ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k15_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: 0.7568
  • Qwk: 0.5446
  • Mse: 0.7568
  • Rmse: 0.8699

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 0.0513 2 4.6165 -0.0179 4.6165 2.1486
No log 0.1026 4 2.8710 -0.0231 2.8710 1.6944
No log 0.1538 6 2.1203 -0.0647 2.1203 1.4561
No log 0.2051 8 1.4524 0.0279 1.4524 1.2051
No log 0.2564 10 1.6575 0.0300 1.6575 1.2874
No log 0.3077 12 1.5431 0.0371 1.5431 1.2422
No log 0.3590 14 1.3230 -0.0511 1.3230 1.1502
No log 0.4103 16 1.1595 0.0882 1.1595 1.0768
No log 0.4615 18 1.2108 0.0909 1.2108 1.1004
No log 0.5128 20 1.1741 0.1154 1.1741 1.0836
No log 0.5641 22 1.1535 0.0792 1.1535 1.0740
No log 0.6154 24 1.1449 0.1408 1.1449 1.0700
No log 0.6667 26 1.1799 0.0970 1.1799 1.0862
No log 0.7179 28 1.2804 0.0232 1.2804 1.1315
No log 0.7692 30 1.3531 0.0 1.3531 1.1632
No log 0.8205 32 1.2932 0.0380 1.2932 1.1372
No log 0.8718 34 1.1336 0.2074 1.1336 1.0647
No log 0.9231 36 1.0738 0.1218 1.0738 1.0363
No log 0.9744 38 1.0661 0.1370 1.0661 1.0325
No log 1.0256 40 1.0737 0.1848 1.0737 1.0362
No log 1.0769 42 1.0947 0.2074 1.0947 1.0463
No log 1.1282 44 1.1012 0.2125 1.1012 1.0494
No log 1.1795 46 1.0272 0.1725 1.0272 1.0135
No log 1.2308 48 0.9670 0.2944 0.9670 0.9833
No log 1.2821 50 0.9680 0.3288 0.9680 0.9838
No log 1.3333 52 0.9473 0.2944 0.9473 0.9733
No log 1.3846 54 0.9451 0.2842 0.9451 0.9722
No log 1.4359 56 0.9414 0.2865 0.9414 0.9703
No log 1.4872 58 0.9470 0.3979 0.9470 0.9731
No log 1.5385 60 1.0563 0.2441 1.0563 1.0277
No log 1.5897 62 1.0513 0.2834 1.0513 1.0253
No log 1.6410 64 1.0556 0.3108 1.0556 1.0274
No log 1.6923 66 1.0785 0.3547 1.0785 1.0385
No log 1.7436 68 1.1076 0.2835 1.1076 1.0524
No log 1.7949 70 1.1437 0.2669 1.1437 1.0694
No log 1.8462 72 1.0474 0.2551 1.0474 1.0234
No log 1.8974 74 1.0008 0.3414 1.0008 1.0004
No log 1.9487 76 0.9496 0.3819 0.9496 0.9745
No log 2.0 78 0.9968 0.3063 0.9968 0.9984
No log 2.0513 80 1.0099 0.2474 1.0099 1.0050
No log 2.1026 82 0.9361 0.3153 0.9361 0.9675
No log 2.1538 84 0.9225 0.3304 0.9225 0.9605
No log 2.2051 86 0.8860 0.3214 0.8860 0.9413
No log 2.2564 88 0.8880 0.3175 0.8880 0.9423
No log 2.3077 90 0.8734 0.3744 0.8734 0.9346
No log 2.3590 92 0.8972 0.3976 0.8972 0.9472
No log 2.4103 94 0.9447 0.4466 0.9447 0.9719
No log 2.4615 96 0.9653 0.4231 0.9653 0.9825
No log 2.5128 98 0.9781 0.4231 0.9781 0.9890
No log 2.5641 100 0.9767 0.4404 0.9767 0.9883
No log 2.6154 102 1.0069 0.4711 1.0069 1.0034
No log 2.6667 104 0.9996 0.4662 0.9996 0.9998
No log 2.7179 106 1.1371 0.3437 1.1371 1.0663
No log 2.7692 108 1.0179 0.4211 1.0179 1.0089
No log 2.8205 110 0.9999 0.4211 0.9999 0.9999
No log 2.8718 112 1.0285 0.3787 1.0285 1.0142
No log 2.9231 114 1.0194 0.3787 1.0194 1.0096
No log 2.9744 116 0.9353 0.3335 0.9353 0.9671
No log 3.0256 118 0.9335 0.4606 0.9335 0.9662
No log 3.0769 120 1.0004 0.4278 1.0004 1.0002
No log 3.1282 122 0.8726 0.4879 0.8726 0.9341
No log 3.1795 124 1.0981 0.4515 1.0981 1.0479
No log 3.2308 126 1.1562 0.4471 1.1562 1.0753
No log 3.2821 128 0.9591 0.5106 0.9591 0.9794
No log 3.3333 130 0.8275 0.5618 0.8275 0.9097
No log 3.3846 132 1.0220 0.3878 1.0220 1.0109
No log 3.4359 134 1.1379 0.3666 1.1379 1.0667
No log 3.4872 136 0.9192 0.4268 0.9192 0.9587
No log 3.5385 138 0.8057 0.4792 0.8057 0.8976
No log 3.5897 140 0.9502 0.2543 0.9502 0.9748
No log 3.6410 142 0.9009 0.3622 0.9009 0.9492
No log 3.6923 144 0.7538 0.5510 0.7538 0.8682
No log 3.7436 146 0.8009 0.4943 0.8009 0.8949
No log 3.7949 148 0.9927 0.4493 0.9927 0.9963
No log 3.8462 150 0.9957 0.4579 0.9957 0.9979
No log 3.8974 152 0.8076 0.5291 0.8076 0.8986
No log 3.9487 154 0.7955 0.5920 0.7955 0.8919
No log 4.0 156 0.7960 0.6082 0.7960 0.8922
No log 4.0513 158 0.7556 0.5260 0.7556 0.8693
No log 4.1026 160 0.8811 0.3001 0.8811 0.9387
No log 4.1538 162 1.0139 0.1487 1.0139 1.0069
No log 4.2051 164 0.9353 0.3743 0.9353 0.9671
No log 4.2564 166 0.7945 0.4988 0.7945 0.8913
No log 4.3077 168 0.8683 0.3541 0.8683 0.9318
No log 4.3590 170 0.8541 0.3704 0.8541 0.9242
No log 4.4103 172 0.8820 0.5065 0.8820 0.9391
No log 4.4615 174 0.9687 0.4794 0.9687 0.9842
No log 4.5128 176 0.8793 0.4824 0.8793 0.9377
No log 4.5641 178 0.7916 0.4119 0.7916 0.8897
No log 4.6154 180 0.8567 0.4004 0.8567 0.9256
No log 4.6667 182 0.8216 0.5089 0.8216 0.9064
No log 4.7179 184 0.7702 0.5939 0.7702 0.8776
No log 4.7692 186 0.8413 0.5059 0.8413 0.9172
No log 4.8205 188 0.8852 0.4607 0.8852 0.9409
No log 4.8718 190 0.8603 0.5305 0.8603 0.9275
No log 4.9231 192 0.8574 0.4799 0.8574 0.9259
No log 4.9744 194 0.8373 0.4661 0.8373 0.9150
No log 5.0256 196 0.8090 0.4110 0.8090 0.8995
No log 5.0769 198 0.7960 0.4244 0.7960 0.8922
No log 5.1282 200 0.7876 0.4411 0.7876 0.8874
No log 5.1795 202 0.8073 0.3941 0.8073 0.8985
No log 5.2308 204 0.9128 0.5292 0.9128 0.9554
No log 5.2821 206 0.9012 0.4250 0.9012 0.9493
No log 5.3333 208 0.8633 0.4875 0.8633 0.9292
No log 5.3846 210 0.8718 0.4869 0.8718 0.9337
No log 5.4359 212 0.8762 0.5002 0.8762 0.9360
No log 5.4872 214 0.8698 0.5129 0.8698 0.9326
No log 5.5385 216 0.8721 0.4863 0.8721 0.9338
No log 5.5897 218 0.8440 0.5304 0.8440 0.9187
No log 5.6410 220 0.9335 0.4270 0.9335 0.9662
No log 5.6923 222 0.9326 0.4349 0.9326 0.9657
No log 5.7436 224 0.8294 0.4728 0.8294 0.9107
No log 5.7949 226 0.8017 0.4353 0.8017 0.8954
No log 5.8462 228 0.8143 0.3959 0.8143 0.9024
No log 5.8974 230 0.8392 0.4712 0.8392 0.9161
No log 5.9487 232 0.7845 0.5010 0.7845 0.8857
No log 6.0 234 0.7825 0.5370 0.7825 0.8846
No log 6.0513 236 0.8422 0.5279 0.8422 0.9177
No log 6.1026 238 0.8607 0.5057 0.8607 0.9278
No log 6.1538 240 0.8598 0.5057 0.8598 0.9273
No log 6.2051 242 0.8166 0.5463 0.8166 0.9036
No log 6.2564 244 0.8020 0.4918 0.8020 0.8955
No log 6.3077 246 0.8120 0.4012 0.8120 0.9011
No log 6.3590 248 0.8552 0.3922 0.8552 0.9248
No log 6.4103 250 0.8461 0.3922 0.8461 0.9198
No log 6.4615 252 0.7902 0.4223 0.7902 0.8889
No log 6.5128 254 0.7790 0.4692 0.7790 0.8826
No log 6.5641 256 0.7647 0.4804 0.7647 0.8745
No log 6.6154 258 0.7802 0.5074 0.7802 0.8833
No log 6.6667 260 0.8180 0.4845 0.8180 0.9044
No log 6.7179 262 0.8144 0.5370 0.8144 0.9025
No log 6.7692 264 0.8191 0.5669 0.8191 0.9050
No log 6.8205 266 0.8116 0.5370 0.8116 0.9009
No log 6.8718 268 0.8203 0.4706 0.8203 0.9057
No log 6.9231 270 0.8084 0.4706 0.8084 0.8991
No log 6.9744 272 0.8021 0.5275 0.8021 0.8956
No log 7.0256 274 0.7935 0.5580 0.7935 0.8908
No log 7.0769 276 0.7835 0.5545 0.7835 0.8852
No log 7.1282 278 0.8000 0.5494 0.8000 0.8944
No log 7.1795 280 0.8327 0.5366 0.8327 0.9125
No log 7.2308 282 0.7913 0.5331 0.7913 0.8895
No log 7.2821 284 0.7506 0.5570 0.7506 0.8664
No log 7.3333 286 0.7462 0.6076 0.7462 0.8638
No log 7.3846 288 0.7442 0.5582 0.7442 0.8627
No log 7.4359 290 0.7762 0.5558 0.7762 0.8810
No log 7.4872 292 0.7830 0.5331 0.7830 0.8849
No log 7.5385 294 0.7635 0.5121 0.7635 0.8738
No log 7.5897 296 0.7906 0.5234 0.7906 0.8892
No log 7.6410 298 0.8031 0.4645 0.8031 0.8962
No log 7.6923 300 0.7985 0.4645 0.7985 0.8936
No log 7.7436 302 0.8470 0.5291 0.8470 0.9203
No log 7.7949 304 0.9654 0.5222 0.9654 0.9826
No log 7.8462 306 1.0083 0.4354 1.0083 1.0041
No log 7.8974 308 0.9160 0.3523 0.9160 0.9571
No log 7.9487 310 0.8343 0.4251 0.8343 0.9134
No log 8.0 312 0.8437 0.4165 0.8437 0.9185
No log 8.0513 314 0.8416 0.4440 0.8416 0.9174
No log 8.1026 316 0.7828 0.4660 0.7828 0.8848
No log 8.1538 318 0.8145 0.4630 0.8145 0.9025
No log 8.2051 320 0.9292 0.5230 0.9292 0.9640
No log 8.2564 322 0.8687 0.5372 0.8687 0.9320
No log 8.3077 324 0.7532 0.4760 0.7532 0.8679
No log 8.3590 326 0.7863 0.4984 0.7863 0.8867
No log 8.4103 328 0.8325 0.5220 0.8325 0.9124
No log 8.4615 330 0.7714 0.5176 0.7714 0.8783
No log 8.5128 332 0.7843 0.5442 0.7843 0.8856
No log 8.5641 334 0.8575 0.5291 0.8575 0.9260
No log 8.6154 336 0.8189 0.5410 0.8189 0.9049
No log 8.6667 338 0.7704 0.5010 0.7704 0.8777
No log 8.7179 340 0.7651 0.5402 0.7651 0.8747
No log 8.7692 342 0.7648 0.4760 0.7648 0.8745
No log 8.8205 344 0.7866 0.4353 0.7866 0.8869
No log 8.8718 346 0.7921 0.4082 0.7921 0.8900
No log 8.9231 348 0.8006 0.4082 0.8006 0.8948
No log 8.9744 350 0.7787 0.4223 0.7787 0.8824
No log 9.0256 352 0.7718 0.4625 0.7718 0.8785
No log 9.0769 354 0.7708 0.5142 0.7708 0.8779
No log 9.1282 356 0.7802 0.4760 0.7802 0.8833
No log 9.1795 358 0.8296 0.4491 0.8296 0.9108
No log 9.2308 360 0.8122 0.4960 0.8122 0.9012
No log 9.2821 362 0.7961 0.5288 0.7961 0.8922
No log 9.3333 364 0.8481 0.4749 0.8481 0.9209
No log 9.3846 366 0.8183 0.4444 0.8183 0.9046
No log 9.4359 368 0.8061 0.4371 0.8061 0.8978
No log 9.4872 370 0.8997 0.5305 0.8997 0.9485
No log 9.5385 372 0.8998 0.4952 0.8998 0.9486
No log 9.5897 374 0.8120 0.4216 0.8120 0.9011
No log 9.6410 376 0.7773 0.4277 0.7773 0.8816
No log 9.6923 378 0.8506 0.4752 0.8506 0.9223
No log 9.7436 380 0.8252 0.5204 0.8252 0.9084
No log 9.7949 382 0.7663 0.5548 0.7663 0.8754
No log 9.8462 384 0.7358 0.5288 0.7358 0.8578
No log 9.8974 386 0.7881 0.5208 0.7881 0.8877
No log 9.9487 388 0.8637 0.5160 0.8637 0.9294
No log 10.0 390 0.8491 0.4946 0.8491 0.9215
No log 10.0513 392 0.8079 0.4494 0.8079 0.8988
No log 10.1026 394 0.7924 0.4507 0.7924 0.8902
No log 10.1538 396 0.7694 0.4405 0.7694 0.8772
No log 10.2051 398 0.7560 0.5142 0.7560 0.8695
No log 10.2564 400 0.7817 0.4858 0.7817 0.8842
No log 10.3077 402 0.8922 0.5458 0.8922 0.9445
No log 10.3590 404 0.9171 0.4916 0.9171 0.9577
No log 10.4103 406 0.8472 0.5306 0.8472 0.9205
No log 10.4615 408 0.7580 0.4628 0.7580 0.8706
No log 10.5128 410 0.7043 0.5399 0.7043 0.8392
No log 10.5641 412 0.6979 0.5399 0.6979 0.8354
No log 10.6154 414 0.6915 0.5498 0.6915 0.8316
No log 10.6667 416 0.7144 0.5346 0.7144 0.8452
No log 10.7179 418 0.7029 0.5492 0.7029 0.8384
No log 10.7692 420 0.7007 0.5831 0.7007 0.8371
No log 10.8205 422 0.7120 0.5409 0.7120 0.8438
No log 10.8718 424 0.7198 0.4778 0.7198 0.8484
No log 10.9231 426 0.7308 0.4659 0.7308 0.8549
No log 10.9744 428 0.7425 0.4659 0.7425 0.8617
No log 11.0256 430 0.7532 0.4540 0.7532 0.8679
No log 11.0769 432 0.7558 0.4908 0.7558 0.8694
No log 11.1282 434 0.7613 0.4628 0.7613 0.8725
No log 11.1795 436 0.7515 0.4628 0.7515 0.8669
No log 11.2308 438 0.7441 0.5017 0.7441 0.8626
No log 11.2821 440 0.7399 0.4888 0.7399 0.8602
No log 11.3333 442 0.7240 0.4644 0.7240 0.8509
No log 11.3846 444 0.7116 0.4988 0.7116 0.8436
No log 11.4359 446 0.7072 0.5654 0.7072 0.8410
No log 11.4872 448 0.6701 0.5905 0.6701 0.8186
No log 11.5385 450 0.6630 0.5988 0.6630 0.8142
No log 11.5897 452 0.6584 0.5988 0.6584 0.8114
No log 11.6410 454 0.6558 0.5988 0.6558 0.8098
No log 11.6923 456 0.6526 0.5988 0.6526 0.8079
No log 11.7436 458 0.6552 0.5988 0.6552 0.8095
No log 11.7949 460 0.6613 0.5988 0.6613 0.8132
No log 11.8462 462 0.6737 0.5988 0.6737 0.8208
No log 11.8974 464 0.6644 0.5988 0.6644 0.8151
No log 11.9487 466 0.6623 0.5961 0.6623 0.8138
No log 12.0 468 0.6670 0.5542 0.6670 0.8167
No log 12.0513 470 0.6739 0.5845 0.6739 0.8209
No log 12.1026 472 0.6654 0.5542 0.6654 0.8157
No log 12.1538 474 0.6615 0.5542 0.6615 0.8133
No log 12.2051 476 0.6597 0.5759 0.6597 0.8122
No log 12.2564 478 0.6686 0.5492 0.6686 0.8177
No log 12.3077 480 0.6927 0.5235 0.6927 0.8323
No log 12.3590 482 0.7280 0.5654 0.7280 0.8532
No log 12.4103 484 0.7181 0.5208 0.7181 0.8474
No log 12.4615 486 0.7171 0.5657 0.7171 0.8468
No log 12.5128 488 0.7037 0.6028 0.7037 0.8389
No log 12.5641 490 0.6923 0.5713 0.6923 0.8321
No log 12.6154 492 0.6854 0.5606 0.6854 0.8279
No log 12.6667 494 0.6867 0.4923 0.6867 0.8287
No log 12.7179 496 0.6851 0.5174 0.6851 0.8277
No log 12.7692 498 0.6821 0.5626 0.6821 0.8259
0.313 12.8205 500 0.6865 0.5736 0.6865 0.8286
0.313 12.8718 502 0.6896 0.5500 0.6896 0.8304
0.313 12.9231 504 0.6987 0.5945 0.6987 0.8359
0.313 12.9744 506 0.7213 0.6234 0.7213 0.8493
0.313 13.0256 508 0.7276 0.6256 0.7276 0.8530
0.313 13.0769 510 0.6891 0.6078 0.6891 0.8301
0.313 13.1282 512 0.7008 0.5010 0.7008 0.8372
0.313 13.1795 514 0.7365 0.5093 0.7365 0.8582
0.313 13.2308 516 0.7148 0.4988 0.7148 0.8454
0.313 13.2821 518 0.6964 0.5428 0.6964 0.8345
0.313 13.3333 520 0.7568 0.5446 0.7568 0.8699

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_run1_AugV5_k15_task5_organization

Finetuned
(4205)
this model