ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k5_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: 0.5319
  • Qwk: 0.6620
  • Mse: 0.5319
  • Rmse: 0.7293

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 0.1333 2 4.0121 0.0069 4.0121 2.0030
No log 0.2667 4 2.1405 0.0450 2.1405 1.4630
No log 0.4 6 1.4755 0.0408 1.4755 1.2147
No log 0.5333 8 1.0516 0.2734 1.0516 1.0255
No log 0.6667 10 1.0824 0.1643 1.0824 1.0404
No log 0.8 12 1.2759 -0.1333 1.2759 1.1295
No log 0.9333 14 1.4281 -0.0777 1.4281 1.1951
No log 1.0667 16 1.5161 -0.0709 1.5161 1.2313
No log 1.2 18 1.2867 -0.0394 1.2867 1.1343
No log 1.3333 20 1.1995 0.0967 1.1995 1.0952
No log 1.4667 22 1.2540 -0.0032 1.2540 1.1198
No log 1.6 24 1.1729 0.0820 1.1729 1.0830
No log 1.7333 26 1.0244 0.3326 1.0244 1.0121
No log 1.8667 28 1.0345 0.2697 1.0345 1.0171
No log 2.0 30 1.0688 0.2236 1.0688 1.0338
No log 2.1333 32 1.0751 0.2390 1.0751 1.0369
No log 2.2667 34 1.0323 0.2416 1.0323 1.0160
No log 2.4 36 1.0861 0.1436 1.0861 1.0422
No log 2.5333 38 1.0908 0.1436 1.0908 1.0444
No log 2.6667 40 0.9866 0.2416 0.9866 0.9933
No log 2.8 42 0.9687 0.2265 0.9687 0.9842
No log 2.9333 44 0.9994 0.3372 0.9994 0.9997
No log 3.0667 46 1.0022 0.3687 1.0022 1.0011
No log 3.2 48 1.1401 0.3863 1.1401 1.0678
No log 3.3333 50 1.2943 0.2993 1.2943 1.1377
No log 3.4667 52 1.1018 0.3502 1.1018 1.0497
No log 3.6 54 0.8783 0.4494 0.8783 0.9372
No log 3.7333 56 1.0112 0.3449 1.0112 1.0056
No log 3.8667 58 1.3693 0.0840 1.3693 1.1702
No log 4.0 60 1.4294 0.1379 1.4294 1.1956
No log 4.1333 62 1.1873 0.2857 1.1873 1.0896
No log 4.2667 64 0.8918 0.4265 0.8918 0.9443
No log 4.4 66 0.7505 0.5010 0.7505 0.8663
No log 4.5333 68 0.7444 0.5375 0.7444 0.8628
No log 4.6667 70 0.7857 0.5199 0.7857 0.8864
No log 4.8 72 0.9551 0.3624 0.9551 0.9773
No log 4.9333 74 0.8291 0.5586 0.8291 0.9105
No log 5.0667 76 0.7306 0.4850 0.7306 0.8547
No log 5.2 78 0.8554 0.5230 0.8554 0.9249
No log 5.3333 80 0.7357 0.5163 0.7357 0.8578
No log 5.4667 82 0.6618 0.5235 0.6618 0.8135
No log 5.6 84 0.7039 0.5910 0.7039 0.8390
No log 5.7333 86 0.6963 0.4708 0.6963 0.8345
No log 5.8667 88 0.6581 0.4995 0.6581 0.8112
No log 6.0 90 0.7346 0.5598 0.7346 0.8571
No log 6.1333 92 0.6786 0.5860 0.6786 0.8238
No log 6.2667 94 0.6124 0.6095 0.6124 0.7826
No log 6.4 96 0.5998 0.6306 0.5998 0.7745
No log 6.5333 98 0.6586 0.6573 0.6586 0.8115
No log 6.6667 100 0.6830 0.6395 0.6830 0.8264
No log 6.8 102 0.6050 0.7001 0.6050 0.7778
No log 6.9333 104 0.7241 0.5259 0.7241 0.8509
No log 7.0667 106 1.0517 0.4929 1.0517 1.0255
No log 7.2 108 0.8991 0.5283 0.8991 0.9482
No log 7.3333 110 0.6204 0.5876 0.6204 0.7876
No log 7.4667 112 0.6082 0.6695 0.6082 0.7799
No log 7.6 114 0.5754 0.7074 0.5754 0.7585
No log 7.7333 116 0.6044 0.6234 0.6044 0.7774
No log 7.8667 118 0.7455 0.5664 0.7455 0.8634
No log 8.0 120 0.7479 0.5821 0.7479 0.8648
No log 8.1333 122 0.6144 0.6386 0.6144 0.7838
No log 8.2667 124 0.6060 0.6345 0.6060 0.7784
No log 8.4 126 0.6244 0.6237 0.6244 0.7902
No log 8.5333 128 0.8180 0.5157 0.8180 0.9044
No log 8.6667 130 0.9115 0.4961 0.9115 0.9547
No log 8.8 132 0.7593 0.4767 0.7593 0.8714
No log 8.9333 134 0.6838 0.5438 0.6838 0.8269
No log 9.0667 136 0.6782 0.5327 0.6782 0.8235
No log 9.2 138 0.8244 0.5804 0.8244 0.9080
No log 9.3333 140 0.8647 0.5581 0.8647 0.9299
No log 9.4667 142 0.6710 0.5325 0.6710 0.8191
No log 9.6 144 0.6290 0.6055 0.6290 0.7931
No log 9.7333 146 0.6244 0.6055 0.6244 0.7902
No log 9.8667 148 0.6315 0.6234 0.6315 0.7947
No log 10.0 150 0.7901 0.6057 0.7901 0.8889
No log 10.1333 152 0.7441 0.6074 0.7441 0.8626
No log 10.2667 154 0.5948 0.6374 0.5948 0.7712
No log 10.4 156 0.7070 0.6291 0.7070 0.8408
No log 10.5333 158 0.7442 0.5745 0.7442 0.8626
No log 10.6667 160 0.6055 0.6605 0.6055 0.7781
No log 10.8 162 0.6192 0.5794 0.6192 0.7869
No log 10.9333 164 0.7527 0.5905 0.7527 0.8676
No log 11.0667 166 0.6687 0.6014 0.6687 0.8177
No log 11.2 168 0.5640 0.6667 0.5640 0.7510
No log 11.3333 170 0.5807 0.6623 0.5807 0.7620
No log 11.4667 172 0.5696 0.6335 0.5696 0.7547
No log 11.6 174 0.5696 0.6750 0.5696 0.7547
No log 11.7333 176 0.5664 0.6409 0.5664 0.7526
No log 11.8667 178 0.5595 0.6699 0.5595 0.7480
No log 12.0 180 0.5714 0.6497 0.5714 0.7559
No log 12.1333 182 0.5717 0.6393 0.5717 0.7561
No log 12.2667 184 0.5515 0.6374 0.5515 0.7426
No log 12.4 186 0.5841 0.5865 0.5841 0.7643
No log 12.5333 188 0.6035 0.6050 0.6035 0.7769
No log 12.6667 190 0.5787 0.5926 0.5787 0.7607
No log 12.8 192 0.5802 0.6051 0.5802 0.7617
No log 12.9333 194 0.5536 0.6460 0.5536 0.7440
No log 13.0667 196 0.5157 0.7409 0.5157 0.7181
No log 13.2 198 0.5539 0.6485 0.5539 0.7442
No log 13.3333 200 0.4963 0.7165 0.4963 0.7045
No log 13.4667 202 0.4672 0.7110 0.4672 0.6835
No log 13.6 204 0.4704 0.7158 0.4704 0.6859
No log 13.7333 206 0.4760 0.6748 0.4760 0.6899
No log 13.8667 208 0.5319 0.6572 0.5319 0.7293
No log 14.0 210 0.5973 0.5873 0.5973 0.7729
No log 14.1333 212 0.5754 0.6302 0.5754 0.7586
No log 14.2667 214 0.5846 0.6322 0.5846 0.7646
No log 14.4 216 0.6027 0.6435 0.6027 0.7764
No log 14.5333 218 0.5950 0.5759 0.5950 0.7714
No log 14.6667 220 0.6926 0.5598 0.6926 0.8323
No log 14.8 222 0.7060 0.5590 0.7060 0.8402
No log 14.9333 224 0.6087 0.5876 0.6087 0.7802
No log 15.0667 226 0.5902 0.5817 0.5902 0.7683
No log 15.2 228 0.5766 0.6207 0.5766 0.7593
No log 15.3333 230 0.5803 0.6018 0.5803 0.7618
No log 15.4667 232 0.6179 0.6125 0.6179 0.7861
No log 15.6 234 0.7473 0.5257 0.7473 0.8645
No log 15.7333 236 0.7555 0.5039 0.7555 0.8692
No log 15.8667 238 0.8393 0.4826 0.8393 0.9161
No log 16.0 240 1.0294 0.4228 1.0294 1.0146
No log 16.1333 242 0.9448 0.3973 0.9448 0.9720
No log 16.2667 244 0.6934 0.5138 0.6934 0.8327
No log 16.4 246 0.6082 0.6057 0.6082 0.7799
No log 16.5333 248 0.5950 0.5735 0.5950 0.7713
No log 16.6667 250 0.5974 0.5373 0.5974 0.7729
No log 16.8 252 0.6038 0.5886 0.6038 0.7770
No log 16.9333 254 0.6004 0.6187 0.6004 0.7749
No log 17.0667 256 0.6427 0.6090 0.6427 0.8017
No log 17.2 258 0.6524 0.5970 0.6524 0.8077
No log 17.3333 260 0.6206 0.6499 0.6206 0.7878
No log 17.4667 262 0.6026 0.6435 0.6026 0.7763
No log 17.6 264 0.6124 0.6076 0.6124 0.7825
No log 17.7333 266 0.6104 0.5690 0.6104 0.7813
No log 17.8667 268 0.6023 0.6105 0.6023 0.7761
No log 18.0 270 0.5935 0.6549 0.5935 0.7704
No log 18.1333 272 0.6049 0.6415 0.6049 0.7778
No log 18.2667 274 0.6007 0.6301 0.6007 0.7751
No log 18.4 276 0.5746 0.5978 0.5746 0.7580
No log 18.5333 278 0.5538 0.5921 0.5538 0.7442
No log 18.6667 280 0.5377 0.6228 0.5377 0.7333
No log 18.8 282 0.5058 0.6857 0.5058 0.7112
No log 18.9333 284 0.5029 0.6962 0.5029 0.7091
No log 19.0667 286 0.4965 0.6962 0.4965 0.7046
No log 19.2 288 0.4966 0.6962 0.4966 0.7047
No log 19.3333 290 0.5004 0.7001 0.5004 0.7074
No log 19.4667 292 0.5033 0.7001 0.5033 0.7094
No log 19.6 294 0.5183 0.6993 0.5183 0.7200
No log 19.7333 296 0.5118 0.7001 0.5118 0.7154
No log 19.8667 298 0.5325 0.6383 0.5325 0.7297
No log 20.0 300 0.5527 0.6248 0.5527 0.7434
No log 20.1333 302 0.5250 0.6374 0.5250 0.7246
No log 20.2667 304 0.5470 0.6807 0.5470 0.7396
No log 20.4 306 0.5785 0.6807 0.5785 0.7606
No log 20.5333 308 0.5470 0.6815 0.5470 0.7396
No log 20.6667 310 0.5703 0.5831 0.5703 0.7552
No log 20.8 312 0.6233 0.5699 0.6233 0.7895
No log 20.9333 314 0.6063 0.6092 0.6063 0.7787
No log 21.0667 316 0.5146 0.6838 0.5146 0.7174
No log 21.2 318 0.4926 0.7164 0.4926 0.7019
No log 21.3333 320 0.6147 0.6300 0.6147 0.7840
No log 21.4667 322 0.6386 0.5835 0.6386 0.7992
No log 21.6 324 0.5804 0.6654 0.5804 0.7619
No log 21.7333 326 0.5391 0.5666 0.5391 0.7342
No log 21.8667 328 0.5396 0.5704 0.5396 0.7346
No log 22.0 330 0.5383 0.6129 0.5383 0.7337
No log 22.1333 332 0.5272 0.6390 0.5272 0.7261
No log 22.2667 334 0.5411 0.6588 0.5411 0.7356
No log 22.4 336 0.6175 0.6295 0.6175 0.7858
No log 22.5333 338 0.6316 0.6101 0.6316 0.7947
No log 22.6667 340 0.6025 0.6051 0.6025 0.7762
No log 22.8 342 0.5840 0.6407 0.5840 0.7642
No log 22.9333 344 0.5864 0.5188 0.5864 0.7657
No log 23.0667 346 0.5979 0.5568 0.5979 0.7732
No log 23.2 348 0.5749 0.5301 0.5749 0.7583
No log 23.3333 350 0.5665 0.6407 0.5665 0.7527
No log 23.4667 352 0.5613 0.5845 0.5613 0.7492
No log 23.6 354 0.6211 0.5977 0.6211 0.7881
No log 23.7333 356 0.7599 0.5491 0.7599 0.8717
No log 23.8667 358 0.7348 0.5495 0.7348 0.8572
No log 24.0 360 0.6497 0.5782 0.6497 0.8060
No log 24.1333 362 0.5732 0.5669 0.5732 0.7571
No log 24.2667 364 0.5905 0.6122 0.5905 0.7684
No log 24.4 366 0.6120 0.6021 0.6120 0.7823
No log 24.5333 368 0.5852 0.6241 0.5852 0.7650
No log 24.6667 370 0.5725 0.6518 0.5725 0.7566
No log 24.8 372 0.5717 0.6241 0.5717 0.7561
No log 24.9333 374 0.5861 0.5763 0.5861 0.7656
No log 25.0667 376 0.5692 0.5986 0.5692 0.7544
No log 25.2 378 0.5601 0.6241 0.5601 0.7484
No log 25.3333 380 0.5625 0.6688 0.5625 0.7500
No log 25.4667 382 0.5724 0.6499 0.5724 0.7566
No log 25.6 384 0.5883 0.6377 0.5883 0.7670
No log 25.7333 386 0.6158 0.6244 0.6158 0.7847
No log 25.8667 388 0.6442 0.6244 0.6442 0.8026
No log 26.0 390 0.6119 0.6244 0.6119 0.7823
No log 26.1333 392 0.5540 0.6460 0.5540 0.7443
No log 26.2667 394 0.5267 0.6230 0.5267 0.7257
No log 26.4 396 0.5248 0.6787 0.5248 0.7244
No log 26.5333 398 0.5055 0.6978 0.5055 0.7110
No log 26.6667 400 0.5111 0.6479 0.5111 0.7149
No log 26.8 402 0.5614 0.6646 0.5614 0.7493
No log 26.9333 404 0.5711 0.6916 0.5711 0.7557
No log 27.0667 406 0.5579 0.6902 0.5579 0.7469
No log 27.2 408 0.5467 0.6161 0.5467 0.7394
No log 27.3333 410 0.5475 0.6276 0.5475 0.7399
No log 27.4667 412 0.5345 0.6139 0.5345 0.7311
No log 27.6 414 0.5085 0.6950 0.5085 0.7131
No log 27.7333 416 0.5218 0.7051 0.5218 0.7224
No log 27.8667 418 0.5390 0.7051 0.5390 0.7342
No log 28.0 420 0.5683 0.6539 0.5683 0.7538
No log 28.1333 422 0.5992 0.6415 0.5992 0.7741
No log 28.2667 424 0.6020 0.6210 0.6020 0.7759
No log 28.4 426 0.6044 0.6444 0.6044 0.7774
No log 28.5333 428 0.6084 0.6394 0.6084 0.7800
No log 28.6667 430 0.5814 0.6601 0.5814 0.7625
No log 28.8 432 0.5689 0.6601 0.5689 0.7543
No log 28.9333 434 0.5527 0.6620 0.5527 0.7435
No log 29.0667 436 0.5604 0.6302 0.5604 0.7486
No log 29.2 438 0.5787 0.5359 0.5787 0.7607
No log 29.3333 440 0.5624 0.6067 0.5624 0.7500
No log 29.4667 442 0.5443 0.6508 0.5443 0.7378
No log 29.6 444 0.5581 0.6620 0.5581 0.7471
No log 29.7333 446 0.5841 0.6394 0.5841 0.7643
No log 29.8667 448 0.6036 0.6394 0.6036 0.7769
No log 30.0 450 0.5883 0.6769 0.5883 0.7670
No log 30.1333 452 0.5650 0.6243 0.5650 0.7517
No log 30.2667 454 0.5431 0.6343 0.5431 0.7369
No log 30.4 456 0.5365 0.6685 0.5365 0.7325
No log 30.5333 458 0.5069 0.6442 0.5069 0.7119
No log 30.6667 460 0.5036 0.6712 0.5036 0.7096
No log 30.8 462 0.5081 0.6880 0.5081 0.7128
No log 30.9333 464 0.5110 0.6649 0.5110 0.7149
No log 31.0667 466 0.5487 0.6334 0.5487 0.7408
No log 31.2 468 0.5944 0.6308 0.5944 0.7710
No log 31.3333 470 0.6059 0.5913 0.6059 0.7784
No log 31.4667 472 0.5750 0.6292 0.5750 0.7583
No log 31.6 474 0.5660 0.6681 0.5660 0.7524
No log 31.7333 476 0.5597 0.6354 0.5597 0.7481
No log 31.8667 478 0.5518 0.6479 0.5518 0.7428
No log 32.0 480 0.5442 0.6535 0.5442 0.7377
No log 32.1333 482 0.5363 0.6215 0.5363 0.7323
No log 32.2667 484 0.5282 0.6575 0.5282 0.7268
No log 32.4 486 0.5314 0.7009 0.5314 0.7290
No log 32.5333 488 0.5594 0.7035 0.5594 0.7479
No log 32.6667 490 0.6227 0.5981 0.6227 0.7891
No log 32.8 492 0.6521 0.5860 0.6521 0.8075
No log 32.9333 494 0.6376 0.5860 0.6376 0.7985
No log 33.0667 496 0.6016 0.6009 0.6016 0.7756
No log 33.2 498 0.5645 0.7035 0.5645 0.7513
0.268 33.3333 500 0.5431 0.6903 0.5431 0.7369
0.268 33.4667 502 0.5382 0.6575 0.5382 0.7336
0.268 33.6 504 0.5327 0.6903 0.5327 0.7299
0.268 33.7333 506 0.5355 0.7043 0.5355 0.7318
0.268 33.8667 508 0.5549 0.7035 0.5549 0.7449
0.268 34.0 510 0.5987 0.6520 0.5987 0.7738
0.268 34.1333 512 0.5974 0.6691 0.5974 0.7729
0.268 34.2667 514 0.5568 0.6985 0.5568 0.7462
0.268 34.4 516 0.5250 0.6824 0.5250 0.7246
0.268 34.5333 518 0.5154 0.6380 0.5154 0.7179
0.268 34.6667 520 0.5138 0.6488 0.5138 0.7168
0.268 34.8 522 0.5250 0.7101 0.5250 0.7246
0.268 34.9333 524 0.5509 0.7157 0.5509 0.7422
0.268 35.0667 526 0.5415 0.7101 0.5415 0.7359
0.268 35.2 528 0.5170 0.6993 0.5170 0.7190
0.268 35.3333 530 0.5086 0.6911 0.5086 0.7132
0.268 35.4667 532 0.5172 0.6675 0.5172 0.7192
0.268 35.6 534 0.5092 0.6675 0.5092 0.7136
0.268 35.7333 536 0.4906 0.6770 0.4906 0.7004
0.268 35.8667 538 0.4885 0.6962 0.4885 0.6989
0.268 36.0 540 0.5149 0.6993 0.5149 0.7176
0.268 36.1333 542 0.5228 0.6993 0.5228 0.7230
0.268 36.2667 544 0.5029 0.7171 0.5029 0.7092
0.268 36.4 546 0.5031 0.6681 0.5031 0.7093
0.268 36.5333 548 0.5101 0.6911 0.5101 0.7142
0.268 36.6667 550 0.4975 0.7186 0.4975 0.7053
0.268 36.8 552 0.4923 0.7082 0.4923 0.7017
0.268 36.9333 554 0.5038 0.6778 0.5038 0.7098
0.268 37.0667 556 0.5383 0.6828 0.5383 0.7337
0.268 37.2 558 0.5528 0.6707 0.5528 0.7435
0.268 37.3333 560 0.5621 0.6648 0.5621 0.7497
0.268 37.4667 562 0.5319 0.6620 0.5319 0.7293

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_k5_task5_organization

Finetuned
(4205)
this model