ArabicNewSplits7_FineTuningAraBERT_run3_AugV5_k12_task1_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: 0.6873
  • Qwk: 0.7083
  • Mse: 0.6873
  • Rmse: 0.8290

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 0.0357 2 6.6058 0.0179 6.6058 2.5702
No log 0.0714 4 4.2642 0.0267 4.2642 2.0650
No log 0.1071 6 2.7138 0.0633 2.7138 1.6474
No log 0.1429 8 2.2901 0.1233 2.2901 1.5133
No log 0.1786 10 1.9609 0.2295 1.9609 1.4003
No log 0.2143 12 1.7845 0.1982 1.7845 1.3359
No log 0.25 14 1.9466 0.2295 1.9466 1.3952
No log 0.2857 16 1.7824 0.2105 1.7824 1.3351
No log 0.3214 18 1.5792 0.2243 1.5792 1.2567
No log 0.3571 20 1.9464 0.1440 1.9464 1.3951
No log 0.3929 22 2.9688 0.0633 2.9688 1.7230
No log 0.4286 24 2.7854 0.0392 2.7854 1.6690
No log 0.4643 26 2.1139 0.1679 2.1139 1.4539
No log 0.5 28 1.5507 0.3252 1.5507 1.2453
No log 0.5357 30 1.3208 0.3009 1.3208 1.1493
No log 0.5714 32 1.2703 0.3091 1.2703 1.1271
No log 0.6071 34 1.5034 0.2243 1.5034 1.2261
No log 0.6429 36 1.8511 0.1346 1.8511 1.3606
No log 0.6786 38 1.6610 0.2075 1.6610 1.2888
No log 0.7143 40 1.2975 0.3393 1.2975 1.1391
No log 0.75 42 1.1569 0.4615 1.1569 1.0756
No log 0.7857 44 1.1056 0.5238 1.1056 1.0515
No log 0.8214 46 1.1171 0.5312 1.1171 1.0569
No log 0.8571 48 1.1044 0.5197 1.1044 1.0509
No log 0.8929 50 1.1045 0.5 1.1045 1.0509
No log 0.9286 52 1.1086 0.4754 1.1086 1.0529
No log 0.9643 54 1.1098 0.4918 1.1098 1.0534
No log 1.0 56 1.0842 0.4918 1.0842 1.0412
No log 1.0357 58 1.0521 0.4878 1.0521 1.0257
No log 1.0714 60 1.0350 0.5760 1.0350 1.0173
No log 1.1071 62 1.3422 0.4167 1.3422 1.1586
No log 1.1429 64 1.5860 0.3636 1.5860 1.2594
No log 1.1786 66 1.3925 0.4132 1.3925 1.1800
No log 1.2143 68 1.0482 0.5970 1.0482 1.0238
No log 1.25 70 0.9976 0.6522 0.9976 0.9988
No log 1.2857 72 0.9308 0.6131 0.9308 0.9648
No log 1.3214 74 1.0140 0.5821 1.0140 1.0070
No log 1.3571 76 1.6188 0.2969 1.6188 1.2723
No log 1.3929 78 1.9134 0.2080 1.9134 1.3833
No log 1.4286 80 1.6814 0.2656 1.6814 1.2967
No log 1.4643 82 1.3216 0.4186 1.3216 1.1496
No log 1.5 84 0.9748 0.6462 0.9748 0.9873
No log 1.5357 86 0.9671 0.5574 0.9671 0.9834
No log 1.5714 88 1.1233 0.5271 1.1233 1.0599
No log 1.6071 90 1.0428 0.5839 1.0428 1.0212
No log 1.6429 92 0.8449 0.6619 0.8449 0.9192
No log 1.6786 94 0.7773 0.6944 0.7773 0.8816
No log 1.7143 96 0.8418 0.6986 0.8418 0.9175
No log 1.75 98 0.8897 0.6800 0.8897 0.9433
No log 1.7857 100 0.8330 0.6849 0.8330 0.9127
No log 1.8214 102 0.7693 0.7468 0.7693 0.8771
No log 1.8571 104 0.7496 0.7451 0.7496 0.8658
No log 1.8929 106 0.9134 0.6623 0.9134 0.9557
No log 1.9286 108 0.9100 0.6447 0.9100 0.9539
No log 1.9643 110 0.7621 0.6986 0.7621 0.8730
No log 2.0 112 0.7728 0.7211 0.7728 0.8791
No log 2.0357 114 0.8176 0.6944 0.8176 0.9042
No log 2.0714 116 0.8449 0.6809 0.8449 0.9192
No log 2.1071 118 0.8800 0.6575 0.8800 0.9381
No log 2.1429 120 0.9320 0.6490 0.9320 0.9654
No log 2.1786 122 0.8841 0.6933 0.8841 0.9402
No log 2.2143 124 0.7999 0.7383 0.7999 0.8944
No log 2.25 126 0.8081 0.7162 0.8081 0.8989
No log 2.2857 128 0.7812 0.7792 0.7812 0.8838
No log 2.3214 130 0.8976 0.6974 0.8976 0.9474
No log 2.3571 132 1.0852 0.6087 1.0852 1.0417
No log 2.3929 134 1.0691 0.6131 1.0691 1.0340
No log 2.4286 136 0.9661 0.6986 0.9661 0.9829
No log 2.4643 138 0.8222 0.6939 0.8222 0.9068
No log 2.5 140 0.6824 0.7595 0.6824 0.8261
No log 2.5357 142 0.6778 0.7595 0.6778 0.8233
No log 2.5714 144 0.6944 0.7329 0.6944 0.8333
No log 2.6071 146 0.7641 0.7179 0.7641 0.8741
No log 2.6429 148 0.7272 0.7320 0.7272 0.8528
No log 2.6786 150 0.8247 0.6939 0.8247 0.9081
No log 2.7143 152 0.9447 0.6711 0.9447 0.9720
No log 2.75 154 0.7376 0.7075 0.7376 0.8588
No log 2.7857 156 0.7775 0.7114 0.7775 0.8817
No log 2.8214 158 0.9990 0.5906 0.9990 0.9995
No log 2.8571 160 1.0353 0.5752 1.0353 1.0175
No log 2.8929 162 1.1321 0.5882 1.1321 1.0640
No log 2.9286 164 1.1226 0.6533 1.1226 1.0595
No log 2.9643 166 1.0666 0.6483 1.0666 1.0328
No log 3.0 168 1.0098 0.6621 1.0098 1.0049
No log 3.0357 170 0.9116 0.6853 0.9116 0.9548
No log 3.0714 172 0.8189 0.7050 0.8189 0.9049
No log 3.1071 174 0.7956 0.7 0.7956 0.8920
No log 3.1429 176 0.7588 0.7042 0.7588 0.8711
No log 3.1786 178 0.6739 0.7632 0.6739 0.8209
No log 3.2143 180 0.7761 0.7195 0.7761 0.8810
No log 3.25 182 0.9228 0.6788 0.9228 0.9606
No log 3.2857 184 0.7391 0.75 0.7391 0.8597
No log 3.3214 186 0.6308 0.7643 0.6308 0.7942
No log 3.3571 188 0.8103 0.7067 0.8103 0.9002
No log 3.3929 190 0.8286 0.6986 0.8286 0.9103
No log 3.4286 192 0.7478 0.7518 0.7478 0.8648
No log 3.4643 194 0.7444 0.7273 0.7444 0.8628
No log 3.5 196 0.7220 0.7682 0.7220 0.8497
No log 3.5357 198 0.7223 0.7123 0.7223 0.8499
No log 3.5714 200 0.7177 0.7123 0.7177 0.8472
No log 3.6071 202 0.7103 0.7123 0.7103 0.8428
No log 3.6429 204 0.7668 0.6897 0.7668 0.8757
No log 3.6786 206 0.7323 0.7436 0.7323 0.8558
No log 3.7143 208 0.6277 0.7742 0.6277 0.7923
No log 3.75 210 0.7196 0.775 0.7196 0.8483
No log 3.7857 212 0.7222 0.7673 0.7222 0.8498
No log 3.8214 214 0.6309 0.8 0.6309 0.7943
No log 3.8571 216 0.7744 0.6803 0.7744 0.8800
No log 3.8929 218 0.8862 0.6667 0.8862 0.9414
No log 3.9286 220 0.8276 0.6897 0.8276 0.9097
No log 3.9643 222 0.7997 0.7310 0.7997 0.8943
No log 4.0 224 0.7784 0.7383 0.7784 0.8823
No log 4.0357 226 0.8571 0.6803 0.8571 0.9258
No log 4.0714 228 1.0037 0.6309 1.0037 1.0018
No log 4.1071 230 1.0234 0.6625 1.0234 1.0116
No log 4.1429 232 0.8059 0.6835 0.8059 0.8977
No log 4.1786 234 0.6301 0.7564 0.6301 0.7938
No log 4.2143 236 0.6107 0.8415 0.6107 0.7815
No log 4.25 238 0.6538 0.7975 0.6538 0.8086
No log 4.2857 240 0.6148 0.8323 0.6148 0.7841
No log 4.3214 242 0.6933 0.7190 0.6933 0.8327
No log 4.3571 244 0.7078 0.72 0.7078 0.8413
No log 4.3929 246 0.6942 0.7755 0.6942 0.8332
No log 4.4286 248 0.6953 0.7483 0.6953 0.8339
No log 4.4643 250 0.6847 0.7568 0.6847 0.8275
No log 4.5 252 0.6898 0.7190 0.6898 0.8306
No log 4.5357 254 0.6576 0.7368 0.6576 0.8109
No log 4.5714 256 0.6140 0.7975 0.6140 0.7836
No log 4.6071 258 0.6493 0.8242 0.6493 0.8058
No log 4.6429 260 0.6245 0.8242 0.6245 0.7903
No log 4.6786 262 0.5883 0.8049 0.5883 0.7670
No log 4.7143 264 0.7161 0.7205 0.7161 0.8462
No log 4.75 266 0.7068 0.7485 0.7068 0.8407
No log 4.7857 268 0.6245 0.7432 0.6245 0.7903
No log 4.8214 270 0.6718 0.75 0.6718 0.8196
No log 4.8571 272 0.8139 0.6571 0.8139 0.9022
No log 4.8929 274 0.8239 0.6619 0.8239 0.9077
No log 4.9286 276 0.7584 0.7101 0.7584 0.8709
No log 4.9643 278 0.7301 0.7465 0.7301 0.8544
No log 5.0 280 0.7073 0.7606 0.7073 0.8410
No log 5.0357 282 0.6567 0.7552 0.6567 0.8104
No log 5.0714 284 0.6314 0.7871 0.6314 0.7946
No log 5.1071 286 0.6454 0.7975 0.6454 0.8034
No log 5.1429 288 0.6684 0.7975 0.6684 0.8175
No log 5.1786 290 0.6844 0.7799 0.6844 0.8273
No log 5.2143 292 0.7041 0.7333 0.7041 0.8391
No log 5.25 294 0.7048 0.7105 0.7048 0.8395
No log 5.2857 296 0.6852 0.7582 0.6852 0.8278
No log 5.3214 298 0.6898 0.7742 0.6898 0.8306
No log 5.3571 300 0.7372 0.7692 0.7372 0.8586
No log 5.3929 302 0.8882 0.6887 0.8882 0.9425
No log 5.4286 304 1.0514 0.5793 1.0514 1.0254
No log 5.4643 306 1.1073 0.5455 1.1073 1.0523
No log 5.5 308 1.0262 0.5468 1.0262 1.0130
No log 5.5357 310 0.8550 0.7 0.8550 0.9246
No log 5.5714 312 0.7759 0.7133 0.7759 0.8809
No log 5.6071 314 0.7603 0.7248 0.7603 0.8720
No log 5.6429 316 0.7364 0.7484 0.7364 0.8582
No log 5.6786 318 0.7051 0.7848 0.7051 0.8397
No log 5.7143 320 0.6866 0.8050 0.6866 0.8286
No log 5.75 322 0.6912 0.7867 0.6912 0.8314
No log 5.7857 324 0.7847 0.7183 0.7847 0.8858
No log 5.8214 326 0.8691 0.7234 0.8691 0.9322
No log 5.8571 328 0.8792 0.7059 0.8792 0.9377
No log 5.8929 330 0.8465 0.6618 0.8465 0.9200
No log 5.9286 332 0.7888 0.6667 0.7888 0.8881
No log 5.9643 334 0.7015 0.7534 0.7015 0.8375
No log 6.0 336 0.6199 0.7792 0.6199 0.7874
No log 6.0357 338 0.5811 0.7853 0.5811 0.7623
No log 6.0714 340 0.5511 0.8121 0.5511 0.7424
No log 6.1071 342 0.5578 0.8121 0.5578 0.7469
No log 6.1429 344 0.6028 0.8098 0.6028 0.7764
No log 6.1786 346 0.5941 0.7875 0.5941 0.7708
No log 6.2143 348 0.6123 0.8075 0.6123 0.7825
No log 6.25 350 0.6797 0.7368 0.6797 0.8244
No log 6.2857 352 0.7154 0.7417 0.7154 0.8458
No log 6.3214 354 0.8056 0.6944 0.8056 0.8976
No log 6.3571 356 0.8856 0.6099 0.8856 0.9411
No log 6.3929 358 0.8678 0.6099 0.8678 0.9315
No log 6.4286 360 0.7800 0.75 0.7800 0.8832
No log 6.4643 362 0.7208 0.7310 0.7208 0.8490
No log 6.5 364 0.7309 0.7467 0.7309 0.8549
No log 6.5357 366 0.6874 0.7467 0.6874 0.8291
No log 6.5714 368 0.6245 0.7662 0.6245 0.7902
No log 6.6071 370 0.6078 0.7742 0.6078 0.7796
No log 6.6429 372 0.6257 0.7848 0.6257 0.7910
No log 6.6786 374 0.6418 0.7922 0.6418 0.8011
No log 6.7143 376 0.6666 0.7451 0.6666 0.8165
No log 6.75 378 0.7242 0.7260 0.7242 0.8510
No log 6.7857 380 0.7169 0.7260 0.7169 0.8467
No log 6.8214 382 0.6740 0.75 0.6740 0.8210
No log 6.8571 384 0.6488 0.7867 0.6488 0.8055
No log 6.8929 386 0.7439 0.7417 0.7439 0.8625
No log 6.9286 388 0.8948 0.6345 0.8948 0.9459
No log 6.9643 390 0.7997 0.7114 0.7997 0.8943
No log 7.0 392 0.6088 0.7919 0.6088 0.7802
No log 7.0357 394 0.5895 0.7763 0.5895 0.7678
No log 7.0714 396 0.5778 0.7895 0.5778 0.7601
No log 7.1071 398 0.5855 0.8105 0.5855 0.7652
No log 7.1429 400 0.6134 0.7582 0.6134 0.7832
No log 7.1786 402 0.6356 0.7532 0.6356 0.7972
No log 7.2143 404 0.6962 0.6974 0.6962 0.8344
No log 7.25 406 0.8255 0.6933 0.8255 0.9086
No log 7.2857 408 0.9429 0.6933 0.9429 0.9710
No log 7.3214 410 0.9996 0.6528 0.9996 0.9998
No log 7.3571 412 0.9406 0.6803 0.9406 0.9699
No log 7.3929 414 0.7886 0.6713 0.7886 0.8880
No log 7.4286 416 0.7409 0.7273 0.7409 0.8608
No log 7.4643 418 0.7262 0.7361 0.7262 0.8522
No log 7.5 420 0.6984 0.7172 0.6984 0.8357
No log 7.5357 422 0.6845 0.7034 0.6845 0.8273
No log 7.5714 424 0.7235 0.6980 0.7235 0.8506
No log 7.6071 426 0.8140 0.7059 0.8140 0.9022
No log 7.6429 428 0.8351 0.7051 0.8351 0.9138
No log 7.6786 430 0.7041 0.7143 0.7041 0.8391
No log 7.7143 432 0.6097 0.8158 0.6097 0.7808
No log 7.75 434 0.7396 0.75 0.7396 0.8600
No log 7.7857 436 0.7847 0.6892 0.7847 0.8858
No log 7.8214 438 0.7195 0.7397 0.7195 0.8483
No log 7.8571 440 0.6645 0.7361 0.6645 0.8152
No log 7.8929 442 0.6651 0.7448 0.6651 0.8155
No log 7.9286 444 0.6374 0.7703 0.6374 0.7984
No log 7.9643 446 0.6563 0.7703 0.6563 0.8101
No log 8.0 448 0.7301 0.7114 0.7301 0.8545
No log 8.0357 450 0.6689 0.7368 0.6689 0.8179
No log 8.0714 452 0.5703 0.8182 0.5703 0.7552
No log 8.1071 454 0.5869 0.7643 0.5869 0.7661
No log 8.1429 456 0.6124 0.7547 0.6124 0.7826
No log 8.1786 458 0.5698 0.7742 0.5698 0.7548
No log 8.2143 460 0.5493 0.8105 0.5493 0.7411
No log 8.25 462 0.5781 0.8258 0.5781 0.7603
No log 8.2857 464 0.5561 0.8333 0.5561 0.7457
No log 8.3214 466 0.5524 0.7949 0.5524 0.7432
No log 8.3571 468 0.6288 0.7320 0.6288 0.7930
No log 8.3929 470 0.6597 0.7211 0.6597 0.8122
No log 8.4286 472 0.6437 0.7724 0.6437 0.8023
No log 8.4643 474 0.6382 0.7862 0.6382 0.7989
No log 8.5 476 0.6176 0.7945 0.6176 0.7859
No log 8.5357 478 0.5925 0.7733 0.5925 0.7698
No log 8.5714 480 0.5992 0.7368 0.5992 0.7741
No log 8.6071 482 0.5837 0.7785 0.5837 0.7640
No log 8.6429 484 0.5697 0.8082 0.5697 0.7548
No log 8.6786 486 0.5433 0.8212 0.5433 0.7371
No log 8.7143 488 0.5389 0.8129 0.5389 0.7341
No log 8.75 490 0.6041 0.7836 0.6041 0.7772
No log 8.7857 492 0.6540 0.7771 0.6540 0.8087
No log 8.8214 494 0.6778 0.7586 0.6778 0.8233
No log 8.8571 496 0.6299 0.7403 0.6299 0.7937
No log 8.8929 498 0.5958 0.7808 0.5958 0.7719
0.4356 8.9286 500 0.5975 0.7808 0.5975 0.7730
0.4356 8.9643 502 0.6192 0.75 0.6192 0.7869
0.4356 9.0 504 0.6204 0.75 0.6204 0.7877
0.4356 9.0357 506 0.6639 0.7083 0.6639 0.8148
0.4356 9.0714 508 0.7116 0.6993 0.7116 0.8436
0.4356 9.1071 510 0.6873 0.7083 0.6873 0.8290

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
2
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_FineTuningAraBERT_run3_AugV5_k12_task1_organization

Finetuned
(4040)
this model