ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run2_AugV5_k20_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: 0.6235
  • Qwk: 0.4630
  • Mse: 0.6235
  • Rmse: 0.7896

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 0.0194 2 4.5725 -0.0101 4.5725 2.1383
No log 0.0388 4 3.0066 0.0136 3.0066 1.7340
No log 0.0583 6 1.5657 0.0388 1.5657 1.2513
No log 0.0777 8 1.2767 0.0006 1.2767 1.1299
No log 0.0971 10 1.2069 -0.0229 1.2069 1.0986
No log 0.1165 12 1.1111 -0.1210 1.1111 1.0541
No log 0.1359 14 0.9557 -0.0099 0.9557 0.9776
No log 0.1553 16 0.8730 0.1430 0.8730 0.9343
No log 0.1748 18 0.8481 0.2110 0.8481 0.9209
No log 0.1942 20 0.8233 0.2231 0.8233 0.9074
No log 0.2136 22 0.8361 0.1983 0.8361 0.9144
No log 0.2330 24 0.8986 0.1429 0.8986 0.9479
No log 0.2524 26 0.9921 0.1528 0.9921 0.9961
No log 0.2718 28 1.0946 0.0889 1.0946 1.0462
No log 0.2913 30 1.2825 0.0352 1.2825 1.1325
No log 0.3107 32 1.3892 0.0411 1.3892 1.1786
No log 0.3301 34 1.1594 0.1516 1.1594 1.0768
No log 0.3495 36 1.0615 0.1815 1.0615 1.0303
No log 0.3689 38 1.0249 0.2111 1.0249 1.0124
No log 0.3883 40 1.0166 0.1653 1.0166 1.0083
No log 0.4078 42 0.9335 0.1671 0.9335 0.9662
No log 0.4272 44 0.8300 0.2097 0.8300 0.9110
No log 0.4466 46 0.7057 0.3476 0.7057 0.8401
No log 0.4660 48 0.6860 0.3874 0.6860 0.8283
No log 0.4854 50 0.6934 0.3096 0.6934 0.8327
No log 0.5049 52 0.7051 0.2957 0.7051 0.8397
No log 0.5243 54 0.7641 0.2339 0.7641 0.8741
No log 0.5437 56 0.8437 0.1603 0.8437 0.9186
No log 0.5631 58 0.8470 0.2421 0.8470 0.9203
No log 0.5825 60 0.8444 0.2446 0.8444 0.9189
No log 0.6019 62 0.8182 0.2805 0.8182 0.9046
No log 0.6214 64 0.7412 0.3301 0.7412 0.8609
No log 0.6408 66 0.7115 0.3436 0.7115 0.8435
No log 0.6602 68 0.6844 0.4048 0.6844 0.8273
No log 0.6796 70 0.6871 0.4155 0.6871 0.8289
No log 0.6990 72 0.7701 0.3403 0.7701 0.8776
No log 0.7184 74 0.9350 0.2006 0.9350 0.9669
No log 0.7379 76 1.3180 0.0661 1.3180 1.1480
No log 0.7573 78 1.4866 0.0318 1.4866 1.2193
No log 0.7767 80 1.0595 0.1426 1.0595 1.0293
No log 0.7961 82 0.7222 0.3529 0.7222 0.8498
No log 0.8155 84 0.6588 0.4368 0.6588 0.8117
No log 0.8350 86 0.7836 0.3926 0.7836 0.8852
No log 0.8544 88 0.8189 0.3883 0.8189 0.9049
No log 0.8738 90 0.7500 0.4510 0.7500 0.8660
No log 0.8932 92 0.6780 0.4743 0.6780 0.8234
No log 0.9126 94 0.6581 0.4480 0.6581 0.8112
No log 0.9320 96 0.6561 0.4618 0.6561 0.8100
No log 0.9515 98 0.6794 0.4563 0.6794 0.8243
No log 0.9709 100 0.6944 0.3959 0.6944 0.8333
No log 0.9903 102 0.6008 0.4742 0.6008 0.7751
No log 1.0097 104 0.6806 0.4350 0.6806 0.8250
No log 1.0291 106 0.7232 0.4076 0.7232 0.8504
No log 1.0485 108 0.6671 0.4315 0.6671 0.8168
No log 1.0680 110 0.6227 0.4605 0.6227 0.7891
No log 1.0874 112 0.5851 0.4759 0.5851 0.7649
No log 1.1068 114 0.6052 0.4912 0.6052 0.7779
No log 1.1262 116 0.5904 0.4798 0.5904 0.7683
No log 1.1456 118 0.5806 0.5103 0.5806 0.7620
No log 1.1650 120 0.5953 0.4768 0.5953 0.7716
No log 1.1845 122 0.6096 0.3858 0.6096 0.7808
No log 1.2039 124 0.6104 0.4715 0.6104 0.7813
No log 1.2233 126 0.6016 0.4598 0.6016 0.7756
No log 1.2427 128 0.6012 0.4523 0.6012 0.7754
No log 1.2621 130 0.5987 0.5303 0.5987 0.7738
No log 1.2816 132 0.6576 0.5444 0.6576 0.8109
No log 1.3010 134 0.7865 0.4025 0.7865 0.8869
No log 1.3204 136 0.7096 0.5130 0.7096 0.8424
No log 1.3398 138 0.6632 0.5438 0.6632 0.8144
No log 1.3592 140 0.6400 0.5837 0.6400 0.8000
No log 1.3786 142 0.6262 0.5570 0.6262 0.7913
No log 1.3981 144 0.6443 0.4786 0.6443 0.8027
No log 1.4175 146 0.6744 0.4781 0.6744 0.8212
No log 1.4369 148 0.7384 0.4916 0.7384 0.8593
No log 1.4563 150 0.7408 0.4337 0.7408 0.8607
No log 1.4757 152 0.7076 0.4585 0.7076 0.8412
No log 1.4951 154 0.6756 0.4260 0.6756 0.8220
No log 1.5146 156 0.6835 0.3826 0.6835 0.8267
No log 1.5340 158 0.6851 0.3324 0.6851 0.8277
No log 1.5534 160 0.7218 0.4038 0.7218 0.8496
No log 1.5728 162 0.8826 0.3757 0.8826 0.9394
No log 1.5922 164 0.8438 0.3966 0.8438 0.9186
No log 1.6117 166 0.7252 0.4911 0.7252 0.8516
No log 1.6311 168 0.6667 0.4628 0.6667 0.8165
No log 1.6505 170 0.6846 0.4514 0.6846 0.8274
No log 1.6699 172 0.6683 0.4512 0.6683 0.8175
No log 1.6893 174 0.6892 0.5138 0.6892 0.8302
No log 1.7087 176 0.8026 0.4427 0.8026 0.8959
No log 1.7282 178 0.7905 0.4298 0.7905 0.8891
No log 1.7476 180 0.7270 0.4743 0.7270 0.8526
No log 1.7670 182 0.7024 0.4969 0.7024 0.8381
No log 1.7864 184 0.6706 0.5167 0.6706 0.8189
No log 1.8058 186 0.6757 0.4116 0.6757 0.8220
No log 1.8252 188 0.6682 0.3941 0.6682 0.8174
No log 1.8447 190 0.7087 0.4628 0.7087 0.8419
No log 1.8641 192 0.6990 0.4455 0.6990 0.8360
No log 1.8835 194 0.6465 0.4189 0.6465 0.8041
No log 1.9029 196 0.6353 0.4181 0.6353 0.7970
No log 1.9223 198 0.6473 0.4440 0.6473 0.8046
No log 1.9417 200 0.6759 0.4664 0.6759 0.8221
No log 1.9612 202 0.6653 0.4577 0.6653 0.8157
No log 1.9806 204 0.6238 0.4463 0.6238 0.7898
No log 2.0 206 0.6052 0.4360 0.6052 0.7780
No log 2.0194 208 0.6151 0.4666 0.6151 0.7843
No log 2.0388 210 0.6850 0.4946 0.6850 0.8276
No log 2.0583 212 0.7498 0.4187 0.7498 0.8659
No log 2.0777 214 0.6535 0.4739 0.6535 0.8084
No log 2.0971 216 0.6043 0.4717 0.6043 0.7774
No log 2.1165 218 0.6093 0.3819 0.6093 0.7806
No log 2.1359 220 0.6111 0.4798 0.6111 0.7817
No log 2.1553 222 0.6842 0.5016 0.6842 0.8272
No log 2.1748 224 0.7012 0.5042 0.7012 0.8374
No log 2.1942 226 0.6827 0.4709 0.6827 0.8263
No log 2.2136 228 0.6303 0.5456 0.6303 0.7939
No log 2.2330 230 0.6310 0.5322 0.6310 0.7944
No log 2.2524 232 0.6304 0.5347 0.6304 0.7940
No log 2.2718 234 0.6360 0.4983 0.6360 0.7975
No log 2.2913 236 0.6290 0.4888 0.6290 0.7931
No log 2.3107 238 0.6211 0.4770 0.6211 0.7881
No log 2.3301 240 0.6215 0.4151 0.6215 0.7884
No log 2.3495 242 0.6275 0.4173 0.6275 0.7921
No log 2.3689 244 0.6377 0.4181 0.6377 0.7986
No log 2.3883 246 0.6527 0.4395 0.6527 0.8079
No log 2.4078 248 0.6359 0.4539 0.6359 0.7975
No log 2.4272 250 0.6242 0.4887 0.6242 0.7900
No log 2.4466 252 0.6112 0.4977 0.6112 0.7818
No log 2.4660 254 0.6182 0.5224 0.6182 0.7863
No log 2.4854 256 0.6617 0.5230 0.6617 0.8134
No log 2.5049 258 0.7562 0.5302 0.7562 0.8696
No log 2.5243 260 0.6974 0.5195 0.6974 0.8351
No log 2.5437 262 0.6282 0.4856 0.6282 0.7926
No log 2.5631 264 0.6905 0.4206 0.6905 0.8310
No log 2.5825 266 0.6468 0.4581 0.6468 0.8042
No log 2.6019 268 0.6020 0.4938 0.6020 0.7759
No log 2.6214 270 0.6064 0.5142 0.6064 0.7787
No log 2.6408 272 0.6080 0.5328 0.6080 0.7797
No log 2.6602 274 0.5723 0.5222 0.5723 0.7565
No log 2.6796 276 0.5651 0.5261 0.5651 0.7517
No log 2.6990 278 0.5809 0.5486 0.5809 0.7621
No log 2.7184 280 0.6179 0.5234 0.6179 0.7861
No log 2.7379 282 0.6129 0.5588 0.6129 0.7829
No log 2.7573 284 0.5837 0.5509 0.5837 0.7640
No log 2.7767 286 0.5878 0.5750 0.5878 0.7667
No log 2.7961 288 0.5897 0.5858 0.5897 0.7679
No log 2.8155 290 0.5805 0.5837 0.5805 0.7619
No log 2.8350 292 0.5807 0.5128 0.5807 0.7620
No log 2.8544 294 0.6052 0.4953 0.6052 0.7779
No log 2.8738 296 0.6585 0.4855 0.6585 0.8115
No log 2.8932 298 0.6439 0.5262 0.6439 0.8024
No log 2.9126 300 0.6080 0.4857 0.6080 0.7797
No log 2.9320 302 0.6082 0.5343 0.6082 0.7798
No log 2.9515 304 0.6182 0.6069 0.6182 0.7863
No log 2.9709 306 0.6489 0.5207 0.6489 0.8055
No log 2.9903 308 0.6454 0.5344 0.6454 0.8034
No log 3.0097 310 0.6683 0.5289 0.6683 0.8175
No log 3.0291 312 0.7070 0.5383 0.7070 0.8409
No log 3.0485 314 0.6539 0.5370 0.6539 0.8086
No log 3.0680 316 0.6320 0.4770 0.6320 0.7950
No log 3.0874 318 0.6184 0.4540 0.6184 0.7864
No log 3.1068 320 0.6154 0.4421 0.6154 0.7844
No log 3.1262 322 0.6004 0.4582 0.6004 0.7748
No log 3.1456 324 0.6246 0.4507 0.6246 0.7903
No log 3.1650 326 0.7071 0.4399 0.7071 0.8409
No log 3.1845 328 0.6820 0.4524 0.6820 0.8258
No log 3.2039 330 0.6095 0.4804 0.6095 0.7807
No log 3.2233 332 0.5813 0.4546 0.5813 0.7624
No log 3.2427 334 0.6576 0.4366 0.6576 0.8109
No log 3.2621 336 0.6976 0.4023 0.6976 0.8352
No log 3.2816 338 0.6308 0.4279 0.6308 0.7942
No log 3.3010 340 0.5719 0.5117 0.5719 0.7562
No log 3.3204 342 0.5626 0.5347 0.5626 0.7501
No log 3.3398 344 0.5833 0.5654 0.5833 0.7638
No log 3.3592 346 0.6174 0.5395 0.6174 0.7857
No log 3.3786 348 0.6616 0.4818 0.6616 0.8134
No log 3.3981 350 0.6373 0.5056 0.6373 0.7983
No log 3.4175 352 0.6018 0.5434 0.6018 0.7757
No log 3.4369 354 0.5940 0.5345 0.5940 0.7707
No log 3.4563 356 0.5923 0.5566 0.5923 0.7696
No log 3.4757 358 0.6339 0.4610 0.6339 0.7962
No log 3.4951 360 0.7272 0.4283 0.7272 0.8528
No log 3.5146 362 0.6838 0.4569 0.6838 0.8269
No log 3.5340 364 0.6761 0.4916 0.6761 0.8222
No log 3.5534 366 0.6390 0.5215 0.6390 0.7994
No log 3.5728 368 0.6279 0.5126 0.6279 0.7924
No log 3.5922 370 0.6369 0.5102 0.6369 0.7981
No log 3.6117 372 0.6121 0.4893 0.6121 0.7824
No log 3.6311 374 0.6001 0.4998 0.6001 0.7747
No log 3.6505 376 0.5947 0.4998 0.5947 0.7712
No log 3.6699 378 0.5783 0.5270 0.5783 0.7604
No log 3.6893 380 0.5794 0.4819 0.5794 0.7612
No log 3.7087 382 0.5744 0.5264 0.5744 0.7579
No log 3.7282 384 0.5728 0.5640 0.5728 0.7569
No log 3.7476 386 0.6228 0.5691 0.6228 0.7892
No log 3.7670 388 0.6268 0.5341 0.6268 0.7917
No log 3.7864 390 0.6024 0.4942 0.6024 0.7761
No log 3.8058 392 0.6670 0.4739 0.6670 0.8167
No log 3.8252 394 0.6725 0.4835 0.6725 0.8200
No log 3.8447 396 0.6095 0.4779 0.6095 0.7807
No log 3.8641 398 0.5717 0.5161 0.5717 0.7561
No log 3.8835 400 0.5655 0.5034 0.5655 0.7520
No log 3.9029 402 0.5856 0.4847 0.5856 0.7653
No log 3.9223 404 0.6292 0.4714 0.6292 0.7932
No log 3.9417 406 0.6177 0.4743 0.6177 0.7859
No log 3.9612 408 0.5915 0.4840 0.5915 0.7691
No log 3.9806 410 0.5792 0.5601 0.5792 0.7610
No log 4.0 412 0.6271 0.5358 0.6271 0.7919
No log 4.0194 414 0.6406 0.5236 0.6406 0.8004
No log 4.0388 416 0.5979 0.5561 0.5979 0.7732
No log 4.0583 418 0.6106 0.4589 0.6106 0.7814
No log 4.0777 420 0.6238 0.4591 0.6238 0.7898
No log 4.0971 422 0.5953 0.5046 0.5953 0.7715
No log 4.1165 424 0.5883 0.5395 0.5883 0.7670
No log 4.1359 426 0.6233 0.5263 0.6233 0.7895
No log 4.1553 428 0.6347 0.5438 0.6347 0.7967
No log 4.1748 430 0.6334 0.5561 0.6334 0.7959
No log 4.1942 432 0.6437 0.5017 0.6437 0.8023
No log 4.2136 434 0.6806 0.5291 0.6806 0.8250
No log 4.2330 436 0.7419 0.4655 0.7419 0.8613
No log 4.2524 438 0.6837 0.4700 0.6837 0.8268
No log 4.2718 440 0.6244 0.4345 0.6244 0.7902
No log 4.2913 442 0.6452 0.4257 0.6452 0.8033
No log 4.3107 444 0.6332 0.4600 0.6332 0.7958
No log 4.3301 446 0.6138 0.4221 0.6138 0.7834
No log 4.3495 448 0.6995 0.4519 0.6995 0.8364
No log 4.3689 450 0.8418 0.3891 0.8418 0.9175
No log 4.3883 452 0.8389 0.4058 0.8389 0.9159
No log 4.4078 454 0.7105 0.4495 0.7105 0.8429
No log 4.4272 456 0.6294 0.4409 0.6294 0.7933
No log 4.4466 458 0.6195 0.5278 0.6195 0.7871
No log 4.4660 460 0.6463 0.4500 0.6463 0.8039
No log 4.4854 462 0.6093 0.4999 0.6093 0.7806
No log 4.5049 464 0.5877 0.5056 0.5877 0.7666
No log 4.5243 466 0.5956 0.4600 0.5956 0.7718
No log 4.5437 468 0.6025 0.4724 0.6025 0.7762
No log 4.5631 470 0.5816 0.5151 0.5816 0.7626
No log 4.5825 472 0.5891 0.5164 0.5891 0.7675
No log 4.6019 474 0.5916 0.5043 0.5916 0.7692
No log 4.6214 476 0.5774 0.4916 0.5774 0.7599
No log 4.6408 478 0.5820 0.4605 0.5820 0.7629
No log 4.6602 480 0.5951 0.4447 0.5951 0.7714
No log 4.6796 482 0.5983 0.4779 0.5983 0.7735
No log 4.6990 484 0.5977 0.4514 0.5977 0.7731
No log 4.7184 486 0.6009 0.4607 0.6009 0.7752
No log 4.7379 488 0.6086 0.4139 0.6086 0.7801
No log 4.7573 490 0.6073 0.4454 0.6073 0.7793
No log 4.7767 492 0.6189 0.4875 0.6189 0.7867
No log 4.7961 494 0.6172 0.5316 0.6172 0.7856
No log 4.8155 496 0.6071 0.53 0.6071 0.7791
No log 4.8350 498 0.6022 0.5452 0.6022 0.7760
0.3831 4.8544 500 0.6281 0.4706 0.6281 0.7926
0.3831 4.8738 502 0.6359 0.4792 0.6359 0.7974
0.3831 4.8932 504 0.6602 0.4606 0.6602 0.8125
0.3831 4.9126 506 0.6065 0.4404 0.6065 0.7788
0.3831 4.9320 508 0.5716 0.5304 0.5716 0.7560
0.3831 4.9515 510 0.5736 0.5168 0.5736 0.7573
0.3831 4.9709 512 0.5954 0.4232 0.5954 0.7716
0.3831 4.9903 514 0.6291 0.4374 0.6291 0.7931
0.3831 5.0097 516 0.6245 0.4639 0.6245 0.7903
0.3831 5.0291 518 0.5927 0.5459 0.5927 0.7698
0.3831 5.0485 520 0.6217 0.4729 0.6217 0.7885
0.3831 5.0680 522 0.6476 0.4811 0.6476 0.8047
0.3831 5.0874 524 0.6117 0.4542 0.6117 0.7821
0.3831 5.1068 526 0.5871 0.5285 0.5871 0.7662
0.3831 5.1262 528 0.6108 0.4853 0.6108 0.7815
0.3831 5.1456 530 0.6090 0.4535 0.6090 0.7804
0.3831 5.1650 532 0.6119 0.4535 0.6119 0.7822
0.3831 5.1845 534 0.6023 0.4661 0.6023 0.7761
0.3831 5.2039 536 0.5865 0.4717 0.5865 0.7658
0.3831 5.2233 538 0.5893 0.4677 0.5893 0.7677
0.3831 5.2427 540 0.6246 0.4385 0.6246 0.7903
0.3831 5.2621 542 0.6664 0.4564 0.6664 0.8163
0.3831 5.2816 544 0.6374 0.4448 0.6374 0.7984
0.3831 5.3010 546 0.6235 0.4630 0.6235 0.7896

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
4
Safetensors
Model size
135M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for MayBashendy/ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run2_AugV5_k20_task2_organization

Finetuned
(4206)
this model