ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run2_AugV5_k18_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: 0.6210
  • Qwk: 0.4609
  • Mse: 0.6210
  • Rmse: 0.7880

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 0.0217 2 4.6581 -0.0183 4.6581 2.1583
No log 0.0435 4 2.9828 0.0227 2.9828 1.7271
No log 0.0652 6 1.7970 -0.0147 1.7970 1.3405
No log 0.0870 8 1.4768 -0.0410 1.4768 1.2153
No log 0.1087 10 1.3729 -0.0606 1.3729 1.1717
No log 0.1304 12 1.1036 -0.0007 1.1036 1.0505
No log 0.1522 14 1.1617 0.0781 1.1617 1.0778
No log 0.1739 16 0.8538 0.2034 0.8538 0.9240
No log 0.1957 18 0.8206 0.1543 0.8206 0.9059
No log 0.2174 20 0.8436 0.1505 0.8436 0.9185
No log 0.2391 22 0.8146 0.1405 0.8146 0.9026
No log 0.2609 24 1.2212 0.2254 1.2212 1.1051
No log 0.2826 26 1.4730 0.1110 1.4730 1.2137
No log 0.3043 28 1.2595 0.1079 1.2595 1.1223
No log 0.3261 30 0.9000 0.1780 0.9000 0.9487
No log 0.3478 32 0.7005 0.3486 0.7005 0.8370
No log 0.3696 34 0.6581 0.2618 0.6581 0.8112
No log 0.3913 36 0.6702 0.2027 0.6702 0.8187
No log 0.4130 38 0.6651 0.2324 0.6651 0.8156
No log 0.4348 40 0.6328 0.2769 0.6328 0.7955
No log 0.4565 42 0.6460 0.4033 0.6460 0.8037
No log 0.4783 44 0.7341 0.3226 0.7341 0.8568
No log 0.5 46 0.8600 0.2892 0.8600 0.9273
No log 0.5217 48 0.9402 0.2947 0.9402 0.9696
No log 0.5435 50 1.0115 0.2611 1.0115 1.0057
No log 0.5652 52 0.9421 0.2481 0.9421 0.9706
No log 0.5870 54 0.8204 0.3612 0.8204 0.9058
No log 0.6087 56 0.7208 0.4139 0.7208 0.8490
No log 0.6304 58 0.6127 0.4421 0.6127 0.7827
No log 0.6522 60 0.6134 0.3538 0.6134 0.7832
No log 0.6739 62 0.5990 0.5244 0.5990 0.7740
No log 0.6957 64 0.6488 0.4444 0.6488 0.8055
No log 0.7174 66 0.6384 0.4513 0.6384 0.7990
No log 0.7391 68 0.6947 0.4571 0.6947 0.8335
No log 0.7609 70 0.7576 0.5010 0.7576 0.8704
No log 0.7826 72 0.9306 0.3931 0.9306 0.9647
No log 0.8043 74 0.8819 0.4199 0.8819 0.9391
No log 0.8261 76 0.7890 0.4673 0.7890 0.8883
No log 0.8478 78 0.7345 0.4630 0.7345 0.8570
No log 0.8696 80 0.7589 0.4630 0.7589 0.8711
No log 0.8913 82 0.7975 0.4767 0.7975 0.8930
No log 0.9130 84 0.9517 0.3722 0.9517 0.9756
No log 0.9348 86 1.2476 0.2778 1.2476 1.1170
No log 0.9565 88 1.2857 0.2480 1.2857 1.1339
No log 0.9783 90 1.0334 0.2524 1.0334 1.0165
No log 1.0 92 0.6668 0.4638 0.6668 0.8166
No log 1.0217 94 0.5977 0.5206 0.5977 0.7731
No log 1.0435 96 0.6250 0.5101 0.6250 0.7906
No log 1.0652 98 0.5967 0.5096 0.5967 0.7725
No log 1.0870 100 0.5885 0.4636 0.5885 0.7671
No log 1.1087 102 0.5910 0.5282 0.5910 0.7688
No log 1.1304 104 0.6078 0.5638 0.6078 0.7796
No log 1.1522 106 0.6146 0.5398 0.6146 0.7840
No log 1.1739 108 0.6257 0.5514 0.6257 0.7910
No log 1.1957 110 0.6281 0.5593 0.6281 0.7926
No log 1.2174 112 0.6266 0.5574 0.6266 0.7916
No log 1.2391 114 0.6427 0.5097 0.6427 0.8017
No log 1.2609 116 0.7232 0.5306 0.7232 0.8504
No log 1.2826 118 0.6676 0.5645 0.6676 0.8170
No log 1.3043 120 0.6214 0.5197 0.6214 0.7883
No log 1.3261 122 0.6511 0.5499 0.6511 0.8069
No log 1.3478 124 0.6394 0.5594 0.6394 0.7996
No log 1.3696 126 0.6183 0.5474 0.6183 0.7864
No log 1.3913 128 0.6230 0.5474 0.6230 0.7893
No log 1.4130 130 0.7057 0.4908 0.7057 0.8401
No log 1.4348 132 0.7682 0.4823 0.7682 0.8765
No log 1.4565 134 0.6600 0.5540 0.6600 0.8124
No log 1.4783 136 0.6445 0.5751 0.6445 0.8028
No log 1.5 138 0.6670 0.5657 0.6670 0.8167
No log 1.5217 140 0.5923 0.5215 0.5923 0.7696
No log 1.5435 142 0.6353 0.5521 0.6353 0.7971
No log 1.5652 144 0.6807 0.5101 0.6807 0.8250
No log 1.5870 146 0.6462 0.5039 0.6462 0.8039
No log 1.6087 148 0.5883 0.4611 0.5883 0.7670
No log 1.6304 150 0.6040 0.4265 0.6040 0.7772
No log 1.6522 152 0.6295 0.4572 0.6295 0.7934
No log 1.6739 154 0.6342 0.4858 0.6342 0.7964
No log 1.6957 156 0.6778 0.5653 0.6778 0.8233
No log 1.7174 158 0.8514 0.4539 0.8514 0.9227
No log 1.7391 160 0.8155 0.5146 0.8155 0.9030
No log 1.7609 162 0.7597 0.5492 0.7597 0.8716
No log 1.7826 164 0.8027 0.5381 0.8027 0.8959
No log 1.8043 166 0.8361 0.5289 0.8361 0.9144
No log 1.8261 168 0.7939 0.5381 0.7939 0.8910
No log 1.8478 170 0.7732 0.5371 0.7732 0.8793
No log 1.8696 172 0.7089 0.5086 0.7089 0.8420
No log 1.8913 174 0.7370 0.4887 0.7370 0.8585
No log 1.9130 176 0.7515 0.4269 0.7515 0.8669
No log 1.9348 178 0.6376 0.5077 0.6376 0.7985
No log 1.9565 180 0.6071 0.4621 0.6071 0.7792
No log 1.9783 182 0.6741 0.4601 0.6741 0.8210
No log 2.0 184 0.8180 0.4245 0.8180 0.9044
No log 2.0217 186 0.8652 0.4194 0.8652 0.9302
No log 2.0435 188 0.7980 0.4202 0.7980 0.8933
No log 2.0652 190 0.6674 0.5678 0.6674 0.8170
No log 2.0870 192 0.6537 0.5637 0.6537 0.8085
No log 2.1087 194 0.6775 0.5108 0.6775 0.8231
No log 2.1304 196 0.6215 0.5507 0.6215 0.7883
No log 2.1522 198 0.6186 0.5144 0.6186 0.7865
No log 2.1739 200 0.6616 0.5054 0.6616 0.8134
No log 2.1957 202 0.5992 0.5462 0.5992 0.7741
No log 2.2174 204 0.6667 0.5205 0.6667 0.8165
No log 2.2391 206 0.8181 0.4716 0.8181 0.9045
No log 2.2609 208 0.7356 0.5328 0.7356 0.8577
No log 2.2826 210 0.6108 0.5316 0.6108 0.7815
No log 2.3043 212 0.5989 0.4810 0.5989 0.7739
No log 2.3261 214 0.6400 0.4971 0.6400 0.8000
No log 2.3478 216 0.6865 0.5002 0.6865 0.8285
No log 2.3696 218 0.6424 0.5294 0.6424 0.8015
No log 2.3913 220 0.6653 0.4878 0.6653 0.8157
No log 2.4130 222 0.6668 0.4765 0.6668 0.8166
No log 2.4348 224 0.6442 0.5124 0.6442 0.8026
No log 2.4565 226 0.6733 0.4608 0.6733 0.8205
No log 2.4783 228 0.6701 0.4339 0.6701 0.8186
No log 2.5 230 0.5993 0.4394 0.5993 0.7741
No log 2.5217 232 0.5947 0.5213 0.5947 0.7712
No log 2.5435 234 0.5762 0.4570 0.5762 0.7591
No log 2.5652 236 0.6306 0.4840 0.6306 0.7941
No log 2.5870 238 0.6804 0.4949 0.6804 0.8249
No log 2.6087 240 0.6093 0.5257 0.6093 0.7806
No log 2.6304 242 0.5851 0.5170 0.5851 0.7649
No log 2.6522 244 0.5902 0.4796 0.5902 0.7682
No log 2.6739 246 0.6004 0.5294 0.6004 0.7748
No log 2.6957 248 0.6903 0.4905 0.6903 0.8308
No log 2.7174 250 0.7680 0.4643 0.7680 0.8763
No log 2.7391 252 0.6888 0.5501 0.6888 0.8299
No log 2.7609 254 0.6519 0.5062 0.6519 0.8074
No log 2.7826 256 0.6215 0.5699 0.6215 0.7883
No log 2.8043 258 0.6478 0.5773 0.6478 0.8049
No log 2.8261 260 0.7408 0.5274 0.7408 0.8607
No log 2.8478 262 0.9677 0.4245 0.9677 0.9837
No log 2.8696 264 0.9934 0.4122 0.9934 0.9967
No log 2.8913 266 0.8591 0.4734 0.8591 0.9269
No log 2.9130 268 0.6470 0.5751 0.6470 0.8043
No log 2.9348 270 0.6212 0.4813 0.6212 0.7881
No log 2.9565 272 0.6262 0.4999 0.6262 0.7913
No log 2.9783 274 0.5850 0.5051 0.5850 0.7648
No log 3.0 276 0.5727 0.4693 0.5727 0.7568
No log 3.0217 278 0.5702 0.4948 0.5702 0.7551
No log 3.0435 280 0.5815 0.4823 0.5815 0.7625
No log 3.0652 282 0.5966 0.48 0.5966 0.7724
No log 3.0870 284 0.6107 0.4714 0.6107 0.7815
No log 3.1087 286 0.6009 0.4766 0.6009 0.7752
No log 3.1304 288 0.5867 0.5051 0.5867 0.7660
No log 3.1522 290 0.5887 0.5080 0.5887 0.7673
No log 3.1739 292 0.6361 0.4812 0.6361 0.7976
No log 3.1957 294 0.6657 0.4765 0.6657 0.8159
No log 3.2174 296 0.5951 0.5556 0.5951 0.7714
No log 3.2391 298 0.5806 0.5032 0.5806 0.7620
No log 3.2609 300 0.5980 0.4582 0.5980 0.7733
No log 3.2826 302 0.6140 0.4733 0.6140 0.7836
No log 3.3043 304 0.5871 0.4623 0.5871 0.7663
No log 3.3261 306 0.6022 0.5213 0.6022 0.7760
No log 3.3478 308 0.5996 0.5012 0.5996 0.7743
No log 3.3696 310 0.5904 0.4591 0.5904 0.7684
No log 3.3913 312 0.6039 0.4703 0.6039 0.7771
No log 3.4130 314 0.5890 0.4002 0.5890 0.7674
No log 3.4348 316 0.6014 0.4235 0.6014 0.7755
No log 3.4565 318 0.6468 0.5660 0.6468 0.8042
No log 3.4783 320 0.6133 0.5089 0.6133 0.7831
No log 3.5 322 0.5906 0.4657 0.5906 0.7685
No log 3.5217 324 0.5734 0.4355 0.5734 0.7572
No log 3.5435 326 0.5775 0.4400 0.5775 0.7599
No log 3.5652 328 0.5981 0.4739 0.5981 0.7734
No log 3.5870 330 0.6180 0.4448 0.6180 0.7861
No log 3.6087 332 0.5896 0.3980 0.5896 0.7679
No log 3.6304 334 0.5963 0.4255 0.5963 0.7722
No log 3.6522 336 0.6013 0.4566 0.6013 0.7754
No log 3.6739 338 0.6105 0.4868 0.6105 0.7813
No log 3.6957 340 0.6400 0.4519 0.6400 0.8000
No log 3.7174 342 0.6565 0.4496 0.6565 0.8103
No log 3.7391 344 0.6068 0.4839 0.6068 0.7790
No log 3.7609 346 0.5933 0.4614 0.5933 0.7702
No log 3.7826 348 0.5962 0.4757 0.5962 0.7721
No log 3.8043 350 0.6026 0.4512 0.6026 0.7763
No log 3.8261 352 0.6720 0.4285 0.6720 0.8197
No log 3.8478 354 0.6197 0.4353 0.6197 0.7872
No log 3.8696 356 0.5757 0.4235 0.5757 0.7587
No log 3.8913 358 0.6131 0.4598 0.6131 0.7830
No log 3.9130 360 0.6223 0.4728 0.6223 0.7889
No log 3.9348 362 0.5840 0.4632 0.5840 0.7642
No log 3.9565 364 0.6425 0.4748 0.6425 0.8016
No log 3.9783 366 0.6422 0.5010 0.6422 0.8014
No log 4.0 368 0.6564 0.4748 0.6564 0.8102
No log 4.0217 370 0.6238 0.5309 0.6238 0.7898
No log 4.0435 372 0.6031 0.5061 0.6031 0.7766
No log 4.0652 374 0.5892 0.5233 0.5892 0.7676
No log 4.0870 376 0.5674 0.4482 0.5674 0.7532
No log 4.1087 378 0.5651 0.4933 0.5651 0.7517
No log 4.1304 380 0.5623 0.4977 0.5623 0.7498
No log 4.1522 382 0.5697 0.5111 0.5697 0.7548
No log 4.1739 384 0.5795 0.5122 0.5795 0.7613
No log 4.1957 386 0.5862 0.4992 0.5862 0.7656
No log 4.2174 388 0.6154 0.5364 0.6154 0.7845
No log 4.2391 390 0.6902 0.5386 0.6902 0.8308
No log 4.2609 392 0.6898 0.5535 0.6898 0.8305
No log 4.2826 394 0.6113 0.4912 0.6113 0.7819
No log 4.3043 396 0.5846 0.4573 0.5846 0.7646
No log 4.3261 398 0.5943 0.5231 0.5943 0.7709
No log 4.3478 400 0.5797 0.4339 0.5797 0.7614
No log 4.3696 402 0.5677 0.4096 0.5677 0.7534
No log 4.3913 404 0.5588 0.4620 0.5588 0.7475
No log 4.4130 406 0.5552 0.4439 0.5552 0.7451
No log 4.4348 408 0.5597 0.4712 0.5597 0.7481
No log 4.4565 410 0.5651 0.4901 0.5651 0.7518
No log 4.4783 412 0.5590 0.5465 0.5590 0.7477
No log 4.5 414 0.5632 0.5672 0.5632 0.7505
No log 4.5217 416 0.5860 0.5370 0.5860 0.7655
No log 4.5435 418 0.5715 0.5370 0.5715 0.7560
No log 4.5652 420 0.5775 0.5289 0.5775 0.7600
No log 4.5870 422 0.5523 0.5584 0.5523 0.7432
No log 4.6087 424 0.5527 0.5940 0.5527 0.7435
No log 4.6304 426 0.5588 0.5935 0.5588 0.7475
No log 4.6522 428 0.5857 0.5363 0.5857 0.7653
No log 4.6739 430 0.5687 0.5790 0.5687 0.7541
No log 4.6957 432 0.5670 0.5414 0.5670 0.7530
No log 4.7174 434 0.6508 0.4137 0.6508 0.8067
No log 4.7391 436 0.6567 0.4077 0.6567 0.8104
No log 4.7609 438 0.6022 0.4898 0.6022 0.7760
No log 4.7826 440 0.5876 0.5057 0.5876 0.7666
No log 4.8043 442 0.5981 0.5649 0.5981 0.7733
No log 4.8261 444 0.6367 0.5217 0.6367 0.7979
No log 4.8478 446 0.6197 0.5264 0.6197 0.7872
No log 4.8696 448 0.5717 0.5287 0.5717 0.7561
No log 4.8913 450 0.5714 0.4655 0.5714 0.7559
No log 4.9130 452 0.5774 0.4451 0.5774 0.7599
No log 4.9348 454 0.5646 0.5260 0.5646 0.7514
No log 4.9565 456 0.5643 0.5409 0.5643 0.7512
No log 4.9783 458 0.5737 0.5287 0.5737 0.7574
No log 5.0 460 0.5712 0.5247 0.5712 0.7558
No log 5.0217 462 0.5849 0.5724 0.5849 0.7648
No log 5.0435 464 0.5990 0.5462 0.5990 0.7740
No log 5.0652 466 0.6392 0.4945 0.6392 0.7995
No log 5.0870 468 0.6402 0.4895 0.6402 0.8001
No log 5.1087 470 0.5894 0.4855 0.5894 0.7677
No log 5.1304 472 0.5896 0.4992 0.5896 0.7678
No log 5.1522 474 0.6103 0.5289 0.6103 0.7812
No log 5.1739 476 0.6107 0.5378 0.6107 0.7814
No log 5.1957 478 0.5791 0.4418 0.5791 0.7610
No log 5.2174 480 0.5947 0.4458 0.5947 0.7711
No log 5.2391 482 0.6036 0.4976 0.6036 0.7769
No log 5.2609 484 0.5769 0.4513 0.5769 0.7595
No log 5.2826 486 0.5696 0.4105 0.5696 0.7547
No log 5.3043 488 0.5686 0.4545 0.5686 0.7540
No log 5.3261 490 0.5654 0.4733 0.5654 0.7519
No log 5.3478 492 0.5596 0.4200 0.5596 0.7480
No log 5.3696 494 0.5581 0.4300 0.5581 0.7471
No log 5.3913 496 0.5631 0.4440 0.5631 0.7504
No log 5.4130 498 0.5787 0.4489 0.5787 0.7607
0.373 5.4348 500 0.6061 0.4910 0.6061 0.7786
0.373 5.4565 502 0.5845 0.4937 0.5845 0.7646
0.373 5.4783 504 0.5913 0.5090 0.5913 0.7689
0.373 5.5 506 0.5868 0.5124 0.5868 0.7660
0.373 5.5217 508 0.6091 0.4393 0.6091 0.7804
0.373 5.5435 510 0.6039 0.4393 0.6039 0.7771
0.373 5.5652 512 0.6530 0.4983 0.6530 0.8081
0.373 5.5870 514 0.6992 0.4816 0.6992 0.8362
0.373 5.6087 516 0.6450 0.4958 0.6450 0.8031
0.373 5.6304 518 0.5703 0.4824 0.5703 0.7552
0.373 5.6522 520 0.5639 0.4872 0.5639 0.7510
0.373 5.6739 522 0.5672 0.4840 0.5672 0.7531
0.373 5.6957 524 0.5806 0.4840 0.5806 0.7620
0.373 5.7174 526 0.6210 0.4609 0.6210 0.7880

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_run2_AugV5_k18_task2_organization

Finetuned
(4206)
this model