ArabicNewSplits7_usingALLEssays_FineTuningAraBERT_run1_AugV5_k2_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: 0.8973
  • Qwk: 0.3944
  • Mse: 0.8973
  • Rmse: 0.9472

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 0.2222 2 4.3474 -0.0102 4.3474 2.0851
No log 0.4444 4 2.6091 0.0908 2.6091 1.6153
No log 0.6667 6 1.6447 -0.0078 1.6447 1.2824
No log 0.8889 8 1.2036 0.1910 1.2036 1.0971
No log 1.1111 10 1.0253 0.2366 1.0253 1.0126
No log 1.3333 12 1.0078 0.4339 1.0078 1.0039
No log 1.5556 14 1.0140 0.3655 1.0140 1.0070
No log 1.7778 16 0.9551 0.3616 0.9551 0.9773
No log 2.0 18 1.0504 0.1805 1.0504 1.0249
No log 2.2222 20 1.1300 0.1233 1.1300 1.0630
No log 2.4444 22 1.0812 0.1738 1.0812 1.0398
No log 2.6667 24 1.0359 0.2070 1.0359 1.0178
No log 2.8889 26 0.9943 0.3187 0.9943 0.9971
No log 3.1111 28 0.9098 0.3915 0.9098 0.9538
No log 3.3333 30 0.9333 0.3981 0.9333 0.9661
No log 3.5556 32 0.9052 0.3425 0.9052 0.9514
No log 3.7778 34 0.8757 0.4338 0.8757 0.9358
No log 4.0 36 1.0746 0.3208 1.0746 1.0366
No log 4.2222 38 0.9915 0.3851 0.9915 0.9957
No log 4.4444 40 0.8903 0.4708 0.8903 0.9435
No log 4.6667 42 0.9047 0.3740 0.9047 0.9511
No log 4.8889 44 0.9207 0.4012 0.9207 0.9596
No log 5.1111 46 0.9465 0.3744 0.9465 0.9729
No log 5.3333 48 0.9083 0.4962 0.9083 0.9530
No log 5.5556 50 0.9396 0.4124 0.9396 0.9693
No log 5.7778 52 0.8951 0.4370 0.8951 0.9461
No log 6.0 54 0.9019 0.4757 0.9019 0.9497
No log 6.2222 56 0.9166 0.3861 0.9166 0.9574
No log 6.4444 58 0.8580 0.5261 0.8580 0.9263
No log 6.6667 60 0.9248 0.3637 0.9248 0.9617
No log 6.8889 62 0.9346 0.3637 0.9346 0.9667
No log 7.1111 64 0.9208 0.5599 0.9208 0.9596
No log 7.3333 66 1.0457 0.2685 1.0457 1.0226
No log 7.5556 68 1.1624 0.3065 1.1624 1.0781
No log 7.7778 70 1.1225 0.3331 1.1225 1.0595
No log 8.0 72 1.0644 0.3584 1.0644 1.0317
No log 8.2222 74 1.0020 0.5264 1.0020 1.0010
No log 8.4444 76 0.9652 0.5264 0.9652 0.9825
No log 8.6667 78 0.9050 0.5251 0.9050 0.9513
No log 8.8889 80 0.9015 0.5312 0.9015 0.9494
No log 9.1111 82 0.9107 0.5636 0.9107 0.9543
No log 9.3333 84 0.8466 0.5752 0.8466 0.9201
No log 9.5556 86 0.8309 0.5418 0.8309 0.9115
No log 9.7778 88 0.8434 0.5002 0.8434 0.9184
No log 10.0 90 0.8804 0.3767 0.8804 0.9383
No log 10.2222 92 1.0238 0.3387 1.0238 1.0118
No log 10.4444 94 0.9441 0.3675 0.9441 0.9716
No log 10.6667 96 0.8335 0.4495 0.8335 0.9130
No log 10.8889 98 0.9542 0.5854 0.9542 0.9768
No log 11.1111 100 0.9915 0.5763 0.9915 0.9957
No log 11.3333 102 0.8642 0.5638 0.8642 0.9296
No log 11.5556 104 1.0208 0.4287 1.0208 1.0104
No log 11.7778 106 1.1965 0.4392 1.1965 1.0939
No log 12.0 108 1.0737 0.4186 1.0737 1.0362
No log 12.2222 110 0.8888 0.4292 0.8888 0.9428
No log 12.4444 112 0.8128 0.5628 0.8128 0.9016
No log 12.6667 114 0.9327 0.5475 0.9327 0.9657
No log 12.8889 116 0.9210 0.5753 0.9210 0.9597
No log 13.1111 118 0.8118 0.5886 0.8118 0.9010
No log 13.3333 120 0.8566 0.5052 0.8566 0.9255
No log 13.5556 122 0.8405 0.5048 0.8405 0.9168
No log 13.7778 124 0.7757 0.5187 0.7757 0.8808
No log 14.0 126 0.7422 0.5796 0.7422 0.8615
No log 14.2222 128 0.7518 0.6186 0.7518 0.8671
No log 14.4444 130 0.7576 0.6284 0.7576 0.8704
No log 14.6667 132 0.8139 0.4781 0.8139 0.9022
No log 14.8889 134 0.9942 0.3921 0.9942 0.9971
No log 15.1111 136 1.0048 0.3833 1.0048 1.0024
No log 15.3333 138 0.8771 0.4677 0.8771 0.9365
No log 15.5556 140 0.8093 0.5369 0.8093 0.8996
No log 15.7778 142 0.7886 0.6051 0.7886 0.8880
No log 16.0 144 0.7888 0.5102 0.7888 0.8881
No log 16.2222 146 0.8641 0.4205 0.8641 0.9296
No log 16.4444 148 0.9000 0.4257 0.9000 0.9487
No log 16.6667 150 0.8445 0.4614 0.8445 0.9189
No log 16.8889 152 0.8602 0.5847 0.8602 0.9274
No log 17.1111 154 0.9211 0.5624 0.9211 0.9597
No log 17.3333 156 0.8999 0.5201 0.8999 0.9486
No log 17.5556 158 0.9278 0.4913 0.9278 0.9632
No log 17.7778 160 0.9461 0.4515 0.9461 0.9727
No log 18.0 162 1.0212 0.3419 1.0212 1.0106
No log 18.2222 164 1.0817 0.3907 1.0817 1.0400
No log 18.4444 166 1.0522 0.3814 1.0522 1.0258
No log 18.6667 168 0.9635 0.3488 0.9635 0.9816
No log 18.8889 170 0.9211 0.4761 0.9211 0.9597
No log 19.1111 172 0.9211 0.4990 0.9211 0.9597
No log 19.3333 174 0.9485 0.5071 0.9485 0.9739
No log 19.5556 176 0.9827 0.4453 0.9827 0.9913
No log 19.7778 178 0.9542 0.4918 0.9542 0.9768
No log 20.0 180 0.9297 0.4719 0.9297 0.9642
No log 20.2222 182 0.9070 0.4513 0.9070 0.9523
No log 20.4444 184 0.8585 0.4328 0.8585 0.9265
No log 20.6667 186 0.8348 0.5102 0.8348 0.9137
No log 20.8889 188 0.8271 0.4938 0.8271 0.9095
No log 21.1111 190 0.8498 0.5415 0.8498 0.9218
No log 21.3333 192 0.8345 0.5263 0.8345 0.9135
No log 21.5556 194 0.8494 0.5427 0.8494 0.9216
No log 21.7778 196 0.8426 0.5094 0.8426 0.9179
No log 22.0 198 0.8629 0.4840 0.8629 0.9289
No log 22.2222 200 0.8575 0.4853 0.8575 0.9260
No log 22.4444 202 0.8132 0.5208 0.8132 0.9018
No log 22.6667 204 0.7972 0.5861 0.7972 0.8928
No log 22.8889 206 0.8065 0.4803 0.8065 0.8981
No log 23.1111 208 0.8282 0.4764 0.8282 0.9100
No log 23.3333 210 0.9151 0.3811 0.9151 0.9566
No log 23.5556 212 0.9865 0.3772 0.9865 0.9932
No log 23.7778 214 0.9273 0.3862 0.9273 0.9630
No log 24.0 216 0.8171 0.4572 0.8171 0.9039
No log 24.2222 218 0.7935 0.5905 0.7935 0.8908
No log 24.4444 220 0.8258 0.5902 0.8258 0.9087
No log 24.6667 222 0.8326 0.5561 0.8326 0.9125
No log 24.8889 224 0.8455 0.5196 0.8455 0.9195
No log 25.1111 226 0.9509 0.4927 0.9509 0.9752
No log 25.3333 228 0.9854 0.4821 0.9854 0.9927
No log 25.5556 230 0.9133 0.3902 0.9133 0.9557
No log 25.7778 232 0.8769 0.5673 0.8769 0.9364
No log 26.0 234 0.9653 0.5697 0.9653 0.9825
No log 26.2222 236 1.0018 0.4998 1.0018 1.0009
No log 26.4444 238 0.9468 0.5299 0.9468 0.9731
No log 26.6667 240 0.8496 0.5263 0.8496 0.9217
No log 26.8889 242 0.8776 0.5197 0.8776 0.9368
No log 27.1111 244 0.9116 0.4465 0.9116 0.9548
No log 27.3333 246 0.9008 0.4604 0.9008 0.9491
No log 27.5556 248 0.8907 0.4884 0.8907 0.9437
No log 27.7778 250 0.8807 0.4816 0.8807 0.9385
No log 28.0 252 0.8960 0.5014 0.8960 0.9466
No log 28.2222 254 0.9120 0.5002 0.9120 0.9550
No log 28.4444 256 0.9266 0.4006 0.9266 0.9626
No log 28.6667 258 0.9002 0.4374 0.9002 0.9488
No log 28.8889 260 0.8529 0.4977 0.8529 0.9235
No log 29.1111 262 0.8418 0.4863 0.8418 0.9175
No log 29.3333 264 0.8210 0.5186 0.8210 0.9061
No log 29.5556 266 0.7884 0.5797 0.7884 0.8879
No log 29.7778 268 0.7789 0.5471 0.7789 0.8825
No log 30.0 270 0.7765 0.5785 0.7765 0.8812
No log 30.2222 272 0.7948 0.5711 0.7948 0.8915
No log 30.4444 274 0.8300 0.4849 0.8300 0.9111
No log 30.6667 276 0.8529 0.4846 0.8529 0.9235
No log 30.8889 278 0.8238 0.5349 0.8238 0.9077
No log 31.1111 280 0.8042 0.5451 0.8042 0.8968
No log 31.3333 282 0.7975 0.5066 0.7975 0.8931
No log 31.5556 284 0.7675 0.5098 0.7675 0.8761
No log 31.7778 286 0.7645 0.5431 0.7645 0.8744
No log 32.0 288 0.7909 0.5522 0.7909 0.8893
No log 32.2222 290 0.8158 0.5147 0.8158 0.9032
No log 32.4444 292 0.7826 0.5221 0.7826 0.8847
No log 32.6667 294 0.7606 0.5809 0.7606 0.8721
No log 32.8889 296 0.7673 0.5690 0.7673 0.8760
No log 33.1111 298 0.7967 0.5188 0.7967 0.8926
No log 33.3333 300 0.8811 0.4205 0.8811 0.9387
No log 33.5556 302 0.8816 0.4214 0.8816 0.9389
No log 33.7778 304 0.8475 0.4327 0.8475 0.9206
No log 34.0 306 0.8715 0.4278 0.8715 0.9335
No log 34.2222 308 0.8794 0.4255 0.8794 0.9378
No log 34.4444 310 0.8706 0.4348 0.8706 0.9331
No log 34.6667 312 0.8429 0.5027 0.8429 0.9181
No log 34.8889 314 0.8390 0.4806 0.8390 0.9160
No log 35.1111 316 0.8574 0.4806 0.8574 0.9260
No log 35.3333 318 0.8503 0.4806 0.8503 0.9221
No log 35.5556 320 0.8581 0.4806 0.8581 0.9264
No log 35.7778 322 0.8492 0.4924 0.8492 0.9215
No log 36.0 324 0.8573 0.4720 0.8573 0.9259
No log 36.2222 326 0.8777 0.4730 0.8777 0.9368
No log 36.4444 328 0.8300 0.5349 0.8300 0.9110
No log 36.6667 330 0.8103 0.5673 0.8103 0.9001
No log 36.8889 332 0.8493 0.4834 0.8493 0.9216
No log 37.1111 334 0.8574 0.5018 0.8574 0.9259
No log 37.3333 336 0.8321 0.4924 0.8321 0.9122
No log 37.5556 338 0.7999 0.5634 0.7999 0.8944
No log 37.7778 340 0.7763 0.5740 0.7763 0.8811
No log 38.0 342 0.7579 0.5866 0.7579 0.8706
No log 38.2222 344 0.7358 0.5471 0.7358 0.8578
No log 38.4444 346 0.7346 0.5796 0.7346 0.8571
No log 38.6667 348 0.7482 0.5455 0.7482 0.8650
No log 38.8889 350 0.7969 0.5505 0.7969 0.8927
No log 39.1111 352 0.8541 0.4625 0.8541 0.9242
No log 39.3333 354 0.8503 0.4517 0.8503 0.9221
No log 39.5556 356 0.7931 0.5599 0.7931 0.8906
No log 39.7778 358 0.7412 0.5902 0.7412 0.8609
No log 40.0 360 0.7230 0.6306 0.7230 0.8503
No log 40.2222 362 0.7208 0.6124 0.7208 0.8490
No log 40.4444 364 0.7212 0.6306 0.7212 0.8493
No log 40.6667 366 0.7598 0.5752 0.7598 0.8717
No log 40.8889 368 0.8590 0.4167 0.8590 0.9268
No log 41.1111 370 0.9251 0.3642 0.9251 0.9618
No log 41.3333 372 0.9195 0.3461 0.9195 0.9589
No log 41.5556 374 0.8334 0.4191 0.8334 0.9129
No log 41.7778 376 0.7559 0.5618 0.7559 0.8694
No log 42.0 378 0.7102 0.5964 0.7102 0.8427
No log 42.2222 380 0.7045 0.5851 0.7045 0.8393
No log 42.4444 382 0.7053 0.6167 0.7053 0.8398
No log 42.6667 384 0.7264 0.6022 0.7264 0.8523
No log 42.8889 386 0.7548 0.5819 0.7548 0.8688
No log 43.1111 388 0.7483 0.6301 0.7483 0.8651
No log 43.3333 390 0.7539 0.6075 0.7539 0.8682
No log 43.5556 392 0.7429 0.6781 0.7429 0.8619
No log 43.7778 394 0.7332 0.6820 0.7332 0.8563
No log 44.0 396 0.7307 0.6650 0.7307 0.8548
No log 44.2222 398 0.7366 0.6048 0.7366 0.8583
No log 44.4444 400 0.7397 0.6048 0.7397 0.8601
No log 44.6667 402 0.7432 0.5853 0.7432 0.8621
No log 44.8889 404 0.7438 0.6288 0.7438 0.8624
No log 45.1111 406 0.7525 0.6350 0.7525 0.8675
No log 45.3333 408 0.7520 0.6383 0.7520 0.8672
No log 45.5556 410 0.7606 0.6350 0.7606 0.8721
No log 45.7778 412 0.7826 0.5401 0.7826 0.8846
No log 46.0 414 0.8032 0.5074 0.8032 0.8962
No log 46.2222 416 0.8109 0.5291 0.8109 0.9005
No log 46.4444 418 0.8018 0.5291 0.8018 0.8954
No log 46.6667 420 0.7872 0.5629 0.7872 0.8872
No log 46.8889 422 0.7759 0.5629 0.7759 0.8809
No log 47.1111 424 0.7648 0.5891 0.7648 0.8745
No log 47.3333 426 0.7709 0.5891 0.7709 0.8780
No log 47.5556 428 0.7806 0.5629 0.7806 0.8835
No log 47.7778 430 0.7942 0.5629 0.7942 0.8912
No log 48.0 432 0.8006 0.5830 0.8006 0.8947
No log 48.2222 434 0.8246 0.5603 0.8246 0.9081
No log 48.4444 436 0.8266 0.5603 0.8266 0.9092
No log 48.6667 438 0.8359 0.5401 0.8359 0.9143
No log 48.8889 440 0.8393 0.5404 0.8393 0.9161
No log 49.1111 442 0.8355 0.5404 0.8355 0.9141
No log 49.3333 444 0.8104 0.5637 0.8104 0.9002
No log 49.5556 446 0.7911 0.5645 0.7911 0.8894
No log 49.7778 448 0.7893 0.5565 0.7893 0.8884
No log 50.0 450 0.7997 0.5676 0.7997 0.8943
No log 50.2222 452 0.8122 0.5663 0.8122 0.9012
No log 50.4444 454 0.7922 0.5676 0.7922 0.8901
No log 50.6667 456 0.7744 0.5921 0.7744 0.8800
No log 50.8889 458 0.7622 0.5570 0.7622 0.8730
No log 51.1111 460 0.7750 0.6066 0.7750 0.8803
No log 51.3333 462 0.8055 0.6038 0.8055 0.8975
No log 51.5556 464 0.8601 0.5235 0.8601 0.9274
No log 51.7778 466 0.8946 0.4333 0.8946 0.9458
No log 52.0 468 0.8923 0.4333 0.8923 0.9446
No log 52.2222 470 0.8603 0.4840 0.8603 0.9275
No log 52.4444 472 0.8070 0.5637 0.8070 0.8983
No log 52.6667 474 0.7745 0.5329 0.7745 0.8801
No log 52.8889 476 0.7636 0.5570 0.7636 0.8738
No log 53.1111 478 0.7682 0.5570 0.7682 0.8764
No log 53.3333 480 0.7860 0.5921 0.7860 0.8866
No log 53.5556 482 0.7976 0.5666 0.7976 0.8931
No log 53.7778 484 0.8190 0.5304 0.8190 0.9050
No log 54.0 486 0.8362 0.4956 0.8362 0.9144
No log 54.2222 488 0.8508 0.4735 0.8508 0.9224
No log 54.4444 490 0.8520 0.4735 0.8520 0.9230
No log 54.6667 492 0.8284 0.5291 0.8284 0.9102
No log 54.8889 494 0.8139 0.5618 0.8139 0.9022
No log 55.1111 496 0.7976 0.5637 0.7976 0.8931
No log 55.3333 498 0.7915 0.5637 0.7915 0.8897
0.2177 55.5556 500 0.7956 0.5645 0.7956 0.8919
0.2177 55.7778 502 0.8107 0.5186 0.8107 0.9004
0.2177 56.0 504 0.8355 0.5054 0.8355 0.9141
0.2177 56.2222 506 0.8759 0.4285 0.8759 0.9359
0.2177 56.4444 508 0.8936 0.4058 0.8936 0.9453
0.2177 56.6667 510 0.8973 0.3944 0.8973 0.9472

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
-
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/ArabicNewSplits7_usingALLEssays_FineTuningAraBERT_run1_AugV5_k2_task5_organization

Finetuned
(4019)
this model