ArabicNewSplits8_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k19_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: 0.6117
  • Qwk: 0.4195
  • Mse: 0.6117
  • Rmse: 0.7821

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 0.02 2 4.2800 -0.0205 4.2800 2.0688
No log 0.04 4 2.3165 0.0174 2.3165 1.5220
No log 0.06 6 1.6019 -0.0117 1.6019 1.2657
No log 0.08 8 1.1547 -0.0281 1.1547 1.0746
No log 0.1 10 1.0231 -0.1313 1.0231 1.0115
No log 0.12 12 1.0132 -0.0622 1.0132 1.0066
No log 0.14 14 1.0370 -0.0335 1.0370 1.0183
No log 0.16 16 0.9172 0.1596 0.9172 0.9577
No log 0.18 18 0.8578 0.1305 0.8578 0.9262
No log 0.2 20 0.8466 0.0796 0.8466 0.9201
No log 0.22 22 0.8512 0.1132 0.8512 0.9226
No log 0.24 24 0.8913 0.1934 0.8913 0.9441
No log 0.26 26 1.2254 -0.0273 1.2254 1.1070
No log 0.28 28 2.0847 0.0299 2.0847 1.4438
No log 0.3 30 1.8451 0.0850 1.8451 1.3583
No log 0.32 32 1.4113 0.0639 1.4113 1.1880
No log 0.34 34 1.1351 0.0309 1.1351 1.0654
No log 0.36 36 0.9345 0.0852 0.9345 0.9667
No log 0.38 38 0.8942 0.1618 0.8942 0.9456
No log 0.4 40 0.8197 0.2124 0.8197 0.9054
No log 0.42 42 0.8296 0.2089 0.8296 0.9108
No log 0.44 44 0.8628 0.1923 0.8628 0.9289
No log 0.46 46 0.8274 0.1991 0.8274 0.9096
No log 0.48 48 0.7620 0.2269 0.7620 0.8730
No log 0.5 50 0.7483 0.3038 0.7483 0.8650
No log 0.52 52 0.8225 0.1920 0.8225 0.9069
No log 0.54 54 0.9542 0.0903 0.9542 0.9768
No log 0.56 56 0.8998 0.1072 0.8998 0.9486
No log 0.58 58 0.7948 0.2517 0.7948 0.8915
No log 0.6 60 0.7526 0.3191 0.7526 0.8675
No log 0.62 62 0.8607 0.0915 0.8607 0.9277
No log 0.64 64 0.9098 0.0898 0.9098 0.9539
No log 0.66 66 0.8473 0.1275 0.8473 0.9205
No log 0.68 68 0.7585 0.2800 0.7585 0.8709
No log 0.7 70 0.6809 0.2914 0.6809 0.8251
No log 0.72 72 0.7075 0.3086 0.7075 0.8411
No log 0.74 74 0.6906 0.3413 0.6906 0.8310
No log 0.76 76 0.6853 0.3353 0.6853 0.8278
No log 0.78 78 0.6584 0.3837 0.6584 0.8114
No log 0.8 80 0.6544 0.3821 0.6544 0.8090
No log 0.82 82 0.7208 0.3796 0.7208 0.8490
No log 0.84 84 0.7481 0.2381 0.7481 0.8649
No log 0.86 86 0.6797 0.3299 0.6797 0.8245
No log 0.88 88 0.6023 0.3644 0.6023 0.7761
No log 0.9 90 0.6392 0.3741 0.6392 0.7995
No log 0.92 92 0.6756 0.4219 0.6756 0.8220
No log 0.94 94 0.6465 0.3992 0.6465 0.8041
No log 0.96 96 0.6097 0.3827 0.6097 0.7809
No log 0.98 98 0.6599 0.3277 0.6599 0.8124
No log 1.0 100 0.6368 0.3691 0.6368 0.7980
No log 1.02 102 0.6325 0.3933 0.6325 0.7953
No log 1.04 104 0.6358 0.3691 0.6358 0.7973
No log 1.06 106 0.6275 0.4105 0.6275 0.7922
No log 1.08 108 0.6485 0.4154 0.6485 0.8053
No log 1.1 110 0.7125 0.4139 0.7125 0.8441
No log 1.12 112 0.6862 0.4243 0.6862 0.8284
No log 1.1400 114 0.6503 0.4016 0.6503 0.8064
No log 1.16 116 0.6601 0.4234 0.6601 0.8125
No log 1.18 118 0.6533 0.4013 0.6533 0.8083
No log 1.2 120 0.6552 0.3261 0.6552 0.8094
No log 1.22 122 0.6802 0.3622 0.6802 0.8247
No log 1.24 124 0.9328 0.3485 0.9328 0.9658
No log 1.26 126 1.1546 0.2526 1.1546 1.0745
No log 1.28 128 0.8676 0.3683 0.8676 0.9315
No log 1.3 130 0.7993 0.4396 0.7993 0.8940
No log 1.32 132 0.9713 0.4003 0.9713 0.9856
No log 1.34 134 0.9582 0.4007 0.9582 0.9789
No log 1.3600 136 0.7276 0.3961 0.7276 0.8530
No log 1.38 138 0.8958 0.3998 0.8958 0.9464
No log 1.4 140 0.9529 0.3560 0.9529 0.9761
No log 1.42 142 0.7671 0.3892 0.7671 0.8758
No log 1.44 144 0.6679 0.4451 0.6679 0.8173
No log 1.46 146 0.6708 0.4805 0.6708 0.8191
No log 1.48 148 0.9141 0.3552 0.9141 0.9561
No log 1.5 150 1.0101 0.3420 1.0101 1.0050
No log 1.52 152 0.7386 0.4824 0.7386 0.8594
No log 1.54 154 0.6492 0.5404 0.6492 0.8057
No log 1.56 156 0.6833 0.5793 0.6833 0.8266
No log 1.58 158 0.8132 0.5048 0.8132 0.9018
No log 1.6 160 0.8946 0.4367 0.8946 0.9458
No log 1.62 162 0.9620 0.4074 0.9620 0.9808
No log 1.6400 164 0.8485 0.4594 0.8485 0.9211
No log 1.6600 166 0.7189 0.5014 0.7189 0.8479
No log 1.6800 168 0.6821 0.5241 0.6821 0.8259
No log 1.7 170 0.6774 0.5247 0.6774 0.8231
No log 1.72 172 0.6738 0.4850 0.6738 0.8209
No log 1.74 174 0.6690 0.5327 0.6690 0.8179
No log 1.76 176 0.6672 0.5509 0.6672 0.8168
No log 1.78 178 0.6627 0.5697 0.6627 0.8141
No log 1.8 180 0.6518 0.5544 0.6518 0.8074
No log 1.8200 182 0.6385 0.5762 0.6385 0.7991
No log 1.8400 184 0.6433 0.5637 0.6433 0.8021
No log 1.8600 186 0.7355 0.4949 0.7355 0.8576
No log 1.88 188 0.7027 0.4859 0.7027 0.8382
No log 1.9 190 0.6572 0.4961 0.6572 0.8107
No log 1.92 192 0.6432 0.4937 0.6432 0.8020
No log 1.94 194 0.6570 0.5084 0.6570 0.8105
No log 1.96 196 0.6539 0.4933 0.6539 0.8086
No log 1.98 198 0.6297 0.4955 0.6297 0.7935
No log 2.0 200 0.6665 0.4743 0.6665 0.8164
No log 2.02 202 0.6187 0.4885 0.6187 0.7866
No log 2.04 204 0.6236 0.4542 0.6236 0.7897
No log 2.06 206 0.6490 0.4672 0.6490 0.8056
No log 2.08 208 0.7634 0.4420 0.7634 0.8738
No log 2.1 210 0.6759 0.4606 0.6759 0.8221
No log 2.12 212 0.6361 0.5059 0.6361 0.7975
No log 2.14 214 0.7358 0.3606 0.7358 0.8578
No log 2.16 216 0.7013 0.3918 0.7013 0.8374
No log 2.18 218 0.6145 0.4803 0.6145 0.7839
No log 2.2 220 0.6605 0.4700 0.6605 0.8127
No log 2.22 222 0.8211 0.4567 0.8211 0.9062
No log 2.24 224 0.7570 0.4782 0.7570 0.8701
No log 2.26 226 0.6113 0.4561 0.6113 0.7818
No log 2.2800 228 0.6198 0.4654 0.6198 0.7873
No log 2.3 230 0.6351 0.4371 0.6351 0.7969
No log 2.32 232 0.6305 0.5073 0.6305 0.7940
No log 2.34 234 0.6402 0.5290 0.6402 0.8001
No log 2.36 236 0.6521 0.4726 0.6521 0.8075
No log 2.38 238 0.7104 0.4994 0.7104 0.8429
No log 2.4 240 0.7786 0.4337 0.7786 0.8824
No log 2.42 242 0.8299 0.4085 0.8299 0.9110
No log 2.44 244 0.7675 0.4189 0.7675 0.8760
No log 2.46 246 0.7619 0.4339 0.7619 0.8729
No log 2.48 248 0.7489 0.4350 0.7489 0.8654
No log 2.5 250 0.7829 0.4185 0.7829 0.8848
No log 2.52 252 0.7485 0.4644 0.7485 0.8651
No log 2.54 254 0.6474 0.4514 0.6474 0.8046
No log 2.56 256 0.6862 0.4100 0.6862 0.8284
No log 2.58 258 0.7686 0.3851 0.7686 0.8767
No log 2.6 260 0.6721 0.4799 0.6721 0.8198
No log 2.62 262 0.6585 0.4585 0.6585 0.8115
No log 2.64 264 0.7101 0.4529 0.7101 0.8427
No log 2.66 266 0.6896 0.4675 0.6896 0.8304
No log 2.68 268 0.6314 0.4807 0.6314 0.7946
No log 2.7 270 0.6123 0.3831 0.6123 0.7825
No log 2.7200 272 0.6004 0.4690 0.6004 0.7749
No log 2.74 274 0.6307 0.4488 0.6307 0.7942
No log 2.76 276 0.6609 0.4874 0.6609 0.8130
No log 2.7800 278 0.6067 0.5205 0.6067 0.7789
No log 2.8 280 0.6316 0.5198 0.6316 0.7947
No log 2.82 282 0.6694 0.4507 0.6694 0.8181
No log 2.84 284 0.6879 0.4472 0.6879 0.8294
No log 2.86 286 0.6084 0.4876 0.6084 0.7800
No log 2.88 288 0.5946 0.4864 0.5946 0.7711
No log 2.9 290 0.6044 0.5071 0.6044 0.7775
No log 2.92 292 0.6315 0.5280 0.6315 0.7947
No log 2.94 294 0.6977 0.4914 0.6977 0.8353
No log 2.96 296 0.6768 0.5114 0.6768 0.8227
No log 2.98 298 0.6217 0.4859 0.6217 0.7885
No log 3.0 300 0.5990 0.4576 0.5990 0.7739
No log 3.02 302 0.6332 0.4592 0.6332 0.7957
No log 3.04 304 0.6188 0.4359 0.6188 0.7866
No log 3.06 306 0.5971 0.4630 0.5971 0.7727
No log 3.08 308 0.6397 0.4592 0.6397 0.7998
No log 3.1 310 0.6368 0.4614 0.6368 0.7980
No log 3.12 312 0.5803 0.4891 0.5803 0.7618
No log 3.14 314 0.5741 0.4788 0.5741 0.7577
No log 3.16 316 0.5622 0.4710 0.5622 0.7498
No log 3.18 318 0.5581 0.5205 0.5581 0.7470
No log 3.2 320 0.6036 0.4684 0.6036 0.7769
No log 3.22 322 0.6207 0.4707 0.6207 0.7878
No log 3.24 324 0.5753 0.4835 0.5753 0.7585
No log 3.26 326 0.5584 0.5177 0.5584 0.7472
No log 3.2800 328 0.5920 0.4422 0.5920 0.7694
No log 3.3 330 0.6298 0.5059 0.6298 0.7936
No log 3.32 332 0.6616 0.4791 0.6616 0.8134
No log 3.34 334 0.6161 0.5388 0.6161 0.7849
No log 3.36 336 0.6145 0.5221 0.6145 0.7839
No log 3.38 338 0.5916 0.5513 0.5916 0.7691
No log 3.4 340 0.6057 0.5166 0.6057 0.7782
No log 3.42 342 0.6562 0.4896 0.6562 0.8101
No log 3.44 344 0.8362 0.5380 0.8362 0.9145
No log 3.46 346 0.9269 0.4168 0.9269 0.9627
No log 3.48 348 0.8449 0.4658 0.8449 0.9192
No log 3.5 350 0.6750 0.5254 0.6750 0.8216
No log 3.52 352 0.6049 0.4756 0.6049 0.7778
No log 3.54 354 0.5976 0.4834 0.5976 0.7731
No log 3.56 356 0.5805 0.4673 0.5805 0.7619
No log 3.58 358 0.6192 0.4076 0.6192 0.7869
No log 3.6 360 0.6283 0.4071 0.6283 0.7926
No log 3.62 362 0.6508 0.4545 0.6508 0.8067
No log 3.64 364 0.6906 0.4606 0.6906 0.8310
No log 3.66 366 0.7101 0.4522 0.7101 0.8427
No log 3.68 368 0.6170 0.4993 0.6170 0.7855
No log 3.7 370 0.5714 0.4911 0.5714 0.7559
No log 3.7200 372 0.5782 0.5236 0.5782 0.7604
No log 3.74 374 0.5678 0.4975 0.5678 0.7535
No log 3.76 376 0.5571 0.4997 0.5571 0.7464
No log 3.7800 378 0.5688 0.5528 0.5688 0.7542
No log 3.8 380 0.5905 0.4749 0.5905 0.7684
No log 3.82 382 0.5621 0.5448 0.5621 0.7497
No log 3.84 384 0.5997 0.4908 0.5997 0.7744
No log 3.86 386 0.7106 0.4670 0.7106 0.8430
No log 3.88 388 0.7999 0.4595 0.7999 0.8944
No log 3.9 390 0.7796 0.4866 0.7796 0.8830
No log 3.92 392 0.7753 0.4924 0.7753 0.8805
No log 3.94 394 0.6826 0.5527 0.6826 0.8262
No log 3.96 396 0.6117 0.5309 0.6117 0.7821
No log 3.98 398 0.6373 0.4981 0.6373 0.7983
No log 4.0 400 0.6789 0.4949 0.6789 0.8239
No log 4.02 402 0.6653 0.4915 0.6653 0.8156
No log 4.04 404 0.6232 0.5127 0.6232 0.7894
No log 4.06 406 0.6281 0.4712 0.6281 0.7925
No log 4.08 408 0.6360 0.5258 0.6360 0.7975
No log 4.1 410 0.6209 0.4919 0.6209 0.7879
No log 4.12 412 0.6049 0.4862 0.6049 0.7778
No log 4.14 414 0.6120 0.4648 0.6120 0.7823
No log 4.16 416 0.6939 0.4481 0.6939 0.8330
No log 4.18 418 0.7071 0.4322 0.7071 0.8409
No log 4.2 420 0.6439 0.5414 0.6439 0.8025
No log 4.22 422 0.6296 0.4854 0.6296 0.7935
No log 4.24 424 0.6678 0.4856 0.6678 0.8172
No log 4.26 426 0.6865 0.5191 0.6865 0.8285
No log 4.28 428 0.6817 0.4932 0.6817 0.8256
No log 4.3 430 0.6454 0.4633 0.6454 0.8034
No log 4.32 432 0.6396 0.4896 0.6396 0.7997
No log 4.34 434 0.6401 0.5251 0.6401 0.8001
No log 4.36 436 0.6675 0.4797 0.6675 0.8170
No log 4.38 438 0.7103 0.5304 0.7103 0.8428
No log 4.4 440 0.7697 0.5383 0.7697 0.8773
No log 4.42 442 0.7462 0.5514 0.7462 0.8638
No log 4.44 444 0.7146 0.5311 0.7146 0.8453
No log 4.46 446 0.7342 0.5222 0.7342 0.8569
No log 4.48 448 0.7497 0.5551 0.7497 0.8658
No log 4.5 450 0.8206 0.4821 0.8206 0.9059
No log 4.52 452 0.7485 0.5267 0.7485 0.8652
No log 4.54 454 0.6546 0.4519 0.6545 0.8090
No log 4.5600 456 0.6062 0.3921 0.6062 0.7786
No log 4.58 458 0.5952 0.4051 0.5952 0.7715
No log 4.6 460 0.5945 0.4250 0.5945 0.7711
No log 4.62 462 0.5822 0.4116 0.5822 0.7630
No log 4.64 464 0.5944 0.4094 0.5944 0.7710
No log 4.66 466 0.6799 0.4665 0.6799 0.8245
No log 4.68 468 0.7511 0.4749 0.7511 0.8666
No log 4.7 470 0.7433 0.4810 0.7433 0.8621
No log 4.72 472 0.6517 0.5061 0.6517 0.8073
No log 4.74 474 0.6299 0.4911 0.6299 0.7937
No log 4.76 476 0.6744 0.5473 0.6744 0.8212
No log 4.78 478 0.7652 0.5131 0.7652 0.8748
No log 4.8 480 0.9837 0.4165 0.9837 0.9918
No log 4.82 482 1.1704 0.2621 1.1704 1.0819
No log 4.84 484 1.0257 0.3567 1.0257 1.0128
No log 4.86 486 0.7896 0.4539 0.7896 0.8886
No log 4.88 488 0.6923 0.4981 0.6923 0.8321
No log 4.9 490 0.5727 0.4529 0.5727 0.7568
No log 4.92 492 0.5428 0.4292 0.5428 0.7367
No log 4.9400 494 0.5458 0.4079 0.5458 0.7387
No log 4.96 496 0.5558 0.4160 0.5558 0.7455
No log 4.98 498 0.5649 0.4153 0.5649 0.7516
0.3889 5.0 500 0.5742 0.4811 0.5742 0.7578
0.3889 5.02 502 0.5789 0.5528 0.5789 0.7609
0.3889 5.04 504 0.5438 0.4998 0.5438 0.7374
0.3889 5.06 506 0.5470 0.5283 0.5470 0.7396
0.3889 5.08 508 0.5846 0.5357 0.5846 0.7646
0.3889 5.1 510 0.6202 0.5419 0.6202 0.7875
0.3889 5.12 512 0.6152 0.5438 0.6152 0.7844
0.3889 5.14 514 0.6342 0.5527 0.6342 0.7963
0.3889 5.16 516 0.6155 0.5698 0.6155 0.7846
0.3889 5.18 518 0.6203 0.5760 0.6203 0.7876
0.3889 5.2 520 0.5693 0.5711 0.5693 0.7545
0.3889 5.22 522 0.5578 0.5680 0.5578 0.7469
0.3889 5.24 524 0.5703 0.5833 0.5703 0.7552
0.3889 5.26 526 0.6174 0.4975 0.6174 0.7858
0.3889 5.28 528 0.6816 0.4740 0.6816 0.8256
0.3889 5.3 530 0.7140 0.5068 0.7140 0.8450
0.3889 5.32 532 0.6962 0.5305 0.6962 0.8344
0.3889 5.34 534 0.6558 0.5356 0.6558 0.8098
0.3889 5.36 536 0.6822 0.5030 0.6822 0.8259
0.3889 5.38 538 0.7239 0.4961 0.7239 0.8509
0.3889 5.4 540 0.7017 0.4910 0.7017 0.8377
0.3889 5.42 542 0.7218 0.5127 0.7218 0.8496
0.3889 5.44 544 0.7185 0.4635 0.7185 0.8476
0.3889 5.46 546 0.7086 0.4776 0.7086 0.8418
0.3889 5.48 548 0.6824 0.5405 0.6824 0.8261
0.3889 5.5 550 0.6321 0.4966 0.6321 0.7950
0.3889 5.52 552 0.6546 0.5214 0.6546 0.8091
0.3889 5.54 554 0.6375 0.5167 0.6375 0.7984
0.3889 5.5600 556 0.6227 0.5083 0.6227 0.7891
0.3889 5.58 558 0.5778 0.4795 0.5778 0.7602
0.3889 5.6 560 0.5675 0.4110 0.5675 0.7533
0.3889 5.62 562 0.5678 0.3914 0.5678 0.7535
0.3889 5.64 564 0.5708 0.4490 0.5708 0.7555
0.3889 5.66 566 0.6119 0.5130 0.6119 0.7823
0.3889 5.68 568 0.6312 0.5178 0.6312 0.7945
0.3889 5.7 570 0.5979 0.5180 0.5979 0.7732
0.3889 5.72 572 0.5730 0.4737 0.5730 0.7569
0.3889 5.74 574 0.5991 0.4489 0.5991 0.7740
0.3889 5.76 576 0.6065 0.4734 0.6065 0.7788
0.3889 5.78 578 0.5991 0.4890 0.5991 0.7740
0.3889 5.8 580 0.6570 0.4582 0.6570 0.8106
0.3889 5.82 582 0.7175 0.5215 0.7175 0.8470
0.3889 5.84 584 0.7468 0.5118 0.7468 0.8642
0.3889 5.86 586 0.7061 0.5185 0.7061 0.8403
0.3889 5.88 588 0.6102 0.4581 0.6102 0.7812
0.3889 5.9 590 0.5814 0.4865 0.5814 0.7625
0.3889 5.92 592 0.5770 0.4381 0.5770 0.7596
0.3889 5.9400 594 0.5833 0.3896 0.5833 0.7638
0.3889 5.96 596 0.6326 0.4303 0.6326 0.7954
0.3889 5.98 598 0.6397 0.4195 0.6397 0.7998
0.3889 6.0 600 0.6117 0.4195 0.6117 0.7821

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_usingWellWrittenEssays_FineTuningAraBERT_run2_AugV5_k19_task2_organization

Finetuned
(4206)
this model