MayBashendy's picture
End of training
dbde966 verified
metadata
library_name: transformers
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: arabert_augWithOrig_disEquV3_k10_organization_task3_fold1
    results: []

arabert_augWithOrig_disEquV3_k10_organization_task3_fold1

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: 1.2428
  • Qwk: -0.1092
  • Mse: 1.2428
  • Rmse: 1.1148

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 0.0444 2 3.4864 0.0 3.4864 1.8672
No log 0.0889 4 2.0043 0.0571 2.0043 1.4157
No log 0.1333 6 1.6370 -0.1041 1.6370 1.2795
No log 0.1778 8 1.8929 -0.1859 1.8929 1.3758
No log 0.2222 10 2.8239 -0.1242 2.8239 1.6804
No log 0.2667 12 1.7517 -0.1547 1.7517 1.3235
No log 0.3111 14 1.3023 -0.0097 1.3023 1.1412
No log 0.3556 16 1.0038 0.0 1.0038 1.0019
No log 0.4 18 1.0572 0.0 1.0572 1.0282
No log 0.4444 20 1.5174 -0.0939 1.5174 1.2318
No log 0.4889 22 1.7392 -0.0396 1.7392 1.3188
No log 0.5333 24 1.4299 -0.0302 1.4299 1.1958
No log 0.5778 26 1.0314 0.0 1.0314 1.0156
No log 0.6222 28 1.0717 0.0 1.0717 1.0352
No log 0.6667 30 1.2985 -0.0168 1.2985 1.1395
No log 0.7111 32 1.4038 -0.1041 1.4038 1.1848
No log 0.7556 34 1.5976 -0.1547 1.5976 1.2639
No log 0.8 36 1.7313 -0.1476 1.7313 1.3158
No log 0.8444 38 1.5489 -0.1476 1.5489 1.2445
No log 0.8889 40 1.3383 0.0 1.3383 1.1568
No log 0.9333 42 1.2755 0.0 1.2755 1.1294
No log 0.9778 44 1.2479 0.0 1.2479 1.1171
No log 1.0222 46 1.0508 0.0 1.0508 1.0251
No log 1.0667 48 1.0033 0.0 1.0033 1.0017
No log 1.1111 50 0.9655 0.0 0.9655 0.9826
No log 1.1556 52 1.0259 0.0 1.0259 1.0128
No log 1.2 54 1.0851 0.0 1.0851 1.0417
No log 1.2444 56 1.0763 0.0 1.0763 1.0375
No log 1.2889 58 1.0204 0.0 1.0204 1.0101
No log 1.3333 60 1.0053 0.0 1.0053 1.0026
No log 1.3778 62 1.1461 0.0 1.1461 1.0706
No log 1.4222 64 1.1686 0.0 1.1686 1.0810
No log 1.4667 66 1.0498 0.0 1.0498 1.0246
No log 1.5111 68 1.0010 0.0 1.0010 1.0005
No log 1.5556 70 0.9985 0.0 0.9985 0.9993
No log 1.6 72 1.0951 0.0 1.0951 1.0465
No log 1.6444 74 1.1076 0.0 1.1076 1.0524
No log 1.6889 76 1.0404 0.0 1.0404 1.0200
No log 1.7333 78 0.8997 0.0 0.8997 0.9485
No log 1.7778 80 0.8316 0.0 0.8316 0.9119
No log 1.8222 82 0.8784 0.0 0.8784 0.9372
No log 1.8667 84 0.8497 0.0 0.8497 0.9218
No log 1.9111 86 0.8231 0.0 0.8231 0.9072
No log 1.9556 88 0.9486 0.0 0.9486 0.9740
No log 2.0 90 1.2336 -0.0097 1.2336 1.1107
No log 2.0444 92 1.3558 -0.0168 1.3558 1.1644
No log 2.0889 94 1.3157 -0.0097 1.3157 1.1470
No log 2.1333 96 1.2647 0.0 1.2647 1.1246
No log 2.1778 98 1.3116 -0.0097 1.3116 1.1453
No log 2.2222 100 1.3005 -0.0097 1.3005 1.1404
No log 2.2667 102 1.1216 0.0 1.1216 1.0590
No log 2.3111 104 0.9006 0.0 0.9006 0.9490
No log 2.3556 106 0.8380 0.0 0.8380 0.9154
No log 2.4 108 0.8864 0.0 0.8864 0.9415
No log 2.4444 110 1.0197 0.0 1.0197 1.0098
No log 2.4889 112 1.0488 0.0 1.0488 1.0241
No log 2.5333 114 0.9240 0.0 0.9240 0.9613
No log 2.5778 116 0.9174 0.0 0.9174 0.9578
No log 2.6222 118 1.0649 0.0 1.0649 1.0319
No log 2.6667 120 1.1843 0.0 1.1843 1.0883
No log 2.7111 122 1.2064 0.0 1.2064 1.0984
No log 2.7556 124 1.1095 0.0 1.1095 1.0533
No log 2.8 126 0.9400 0.0 0.9400 0.9696
No log 2.8444 128 0.9558 0.0 0.9558 0.9777
No log 2.8889 130 1.0438 0.0 1.0438 1.0217
No log 2.9333 132 1.3149 0.0 1.3149 1.1467
No log 2.9778 134 1.6249 0.0 1.6249 1.2747
No log 3.0222 136 1.7446 0.0 1.7446 1.3208
No log 3.0667 138 1.6877 0.0 1.6877 1.2991
No log 3.1111 140 1.5473 0.0041 1.5473 1.2439
No log 3.1556 142 1.3744 0.0 1.3744 1.1724
No log 3.2 144 1.1492 0.0 1.1492 1.0720
No log 3.2444 146 0.9814 0.0 0.9814 0.9906
No log 3.2889 148 0.9800 0.0 0.9800 0.9900
No log 3.3333 150 1.0305 0.0 1.0305 1.0151
No log 3.3778 152 1.2752 0.0 1.2752 1.1292
No log 3.4222 154 1.4778 0.0276 1.4778 1.2156
No log 3.4667 156 1.8209 0.0 1.8209 1.3494
No log 3.5111 158 1.8357 0.0 1.8357 1.3549
No log 3.5556 160 1.6119 0.0 1.6119 1.2696
No log 3.6 162 1.3326 0.0 1.3326 1.1544
No log 3.6444 164 1.1910 0.0 1.1910 1.0913
No log 3.6889 166 1.0941 0.0 1.0941 1.0460
No log 3.7333 168 1.0359 0.0 1.0359 1.0178
No log 3.7778 170 1.0566 0.0 1.0566 1.0279
No log 3.8222 172 1.1308 0.0 1.1308 1.0634
No log 3.8667 174 1.2408 0.0 1.2408 1.1139
No log 3.9111 176 1.3346 0.0 1.3346 1.1553
No log 3.9556 178 1.3636 0.0 1.3636 1.1677
No log 4.0 180 1.4247 -0.0168 1.4247 1.1936
No log 4.0444 182 1.4550 -0.0331 1.4550 1.2062
No log 4.0889 184 1.4566 -0.0331 1.4566 1.2069
No log 4.1333 186 1.4216 -0.0223 1.4216 1.1923
No log 4.1778 188 1.4111 -0.0168 1.4111 1.1879
No log 4.2222 190 1.4072 -0.0097 1.4072 1.1862
No log 4.2667 192 1.3626 0.0 1.3626 1.1673
No log 4.3111 194 1.2592 0.0 1.2592 1.1221
No log 4.3556 196 1.1454 0.0 1.1454 1.0702
No log 4.4 198 1.1266 0.0 1.1266 1.0614
No log 4.4444 200 1.0900 0.0 1.0900 1.0440
No log 4.4889 202 1.0973 0.0 1.0973 1.0475
No log 4.5333 204 1.1359 0.0 1.1359 1.0658
No log 4.5778 206 1.1612 0.0 1.1612 1.0776
No log 4.6222 208 1.1106 0.0 1.1106 1.0539
No log 4.6667 210 1.1000 0.0 1.1000 1.0488
No log 4.7111 212 1.0494 0.0 1.0494 1.0244
No log 4.7556 214 0.9639 0.0 0.9639 0.9818
No log 4.8 216 0.9232 0.0 0.9232 0.9608
No log 4.8444 218 0.9417 0.0 0.9417 0.9704
No log 4.8889 220 0.9741 0.0 0.9741 0.9869
No log 4.9333 222 0.9442 0.0 0.9442 0.9717
No log 4.9778 224 0.9816 0.0 0.9816 0.9908
No log 5.0222 226 0.9082 0.0 0.9082 0.9530
No log 5.0667 228 0.8310 0.0 0.8310 0.9116
No log 5.1111 230 0.8364 0.0 0.8364 0.9145
No log 5.1556 232 0.9725 0.0 0.9725 0.9862
No log 5.2 234 1.1735 0.0 1.1735 1.0833
No log 5.2444 236 1.5048 -0.0896 1.5048 1.2267
No log 5.2889 238 1.5860 -0.0896 1.5860 1.2594
No log 5.3333 240 1.5805 -0.0896 1.5805 1.2572
No log 5.3778 242 1.6225 -0.0896 1.6225 1.2738
No log 5.4222 244 1.5620 -0.0896 1.5620 1.2498
No log 5.4667 246 1.4637 -0.1631 1.4637 1.2098
No log 5.5111 248 1.4744 -0.1000 1.4744 1.2143
No log 5.5556 250 1.4683 -0.0302 1.4683 1.2117
No log 5.6 252 1.3695 -0.0097 1.3695 1.1703
No log 5.6444 254 1.3030 -0.0097 1.3030 1.1415
No log 5.6889 256 1.2499 0.0 1.2499 1.1180
No log 5.7333 258 1.2426 0.0 1.2426 1.1147
No log 5.7778 260 1.3214 0.0 1.3214 1.1495
No log 5.8222 262 1.3767 -0.1041 1.3767 1.1733
No log 5.8667 264 1.3205 -0.1092 1.3205 1.1491
No log 5.9111 266 1.3975 -0.0267 1.3975 1.1822
No log 5.9556 268 1.3522 -0.0267 1.3522 1.1628
No log 6.0 270 1.2845 -0.0168 1.2845 1.1334
No log 6.0444 272 1.1708 0.0 1.1708 1.0820
No log 6.0889 274 1.1557 0.0 1.1557 1.0750
No log 6.1333 276 1.4504 -0.0302 1.4504 1.2043
No log 6.1778 278 1.4509 -0.0267 1.4509 1.2045
No log 6.2222 280 1.0782 -0.0168 1.0782 1.0384
No log 6.2667 282 1.0491 -0.0168 1.0491 1.0243
No log 6.3111 284 0.9138 0.0 0.9138 0.9559
No log 6.3556 286 0.9343 0.0 0.9343 0.9666
No log 6.4 288 1.2179 -0.0223 1.2179 1.1036
No log 6.4444 290 1.3739 -0.0267 1.3739 1.1721
No log 6.4889 292 1.6702 0.0660 1.6702 1.2924
No log 6.5333 294 1.4043 -0.0302 1.4043 1.1850
No log 6.5778 296 1.0761 -0.0097 1.0761 1.0373
No log 6.6222 298 1.0577 -0.0097 1.0577 1.0285
No log 6.6667 300 1.0005 -0.0097 1.0005 1.0002
No log 6.7111 302 1.0324 -0.0097 1.0324 1.0161
No log 6.7556 304 1.2023 -0.0097 1.2023 1.0965
No log 6.8 306 1.3136 0.0595 1.3136 1.1461
No log 6.8444 308 1.3552 0.0467 1.3552 1.1641
No log 6.8889 310 1.2807 -0.0097 1.2807 1.1317
No log 6.9333 312 1.0514 -0.0097 1.0514 1.0254
No log 6.9778 314 0.9686 -0.0097 0.9686 0.9842
No log 7.0222 316 0.9959 -0.0097 0.9959 0.9980
No log 7.0667 318 1.0031 -0.0097 1.0031 1.0015
No log 7.1111 320 1.1537 -0.0097 1.1537 1.0741
No log 7.1556 322 1.2575 -0.1092 1.2575 1.1214
No log 7.2 324 1.3581 -0.1041 1.3581 1.1654
No log 7.2444 326 1.3414 -0.1092 1.3414 1.1582
No log 7.2889 328 1.4326 -0.0302 1.4326 1.1969
No log 7.3333 330 1.3759 -0.0223 1.3759 1.1730
No log 7.3778 332 1.2021 -0.1092 1.2021 1.0964
No log 7.4222 334 1.2243 -0.1092 1.2243 1.1065
No log 7.4667 336 1.2326 -0.1092 1.2326 1.1102
No log 7.5111 338 1.1986 -0.1092 1.1986 1.0948
No log 7.5556 340 1.0890 -0.0087 1.0890 1.0436
No log 7.6 342 1.1881 -0.1092 1.1881 1.0900
No log 7.6444 344 1.2298 -0.0223 1.2298 1.1089
No log 7.6889 346 1.1548 -0.0087 1.1548 1.0746
No log 7.7333 348 1.2593 0.0692 1.2593 1.1222
No log 7.7778 350 1.4425 -0.0223 1.4425 1.2010
No log 7.8222 352 1.7188 -0.0267 1.7188 1.3110
No log 7.8667 354 1.8682 -0.0302 1.8682 1.3668
No log 7.9111 356 1.7113 -0.0267 1.7113 1.3082
No log 7.9556 358 1.6667 -0.0267 1.6667 1.2910
No log 8.0 360 1.5718 -0.0223 1.5718 1.2537
No log 8.0444 362 1.5251 -0.0223 1.5251 1.2350
No log 8.0889 364 1.5152 -0.0223 1.5152 1.2309
No log 8.1333 366 1.4215 -0.1092 1.4215 1.1923
No log 8.1778 368 1.4308 -0.1092 1.4308 1.1962
No log 8.2222 370 1.5093 -0.0223 1.5093 1.2286
No log 8.2667 372 1.4669 -0.1092 1.4669 1.2111
No log 8.3111 374 1.4652 -0.1092 1.4652 1.2104
No log 8.3556 376 1.5336 -0.0223 1.5336 1.2384
No log 8.4 378 1.6953 -0.0302 1.6953 1.3020
No log 8.4444 380 1.7894 -0.0302 1.7894 1.3377
No log 8.4889 382 1.7805 -0.0302 1.7805 1.3344
No log 8.5333 384 1.5994 -0.0267 1.5994 1.2647
No log 8.5778 386 1.3078 -0.1092 1.3078 1.1436
No log 8.6222 388 1.0650 0.1111 1.0650 1.0320
No log 8.6667 390 0.9261 0.1111 0.9261 0.9623
No log 8.7111 392 0.7976 -0.1058 0.7976 0.8931
No log 8.7556 394 0.7612 -0.1000 0.7612 0.8724
No log 8.8 396 0.7997 -0.1058 0.7997 0.8943
No log 8.8444 398 0.9190 0.1111 0.9190 0.9586
No log 8.8889 400 1.0208 0.1111 1.0208 1.0103
No log 8.9333 402 1.1857 -0.1092 1.1857 1.0889
No log 8.9778 404 1.4002 -0.0223 1.4002 1.1833
No log 9.0222 406 1.5712 -0.0223 1.5712 1.2535
No log 9.0667 408 1.6608 -0.0267 1.6608 1.2887
No log 9.1111 410 1.6400 -0.0267 1.6400 1.2806
No log 9.1556 412 1.5410 -0.0223 1.5410 1.2414
No log 9.2 414 1.4459 -0.0223 1.4459 1.2024
No log 9.2444 416 1.3406 -0.1092 1.3406 1.1578
No log 9.2889 418 1.2625 -0.1092 1.2625 1.1236
No log 9.3333 420 1.2268 -0.1092 1.2268 1.1076
No log 9.3778 422 1.2060 -0.1092 1.2060 1.0982
No log 9.4222 424 1.1747 -0.0087 1.1747 1.0838
No log 9.4667 426 1.1850 -0.1092 1.1850 1.0886
No log 9.5111 428 1.1977 -0.1092 1.1977 1.0944
No log 9.5556 430 1.2084 -0.1092 1.2084 1.0993
No log 9.6 432 1.1950 -0.1092 1.1950 1.0932
No log 9.6444 434 1.1751 -0.1092 1.1751 1.0840
No log 9.6889 436 1.1725 -0.1092 1.1725 1.0828
No log 9.7333 438 1.1637 -0.0087 1.1637 1.0787
No log 9.7778 440 1.1726 -0.1092 1.1726 1.0829
No log 9.8222 442 1.1921 -0.1092 1.1921 1.0918
No log 9.8667 444 1.2037 -0.1092 1.2037 1.0971
No log 9.9111 446 1.2199 -0.1092 1.2199 1.1045
No log 9.9556 448 1.2353 -0.1092 1.2353 1.1114
No log 10.0 450 1.2428 -0.1092 1.2428 1.1148

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1