ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run3_AugV5_k2_task2_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: 0.5740
  • Qwk: 0.5582
  • Mse: 0.5740
  • Rmse: 0.7577

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 0.1538 2 4.3166 -0.0182 4.3166 2.0776
No log 0.3077 4 2.0843 0.0215 2.0843 1.4437
No log 0.4615 6 1.1484 -0.0111 1.1484 1.0716
No log 0.6154 8 0.8337 0.1201 0.8337 0.9131
No log 0.7692 10 0.8068 0.2451 0.8068 0.8982
No log 0.9231 12 1.0199 -0.0335 1.0199 1.0099
No log 1.0769 14 1.5561 0.1011 1.5561 1.2474
No log 1.2308 16 1.2655 0.0262 1.2655 1.1249
No log 1.3846 18 0.9307 0.1798 0.9307 0.9647
No log 1.5385 20 0.9386 0.1789 0.9386 0.9688
No log 1.6923 22 0.9229 0.2181 0.9229 0.9607
No log 1.8462 24 0.7977 0.2641 0.7977 0.8931
No log 2.0 26 0.6855 0.3686 0.6855 0.8279
No log 2.1538 28 0.6591 0.3407 0.6591 0.8119
No log 2.3077 30 0.7682 0.2751 0.7682 0.8765
No log 2.4615 32 1.0704 0.1400 1.0704 1.0346
No log 2.6154 34 1.0220 0.2000 1.0220 1.0110
No log 2.7692 36 0.7401 0.2859 0.7401 0.8603
No log 2.9231 38 0.6803 0.3668 0.6803 0.8248
No log 3.0769 40 0.6391 0.3655 0.6391 0.7994
No log 3.2308 42 0.6932 0.3668 0.6932 0.8326
No log 3.3846 44 0.8723 0.3535 0.8723 0.9340
No log 3.5385 46 0.8235 0.4066 0.8235 0.9075
No log 3.6923 48 0.7124 0.4085 0.7124 0.8440
No log 3.8462 50 0.8337 0.3710 0.8337 0.9131
No log 4.0 52 1.2769 0.3200 1.2769 1.1300
No log 4.1538 54 1.3296 0.2698 1.3296 1.1531
No log 4.3077 56 0.8080 0.4030 0.8080 0.8989
No log 4.4615 58 0.5909 0.5832 0.5909 0.7687
No log 4.6154 60 0.6067 0.5297 0.6067 0.7789
No log 4.7692 62 0.7153 0.4580 0.7153 0.8458
No log 4.9231 64 1.0223 0.2693 1.0223 1.0111
No log 5.0769 66 1.0004 0.2956 1.0004 1.0002
No log 5.2308 68 0.8143 0.4005 0.8143 0.9024
No log 5.3846 70 0.6096 0.4791 0.6096 0.7808
No log 5.5385 72 0.5470 0.5367 0.5470 0.7396
No log 5.6923 74 0.5499 0.5348 0.5499 0.7416
No log 5.8462 76 0.5558 0.5932 0.5558 0.7455
No log 6.0 78 0.5468 0.6171 0.5468 0.7395
No log 6.1538 80 0.5554 0.5755 0.5554 0.7453
No log 6.3077 82 0.6464 0.5197 0.6464 0.8040
No log 6.4615 84 0.6717 0.5045 0.6717 0.8196
No log 6.6154 86 0.6752 0.5394 0.6752 0.8217
No log 6.7692 88 0.6191 0.5860 0.6191 0.7869
No log 6.9231 90 0.7234 0.5735 0.7234 0.8505
No log 7.0769 92 0.8108 0.5761 0.8108 0.9004
No log 7.2308 94 0.8017 0.5777 0.8017 0.8954
No log 7.3846 96 0.7130 0.5655 0.7130 0.8444
No log 7.5385 98 0.7170 0.5353 0.7170 0.8468
No log 7.6923 100 0.6341 0.5730 0.6341 0.7963
No log 7.8462 102 0.5881 0.6089 0.5881 0.7669
No log 8.0 104 0.6092 0.5540 0.6092 0.7805
No log 8.1538 106 0.5621 0.5972 0.5621 0.7498
No log 8.3077 108 0.8307 0.4650 0.8307 0.9114
No log 8.4615 110 1.3354 0.3244 1.3354 1.1556
No log 8.6154 112 1.2251 0.3359 1.2251 1.1068
No log 8.7692 114 0.8733 0.4380 0.8733 0.9345
No log 8.9231 116 0.6120 0.5583 0.6120 0.7823
No log 9.0769 118 0.5930 0.5968 0.5930 0.7701
No log 9.2308 120 0.5794 0.5719 0.5794 0.7612
No log 9.3846 122 0.6149 0.5502 0.6149 0.7841
No log 9.5385 124 0.6253 0.5717 0.6253 0.7908
No log 9.6923 126 0.5867 0.5679 0.5867 0.7660
No log 9.8462 128 0.5932 0.5733 0.5932 0.7702
No log 10.0 130 0.7043 0.4465 0.7043 0.8393
No log 10.1538 132 0.6316 0.5452 0.6316 0.7947
No log 10.3077 134 0.5982 0.5152 0.5982 0.7734
No log 10.4615 136 0.5870 0.5662 0.5870 0.7661
No log 10.6154 138 0.6379 0.4895 0.6379 0.7987
No log 10.7692 140 0.6773 0.4741 0.6773 0.8230
No log 10.9231 142 0.6862 0.5269 0.6862 0.8284
No log 11.0769 144 0.6109 0.5259 0.6109 0.7816
No log 11.2308 146 0.5930 0.5385 0.5930 0.7700
No log 11.3846 148 0.6006 0.5508 0.6006 0.7750
No log 11.5385 150 0.5931 0.5467 0.5931 0.7702
No log 11.6923 152 0.6110 0.5613 0.6110 0.7816
No log 11.8462 154 0.6326 0.5724 0.6326 0.7954
No log 12.0 156 0.6190 0.5190 0.6190 0.7868
No log 12.1538 158 0.6447 0.5518 0.6447 0.8029
No log 12.3077 160 0.6761 0.5431 0.6761 0.8223
No log 12.4615 162 0.7183 0.5674 0.7183 0.8475
No log 12.6154 164 0.7084 0.5660 0.7084 0.8417
No log 12.7692 166 0.7161 0.5152 0.7161 0.8462
No log 12.9231 168 0.7082 0.5103 0.7082 0.8415
No log 13.0769 170 0.7004 0.5039 0.7004 0.8369
No log 13.2308 172 0.6535 0.5201 0.6535 0.8084
No log 13.3846 174 0.6000 0.5540 0.6000 0.7746
No log 13.5385 176 0.5964 0.5259 0.5964 0.7723
No log 13.6923 178 0.6162 0.5313 0.6162 0.7850
No log 13.8462 180 0.6061 0.5447 0.6061 0.7785
No log 14.0 182 0.6111 0.5808 0.6111 0.7817
No log 14.1538 184 0.6116 0.6021 0.6116 0.7821
No log 14.3077 186 0.6198 0.5753 0.6198 0.7873
No log 14.4615 188 0.6357 0.5907 0.6357 0.7973
No log 14.6154 190 0.6446 0.5628 0.6446 0.8029
No log 14.7692 192 0.6561 0.5915 0.6561 0.8100
No log 14.9231 194 0.6590 0.5754 0.6590 0.8118
No log 15.0769 196 0.6613 0.5851 0.6613 0.8132
No log 15.2308 198 0.6526 0.5872 0.6526 0.8078
No log 15.3846 200 0.6648 0.4991 0.6648 0.8153
No log 15.5385 202 0.6105 0.5499 0.6105 0.7814
No log 15.6923 204 0.5950 0.5757 0.5950 0.7713
No log 15.8462 206 0.5680 0.5560 0.5680 0.7537
No log 16.0 208 0.5635 0.5767 0.5635 0.7507
No log 16.1538 210 0.5725 0.5560 0.5725 0.7566
No log 16.3077 212 0.5931 0.5540 0.5931 0.7701
No log 16.4615 214 0.6073 0.5488 0.6073 0.7793
No log 16.6154 216 0.6170 0.6094 0.6170 0.7855
No log 16.7692 218 0.6059 0.5442 0.6059 0.7784
No log 16.9231 220 0.5896 0.5476 0.5896 0.7679
No log 17.0769 222 0.5934 0.5965 0.5934 0.7703
No log 17.2308 224 0.6235 0.5323 0.6235 0.7896
No log 17.3846 226 0.5803 0.5832 0.5803 0.7618
No log 17.5385 228 0.5612 0.6000 0.5612 0.7491
No log 17.6923 230 0.5804 0.5609 0.5804 0.7619
No log 17.8462 232 0.5921 0.6033 0.5921 0.7695
No log 18.0 234 0.6493 0.5634 0.6493 0.8058
No log 18.1538 236 0.7160 0.5595 0.7160 0.8462
No log 18.3077 238 0.6602 0.5634 0.6602 0.8125
No log 18.4615 240 0.6085 0.5958 0.6085 0.7801
No log 18.6154 242 0.6087 0.5420 0.6087 0.7802
No log 18.7692 244 0.6068 0.5570 0.6068 0.7790
No log 18.9231 246 0.5978 0.6000 0.5978 0.7732
No log 19.0769 248 0.6424 0.6101 0.6424 0.8015
No log 19.2308 250 0.6373 0.6100 0.6373 0.7983
No log 19.3846 252 0.6111 0.5689 0.6111 0.7817
No log 19.5385 254 0.5998 0.5420 0.5998 0.7745
No log 19.6923 256 0.5785 0.5875 0.5785 0.7606
No log 19.8462 258 0.5633 0.5816 0.5633 0.7505
No log 20.0 260 0.5699 0.5528 0.5699 0.7549
No log 20.1538 262 0.5742 0.5588 0.5742 0.7577
No log 20.3077 264 0.5676 0.5675 0.5676 0.7534
No log 20.4615 266 0.5787 0.5845 0.5787 0.7607
No log 20.6154 268 0.5854 0.5794 0.5854 0.7651
No log 20.7692 270 0.6018 0.5732 0.6018 0.7758
No log 20.9231 272 0.6101 0.5748 0.6101 0.7811
No log 21.0769 274 0.5999 0.5634 0.5999 0.7745
No log 21.2308 276 0.5755 0.6004 0.5755 0.7586
No log 21.3846 278 0.5764 0.5927 0.5764 0.7592
No log 21.5385 280 0.5695 0.5991 0.5695 0.7547
No log 21.6923 282 0.6902 0.4982 0.6902 0.8308
No log 21.8462 284 0.7838 0.4876 0.7838 0.8853
No log 22.0 286 0.7335 0.4734 0.7335 0.8565
No log 22.1538 288 0.6043 0.5569 0.6043 0.7774
No log 22.3077 290 0.6099 0.5291 0.6099 0.7809
No log 22.4615 292 0.6723 0.4971 0.6723 0.8199
No log 22.6154 294 0.6206 0.5386 0.6206 0.7878
No log 22.7692 296 0.5784 0.6049 0.5784 0.7605
No log 22.9231 298 0.5803 0.5932 0.5803 0.7618
No log 23.0769 300 0.6113 0.5722 0.6113 0.7819
No log 23.2308 302 0.5996 0.5705 0.5996 0.7743
No log 23.3846 304 0.5707 0.5658 0.5707 0.7554
No log 23.5385 306 0.5790 0.5681 0.5790 0.7609
No log 23.6923 308 0.6174 0.5710 0.6174 0.7857
No log 23.8462 310 0.6609 0.5311 0.6609 0.8130
No log 24.0 312 0.6601 0.5451 0.6601 0.8125
No log 24.1538 314 0.6304 0.5961 0.6304 0.7940
No log 24.3077 316 0.6300 0.5864 0.6300 0.7937
No log 24.4615 318 0.6495 0.5864 0.6495 0.8059
No log 24.6154 320 0.6751 0.5954 0.6751 0.8216
No log 24.7692 322 0.6698 0.5630 0.6698 0.8184
No log 24.9231 324 0.6769 0.5499 0.6769 0.8227
No log 25.0769 326 0.6889 0.5903 0.6889 0.8300
No log 25.2308 328 0.8172 0.4687 0.8172 0.9040
No log 25.3846 330 0.9111 0.4532 0.9111 0.9545
No log 25.5385 332 0.8508 0.4682 0.8508 0.9224
No log 25.6923 334 0.7333 0.5726 0.7333 0.8563
No log 25.8462 336 0.7399 0.5431 0.7399 0.8602
No log 26.0 338 0.7518 0.5606 0.7518 0.8671
No log 26.1538 340 0.7097 0.5436 0.7097 0.8424
No log 26.3077 342 0.6625 0.5542 0.6625 0.8139
No log 26.4615 344 0.6316 0.5701 0.6316 0.7947
No log 26.6154 346 0.6173 0.5787 0.6173 0.7857
No log 26.7692 348 0.6029 0.5901 0.6029 0.7765
No log 26.9231 350 0.6030 0.5907 0.6030 0.7765
No log 27.0769 352 0.6197 0.5912 0.6197 0.7872
No log 27.2308 354 0.6146 0.6004 0.6146 0.7839
No log 27.3846 356 0.6062 0.5829 0.6062 0.7786
No log 27.5385 358 0.6183 0.5179 0.6183 0.7863
No log 27.6923 360 0.6465 0.5779 0.6465 0.8040
No log 27.8462 362 0.6023 0.5725 0.6023 0.7761
No log 28.0 364 0.5663 0.6216 0.5663 0.7525
No log 28.1538 366 0.5673 0.5921 0.5673 0.7532
No log 28.3077 368 0.5891 0.6027 0.5891 0.7675
No log 28.4615 370 0.6038 0.5982 0.6038 0.7770
No log 28.6154 372 0.6444 0.5727 0.6444 0.8027
No log 28.7692 374 0.6937 0.5485 0.6937 0.8329
No log 28.9231 376 0.7086 0.5382 0.7086 0.8418
No log 29.0769 378 0.6423 0.5759 0.6423 0.8014
No log 29.2308 380 0.5755 0.6227 0.5755 0.7586
No log 29.3846 382 0.5606 0.5805 0.5606 0.7487
No log 29.5385 384 0.5545 0.6075 0.5545 0.7447
No log 29.6923 386 0.5713 0.6557 0.5713 0.7558
No log 29.8462 388 0.5733 0.6257 0.5733 0.7572
No log 30.0 390 0.5605 0.6478 0.5605 0.7487
No log 30.1538 392 0.5521 0.6128 0.5521 0.7430
No log 30.3077 394 0.5593 0.6313 0.5593 0.7479
No log 30.4615 396 0.5647 0.6143 0.5647 0.7514
No log 30.6154 398 0.5598 0.6031 0.5598 0.7482
No log 30.7692 400 0.5529 0.6134 0.5529 0.7436
No log 30.9231 402 0.5541 0.5863 0.5541 0.7444
No log 31.0769 404 0.5766 0.5595 0.5766 0.7594
No log 31.2308 406 0.5851 0.5576 0.5851 0.7649
No log 31.3846 408 0.5802 0.5989 0.5802 0.7617
No log 31.5385 410 0.5939 0.5988 0.5939 0.7706
No log 31.6923 412 0.6295 0.5816 0.6295 0.7934
No log 31.8462 414 0.6348 0.5318 0.6348 0.7968
No log 32.0 416 0.5894 0.6025 0.5894 0.7677
No log 32.1538 418 0.5873 0.5742 0.5873 0.7663
No log 32.3077 420 0.6661 0.5471 0.6661 0.8161
No log 32.4615 422 0.6914 0.5492 0.6914 0.8315
No log 32.6154 424 0.6486 0.5256 0.6486 0.8053
No log 32.7692 426 0.5781 0.5804 0.5781 0.7604
No log 32.9231 428 0.5705 0.6007 0.5705 0.7553
No log 33.0769 430 0.5963 0.5581 0.5963 0.7722
No log 33.2308 432 0.5858 0.6057 0.5858 0.7654
No log 33.3846 434 0.5581 0.6023 0.5581 0.7470
No log 33.5385 436 0.5552 0.5746 0.5552 0.7451
No log 33.6923 438 0.5499 0.5767 0.5499 0.7416
No log 33.8462 440 0.5448 0.5921 0.5448 0.7381
No log 34.0 442 0.5549 0.6065 0.5549 0.7449
No log 34.1538 444 0.5462 0.5799 0.5462 0.7391
No log 34.3077 446 0.5406 0.5827 0.5406 0.7353
No log 34.4615 448 0.5485 0.5789 0.5485 0.7406
No log 34.6154 450 0.5459 0.5887 0.5459 0.7388
No log 34.7692 452 0.5542 0.6020 0.5542 0.7444
No log 34.9231 454 0.5702 0.6018 0.5702 0.7551
No log 35.0769 456 0.5847 0.5843 0.5847 0.7647
No log 35.2308 458 0.5804 0.6128 0.5804 0.7619
No log 35.3846 460 0.5919 0.5877 0.5919 0.7694
No log 35.5385 462 0.5943 0.6016 0.5943 0.7709
No log 35.6923 464 0.5944 0.5794 0.5944 0.7710
No log 35.8462 466 0.5890 0.5872 0.5890 0.7675
No log 36.0 468 0.5800 0.5901 0.5800 0.7616
No log 36.1538 470 0.5976 0.5390 0.5976 0.7730
No log 36.3077 472 0.5806 0.5308 0.5806 0.7620
No log 36.4615 474 0.5507 0.5704 0.5507 0.7421
No log 36.6154 476 0.5499 0.5535 0.5499 0.7416
No log 36.7692 478 0.5503 0.5569 0.5503 0.7418
No log 36.9231 480 0.5526 0.5535 0.5526 0.7434
No log 37.0769 482 0.5537 0.5845 0.5537 0.7441
No log 37.2308 484 0.5617 0.5705 0.5617 0.7494
No log 37.3846 486 0.5783 0.5481 0.5783 0.7605
No log 37.5385 488 0.5681 0.5745 0.5681 0.7537
No log 37.6923 490 0.5650 0.5783 0.5650 0.7517
No log 37.8462 492 0.5636 0.5901 0.5636 0.7507
No log 38.0 494 0.5697 0.6065 0.5697 0.7548
No log 38.1538 496 0.5675 0.5784 0.5675 0.7533
No log 38.3077 498 0.5759 0.5868 0.5759 0.7589
0.2756 38.4615 500 0.5910 0.5815 0.5910 0.7688
0.2756 38.6154 502 0.5843 0.5693 0.5843 0.7644
0.2756 38.7692 504 0.5624 0.5901 0.5624 0.7499
0.2756 38.9231 506 0.5804 0.5784 0.5804 0.7618
0.2756 39.0769 508 0.6115 0.5738 0.6115 0.7820
0.2756 39.2308 510 0.6113 0.5659 0.6113 0.7819
0.2756 39.3846 512 0.5769 0.5668 0.5769 0.7595
0.2756 39.5385 514 0.5634 0.5957 0.5634 0.7506
0.2756 39.6923 516 0.5693 0.5827 0.5693 0.7545
0.2756 39.8462 518 0.5748 0.5827 0.5748 0.7581
0.2756 40.0 520 0.5905 0.5508 0.5905 0.7684
0.2756 40.1538 522 0.5973 0.5384 0.5973 0.7728
0.2756 40.3077 524 0.5959 0.5567 0.5959 0.7719
0.2756 40.4615 526 0.5811 0.5887 0.5811 0.7623
0.2756 40.6154 528 0.5801 0.5894 0.5801 0.7616
0.2756 40.7692 530 0.5846 0.5478 0.5846 0.7646
0.2756 40.9231 532 0.5938 0.5404 0.5938 0.7706
0.2756 41.0769 534 0.5872 0.5778 0.5872 0.7663
0.2756 41.2308 536 0.5907 0.5949 0.5907 0.7686
0.2756 41.3846 538 0.6027 0.6003 0.6027 0.7763
0.2756 41.5385 540 0.6283 0.5896 0.6283 0.7927
0.2756 41.6923 542 0.6599 0.5246 0.6599 0.8123
0.2756 41.8462 544 0.6607 0.5422 0.6607 0.8128
0.2756 42.0 546 0.6380 0.5348 0.6380 0.7988
0.2756 42.1538 548 0.6070 0.5264 0.6070 0.7791
0.2756 42.3077 550 0.5740 0.5582 0.5740 0.7577

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
4
Safetensors
Model size
135M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for MayBashendy/ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run3_AugV5_k2_task2_organization

Finetuned
(4206)
this model