ArabicNewSplits7_FineTuningAraBERT_run2_AugV5_k7_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: 0.7036
  • Qwk: 0.0879
  • Mse: 0.7036
  • Rmse: 0.8388

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 0.0952 2 3.6784 -0.0068 3.6784 1.9179
No log 0.1905 4 2.0918 0.0737 2.0918 1.4463
No log 0.2857 6 2.2968 0.0076 2.2968 1.5155
No log 0.3810 8 1.4426 0.0047 1.4426 1.2011
No log 0.4762 10 1.0063 -0.0936 1.0063 1.0031
No log 0.5714 12 1.0118 -0.0606 1.0118 1.0059
No log 0.6667 14 0.9097 0.0207 0.9097 0.9538
No log 0.7619 16 0.7505 0.0759 0.7505 0.8663
No log 0.8571 18 0.7451 0.0807 0.7451 0.8632
No log 0.9524 20 1.0125 -0.0638 1.0125 1.0062
No log 1.0476 22 1.2395 -0.0744 1.2395 1.1133
No log 1.1429 24 1.4883 0.0 1.4883 1.2200
No log 1.2381 26 1.1733 -0.0490 1.1733 1.0832
No log 1.3333 28 0.9321 -0.0961 0.9321 0.9654
No log 1.4286 30 0.8129 -0.1239 0.8129 0.9016
No log 1.5238 32 0.8522 0.0043 0.8522 0.9231
No log 1.6190 34 0.8500 -0.0766 0.8500 0.9220
No log 1.7143 36 0.9093 -0.0916 0.9093 0.9536
No log 1.8095 38 1.1113 -0.0479 1.1113 1.0542
No log 1.9048 40 1.3176 -0.0247 1.3176 1.1479
No log 2.0 42 1.8691 0.0 1.8691 1.3671
No log 2.0952 44 2.1069 -0.0015 2.1069 1.4515
No log 2.1905 46 1.7412 0.0 1.7412 1.3195
No log 2.2857 48 1.2256 0.0 1.2256 1.1071
No log 2.3810 50 0.8572 -0.1253 0.8572 0.9259
No log 2.4762 52 0.7580 -0.1223 0.7580 0.8706
No log 2.5714 54 0.7225 -0.0035 0.7225 0.8500
No log 2.6667 56 0.8083 0.0129 0.8083 0.8991
No log 2.7619 58 1.2583 0.0746 1.2583 1.1217
No log 2.8571 60 1.2926 0.0115 1.2926 1.1369
No log 2.9524 62 1.1273 0.0878 1.1273 1.0617
No log 3.0476 64 1.1606 -0.0361 1.1606 1.0773
No log 3.1429 66 0.7909 -0.0675 0.7909 0.8893
No log 3.2381 68 0.7315 -0.0069 0.7315 0.8553
No log 3.3333 70 0.9204 -0.0526 0.9204 0.9594
No log 3.4286 72 1.3156 -0.0207 1.3156 1.1470
No log 3.5238 74 1.2269 -0.0207 1.2269 1.1076
No log 3.6190 76 0.8623 0.0676 0.8623 0.9286
No log 3.7143 78 0.7682 0.0374 0.7682 0.8765
No log 3.8095 80 0.8102 0.0628 0.8102 0.9001
No log 3.9048 82 0.9143 0.0016 0.9143 0.9562
No log 4.0 84 0.8293 0.0956 0.8293 0.9106
No log 4.0952 86 0.8797 0.0805 0.8797 0.9379
No log 4.1905 88 1.5015 -0.0113 1.5015 1.2254
No log 4.2857 90 1.4535 0.0179 1.4535 1.2056
No log 4.3810 92 0.9694 -0.0349 0.9694 0.9846
No log 4.4762 94 0.8759 0.0441 0.8759 0.9359
No log 4.5714 96 0.9118 -0.0128 0.9118 0.9549
No log 4.6667 98 1.1852 0.0950 1.1852 1.0887
No log 4.7619 100 0.9421 -0.0939 0.9421 0.9706
No log 4.8571 102 0.9630 0.1361 0.9630 0.9813
No log 4.9524 104 0.8939 -0.0569 0.8939 0.9455
No log 5.0476 106 1.4396 0.0370 1.4396 1.1998
No log 5.1429 108 1.3095 -0.0080 1.3095 1.1443
No log 5.2381 110 0.9394 -0.0828 0.9394 0.9692
No log 5.3333 112 1.0633 -0.0175 1.0633 1.0312
No log 5.4286 114 1.0540 -0.0175 1.0540 1.0266
No log 5.5238 116 0.9231 -0.0425 0.9231 0.9608
No log 5.6190 118 0.8762 -0.0799 0.8762 0.9361
No log 5.7143 120 0.8343 0.0123 0.8343 0.9134
No log 5.8095 122 0.8235 0.0538 0.8235 0.9075
No log 5.9048 124 0.9275 0.0293 0.9275 0.9631
No log 6.0 126 0.7888 0.0538 0.7888 0.8882
No log 6.0952 128 0.8064 0.1393 0.8064 0.8980
No log 6.1905 130 0.7925 0.0985 0.7925 0.8902
No log 6.2857 132 0.8138 0.0633 0.8138 0.9021
No log 6.3810 134 0.7916 0.0798 0.7916 0.8897
No log 6.4762 136 0.8980 0.0377 0.8980 0.9476
No log 6.5714 138 0.8812 0.0741 0.8812 0.9387
No log 6.6667 140 0.7706 0.1287 0.7706 0.8779
No log 6.7619 142 0.7749 0.1347 0.7749 0.8803
No log 6.8571 144 0.8212 0.1379 0.8212 0.9062
No log 6.9524 146 0.8853 -0.0187 0.8853 0.9409
No log 7.0476 148 0.9283 -0.0904 0.9283 0.9635
No log 7.1429 150 0.8647 -0.0465 0.8647 0.9299
No log 7.2381 152 0.7793 0.0869 0.7793 0.8828
No log 7.3333 154 0.8856 0.0711 0.8856 0.9411
No log 7.4286 156 0.8809 0.0346 0.8809 0.9386
No log 7.5238 158 0.7140 0.1244 0.7140 0.8450
No log 7.6190 160 0.7433 0.1030 0.7433 0.8622
No log 7.7143 162 0.7357 0.1501 0.7357 0.8578
No log 7.8095 164 0.7423 0.0557 0.7423 0.8616
No log 7.9048 166 0.7486 0.0879 0.7486 0.8652
No log 8.0 168 1.0417 0.0428 1.0417 1.0206
No log 8.0952 170 1.1662 -0.0065 1.1662 1.0799
No log 8.1905 172 0.8146 0.0600 0.8146 0.9026
No log 8.2857 174 0.8241 0.0240 0.8241 0.9078
No log 8.3810 176 0.9243 0.0789 0.9243 0.9614
No log 8.4762 178 0.7784 0.0141 0.7784 0.8822
No log 8.5714 180 0.7915 0.0639 0.7915 0.8897
No log 8.6667 182 1.0052 0.0815 1.0052 1.0026
No log 8.7619 184 0.9041 -0.0008 0.9041 0.9508
No log 8.8571 186 0.7443 0.0976 0.7443 0.8627
No log 8.9524 188 0.7310 0.1525 0.7310 0.8550
No log 9.0476 190 0.7565 0.0690 0.7565 0.8698
No log 9.1429 192 0.8668 0.0016 0.8668 0.9310
No log 9.2381 194 0.7970 0.0490 0.7970 0.8928
No log 9.3333 196 0.7201 0.1538 0.7201 0.8486
No log 9.4286 198 0.7952 0.1128 0.7952 0.8918
No log 9.5238 200 0.7634 0.1928 0.7634 0.8737
No log 9.6190 202 0.7533 0.0600 0.7533 0.8680
No log 9.7143 204 0.9672 0.1225 0.9672 0.9835
No log 9.8095 206 0.8921 0.0293 0.8921 0.9445
No log 9.9048 208 0.7824 0.0690 0.7824 0.8845
No log 10.0 210 0.7589 0.0922 0.7589 0.8711
No log 10.0952 212 0.7716 0.0355 0.7716 0.8784
No log 10.1905 214 0.9310 -0.0097 0.9310 0.9649
No log 10.2857 216 1.3196 -0.0129 1.3196 1.1487
No log 10.3810 218 1.3604 0.0359 1.3604 1.1664
No log 10.4762 220 1.0629 -0.0618 1.0629 1.0310
No log 10.5714 222 0.8274 0.0690 0.8274 0.9096
No log 10.6667 224 0.8250 0.0776 0.8250 0.9083
No log 10.7619 226 0.9956 -0.0118 0.9956 0.9978
No log 10.8571 228 1.3141 0.0148 1.3141 1.1464
No log 10.9524 230 1.1967 0.0252 1.1967 1.0939
No log 11.0476 232 0.8229 0.0362 0.8229 0.9072
No log 11.1429 234 0.7217 -0.0113 0.7217 0.8496
No log 11.2381 236 0.7276 -0.0228 0.7276 0.8530
No log 11.3333 238 0.9298 0.1579 0.9298 0.9642
No log 11.4286 240 1.0608 0.2069 1.0608 1.0299
No log 11.5238 242 0.8560 0.1149 0.8560 0.9252
No log 11.6190 244 0.7747 0.0152 0.7747 0.8802
No log 11.7143 246 0.8758 0.0438 0.8758 0.9358
No log 11.8095 248 0.8935 0.0438 0.8935 0.9452
No log 11.9048 250 0.9035 0.0040 0.9035 0.9505
No log 12.0 252 0.8144 0.0323 0.8144 0.9024
No log 12.0952 254 0.8054 0.0776 0.8054 0.8974
No log 12.1905 256 0.9311 -0.0033 0.9311 0.9649
No log 12.2857 258 0.9944 0.0642 0.9944 0.9972
No log 12.3810 260 0.8533 -0.0425 0.8533 0.9237
No log 12.4762 262 0.7287 0.0296 0.7287 0.8536
No log 12.5714 264 0.7065 -0.0179 0.7065 0.8405
No log 12.6667 266 0.7171 0.1202 0.7171 0.8468
No log 12.7619 268 0.7150 0.0723 0.7150 0.8456
No log 12.8571 270 0.7819 0.0071 0.7819 0.8842
No log 12.9524 272 0.8487 0.0377 0.8487 0.9213
No log 13.0476 274 0.9962 0.1042 0.9962 0.9981
No log 13.1429 276 0.8510 0.0346 0.8510 0.9225
No log 13.2381 278 0.6936 0.0303 0.6936 0.8328
No log 13.3333 280 0.6872 0.1081 0.6872 0.8290
No log 13.4286 282 0.6675 -0.0179 0.6675 0.8170
No log 13.5238 284 0.7149 0.1047 0.7149 0.8455
No log 13.6190 286 0.8534 0.1453 0.8534 0.9238
No log 13.7143 288 0.8407 0.0711 0.8407 0.9169
No log 13.8095 290 0.7545 0.0956 0.7545 0.8686
No log 13.9048 292 0.7502 0.0562 0.7502 0.8661
No log 14.0 294 0.7082 0.0723 0.7082 0.8415
No log 14.0952 296 0.7578 0.0600 0.7578 0.8705
No log 14.1905 298 0.8057 0.0040 0.8057 0.8976
No log 14.2857 300 0.8296 0.0377 0.8296 0.9108
No log 14.3810 302 0.7516 0.0959 0.7516 0.8670
No log 14.4762 304 0.7390 0.0600 0.7390 0.8596
No log 14.5714 306 0.7054 0.0791 0.7054 0.8399
No log 14.6667 308 0.6988 0.0528 0.6988 0.8359
No log 14.7619 310 0.6608 -0.0152 0.6608 0.8129
No log 14.8571 312 0.7079 0.1627 0.7079 0.8414
No log 14.9524 314 0.7476 0.1627 0.7476 0.8647
No log 15.0476 316 0.7127 0.1146 0.7127 0.8442
No log 15.1429 318 0.7213 0.0528 0.7213 0.8493
No log 15.2381 320 0.7909 0.0249 0.7909 0.8894
No log 15.3333 322 0.7490 0.0985 0.7490 0.8654
No log 15.4286 324 0.7433 0.1048 0.7433 0.8622
No log 15.5238 326 0.7744 0.0876 0.7744 0.8800
No log 15.6190 328 0.7312 0.0600 0.7312 0.8551
No log 15.7143 330 0.6998 0.0821 0.6998 0.8365
No log 15.8095 332 0.7120 0.0214 0.7120 0.8438
No log 15.9048 334 0.7160 0.0214 0.7160 0.8462
No log 16.0 336 0.7221 0.0214 0.7221 0.8498
No log 16.0952 338 0.8298 0.0711 0.8298 0.9109
No log 16.1905 340 0.9326 0.1705 0.9326 0.9657
No log 16.2857 342 0.9326 0.1705 0.9326 0.9657
No log 16.3810 344 0.8817 0.0873 0.8817 0.9390
No log 16.4762 346 0.8128 0.0362 0.8128 0.9015
No log 16.5714 348 0.7784 0.0923 0.7784 0.8823
No log 16.6667 350 0.7641 0.1050 0.7641 0.8741
No log 16.7619 352 0.7969 0.1386 0.7969 0.8927
No log 16.8571 354 0.7585 0.1434 0.7585 0.8709
No log 16.9524 356 0.7131 0.1196 0.7131 0.8444
No log 17.0476 358 0.7275 0.0123 0.7275 0.8529
No log 17.1429 360 0.7281 0.0071 0.7281 0.8533
No log 17.2381 362 0.7147 0.0549 0.7147 0.8454
No log 17.3333 364 0.7216 0.0600 0.7216 0.8495
No log 17.4286 366 0.7488 -0.0336 0.7488 0.8653
No log 17.5238 368 0.7850 -0.0355 0.7850 0.8860
No log 17.6190 370 0.7326 0.0600 0.7326 0.8559
No log 17.7143 372 0.6997 0.1096 0.6997 0.8365
No log 17.8095 374 0.7456 0.0999 0.7456 0.8635
No log 17.9048 376 0.7970 0.0017 0.7970 0.8928
No log 18.0 378 0.8264 0.0316 0.8264 0.9090
No log 18.0952 380 0.7175 0.0768 0.7175 0.8470
No log 18.1905 382 0.7067 0.0926 0.7067 0.8406
No log 18.2857 384 0.7029 0.0926 0.7029 0.8384
No log 18.3810 386 0.7100 0.0723 0.7100 0.8426
No log 18.4762 388 0.8035 0.0711 0.8035 0.8964
No log 18.5714 390 0.7901 0.0711 0.7901 0.8889
No log 18.6667 392 0.6870 0.0680 0.6870 0.8289
No log 18.7619 394 0.6727 0.1474 0.6727 0.8202
No log 18.8571 396 0.6672 0.0970 0.6672 0.8168
No log 18.9524 398 0.7027 0.1047 0.7027 0.8382
No log 19.0476 400 0.8852 0.0909 0.8852 0.9409
No log 19.1429 402 0.8774 0.0909 0.8774 0.9367
No log 19.2381 404 0.7221 0.0071 0.7221 0.8498
No log 19.3333 406 0.6709 0.0513 0.6709 0.8191
No log 19.4286 408 0.6927 0.0585 0.6927 0.8323
No log 19.5238 410 0.6721 0.1024 0.6721 0.8198
No log 19.6190 412 0.6869 0.1202 0.6869 0.8288
No log 19.7143 414 0.7207 0.1565 0.7207 0.8489
No log 19.8095 416 0.7138 0.0768 0.7138 0.8448
No log 19.9048 418 0.6887 0.1433 0.6887 0.8299
No log 20.0 420 0.7020 0.0970 0.7020 0.8378
No log 20.0952 422 0.7071 0.0496 0.7071 0.8409
No log 20.1905 424 0.7206 0.0814 0.7206 0.8489
No log 20.2857 426 0.9089 0.1231 0.9089 0.9534
No log 20.3810 428 1.0438 -0.0084 1.0438 1.0217
No log 20.4762 430 0.9830 0.0260 0.9830 0.9915
No log 20.5714 432 0.8156 -0.0425 0.8156 0.9031
No log 20.6667 434 0.7629 0.0095 0.7629 0.8735
No log 20.7619 436 0.7493 -0.0295 0.7493 0.8656
No log 20.8571 438 0.8264 0.1065 0.8264 0.9090
No log 20.9524 440 0.9007 0.1579 0.9007 0.9491
No log 21.0476 442 0.8296 0.1106 0.8296 0.9108
No log 21.1429 444 0.7692 0.0956 0.7692 0.8771
No log 21.2381 446 0.7855 0.1286 0.7855 0.8863
No log 21.3333 448 0.8644 0.0545 0.8644 0.9297
No log 21.4286 450 0.9508 -0.0049 0.9508 0.9751
No log 21.5238 452 0.8621 0.0772 0.8621 0.9285
No log 21.6190 454 0.8447 0.0984 0.8447 0.9191
No log 21.7143 456 0.8716 0.1152 0.8716 0.9336
No log 21.8095 458 0.7554 0.1047 0.7554 0.8691
No log 21.9048 460 0.6931 0.0759 0.6931 0.8325
No log 22.0 462 0.6868 0.0857 0.6868 0.8288
No log 22.0952 464 0.7073 0.0791 0.7073 0.8410
No log 22.1905 466 0.7379 0.1048 0.7379 0.8590
No log 22.2857 468 0.8232 0.1239 0.8232 0.9073
No log 22.3810 470 0.8125 0.1286 0.8125 0.9014
No log 22.4762 472 0.7394 0.1047 0.7394 0.8599
No log 22.5714 474 0.6963 0.1202 0.6963 0.8345
No log 22.6667 476 0.6793 0.0374 0.6793 0.8242
No log 22.7619 478 0.6763 0.1021 0.6763 0.8224
No log 22.8571 480 0.6728 0.0909 0.6728 0.8202
No log 22.9524 482 0.7066 0.1047 0.7066 0.8406
No log 23.0476 484 0.7209 0.1047 0.7209 0.8491
No log 23.1429 486 0.7595 0.1047 0.7595 0.8715
No log 23.2381 488 0.7584 0.1047 0.7584 0.8709
No log 23.3333 490 0.7008 0.1047 0.7008 0.8371
No log 23.4286 492 0.6631 0.2030 0.6631 0.8143
No log 23.5238 494 0.7192 0.0610 0.7192 0.8481
No log 23.6190 496 0.7170 0.0148 0.7170 0.8468
No log 23.7143 498 0.6419 0.2030 0.6419 0.8012
0.2982 23.8095 500 0.7027 0.1047 0.7027 0.8383
0.2982 23.9048 502 0.7465 0.1449 0.7465 0.8640
0.2982 24.0 504 0.7495 0.1449 0.7495 0.8657
0.2982 24.0952 506 0.7345 0.1449 0.7345 0.8570
0.2982 24.1905 508 0.7066 0.1047 0.7066 0.8406
0.2982 24.2857 510 0.6995 0.1565 0.6995 0.8364
0.2982 24.3810 512 0.6588 0.1259 0.6588 0.8117
0.2982 24.4762 514 0.6621 0.1024 0.6621 0.8137
0.2982 24.5714 516 0.6622 0.0479 0.6622 0.8137
0.2982 24.6667 518 0.6689 0.1318 0.6689 0.8179
0.2982 24.7619 520 0.7148 0.1565 0.7148 0.8455
0.2982 24.8571 522 0.7445 0.1506 0.7445 0.8628
0.2982 24.9524 524 0.7199 0.1565 0.7199 0.8485
0.2982 25.0476 526 0.7033 0.1565 0.7033 0.8387
0.2982 25.1429 528 0.7287 0.1565 0.7287 0.8536
0.2982 25.2381 530 0.7356 0.1440 0.7356 0.8577
0.2982 25.3333 532 0.6855 0.2009 0.6855 0.8279
0.2982 25.4286 534 0.7315 0.1440 0.7315 0.8553
0.2982 25.5238 536 0.8395 0.1316 0.8395 0.9163
0.2982 25.6190 538 0.8286 0.1360 0.8286 0.9103
0.2982 25.7143 540 0.7846 0.1196 0.7846 0.8858
0.2982 25.8095 542 0.7645 0.0909 0.7645 0.8743
0.2982 25.9048 544 0.7185 0.0999 0.7185 0.8477
0.2982 26.0 546 0.7614 0.0476 0.7614 0.8726
0.2982 26.0952 548 0.7887 0.1243 0.7887 0.8881
0.2982 26.1905 550 0.7640 0.0476 0.7640 0.8741
0.2982 26.2857 552 0.7575 0.0476 0.7575 0.8703
0.2982 26.3810 554 0.7012 0.1047 0.7012 0.8374
0.2982 26.4762 556 0.6985 0.1047 0.6985 0.8358
0.2982 26.5714 558 0.7036 0.0879 0.7036 0.8388

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
0
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_run2_AugV5_k7_task3_organization

Finetuned
(2729)
this model