ArabicNewSplits7_usingALLEssays_FineTuningAraBERT_run3_AugV5_k20_task5_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: 0.6771
  • Qwk: 0.5202
  • Mse: 0.6771
  • Rmse: 0.8228

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 0.0312 2 4.4628 -0.0088 4.4628 2.1125
No log 0.0625 4 2.8743 -0.0398 2.8743 1.6954
No log 0.0938 6 1.6808 0.0165 1.6808 1.2965
No log 0.125 8 1.1978 0.0170 1.1978 1.0944
No log 0.1562 10 1.2059 -0.0160 1.2059 1.0981
No log 0.1875 12 1.2719 0.0201 1.2719 1.1278
No log 0.2188 14 1.2254 -0.0212 1.2254 1.1070
No log 0.25 16 1.2403 0.0 1.2403 1.1137
No log 0.2812 18 1.2048 0.0232 1.2048 1.0976
No log 0.3125 20 1.2024 0.0760 1.2024 1.0966
No log 0.3438 22 1.1880 0.1205 1.1880 1.0899
No log 0.375 24 1.1834 0.2489 1.1834 1.0879
No log 0.4062 26 1.2651 0.0053 1.2651 1.1247
No log 0.4375 28 1.3638 0.0613 1.3638 1.1678
No log 0.4688 30 1.5362 0.0 1.5362 1.2394
No log 0.5 32 1.5392 0.0 1.5392 1.2406
No log 0.5312 34 1.3670 0.0496 1.3670 1.1692
No log 0.5625 36 1.3258 -0.0064 1.3258 1.1514
No log 0.5938 38 1.1938 0.1268 1.1938 1.0926
No log 0.625 40 1.1566 0.1296 1.1566 1.0754
No log 0.6562 42 1.2073 0.1261 1.2073 1.0988
No log 0.6875 44 1.2360 0.1142 1.2360 1.1117
No log 0.7188 46 1.2311 0.2004 1.2311 1.1095
No log 0.75 48 1.3242 0.0349 1.3242 1.1507
No log 0.7812 50 1.4024 0.0380 1.4024 1.1842
No log 0.8125 52 1.3341 0.0349 1.3341 1.1550
No log 0.8438 54 1.1262 0.1509 1.1262 1.0612
No log 0.875 56 1.0895 0.2251 1.0895 1.0438
No log 0.9062 58 1.1141 0.1953 1.1141 1.0555
No log 0.9375 60 1.1007 0.1767 1.1007 1.0492
No log 0.9688 62 1.1904 0.1148 1.1904 1.0911
No log 1.0 64 1.1323 0.1389 1.1323 1.0641
No log 1.0312 66 1.1141 0.1509 1.1141 1.0555
No log 1.0625 68 1.1417 0.2138 1.1417 1.0685
No log 1.0938 70 1.0206 0.2921 1.0206 1.0102
No log 1.125 72 1.0118 0.3445 1.0118 1.0059
No log 1.1562 74 0.9835 0.2602 0.9835 0.9917
No log 1.1875 76 1.0596 0.3402 1.0596 1.0294
No log 1.2188 78 1.0768 0.2690 1.0768 1.0377
No log 1.25 80 0.9509 0.3117 0.9509 0.9751
No log 1.2812 82 0.9732 0.3693 0.9732 0.9865
No log 1.3125 84 0.9535 0.3428 0.9535 0.9765
No log 1.3438 86 1.0309 0.2822 1.0309 1.0153
No log 1.375 88 0.9564 0.3676 0.9564 0.9780
No log 1.4062 90 1.0627 0.2384 1.0627 1.0309
No log 1.4375 92 1.3972 0.0860 1.3972 1.1821
No log 1.4688 94 1.1979 0.1601 1.1979 1.0945
No log 1.5 96 0.8625 0.4624 0.8625 0.9287
No log 1.5312 98 0.8437 0.4676 0.8437 0.9185
No log 1.5625 100 0.8352 0.4789 0.8352 0.9139
No log 1.5938 102 0.8284 0.4789 0.8284 0.9101
No log 1.625 104 0.8992 0.3577 0.8992 0.9483
No log 1.6562 106 0.9440 0.3775 0.9440 0.9716
No log 1.6875 108 0.8387 0.4645 0.8387 0.9158
No log 1.7188 110 0.8633 0.3633 0.8633 0.9292
No log 1.75 112 0.8770 0.3633 0.8770 0.9365
No log 1.7812 114 0.8494 0.3633 0.8494 0.9216
No log 1.8125 116 0.8089 0.4903 0.8089 0.8994
No log 1.8438 118 0.9064 0.4123 0.9064 0.9521
No log 1.875 120 0.8522 0.4357 0.8522 0.9232
No log 1.9062 122 0.7954 0.5386 0.7954 0.8919
No log 1.9375 124 0.8007 0.4995 0.8007 0.8948
No log 1.9688 126 0.8736 0.4253 0.8736 0.9347
No log 2.0 128 0.8897 0.4262 0.8897 0.9433
No log 2.0312 130 0.8190 0.5220 0.8190 0.9050
No log 2.0625 132 0.8685 0.4489 0.8685 0.9320
No log 2.0938 134 0.9329 0.4006 0.9329 0.9659
No log 2.125 136 0.8365 0.4606 0.8365 0.9146
No log 2.1562 138 0.8364 0.4980 0.8364 0.9145
No log 2.1875 140 0.8730 0.4478 0.8730 0.9343
No log 2.2188 142 0.8176 0.4289 0.8176 0.9042
No log 2.25 144 0.8007 0.4660 0.8007 0.8948
No log 2.2812 146 0.7937 0.3840 0.7937 0.8909
No log 2.3125 148 0.8380 0.4577 0.8380 0.9154
No log 2.3438 150 0.8421 0.4349 0.8421 0.9177
No log 2.375 152 0.7985 0.4465 0.7985 0.8936
No log 2.4062 154 0.7660 0.4778 0.7660 0.8752
No log 2.4375 156 0.7962 0.3407 0.7962 0.8923
No log 2.4688 158 0.8107 0.4006 0.8107 0.9004
No log 2.5 160 0.7642 0.4944 0.7642 0.8742
No log 2.5312 162 0.7908 0.5279 0.7908 0.8893
No log 2.5625 164 0.8235 0.4492 0.8235 0.9074
No log 2.5938 166 0.8236 0.4884 0.8236 0.9075
No log 2.625 168 0.8284 0.4676 0.8284 0.9102
No log 2.6562 170 0.8427 0.3915 0.8427 0.9180
No log 2.6875 172 0.9304 0.3143 0.9304 0.9646
No log 2.7188 174 1.1573 0.2569 1.1573 1.0758
No log 2.75 176 1.1530 0.2341 1.1530 1.0738
No log 2.7812 178 0.9078 0.3104 0.9078 0.9528
No log 2.8125 180 0.8517 0.3982 0.8517 0.9229
No log 2.8438 182 0.8467 0.3604 0.8467 0.9202
No log 2.875 184 0.8840 0.4263 0.8840 0.9402
No log 2.9062 186 0.9181 0.4026 0.9181 0.9582
No log 2.9375 188 0.7404 0.3814 0.7404 0.8604
No log 2.9688 190 0.6991 0.5317 0.6991 0.8361
No log 3.0 192 0.8559 0.5625 0.8559 0.9251
No log 3.0312 194 0.8570 0.5515 0.8570 0.9257
No log 3.0625 196 0.7049 0.5397 0.7049 0.8396
No log 3.0938 198 0.7020 0.4592 0.7020 0.8379
No log 3.125 200 0.8103 0.4926 0.8103 0.9002
No log 3.1562 202 0.8124 0.5258 0.8124 0.9013
No log 3.1875 204 0.7026 0.4826 0.7026 0.8382
No log 3.2188 206 0.6865 0.5069 0.6865 0.8285
No log 3.25 208 0.6980 0.4398 0.6980 0.8354
No log 3.2812 210 0.7411 0.4115 0.7411 0.8609
No log 3.3125 212 0.8669 0.5230 0.8669 0.9311
No log 3.3438 214 0.9045 0.5208 0.9045 0.9510
No log 3.375 216 0.8266 0.4209 0.8266 0.9092
No log 3.4062 218 0.8236 0.4277 0.8236 0.9075
No log 3.4375 220 0.9559 0.3995 0.9559 0.9777
No log 3.4688 222 0.8954 0.4598 0.8954 0.9463
No log 3.5 224 0.7835 0.4133 0.7835 0.8851
No log 3.5312 226 0.8584 0.4460 0.8584 0.9265
No log 3.5625 228 0.9971 0.4434 0.9971 0.9985
No log 3.5938 230 0.9794 0.4186 0.9794 0.9896
No log 3.625 232 0.8556 0.4057 0.8556 0.9250
No log 3.6562 234 0.7957 0.3842 0.7957 0.8920
No log 3.6875 236 0.7648 0.4102 0.7648 0.8745
No log 3.7188 238 0.7817 0.4935 0.7817 0.8841
No log 3.75 240 0.8606 0.4805 0.8606 0.9277
No log 3.7812 242 1.0241 0.4786 1.0241 1.0120
No log 3.8125 244 0.9469 0.4786 0.9469 0.9731
No log 3.8438 246 0.7579 0.5255 0.7579 0.8706
No log 3.875 248 0.7562 0.4849 0.7562 0.8696
No log 3.9062 250 0.7569 0.4983 0.7569 0.8700
No log 3.9375 252 0.7116 0.5446 0.7116 0.8436
No log 3.9688 254 0.7692 0.4710 0.7692 0.8770
No log 4.0 256 0.8239 0.4916 0.8239 0.9077
No log 4.0312 258 0.7680 0.4948 0.7680 0.8764
No log 4.0625 260 0.7279 0.4082 0.7279 0.8532
No log 4.0938 262 0.7370 0.4427 0.7370 0.8585
No log 4.125 264 0.7339 0.4817 0.7339 0.8567
No log 4.1562 266 0.7350 0.4337 0.7350 0.8573
No log 4.1875 268 0.7554 0.4473 0.7554 0.8692
No log 4.2188 270 0.7624 0.4836 0.7624 0.8731
No log 4.25 272 0.7675 0.4836 0.7675 0.8761
No log 4.2812 274 0.7522 0.4478 0.7522 0.8673
No log 4.3125 276 0.7803 0.4836 0.7803 0.8834
No log 4.3438 278 0.7533 0.4345 0.7533 0.8679
No log 4.375 280 0.7545 0.4363 0.7545 0.8686
No log 4.4062 282 0.7703 0.4353 0.7703 0.8777
No log 4.4375 284 0.7894 0.3658 0.7894 0.8885
No log 4.4688 286 0.7800 0.4115 0.7800 0.8832
No log 4.5 288 0.7827 0.4675 0.7827 0.8847
No log 4.5312 290 0.8058 0.3934 0.8058 0.8977
No log 4.5625 292 0.7990 0.4312 0.7990 0.8939
No log 4.5938 294 0.7880 0.3896 0.7880 0.8877
No log 4.625 296 0.8938 0.4783 0.8938 0.9454
No log 4.6562 298 0.9675 0.4987 0.9675 0.9836
No log 4.6875 300 0.8733 0.3845 0.8733 0.9345
No log 4.7188 302 0.7782 0.4327 0.7782 0.8822
No log 4.75 304 0.7588 0.4261 0.7588 0.8711
No log 4.7812 306 0.7680 0.4097 0.7680 0.8764
No log 4.8125 308 0.7717 0.4097 0.7717 0.8785
No log 4.8438 310 0.7688 0.3879 0.7688 0.8768
No log 4.875 312 0.7923 0.4476 0.7923 0.8901
No log 4.9062 314 0.8744 0.4916 0.8744 0.9351
No log 4.9375 316 0.9629 0.3985 0.9629 0.9813
No log 4.9688 318 0.8915 0.4197 0.8915 0.9442
No log 5.0 320 0.8023 0.3802 0.8023 0.8957
No log 5.0312 322 0.8177 0.4259 0.8177 0.9043
No log 5.0625 324 0.8159 0.3455 0.8159 0.9032
No log 5.0938 326 0.8456 0.3596 0.8456 0.9196
No log 5.125 328 0.9316 0.4911 0.9316 0.9652
No log 5.1562 330 0.9519 0.5119 0.9519 0.9757
No log 5.1875 332 0.8526 0.3771 0.8526 0.9234
No log 5.2188 334 0.7929 0.3804 0.7929 0.8905
No log 5.25 336 0.7624 0.3860 0.7624 0.8732
No log 5.2812 338 0.7474 0.3959 0.7474 0.8645
No log 5.3125 340 0.7448 0.3959 0.7448 0.8630
No log 5.3438 342 0.7347 0.4093 0.7347 0.8571
No log 5.375 344 0.7334 0.4106 0.7334 0.8564
No log 5.4062 346 0.7682 0.3842 0.7682 0.8765
No log 5.4375 348 0.7854 0.3842 0.7854 0.8862
No log 5.4688 350 0.7878 0.4115 0.7878 0.8876
No log 5.5 352 0.7827 0.3687 0.7827 0.8847
No log 5.5312 354 0.7562 0.4363 0.7562 0.8696
No log 5.5625 356 0.7669 0.3961 0.7669 0.8757
No log 5.5938 358 0.7829 0.3515 0.7829 0.8848
No log 5.625 360 0.7952 0.3515 0.7952 0.8918
No log 5.6562 362 0.7828 0.3515 0.7828 0.8847
No log 5.6875 364 0.7752 0.4063 0.7752 0.8804
No log 5.7188 366 0.7792 0.3902 0.7792 0.8827
No log 5.75 368 0.7770 0.4576 0.7770 0.8815
No log 5.7812 370 0.7395 0.4223 0.7395 0.8599
No log 5.8125 372 0.7233 0.4540 0.7233 0.8505
No log 5.8438 374 0.7110 0.4422 0.7110 0.8432
No log 5.875 376 0.6998 0.4422 0.6998 0.8366
No log 5.9062 378 0.7025 0.4887 0.7025 0.8382
No log 5.9375 380 0.7076 0.4746 0.7076 0.8412
No log 5.9688 382 0.6946 0.6025 0.6946 0.8334
No log 6.0 384 0.6556 0.5785 0.6556 0.8097
No log 6.0312 386 0.6552 0.6099 0.6552 0.8094
No log 6.0625 388 0.6514 0.6470 0.6514 0.8071
No log 6.0938 390 0.6381 0.6680 0.6381 0.7988
No log 6.125 392 0.7072 0.6208 0.7072 0.8410
No log 6.1562 394 0.7582 0.5820 0.7582 0.8707
No log 6.1875 396 0.7230 0.5912 0.7230 0.8503
No log 6.2188 398 0.7012 0.5273 0.7012 0.8374
No log 6.25 400 0.7162 0.5026 0.7162 0.8463
No log 6.2812 402 0.7250 0.5042 0.7250 0.8514
No log 6.3125 404 0.7352 0.4409 0.7352 0.8575
No log 6.3438 406 0.7182 0.5048 0.7182 0.8475
No log 6.375 408 0.7402 0.5798 0.7402 0.8603
No log 6.4062 410 0.7654 0.5279 0.7654 0.8749
No log 6.4375 412 0.7221 0.5467 0.7221 0.8498
No log 6.4688 414 0.7343 0.4573 0.7343 0.8569
No log 6.5 416 0.7614 0.4590 0.7614 0.8726
No log 6.5312 418 0.7314 0.5048 0.7314 0.8552
No log 6.5625 420 0.7463 0.4988 0.7463 0.8639
No log 6.5938 422 0.7482 0.4988 0.7482 0.8650
No log 6.625 424 0.7232 0.4503 0.7232 0.8504
No log 6.6562 426 0.7825 0.4872 0.7825 0.8846
No log 6.6875 428 0.7926 0.4872 0.7926 0.8903
No log 6.7188 430 0.7213 0.5069 0.7213 0.8493
No log 6.75 432 0.7205 0.5898 0.7205 0.8488
No log 6.7812 434 0.7400 0.6045 0.7400 0.8602
No log 6.8125 436 0.6792 0.6142 0.6792 0.8242
No log 6.8438 438 0.6597 0.5871 0.6597 0.8122
No log 6.875 440 0.6576 0.5288 0.6576 0.8109
No log 6.9062 442 0.6589 0.6105 0.6589 0.8117
No log 6.9375 444 0.6819 0.5858 0.6819 0.8258
No log 6.9688 446 0.6890 0.6064 0.6890 0.8301
No log 7.0 448 0.6884 0.6142 0.6884 0.8297
No log 7.0312 450 0.6765 0.5977 0.6765 0.8225
No log 7.0625 452 0.6723 0.6314 0.6723 0.8200
No log 7.0938 454 0.6719 0.6491 0.6719 0.8197
No log 7.125 456 0.6842 0.5855 0.6842 0.8271
No log 7.1562 458 0.7328 0.5777 0.7328 0.8560
No log 7.1875 460 0.7459 0.5973 0.7459 0.8636
No log 7.2188 462 0.7159 0.5798 0.7159 0.8461
No log 7.25 464 0.6878 0.5373 0.6878 0.8293
No log 7.2812 466 0.7172 0.4864 0.7172 0.8469
No log 7.3125 468 0.7246 0.4864 0.7246 0.8512
No log 7.3438 470 0.7061 0.5386 0.7061 0.8403
No log 7.375 472 0.8012 0.5353 0.8012 0.8951
No log 7.4062 474 0.8901 0.5 0.8901 0.9435
No log 7.4375 476 0.8548 0.4915 0.8548 0.9245
No log 7.4688 478 0.7454 0.5894 0.7454 0.8633
No log 7.5 480 0.6929 0.5399 0.6929 0.8324
No log 7.5312 482 0.6979 0.4941 0.6979 0.8354
No log 7.5625 484 0.6965 0.5516 0.6965 0.8346
No log 7.5938 486 0.7315 0.5832 0.7315 0.8553
No log 7.625 488 0.7619 0.5588 0.7619 0.8729
No log 7.6562 490 0.7431 0.5832 0.7431 0.8620
No log 7.6875 492 0.7335 0.5301 0.7335 0.8564
No log 7.7188 494 0.7356 0.5060 0.7356 0.8576
No log 7.75 496 0.7436 0.4707 0.7436 0.8623
No log 7.7812 498 0.7204 0.5302 0.7204 0.8488
0.3063 7.8125 500 0.7113 0.5653 0.7113 0.8434
0.3063 7.8438 502 0.7097 0.5653 0.7097 0.8424
0.3063 7.875 504 0.7052 0.5653 0.7052 0.8398
0.3063 7.9062 506 0.7051 0.5874 0.7051 0.8397
0.3063 7.9375 508 0.7159 0.5874 0.7159 0.8461
0.3063 7.9688 510 0.7224 0.5529 0.7224 0.8499
0.3063 8.0 512 0.7114 0.5529 0.7114 0.8434
0.3063 8.0312 514 0.6931 0.5529 0.6931 0.8325
0.3063 8.0625 516 0.7062 0.6102 0.7062 0.8403
0.3063 8.0938 518 0.7237 0.6003 0.7237 0.8507
0.3063 8.125 520 0.7195 0.5823 0.7195 0.8482
0.3063 8.1562 522 0.6628 0.5032 0.6628 0.8141
0.3063 8.1875 524 0.6858 0.5328 0.6858 0.8281
0.3063 8.2188 526 0.7016 0.4872 0.7016 0.8376
0.3063 8.25 528 0.6897 0.5568 0.6897 0.8305
0.3063 8.2812 530 0.6771 0.5202 0.6771 0.8228

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
1
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_run3_AugV5_k20_task5_organization

Finetuned
(4033)
this model