ArabicNewSplits5_FineTuningAraBERT_run3_AugV5_k10_task1_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: 0.7907
  • Qwk: 0.6339
  • Mse: 0.7907
  • Rmse: 0.8892

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 0.0312 2 5.2730 -0.0306 5.2730 2.2963
No log 0.0625 4 3.1234 0.0817 3.1234 1.7673
No log 0.0938 6 2.6627 -0.1526 2.6627 1.6318
No log 0.125 8 2.6211 -0.1763 2.6211 1.6190
No log 0.1562 10 2.7341 -0.1793 2.7341 1.6535
No log 0.1875 12 1.9606 -0.0376 1.9606 1.4002
No log 0.2188 14 1.8737 0.0143 1.8737 1.3688
No log 0.25 16 1.8202 0.0187 1.8202 1.3492
No log 0.2812 18 1.8011 0.0368 1.8011 1.3420
No log 0.3125 20 1.6309 0.0187 1.6309 1.2771
No log 0.3438 22 1.4236 0.0445 1.4236 1.1931
No log 0.375 24 1.2946 0.2327 1.2946 1.1378
No log 0.4062 26 1.2981 0.2300 1.2981 1.1393
No log 0.4375 28 1.5811 0.0565 1.5811 1.2574
No log 0.4688 30 2.0215 0.0585 2.0215 1.4218
No log 0.5 32 2.4869 0.0669 2.4869 1.5770
No log 0.5312 34 2.1876 0.1259 2.1876 1.4790
No log 0.5625 36 1.8208 0.1095 1.8208 1.3494
No log 0.5938 38 1.5776 0.0819 1.5776 1.2560
No log 0.625 40 1.2765 0.1636 1.2765 1.1298
No log 0.6562 42 1.1644 0.2661 1.1644 1.0791
No log 0.6875 44 1.1738 0.2653 1.1738 1.0834
No log 0.7188 46 1.1974 0.2971 1.1974 1.0943
No log 0.75 48 1.3675 0.2095 1.3675 1.1694
No log 0.7812 50 1.4411 0.2358 1.4411 1.2005
No log 0.8125 52 1.4979 0.2078 1.4979 1.2239
No log 0.8438 54 1.3417 0.2477 1.3417 1.1583
No log 0.875 56 1.2316 0.2554 1.2316 1.1098
No log 0.9062 58 1.2764 0.2512 1.2764 1.1298
No log 0.9375 60 1.2238 0.2746 1.2238 1.1063
No log 0.9688 62 1.2795 0.2639 1.2795 1.1312
No log 1.0 64 1.2922 0.2411 1.2922 1.1367
No log 1.0312 66 1.2549 0.2175 1.2549 1.1202
No log 1.0625 68 1.2185 0.2506 1.2185 1.1038
No log 1.0938 70 1.3274 0.2906 1.3274 1.1521
No log 1.125 72 1.4894 0.3146 1.4894 1.2204
No log 1.1562 74 1.5153 0.2926 1.5153 1.2310
No log 1.1875 76 1.3196 0.3821 1.3196 1.1488
No log 1.2188 78 1.1990 0.4265 1.1990 1.0950
No log 1.25 80 1.1128 0.4141 1.1128 1.0549
No log 1.2812 82 1.0543 0.4676 1.0543 1.0268
No log 1.3125 84 1.0984 0.4868 1.0984 1.0480
No log 1.3438 86 1.0439 0.5027 1.0439 1.0217
No log 1.375 88 1.0072 0.5045 1.0072 1.0036
No log 1.4062 90 1.0291 0.5472 1.0291 1.0144
No log 1.4375 92 1.1078 0.5379 1.1078 1.0525
No log 1.4688 94 1.1155 0.5498 1.1155 1.0562
No log 1.5 96 1.0191 0.5447 1.0191 1.0095
No log 1.5312 98 0.9457 0.5450 0.9457 0.9725
No log 1.5625 100 0.9303 0.5475 0.9303 0.9645
No log 1.5938 102 0.9616 0.5093 0.9616 0.9806
No log 1.625 104 0.9297 0.5224 0.9297 0.9642
No log 1.6562 106 0.9369 0.5416 0.9369 0.9679
No log 1.6875 108 1.0587 0.5118 1.0587 1.0289
No log 1.7188 110 1.1953 0.4750 1.1953 1.0933
No log 1.75 112 1.1153 0.4948 1.1153 1.0561
No log 1.7812 114 0.9279 0.5845 0.9279 0.9633
No log 1.8125 116 0.8810 0.6086 0.8810 0.9386
No log 1.8438 118 0.8483 0.6144 0.8483 0.9210
No log 1.875 120 0.7674 0.6598 0.7674 0.8760
No log 1.9062 122 0.7347 0.6874 0.7347 0.8572
No log 1.9375 124 0.7329 0.6725 0.7329 0.8561
No log 1.9688 126 0.7896 0.6173 0.7896 0.8886
No log 2.0 128 0.8466 0.5729 0.8466 0.9201
No log 2.0312 130 0.8584 0.5729 0.8584 0.9265
No log 2.0625 132 0.7997 0.5883 0.7997 0.8943
No log 2.0938 134 0.7538 0.6338 0.7538 0.8682
No log 2.125 136 0.7074 0.6544 0.7074 0.8411
No log 2.1562 138 0.7219 0.6696 0.7219 0.8496
No log 2.1875 140 0.7525 0.6548 0.7525 0.8675
No log 2.2188 142 0.7905 0.6314 0.7905 0.8891
No log 2.25 144 0.8626 0.6409 0.8626 0.9288
No log 2.2812 146 0.8647 0.5848 0.8647 0.9299
No log 2.3125 148 0.8404 0.5985 0.8404 0.9167
No log 2.3438 150 0.8383 0.6854 0.8383 0.9156
No log 2.375 152 0.9006 0.5970 0.9006 0.9490
No log 2.4062 154 0.8904 0.6201 0.8904 0.9436
No log 2.4375 156 0.8156 0.6613 0.8156 0.9031
No log 2.4688 158 0.7811 0.6482 0.7811 0.8838
No log 2.5 160 0.7426 0.6536 0.7426 0.8618
No log 2.5312 162 0.7027 0.6456 0.7027 0.8383
No log 2.5625 164 0.6987 0.6397 0.6987 0.8359
No log 2.5938 166 0.7211 0.5704 0.7211 0.8491
No log 2.625 168 0.7536 0.5586 0.7536 0.8681
No log 2.6562 170 0.7708 0.6042 0.7708 0.8780
No log 2.6875 172 0.7657 0.6179 0.7657 0.8750
No log 2.7188 174 0.7389 0.5940 0.7389 0.8596
No log 2.75 176 0.7654 0.5776 0.7654 0.8749
No log 2.7812 178 0.8288 0.5806 0.8288 0.9104
No log 2.8125 180 0.8327 0.5886 0.8327 0.9125
No log 2.8438 182 0.7975 0.5787 0.7975 0.8930
No log 2.875 184 0.8054 0.5429 0.8054 0.8974
No log 2.9062 186 0.8298 0.5614 0.8298 0.9109
No log 2.9375 188 0.8341 0.5461 0.8341 0.9133
No log 2.9688 190 0.8604 0.5873 0.8604 0.9276
No log 3.0 192 0.8625 0.5852 0.8625 0.9287
No log 3.0312 194 0.8236 0.5925 0.8236 0.9075
No log 3.0625 196 0.8014 0.5610 0.8014 0.8952
No log 3.0938 198 0.8090 0.5288 0.8090 0.8994
No log 3.125 200 0.8175 0.5198 0.8175 0.9041
No log 3.1562 202 0.8306 0.5869 0.8306 0.9114
No log 3.1875 204 0.8828 0.5715 0.8828 0.9396
No log 3.2188 206 0.8826 0.5922 0.8826 0.9395
No log 3.25 208 0.8109 0.6010 0.8109 0.9005
No log 3.2812 210 0.7779 0.5969 0.7779 0.8820
No log 3.3125 212 0.7395 0.6182 0.7395 0.8599
No log 3.3438 214 0.6825 0.6580 0.6825 0.8261
No log 3.375 216 0.7496 0.6613 0.7496 0.8658
No log 3.4062 218 0.8040 0.6141 0.8040 0.8967
No log 3.4375 220 0.7974 0.6054 0.7974 0.8930
No log 3.4688 222 0.7978 0.5571 0.7978 0.8932
No log 3.5 224 0.7779 0.6122 0.7779 0.8820
No log 3.5312 226 0.7454 0.6431 0.7454 0.8634
No log 3.5625 228 0.7267 0.6150 0.7267 0.8525
No log 3.5938 230 0.7392 0.5988 0.7392 0.8597
No log 3.625 232 0.8220 0.6154 0.8220 0.9067
No log 3.6562 234 0.9559 0.5793 0.9559 0.9777
No log 3.6875 236 0.9734 0.5700 0.9734 0.9866
No log 3.7188 238 0.9589 0.5700 0.9589 0.9792
No log 3.75 240 0.8491 0.5967 0.8491 0.9214
No log 3.7812 242 0.7725 0.6082 0.7725 0.8789
No log 3.8125 244 0.7824 0.5998 0.7824 0.8845
No log 3.8438 246 0.8094 0.5998 0.8094 0.8997
No log 3.875 248 0.8677 0.5901 0.8677 0.9315
No log 3.9062 250 1.0001 0.5715 1.0001 1.0000
No log 3.9375 252 1.0829 0.5354 1.0829 1.0406
No log 3.9688 254 1.1000 0.5502 1.1000 1.0488
No log 4.0 256 0.9948 0.6002 0.9948 0.9974
No log 4.0312 258 0.8934 0.6278 0.8934 0.9452
No log 4.0625 260 0.7954 0.6401 0.7954 0.8919
No log 4.0938 262 0.7826 0.6338 0.7826 0.8846
No log 4.125 264 0.8288 0.6421 0.8288 0.9104
No log 4.1562 266 0.9484 0.6355 0.9484 0.9738
No log 4.1875 268 1.1101 0.5918 1.1101 1.0536
No log 4.2188 270 1.1304 0.5738 1.1304 1.0632
No log 4.25 272 1.0093 0.5837 1.0093 1.0046
No log 4.2812 274 0.8434 0.6703 0.8434 0.9184
No log 4.3125 276 0.7552 0.6668 0.7552 0.8690
No log 4.3438 278 0.7074 0.6966 0.7074 0.8411
No log 4.375 280 0.7111 0.7108 0.7111 0.8433
No log 4.4062 282 0.7328 0.6671 0.7328 0.8561
No log 4.4375 284 0.7618 0.6732 0.7618 0.8728
No log 4.4688 286 0.7734 0.6681 0.7734 0.8794
No log 4.5 288 0.7589 0.6758 0.7589 0.8712
No log 4.5312 290 0.7782 0.6479 0.7782 0.8822
No log 4.5625 292 0.8666 0.5977 0.8666 0.9309
No log 4.5938 294 0.9234 0.5987 0.9234 0.9609
No log 4.625 296 0.9133 0.6173 0.9133 0.9556
No log 4.6562 298 0.8278 0.6469 0.8278 0.9098
No log 4.6875 300 0.7663 0.6683 0.7663 0.8754
No log 4.7188 302 0.7541 0.6816 0.7541 0.8684
No log 4.75 304 0.7941 0.6503 0.7941 0.8911
No log 4.7812 306 0.9031 0.6121 0.9031 0.9503
No log 4.8125 308 1.0152 0.5773 1.0152 1.0076
No log 4.8438 310 1.0099 0.5680 1.0099 1.0050
No log 4.875 312 0.9489 0.5711 0.9489 0.9741
No log 4.9062 314 0.8479 0.5920 0.8479 0.9208
No log 4.9375 316 0.7440 0.6512 0.7440 0.8626
No log 4.9688 318 0.7153 0.6690 0.7153 0.8457
No log 5.0 320 0.7557 0.6581 0.7557 0.8693
No log 5.0312 322 0.7922 0.6355 0.7922 0.8900
No log 5.0625 324 0.8104 0.6496 0.8104 0.9002
No log 5.0938 326 0.7869 0.6515 0.7869 0.8871
No log 5.125 328 0.7551 0.6464 0.7551 0.8690
No log 5.1562 330 0.7513 0.6486 0.7513 0.8668
No log 5.1875 332 0.7769 0.6591 0.7769 0.8814
No log 5.2188 334 0.8496 0.6251 0.8496 0.9217
No log 5.25 336 0.8751 0.6375 0.8751 0.9355
No log 5.2812 338 0.8734 0.6389 0.8734 0.9346
No log 5.3125 340 0.9158 0.6114 0.9158 0.9570
No log 5.3438 342 0.9125 0.6221 0.9125 0.9552
No log 5.375 344 0.8790 0.6259 0.8790 0.9376
No log 5.4062 346 0.8098 0.6627 0.8098 0.8999
No log 5.4375 348 0.7856 0.6595 0.7856 0.8863
No log 5.4688 350 0.7786 0.6775 0.7786 0.8824
No log 5.5 352 0.7758 0.6674 0.7758 0.8808
No log 5.5312 354 0.7902 0.6584 0.7902 0.8889
No log 5.5625 356 0.8065 0.6295 0.8065 0.8980
No log 5.5938 358 0.7695 0.6574 0.7695 0.8772
No log 5.625 360 0.7299 0.6492 0.7299 0.8544
No log 5.6562 362 0.7141 0.6605 0.7141 0.8451
No log 5.6875 364 0.7215 0.6756 0.7215 0.8494
No log 5.7188 366 0.7707 0.6293 0.7707 0.8779
No log 5.75 368 0.8384 0.6195 0.8384 0.9156
No log 5.7812 370 0.8561 0.6234 0.8561 0.9253
No log 5.8125 372 0.8172 0.6384 0.8172 0.9040
No log 5.8438 374 0.7855 0.6484 0.7855 0.8863
No log 5.875 376 0.7783 0.6596 0.7783 0.8822
No log 5.9062 378 0.7612 0.6641 0.7612 0.8725
No log 5.9375 380 0.7678 0.6596 0.7678 0.8762
No log 5.9688 382 0.7594 0.6557 0.7594 0.8714
No log 6.0 384 0.7836 0.6516 0.7836 0.8852
No log 6.0312 386 0.7921 0.6643 0.7921 0.8900
No log 6.0625 388 0.7733 0.6703 0.7733 0.8794
No log 6.0938 390 0.7124 0.6567 0.7124 0.8440
No log 6.125 392 0.6907 0.6467 0.6907 0.8311
No log 6.1562 394 0.6812 0.6653 0.6812 0.8254
No log 6.1875 396 0.6703 0.6970 0.6703 0.8187
No log 6.2188 398 0.6673 0.7040 0.6673 0.8169
No log 6.25 400 0.6843 0.6962 0.6843 0.8272
No log 6.2812 402 0.7395 0.6729 0.7395 0.8600
No log 6.3125 404 0.7775 0.6669 0.7775 0.8818
No log 6.3438 406 0.7618 0.6669 0.7618 0.8728
No log 6.375 408 0.7414 0.6746 0.7414 0.8611
No log 6.4062 410 0.7222 0.6732 0.7222 0.8498
No log 6.4375 412 0.6839 0.7245 0.6839 0.8270
No log 6.4688 414 0.6823 0.7266 0.6823 0.8260
No log 6.5 416 0.7288 0.6703 0.7288 0.8537
No log 6.5312 418 0.8318 0.6389 0.8318 0.9120
No log 6.5625 420 0.9075 0.6190 0.9075 0.9526
No log 6.5938 422 0.9099 0.6190 0.9099 0.9539
No log 6.625 424 0.8791 0.6227 0.8791 0.9376
No log 6.6562 426 0.8060 0.6510 0.8060 0.8978
No log 6.6875 428 0.7170 0.6622 0.7170 0.8467
No log 6.7188 430 0.6572 0.7175 0.6572 0.8107
No log 6.75 432 0.6526 0.7181 0.6526 0.8078
No log 6.7812 434 0.6476 0.7013 0.6476 0.8047
No log 6.8125 436 0.6568 0.7116 0.6568 0.8104
No log 6.8438 438 0.6891 0.6801 0.6891 0.8301
No log 6.875 440 0.7410 0.6459 0.7410 0.8608
No log 6.9062 442 0.7507 0.6459 0.7507 0.8664
No log 6.9375 444 0.7684 0.6590 0.7684 0.8766
No log 6.9688 446 0.7884 0.6573 0.7884 0.8879
No log 7.0 448 0.7806 0.6493 0.7806 0.8835
No log 7.0312 450 0.7490 0.6323 0.7490 0.8654
No log 7.0625 452 0.6923 0.6520 0.6923 0.8321
No log 7.0938 454 0.6586 0.7024 0.6586 0.8115
No log 7.125 456 0.6336 0.7223 0.6336 0.7960
No log 7.1562 458 0.6211 0.7228 0.6211 0.7881
No log 7.1875 460 0.6276 0.7223 0.6276 0.7922
No log 7.2188 462 0.6649 0.6690 0.6649 0.8154
No log 7.25 464 0.7408 0.6591 0.7408 0.8607
No log 7.2812 466 0.8356 0.6101 0.8356 0.9141
No log 7.3125 468 0.8937 0.6074 0.8937 0.9454
No log 7.3438 470 0.8992 0.5982 0.8992 0.9483
No log 7.375 472 0.8620 0.6163 0.8620 0.9284
No log 7.4062 474 0.7952 0.6167 0.7952 0.8917
No log 7.4375 476 0.7398 0.6598 0.7398 0.8601
No log 7.4688 478 0.7152 0.6606 0.7152 0.8457
No log 7.5 480 0.7043 0.6696 0.7043 0.8392
No log 7.5312 482 0.7042 0.6557 0.7042 0.8392
No log 7.5625 484 0.7280 0.6606 0.7280 0.8533
No log 7.5938 486 0.7526 0.6581 0.7526 0.8675
No log 7.625 488 0.7719 0.6541 0.7719 0.8786
No log 7.6562 490 0.7837 0.6524 0.7837 0.8853
No log 7.6875 492 0.8133 0.6369 0.8133 0.9018
No log 7.7188 494 0.8175 0.6446 0.8175 0.9041
No log 7.75 496 0.8210 0.6446 0.8210 0.9061
No log 7.7812 498 0.8316 0.6354 0.8316 0.9119
0.4799 7.8125 500 0.8311 0.6210 0.8311 0.9117
0.4799 7.8438 502 0.8123 0.6353 0.8123 0.9013
0.4799 7.875 504 0.7847 0.6530 0.7847 0.8858
0.4799 7.9062 506 0.7558 0.6570 0.7558 0.8694
0.4799 7.9375 508 0.7228 0.6629 0.7228 0.8502
0.4799 7.9688 510 0.6999 0.6646 0.6999 0.8366
0.4799 8.0 512 0.6951 0.6646 0.6951 0.8337
0.4799 8.0312 514 0.7111 0.6646 0.7111 0.8433
0.4799 8.0625 516 0.7253 0.6575 0.7253 0.8516
0.4799 8.0938 518 0.7526 0.6562 0.7526 0.8675
0.4799 8.125 520 0.7794 0.6546 0.7794 0.8828
0.4799 8.1562 522 0.7876 0.6473 0.7876 0.8875
0.4799 8.1875 524 0.7962 0.6352 0.7962 0.8923
0.4799 8.2188 526 0.8164 0.6293 0.8164 0.9035
0.4799 8.25 528 0.8121 0.6293 0.8121 0.9012
0.4799 8.2812 530 0.8118 0.6293 0.8118 0.9010
0.4799 8.3125 532 0.7914 0.6486 0.7914 0.8896
0.4799 8.3438 534 0.7610 0.6518 0.7610 0.8724
0.4799 8.375 536 0.7563 0.6518 0.7563 0.8696
0.4799 8.4062 538 0.7535 0.6584 0.7535 0.8681
0.4799 8.4375 540 0.7648 0.6584 0.7648 0.8745
0.4799 8.4688 542 0.7605 0.6584 0.7605 0.8721
0.4799 8.5 544 0.7829 0.6507 0.7829 0.8848
0.4799 8.5312 546 0.8259 0.6380 0.8259 0.9088
0.4799 8.5625 548 0.8727 0.6307 0.8727 0.9342
0.4799 8.5938 550 0.9046 0.6357 0.9046 0.9511
0.4799 8.625 552 0.9118 0.6357 0.9118 0.9549
0.4799 8.6562 554 0.8991 0.6357 0.8991 0.9482
0.4799 8.6875 556 0.8782 0.6293 0.8782 0.9371
0.4799 8.7188 558 0.8607 0.6243 0.8607 0.9278
0.4799 8.75 560 0.8566 0.6286 0.8566 0.9255
0.4799 8.7812 562 0.8673 0.6243 0.8673 0.9313
0.4799 8.8125 564 0.8656 0.6286 0.8656 0.9304
0.4799 8.8438 566 0.8571 0.6408 0.8571 0.9258
0.4799 8.875 568 0.8381 0.6359 0.8381 0.9155
0.4799 8.9062 570 0.8192 0.6374 0.8192 0.9051
0.4799 8.9375 572 0.8010 0.6301 0.8010 0.8950
0.4799 8.9688 574 0.7944 0.6265 0.7944 0.8913
0.4799 9.0 576 0.7813 0.6279 0.7813 0.8839
0.4799 9.0312 578 0.7747 0.6339 0.7747 0.8802
0.4799 9.0625 580 0.7715 0.6241 0.7715 0.8784
0.4799 9.0938 582 0.7682 0.6241 0.7682 0.8765
0.4799 9.125 584 0.7734 0.6227 0.7734 0.8794
0.4799 9.1562 586 0.7820 0.6181 0.7820 0.8843
0.4799 9.1875 588 0.7965 0.6249 0.7965 0.8925
0.4799 9.2188 590 0.8010 0.6345 0.8010 0.8950
0.4799 9.25 592 0.8038 0.6345 0.8038 0.8965
0.4799 9.2812 594 0.8068 0.6345 0.8068 0.8982
0.4799 9.3125 596 0.8065 0.6345 0.8065 0.8980
0.4799 9.3438 598 0.7971 0.6345 0.7971 0.8928
0.4799 9.375 600 0.7954 0.6345 0.7954 0.8919
0.4799 9.4062 602 0.7933 0.6345 0.7933 0.8907
0.4799 9.4375 604 0.7967 0.6345 0.7967 0.8926
0.4799 9.4688 606 0.7979 0.6345 0.7979 0.8933
0.4799 9.5 608 0.7954 0.6279 0.7954 0.8919
0.4799 9.5312 610 0.7884 0.6279 0.7884 0.8879
0.4799 9.5625 612 0.7830 0.6353 0.7830 0.8849
0.4799 9.5938 614 0.7785 0.6353 0.7785 0.8823
0.4799 9.625 616 0.7762 0.6353 0.7762 0.8810
0.4799 9.6562 618 0.7748 0.6353 0.7748 0.8802
0.4799 9.6875 620 0.7756 0.6353 0.7756 0.8807
0.4799 9.7188 622 0.7773 0.6353 0.7773 0.8816
0.4799 9.75 624 0.7800 0.6353 0.7800 0.8832
0.4799 9.7812 626 0.7835 0.6339 0.7835 0.8852
0.4799 9.8125 628 0.7862 0.6339 0.7862 0.8867
0.4799 9.8438 630 0.7888 0.6339 0.7888 0.8881
0.4799 9.875 632 0.7908 0.6339 0.7908 0.8893
0.4799 9.9062 634 0.7913 0.6339 0.7913 0.8895
0.4799 9.9375 636 0.7912 0.6339 0.7912 0.8895
0.4799 9.9688 638 0.7909 0.6339 0.7909 0.8893
0.4799 10.0 640 0.7907 0.6339 0.7907 0.8892

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
-
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_run3_AugV5_k10_task1_organization

Finetuned
(4023)
this model