MayBashendy's picture
Training in progress, step 500
f1340bb verified
|
raw
history blame
22.1 kB
metadata
library_name: transformers
base_model: aubmindlab/bert-base-arabertv02
tags:
  - generated_from_trainer
model-index:
  - name: ArabicNewSplits7_FineTuningAraBERT_run3_AugV5_k1_task3_organization
    results: []

ArabicNewSplits7_FineTuningAraBERT_run3_AugV5_k1_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: 0.7947
  • Qwk: 0.0732
  • Mse: 0.7947
  • Rmse: 0.8915

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 0.3333 2 3.5985 -0.0058 3.5985 1.8970
No log 0.6667 4 2.0854 0.0304 2.0854 1.4441
No log 1.0 6 1.4246 -0.0265 1.4246 1.1936
No log 1.3333 8 1.6141 0.0194 1.6141 1.2705
No log 1.6667 10 0.8606 0.0129 0.8606 0.9277
No log 2.0 12 0.7360 0.0857 0.7360 0.8579
No log 2.3333 14 0.7941 0.0191 0.7941 0.8911
No log 2.6667 16 0.7895 0.0191 0.7895 0.8886
No log 3.0 18 1.0750 0.0309 1.0750 1.0368
No log 3.3333 20 0.9576 0.0320 0.9576 0.9786
No log 3.6667 22 0.8243 0.1561 0.8243 0.9079
No log 4.0 24 0.9648 0.1636 0.9648 0.9822
No log 4.3333 26 1.2644 0.0310 1.2644 1.1244
No log 4.6667 28 1.1342 0.0808 1.1342 1.0650
No log 5.0 30 1.0170 0.1490 1.0170 1.0084
No log 5.3333 32 1.1711 0.0746 1.1711 1.0822
No log 5.6667 34 1.2028 0.0448 1.2028 1.0967
No log 6.0 36 1.1016 -0.0007 1.1016 1.0496
No log 6.3333 38 1.2012 0.0379 1.2012 1.0960
No log 6.6667 40 0.9958 0.0852 0.9958 0.9979
No log 7.0 42 1.2038 0.1011 1.2038 1.0972
No log 7.3333 44 1.0823 -0.0323 1.0823 1.0403
No log 7.6667 46 1.2943 0.0599 1.2943 1.1377
No log 8.0 48 1.0769 -0.0304 1.0769 1.0377
No log 8.3333 50 1.1115 0.0657 1.1115 1.0543
No log 8.6667 52 1.1320 0.0063 1.1320 1.0640
No log 9.0 54 0.9966 0.0559 0.9966 0.9983
No log 9.3333 56 1.0106 -0.0535 1.0106 1.0053
No log 9.6667 58 1.0469 -0.0194 1.0469 1.0232
No log 10.0 60 1.0263 -0.0409 1.0263 1.0131
No log 10.3333 62 1.0840 -0.0285 1.0840 1.0411
No log 10.6667 64 0.9976 0.0476 0.9976 0.9988
No log 11.0 66 1.0476 0.0244 1.0476 1.0235
No log 11.3333 68 1.0282 0.0802 1.0282 1.0140
No log 11.6667 70 1.0249 0.0996 1.0249 1.0124
No log 12.0 72 0.9961 -0.0208 0.9961 0.9980
No log 12.3333 74 0.8806 0.0606 0.8806 0.9384
No log 12.6667 76 0.7950 0.0449 0.7950 0.8916
No log 13.0 78 0.9334 0.0207 0.9334 0.9661
No log 13.3333 80 0.8615 0.0490 0.8615 0.9282
No log 13.6667 82 0.8439 0.0025 0.8439 0.9186
No log 14.0 84 1.0273 0.0734 1.0273 1.0136
No log 14.3333 86 0.9783 0.0464 0.9783 0.9891
No log 14.6667 88 1.0563 0.0149 1.0563 1.0278
No log 15.0 90 1.0854 0.0062 1.0854 1.0418
No log 15.3333 92 0.9269 0.0262 0.9269 0.9628
No log 15.6667 94 0.9040 0.0172 0.9040 0.9508
No log 16.0 96 0.8451 -0.0178 0.8451 0.9193
No log 16.3333 98 0.8333 -0.0614 0.8333 0.9128
No log 16.6667 100 0.8459 0.0051 0.8459 0.9197
No log 17.0 102 0.8893 0.0208 0.8893 0.9430
No log 17.3333 104 0.9031 -0.0138 0.9031 0.9503
No log 17.6667 106 0.9573 0.0547 0.9573 0.9784
No log 18.0 108 1.1123 0.0366 1.1123 1.0546
No log 18.3333 110 1.0005 0.0494 1.0005 1.0002
No log 18.6667 112 0.9932 -0.0044 0.9932 0.9966
No log 19.0 114 0.9629 0.0913 0.9629 0.9813
No log 19.3333 116 0.9107 0.0870 0.9107 0.9543
No log 19.6667 118 0.8642 -0.0186 0.8642 0.9296
No log 20.0 120 0.9241 -0.0408 0.9241 0.9613
No log 20.3333 122 0.9368 -0.0441 0.9368 0.9679
No log 20.6667 124 0.8366 -0.0295 0.8366 0.9147
No log 21.0 126 0.8295 -0.0391 0.8295 0.9108
No log 21.3333 128 0.8510 -0.0357 0.8510 0.9225
No log 21.6667 130 0.8825 0.0867 0.8825 0.9394
No log 22.0 132 1.0851 0.1273 1.0851 1.0417
No log 22.3333 134 0.9288 -0.0033 0.9288 0.9637
No log 22.6667 136 0.8554 -0.0326 0.8554 0.9249
No log 23.0 138 0.9672 0.0192 0.9672 0.9835
No log 23.3333 140 0.9087 0.0494 0.9087 0.9533
No log 23.6667 142 1.1079 0.0225 1.1079 1.0526
No log 24.0 144 1.1600 -0.0159 1.1600 1.0771
No log 24.3333 146 0.9404 -0.0171 0.9404 0.9697
No log 24.6667 148 0.9017 0.0192 0.9017 0.9496
No log 25.0 150 0.8737 0.0947 0.8737 0.9347
No log 25.3333 152 0.9176 -0.1197 0.9176 0.9579
No log 25.6667 154 1.0011 -0.0787 1.0011 1.0005
No log 26.0 156 0.8483 -0.0672 0.8483 0.9211
No log 26.3333 158 0.8257 0.0834 0.8257 0.9087
No log 26.6667 160 0.9019 -0.1144 0.9019 0.9497
No log 27.0 162 0.9239 -0.1093 0.9239 0.9612
No log 27.3333 164 0.8900 0.0725 0.8900 0.9434
No log 27.6667 166 0.8842 0.0851 0.8842 0.9403
No log 28.0 168 0.8958 -0.0643 0.8958 0.9465
No log 28.3333 170 0.8807 -0.0260 0.8807 0.9385
No log 28.6667 172 0.8457 0.0049 0.8457 0.9196
No log 29.0 174 0.9149 0.0637 0.9149 0.9565
No log 29.3333 176 0.9312 -0.0111 0.9312 0.9650
No log 29.6667 178 0.8376 -0.0026 0.8376 0.9152
No log 30.0 180 0.9720 -0.0054 0.9720 0.9859
No log 30.3333 182 1.1032 0.0753 1.1032 1.0503
No log 30.6667 184 0.9559 0.0038 0.9559 0.9777
No log 31.0 186 0.8902 0.0049 0.8902 0.9435
No log 31.3333 188 0.8956 -0.0238 0.8956 0.9464
No log 31.6667 190 0.8262 -0.0821 0.8262 0.9090
No log 32.0 192 0.8161 0.0236 0.8161 0.9034
No log 32.3333 194 0.8617 0.0442 0.8617 0.9283
No log 32.6667 196 0.8062 0.1199 0.8062 0.8979
No log 33.0 198 0.8105 -0.0821 0.8105 0.9003
No log 33.3333 200 0.8802 0.0200 0.8802 0.9382
No log 33.6667 202 0.8624 0.0119 0.8624 0.9286
No log 34.0 204 0.8567 0.0376 0.8567 0.9256
No log 34.3333 206 0.8484 0.0277 0.8484 0.9211
No log 34.6667 208 0.8571 0.0660 0.8571 0.9258
No log 35.0 210 0.8159 -0.0108 0.8159 0.9033
No log 35.3333 212 0.8200 -0.0407 0.8200 0.9056
No log 35.6667 214 0.7955 -0.0056 0.7955 0.8919
No log 36.0 216 0.8426 0.0831 0.8426 0.9179
No log 36.3333 218 1.0023 0.0233 1.0023 1.0012
No log 36.6667 220 1.0014 0.0260 1.0014 1.0007
No log 37.0 222 0.8872 0.0470 0.8872 0.9419
No log 37.3333 224 0.9185 0.0172 0.9185 0.9584
No log 37.6667 226 1.0297 -0.0762 1.0297 1.0148
No log 38.0 228 0.9523 0.0220 0.9523 0.9759
No log 38.3333 230 0.8529 0.0359 0.8529 0.9235
No log 38.6667 232 0.9474 0.0762 0.9474 0.9733
No log 39.0 234 1.0047 0.0585 1.0047 1.0023
No log 39.3333 236 0.8922 0.0016 0.8922 0.9446
No log 39.6667 238 0.8036 -0.0113 0.8036 0.8964
No log 40.0 240 0.7915 0.0930 0.7915 0.8896
No log 40.3333 242 0.8358 0.0606 0.8358 0.9142
No log 40.6667 244 0.8391 0.0595 0.8391 0.9160
No log 41.0 246 0.7985 0.0449 0.7985 0.8936
No log 41.3333 248 0.8385 0.0700 0.8385 0.9157
No log 41.6667 250 0.8742 0.0140 0.8742 0.9350
No log 42.0 252 0.8733 0.0216 0.8733 0.9345
No log 42.3333 254 0.8732 0.1327 0.8732 0.9345
No log 42.6667 256 0.8734 0.1327 0.8734 0.9346
No log 43.0 258 0.8562 0.1340 0.8562 0.9253
No log 43.3333 260 0.8477 0.0879 0.8477 0.9207
No log 43.6667 262 0.8516 0.0709 0.8516 0.9228
No log 44.0 264 0.8307 0.0308 0.8307 0.9114
No log 44.3333 266 0.8278 -0.0186 0.8278 0.9098
No log 44.6667 268 0.7985 0.0449 0.7985 0.8936
No log 45.0 270 0.7965 0.0449 0.7965 0.8925
No log 45.3333 272 0.8223 0.0341 0.8223 0.9068
No log 45.6667 274 0.8558 0.0709 0.8558 0.9251
No log 46.0 276 0.8764 0.0889 0.8764 0.9362
No log 46.3333 278 0.8812 0.0949 0.8812 0.9387
No log 46.6667 280 0.8776 0.0559 0.8776 0.9368
No log 47.0 282 0.8562 0.0949 0.8562 0.9253
No log 47.3333 284 0.8402 0.0944 0.8402 0.9166
No log 47.6667 286 0.8205 0.0840 0.8205 0.9058
No log 48.0 288 0.8217 0.0749 0.8217 0.9065
No log 48.3333 290 0.8259 0.0840 0.8259 0.9088
No log 48.6667 292 0.8321 0.0884 0.8321 0.9122
No log 49.0 294 0.8541 0.1094 0.8541 0.9242
No log 49.3333 296 0.9177 -0.0291 0.9177 0.9580
No log 49.6667 298 0.9040 -0.0291 0.9040 0.9508
No log 50.0 300 0.8587 0.0840 0.8587 0.9267
No log 50.3333 302 0.8834 0.0559 0.8834 0.9399
No log 50.6667 304 0.8662 0.0902 0.8662 0.9307
No log 51.0 306 0.8545 0.0376 0.8545 0.9244
No log 51.3333 308 0.8475 0.0791 0.8475 0.9206
No log 51.6667 310 0.8497 0.0622 0.8497 0.9218
No log 52.0 312 0.8447 0.0068 0.8447 0.9191
No log 52.3333 314 0.8100 0.1254 0.8100 0.9000
No log 52.6667 316 0.7713 0.0394 0.7713 0.8783
No log 53.0 318 0.8009 0.0583 0.8009 0.8949
No log 53.3333 320 0.8169 0.0545 0.8169 0.9039
No log 53.6667 322 0.7913 0.0449 0.7913 0.8896
No log 54.0 324 0.8021 0.0776 0.8021 0.8956
No log 54.3333 326 0.8213 0.1096 0.8213 0.9062
No log 54.6667 328 0.8012 0.0776 0.8012 0.8951
No log 55.0 330 0.7843 0.0394 0.7843 0.8856
No log 55.3333 332 0.8227 0.1032 0.8227 0.9070
No log 55.6667 334 0.8297 0.1032 0.8297 0.9109
No log 56.0 336 0.8016 0.0930 0.8016 0.8953
No log 56.3333 338 0.7922 0.0732 0.7922 0.8901
No log 56.6667 340 0.8520 0.0999 0.8520 0.9230
No log 57.0 342 0.9098 -0.0425 0.9098 0.9538
No log 57.3333 344 0.9137 -0.0425 0.9137 0.9559
No log 57.6667 346 0.8363 0.1047 0.8363 0.9145
No log 58.0 348 0.7976 0.0394 0.7976 0.8931
No log 58.3333 350 0.8073 0.0940 0.8073 0.8985
No log 58.6667 352 0.8085 0.1379 0.8085 0.8992
No log 59.0 354 0.7932 0.0432 0.7932 0.8906
No log 59.3333 356 0.7877 0.0432 0.7877 0.8875
No log 59.6667 358 0.7904 0.0432 0.7904 0.8890
No log 60.0 360 0.7952 -0.0170 0.7952 0.8917
No log 60.3333 362 0.7804 0.0869 0.7804 0.8834
No log 60.6667 364 0.7551 0.0414 0.7551 0.8690
No log 61.0 366 0.7495 0.0432 0.7495 0.8657
No log 61.3333 368 0.7590 0.0543 0.7590 0.8712
No log 61.6667 370 0.7608 0.1028 0.7608 0.8722
No log 62.0 372 0.7552 0.0432 0.7552 0.8690
No log 62.3333 374 0.7684 0.0432 0.7684 0.8766
No log 62.6667 376 0.7845 0.0874 0.7845 0.8857
No log 63.0 378 0.8086 0.2222 0.8086 0.8992
No log 63.3333 380 0.8226 0.2589 0.8226 0.9070
No log 63.6667 382 0.8286 0.1689 0.8286 0.9103
No log 64.0 384 0.8635 -0.0260 0.8635 0.9292
No log 64.3333 386 0.8753 -0.0679 0.8753 0.9356
No log 64.6667 388 0.8557 0.0161 0.8557 0.9251
No log 65.0 390 0.8268 0.1630 0.8268 0.9093
No log 65.3333 392 0.8117 0.2153 0.8117 0.9009
No log 65.6667 394 0.8089 0.2194 0.8089 0.8994
No log 66.0 396 0.7973 0.1796 0.7973 0.8929
No log 66.3333 398 0.7919 0.1244 0.7919 0.8899
No log 66.6667 400 0.8197 0.1144 0.8197 0.9053
No log 67.0 402 0.8457 0.0512 0.8457 0.9196
No log 67.3333 404 0.8401 0.0512 0.8401 0.9165
No log 67.6667 406 0.7983 0.2180 0.7983 0.8935
No log 68.0 408 0.7656 0.0821 0.7656 0.8750
No log 68.3333 410 0.7635 0.0828 0.7635 0.8738
No log 68.6667 412 0.7756 0.1249 0.7756 0.8807
No log 69.0 414 0.7901 0.1192 0.7901 0.8889
No log 69.3333 416 0.7997 0.1192 0.7997 0.8942
No log 69.6667 418 0.8014 0.1192 0.8014 0.8952
No log 70.0 420 0.8106 0.1096 0.8106 0.9004
No log 70.3333 422 0.8395 0.0041 0.8395 0.9162
No log 70.6667 424 0.8437 0.0016 0.8437 0.9185
No log 71.0 426 0.8133 0.1047 0.8133 0.9018
No log 71.3333 428 0.7787 0.1675 0.7787 0.8825
No log 71.6667 430 0.7638 0.1740 0.7638 0.8740
No log 72.0 432 0.7548 0.0394 0.7548 0.8688
No log 72.3333 434 0.7535 0.0375 0.7535 0.8681
No log 72.6667 436 0.7629 0.1249 0.7629 0.8734
No log 73.0 438 0.7891 0.1627 0.7891 0.8883
No log 73.3333 440 0.8110 0.1097 0.8110 0.9006
No log 73.6667 442 0.8149 0.1097 0.8149 0.9027
No log 74.0 444 0.7956 0.0690 0.7956 0.8920
No log 74.3333 446 0.7878 0.1244 0.7878 0.8876
No log 74.6667 448 0.7940 0.0690 0.7940 0.8911
No log 75.0 450 0.8209 0.0123 0.8209 0.9060
No log 75.3333 452 0.8424 0.0043 0.8424 0.9178
No log 75.6667 454 0.8316 0.0512 0.8316 0.9119
No log 76.0 456 0.8145 0.0123 0.8145 0.9025
No log 76.3333 458 0.8121 0.0175 0.8121 0.9011
No log 76.6667 460 0.8129 0.0146 0.8129 0.9016
No log 77.0 462 0.8091 0.0205 0.8091 0.8995
No log 77.3333 464 0.8122 0.0205 0.8122 0.9012
No log 77.6667 466 0.8338 0.0146 0.8338 0.9131
No log 78.0 468 0.8408 0.0146 0.8408 0.9170
No log 78.3333 470 0.8372 0.0146 0.8372 0.9150
No log 78.6667 472 0.8344 0.0562 0.8344 0.9135
No log 79.0 474 0.8095 0.0205 0.8095 0.8997
No log 79.3333 476 0.7876 0.0690 0.7876 0.8875
No log 79.6667 478 0.7699 0.1249 0.7699 0.8774
No log 80.0 480 0.7639 0.1249 0.7639 0.8740
No log 80.3333 482 0.7621 0.0874 0.7621 0.8730
No log 80.6667 484 0.7589 0.0874 0.7589 0.8711
No log 81.0 486 0.7557 0.0869 0.7557 0.8693
No log 81.3333 488 0.7520 0.0821 0.7520 0.8672
No log 81.6667 490 0.7495 0.1249 0.7495 0.8657
No log 82.0 492 0.7469 0.1249 0.7469 0.8642
No log 82.3333 494 0.7467 0.1249 0.7467 0.8641
No log 82.6667 496 0.7499 0.1249 0.7499 0.8659
No log 83.0 498 0.7582 0.1249 0.7582 0.8708
0.192 83.3333 500 0.7632 0.1249 0.7632 0.8736
0.192 83.6667 502 0.7692 0.1249 0.7692 0.8771
0.192 84.0 504 0.7688 0.1249 0.7688 0.8768
0.192 84.3333 506 0.7721 0.1249 0.7721 0.8787
0.192 84.6667 508 0.7822 0.0732 0.7822 0.8844
0.192 85.0 510 0.7947 0.0732 0.7947 0.8915

Framework versions

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