ArabicNewSplits6_FineTuningAraBERT_run3_AugV5_k13_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: 0.9269
  • Qwk: 0.6421
  • Mse: 0.9269
  • Rmse: 0.9628

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: 10

Training results

Training Loss Epoch Step Validation Loss Qwk Mse Rmse
No log 0.0417 2 2.4618 0.0209 2.4618 1.5690
No log 0.0833 4 1.6981 0.1695 1.6981 1.3031
No log 0.125 6 1.4154 0.1779 1.4154 1.1897
No log 0.1667 8 1.4762 0.1082 1.4762 1.2150
No log 0.2083 10 1.5313 0.1826 1.5313 1.2375
No log 0.25 12 1.5920 0.3611 1.5919 1.2617
No log 0.2917 14 1.5720 0.3917 1.5720 1.2538
No log 0.3333 16 1.4767 0.3594 1.4767 1.2152
No log 0.375 18 1.3089 0.3174 1.3089 1.1441
No log 0.4167 20 1.2220 0.2737 1.2220 1.1055
No log 0.4583 22 1.1971 0.4039 1.1971 1.0941
No log 0.5 24 1.2417 0.4420 1.2417 1.1143
No log 0.5417 26 1.2569 0.4270 1.2569 1.1211
No log 0.5833 28 1.1813 0.4352 1.1813 1.0869
No log 0.625 30 1.1960 0.3978 1.1960 1.0936
No log 0.6667 32 1.2117 0.4157 1.2117 1.1008
No log 0.7083 34 1.1840 0.3451 1.1840 1.0881
No log 0.75 36 1.2104 0.3773 1.2104 1.1002
No log 0.7917 38 1.1953 0.3606 1.1953 1.0933
No log 0.8333 40 1.2142 0.2950 1.2142 1.1019
No log 0.875 42 1.2025 0.3090 1.2025 1.0966
No log 0.9167 44 1.2111 0.3619 1.2111 1.1005
No log 0.9583 46 1.2840 0.3676 1.2840 1.1331
No log 1.0 48 1.4769 0.3562 1.4769 1.2153
No log 1.0417 50 1.5730 0.3570 1.5730 1.2542
No log 1.0833 52 1.4050 0.3681 1.4050 1.1853
No log 1.125 54 1.1556 0.4099 1.1556 1.0750
No log 1.1667 56 1.0999 0.4011 1.0999 1.0488
No log 1.2083 58 1.1373 0.4548 1.1373 1.0665
No log 1.25 60 1.1829 0.4387 1.1829 1.0876
No log 1.2917 62 1.1006 0.4763 1.1006 1.0491
No log 1.3333 64 1.0552 0.4142 1.0552 1.0272
No log 1.375 66 1.0296 0.4328 1.0296 1.0147
No log 1.4167 68 1.0382 0.5090 1.0382 1.0189
No log 1.4583 70 0.9766 0.4826 0.9766 0.9882
No log 1.5 72 0.9635 0.4787 0.9635 0.9816
No log 1.5417 74 0.9811 0.5122 0.9811 0.9905
No log 1.5833 76 1.1590 0.5096 1.1590 1.0765
No log 1.625 78 1.1502 0.5592 1.1502 1.0725
No log 1.6667 80 1.0272 0.5104 1.0272 1.0135
No log 1.7083 82 0.9893 0.4773 0.9893 0.9947
No log 1.75 84 1.0180 0.5626 1.0180 1.0090
No log 1.7917 86 0.9670 0.4944 0.9670 0.9834
No log 1.8333 88 0.9261 0.5066 0.9261 0.9623
No log 1.875 90 0.9467 0.5273 0.9467 0.9730
No log 1.9167 92 1.0169 0.5199 1.0169 1.0084
No log 1.9583 94 1.0219 0.5199 1.0219 1.0109
No log 2.0 96 1.1411 0.4535 1.1411 1.0682
No log 2.0417 98 1.4137 0.4312 1.4137 1.1890
No log 2.0833 100 1.4251 0.4710 1.4251 1.1938
No log 2.125 102 1.1976 0.5146 1.1976 1.0944
No log 2.1667 104 0.9843 0.5611 0.9843 0.9921
No log 2.2083 106 0.8887 0.6032 0.8887 0.9427
No log 2.25 108 0.8605 0.6032 0.8605 0.9276
No log 2.2917 110 0.9131 0.5948 0.9131 0.9556
No log 2.3333 112 1.1651 0.5703 1.1651 1.0794
No log 2.375 114 1.2711 0.5605 1.2711 1.1274
No log 2.4167 116 1.0990 0.5998 1.0990 1.0483
No log 2.4583 118 0.9610 0.6095 0.9610 0.9803
No log 2.5 120 1.0572 0.5956 1.0572 1.0282
No log 2.5417 122 1.1787 0.5632 1.1787 1.0857
No log 2.5833 124 1.1460 0.5858 1.1460 1.0705
No log 2.625 126 1.1614 0.5885 1.1614 1.0777
No log 2.6667 128 1.4076 0.5446 1.4076 1.1864
No log 2.7083 130 1.5115 0.5261 1.5115 1.2294
No log 2.75 132 1.5567 0.5169 1.5567 1.2477
No log 2.7917 134 1.2062 0.6271 1.2062 1.0983
No log 2.8333 136 0.9158 0.6056 0.9158 0.9570
No log 2.875 138 0.9115 0.6065 0.9115 0.9547
No log 2.9167 140 1.0425 0.6155 1.0425 1.0210
No log 2.9583 142 1.0130 0.6135 1.0130 1.0065
No log 3.0 144 0.8879 0.5899 0.8879 0.9423
No log 3.0417 146 0.8085 0.6360 0.8085 0.8992
No log 3.0833 148 0.7864 0.6351 0.7864 0.8868
No log 3.125 150 0.7729 0.6547 0.7729 0.8791
No log 3.1667 152 0.8336 0.6194 0.8336 0.9130
No log 3.2083 154 1.0942 0.6124 1.0942 1.0460
No log 3.25 156 1.1374 0.6033 1.1374 1.0665
No log 3.2917 158 1.1271 0.5884 1.1271 1.0617
No log 3.3333 160 0.9810 0.5880 0.9810 0.9904
No log 3.375 162 0.9278 0.6043 0.9278 0.9632
No log 3.4167 164 1.0002 0.6345 1.0002 1.0001
No log 3.4583 166 1.0527 0.6375 1.0527 1.0260
No log 3.5 168 0.9230 0.6437 0.9230 0.9607
No log 3.5417 170 0.9248 0.6055 0.9248 0.9617
No log 3.5833 172 0.9252 0.6175 0.9252 0.9619
No log 3.625 174 0.9129 0.6303 0.9129 0.9554
No log 3.6667 176 1.0579 0.6054 1.0579 1.0285
No log 3.7083 178 1.2384 0.5586 1.2384 1.1128
No log 3.75 180 1.1114 0.6092 1.1114 1.0542
No log 3.7917 182 1.0299 0.5856 1.0299 1.0148
No log 3.8333 184 0.9176 0.6213 0.9176 0.9579
No log 3.875 186 0.9111 0.6287 0.9111 0.9545
No log 3.9167 188 1.1012 0.6003 1.1012 1.0494
No log 3.9583 190 1.4631 0.5641 1.4631 1.2096
No log 4.0 192 1.6035 0.5360 1.6035 1.2663
No log 4.0417 194 1.3871 0.5766 1.3871 1.1778
No log 4.0833 196 1.1107 0.6092 1.1107 1.0539
No log 4.125 198 0.9700 0.6264 0.9700 0.9849
No log 4.1667 200 1.0459 0.6252 1.0459 1.0227
No log 4.2083 202 1.2831 0.6010 1.2831 1.1328
No log 4.25 204 1.4659 0.5736 1.4659 1.2107
No log 4.2917 206 1.6888 0.5172 1.6888 1.2995
No log 4.3333 208 1.6177 0.5189 1.6177 1.2719
No log 4.375 210 1.2676 0.5687 1.2676 1.1259
No log 4.4167 212 1.0134 0.6338 1.0134 1.0067
No log 4.4583 214 0.9832 0.6181 0.9832 0.9916
No log 4.5 216 1.0426 0.5923 1.0426 1.0211
No log 4.5417 218 1.2679 0.5531 1.2679 1.1260
No log 4.5833 220 1.3381 0.5467 1.3381 1.1567
No log 4.625 222 1.2078 0.5468 1.2078 1.0990
No log 4.6667 224 1.0378 0.5735 1.0378 1.0187
No log 4.7083 226 0.9537 0.5938 0.9537 0.9766
No log 4.75 228 0.9622 0.6280 0.9622 0.9809
No log 4.7917 230 1.0191 0.6354 1.0191 1.0095
No log 4.8333 232 1.1339 0.5919 1.1339 1.0649
No log 4.875 234 1.2757 0.5698 1.2757 1.1295
No log 4.9167 236 1.1494 0.6016 1.1494 1.0721
No log 4.9583 238 0.8837 0.6609 0.8837 0.9400
No log 5.0 240 0.8024 0.6301 0.8024 0.8958
No log 5.0417 242 0.8567 0.6472 0.8567 0.9256
No log 5.0833 244 1.0331 0.6324 1.0331 1.0164
No log 5.125 246 1.2927 0.5870 1.2927 1.1370
No log 5.1667 248 1.3119 0.5794 1.3119 1.1454
No log 5.2083 250 1.1441 0.5962 1.1441 1.0696
No log 5.25 252 0.9732 0.6232 0.9732 0.9865
No log 5.2917 254 0.9086 0.6412 0.9086 0.9532
No log 5.3333 256 0.8850 0.6379 0.8850 0.9407
No log 5.375 258 0.9326 0.6490 0.9326 0.9657
No log 5.4167 260 1.0413 0.6324 1.0413 1.0205
No log 5.4583 262 1.0739 0.6238 1.0739 1.0363
No log 5.5 264 1.0568 0.6409 1.0568 1.0280
No log 5.5417 266 0.9910 0.6474 0.9910 0.9955
No log 5.5833 268 0.8778 0.6349 0.8778 0.9369
No log 5.625 270 0.8126 0.6303 0.8126 0.9014
No log 5.6667 272 0.8283 0.6399 0.8283 0.9101
No log 5.7083 274 0.9419 0.6441 0.9419 0.9705
No log 5.75 276 1.1308 0.6263 1.1308 1.0634
No log 5.7917 278 1.2358 0.5950 1.2358 1.1117
No log 5.8333 280 1.1893 0.5994 1.1893 1.0906
No log 5.875 282 1.0584 0.6289 1.0584 1.0288
No log 5.9167 284 0.9474 0.6387 0.9474 0.9734
No log 5.9583 286 0.9364 0.6345 0.9364 0.9677
No log 6.0 288 0.9770 0.6168 0.9770 0.9884
No log 6.0417 290 0.9732 0.6344 0.9732 0.9865
No log 6.0833 292 0.8948 0.6468 0.8948 0.9460
No log 6.125 294 0.8203 0.6311 0.8203 0.9057
No log 6.1667 296 0.8007 0.6340 0.8007 0.8948
No log 6.2083 298 0.8115 0.6340 0.8115 0.9008
No log 6.25 300 0.8223 0.6374 0.8223 0.9068
No log 6.2917 302 0.8469 0.6437 0.8469 0.9203
No log 6.3333 304 0.8860 0.6471 0.8860 0.9413
No log 6.375 306 0.9028 0.6351 0.9028 0.9502
No log 6.4167 308 0.9677 0.6103 0.9677 0.9837
No log 6.4583 310 1.0167 0.6215 1.0167 1.0083
No log 6.5 312 1.0051 0.6261 1.0051 1.0025
No log 6.5417 314 1.0120 0.6261 1.0120 1.0060
No log 6.5833 316 0.9368 0.6284 0.9368 0.9679
No log 6.625 318 0.9264 0.6284 0.9264 0.9625
No log 6.6667 320 0.9281 0.6284 0.9281 0.9634
No log 6.7083 322 0.9480 0.6548 0.9480 0.9736
No log 6.75 324 1.0112 0.6194 1.0112 1.0056
No log 6.7917 326 1.1085 0.6059 1.1085 1.0528
No log 6.8333 328 1.1835 0.5885 1.1835 1.0879
No log 6.875 330 1.1379 0.6075 1.1379 1.0667
No log 6.9167 332 1.0511 0.6195 1.0511 1.0252
No log 6.9583 334 1.0649 0.6235 1.0649 1.0320
No log 7.0 336 1.1394 0.6091 1.1394 1.0674
No log 7.0417 338 1.1184 0.6237 1.1184 1.0576
No log 7.0833 340 1.0021 0.6441 1.0021 1.0011
No log 7.125 342 0.9311 0.6550 0.9311 0.9649
No log 7.1667 344 0.9198 0.6571 0.9198 0.9591
No log 7.2083 346 0.9755 0.6357 0.9755 0.9877
No log 7.25 348 1.0410 0.6275 1.0410 1.0203
No log 7.2917 350 1.0498 0.6275 1.0498 1.0246
No log 7.3333 352 1.0454 0.6275 1.0454 1.0225
No log 7.375 354 0.9589 0.6429 0.9589 0.9792
No log 7.4167 356 0.8336 0.6603 0.8336 0.9130
No log 7.4583 358 0.7534 0.6814 0.7534 0.8680
No log 7.5 360 0.7408 0.6741 0.7408 0.8607
No log 7.5417 362 0.7637 0.6729 0.7637 0.8739
No log 7.5833 364 0.8370 0.6562 0.8370 0.9149
No log 7.625 366 0.8820 0.6558 0.8820 0.9392
No log 7.6667 368 0.9472 0.6429 0.9472 0.9733
No log 7.7083 370 0.9862 0.6375 0.9862 0.9931
No log 7.75 372 1.0315 0.6289 1.0315 1.0156
No log 7.7917 374 1.0033 0.6275 1.0033 1.0016
No log 7.8333 376 0.9185 0.6459 0.9185 0.9584
No log 7.875 378 0.8422 0.6498 0.8422 0.9177
No log 7.9167 380 0.8137 0.6600 0.8137 0.9021
No log 7.9583 382 0.8153 0.6600 0.8153 0.9029
No log 8.0 384 0.8503 0.6603 0.8503 0.9221
No log 8.0417 386 0.8743 0.6493 0.8743 0.9350
No log 8.0833 388 0.8739 0.6374 0.8739 0.9348
No log 8.125 390 0.8779 0.6374 0.8779 0.9370
No log 8.1667 392 0.8639 0.6407 0.8639 0.9294
No log 8.2083 394 0.8693 0.6389 0.8693 0.9324
No log 8.25 396 0.8744 0.6374 0.8744 0.9351
No log 8.2917 398 0.8805 0.6399 0.8805 0.9383
No log 8.3333 400 0.8667 0.6399 0.8667 0.9310
No log 8.375 402 0.8530 0.6471 0.8530 0.9236
No log 8.4167 404 0.8452 0.6561 0.8452 0.9193
No log 8.4583 406 0.8490 0.6561 0.8490 0.9214
No log 8.5 408 0.8664 0.6471 0.8664 0.9308
No log 8.5417 410 0.8672 0.6561 0.8672 0.9312
No log 8.5833 412 0.8599 0.6520 0.8599 0.9273
No log 8.625 414 0.8509 0.6444 0.8509 0.9224
No log 8.6667 416 0.8375 0.6628 0.8375 0.9152
No log 8.7083 418 0.8409 0.6636 0.8409 0.9170
No log 8.75 420 0.8340 0.6653 0.8340 0.9132
No log 8.7917 422 0.8365 0.6430 0.8365 0.9146
No log 8.8333 424 0.8451 0.6385 0.8451 0.9193
No log 8.875 426 0.8645 0.6405 0.8645 0.9298
No log 8.9167 428 0.8934 0.6295 0.8934 0.9452
No log 8.9583 430 0.9245 0.6161 0.9245 0.9615
No log 9.0 432 0.9437 0.6161 0.9437 0.9714
No log 9.0417 434 0.9612 0.6253 0.9612 0.9804
No log 9.0833 436 0.9630 0.6253 0.9630 0.9813
No log 9.125 438 0.9473 0.6224 0.9473 0.9733
No log 9.1667 440 0.9209 0.6161 0.9209 0.9596
No log 9.2083 442 0.8934 0.6204 0.8934 0.9452
No log 9.25 444 0.8723 0.6186 0.8723 0.9340
No log 9.2917 446 0.8552 0.6405 0.8552 0.9248
No log 9.3333 448 0.8441 0.6449 0.8441 0.9188
No log 9.375 450 0.8286 0.6349 0.8286 0.9103
No log 9.4167 452 0.8240 0.6518 0.8240 0.9077
No log 9.4583 454 0.8237 0.6792 0.8237 0.9076
No log 9.5 456 0.8305 0.6799 0.8305 0.9113
No log 9.5417 458 0.8456 0.6417 0.8456 0.9196
No log 9.5833 460 0.8688 0.6194 0.8688 0.9321
No log 9.625 462 0.8958 0.6228 0.8958 0.9465
No log 9.6667 464 0.9148 0.6377 0.9148 0.9564
No log 9.7083 466 0.9290 0.6421 0.9290 0.9639
No log 9.75 468 0.9347 0.6421 0.9347 0.9668
No log 9.7917 470 0.9362 0.6421 0.9362 0.9676
No log 9.8333 472 0.9370 0.6421 0.9370 0.9680
No log 9.875 474 0.9348 0.6421 0.9348 0.9669
No log 9.9167 476 0.9307 0.6421 0.9307 0.9647
No log 9.9583 478 0.9280 0.6421 0.9280 0.9633
No log 10.0 480 0.9269 0.6421 0.9269 0.9628

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
2
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/ArabicNewSplits6_FineTuningAraBERT_run3_AugV5_k13_task5_organization

Finetuned
(4040)
this model