ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k10_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: 0.5311
  • Qwk: 0.5959
  • Mse: 0.5311
  • Rmse: 0.7287

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 0.0741 2 4.0880 0.0024 4.0880 2.0219
No log 0.1481 4 2.3282 0.0541 2.3282 1.5258
No log 0.2222 6 2.0560 -0.0450 2.0560 1.4339
No log 0.2963 8 1.4911 0.0294 1.4911 1.2211
No log 0.3704 10 1.1092 0.3003 1.1092 1.0532
No log 0.4444 12 1.0452 0.3625 1.0452 1.0223
No log 0.5185 14 1.0255 0.3521 1.0255 1.0127
No log 0.5926 16 1.0632 0.1764 1.0632 1.0311
No log 0.6667 18 1.1130 0.1764 1.1130 1.0550
No log 0.7407 20 1.0794 0.2981 1.0794 1.0389
No log 0.8148 22 1.0039 0.2108 1.0039 1.0019
No log 0.8889 24 1.0397 0.1516 1.0397 1.0197
No log 0.9630 26 1.0547 0.1137 1.0547 1.0270
No log 1.0370 28 1.2706 0.0814 1.2706 1.1272
No log 1.1111 30 1.3902 0.1487 1.3902 1.1791
No log 1.1852 32 1.0989 0.2441 1.0989 1.0483
No log 1.2593 34 1.0044 0.2265 1.0044 1.0022
No log 1.3333 36 1.1569 0.2293 1.1569 1.0756
No log 1.4074 38 1.3568 -0.0296 1.3568 1.1648
No log 1.4815 40 1.4769 -0.0148 1.4769 1.2153
No log 1.5556 42 1.3959 -0.0148 1.3959 1.1815
No log 1.6296 44 1.3592 0.0 1.3592 1.1658
No log 1.7037 46 1.1966 0.1024 1.1966 1.0939
No log 1.7778 48 1.0175 0.3003 1.0175 1.0087
No log 1.8519 50 0.9568 0.2566 0.9568 0.9782
No log 1.9259 52 0.9354 0.2849 0.9354 0.9672
No log 2.0 54 0.9409 0.1389 0.9409 0.9700
No log 2.0741 56 0.9543 0.1601 0.9543 0.9769
No log 2.1481 58 0.9327 0.2818 0.9327 0.9658
No log 2.2222 60 0.9016 0.4402 0.9016 0.9495
No log 2.2963 62 0.8892 0.4312 0.8892 0.9430
No log 2.3704 64 0.8344 0.4022 0.8344 0.9135
No log 2.4444 66 0.8468 0.3288 0.8468 0.9202
No log 2.5185 68 0.9091 0.2262 0.9091 0.9535
No log 2.5926 70 0.9734 0.1998 0.9734 0.9866
No log 2.6667 72 0.9566 0.1799 0.9566 0.9781
No log 2.7407 74 0.8942 0.3094 0.8942 0.9456
No log 2.8148 76 0.8805 0.4275 0.8805 0.9384
No log 2.8889 78 0.8467 0.4710 0.8467 0.9201
No log 2.9630 80 0.8043 0.4727 0.8043 0.8968
No log 3.0370 82 0.7295 0.4932 0.7295 0.8541
No log 3.1111 84 0.7177 0.5146 0.7177 0.8472
No log 3.1852 86 0.8133 0.3844 0.8133 0.9019
No log 3.2593 88 0.8868 0.4004 0.8868 0.9417
No log 3.3333 90 0.9298 0.2960 0.9298 0.9642
No log 3.4074 92 0.9505 0.3283 0.9505 0.9749
No log 3.4815 94 0.7993 0.4650 0.7993 0.8941
No log 3.5556 96 0.7235 0.5403 0.7235 0.8506
No log 3.6296 98 0.7522 0.5435 0.7522 0.8673
No log 3.7037 100 0.7399 0.5994 0.7399 0.8602
No log 3.7778 102 0.7164 0.6079 0.7164 0.8464
No log 3.8519 104 0.6414 0.6209 0.6414 0.8009
No log 3.9259 106 0.5822 0.6252 0.5822 0.7630
No log 4.0 108 0.5971 0.6032 0.5971 0.7727
No log 4.0741 110 0.7344 0.5916 0.7344 0.8570
No log 4.1481 112 0.8790 0.4681 0.8790 0.9375
No log 4.2222 114 0.8021 0.4902 0.8021 0.8956
No log 4.2963 116 0.6624 0.5923 0.6624 0.8139
No log 4.3704 118 0.5633 0.7049 0.5633 0.7505
No log 4.4444 120 0.5428 0.7018 0.5428 0.7367
No log 4.5185 122 0.5315 0.6931 0.5315 0.7291
No log 4.5926 124 0.5686 0.6324 0.5686 0.7540
No log 4.6667 126 0.5711 0.5840 0.5711 0.7557
No log 4.7407 128 0.5483 0.6301 0.5483 0.7404
No log 4.8148 130 0.5646 0.6634 0.5646 0.7514
No log 4.8889 132 0.5655 0.6419 0.5655 0.7520
No log 4.9630 134 0.5288 0.6324 0.5288 0.7272
No log 5.0370 136 0.7335 0.6539 0.7335 0.8565
No log 5.1111 138 0.7308 0.6539 0.7308 0.8549
No log 5.1852 140 0.5509 0.6324 0.5509 0.7422
No log 5.2593 142 0.6552 0.6080 0.6552 0.8095
No log 5.3333 144 0.6951 0.6275 0.6951 0.8337
No log 5.4074 146 0.5921 0.6215 0.5921 0.7695
No log 5.4815 148 0.6195 0.6314 0.6195 0.7871
No log 5.5556 150 0.6243 0.6700 0.6243 0.7902
No log 5.6296 152 0.5638 0.6796 0.5638 0.7509
No log 5.7037 154 0.5513 0.6690 0.5513 0.7425
No log 5.7778 156 0.5388 0.6164 0.5388 0.7341
No log 5.8519 158 0.5407 0.6455 0.5407 0.7353
No log 5.9259 160 0.6336 0.6160 0.6336 0.7960
No log 6.0 162 0.6444 0.5867 0.6444 0.8028
No log 6.0741 164 0.5529 0.6584 0.5529 0.7436
No log 6.1481 166 0.5504 0.5679 0.5504 0.7419
No log 6.2222 168 0.5494 0.5549 0.5494 0.7412
No log 6.2963 170 0.5432 0.5972 0.5432 0.7370
No log 6.3704 172 0.5579 0.6688 0.5579 0.7469
No log 6.4444 174 0.5326 0.6445 0.5326 0.7298
No log 6.5185 176 0.5077 0.6363 0.5077 0.7126
No log 6.5926 178 0.4858 0.6897 0.4858 0.6970
No log 6.6667 180 0.4975 0.6479 0.4975 0.7053
No log 6.7407 182 0.4967 0.6833 0.4967 0.7047
No log 6.8148 184 0.5164 0.6822 0.5164 0.7186
No log 6.8889 186 0.5533 0.6675 0.5533 0.7438
No log 6.9630 188 0.5325 0.6667 0.5325 0.7297
No log 7.0370 190 0.5851 0.6128 0.5851 0.7649
No log 7.1111 192 0.6682 0.6170 0.6682 0.8174
No log 7.1852 194 0.6646 0.5756 0.6646 0.8152
No log 7.2593 196 0.6077 0.6396 0.6077 0.7795
No log 7.3333 198 0.5901 0.6296 0.5901 0.7682
No log 7.4074 200 0.6094 0.6209 0.6094 0.7806
No log 7.4815 202 0.5836 0.5534 0.5836 0.7639
No log 7.5556 204 0.5686 0.5534 0.5686 0.7541
No log 7.6296 206 0.5745 0.5607 0.5745 0.7580
No log 7.7037 208 0.5442 0.6157 0.5442 0.7377
No log 7.7778 210 0.5340 0.6756 0.5340 0.7307
No log 7.8519 212 0.5313 0.6756 0.5313 0.7289
No log 7.9259 214 0.5340 0.6936 0.5340 0.7307
No log 8.0 216 0.6477 0.5938 0.6477 0.8048
No log 8.0741 218 0.7247 0.5905 0.7247 0.8513
No log 8.1481 220 0.6574 0.6209 0.6574 0.8108
No log 8.2222 222 0.5352 0.6528 0.5352 0.7315
No log 8.2963 224 0.5347 0.7175 0.5347 0.7313
No log 8.3704 226 0.5377 0.6572 0.5377 0.7333
No log 8.4444 228 0.5858 0.6227 0.5858 0.7654
No log 8.5185 230 0.6664 0.5745 0.6664 0.8163
No log 8.5926 232 0.5966 0.6455 0.5966 0.7724
No log 8.6667 234 0.5653 0.6974 0.5653 0.7518
No log 8.7407 236 0.5805 0.6010 0.5805 0.7619
No log 8.8148 238 0.5363 0.6833 0.5363 0.7323
No log 8.8889 240 0.6265 0.5318 0.6265 0.7915
No log 8.9630 242 0.6642 0.5589 0.6642 0.8150
No log 9.0370 244 0.5817 0.6751 0.5817 0.7627
No log 9.1111 246 0.5652 0.6814 0.5652 0.7518
No log 9.1852 248 0.5895 0.6865 0.5895 0.7678
No log 9.2593 250 0.6564 0.5414 0.6564 0.8102
No log 9.3333 252 0.6371 0.5777 0.6371 0.7982
No log 9.4074 254 0.5711 0.6003 0.5711 0.7557
No log 9.4815 256 0.5697 0.6157 0.5697 0.7548
No log 9.5556 258 0.5762 0.6445 0.5762 0.7591
No log 9.6296 260 0.5783 0.6410 0.5783 0.7604
No log 9.7037 262 0.5325 0.6310 0.5325 0.7297
No log 9.7778 264 0.4879 0.6602 0.4879 0.6985
No log 9.8519 266 0.4888 0.6736 0.4888 0.6991
No log 9.9259 268 0.5136 0.6639 0.5136 0.7166
No log 10.0 270 0.5441 0.6841 0.5441 0.7376
No log 10.0741 272 0.5635 0.6731 0.5635 0.7507
No log 10.1481 274 0.5521 0.6950 0.5521 0.7430
No log 10.2222 276 0.4993 0.7338 0.4993 0.7066
No log 10.2963 278 0.5022 0.7141 0.5022 0.7087
No log 10.3704 280 0.5143 0.6838 0.5143 0.7172
No log 10.4444 282 0.5331 0.7444 0.5331 0.7302
No log 10.5185 284 0.5707 0.6748 0.5707 0.7554
No log 10.5926 286 0.6048 0.6558 0.6048 0.7777
No log 10.6667 288 0.5719 0.6231 0.5719 0.7563
No log 10.7407 290 0.5712 0.6231 0.5712 0.7558
No log 10.8148 292 0.5789 0.6422 0.5789 0.7609
No log 10.8889 294 0.5946 0.6455 0.5946 0.7711
No log 10.9630 296 0.5765 0.6639 0.5765 0.7593
No log 11.0370 298 0.5718 0.6584 0.5718 0.7562
No log 11.1111 300 0.5694 0.6584 0.5694 0.7546
No log 11.1852 302 0.5607 0.6330 0.5607 0.7488
No log 11.2593 304 0.5809 0.6227 0.5809 0.7622
No log 11.3333 306 0.6187 0.6544 0.6187 0.7866
No log 11.4074 308 0.6037 0.6215 0.6037 0.7770
No log 11.4815 310 0.6234 0.6179 0.6234 0.7896
No log 11.5556 312 0.6970 0.5443 0.6970 0.8349
No log 11.6296 314 0.6613 0.5788 0.6613 0.8132
No log 11.7037 316 0.5711 0.6387 0.5711 0.7557
No log 11.7778 318 0.5437 0.6942 0.5437 0.7373
No log 11.8519 320 0.5270 0.6796 0.5270 0.7259
No log 11.9259 322 0.5476 0.6404 0.5476 0.7400
No log 12.0 324 0.5625 0.6573 0.5625 0.7500
No log 12.0741 326 0.5356 0.6581 0.5356 0.7318
No log 12.1481 328 0.4956 0.7095 0.4956 0.7040
No log 12.2222 330 0.4938 0.7132 0.4938 0.7027
No log 12.2963 332 0.5227 0.6841 0.5227 0.7230
No log 12.3704 334 0.5512 0.6500 0.5512 0.7425
No log 12.4444 336 0.5774 0.6670 0.5774 0.7599
No log 12.5185 338 0.5477 0.6623 0.5477 0.7400
No log 12.5926 340 0.5283 0.6690 0.5283 0.7268
No log 12.6667 342 0.5300 0.6805 0.5300 0.7280
No log 12.7407 344 0.5051 0.6519 0.5051 0.7107
No log 12.8148 346 0.5502 0.6914 0.5502 0.7418
No log 12.8889 348 0.5823 0.6521 0.5823 0.7631
No log 12.9630 350 0.5666 0.6735 0.5666 0.7527
No log 13.0370 352 0.5225 0.7005 0.5225 0.7228
No log 13.1111 354 0.5225 0.6813 0.5225 0.7228
No log 13.1852 356 0.5474 0.6732 0.5474 0.7399
No log 13.2593 358 0.6483 0.6099 0.6483 0.8052
No log 13.3333 360 0.7749 0.5408 0.7749 0.8803
No log 13.4074 362 0.7527 0.5111 0.7527 0.8676
No log 13.4815 364 0.6315 0.6637 0.6315 0.7946
No log 13.5556 366 0.5859 0.6032 0.5859 0.7654
No log 13.6296 368 0.5913 0.6161 0.5913 0.7690
No log 13.7037 370 0.5856 0.6435 0.5856 0.7652
No log 13.7778 372 0.5938 0.6655 0.5938 0.7706
No log 13.8519 374 0.6597 0.5555 0.6597 0.8122
No log 13.9259 376 0.6756 0.5745 0.6756 0.8220
No log 14.0 378 0.5992 0.5677 0.5992 0.7741
No log 14.0741 380 0.5271 0.6857 0.5271 0.7260
No log 14.1481 382 0.5575 0.6775 0.5575 0.7466
No log 14.2222 384 0.5765 0.6569 0.5765 0.7592
No log 14.2963 386 0.5664 0.6209 0.5664 0.7526
No log 14.3704 388 0.6267 0.5356 0.6267 0.7917
No log 14.4444 390 0.6765 0.5745 0.6765 0.8225
No log 14.5185 392 0.6159 0.6015 0.6159 0.7848
No log 14.5926 394 0.5461 0.6593 0.5461 0.7390
No log 14.6667 396 0.5308 0.6632 0.5308 0.7286
No log 14.7407 398 0.5280 0.6528 0.5280 0.7266
No log 14.8148 400 0.5510 0.6656 0.5510 0.7423
No log 14.8889 402 0.5783 0.6218 0.5783 0.7605
No log 14.9630 404 0.5767 0.6137 0.5767 0.7594
No log 15.0370 406 0.5758 0.6361 0.5758 0.7588
No log 15.1111 408 0.5616 0.6584 0.5616 0.7494
No log 15.1852 410 0.5804 0.6473 0.5804 0.7618
No log 15.2593 412 0.5608 0.6584 0.5608 0.7488
No log 15.3333 414 0.5657 0.6584 0.5657 0.7521
No log 15.4074 416 0.5641 0.6695 0.5641 0.7511
No log 15.4815 418 0.5746 0.6445 0.5746 0.7580
No log 15.5556 420 0.5863 0.6243 0.5863 0.7657
No log 15.6296 422 0.6218 0.5654 0.6218 0.7885
No log 15.7037 424 0.6302 0.5279 0.6302 0.7938
No log 15.7778 426 0.5712 0.6073 0.5712 0.7558
No log 15.8519 428 0.5219 0.6488 0.5219 0.7224
No log 15.9259 430 0.5121 0.6888 0.5121 0.7156
No log 16.0 432 0.5126 0.6888 0.5126 0.7160
No log 16.0741 434 0.5315 0.6593 0.5315 0.7290
No log 16.1481 436 0.6147 0.5686 0.6147 0.7840
No log 16.2222 438 0.6604 0.5447 0.6604 0.8126
No log 16.2963 440 0.6404 0.5463 0.6404 0.8002
No log 16.3704 442 0.5848 0.5721 0.5848 0.7647
No log 16.4444 444 0.5820 0.4764 0.5820 0.7629
No log 16.5185 446 0.5829 0.5273 0.5829 0.7635
No log 16.5926 448 0.5910 0.5348 0.5910 0.7688
No log 16.6667 450 0.6212 0.5540 0.6212 0.7882
No log 16.7407 452 0.6159 0.5948 0.6159 0.7848
No log 16.8148 454 0.6009 0.6259 0.6009 0.7752
No log 16.8889 456 0.5895 0.6147 0.5895 0.7678
No log 16.9630 458 0.5696 0.6405 0.5696 0.7547
No log 17.0370 460 0.5753 0.5917 0.5753 0.7585
No log 17.1111 462 0.5826 0.6078 0.5826 0.7633
No log 17.1852 464 0.5775 0.6185 0.5775 0.7600
No log 17.2593 466 0.5566 0.5785 0.5566 0.7461
No log 17.3333 468 0.5596 0.6575 0.5596 0.7481
No log 17.4074 470 0.5257 0.6575 0.5257 0.7251
No log 17.4815 472 0.5139 0.6575 0.5139 0.7169
No log 17.5556 474 0.5078 0.6581 0.5078 0.7126
No log 17.6296 476 0.4817 0.6857 0.4817 0.6941
No log 17.7037 478 0.4822 0.7016 0.4822 0.6944
No log 17.7778 480 0.4919 0.6832 0.4919 0.7014
No log 17.8519 482 0.5146 0.6117 0.5146 0.7174
No log 17.9259 484 0.5686 0.6112 0.5686 0.7540
No log 18.0 486 0.5576 0.6301 0.5576 0.7467
No log 18.0741 488 0.5225 0.6370 0.5225 0.7228
No log 18.1481 490 0.5114 0.6380 0.5114 0.7151
No log 18.2222 492 0.4994 0.6733 0.4994 0.7067
No log 18.2963 494 0.5018 0.6575 0.5018 0.7084
No log 18.3704 496 0.5075 0.6712 0.5075 0.7124
No log 18.4444 498 0.4982 0.6610 0.4982 0.7058
0.3206 18.5185 500 0.4932 0.6649 0.4932 0.7023
0.3206 18.5926 502 0.5077 0.6455 0.5077 0.7125
0.3206 18.6667 504 0.4989 0.6455 0.4989 0.7063
0.3206 18.7407 506 0.4852 0.6762 0.4852 0.6966
0.3206 18.8148 508 0.4992 0.6528 0.4992 0.7066
0.3206 18.8889 510 0.5226 0.6655 0.5226 0.7229
0.3206 18.9630 512 0.5192 0.6456 0.5192 0.7206
0.3206 19.0370 514 0.5159 0.6506 0.5159 0.7182
0.3206 19.1111 516 0.4996 0.6547 0.4996 0.7068
0.3206 19.1852 518 0.4922 0.6753 0.4922 0.7016
0.3206 19.2593 520 0.5074 0.6593 0.5074 0.7123
0.3206 19.3333 522 0.5119 0.6806 0.5119 0.7154
0.3206 19.4074 524 0.5103 0.6745 0.5103 0.7144
0.3206 19.4815 526 0.5049 0.6616 0.5049 0.7106
0.3206 19.5556 528 0.5098 0.7067 0.5098 0.7140
0.3206 19.6296 530 0.5044 0.7075 0.5044 0.7102
0.3206 19.7037 532 0.5191 0.6269 0.5191 0.7205
0.3206 19.7778 534 0.5387 0.5959 0.5387 0.7340
0.3206 19.8519 536 0.5383 0.5959 0.5383 0.7337
0.3206 19.9259 538 0.5534 0.5933 0.5534 0.7439
0.3206 20.0 540 0.5311 0.5959 0.5311 0.7287

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
6
Safetensors
Model size
135M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for MayBashendy/ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k10_task5_organization

Finetuned
(4205)
this model