ArabicNewSplits5_FineTuningAraBERT_run2_AugV5_k9_task3_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: 0.5837
  • Qwk: 0.2201
  • Mse: 0.5837
  • Rmse: 0.7640

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: 10

Training results

Training Loss Epoch Step Validation Loss Qwk Mse Rmse
No log 0.0370 2 3.3236 -0.0138 3.3236 1.8231
No log 0.0741 4 1.7206 -0.0070 1.7206 1.3117
No log 0.1111 6 1.7602 0.0390 1.7602 1.3267
No log 0.1481 8 1.4686 0.0255 1.4686 1.2119
No log 0.1852 10 1.4755 0.0588 1.4755 1.2147
No log 0.2222 12 0.7117 0.25 0.7117 0.8436
No log 0.2593 14 0.5923 0.0569 0.5923 0.7696
No log 0.2963 16 0.6304 0.1746 0.6304 0.7940
No log 0.3333 18 0.8066 0.1220 0.8066 0.8981
No log 0.3704 20 1.1538 0.0 1.1538 1.0741
No log 0.4074 22 1.2782 0.0 1.2782 1.1306
No log 0.4444 24 1.1484 0.0 1.1484 1.0716
No log 0.4815 26 0.8712 0.0685 0.8712 0.9334
No log 0.5185 28 0.7955 0.0476 0.7955 0.8919
No log 0.5556 30 0.7765 0.1323 0.7765 0.8812
No log 0.5926 32 1.0732 0.0288 1.0732 1.0360
No log 0.6296 34 1.3565 0.0596 1.3565 1.1647
No log 0.6667 36 0.9177 0.0320 0.9177 0.9580
No log 0.7037 38 0.8130 0.0359 0.8130 0.9016
No log 0.7407 40 1.2175 0.0861 1.2175 1.1034
No log 0.7778 42 0.9376 0.1186 0.9376 0.9683
No log 0.8148 44 0.5635 0.1304 0.5635 0.7507
No log 0.8519 46 0.5598 0.0 0.5598 0.7482
No log 0.8889 48 0.5340 0.1008 0.5340 0.7307
No log 0.9259 50 0.8824 0.1055 0.8824 0.9393
No log 0.9630 52 1.0621 0.1128 1.0621 1.0306
No log 1.0 54 0.6818 0.2083 0.6818 0.8257
No log 1.0370 56 0.5724 0.1895 0.5724 0.7565
No log 1.0741 58 0.5525 0.1111 0.5525 0.7433
No log 1.1111 60 0.5965 0.1605 0.5965 0.7724
No log 1.1481 62 0.6452 0.1515 0.6452 0.8032
No log 1.1852 64 0.7652 0.0359 0.7652 0.8747
No log 1.2222 66 1.0489 0.1074 1.0489 1.0242
No log 1.2593 68 0.6923 0.1111 0.6923 0.8321
No log 1.2963 70 0.6380 0.0625 0.6380 0.7988
No log 1.3333 72 0.6531 0.0769 0.6531 0.8082
No log 1.3704 74 0.5804 0.1282 0.5804 0.7618
No log 1.4074 76 0.8963 0.1392 0.8963 0.9467
No log 1.4444 78 1.2497 0.0345 1.2497 1.1179
No log 1.4815 80 1.2711 0.0345 1.2711 1.1274
No log 1.5185 82 0.7487 0.1174 0.7487 0.8653
No log 1.5556 84 0.5625 0.0303 0.5625 0.7500
No log 1.5926 86 0.7315 0.2298 0.7315 0.8553
No log 1.6296 88 0.8664 0.1273 0.8664 0.9308
No log 1.6667 90 0.6282 0.1781 0.6282 0.7926
No log 1.7037 92 0.8518 0.0918 0.8518 0.9229
No log 1.7407 94 0.8183 0.1373 0.8183 0.9046
No log 1.7778 96 0.5777 0.1642 0.5777 0.7601
No log 1.8148 98 0.8053 0.1179 0.8053 0.8974
No log 1.8519 100 0.7755 0.1556 0.7755 0.8806
No log 1.8889 102 0.5483 0.0080 0.5483 0.7404
No log 1.9259 104 0.5456 0.2908 0.5456 0.7386
No log 1.9630 106 0.6321 0.2184 0.6321 0.7950
No log 2.0 108 0.6250 0.2889 0.6250 0.7906
No log 2.0370 110 0.5218 0.2533 0.5218 0.7224
No log 2.0741 112 0.6373 0.2360 0.6373 0.7983
No log 2.1111 114 0.8646 0.3333 0.8646 0.9299
No log 2.1481 116 0.6834 0.3191 0.6834 0.8267
No log 2.1852 118 0.5128 0.3865 0.5128 0.7161
No log 2.2222 120 0.8238 0.2397 0.8238 0.9076
No log 2.2593 122 0.8332 0.2397 0.8332 0.9128
No log 2.2963 124 0.5311 0.3086 0.5311 0.7287
No log 2.3333 126 0.6747 0.2832 0.6747 0.8214
No log 2.3704 128 0.7053 0.2457 0.7053 0.8398
No log 2.4074 130 0.6719 0.2857 0.6719 0.8197
No log 2.4444 132 0.5797 0.2208 0.5797 0.7614
No log 2.4815 134 0.5832 0.35 0.5832 0.7636
No log 2.5185 136 0.5874 0.2195 0.5874 0.7664
No log 2.5556 138 0.6448 0.2184 0.6448 0.8030
No log 2.5926 140 0.6101 0.0983 0.6101 0.7811
No log 2.6296 142 0.6630 0.2542 0.6630 0.8143
No log 2.6667 144 0.7060 0.2169 0.7060 0.8403
No log 2.7037 146 0.7733 0.2251 0.7733 0.8793
No log 2.7407 148 0.8997 0.1504 0.8997 0.9485
No log 2.7778 150 0.7280 0.2475 0.7280 0.8532
No log 2.8148 152 0.7857 0.2269 0.7857 0.8864
No log 2.8519 154 0.6999 0.2536 0.6999 0.8366
No log 2.8889 156 0.8842 0.2134 0.8842 0.9403
No log 2.9259 158 1.2367 0.1155 1.2367 1.1121
No log 2.9630 160 0.9930 0.1304 0.9930 0.9965
No log 3.0 162 0.7384 0.1753 0.7384 0.8593
No log 3.0370 164 0.6389 0.2787 0.6389 0.7993
No log 3.0741 166 0.6582 0.2787 0.6582 0.8113
No log 3.1111 168 0.7885 0.1683 0.7885 0.8880
No log 3.1481 170 1.1029 0.1304 1.1029 1.0502
No log 3.1852 172 1.0399 0.0977 1.0399 1.0198
No log 3.2222 174 0.8274 0.1402 0.8274 0.9096
No log 3.2593 176 0.8281 0.1402 0.8281 0.9100
No log 3.2963 178 0.9378 0.125 0.9378 0.9684
No log 3.3333 180 0.7593 0.1414 0.7593 0.8714
No log 3.3704 182 0.6320 0.2381 0.6320 0.7950
No log 3.4074 184 0.6891 0.1364 0.6891 0.8301
No log 3.4444 186 0.8337 0.2287 0.8337 0.9131
No log 3.4815 188 0.6927 0.1364 0.6927 0.8323
No log 3.5185 190 0.5992 0.2749 0.5992 0.7741
No log 3.5556 192 0.6119 0.2184 0.6119 0.7823
No log 3.5926 194 0.5878 0.3103 0.5878 0.7667
No log 3.6296 196 0.8986 0.1621 0.8986 0.9479
No log 3.6667 198 1.1176 0.12 1.1176 1.0572
No log 3.7037 200 0.9107 0.1939 0.9107 0.9543
No log 3.7407 202 0.5640 0.3898 0.5640 0.7510
No log 3.7778 204 0.7869 0.2661 0.7869 0.8871
No log 3.8148 206 0.8894 0.2275 0.8894 0.9431
No log 3.8519 208 0.6358 0.2670 0.6358 0.7974
No log 3.8889 210 0.5509 0.2471 0.5509 0.7422
No log 3.9259 212 0.7413 0.2000 0.7413 0.8610
No log 3.9630 214 0.7747 0.2381 0.7747 0.8802
No log 4.0 216 0.6718 0.2000 0.6718 0.8196
No log 4.0370 218 0.5243 0.2883 0.5243 0.7241
No log 4.0741 220 0.5325 0.2795 0.5325 0.7297
No log 4.1111 222 0.5183 0.2795 0.5183 0.7199
No log 4.1481 224 0.5354 0.2208 0.5354 0.7317
No log 4.1852 226 0.7606 0.2000 0.7606 0.8721
No log 4.2222 228 0.7984 0.2000 0.7984 0.8935
No log 4.2593 230 0.6229 0.2000 0.6229 0.7892
No log 4.2963 232 0.5349 0.2821 0.5349 0.7314
No log 4.3333 234 0.6848 0.2593 0.6848 0.8275
No log 4.3704 236 0.7282 0.2323 0.7282 0.8533
No log 4.4074 238 0.5807 0.1905 0.5807 0.7620
No log 4.4444 240 0.5724 0.2704 0.5724 0.7565
No log 4.4815 242 0.8737 0.2000 0.8737 0.9347
No log 4.5185 244 0.9525 0.1686 0.9525 0.9760
No log 4.5556 246 0.7634 0.1538 0.7634 0.8737
No log 4.5926 248 0.5804 0.3371 0.5804 0.7619
No log 4.6296 250 0.5816 0.3371 0.5816 0.7626
No log 4.6667 252 0.6006 0.2189 0.6006 0.7750
No log 4.7037 254 0.7850 0.1923 0.7850 0.8860
No log 4.7407 256 0.9741 0.1686 0.9741 0.9870
No log 4.7778 258 0.9338 0.2000 0.9338 0.9663
No log 4.8148 260 0.7718 0.1917 0.7718 0.8785
No log 4.8519 262 0.5977 0.2644 0.5977 0.7731
No log 4.8889 264 0.5901 0.3258 0.5901 0.7682
No log 4.9259 266 0.6024 0.2174 0.6024 0.7762
No log 4.9630 268 0.8608 0.2203 0.8608 0.9278
No log 5.0 270 1.0557 0.1378 1.0557 1.0275
No log 5.0370 272 0.9234 0.1934 0.9234 0.9609
No log 5.0741 274 0.7075 0.3208 0.7075 0.8411
No log 5.1111 276 0.5974 0.2865 0.5974 0.7729
No log 5.1481 278 0.6235 0.3299 0.6235 0.7896
No log 5.1852 280 0.7037 0.3271 0.7037 0.8388
No log 5.2222 282 0.6428 0.3769 0.6428 0.8018
No log 5.2593 284 0.6610 0.4227 0.6610 0.8130
No log 5.2963 286 0.6586 0.3878 0.6586 0.8116
No log 5.3333 288 0.5871 0.3520 0.5871 0.7662
No log 5.3704 290 0.5246 0.2970 0.5246 0.7243
No log 5.4074 292 0.5392 0.3208 0.5392 0.7343
No log 5.4444 294 0.5710 0.2857 0.5710 0.7557
No log 5.4815 296 0.5381 0.2611 0.5381 0.7335
No log 5.5185 298 0.5148 0.2821 0.5148 0.7175
No log 5.5556 300 0.5231 0.2771 0.5231 0.7232
No log 5.5926 302 0.5564 0.2611 0.5564 0.7459
No log 5.6296 304 0.5529 0.2883 0.5529 0.7435
No log 5.6667 306 0.5576 0.2883 0.5576 0.7467
No log 5.7037 308 0.5668 0.2883 0.5668 0.7528
No log 5.7407 310 0.6011 0.2575 0.6011 0.7753
No log 5.7778 312 0.6362 0.2663 0.6362 0.7976
No log 5.8148 314 0.6540 0.2593 0.6540 0.8087
No log 5.8519 316 0.6903 0.2653 0.6903 0.8308
No log 5.8889 318 0.6877 0.2653 0.6877 0.8293
No log 5.9259 320 0.6250 0.3407 0.6250 0.7905
No log 5.9630 322 0.5652 0.3295 0.5652 0.7518
No log 6.0 324 0.5716 0.3258 0.5716 0.7561
No log 6.0370 326 0.5716 0.3258 0.5716 0.7560
No log 6.0741 328 0.6652 0.2990 0.6652 0.8156
No log 6.1111 330 0.7379 0.2653 0.7379 0.8590
No log 6.1481 332 0.7143 0.2670 0.7143 0.8452
No log 6.1852 334 0.6318 0.3103 0.6318 0.7949
No log 6.2222 336 0.5791 0.2749 0.5791 0.7610
No log 6.2593 338 0.5619 0.3023 0.5619 0.7496
No log 6.2963 340 0.5683 0.2914 0.5683 0.7539
No log 6.3333 342 0.5776 0.2857 0.5776 0.7600
No log 6.3704 344 0.6903 0.2273 0.6903 0.8308
No log 6.4074 346 0.7369 0.3118 0.7369 0.8584
No log 6.4444 348 0.6707 0.2273 0.6707 0.8190
No log 6.4815 350 0.6564 0.2273 0.6564 0.8102
No log 6.5185 352 0.6108 0.3136 0.6108 0.7815
No log 6.5556 354 0.5498 0.2857 0.5498 0.7415
No log 6.5926 356 0.5381 0.2857 0.5381 0.7336
No log 6.6296 358 0.5604 0.2970 0.5604 0.7486
No log 6.6667 360 0.6092 0.2281 0.6092 0.7805
No log 6.7037 362 0.6689 0.2809 0.6689 0.8179
No log 6.7407 364 0.6181 0.2381 0.6181 0.7862
No log 6.7778 366 0.5444 0.2970 0.5444 0.7378
No log 6.8148 368 0.5202 0.2883 0.5202 0.7212
No log 6.8519 370 0.5223 0.2911 0.5223 0.7227
No log 6.8889 372 0.5343 0.2970 0.5343 0.7309
No log 6.9259 374 0.5596 0.2471 0.5596 0.7481
No log 6.9630 376 0.5639 0.2471 0.5639 0.7510
No log 7.0 378 0.5319 0.2970 0.5319 0.7293
No log 7.0370 380 0.5298 0.2970 0.5298 0.7279
No log 7.0741 382 0.5612 0.2970 0.5612 0.7491
No log 7.1111 384 0.6240 0.2273 0.6240 0.7899
No log 7.1481 386 0.6246 0.2749 0.6246 0.7903
No log 7.1852 388 0.5890 0.2704 0.5890 0.7675
No log 7.2222 390 0.5450 0.2970 0.5450 0.7382
No log 7.2593 392 0.5197 0.3000 0.5197 0.7209
No log 7.2963 394 0.5219 0.3000 0.5219 0.7225
No log 7.3333 396 0.5387 0.2970 0.5387 0.7340
No log 7.3704 398 0.5688 0.3208 0.5688 0.7542
No log 7.4074 400 0.5991 0.2911 0.5991 0.7740
No log 7.4444 402 0.5857 0.3659 0.5857 0.7653
No log 7.4815 404 0.5429 0.2970 0.5429 0.7368
No log 7.5185 406 0.5315 0.3000 0.5315 0.7291
No log 7.5556 408 0.5505 0.2970 0.5505 0.7419
No log 7.5926 410 0.6185 0.2911 0.6185 0.7864
No log 7.6296 412 0.6646 0.2370 0.6646 0.8153
No log 7.6667 414 0.6491 0.2911 0.6491 0.8056
No log 7.7037 416 0.6205 0.2911 0.6205 0.7877
No log 7.7407 418 0.5676 0.2970 0.5676 0.7534
No log 7.7778 420 0.5556 0.2970 0.5556 0.7454
No log 7.8148 422 0.5682 0.2970 0.5682 0.7538
No log 7.8519 424 0.6254 0.3054 0.6254 0.7908
No log 7.8889 426 0.6801 0.2350 0.6801 0.8247
No log 7.9259 428 0.6938 0.2350 0.6938 0.8329
No log 7.9630 430 0.6566 0.2281 0.6566 0.8103
No log 8.0 432 0.6253 0.3054 0.6253 0.7907
No log 8.0370 434 0.6183 0.3054 0.6183 0.7863
No log 8.0741 436 0.6305 0.3171 0.6305 0.7940
No log 8.1111 438 0.6269 0.3171 0.6269 0.7917
No log 8.1481 440 0.6256 0.3171 0.6256 0.7910
No log 8.1852 442 0.6074 0.3171 0.6074 0.7794
No log 8.2222 444 0.5831 0.2593 0.5831 0.7636
No log 8.2593 446 0.5561 0.2611 0.5561 0.7457
No log 8.2963 448 0.5462 0.2611 0.5462 0.7391
No log 8.3333 450 0.5498 0.2611 0.5498 0.7415
No log 8.3704 452 0.5525 0.2611 0.5525 0.7433
No log 8.4074 454 0.5715 0.2208 0.5715 0.7560
No log 8.4444 456 0.5796 0.2308 0.5796 0.7613
No log 8.4815 458 0.5628 0.2208 0.5628 0.7502
No log 8.5185 460 0.5609 0.2208 0.5609 0.7489
No log 8.5556 462 0.5745 0.2201 0.5745 0.7580
No log 8.5926 464 0.5756 0.2201 0.5756 0.7587
No log 8.6296 466 0.5840 0.2201 0.5840 0.7642
No log 8.6667 468 0.5898 0.2201 0.5898 0.7680
No log 8.7037 470 0.5964 0.2683 0.5964 0.7723
No log 8.7407 472 0.5876 0.3054 0.5876 0.7666
No log 8.7778 474 0.5744 0.2970 0.5744 0.7579
No log 8.8148 476 0.5606 0.2970 0.5606 0.7488
No log 8.8519 478 0.5631 0.2970 0.5631 0.7504
No log 8.8889 480 0.5635 0.2970 0.5635 0.7507
No log 8.9259 482 0.5728 0.2970 0.5728 0.7568
No log 8.9630 484 0.5882 0.3412 0.5882 0.7669
No log 9.0 486 0.5909 0.3412 0.5909 0.7687
No log 9.0370 488 0.6043 0.3054 0.6043 0.7774
No log 9.0741 490 0.6048 0.3054 0.6048 0.7777
No log 9.1111 492 0.6163 0.2683 0.6163 0.7850
No log 9.1481 494 0.6279 0.2771 0.6279 0.7924
No log 9.1852 496 0.6343 0.2771 0.6343 0.7964
No log 9.2222 498 0.6126 0.2683 0.6126 0.7827
0.3871 9.2593 500 0.5864 0.2593 0.5864 0.7657
0.3871 9.2963 502 0.5675 0.2970 0.5675 0.7534
0.3871 9.3333 504 0.5613 0.2970 0.5613 0.7492
0.3871 9.3704 506 0.5521 0.2970 0.5521 0.7430
0.3871 9.4074 508 0.5481 0.2970 0.5481 0.7403
0.3871 9.4444 510 0.5488 0.2970 0.5488 0.7408
0.3871 9.4815 512 0.5520 0.2970 0.5520 0.7430
0.3871 9.5185 514 0.5588 0.2970 0.5588 0.7475
0.3871 9.5556 516 0.5695 0.2970 0.5695 0.7547
0.3871 9.5926 518 0.5793 0.2593 0.5793 0.7611
0.3871 9.6296 520 0.5896 0.2201 0.5896 0.7678
0.3871 9.6667 522 0.5945 0.2201 0.5945 0.7711
0.3871 9.7037 524 0.5986 0.2683 0.5986 0.7737
0.3871 9.7407 526 0.6033 0.2683 0.6033 0.7767
0.3871 9.7778 528 0.6007 0.2683 0.6007 0.7750
0.3871 9.8148 530 0.5942 0.2201 0.5942 0.7708
0.3871 9.8519 532 0.5889 0.2201 0.5889 0.7674
0.3871 9.8889 534 0.5855 0.2201 0.5855 0.7652
0.3871 9.9259 536 0.5841 0.2201 0.5841 0.7643
0.3871 9.9630 538 0.5838 0.2201 0.5838 0.7640
0.3871 10.0 540 0.5837 0.2201 0.5837 0.7640

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
0.1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for MayBashendy/ArabicNewSplits5_FineTuningAraBERT_run2_AugV5_k9_task3_organization

Finetuned
(4040)
this model