ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run1_AugV5_k11_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: 0.5621
  • Qwk: 0.4691
  • Mse: 0.5621
  • Rmse: 0.7497

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 0.0351 2 4.4200 -0.0244 4.4200 2.1024
No log 0.0702 4 2.5215 0.0485 2.5215 1.5879
No log 0.1053 6 1.4456 0.0383 1.4456 1.2023
No log 0.1404 8 1.1443 -0.0490 1.1443 1.0697
No log 0.1754 10 0.9800 -0.0408 0.9800 0.9899
No log 0.2105 12 0.9020 0.0512 0.9020 0.9497
No log 0.2456 14 0.8492 0.2676 0.8492 0.9215
No log 0.2807 16 1.5027 0.1211 1.5027 1.2259
No log 0.3158 18 1.5323 0.1155 1.5323 1.2379
No log 0.3509 20 0.8796 0.2564 0.8796 0.9379
No log 0.3860 22 0.6798 0.3074 0.6798 0.8245
No log 0.4211 24 0.6636 0.3967 0.6636 0.8146
No log 0.4561 26 0.7656 0.2830 0.7656 0.8750
No log 0.4912 28 1.1124 0.1708 1.1124 1.0547
No log 0.5263 30 0.9898 0.2224 0.9898 0.9949
No log 0.5614 32 0.9910 0.2224 0.9910 0.9955
No log 0.5965 34 0.8933 0.2191 0.8933 0.9451
No log 0.6316 36 0.9160 0.2191 0.9160 0.9571
No log 0.6667 38 1.0336 0.2622 1.0336 1.0167
No log 0.7018 40 0.9107 0.3279 0.9107 0.9543
No log 0.7368 42 0.6430 0.4285 0.6430 0.8018
No log 0.7719 44 0.7071 0.3596 0.7071 0.8409
No log 0.8070 46 0.7477 0.3873 0.7477 0.8647
No log 0.8421 48 0.6924 0.3774 0.6924 0.8321
No log 0.8772 50 0.6838 0.3935 0.6838 0.8269
No log 0.9123 52 0.8099 0.4007 0.8099 0.9000
No log 0.9474 54 0.7370 0.3941 0.7370 0.8585
No log 0.9825 56 0.7982 0.4033 0.7982 0.8934
No log 1.0175 58 0.7783 0.4033 0.7783 0.8822
No log 1.0526 60 0.6508 0.4716 0.6508 0.8067
No log 1.0877 62 0.6065 0.4974 0.6065 0.7788
No log 1.1228 64 0.6528 0.4791 0.6528 0.8080
No log 1.1579 66 0.7195 0.4408 0.7195 0.8483
No log 1.1930 68 0.8678 0.3754 0.8678 0.9316
No log 1.2281 70 0.7659 0.4184 0.7659 0.8751
No log 1.2632 72 0.6102 0.5172 0.6102 0.7812
No log 1.2982 74 0.5555 0.6053 0.5555 0.7453
No log 1.3333 76 0.5376 0.6186 0.5376 0.7332
No log 1.3684 78 0.7040 0.4806 0.7041 0.8391
No log 1.4035 80 0.9842 0.4319 0.9842 0.9921
No log 1.4386 82 1.0666 0.4093 1.0666 1.0327
No log 1.4737 84 0.7975 0.4314 0.7975 0.8930
No log 1.5088 86 0.5379 0.5368 0.5379 0.7334
No log 1.5439 88 0.5579 0.5361 0.5579 0.7469
No log 1.5789 90 0.5789 0.5227 0.5789 0.7609
No log 1.6140 92 0.5432 0.5492 0.5432 0.7371
No log 1.6491 94 0.7044 0.4918 0.7044 0.8393
No log 1.6842 96 0.8144 0.4688 0.8144 0.9024
No log 1.7193 98 0.7234 0.5464 0.7234 0.8505
No log 1.7544 100 0.8323 0.5349 0.8323 0.9123
No log 1.7895 102 1.0668 0.4505 1.0668 1.0329
No log 1.8246 104 1.0303 0.4786 1.0303 1.0150
No log 1.8596 106 0.9724 0.5279 0.9724 0.9861
No log 1.8947 108 0.8267 0.5602 0.8267 0.9092
No log 1.9298 110 0.7692 0.5869 0.7692 0.8771
No log 1.9649 112 0.7170 0.5614 0.7170 0.8468
No log 2.0 114 0.7642 0.5582 0.7642 0.8742
No log 2.0351 116 0.8182 0.5329 0.8182 0.9045
No log 2.0702 118 0.8717 0.4738 0.8717 0.9336
No log 2.1053 120 0.7082 0.4737 0.7082 0.8416
No log 2.1404 122 0.6336 0.5199 0.6336 0.7960
No log 2.1754 124 0.6287 0.5080 0.6287 0.7929
No log 2.2105 126 0.6005 0.4949 0.6005 0.7749
No log 2.2456 128 0.5940 0.4875 0.5940 0.7707
No log 2.2807 130 0.6019 0.4834 0.6019 0.7758
No log 2.3158 132 0.5799 0.5514 0.5799 0.7615
No log 2.3509 134 0.6264 0.5500 0.6264 0.7915
No log 2.3860 136 0.5986 0.5593 0.5986 0.7737
No log 2.4211 138 0.6129 0.5709 0.6129 0.7829
No log 2.4561 140 0.6691 0.5391 0.6691 0.8180
No log 2.4912 142 0.6760 0.5417 0.6760 0.8222
No log 2.5263 144 0.6174 0.5697 0.6174 0.7857
No log 2.5614 146 0.5978 0.5495 0.5978 0.7732
No log 2.5965 148 0.5874 0.5521 0.5874 0.7664
No log 2.6316 150 0.5975 0.5398 0.5975 0.7730
No log 2.6667 152 0.5653 0.5567 0.5653 0.7519
No log 2.7018 154 0.5644 0.4522 0.5644 0.7513
No log 2.7368 156 0.5877 0.4337 0.5877 0.7666
No log 2.7719 158 0.5592 0.5060 0.5592 0.7478
No log 2.8070 160 0.5769 0.5179 0.5769 0.7595
No log 2.8421 162 0.5915 0.5579 0.5915 0.7691
No log 2.8772 164 0.5628 0.5660 0.5628 0.7502
No log 2.9123 166 0.5587 0.5445 0.5587 0.7475
No log 2.9474 168 0.6018 0.5370 0.6018 0.7757
No log 2.9825 170 1.1185 0.2977 1.1185 1.0576
No log 3.0175 172 1.5856 0.3024 1.5856 1.2592
No log 3.0526 174 1.3929 0.3315 1.3929 1.1802
No log 3.0877 176 0.8295 0.4551 0.8295 0.9108
No log 3.1228 178 0.6394 0.5191 0.6394 0.7996
No log 3.1579 180 0.5464 0.5565 0.5464 0.7392
No log 3.1930 182 0.5890 0.5053 0.5890 0.7675
No log 3.2281 184 0.5669 0.5342 0.5669 0.7529
No log 3.2632 186 0.5556 0.6091 0.5556 0.7454
No log 3.2982 188 0.6250 0.5504 0.6250 0.7906
No log 3.3333 190 0.6007 0.5751 0.6007 0.7751
No log 3.3684 192 0.5782 0.5867 0.5782 0.7604
No log 3.4035 194 0.6393 0.4988 0.6393 0.7996
No log 3.4386 196 0.6734 0.4863 0.6734 0.8206
No log 3.4737 198 0.6358 0.4840 0.6358 0.7974
No log 3.5088 200 0.5793 0.5422 0.5793 0.7611
No log 3.5439 202 0.5611 0.4506 0.5611 0.7491
No log 3.5789 204 0.5658 0.4079 0.5658 0.7522
No log 3.6140 206 0.5685 0.4042 0.5685 0.7540
No log 3.6491 208 0.5801 0.4855 0.5801 0.7617
No log 3.6842 210 0.5960 0.5164 0.5960 0.7720
No log 3.7193 212 0.5987 0.4921 0.5987 0.7738
No log 3.7544 214 0.6403 0.5095 0.6403 0.8002
No log 3.7895 216 0.6176 0.5172 0.6176 0.7859
No log 3.8246 218 0.6512 0.4971 0.6512 0.8070
No log 3.8596 220 0.6619 0.4867 0.6619 0.8136
No log 3.8947 222 0.6091 0.4174 0.6091 0.7805
No log 3.9298 224 0.6686 0.4033 0.6686 0.8177
No log 3.9649 226 0.6089 0.3691 0.6089 0.7803
No log 4.0 228 0.5770 0.4273 0.5770 0.7596
No log 4.0351 230 0.5849 0.4846 0.5849 0.7648
No log 4.0702 232 0.8004 0.4983 0.8004 0.8947
No log 4.1053 234 0.9954 0.3766 0.9954 0.9977
No log 4.1404 236 0.8244 0.4879 0.8244 0.9080
No log 4.1754 238 0.6231 0.5437 0.6231 0.7894
No log 4.2105 240 0.6703 0.5379 0.6703 0.8187
No log 4.2456 242 0.6327 0.5863 0.6327 0.7954
No log 4.2807 244 0.5538 0.4970 0.5538 0.7442
No log 4.3158 246 0.5551 0.5973 0.5551 0.7450
No log 4.3509 248 0.5475 0.5345 0.5475 0.7400
No log 4.3860 250 0.5437 0.4529 0.5437 0.7374
No log 4.4211 252 0.5395 0.4185 0.5395 0.7345
No log 4.4561 254 0.5466 0.5338 0.5466 0.7393
No log 4.4912 256 0.5354 0.4393 0.5354 0.7317
No log 4.5263 258 0.5623 0.4869 0.5623 0.7498
No log 4.5614 260 0.5772 0.5051 0.5772 0.7597
No log 4.5965 262 0.5447 0.5209 0.5447 0.7380
No log 4.6316 264 0.5436 0.5153 0.5436 0.7373
No log 4.6667 266 0.5426 0.5355 0.5426 0.7366
No log 4.7018 268 0.5438 0.5741 0.5438 0.7374
No log 4.7368 270 0.5763 0.5594 0.5763 0.7592
No log 4.7719 272 0.6543 0.5741 0.6543 0.8089
No log 4.8070 274 0.6180 0.5833 0.6180 0.7861
No log 4.8421 276 0.5450 0.6421 0.5450 0.7382
No log 4.8772 278 0.6391 0.4862 0.6391 0.7994
No log 4.9123 280 0.7290 0.5089 0.7290 0.8538
No log 4.9474 282 0.6237 0.5145 0.6237 0.7898
No log 4.9825 284 0.5278 0.4259 0.5278 0.7265
No log 5.0175 286 0.7424 0.4832 0.7424 0.8616
No log 5.0526 288 0.9817 0.4365 0.9817 0.9908
No log 5.0877 290 0.9107 0.4506 0.9107 0.9543
No log 5.1228 292 0.6477 0.5074 0.6477 0.8048
No log 5.1579 294 0.5463 0.4616 0.5463 0.7391
No log 5.1930 296 0.5384 0.4809 0.5384 0.7338
No log 5.2281 298 0.5360 0.5345 0.5360 0.7321
No log 5.2632 300 0.5440 0.4700 0.5440 0.7376
No log 5.2982 302 0.5904 0.5562 0.5904 0.7684
No log 5.3333 304 0.6440 0.5607 0.6440 0.8025
No log 5.3684 306 0.5828 0.6152 0.5828 0.7634
No log 5.4035 308 0.5810 0.5707 0.5810 0.7622
No log 5.4386 310 0.6750 0.5189 0.6750 0.8216
No log 5.4737 312 0.6521 0.5123 0.6521 0.8075
No log 5.5088 314 0.5700 0.5289 0.5700 0.7550
No log 5.5439 316 0.5513 0.5250 0.5513 0.7425
No log 5.5789 318 0.6628 0.5324 0.6628 0.8141
No log 5.6140 320 0.7076 0.5602 0.7076 0.8412
No log 5.6491 322 0.6318 0.6046 0.6318 0.7948
No log 5.6842 324 0.5912 0.6176 0.5912 0.7689
No log 5.7193 326 0.5661 0.5926 0.5661 0.7524
No log 5.7544 328 0.5383 0.5235 0.5383 0.7337
No log 5.7895 330 0.5454 0.5647 0.5454 0.7385
No log 5.8246 332 0.5520 0.5422 0.5520 0.7430
No log 5.8596 334 0.5439 0.5063 0.5439 0.7375
No log 5.8947 336 0.5592 0.5389 0.5592 0.7478
No log 5.9298 338 0.5550 0.5662 0.5550 0.7450
No log 5.9649 340 0.5715 0.5645 0.5715 0.7560
No log 6.0 342 0.5854 0.5591 0.5854 0.7651
No log 6.0351 344 0.5767 0.6363 0.5767 0.7594
No log 6.0702 346 0.6031 0.5732 0.6031 0.7766
No log 6.1053 348 0.7328 0.5677 0.7328 0.8561
No log 6.1404 350 0.7609 0.5186 0.7609 0.8723
No log 6.1754 352 0.6738 0.5381 0.6738 0.8209
No log 6.2105 354 0.5588 0.5569 0.5588 0.7475
No log 6.2456 356 0.5326 0.5596 0.5326 0.7298
No log 6.2807 358 0.5377 0.5073 0.5377 0.7333
No log 6.3158 360 0.5250 0.5259 0.5250 0.7246
No log 6.3509 362 0.5366 0.4697 0.5366 0.7325
No log 6.3860 364 0.6379 0.5442 0.6379 0.7987
No log 6.4211 366 0.8264 0.4867 0.8264 0.9091
No log 6.4561 368 0.8595 0.4788 0.8595 0.9271
No log 6.4912 370 0.6845 0.5709 0.6845 0.8274
No log 6.5263 372 0.5504 0.5772 0.5504 0.7419
No log 6.5614 374 0.5284 0.5947 0.5284 0.7269
No log 6.5965 376 0.5468 0.5678 0.5468 0.7394
No log 6.6316 378 0.5273 0.5593 0.5273 0.7261
No log 6.6667 380 0.5147 0.5562 0.5147 0.7174
No log 6.7018 382 0.5545 0.4926 0.5545 0.7447
No log 6.7368 384 0.6038 0.5023 0.6038 0.7771
No log 6.7719 386 0.5706 0.5076 0.5706 0.7554
No log 6.8070 388 0.5104 0.6306 0.5104 0.7144
No log 6.8421 390 0.5049 0.5583 0.5049 0.7106
No log 6.8772 392 0.5037 0.5428 0.5037 0.7097
No log 6.9123 394 0.5171 0.5570 0.5171 0.7191
No log 6.9474 396 0.5124 0.5732 0.5124 0.7158
No log 6.9825 398 0.5313 0.5593 0.5313 0.7289
No log 7.0175 400 0.5239 0.5435 0.5239 0.7238
No log 7.0526 402 0.5079 0.5888 0.5079 0.7127
No log 7.0877 404 0.5355 0.5124 0.5355 0.7318
No log 7.1228 406 0.5611 0.5104 0.5611 0.7491
No log 7.1579 408 0.5286 0.5452 0.5286 0.7270
No log 7.1930 410 0.5103 0.5694 0.5103 0.7143
No log 7.2281 412 0.5397 0.5565 0.5397 0.7346
No log 7.2632 414 0.5430 0.5540 0.5430 0.7369
No log 7.2982 416 0.5342 0.5495 0.5342 0.7309
No log 7.3333 418 0.4991 0.5336 0.4991 0.7064
No log 7.3684 420 0.5671 0.5380 0.5671 0.7531
No log 7.4035 422 0.7180 0.4929 0.7180 0.8474
No log 7.4386 424 0.8147 0.4307 0.8147 0.9026
No log 7.4737 426 0.7456 0.4806 0.7456 0.8635
No log 7.5088 428 0.5838 0.5197 0.5838 0.7641
No log 7.5439 430 0.4991 0.6270 0.4991 0.7065
No log 7.5789 432 0.4994 0.6424 0.4994 0.7067
No log 7.6140 434 0.5010 0.6183 0.5010 0.7078
No log 7.6491 436 0.5356 0.5971 0.5356 0.7318
No log 7.6842 438 0.5676 0.5367 0.5676 0.7534
No log 7.7193 440 0.5671 0.5626 0.5671 0.7530
No log 7.7544 442 0.5497 0.5214 0.5497 0.7414
No log 7.7895 444 0.5450 0.5414 0.5450 0.7382
No log 7.8246 446 0.5075 0.6425 0.5075 0.7124
No log 7.8596 448 0.5477 0.5997 0.5477 0.7401
No log 7.8947 450 0.6083 0.5469 0.6083 0.7799
No log 7.9298 452 0.5868 0.5865 0.5868 0.7661
No log 7.9649 454 0.5489 0.6232 0.5489 0.7409
No log 8.0 456 0.5350 0.6149 0.5350 0.7314
No log 8.0351 458 0.5697 0.5194 0.5697 0.7548
No log 8.0702 460 0.5706 0.5128 0.5706 0.7554
No log 8.1053 462 0.5640 0.6139 0.5640 0.7510
No log 8.1404 464 0.5557 0.6315 0.5557 0.7454
No log 8.1754 466 0.5593 0.6100 0.5593 0.7479
No log 8.2105 468 0.5432 0.6080 0.5432 0.7370
No log 8.2456 470 0.5335 0.5972 0.5335 0.7304
No log 8.2807 472 0.5327 0.5873 0.5327 0.7299
No log 8.3158 474 0.5274 0.6145 0.5274 0.7262
No log 8.3509 476 0.5379 0.5576 0.5379 0.7334
No log 8.3860 478 0.5603 0.5616 0.5603 0.7485
No log 8.4211 480 0.5466 0.5858 0.5466 0.7393
No log 8.4561 482 0.5453 0.5633 0.5453 0.7384
No log 8.4912 484 0.5365 0.5703 0.5365 0.7324
No log 8.5263 486 0.5434 0.5159 0.5434 0.7371
No log 8.5614 488 0.5399 0.5218 0.5399 0.7348
No log 8.5965 490 0.5293 0.5919 0.5293 0.7275
No log 8.6316 492 0.5873 0.5543 0.5873 0.7663
No log 8.6667 494 0.6121 0.5162 0.6121 0.7823
No log 8.7018 496 0.5640 0.6022 0.5640 0.7510
No log 8.7368 498 0.5594 0.5476 0.5594 0.7479
0.3397 8.7719 500 0.6210 0.5075 0.6210 0.7880
0.3397 8.8070 502 0.6172 0.5249 0.6172 0.7856
0.3397 8.8421 504 0.5883 0.4990 0.5883 0.7670
0.3397 8.8772 506 0.5482 0.5590 0.5482 0.7404
0.3397 8.9123 508 0.5501 0.5831 0.5501 0.7417
0.3397 8.9474 510 0.5630 0.5699 0.5630 0.7503
0.3397 8.9825 512 0.5346 0.5790 0.5346 0.7312
0.3397 9.0175 514 0.5376 0.5626 0.5376 0.7332
0.3397 9.0526 516 0.5941 0.5263 0.5941 0.7708
0.3397 9.0877 518 0.6432 0.5109 0.6432 0.8020
0.3397 9.1228 520 0.5852 0.5281 0.5852 0.7650
0.3397 9.1579 522 0.5555 0.5396 0.5555 0.7453
0.3397 9.1930 524 0.5238 0.5415 0.5238 0.7237
0.3397 9.2281 526 0.5322 0.5487 0.5322 0.7296
0.3397 9.2632 528 0.5302 0.5396 0.5302 0.7281
0.3397 9.2982 530 0.5210 0.5311 0.5210 0.7218
0.3397 9.3333 532 0.5175 0.5205 0.5175 0.7194
0.3397 9.3684 534 0.5259 0.5250 0.5259 0.7252
0.3397 9.4035 536 0.5647 0.5053 0.5647 0.7515
0.3397 9.4386 538 0.6142 0.5448 0.6142 0.7837
0.3397 9.4737 540 0.6146 0.5351 0.6146 0.7840
0.3397 9.5088 542 0.6002 0.5351 0.6002 0.7747
0.3397 9.5439 544 0.5694 0.5176 0.5694 0.7546
0.3397 9.5789 546 0.5348 0.5030 0.5348 0.7313
0.3397 9.6140 548 0.5256 0.4923 0.5256 0.7250
0.3397 9.6491 550 0.5263 0.5155 0.5263 0.7255
0.3397 9.6842 552 0.5327 0.5756 0.5327 0.7298
0.3397 9.7193 554 0.5662 0.5200 0.5662 0.7524
0.3397 9.7544 556 0.5831 0.5474 0.5831 0.7636
0.3397 9.7895 558 0.5479 0.5637 0.5479 0.7402
0.3397 9.8246 560 0.5229 0.5088 0.5229 0.7231
0.3397 9.8596 562 0.5693 0.5195 0.5693 0.7545
0.3397 9.8947 564 0.5860 0.5357 0.5860 0.7655
0.3397 9.9298 566 0.5549 0.5442 0.5549 0.7449
0.3397 9.9649 568 0.5482 0.6003 0.5482 0.7404
0.3397 10.0 570 0.6294 0.5523 0.6294 0.7933
0.3397 10.0351 572 0.7071 0.5215 0.7071 0.8409
0.3397 10.0702 574 0.6636 0.5124 0.6636 0.8146
0.3397 10.1053 576 0.5781 0.5525 0.5781 0.7603
0.3397 10.1404 578 0.5612 0.5481 0.5612 0.7491
0.3397 10.1754 580 0.6054 0.5255 0.6054 0.7781
0.3397 10.2105 582 0.6069 0.5255 0.6069 0.7791
0.3397 10.2456 584 0.5714 0.4864 0.5714 0.7559
0.3397 10.2807 586 0.5403 0.5325 0.5403 0.7350
0.3397 10.3158 588 0.5763 0.5319 0.5763 0.7592
0.3397 10.3509 590 0.6368 0.5627 0.6368 0.7980
0.3397 10.3860 592 0.6454 0.5385 0.6454 0.8034
0.3397 10.4211 594 0.6133 0.5474 0.6133 0.7832
0.3397 10.4561 596 0.5742 0.5403 0.5742 0.7578
0.3397 10.4912 598 0.5713 0.5554 0.5713 0.7558
0.3397 10.5263 600 0.5695 0.5651 0.5695 0.7547
0.3397 10.5614 602 0.5768 0.5768 0.5768 0.7595
0.3397 10.5965 604 0.5729 0.5788 0.5729 0.7569
0.3397 10.6316 606 0.5627 0.5577 0.5627 0.7502
0.3397 10.6667 608 0.5486 0.5535 0.5486 0.7407
0.3397 10.7018 610 0.5429 0.4850 0.5429 0.7368
0.3397 10.7368 612 0.5484 0.4672 0.5484 0.7406
0.3397 10.7719 614 0.5505 0.4672 0.5505 0.7420
0.3397 10.8070 616 0.5516 0.5321 0.5516 0.7427
0.3397 10.8421 618 0.5583 0.5488 0.5583 0.7472
0.3397 10.8772 620 0.5680 0.5033 0.5680 0.7536
0.3397 10.9123 622 0.5885 0.4983 0.5885 0.7671
0.3397 10.9474 624 0.5953 0.4619 0.5953 0.7715
0.3397 10.9825 626 0.5785 0.4694 0.5785 0.7606
0.3397 11.0175 628 0.5621 0.4691 0.5621 0.7497

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
3
Safetensors
Model size
135M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for MayBashendy/ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run1_AugV5_k11_task2_organization

Finetuned
(4222)
this model