ArabicNewSplits7_usingALLEssays_FineTuningAraBERT_run1_AugV5_k15_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: 0.8429
  • Qwk: 0.6573
  • Mse: 0.8429
  • Rmse: 0.9181

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 0.0286 2 7.1026 0.0 7.1026 2.6651
No log 0.0571 4 4.8098 0.0081 4.8098 2.1931
No log 0.0857 6 4.2295 -0.0784 4.2295 2.0566
No log 0.1143 8 2.6426 0.0280 2.6426 1.6256
No log 0.1429 10 2.1830 0.1194 2.1830 1.4775
No log 0.1714 12 2.1397 0.2121 2.1397 1.4628
No log 0.2 14 1.9161 0.2542 1.9161 1.3842
No log 0.2286 16 1.8858 0.2542 1.8858 1.3733
No log 0.2571 18 2.1690 0.1379 2.1690 1.4728
No log 0.2857 20 2.1203 0.1793 2.1203 1.4561
No log 0.3143 22 1.9904 0.3281 1.9904 1.4108
No log 0.3429 24 2.1354 0.1854 2.1354 1.4613
No log 0.3714 26 2.5672 0.1605 2.5672 1.6023
No log 0.4 28 2.6151 0.1697 2.6151 1.6171
No log 0.4286 30 1.9676 0.3194 1.9676 1.4027
No log 0.4571 32 1.8708 0.3239 1.8708 1.3678
No log 0.4857 34 2.2525 0.2105 2.2525 1.5008
No log 0.5143 36 2.5118 0.1375 2.5118 1.5849
No log 0.5429 38 1.9715 0.2838 1.9715 1.4041
No log 0.5714 40 1.6686 0.4296 1.6686 1.2918
No log 0.6 42 1.4944 0.3939 1.4944 1.2225
No log 0.6286 44 1.9033 0.3562 1.9033 1.3796
No log 0.6571 46 2.5483 0.2024 2.5483 1.5963
No log 0.6857 48 2.7087 0.2000 2.7087 1.6458
No log 0.7143 50 2.1001 0.2733 2.1001 1.4492
No log 0.7429 52 1.3018 0.4928 1.3018 1.1410
No log 0.7714 54 1.2138 0.5113 1.2138 1.1017
No log 0.8 56 1.4113 0.3692 1.4113 1.1880
No log 0.8286 58 1.2565 0.4844 1.2565 1.1210
No log 0.8571 60 1.1858 0.5481 1.1858 1.0890
No log 0.8857 62 1.3897 0.4571 1.3897 1.1788
No log 0.9143 64 1.4100 0.4429 1.4100 1.1874
No log 0.9429 66 1.2828 0.4741 1.2828 1.1326
No log 0.9714 68 1.3741 0.4895 1.3741 1.1722
No log 1.0 70 1.3297 0.5175 1.3297 1.1531
No log 1.0286 72 1.5425 0.5276 1.5425 1.2420
No log 1.0571 74 1.3706 0.5590 1.3706 1.1707
No log 1.0857 76 1.0835 0.6143 1.0835 1.0409
No log 1.1143 78 0.9951 0.6029 0.9951 0.9975
No log 1.1429 80 1.3731 0.3937 1.3731 1.1718
No log 1.1714 82 1.8581 0.2222 1.8581 1.3631
No log 1.2 84 1.0689 0.5630 1.0689 1.0339
No log 1.2286 86 1.5334 0.4968 1.5334 1.2383
No log 1.2571 88 1.7775 0.4151 1.7775 1.3332
No log 1.2857 90 1.6966 0.3791 1.6966 1.3025
No log 1.3143 92 1.3698 0.4672 1.3698 1.1704
No log 1.3429 94 1.0250 0.5926 1.0250 1.0124
No log 1.3714 96 1.1666 0.5333 1.1666 1.0801
No log 1.4 98 1.1811 0.5612 1.1811 1.0868
No log 1.4286 100 1.0119 0.5899 1.0119 1.0059
No log 1.4571 102 1.0469 0.5797 1.0469 1.0232
No log 1.4857 104 1.0220 0.6294 1.0220 1.0110
No log 1.5143 106 1.0868 0.6133 1.0868 1.0425
No log 1.5429 108 1.0063 0.6309 1.0063 1.0031
No log 1.5714 110 1.0231 0.6309 1.0231 1.0115
No log 1.6 112 1.1720 0.6013 1.1720 1.0826
No log 1.6286 114 1.1459 0.6013 1.1459 1.0705
No log 1.6571 116 1.0139 0.6133 1.0139 1.0069
No log 1.6857 118 0.8982 0.6667 0.8982 0.9477
No log 1.7143 120 1.1867 0.6087 1.1867 1.0893
No log 1.7429 122 1.7961 0.4845 1.7961 1.3402
No log 1.7714 124 1.6810 0.5026 1.6810 1.2965
No log 1.8 126 0.9798 0.6503 0.9798 0.9899
No log 1.8286 128 0.7869 0.7564 0.7869 0.8871
No log 1.8571 130 0.9647 0.6420 0.9647 0.9822
No log 1.8857 132 1.6076 0.5543 1.6076 1.2679
No log 1.9143 134 1.5544 0.5543 1.5544 1.2467
No log 1.9429 136 1.4842 0.5668 1.4842 1.2183
No log 1.9714 138 1.0030 0.6173 1.0030 1.0015
No log 2.0 140 1.0054 0.6049 1.0054 1.0027
No log 2.0286 142 0.8678 0.7468 0.8678 0.9316
No log 2.0571 144 0.7206 0.7034 0.7206 0.8489
No log 2.0857 146 0.8710 0.6812 0.8710 0.9333
No log 2.1143 148 1.1586 0.5263 1.1586 1.0764
No log 2.1429 150 1.1071 0.5882 1.1071 1.0522
No log 2.1714 152 0.8937 0.6765 0.8937 0.9453
No log 2.2 154 0.8368 0.6853 0.8368 0.9148
No log 2.2286 156 0.8373 0.6803 0.8373 0.9150
No log 2.2571 158 0.7936 0.6849 0.7936 0.8909
No log 2.2857 160 0.7606 0.7248 0.7606 0.8721
No log 2.3143 162 0.7358 0.7297 0.7358 0.8578
No log 2.3429 164 0.7397 0.7582 0.7397 0.8601
No log 2.3714 166 0.7879 0.7425 0.7879 0.8877
No log 2.4 168 0.7596 0.7516 0.7596 0.8716
No log 2.4286 170 0.6954 0.7871 0.6954 0.8339
No log 2.4571 172 0.7124 0.7821 0.7124 0.8440
No log 2.4857 174 0.7769 0.7421 0.7769 0.8814
No log 2.5143 176 0.7680 0.7421 0.7680 0.8763
No log 2.5429 178 0.6825 0.7347 0.6825 0.8261
No log 2.5714 180 0.7136 0.7417 0.7136 0.8447
No log 2.6 182 1.0031 0.6552 1.0031 1.0016
No log 2.6286 184 1.4884 0.5882 1.4884 1.2200
No log 2.6571 186 1.5082 0.5918 1.5082 1.2281
No log 2.6857 188 1.0612 0.6444 1.0612 1.0301
No log 2.7143 190 0.7922 0.7394 0.7922 0.8900
No log 2.7429 192 0.7167 0.7763 0.7167 0.8466
No log 2.7714 194 0.6942 0.7703 0.6942 0.8332
No log 2.8 196 0.7139 0.7333 0.7139 0.8449
No log 2.8286 198 0.9951 0.6536 0.9951 0.9976
No log 2.8571 200 1.1553 0.6076 1.1553 1.0748
No log 2.8857 202 0.9356 0.6389 0.9356 0.9673
No log 2.9143 204 0.6792 0.7310 0.6792 0.8241
No log 2.9429 206 0.6677 0.7299 0.6677 0.8172
No log 2.9714 208 0.6288 0.7310 0.6288 0.7930
No log 3.0 210 0.6047 0.7651 0.6047 0.7776
No log 3.0286 212 0.7898 0.7561 0.7898 0.8887
No log 3.0571 214 0.9268 0.7086 0.9268 0.9627
No log 3.0857 216 0.8277 0.7471 0.8277 0.9098
No log 3.1143 218 0.6497 0.7975 0.6497 0.8060
No log 3.1429 220 0.6576 0.7297 0.6576 0.8109
No log 3.1714 222 0.7031 0.7361 0.7031 0.8385
No log 3.2 224 0.7445 0.7123 0.7445 0.8629
No log 3.2286 226 0.8831 0.6711 0.8831 0.9397
No log 3.2571 228 0.8761 0.6711 0.8761 0.9360
No log 3.2857 230 0.8129 0.6968 0.8129 0.9016
No log 3.3143 232 0.7422 0.7484 0.7422 0.8615
No log 3.3429 234 0.7093 0.7484 0.7093 0.8422
No log 3.3714 236 0.6901 0.7643 0.6901 0.8307
No log 3.4 238 0.7076 0.7901 0.7076 0.8412
No log 3.4286 240 0.7494 0.7484 0.7494 0.8657
No log 3.4571 242 0.7305 0.7564 0.7305 0.8547
No log 3.4857 244 0.6658 0.8 0.6658 0.8159
No log 3.5143 246 0.7157 0.7841 0.7157 0.8460
No log 3.5429 248 0.6763 0.7657 0.6763 0.8224
No log 3.5714 250 0.6247 0.7821 0.6247 0.7904
No log 3.6 252 0.6127 0.7568 0.6127 0.7827
No log 3.6286 254 0.6570 0.7632 0.6570 0.8106
No log 3.6571 256 0.7848 0.7421 0.7848 0.8859
No log 3.6857 258 0.8240 0.7337 0.8240 0.9077
No log 3.7143 260 0.7339 0.7805 0.7339 0.8567
No log 3.7429 262 0.6381 0.7815 0.6381 0.7988
No log 3.7714 264 0.6465 0.7763 0.6465 0.8040
No log 3.8 266 0.6982 0.7531 0.6982 0.8356
No log 3.8286 268 0.7898 0.7665 0.7898 0.8887
No log 3.8571 270 0.9187 0.6864 0.9187 0.9585
No log 3.8857 272 0.8977 0.6994 0.8977 0.9474
No log 3.9143 274 0.8022 0.7123 0.8022 0.8957
No log 3.9429 276 0.8298 0.6897 0.8298 0.9109
No log 3.9714 278 0.8631 0.6286 0.8631 0.9290
No log 4.0 280 0.9310 0.6434 0.9310 0.9649
No log 4.0286 282 0.9496 0.6710 0.9496 0.9745
No log 4.0571 284 0.8208 0.7308 0.8208 0.9060
No log 4.0857 286 0.7354 0.7260 0.7354 0.8575
No log 4.1143 288 0.7180 0.7451 0.7180 0.8473
No log 4.1429 290 0.7044 0.7432 0.7044 0.8393
No log 4.1714 292 0.7279 0.7432 0.7279 0.8532
No log 4.2 294 0.8105 0.7013 0.8105 0.9003
No log 4.2286 296 0.9456 0.6790 0.9456 0.9724
No log 4.2571 298 0.8980 0.6711 0.8980 0.9476
No log 4.2857 300 0.7914 0.6809 0.7914 0.8896
No log 4.3143 302 0.8844 0.6 0.8844 0.9404
No log 4.3429 304 0.9099 0.6364 0.9099 0.9539
No log 4.3714 306 0.7733 0.7153 0.7733 0.8794
No log 4.4 308 0.8579 0.6187 0.8579 0.9262
No log 4.4286 310 1.0384 0.6533 1.0384 1.0190
No log 4.4571 312 0.8761 0.6800 0.8761 0.9360
No log 4.4857 314 0.6165 0.7347 0.6165 0.7852
No log 4.5143 316 0.6132 0.7651 0.6132 0.7831
No log 4.5429 318 0.6216 0.7651 0.6216 0.7884
No log 4.5714 320 0.6747 0.7792 0.6747 0.8214
No log 4.6 322 0.7384 0.7075 0.7384 0.8593
No log 4.6286 324 0.8263 0.6939 0.8263 0.9090
No log 4.6571 326 0.7775 0.6475 0.7775 0.8817
No log 4.6857 328 0.7479 0.6906 0.7479 0.8648
No log 4.7143 330 0.7356 0.7143 0.7356 0.8577
No log 4.7429 332 0.7349 0.7517 0.7349 0.8572
No log 4.7714 334 0.8044 0.7006 0.8044 0.8969
No log 4.8 336 0.7468 0.7237 0.7468 0.8642
No log 4.8286 338 0.7332 0.7237 0.7332 0.8562
No log 4.8571 340 0.6680 0.7821 0.6680 0.8173
No log 4.8857 342 0.6254 0.7922 0.6254 0.7908
No log 4.9143 344 0.6413 0.7922 0.6413 0.8008
No log 4.9429 346 0.6940 0.7484 0.6940 0.8331
No log 4.9714 348 0.7442 0.7105 0.7442 0.8627
No log 5.0 350 0.7520 0.6933 0.7520 0.8672
No log 5.0286 352 0.7178 0.7320 0.7178 0.8472
No log 5.0571 354 0.7060 0.7692 0.7060 0.8402
No log 5.0857 356 0.7451 0.7910 0.7451 0.8632
No log 5.1143 358 0.9936 0.7072 0.9936 0.9968
No log 5.1429 360 1.3470 0.6162 1.3470 1.1606
No log 5.1714 362 1.1778 0.6492 1.1778 1.0853
No log 5.2 364 0.9131 0.7143 0.9131 0.9555
No log 5.2286 366 0.6603 0.8193 0.6603 0.8126
No log 5.2571 368 0.6685 0.7763 0.6685 0.8176
No log 5.2857 370 0.7316 0.7248 0.7316 0.8554
No log 5.3143 372 0.7914 0.7172 0.7914 0.8896
No log 5.3429 374 0.7823 0.6901 0.7823 0.8845
No log 5.3714 376 0.7529 0.7143 0.7529 0.8677
No log 5.4 378 0.7331 0.7101 0.7331 0.8562
No log 5.4286 380 0.6654 0.7376 0.6654 0.8157
No log 5.4571 382 0.6516 0.7671 0.6516 0.8072
No log 5.4857 384 0.6583 0.7785 0.6583 0.8114
No log 5.5143 386 0.6306 0.7651 0.6306 0.7941
No log 5.5429 388 0.6281 0.75 0.6281 0.7925
No log 5.5714 390 0.6373 0.7619 0.6373 0.7983
No log 5.6 392 0.6894 0.7682 0.6894 0.8303
No log 5.6286 394 0.8273 0.6986 0.8273 0.9096
No log 5.6571 396 1.0006 0.6316 1.0006 1.0003
No log 5.6857 398 0.9414 0.6351 0.9414 0.9703
No log 5.7143 400 0.8222 0.6713 0.8222 0.9067
No log 5.7429 402 0.7177 0.7483 0.7177 0.8472
No log 5.7714 404 0.6607 0.7619 0.6607 0.8129
No log 5.8 406 0.6270 0.7619 0.6270 0.7918
No log 5.8286 408 0.5990 0.7763 0.5990 0.7740
No log 5.8571 410 0.6002 0.7651 0.6002 0.7747
No log 5.8857 412 0.6093 0.7651 0.6093 0.7806
No log 5.9143 414 0.6287 0.7651 0.6287 0.7929
No log 5.9429 416 0.6570 0.7619 0.6570 0.8105
No log 5.9714 418 0.6428 0.7619 0.6428 0.8017
No log 6.0 420 0.6348 0.7703 0.6348 0.7967
No log 6.0286 422 0.6902 0.7564 0.6902 0.8308
No log 6.0571 424 0.6860 0.7673 0.6860 0.8282
No log 6.0857 426 0.5584 0.8026 0.5584 0.7472
No log 6.1143 428 0.5379 0.7733 0.5379 0.7334
No log 6.1429 430 0.5858 0.7568 0.5858 0.7654
No log 6.1714 432 0.6087 0.7733 0.6087 0.7802
No log 6.2 434 0.6601 0.7763 0.6601 0.8124
No log 6.2286 436 0.7460 0.7397 0.7460 0.8637
No log 6.2571 438 0.7745 0.6861 0.7745 0.8801
No log 6.2857 440 0.8056 0.7059 0.8056 0.8976
No log 6.3143 442 0.8063 0.6866 0.8063 0.8980
No log 6.3429 444 0.7635 0.7299 0.7635 0.8738
No log 6.3714 446 0.7339 0.7206 0.7339 0.8567
No log 6.4 448 0.7551 0.7083 0.7551 0.8690
No log 6.4286 450 0.7595 0.6853 0.7595 0.8715
No log 6.4571 452 0.6747 0.7310 0.6747 0.8214
No log 6.4857 454 0.6087 0.7785 0.6087 0.7802
No log 6.5143 456 0.6404 0.75 0.6404 0.8002
No log 6.5429 458 0.7464 0.7222 0.7464 0.8639
No log 6.5714 460 0.7396 0.7703 0.7396 0.8600
No log 6.6 462 0.6884 0.7682 0.6884 0.8297
No log 6.6286 464 0.7826 0.7453 0.7826 0.8846
No log 6.6571 466 0.9770 0.6893 0.9770 0.9885
No log 6.6857 468 0.9697 0.6829 0.9697 0.9847
No log 6.7143 470 0.8184 0.7273 0.8184 0.9046
No log 6.7429 472 0.6792 0.7448 0.6792 0.8241
No log 6.7714 474 0.6384 0.7619 0.6384 0.7990
No log 6.8 476 0.6358 0.7619 0.6358 0.7974
No log 6.8286 478 0.6498 0.7922 0.6498 0.8061
No log 6.8571 480 0.6490 0.8118 0.6490 0.8056
No log 6.8857 482 0.6923 0.8092 0.6923 0.8320
No log 6.9143 484 0.6506 0.8187 0.6506 0.8066
No log 6.9429 486 0.6247 0.7976 0.6247 0.7904
No log 6.9714 488 0.6320 0.8125 0.6320 0.7950
No log 7.0 490 0.6711 0.7922 0.6711 0.8192
No log 7.0286 492 0.6925 0.7815 0.6925 0.8322
No log 7.0571 494 0.6679 0.7843 0.6679 0.8173
No log 7.0857 496 0.6258 0.7949 0.6258 0.7911
No log 7.1143 498 0.5758 0.8025 0.5758 0.7588
0.4153 7.1429 500 0.5477 0.8025 0.5477 0.7401
0.4153 7.1714 502 0.5532 0.8025 0.5532 0.7437
0.4153 7.2 504 0.5548 0.7922 0.5548 0.7449
0.4153 7.2286 506 0.5866 0.7619 0.5866 0.7659
0.4153 7.2571 508 0.6897 0.7671 0.6897 0.8305
0.4153 7.2857 510 0.8429 0.6573 0.8429 0.9181

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
2
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/ArabicNewSplits7_usingALLEssays_FineTuningAraBERT_run1_AugV5_k15_task1_organization

Finetuned
(4040)
this model