ArabicNewSplits7_FineTuningAraBERT_run3_AugV5_k18_task3_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: 0.8389
  • Qwk: -0.1051
  • Mse: 0.8389
  • Rmse: 0.9159

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 0.0417 2 3.8561 0.0017 3.8561 1.9637
No log 0.0833 4 2.2122 0.0504 2.2122 1.4874
No log 0.125 6 1.5057 0.0425 1.5057 1.2271
No log 0.1667 8 1.4547 -0.0159 1.4547 1.2061
No log 0.2083 10 2.4269 -0.0318 2.4269 1.5578
No log 0.25 12 1.4429 -0.0207 1.4429 1.2012
No log 0.2917 14 0.7577 -0.0188 0.7577 0.8704
No log 0.3333 16 0.6806 0.0 0.6806 0.8250
No log 0.375 18 0.7776 0.0759 0.7776 0.8818
No log 0.4167 20 0.7610 -0.0679 0.7610 0.8723
No log 0.4583 22 0.7452 -0.0035 0.7452 0.8633
No log 0.5 24 0.8775 -0.0583 0.8775 0.9367
No log 0.5417 26 1.2496 -0.0247 1.2496 1.1179
No log 0.5833 28 1.3808 0.0 1.3808 1.1751
No log 0.625 30 1.2205 0.0 1.2205 1.1048
No log 0.6667 32 1.2570 0.0 1.2570 1.1211
No log 0.7083 34 1.3652 0.0 1.3652 1.1684
No log 0.75 36 1.1904 -0.0247 1.1904 1.0911
No log 0.7917 38 0.9755 -0.0736 0.9755 0.9877
No log 0.8333 40 0.8638 0.0710 0.8638 0.9294
No log 0.875 42 0.7496 0.0 0.7496 0.8658
No log 0.9167 44 0.6932 0.0 0.6932 0.8326
No log 0.9583 46 0.7423 -0.0069 0.7423 0.8615
No log 1.0 48 0.8674 0.0545 0.8674 0.9313
No log 1.0417 50 0.8517 0.0642 0.8517 0.9229
No log 1.0833 52 0.9411 0.0353 0.9411 0.9701
No log 1.125 54 0.8294 -0.0425 0.8294 0.9107
No log 1.1667 56 0.6887 0.0 0.6887 0.8299
No log 1.2083 58 0.7006 -0.0069 0.7006 0.8370
No log 1.25 60 0.6724 0.0 0.6724 0.8200
No log 1.2917 62 0.7290 -0.0160 0.7290 0.8538
No log 1.3333 64 1.0245 -0.0133 1.0245 1.0122
No log 1.375 66 1.3211 -0.0234 1.3211 1.1494
No log 1.4167 68 1.6886 -0.0247 1.6886 1.2995
No log 1.4583 70 1.3238 -0.0247 1.3238 1.1506
No log 1.5 72 1.0028 -0.0207 1.0028 1.0014
No log 1.5417 74 0.8135 -0.0033 0.8135 0.9019
No log 1.5833 76 0.6882 0.0 0.6882 0.8296
No log 1.625 78 0.6640 0.0 0.6640 0.8149
No log 1.6667 80 0.6735 0.0 0.6735 0.8207
No log 1.7083 82 0.6820 0.0 0.6820 0.8258
No log 1.75 84 0.6728 0.0 0.6728 0.8202
No log 1.7917 86 0.7435 -0.0766 0.7435 0.8623
No log 1.8333 88 0.7554 -0.0778 0.7554 0.8691
No log 1.875 90 0.6962 -0.0035 0.6962 0.8344
No log 1.9167 92 0.7361 -0.0240 0.7361 0.8580
No log 1.9583 94 0.8241 0.0017 0.8241 0.9078
No log 2.0 96 0.9818 0.1191 0.9818 0.9909
No log 2.0417 98 0.7076 0.0909 0.7076 0.8412
No log 2.0833 100 0.6494 -0.0069 0.6494 0.8058
No log 2.125 102 0.6634 0.0416 0.6634 0.8145
No log 2.1667 104 1.1348 0.0569 1.1348 1.0653
No log 2.2083 106 1.4112 0.0865 1.4112 1.1880
No log 2.25 108 0.8898 0.0609 0.8898 0.9433
No log 2.2917 110 0.6975 0.0033 0.6975 0.8351
No log 2.3333 112 0.7866 -0.0363 0.7866 0.8869
No log 2.375 114 0.7104 -0.0551 0.7104 0.8429
No log 2.4167 116 0.7336 0.0260 0.7336 0.8565
No log 2.4583 118 0.8667 0.0260 0.8667 0.9310
No log 2.5 120 0.7128 0.1379 0.7128 0.8443
No log 2.5417 122 0.6674 0.0 0.6674 0.8170
No log 2.5833 124 0.7111 0.0999 0.7111 0.8433
No log 2.625 126 0.7262 0.0909 0.7262 0.8522
No log 2.6667 128 0.7734 0.1150 0.7734 0.8794
No log 2.7083 130 0.6730 0.0 0.6730 0.8204
No log 2.75 132 0.7557 0.0099 0.7557 0.8693
No log 2.7917 134 0.7107 -0.0499 0.7107 0.8430
No log 2.8333 136 0.7406 0.0296 0.7406 0.8606
No log 2.875 138 0.7560 0.0375 0.7560 0.8695
No log 2.9167 140 0.7613 0.0557 0.7613 0.8725
No log 2.9583 142 0.8190 0.0310 0.8190 0.9050
No log 3.0 144 0.9283 0.0030 0.9283 0.9635
No log 3.0417 146 0.7981 0.0595 0.7981 0.8934
No log 3.0833 148 0.8321 -0.0260 0.8321 0.9122
No log 3.125 150 0.8195 0.1272 0.8195 0.9053
No log 3.1667 152 0.8601 -0.0089 0.8601 0.9274
No log 3.2083 154 0.8793 -0.0040 0.8793 0.9377
No log 3.25 156 0.7827 0.0644 0.7827 0.8847
No log 3.2917 158 0.7735 0.0028 0.7735 0.8795
No log 3.3333 160 0.7524 -0.0427 0.7524 0.8674
No log 3.375 162 0.7464 -0.0609 0.7464 0.8640
No log 3.4167 164 0.7602 0.0759 0.7602 0.8719
No log 3.4583 166 0.7543 0.1611 0.7543 0.8685
No log 3.5 168 0.7825 0.1995 0.7825 0.8846
No log 3.5417 170 0.8561 0.0330 0.8561 0.9253
No log 3.5833 172 0.8245 0.1358 0.8245 0.9080
No log 3.625 174 0.8662 0.0268 0.8662 0.9307
No log 3.6667 176 0.9539 0.0783 0.9539 0.9767
No log 3.7083 178 0.7941 0.1687 0.7941 0.8911
No log 3.75 180 0.9212 -0.0101 0.9212 0.9598
No log 3.7917 182 0.7575 0.1633 0.7575 0.8704
No log 3.8333 184 0.8312 -0.0063 0.8312 0.9117
No log 3.875 186 0.7652 0.1460 0.7652 0.8747
No log 3.9167 188 0.7799 0.0670 0.7799 0.8831
No log 3.9583 190 0.7434 0.1372 0.7434 0.8622
No log 4.0 192 0.7426 0.0851 0.7426 0.8618
No log 4.0417 194 0.7444 0.1365 0.7444 0.8628
No log 4.0833 196 0.8312 -0.0066 0.8312 0.9117
No log 4.125 198 0.7572 0.1525 0.7572 0.8702
No log 4.1667 200 0.8671 0.0909 0.8671 0.9312
No log 4.2083 202 0.8608 0.0956 0.8608 0.9278
No log 4.25 204 0.7607 0.0652 0.7607 0.8722
No log 4.2917 206 0.8143 0.1176 0.8143 0.9024
No log 4.3333 208 0.7628 0.0652 0.7628 0.8734
No log 4.375 210 0.7508 0.0889 0.7508 0.8665
No log 4.4167 212 0.8383 0.0095 0.8383 0.9156
No log 4.4583 214 0.8239 0.0476 0.8239 0.9077
No log 4.5 216 0.6888 -0.0131 0.6888 0.8300
No log 4.5417 218 0.6632 -0.0069 0.6632 0.8144
No log 4.5833 220 0.6571 0.0460 0.6571 0.8106
No log 4.625 222 0.7147 0.1047 0.7147 0.8454
No log 4.6667 224 0.7226 0.1148 0.7226 0.8500
No log 4.7083 226 0.6530 0.0454 0.6530 0.8081
No log 4.75 228 0.6584 0.0918 0.6584 0.8114
No log 4.7917 230 0.7008 0.0670 0.7008 0.8371
No log 4.8333 232 0.7025 0.0670 0.7025 0.8382
No log 4.875 234 0.6662 0.0828 0.6662 0.8162
No log 4.9167 236 0.7188 0.2498 0.7188 0.8478
No log 4.9583 238 0.8462 0.2055 0.8462 0.9199
No log 5.0 240 0.7442 0.1727 0.7442 0.8627
No log 5.0417 242 0.7385 0.0522 0.7385 0.8594
No log 5.0833 244 0.7815 0.0726 0.7815 0.8840
No log 5.125 246 0.7654 0.0644 0.7654 0.8749
No log 5.1667 248 0.7386 0.0323 0.7386 0.8594
No log 5.2083 250 0.9161 0.0946 0.9161 0.9572
No log 5.25 252 0.7914 0.0639 0.7914 0.8896
No log 5.2917 254 0.7223 0.0513 0.7223 0.8499
No log 5.3333 256 0.7172 0.0513 0.7172 0.8469
No log 5.375 258 0.7417 0.0723 0.7417 0.8612
No log 5.4167 260 0.6829 0.1081 0.6829 0.8264
No log 5.4583 262 0.6679 0.0 0.6679 0.8173
No log 5.5 264 0.6671 0.0 0.6671 0.8167
No log 5.5417 266 0.6632 -0.0035 0.6632 0.8144
No log 5.5833 268 0.7558 0.1342 0.7558 0.8694
No log 5.625 270 0.8604 0.1150 0.8604 0.9276
No log 5.6667 272 0.7133 -0.0056 0.7133 0.8446
No log 5.7083 274 0.8353 0.0420 0.8353 0.9139
No log 5.75 276 0.7775 -0.0173 0.7775 0.8818
No log 5.7917 278 0.7474 -0.0387 0.7474 0.8645
No log 5.8333 280 0.7757 0.1196 0.7757 0.8807
No log 5.875 282 1.0930 0.0353 1.0930 1.0455
No log 5.9167 284 1.1657 0.0260 1.1657 1.0797
No log 5.9583 286 0.7815 0.1965 0.7815 0.8840
No log 6.0 288 0.7269 -0.0892 0.7269 0.8526
No log 6.0417 290 0.7272 -0.0892 0.7272 0.8528
No log 6.0833 292 0.7202 0.0296 0.7202 0.8486
No log 6.125 294 0.8469 0.0984 0.8469 0.9203
No log 6.1667 296 0.8300 0.1196 0.8300 0.9110
No log 6.2083 298 0.7091 -0.0449 0.7091 0.8421
No log 6.25 300 0.7835 0.0328 0.7835 0.8851
No log 6.2917 302 0.7588 0.0251 0.7588 0.8711
No log 6.3333 304 0.6839 -0.0069 0.6839 0.8270
No log 6.375 306 0.7320 0.0670 0.7320 0.8556
No log 6.4167 308 0.7332 0.0680 0.7332 0.8563
No log 6.4583 310 0.7076 0.0 0.7076 0.8412
No log 6.5 312 0.7438 0.0187 0.7438 0.8624
No log 6.5417 314 0.7582 0.0187 0.7582 0.8708
No log 6.5833 316 0.6979 0.1404 0.6979 0.8354
No log 6.625 318 0.8554 0.1107 0.8554 0.9249
No log 6.6667 320 0.9259 0.0431 0.9259 0.9623
No log 6.7083 322 0.6855 0.1879 0.6855 0.8280
No log 6.75 324 0.6841 0.0685 0.6841 0.8271
No log 6.7917 326 0.8534 0.0481 0.8534 0.9238
No log 6.8333 328 0.8139 -0.0289 0.8139 0.9022
No log 6.875 330 0.6630 0.1081 0.6630 0.8142
No log 6.9167 332 0.6792 0.1565 0.6792 0.8242
No log 6.9583 334 0.9634 0.1077 0.9634 0.9815
No log 7.0 336 1.1507 0.0176 1.1507 1.0727
No log 7.0417 338 0.8826 0.1360 0.8826 0.9395
No log 7.0833 340 0.6927 0.0863 0.6927 0.8323
No log 7.125 342 0.7773 -0.0063 0.7773 0.8816
No log 7.1667 344 0.7836 0.0331 0.7836 0.8852
No log 7.2083 346 0.6995 0.0976 0.6995 0.8364
No log 7.25 348 0.7046 -0.0152 0.7046 0.8394
No log 7.2917 350 0.7368 0.0714 0.7368 0.8584
No log 7.3333 352 0.7449 0.0714 0.7449 0.8631
No log 7.375 354 0.7150 0.0357 0.7150 0.8456
No log 7.4167 356 0.7522 0.1033 0.7522 0.8673
No log 7.4583 358 0.7716 0.0664 0.7716 0.8784
No log 7.5 360 0.7844 0.0710 0.7844 0.8856
No log 7.5417 362 0.7650 0.0187 0.7650 0.8747
No log 7.5833 364 0.8461 0.0111 0.8461 0.9199
No log 7.625 366 0.8391 0.0418 0.8391 0.9160
No log 7.6667 368 0.7405 0.0622 0.7405 0.8605
No log 7.7083 370 0.7376 0.0116 0.7376 0.8588
No log 7.75 372 0.7396 -0.0427 0.7396 0.8600
No log 7.7917 374 0.7480 -0.0366 0.7480 0.8649
No log 7.8333 376 0.7477 -0.0513 0.7477 0.8647
No log 7.875 378 0.7994 -0.0606 0.7994 0.8941
No log 7.9167 380 0.8403 -0.0761 0.8403 0.9167
No log 7.9583 382 0.8686 -0.0317 0.8686 0.9320
No log 8.0 384 0.7890 0.0281 0.7890 0.8883
No log 8.0417 386 0.7685 0.1646 0.7685 0.8767
No log 8.0833 388 0.7917 0.1633 0.7917 0.8898
No log 8.125 390 0.8927 0.0673 0.8927 0.9448
No log 8.1667 392 0.9819 0.1044 0.9819 0.9909
No log 8.2083 394 0.9589 0.1044 0.9589 0.9793
No log 8.25 396 0.8499 -0.0014 0.8499 0.9219
No log 8.2917 398 0.7482 0.0983 0.7482 0.8650
No log 8.3333 400 0.7506 0.1298 0.7506 0.8664
No log 8.375 402 0.7843 0.0179 0.7843 0.8856
No log 8.4167 404 0.9214 0.0440 0.9214 0.9599
No log 8.4583 406 0.8835 0.0086 0.8835 0.9400
No log 8.5 408 0.7429 0.0518 0.7429 0.8619
No log 8.5417 410 0.7233 0.1612 0.7233 0.8505
No log 8.5833 412 0.7338 0.0376 0.7338 0.8566
No log 8.625 414 0.8131 0.0281 0.8131 0.9017
No log 8.6667 416 0.9902 0.0134 0.9902 0.9951
No log 8.7083 418 1.0090 0.0134 1.0090 1.0045
No log 8.75 420 0.9872 0.0426 0.9872 0.9936
No log 8.7917 422 0.8568 -0.0128 0.8568 0.9256
No log 8.8333 424 0.8282 0.0074 0.8282 0.9100
No log 8.875 426 0.8260 -0.0300 0.8260 0.9088
No log 8.9167 428 0.8810 0.1039 0.8810 0.9386
No log 8.9583 430 0.9317 0.0753 0.9317 0.9653
No log 9.0 432 0.8155 -0.0195 0.8155 0.9031
No log 9.0417 434 0.7343 -0.0032 0.7343 0.8569
No log 9.0833 436 0.7080 0.0967 0.7080 0.8414
No log 9.125 438 0.7151 0.1024 0.7151 0.8457
No log 9.1667 440 0.7136 0.0967 0.7136 0.8447
No log 9.2083 442 0.7144 0.0967 0.7144 0.8452
No log 9.25 444 0.7097 -0.1040 0.7097 0.8424
No log 9.2917 446 0.7397 0.1031 0.7397 0.8600
No log 9.3333 448 0.8305 0.1536 0.8305 0.9113
No log 9.375 450 0.8844 0.1118 0.8844 0.9404
No log 9.4167 452 0.7917 0.1451 0.7917 0.8898
No log 9.4583 454 0.7824 0.1550 0.7824 0.8845
No log 9.5 456 0.8074 0.1268 0.8074 0.8986
No log 9.5417 458 0.7614 0.0688 0.7614 0.8726
No log 9.5833 460 0.7344 0.0898 0.7344 0.8570
No log 9.625 462 0.7865 0.1724 0.7865 0.8868
No log 9.6667 464 0.7599 0.0866 0.7599 0.8717
No log 9.7083 466 0.7379 0.2345 0.7379 0.8590
No log 9.75 468 0.7558 0.1981 0.7558 0.8694
No log 9.7917 470 0.8318 0.1426 0.8318 0.9120
No log 9.8333 472 0.9763 0.0451 0.9763 0.9881
No log 9.875 474 1.0301 0.1108 1.0301 1.0149
No log 9.9167 476 0.8775 -0.0707 0.8775 0.9368
No log 9.9583 478 0.7405 0.0323 0.7405 0.8605
No log 10.0 480 0.8330 0.0676 0.8330 0.9127
No log 10.0417 482 0.9766 -0.0269 0.9766 0.9882
No log 10.0833 484 0.9184 -0.0236 0.9184 0.9583
No log 10.125 486 0.7990 0.0676 0.7990 0.8939
No log 10.1667 488 0.7116 0.1318 0.7116 0.8436
No log 10.2083 490 0.7282 0.0528 0.7282 0.8533
No log 10.25 492 0.7284 0.1030 0.7284 0.8534
No log 10.2917 494 0.7224 0.0768 0.7224 0.8499
No log 10.3333 496 0.7663 0.0999 0.7663 0.8754
No log 10.375 498 0.7470 0.0953 0.7470 0.8643
0.3738 10.4167 500 0.7335 -0.0179 0.7335 0.8564
0.3738 10.4583 502 0.7563 0.0541 0.7563 0.8697
0.3738 10.5 504 0.7609 0.0587 0.7609 0.8723
0.3738 10.5417 506 0.7386 0.0571 0.7386 0.8594
0.3738 10.5833 508 0.7241 -0.0160 0.7241 0.8509
0.3738 10.625 510 0.8123 0.0867 0.8123 0.9013
0.3738 10.6667 512 0.8378 0.1107 0.8378 0.9153
0.3738 10.7083 514 0.8071 0.1196 0.8071 0.8984
0.3738 10.75 516 0.7327 0.0428 0.7327 0.8560
0.3738 10.7917 518 0.7525 0.0110 0.7525 0.8675
0.3738 10.8333 520 0.7825 0.1079 0.7825 0.8846
0.3738 10.875 522 0.7497 0.0595 0.7497 0.8659
0.3738 10.9167 524 0.7304 0.0978 0.7304 0.8546
0.3738 10.9583 526 0.7149 0.1081 0.7149 0.8455
0.3738 11.0 528 0.6953 0.1023 0.6953 0.8338
0.3738 11.0417 530 0.6917 0.0296 0.6917 0.8317
0.3738 11.0833 532 0.6683 0.1023 0.6683 0.8175
0.3738 11.125 534 0.6609 0.1023 0.6609 0.8129
0.3738 11.1667 536 0.6595 0.0967 0.6595 0.8121
0.3738 11.2083 538 0.6905 0.1148 0.6905 0.8310
0.3738 11.25 540 0.7627 0.0867 0.7627 0.8733
0.3738 11.2917 542 0.6835 0.1722 0.6835 0.8268
0.3738 11.3333 544 0.7092 0.1079 0.7092 0.8421
0.3738 11.375 546 0.7525 0.1079 0.7525 0.8675
0.3738 11.4167 548 0.7248 0.1470 0.7248 0.8513
0.3738 11.4583 550 0.7522 0.1030 0.7522 0.8673
0.3738 11.5 552 0.7147 0.1027 0.7147 0.8454
0.3738 11.5417 554 0.6651 0.1379 0.6651 0.8155
0.3738 11.5833 556 0.6853 0.1627 0.6853 0.8278
0.3738 11.625 558 0.6747 0.0759 0.6747 0.8214
0.3738 11.6667 560 0.6610 0.1444 0.6610 0.8130
0.3738 11.7083 562 0.6671 0.0964 0.6671 0.8167
0.3738 11.75 564 0.6835 0.1318 0.6835 0.8268
0.3738 11.7917 566 0.6943 0.0759 0.6943 0.8332
0.3738 11.8333 568 0.6908 -0.0086 0.6908 0.8311
0.3738 11.875 570 0.7300 0.0985 0.7300 0.8544
0.3738 11.9167 572 0.7252 0.0985 0.7252 0.8516
0.3738 11.9583 574 0.7278 0.0545 0.7278 0.8531
0.3738 12.0 576 0.6995 0.1347 0.6995 0.8364
0.3738 12.0417 578 0.6800 0.1144 0.6800 0.8246
0.3738 12.0833 580 0.6844 0.1449 0.6844 0.8273
0.3738 12.125 582 0.6747 0.1254 0.6747 0.8214
0.3738 12.1667 584 0.6843 0.0834 0.6843 0.8272
0.3738 12.2083 586 0.7401 0.1786 0.7401 0.8603
0.3738 12.25 588 0.7092 0.1372 0.7092 0.8422
0.3738 12.2917 590 0.6971 0.0357 0.6971 0.8349
0.3738 12.3333 592 0.7158 0.0893 0.7158 0.8460
0.3738 12.375 594 0.7881 0.1003 0.7881 0.8878
0.3738 12.4167 596 0.9135 0.1043 0.9135 0.9558
0.3738 12.4583 598 0.9038 0.0753 0.9038 0.9507
0.3738 12.5 600 0.8371 -0.0473 0.8371 0.9149
0.3738 12.5417 602 0.7679 -0.0810 0.7679 0.8763
0.3738 12.5833 604 0.7361 0.0869 0.7361 0.8579
0.3738 12.625 606 0.7435 0.0214 0.7435 0.8623
0.3738 12.6667 608 0.7420 0.0821 0.7420 0.8614
0.3738 12.7083 610 0.7450 0.0869 0.7450 0.8631
0.3738 12.75 612 0.7540 0.0027 0.7540 0.8684
0.3738 12.7917 614 0.7698 -0.0387 0.7698 0.8774
0.3738 12.8333 616 0.7417 -0.0427 0.7417 0.8612
0.3738 12.875 618 0.7207 0.1024 0.7207 0.8489
0.3738 12.9167 620 0.7185 0.0541 0.7185 0.8477
0.3738 12.9583 622 0.7336 0.0 0.7336 0.8565
0.3738 13.0 624 0.7859 -0.1208 0.7859 0.8865
0.3738 13.0417 626 0.8518 -0.0904 0.8518 0.9230
0.3738 13.0833 628 0.8858 -0.1647 0.8858 0.9412
0.3738 13.125 630 0.8728 -0.1299 0.8728 0.9342
0.3738 13.1667 632 0.8389 -0.1051 0.8389 0.9159

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/ArabicNewSplits7_FineTuningAraBERT_run3_AugV5_k18_task3_organization

Finetuned
(4023)
this model