 0.9379
No log 0.8679 46 1.0421 0.0305 1.0421 1.0209
No log 0.9057 48 0.7131 0.0914 0.7131 0.8444
No log 0.9434 50 0.8819 -0.0477 0.8819 0.9391
No log 0.9811 52 0.8102 -0.2154 0.8102 0.9001
No log 1.0189 54 0.8183 0.0016 0.8183 0.9046
No log 1.0566 56 1.5303 0.0064 1.5303 1.2371
No log 1.0943 58 1.5198 0.0065 1.5198 1.2328
No log 1.1321 60 0.9645 0.0067 0.9645 0.9821
No log 1.1698 62 0.7428 -0.0551 0.7428 0.8619
No log 1.2075 64 0.8293 -0.0774 0.8293 0.9107
No log 1.2453 66 0.7594 -0.0451 0.7594 0.8714
No log 1.2830 68 0.8365 -0.1191 0.8365 0.9146
No log 1.3208 70 1.0799 -0.0435 1.0799 1.0392
No log 1.3585 72 1.0396 -0.0411 1.0396 1.0196
No log 1.3962 74 0.7765 0.0159 0.7765 0.8812
No log 1.4340 76 0.7097 0.0555 0.7097 0.8424
No log 1.4717 78 0.7198 0.0033 0.7198 0.8484
No log 1.5094 80 0.8199 -0.0477 0.8199 0.9055
No log 1.5472 82 0.8698 0.0319 0.8698 0.9327
No log 1.5849 84 1.1274 -0.0492 1.1274 1.0618
No log 1.6226 86 1.7019 -0.0215 1.7019 1.3046
No log 1.6604 88 1.2442 -0.0572 1.2442 1.1154
No log 1.6981 90 0.8972 0.0178 0.8972 0.9472
No log 1.7358 92 0.8752 0.0139 0.8752 0.9355
No log 1.7736 94 0.9386 0.0062 0.9386 0.9688
No log 1.8113 96 0.9148 0.0113 0.9148 0.9564
No log 1.8491 98 0.8185 0.0053 0.8185 0.9047
No log 1.8868 100 0.8270 0.1094 0.8270 0.9094
No log 1.9245 102 0.9741 -0.0076 0.9741 0.9870
No log 1.9623 104 0.7763 0.0874 0.7763 0.8811
No log 2.0 106 0.7509 0.0141 0.7509 0.8665
No log 2.0377 108 0.7087 0.0768 0.7087 0.8418
No log 2.0755 110 0.9314 0.0576 0.9314 0.9651
No log 2.1132 112 1.0448 0.0666 1.0448 1.0221
No log 2.1509 114 0.7483 0.0588 0.7483 0.8650
No log 2.1887 116 0.7707 0.0637 0.7707 0.8779
No log 2.2264 118 0.9009 0.0169 0.9009 0.9492
No log 2.2642 120 0.7946 0.1379 0.7946 0.8914
No log 2.3019 122 1.3269 0.0561 1.3269 1.1519
No log 2.3396 124 2.0485 0.0335 2.0485 1.4313
No log 2.3774 126 1.5127 0.0082 1.5127 1.2299
No log 2.4151 128 0.8031 0.0611 0.8031 0.8962
No log 2.4528 130 0.7938 -0.0849 0.7938 0.8910
No log 2.4906 132 0.8324 -0.0116 0.8324 0.9124
No log 2.5283 134 0.7340 0.0918 0.7340 0.8567
No log 2.5660 136 0.8071 -0.0274 0.8071 0.8984
No log 2.6038 138 0.9486 0.1493 0.9486 0.9740
No log 2.6415 140 0.8092 0.0525 0.8092 0.8996
No log 2.6792 142 0.7226 0.0922 0.7226 0.8500
No log 2.7170 144 0.7839 -0.0385 0.7839 0.8854
No log 2.7547 146 0.7940 -0.0230 0.7940 0.8911
No log 2.7925 148 0.8326 0.0167 0.8326 0.9125
No log 2.8302 150 0.8198 0.1315 0.8198 0.9054
No log 2.8679 152 0.8327 -0.0187 0.8327 0.9125
No log 2.9057 154 0.8558 -0.0811 0.8558 0.9251
No log 2.9434 156 0.7856 0.0503 0.7856 0.8864
No log 2.9811 158 0.8408 0.0175 0.8408 0.9169
No log 3.0189 160 0.8317 0.0690 0.8317 0.9120
No log 3.0566 162 0.7562 -0.0030 0.7562 0.8696
No log 3.0943 164 0.7490 0.0033 0.7490 0.8654
No log 3.1321 166 0.7375 0.0479 0.7375 0.8588
No log 3.1698 168 0.7527 -0.0520 0.7527 0.8676
No log 3.2075 170 0.7697 -0.0204 0.7697 0.8773
No log 3.2453 172 1.0299 0.0293 1.0299 1.0149
No log 3.2830 174 0.9202 0.0538 0.9202 0.9593
No log 3.3208 176 0.8092 0.0240 0.8092 0.8996
No log 3.3585 178 0.8807 -0.0289 0.8807 0.9385
No log 3.3962 180 0.8572 0.0406 0.8572 0.9259
No log 3.4340 182 0.7659 0.1081 0.7659 0.8752
No log 3.4717 184 0.9219 0.0016 0.9219 0.9602
No log 3.5094 186 1.2183 0.0296 1.2183 1.1037
No log 3.5472 188 0.9597 -0.0532 0.9597 0.9797
No log 3.5849 190 0.7465 0.0814 0.7465 0.8640
No log 3.6226 192 0.7423 0.0454 0.7423 0.8616
No log 3.6604 194 0.8076 -0.0303 0.8076 0.8987
No log 3.6981 196 0.8893 0.0091 0.8893 0.9430
No log 3.7358 198 0.9009 0.0456 0.9009 0.9491
No log 3.7736 200 0.9070 0.0304 0.9070 0.9523
No log 3.8113 202 0.7494 0.0611 0.7494 0.8657
No log 3.8491 204 0.7885 0.0297 0.7885 0.8880
No log 3.8868 206 0.7881 0.0718 0.7881 0.8877
No log 3.9245 208 0.7420 0.1228 0.7420 0.8614
No log 3.9623 210 0.9642 -0.0194 0.9642 0.9819
No log 4.0 212 0.9299 -0.0138 0.9299 0.9643
No log 4.0377 214 0.8518 0.0871 0.8518 0.9229
No log 4.0755 216 0.8000 0.0532 0.8000 0.8944
No log 4.1132 218 0.7964 0.0545 0.7964 0.8924
No log 4.1509 220 0.7839 0.1304 0.7839 0.8854
No log 4.1887 222 0.7905 0.0976 0.7905 0.8891
No log 4.2264 224 0.8302 0.0068 0.8302 0.9112
No log 4.2642 226 1.0761 0.0046 1.0761 1.0374
No log 4.3019 228 1.0828 0.0067 1.0828 1.0406
No log 4.3396 230 0.8335 0.0041 0.8335 0.9130
No log 4.3774 232 0.8060 0.0574 0.8060 0.8978
No log 4.4151 234 0.8003 0.0985 0.8003 0.8946
No log 4.4528 236 0.9776 -0.0187 0.9776 0.9888
No log 4.4906 238 0.9213 -0.0279 0.9213 0.9598
No log 4.5283 240 0.8171 0.1199 0.8171 0.9039
No log 4.5660 242 0.9384 0.0711 0.9384 0.9687
No log 4.6038 244 0.8485 0.0953 0.8485 0.9212
No log 4.6415 246 0.7516 0.0914 0.7516 0.8670
No log 4.6792 248 0.8191 -0.2336 0.8191 0.9051
No log 4.7170 250 0.7942 -0.0499 0.7942 0.8912
No log 4.7547 252 0.8037 -0.0718 0.8037 0.8965
No log 4.7925 254 1.1981 -0.0648 1.1981 1.0946
No log 4.8302 256 1.1647 -0.0285 1.1647 1.0792
No log 4.8679 258 0.8123 -0.0718 0.8123 0.9013
No log 4.9057 260 0.8065 -0.0406 0.8065 0.8981
No log 4.9434 262 0.8355 0.0155 0.8355 0.9141
No log 4.9811 264 0.7282 -0.0551 0.7282 0.8534
No log 5.0189 266 0.6808 0.0 0.6808 0.8251
No log 5.0566 268 0.6852 0.1498 0.6852 0.8278
No log 5.0943 270 0.7816 0.1047 0.7816 0.8841
No log 5.1321 272 0.8839 0.0016 0.8839 0.9402
No log 5.1698 274 0.7991 0.1553 0.7991 0.8939
No log 5.2075 276 0.7447 0.0930 0.7447 0.8630
No log 5.2453 278 0.7299 0.0058 0.7299 0.8543
No log 5.2830 280 0.6808 0.1498 0.6808 0.8251
No log 5.3208 282 0.7160 0.1506 0.7160 0.8462
No log 5.3585 284 0.7907 0.1605 0.7907 0.8892
No log 5.3962 286 0.7155 0.1565 0.7155 0.8459
No log 5.4340 288 0.7104 0.0524 0.7104 0.8428
No log 5.4717 290 0.7318 -0.0493 0.7318 0.8555
No log 5.5094 292 0.7769 0.0639 0.7769 0.8814
No log 5.5472 294 0.8723 0.0651 0.8723 0.9340
No log 5.5849 296 0.7601 -0.0614 0.7601 0.8719
No log 5.6226 298 0.7980 -0.0195 0.7980 0.8933
No log 5.6604 300 0.7347 -0.0030 0.7347 0.8571
No log 5.6981 302 0.7435 0.1259 0.7435 0.8622
No log 5.7358 304 0.7592 0.0628 0.7592 0.8713
No log 5.7736 306 0.7359 0.1444 0.7359 0.8578
No log 5.8113 308 0.7154 -0.0065 0.7154 0.8458
No log 5.8491 310 0.7237 -0.0065 0.7237 0.8507
No log 5.8868 312 0.7487 0.0247 0.7487 0.8653
No log 5.9245 314 0.9308 0.0651 0.9308 0.9648
No log 5.9623 316 0.9391 0.0651 0.9391 0.9691
No log 6.0 318 0.8764 0.0041 0.8764 0.9362
No log 6.0377 320 0.7878 0.1249 0.7878 0.8876
No log 6.0755 322 0.7591 0.0414 0.7591 0.8713
No log 6.1132 324 0.7288 -0.0096 0.7288 0.8537
No log 6.1509 326 0.7388 0.1148 0.7388 0.8595
No log 6.1887 328 0.7952 0.1342 0.7952 0.8917
No log 6.2264 330 0.7251 0.1318 0.7251 0.8515
No log 6.2642 332 0.7357 0.1259 0.7357 0.8577
No log 6.3019 334 0.8089 0.1395 0.8089 0.8994
No log 6.3396 336 0.7702 0.0776 0.7702 0.8776
No log 6.3774 338 0.7867 -0.0029 0.7867 0.8870
No log 6.4151 340 0.8214 0.1553 0.8214 0.9063
No log 6.4528 342 0.9332 0.0676 0.9332 0.9660
No log 6.4906 344 0.8082 0.1691 0.8082 0.8990
No log 6.5283 346 0.7585 -0.0958 0.7585 0.8709
No log 6.5660 348 0.7535 -0.0473 0.7535 0.8680
No log 6.6038 350 0.7133 0.0506 0.7133 0.8446
No log 6.6415 352 0.7287 0.0506 0.7287 0.8536
No log 6.6792 354 0.8102 0.1449 0.8102 0.9001
No log 6.7170 356 0.9316 -0.0182 0.9316 0.9652
No log 6.7547 358 0.9563 -0.0583 0.9563 0.9779
No log 6.7925 360 0.8005 0.1143 0.8005 0.8947
No log 6.8302 362 0.7875 -0.1813 0.7875 0.8874
No log 6.8679 364 0.7608 -0.0902 0.7608 0.8722
No log 6.9057 366 0.7297 0.0479 0.7297 0.8542
No log 6.9434 368 0.7284 0.1828 0.7284 0.8535
No log 6.9811 370 0.8198 0.0867 0.8198 0.9054
No log 7.0189 372 0.8974 0.0207 0.8974 0.9473
No log 7.0566 374 0.7682 0.1565 0.7682 0.8765
No log 7.0943 376 0.7496 0.0528 0.7496 0.8658
No log 7.1321 378 0.7652 0.1347 0.7652 0.8748
No log 7.1698 380 0.8502 -0.0425 0.8502 0.9221
No log 7.2075 382 1.0374 -0.0236 1.0374 1.0185
No log 7.2453 384 1.1452 -0.0675 1.1452 1.0701
No log 7.2830 386 1.0057 0.0046 1.0057 1.0028
No log 7.3208 388 0.7491 0.1675 0.7491 0.8655
No log 7.3585 390 0.7029 0.1433 0.7029 0.8384
No log 7.3962 392 0.6998 0.1433 0.6998 0.8365
No log 7.4340 394 0.7577 0.0999 0.7577 0.8705
No log 7.4717 396 0.8870 0.0207 0.8870 0.9418
No log 7.5094 398 0.8894 0.0207 0.8894 0.9431
No log 7.5472 400 0.7795 0.0999 0.7795 0.8829
No log 7.5849 402 0.7507 0.1627 0.7507 0.8664
No log 7.6226 404 0.7532 0.1565 0.7532 0.8679
No log 7.6604 406 0.7979 0.1107 0.7979 0.8933
No log 7.6981 408 0.7651 0.0909 0.7651 0.8747
No log 7.7358 410 0.7927 0.0867 0.7927 0.8903
No log 7.7736 412 0.8111 0.0786 0.8111 0.9006
No log 7.8113 414 0.8483 0.0642 0.8483 0.9210
No log 7.8491 416 0.9565 -0.0211 0.9565 0.9780
No log 7.8868 418 0.9244 -0.0909 0.9244 0.9614
No log 7.9245 420 0.8289 0.0876 0.8289 0.9104
No log 7.9623 422 0.8702 0.1107 0.8702 0.9328
No log 8.0 424 0.9092 0.0182 0.9092 0.9535
No log 8.0377 426 0.8949 0.0609 0.8949 0.9460
No log 8.0755 428 0.7862 0.0236 0.7862 0.8867
No log 8.1132 430 0.7934 0.0236 0.7934 0.8908
No log 8.1509 432 0.8331 0.1329 0.8331 0.9127
No log 8.1887 434 0.8232 0.1048 0.8232 0.9073
No log 8.2264 436 0.8027 0.1095 0.8027 0.8959
No log 8.2642 438 0.8097 0.1095 0.8097 0.8998
No log 8.3019 440 0.8488 0.1047 0.8488 0.9213
No log 8.3396 442 0.8372 0.0574 0.8372 0.9150
No log 8.3774 444 0.7849 0.1311 0.7849 0.8859
No log 8.4151 446 0.7610 0.1254 0.7610 0.8723
No log 8.4528 448 0.7871 0.0588 0.7871 0.8872
No log 8.4906 450 0.7653 0.1148 0.7653 0.8748
No log 8.5283 452 0.7351 0.1202 0.7351 0.8574
No log 8.5660 454 0.7220 0.1318 0.7220 0.8497
No log 8.6038 456 0.7275 0.1379 0.7275 0.8530
No log 8.6415 458 0.7779 0.0723 0.7779 0.8820
No log 8.6792 460 0.9000 0.0377 0.9000 0.9487
No log 8.7170 462 1.0665 0.0025 1.0665 1.0327
No log 8.7547 464 1.0218 0.0107 1.0218 1.0108
No log 8.7925 466 0.9809 -0.0218 0.9809 0.9904
No log 8.8302 468 0.9192 -0.0200 0.9192 0.9587
No log 8.8679 470 0.8172 0.0909 0.8172 0.9040
No log 8.9057 472 0.7330 0.0964 0.7330 0.8562
No log 8.9434 474 0.7291 0.0964 0.7291 0.8539
No log 8.9811 476 0.7742 0.1259 0.7742 0.8799
No log 9.0189 478 0.8809 -0.0143 0.8809 0.9386
No log 9.0566 480 0.9155 -0.0143 0.9155 0.9568
No log 9.0943 482 0.9183 -0.0490 0.9183 0.9583
No log 9.1321 484 0.9506 -0.1214 0.9506 0.9750
No log 9.1698 486 0.9365 -0.1494 0.9365 0.9677
No log 9.2075 488 0.9805 -0.1861 0.9805 0.9902
No log 9.2453 490 0.9545 -0.1492 0.9545 0.9770
No log 9.2830 492 0.9301 -0.0767 0.9301 0.9644
No log 9.3208 494 0.9340 -0.1217 0.9340 0.9665
No log 9.3585 496 0.8616 0.0490 0.8616 0.9282
No log 9.3962 498 0.7591 0.0680 0.7591 0.8713
0.3061 9.4340 500 0.8453 0.0748 0.8453 0.9194
0.3061 9.4717 502 0.9621 0.0458 0.9621 0.9808
0.3061 9.5094 504 1.0963 -0.0704 1.0963 1.0470
0.3061 9.5472 506 1.0070 -0.0316 1.0070 1.0035
0.3061 9.5849 508 0.8113 0.1553 0.8113 0.9007
0.3061 9.6226 510 0.8055 0.1553 0.8055 0.8975
0.3061 9.6604 512 0.7448 0.1291 0.7448 0.8630
0.3061 9.6981 514 0.7447 0.0909 0.7447 0.8629
0.3061 9.7358 516 0.7286 0.1096 0.7286 0.8536
0.3061 9.7736 518 0.7632 0.0525 0.7632 0.8736
0.3061 9.8113 520 0.8517 0.1107 0.8517 0.9228
0.3061 9.8491 522 0.9935 -0.0359 0.9935 0.9968
0.3061 9.8868 524 1.0053 -0.0359 1.0053 1.0026
0.3061 9.9245 526 0.8480 -0.0490 0.8480 0.9208
0.3061 9.9623 528 0.7869 0.1144 0.7869 0.8871
0.3061 10.0 530 0.8026 0.1769 0.8026 0.8959
0.3061 10.0377 532 0.8022 0.1047 0.8022 0.8957
0.3061 10.0755 534 0.8549 -0.0870 0.8549 0.9246
0.3061 10.1132 536 0.9401 -0.0617 0.9401 0.9696
0.3061 10.1509 538 0.9764 0.0157 0.9764 0.9881
0.3061 10.1887 540 0.8272 -0.0351 0.8272 0.9095
0.3061 10.2264 542 0.8093 -0.0612 0.8093 0.8996

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_run3_AugV5_k20_task3_organization

Finetuned
(4204)
this model