ArabicNewSplits4_FineTuningAraBERT_run3_AugV5_k12_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: 0.7368
  • Qwk: 0.1675
  • Mse: 0.7368
  • Rmse: 0.8584

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 3.5785 0.0100 3.5785 1.8917
No log 0.0833 4 1.6212 0.0168 1.6212 1.2733
No log 0.125 6 0.6580 0.0769 0.6580 0.8111
No log 0.1667 8 0.5727 0.1111 0.5727 0.7568
No log 0.2083 10 0.6506 0.3455 0.6506 0.8066
No log 0.25 12 1.0567 0.0345 1.0567 1.0279
No log 0.2917 14 0.8285 0.0569 0.8285 0.9102
No log 0.3333 16 0.6461 0.2222 0.6461 0.8038
No log 0.375 18 0.5938 0.0 0.5938 0.7706
No log 0.4167 20 0.5850 0.0476 0.5850 0.7649
No log 0.4583 22 0.6699 0.2090 0.6699 0.8184
No log 0.5 24 0.5861 -0.0233 0.5861 0.7655
No log 0.5417 26 0.5737 -0.0159 0.5737 0.7575
No log 0.5833 28 0.6109 0.0725 0.6109 0.7816
No log 0.625 30 0.8701 0.1605 0.8701 0.9328
No log 0.6667 32 1.1479 0.0388 1.1479 1.0714
No log 0.7083 34 0.8812 0.1861 0.8812 0.9387
No log 0.75 36 0.6032 -0.0159 0.6032 0.7766
No log 0.7917 38 0.6030 0.0 0.6030 0.7765
No log 0.8333 40 0.6179 0.0 0.6179 0.7861
No log 0.875 42 0.6407 0.0 0.6407 0.8004
No log 0.9167 44 0.6893 -0.1242 0.6893 0.8303
No log 0.9583 46 0.9267 0.0431 0.9267 0.9627
No log 1.0 48 1.0854 0.0 1.0854 1.0418
No log 1.0417 50 0.9185 0.0 0.9185 0.9584
No log 1.0833 52 0.8377 0.0345 0.8377 0.9153
No log 1.125 54 0.8315 0.0388 0.8315 0.9118
No log 1.1667 56 0.8849 0.0038 0.8849 0.9407
No log 1.2083 58 0.8516 0.0431 0.8516 0.9228
No log 1.25 60 0.7202 0.0189 0.7202 0.8486
No log 1.2917 62 0.6574 0.0476 0.6574 0.8108
No log 1.3333 64 0.6059 0.0 0.6059 0.7784
No log 1.375 66 0.6091 0.0 0.6091 0.7804
No log 1.4167 68 0.6014 0.0 0.6014 0.7755
No log 1.4583 70 0.5985 0.0 0.5985 0.7737
No log 1.5 72 0.6241 0.0569 0.6241 0.7900
No log 1.5417 74 0.6882 0.0256 0.6882 0.8296
No log 1.5833 76 0.7632 0.0685 0.7632 0.8736
No log 1.625 78 0.6555 0.1206 0.6555 0.8097
No log 1.6667 80 0.6183 0.0388 0.6183 0.7863
No log 1.7083 82 0.5977 0.0388 0.5977 0.7731
No log 1.75 84 0.5873 -0.0159 0.5873 0.7664
No log 1.7917 86 0.6107 0.0388 0.6107 0.7815
No log 1.8333 88 0.8396 0.1169 0.8396 0.9163
No log 1.875 90 1.2962 0.0 1.2962 1.1385
No log 1.9167 92 1.1786 0.0 1.1786 1.0856
No log 1.9583 94 0.8113 0.1111 0.8113 0.9007
No log 2.0 96 0.6183 0.0222 0.6183 0.7863
No log 2.0417 98 0.6333 0.0071 0.6333 0.7958
No log 2.0833 100 0.7280 -0.0575 0.7280 0.8533
No log 2.125 102 0.7092 -0.0058 0.7092 0.8422
No log 2.1667 104 0.6758 0.1020 0.6758 0.8221
No log 2.2083 106 0.6256 0.0222 0.6256 0.7910
No log 2.25 108 0.5885 0.0 0.5885 0.7672
No log 2.2917 110 0.5929 0.0 0.5929 0.7700
No log 2.3333 112 0.6730 0.0815 0.6730 0.8204
No log 2.375 114 0.6802 0.1895 0.6802 0.8247
No log 2.4167 116 0.6961 0.1828 0.6961 0.8343
No log 2.4583 118 0.6503 0.3224 0.6503 0.8064
No log 2.5 120 0.6926 0.2390 0.6926 0.8322
No log 2.5417 122 0.7248 0.2300 0.7248 0.8513
No log 2.5833 124 1.2375 0.1484 1.2375 1.1124
No log 2.625 126 1.1439 0.1458 1.1439 1.0695
No log 2.6667 128 0.6644 0.2308 0.6644 0.8151
No log 2.7083 130 0.6144 0.3267 0.6144 0.7839
No log 2.75 132 0.7515 0.2414 0.7515 0.8669
No log 2.7917 134 0.9515 0.2000 0.9515 0.9755
No log 2.8333 136 0.8511 0.3091 0.8511 0.9225
No log 2.875 138 0.6127 0.3208 0.6127 0.7827
No log 2.9167 140 0.6103 0.3953 0.6103 0.7812
No log 2.9583 142 0.8310 0.2961 0.8310 0.9116
No log 3.0 144 0.9108 0.1628 0.9108 0.9544
No log 3.0417 146 1.0001 0.0853 1.0001 1.0000
No log 3.0833 148 0.7752 0.2759 0.7752 0.8805
No log 3.125 150 0.6496 0.2965 0.6496 0.8060
No log 3.1667 152 0.6288 0.3297 0.6288 0.7930
No log 3.2083 154 1.1545 0.1125 1.1545 1.0745
No log 3.25 156 1.6795 0.0377 1.6795 1.2960
No log 3.2917 158 1.6451 0.0377 1.6451 1.2826
No log 3.3333 160 1.2178 0.0984 1.2178 1.1035
No log 3.375 162 0.5393 0.4348 0.5393 0.7344
No log 3.4167 164 0.5624 0.2558 0.5624 0.7500
No log 3.4583 166 0.5336 0.3966 0.5336 0.7305
No log 3.5 168 0.7580 0.3247 0.7580 0.8706
No log 3.5417 170 0.8683 0.1937 0.8683 0.9318
No log 3.5833 172 1.2880 0.0730 1.2880 1.1349
No log 3.625 174 1.3713 0.0328 1.3713 1.1710
No log 3.6667 176 0.9861 0.1943 0.9861 0.9931
No log 3.7083 178 0.6555 0.4019 0.6555 0.8096
No log 3.75 180 0.6698 0.3744 0.6698 0.8184
No log 3.7917 182 0.9690 0.2456 0.9690 0.9844
No log 3.8333 184 1.3095 0.1226 1.3095 1.1443
No log 3.875 186 1.5530 0.0567 1.5530 1.2462
No log 3.9167 188 1.3641 0.1000 1.3641 1.1679
No log 3.9583 190 0.8273 0.2184 0.8273 0.9096
No log 4.0 192 0.6357 0.3498 0.6357 0.7973
No log 4.0417 194 0.6547 0.36 0.6547 0.8091
No log 4.0833 196 0.9083 0.1719 0.9083 0.9531
No log 4.125 198 0.9392 0.1448 0.9392 0.9691
No log 4.1667 200 0.7136 0.2676 0.7136 0.8448
No log 4.2083 202 0.5867 0.4583 0.5867 0.7660
No log 4.25 204 0.5884 0.2941 0.5884 0.7671
No log 4.2917 206 0.5982 0.4583 0.5982 0.7734
No log 4.3333 208 0.8227 0.1587 0.8227 0.9070
No log 4.375 210 1.0252 0.1439 1.0252 1.0125
No log 4.4167 212 1.0517 0.1439 1.0517 1.0255
No log 4.4583 214 0.7630 0.2423 0.7630 0.8735
No log 4.5 216 0.7645 0.2423 0.7645 0.8744
No log 4.5417 218 0.8357 0.1751 0.8357 0.9141
No log 4.5833 220 0.6855 0.3171 0.6855 0.8279
No log 4.625 222 0.6234 0.3103 0.6234 0.7896
No log 4.6667 224 0.6450 0.2195 0.6450 0.8031
No log 4.7083 226 0.6018 0.4105 0.6018 0.7757
No log 4.75 228 0.7044 0.2893 0.7044 0.8393
No log 4.7917 230 0.8069 0.1652 0.8069 0.8983
No log 4.8333 232 0.8557 0.1692 0.8557 0.9250
No log 4.875 234 0.7962 0.1525 0.7962 0.8923
No log 4.9167 236 0.7526 0.2681 0.7526 0.8675
No log 4.9583 238 0.7485 0.3091 0.7485 0.8652
No log 5.0 240 0.9892 0.1254 0.9892 0.9946
No log 5.0417 242 1.3763 0.1155 1.3763 1.1732
No log 5.0833 244 1.3991 0.1467 1.3991 1.1829
No log 5.125 246 1.1191 0.1111 1.1191 1.0579
No log 5.1667 248 0.8746 0.1212 0.8746 0.9352
No log 5.2083 250 0.6370 0.4286 0.6370 0.7981
No log 5.25 252 0.5980 0.4098 0.5980 0.7733
No log 5.2917 254 0.5942 0.4091 0.5942 0.7709
No log 5.3333 256 0.6513 0.2577 0.6513 0.8071
No log 5.375 258 0.7447 0.1933 0.7447 0.8630
No log 5.4167 260 0.6661 0.3089 0.6661 0.8162
No log 5.4583 262 0.5902 0.2575 0.5902 0.7683
No log 5.5 264 0.5869 0.3171 0.5869 0.7661
No log 5.5417 266 0.6377 0.4098 0.6377 0.7985
No log 5.5833 268 0.7925 0.0847 0.7925 0.8902
No log 5.625 270 0.9527 0.1709 0.9527 0.9761
No log 5.6667 272 0.8399 0.0916 0.8399 0.9165
No log 5.7083 274 0.6344 0.4409 0.6344 0.7965
No log 5.75 276 0.6185 0.3563 0.6185 0.7864
No log 5.7917 278 0.6256 0.3446 0.6256 0.7909
No log 5.8333 280 0.6150 0.4051 0.6150 0.7842
No log 5.875 282 0.8002 0.2140 0.8002 0.8945
No log 5.9167 284 0.8702 0.1934 0.8702 0.9328
No log 5.9583 286 0.7074 0.2780 0.7074 0.8411
No log 6.0 288 0.6595 0.3089 0.6595 0.8121
No log 6.0417 290 0.6879 0.3103 0.6879 0.8294
No log 6.0833 292 0.7223 0.2381 0.7223 0.8499
No log 6.125 294 0.7221 0.2676 0.7221 0.8498
No log 6.1667 296 0.6904 0.3077 0.6904 0.8309
No log 6.2083 298 0.7162 0.2676 0.7162 0.8463
No log 6.25 300 0.7280 0.2676 0.7280 0.8532
No log 6.2917 302 0.8613 0.1864 0.8613 0.9281
No log 6.3333 304 0.9579 0.1318 0.9579 0.9787
No log 6.375 306 1.0151 0.1331 1.0151 1.0075
No log 6.4167 308 1.1140 0.1367 1.1140 1.0555
No log 6.4583 310 0.9622 0.0888 0.9622 0.9809
No log 6.5 312 0.7461 0.2593 0.7461 0.8638
No log 6.5417 314 0.7012 0.2536 0.7012 0.8374
No log 6.5833 316 0.7094 0.2670 0.7094 0.8423
No log 6.625 318 0.8276 0.2511 0.8276 0.9097
No log 6.6667 320 0.8960 0.1169 0.8960 0.9466
No log 6.7083 322 0.8047 0.2153 0.8047 0.8970
No log 6.75 324 0.7593 0.2381 0.7593 0.8714
No log 6.7917 326 0.7414 0.2390 0.7414 0.8610
No log 6.8333 328 0.7296 0.28 0.7296 0.8541
No log 6.875 330 0.8282 0.2661 0.8282 0.9100
No log 6.9167 332 0.9803 0.0988 0.9803 0.9901
No log 6.9583 334 0.9324 0.1276 0.9324 0.9656
No log 7.0 336 0.8197 0.1855 0.8197 0.9054
No log 7.0417 338 0.7682 0.2372 0.7682 0.8765
No log 7.0833 340 0.7648 0.2579 0.7648 0.8745
No log 7.125 342 0.7542 0.2593 0.7542 0.8685
No log 7.1667 344 0.7964 0.2661 0.7964 0.8924
No log 7.2083 346 0.9389 0.0894 0.9389 0.9689
No log 7.25 348 0.9891 0.0672 0.9891 0.9946
No log 7.2917 350 0.9307 0.0820 0.9307 0.9648
No log 7.3333 352 0.8674 0.1405 0.8674 0.9313
No log 7.375 354 0.8554 0.1130 0.8554 0.9249
No log 7.4167 356 0.8574 0.1186 0.8574 0.9260
No log 7.4583 358 0.8290 0.2222 0.8290 0.9105
No log 7.5 360 0.7374 0.1675 0.7374 0.8587
No log 7.5417 362 0.6863 0.2707 0.6863 0.8285
No log 7.5833 364 0.6975 0.2093 0.6975 0.8352
No log 7.625 366 0.6935 0.2093 0.6935 0.8328
No log 7.6667 368 0.6858 0.2093 0.6858 0.8281
No log 7.7083 370 0.6941 0.2093 0.6941 0.8331
No log 7.75 372 0.7137 0.2088 0.7137 0.8448
No log 7.7917 374 0.7072 0.2088 0.7072 0.8409
No log 7.8333 376 0.7385 0.1667 0.7385 0.8593
No log 7.875 378 0.7602 0.1675 0.7602 0.8719
No log 7.9167 380 0.7896 0.2079 0.7896 0.8886
No log 7.9583 382 0.7581 0.1675 0.7581 0.8707
No log 8.0 384 0.7415 0.2245 0.7415 0.8611
No log 8.0417 386 0.7703 0.2390 0.7703 0.8777
No log 8.0833 388 0.7735 0.2390 0.7735 0.8795
No log 8.125 390 0.7772 0.2390 0.7772 0.8816
No log 8.1667 392 0.8273 0.2075 0.8273 0.9096
No log 8.2083 394 0.8598 0.2068 0.8598 0.9272
No log 8.25 396 0.8290 0.2432 0.8290 0.9105
No log 8.2917 398 0.8157 0.2075 0.8157 0.9032
No log 8.3333 400 0.8052 0.2075 0.8052 0.8973
No log 8.375 402 0.8304 0.2607 0.8304 0.9113
No log 8.4167 404 0.8495 0.1858 0.8495 0.9217
No log 8.4583 406 0.8252 0.2607 0.8252 0.9084
No log 8.5 408 0.7664 0.2239 0.7664 0.8754
No log 8.5417 410 0.7190 0.2086 0.7190 0.8479
No log 8.5833 412 0.6928 0.2432 0.6928 0.8323
No log 8.625 414 0.7013 0.2432 0.7013 0.8374
No log 8.6667 416 0.7083 0.2421 0.7083 0.8416
No log 8.7083 418 0.7285 0.2000 0.7285 0.8535
No log 8.75 420 0.7746 0.2077 0.7746 0.8801
No log 8.7917 422 0.8175 0.2593 0.8175 0.9042
No log 8.8333 424 0.8226 0.2676 0.8226 0.9070
No log 8.875 426 0.8152 0.2593 0.8152 0.9029
No log 8.9167 428 0.7823 0.2607 0.7823 0.8845
No log 8.9583 430 0.7369 0.2563 0.7369 0.8584
No log 9.0 432 0.7069 0.2421 0.7069 0.8408
No log 9.0417 434 0.7076 0.2421 0.7076 0.8412
No log 9.0833 436 0.7172 0.2000 0.7172 0.8469
No log 9.125 438 0.7409 0.2390 0.7409 0.8607
No log 9.1667 440 0.7674 0.2563 0.7674 0.8760
No log 9.2083 442 0.7889 0.2941 0.7889 0.8882
No log 9.25 444 0.7748 0.2941 0.7748 0.8802
No log 9.2917 446 0.7503 0.2079 0.7503 0.8662
No log 9.3333 448 0.7331 0.1675 0.7331 0.8562
No log 9.375 450 0.7096 0.2000 0.7096 0.8424
No log 9.4167 452 0.6989 0.2421 0.6989 0.8360
No log 9.4583 454 0.6877 0.2577 0.6877 0.8293
No log 9.5 456 0.6826 0.2821 0.6826 0.8262
No log 9.5417 458 0.6815 0.2821 0.6815 0.8255
No log 9.5833 460 0.6880 0.2577 0.6880 0.8295
No log 9.625 462 0.6990 0.2421 0.6990 0.8360
No log 9.6667 464 0.7134 0.2421 0.7134 0.8446
No log 9.7083 466 0.7269 0.1675 0.7269 0.8526
No log 9.75 468 0.7314 0.1675 0.7314 0.8552
No log 9.7917 470 0.7316 0.1675 0.7316 0.8553
No log 9.8333 472 0.7302 0.1675 0.7302 0.8545
No log 9.875 474 0.7314 0.1675 0.7314 0.8552
No log 9.9167 476 0.7344 0.1675 0.7344 0.8570
No log 9.9583 478 0.7359 0.1675 0.7359 0.8578
No log 10.0 480 0.7368 0.1675 0.7368 0.8584

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
18
Safetensors
Model size
0.1B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for MayBashendy/ArabicNewSplits4_FineTuningAraBERT_run3_AugV5_k12_task3_organization

Finetuned
(4049)
this model