ArabicNewSplits7_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k7_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: 0.7612
  • Qwk: -0.0599
  • Mse: 0.7612
  • Rmse: 0.8725

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 0.1111 2 3.6004 -0.0058 3.6004 1.8975
No log 0.2222 4 2.0616 0.0672 2.0616 1.4358
No log 0.3333 6 2.0090 0.0104 2.0090 1.4174
No log 0.4444 8 1.2097 -0.0457 1.2097 1.0999
No log 0.5556 10 0.8553 -0.0008 0.8553 0.9248
No log 0.6667 12 0.8565 -0.0442 0.8565 0.9255
No log 0.7778 14 0.9952 0.0282 0.9952 0.9976
No log 0.8889 16 1.1332 -0.0500 1.1332 1.0645
No log 1.0 18 1.1442 0.0 1.1442 1.0697
No log 1.1111 20 1.1414 0.0298 1.1414 1.0683
No log 1.2222 22 1.0610 0.0100 1.0610 1.0300
No log 1.3333 24 1.0351 0.0100 1.0351 1.0174
No log 1.4444 26 1.0997 0.0317 1.0997 1.0487
No log 1.5556 28 1.0542 -0.0193 1.0542 1.0267
No log 1.6667 30 0.8201 -0.0371 0.8201 0.9056
No log 1.7778 32 0.7336 -0.0101 0.7336 0.8565
No log 1.8889 34 0.8929 -0.0122 0.8929 0.9449
No log 2.0 36 1.2237 -0.0736 1.2237 1.1062
No log 2.1111 38 1.4392 -0.0207 1.4392 1.1997
No log 2.2222 40 1.2051 -0.0446 1.2051 1.0978
No log 2.3333 42 1.0704 -0.0149 1.0704 1.0346
No log 2.4444 44 1.3189 -0.0207 1.3189 1.1484
No log 2.5556 46 1.3857 -0.0234 1.3857 1.1772
No log 2.6667 48 1.1274 -0.0234 1.1274 1.0618
No log 2.7778 50 1.0728 -0.0193 1.0728 1.0357
No log 2.8889 52 0.9278 0.0207 0.9278 0.9632
No log 3.0 54 0.8682 0.0123 0.8682 0.9318
No log 3.1111 56 0.9521 -0.1221 0.9521 0.9758
No log 3.2222 58 1.1967 -0.0334 1.1967 1.0940
No log 3.3333 60 0.8753 -0.0283 0.8753 0.9356
No log 3.4444 62 0.7331 0.0 0.7331 0.8562
No log 3.5556 64 0.7588 -0.0520 0.7588 0.8711
No log 3.6667 66 0.9085 -0.0008 0.9085 0.9532
No log 3.7778 68 1.0157 -0.0862 1.0157 1.0078
No log 3.8889 70 1.0336 -0.0526 1.0336 1.0167
No log 4.0 72 0.9215 -0.1209 0.9215 0.9599
No log 4.1111 74 0.8238 -0.0627 0.8238 0.9076
No log 4.2222 76 0.8080 -0.0541 0.8080 0.8989
No log 4.3333 78 0.8227 -0.1535 0.8227 0.9070
No log 4.4444 80 1.0018 -0.0378 1.0018 1.0009
No log 4.5556 82 0.9420 -0.1572 0.9420 0.9706
No log 4.6667 84 0.8280 -0.1616 0.8280 0.9099
No log 4.7778 86 0.8147 -0.1616 0.8147 0.9026
No log 4.8889 88 0.8291 -0.1094 0.8291 0.9106
No log 5.0 90 0.8432 0.0260 0.8432 0.9183
No log 5.1111 92 0.8034 0.0334 0.8034 0.8963
No log 5.2222 94 0.8100 -0.1628 0.8100 0.9000
No log 5.3333 96 0.8231 -0.1001 0.8231 0.9072
No log 5.4444 98 0.8201 -0.0583 0.8201 0.9056
No log 5.5556 100 0.8312 -0.0599 0.8312 0.9117
No log 5.6667 102 0.8288 -0.1547 0.8288 0.9104
No log 5.7778 104 0.8548 -0.1001 0.8548 0.9246
No log 5.8889 106 0.8404 -0.0949 0.8404 0.9167
No log 6.0 108 0.8178 -0.0949 0.8178 0.9043
No log 6.1111 110 0.8656 0.0155 0.8656 0.9304
No log 6.2222 112 0.8236 -0.0385 0.8236 0.9075
No log 6.3333 114 0.7791 -0.1060 0.7791 0.8827
No log 6.4444 116 0.8057 -0.0449 0.8057 0.8976
No log 6.5556 118 0.9651 -0.0066 0.9651 0.9824
No log 6.6667 120 0.8794 -0.0385 0.8794 0.9378
No log 6.7778 122 0.8848 0.0089 0.8848 0.9406
No log 6.8889 124 0.9020 0.0089 0.9020 0.9498
No log 7.0 126 0.9570 -0.0591 0.9570 0.9783
No log 7.1111 128 0.8807 -0.0449 0.8807 0.9385
No log 7.2222 130 0.8375 -0.0513 0.8375 0.9151
No log 7.3333 132 0.8209 -0.1521 0.8209 0.9061
No log 7.4444 134 0.7955 -0.0513 0.7955 0.8919
No log 7.5556 136 0.8534 -0.0406 0.8534 0.9238
No log 7.6667 138 0.8335 -0.1001 0.8335 0.9130
No log 7.7778 140 0.7806 -0.1018 0.7806 0.8835
No log 7.8889 142 0.7781 -0.1018 0.7781 0.8821
No log 8.0 144 0.8628 -0.0385 0.8628 0.9289
No log 8.1111 146 0.9878 0.0072 0.9878 0.9939
No log 8.2222 148 0.8654 0.0622 0.8654 0.9303
No log 8.3333 150 0.8790 0.0633 0.8790 0.9376
No log 8.4444 152 1.0912 0.0558 1.0912 1.0446
No log 8.5556 154 1.1485 0.0044 1.1485 1.0717
No log 8.6667 156 0.9953 0.0446 0.9953 0.9977
No log 8.7778 158 0.8150 -0.1040 0.8150 0.9028
No log 8.8889 160 0.7844 -0.0513 0.7844 0.8857
No log 9.0 162 0.8172 -0.1001 0.8172 0.9040
No log 9.1111 164 0.8700 -0.0406 0.8700 0.9327
No log 9.2222 166 0.8724 -0.0406 0.8724 0.9340
No log 9.3333 168 0.7729 -0.0473 0.7729 0.8792
No log 9.4444 170 0.8171 -0.0351 0.8171 0.9039
No log 9.5556 172 0.8307 0.0071 0.8307 0.9114
No log 9.6667 174 0.7809 -0.1033 0.7809 0.8837
No log 9.7778 176 1.0864 0.0845 1.0864 1.0423
No log 9.8889 178 1.2563 -0.0411 1.2563 1.1208
No log 10.0 180 1.2147 -0.0478 1.2147 1.1021
No log 10.1111 182 0.9902 -0.0317 0.9902 0.9951
No log 10.2222 184 0.8103 -0.1040 0.8103 0.9002
No log 10.3333 186 0.8016 -0.1033 0.8016 0.8953
No log 10.4444 188 0.8199 -0.1538 0.8199 0.9055
No log 10.5556 190 0.8889 -0.1399 0.8889 0.9428
No log 10.6667 192 0.9169 -0.1201 0.9169 0.9575
No log 10.7778 194 0.9971 -0.0934 0.9971 0.9985
No log 10.8889 196 1.0062 -0.0843 1.0062 1.0031
No log 11.0 198 0.8853 -0.1893 0.8853 0.9409
No log 11.1111 200 0.8711 -0.0251 0.8711 0.9334
No log 11.2222 202 0.8409 -0.0209 0.8409 0.9170
No log 11.3333 204 0.8096 -0.1033 0.8096 0.8998
No log 11.4444 206 0.8798 -0.1001 0.8798 0.9380
No log 11.5556 208 0.9217 -0.1142 0.9217 0.9601
No log 11.6667 210 0.8226 -0.1473 0.8226 0.9069
No log 11.7778 212 0.7562 -0.0513 0.7562 0.8696
No log 11.8889 214 0.7978 -0.0513 0.7978 0.8932
No log 12.0 216 0.8445 -0.0513 0.8445 0.9190
No log 12.1111 218 0.9257 -0.1535 0.9257 0.9622
No log 12.2222 220 0.9362 -0.0591 0.9362 0.9676
No log 12.3333 222 0.8986 -0.1753 0.8986 0.9480
No log 12.4444 224 0.8775 -0.1329 0.8775 0.9368
No log 12.5556 226 0.8601 -0.1905 0.8601 0.9274
No log 12.6667 228 0.8963 -0.0774 0.8963 0.9467
No log 12.7778 230 0.9178 -0.0774 0.9178 0.9580
No log 12.8889 232 0.9245 -0.0774 0.9245 0.9615
No log 13.0 234 0.9098 -0.0774 0.9098 0.9538
No log 13.1111 236 0.8440 -0.1547 0.8440 0.9187
No log 13.2222 238 0.8287 -0.0532 0.8287 0.9103
No log 13.3333 240 0.8579 -0.1001 0.8579 0.9262
No log 13.4444 242 0.9082 -0.0284 0.9082 0.9530
No log 13.5556 244 0.9435 0.0749 0.9435 0.9713
No log 13.6667 246 0.8809 -0.0363 0.8809 0.9386
No log 13.7778 248 0.8143 -0.1018 0.8143 0.9024
No log 13.8889 250 0.8568 -0.0363 0.8568 0.9257
No log 14.0 252 0.9783 0.0805 0.9783 0.9891
No log 14.1111 254 0.9529 0.1157 0.9529 0.9762
No log 14.2222 256 0.8095 -0.0958 0.8095 0.8997
No log 14.3333 258 0.7735 -0.1018 0.7735 0.8795
No log 14.4444 260 0.8497 -0.0363 0.8497 0.9218
No log 14.5556 262 0.9512 0.0345 0.9512 0.9753
No log 14.6667 264 0.9005 -0.0724 0.9005 0.9490
No log 14.7778 266 0.8158 -0.0939 0.8158 0.9032
No log 14.8889 268 0.7825 -0.1018 0.7825 0.8846
No log 15.0 270 0.8377 -0.1833 0.8377 0.9153
No log 15.1111 272 0.9509 0.0092 0.9509 0.9752
No log 15.2222 274 0.9874 0.0492 0.9874 0.9937
No log 15.3333 276 0.9095 0.0331 0.9095 0.9537
No log 15.4444 278 0.8686 -0.1851 0.8686 0.9320
No log 15.5556 280 0.8561 -0.1851 0.8561 0.9253
No log 15.6667 282 0.8525 -0.1397 0.8525 0.9233
No log 15.7778 284 0.8897 -0.1474 0.8897 0.9432
No log 15.8889 286 0.8534 -0.0406 0.8534 0.9238
No log 16.0 288 0.7757 -0.1001 0.7757 0.8808
No log 16.1111 290 0.7354 -0.1111 0.7354 0.8575
No log 16.2222 292 0.7367 -0.0690 0.7367 0.8583
No log 16.3333 294 0.7376 -0.0513 0.7376 0.8589
No log 16.4444 296 0.8600 -0.0363 0.8600 0.9274
No log 16.5556 298 0.9953 -0.1099 0.9953 0.9977
No log 16.6667 300 1.0160 -0.0970 1.0160 1.0079
No log 16.7778 302 0.9052 0.0345 0.9052 0.9514
No log 16.8889 304 0.8396 0.0173 0.8396 0.9163
No log 17.0 306 0.8046 -0.0892 0.8046 0.8970
No log 17.1111 308 0.7874 -0.0892 0.7874 0.8873
No log 17.2222 310 0.8263 -0.1399 0.8263 0.9090
No log 17.3333 312 0.8186 -0.0786 0.8186 0.9048
No log 17.4444 314 0.7962 -0.0786 0.7962 0.8923
No log 17.5556 316 0.8798 -0.0089 0.8798 0.9380
No log 17.6667 318 0.8762 0.1124 0.8762 0.9361
No log 17.7778 320 0.9284 0.0754 0.9284 0.9636
No log 17.8889 322 0.9152 0.0315 0.9152 0.9566
No log 18.0 324 0.8337 -0.0837 0.8337 0.9131
No log 18.1111 326 0.7672 -0.0532 0.7672 0.8759
No log 18.2222 328 0.7455 -0.0550 0.7455 0.8634
No log 18.3333 330 0.7492 -0.0473 0.7492 0.8656
No log 18.4444 332 0.7681 -0.1001 0.7681 0.8764
No log 18.5556 334 0.7615 -0.1001 0.7615 0.8726
No log 18.6667 336 0.7684 -0.1001 0.7684 0.8766
No log 18.7778 338 0.8064 -0.1001 0.8064 0.8980
No log 18.8889 340 0.8532 -0.0406 0.8532 0.9237
No log 19.0 342 0.8500 -0.0406 0.8500 0.9220
No log 19.1111 344 0.7700 -0.0473 0.7700 0.8775
No log 19.2222 346 0.7593 -0.0218 0.7593 0.8714
No log 19.3333 348 0.7562 0.0205 0.7562 0.8696
No log 19.4444 350 0.7383 -0.0030 0.7383 0.8593
No log 19.5556 352 0.7820 -0.0345 0.7820 0.8843
No log 19.6667 354 0.8049 -0.0237 0.8049 0.8971
No log 19.7778 356 0.7885 -0.0837 0.7885 0.8880
No log 19.8889 358 0.7236 0.0031 0.7236 0.8506
No log 20.0 360 0.7248 0.0571 0.7248 0.8513
No log 20.1111 362 0.7588 -0.0345 0.7588 0.8711
No log 20.2222 364 0.7800 0.0148 0.7800 0.8832
No log 20.3333 366 0.7509 -0.0473 0.7509 0.8666
No log 20.4444 368 0.7295 -0.0473 0.7295 0.8541
No log 20.5556 370 0.7319 -0.1001 0.7319 0.8555
No log 20.6667 372 0.7460 -0.0473 0.7460 0.8637
No log 20.7778 374 0.7748 0.0628 0.7748 0.8802
No log 20.8889 376 0.7577 -0.0473 0.7577 0.8704
No log 21.0 378 0.7038 0.0 0.7038 0.8389
No log 21.1111 380 0.6863 0.0 0.6863 0.8284
No log 21.2222 382 0.7303 -0.0473 0.7303 0.8546
No log 21.3333 384 0.8142 0.0155 0.8142 0.9023
No log 21.4444 386 0.8678 0.1185 0.8678 0.9315
No log 21.5556 388 0.8575 0.0705 0.8575 0.9260
No log 21.6667 390 0.7587 0.0571 0.7587 0.8711
No log 21.7778 392 0.7250 0.0031 0.7250 0.8515
No log 21.8889 394 0.7503 0.0031 0.7503 0.8662
No log 22.0 396 0.8214 0.1185 0.8214 0.9063
No log 22.1111 398 0.8131 -0.0406 0.8131 0.9017
No log 22.2222 400 0.7394 0.0031 0.7394 0.8599
No log 22.3333 402 0.7260 0.0031 0.7260 0.8521
No log 22.4444 404 0.7690 -0.1001 0.7690 0.8770
No log 22.5556 406 0.7823 -0.1001 0.7823 0.8845
No log 22.6667 408 0.8109 -0.1001 0.8109 0.9005
No log 22.7778 410 0.8158 -0.1001 0.8158 0.9032
No log 22.8889 412 0.8169 -0.1001 0.8169 0.9038
No log 23.0 414 0.7754 -0.1001 0.7754 0.8806
No log 23.1111 416 0.8037 -0.0406 0.8037 0.8965
No log 23.2222 418 0.8417 0.0685 0.8417 0.9174
No log 23.3333 420 0.8185 0.0155 0.8185 0.9047
No log 23.4444 422 0.7829 -0.1001 0.7829 0.8848
No log 23.5556 424 0.7509 -0.1001 0.7509 0.8666
No log 23.6667 426 0.7480 -0.0473 0.7480 0.8649
No log 23.7778 428 0.7509 -0.0473 0.7509 0.8665
No log 23.8889 430 0.7809 -0.1001 0.7809 0.8837
No log 24.0 432 0.8022 0.0181 0.8022 0.8956
No log 24.1111 434 0.8066 -0.0284 0.8066 0.8981
No log 24.2222 436 0.7715 -0.0473 0.7715 0.8783
No log 24.3333 438 0.7398 0.0031 0.7398 0.8601
No log 24.4444 440 0.7530 -0.1001 0.7530 0.8678
No log 24.5556 442 0.7762 -0.0406 0.7762 0.8810
No log 24.6667 444 0.7814 -0.0406 0.7814 0.8839
No log 24.7778 446 0.7488 -0.0406 0.7488 0.8653
No log 24.8889 448 0.7282 -0.1001 0.7282 0.8533
No log 25.0 450 0.7152 -0.0473 0.7152 0.8457
No log 25.1111 452 0.7336 0.0357 0.7336 0.8565
No log 25.2222 454 0.7567 0.1003 0.7567 0.8699
No log 25.3333 456 0.7346 0.0 0.7346 0.8571
No log 25.4444 458 0.7894 0.0155 0.7894 0.8885
No log 25.5556 460 0.8018 0.0181 0.8018 0.8954
No log 25.6667 462 0.7610 -0.0406 0.7610 0.8724
No log 25.7778 464 0.7063 0.0031 0.7063 0.8404
No log 25.8889 466 0.7064 -0.0059 0.7064 0.8405
No log 26.0 468 0.7160 0.0031 0.7160 0.8461
No log 26.1111 470 0.7137 0.0471 0.7137 0.8448
No log 26.2222 472 0.7093 0.0031 0.7093 0.8422
No log 26.3333 474 0.7318 -0.0428 0.7318 0.8555
No log 26.4444 476 0.7430 0.0094 0.7430 0.8620
No log 26.5556 478 0.7359 -0.0473 0.7359 0.8578
No log 26.6667 480 0.7501 -0.0406 0.7501 0.8661
No log 26.7778 482 0.7358 -0.0473 0.7358 0.8578
No log 26.8889 484 0.7475 0.0031 0.7475 0.8646
No log 27.0 486 0.7458 0.0031 0.7458 0.8636
No log 27.1111 488 0.7611 0.0031 0.7611 0.8724
No log 27.2222 490 0.7680 0.0 0.7680 0.8764
No log 27.3333 492 0.7669 -0.0550 0.7669 0.8757
No log 27.4444 494 0.7892 0.1080 0.7892 0.8884
No log 27.5556 496 0.8456 0.0683 0.8456 0.9196
No log 27.6667 498 0.8572 0.0229 0.8572 0.9259
0.243 27.7778 500 0.8039 0.0155 0.8039 0.8966
0.243 27.8889 502 0.7577 -0.0473 0.7577 0.8705
0.243 28.0 504 0.7493 0.0 0.7493 0.8656
0.243 28.1111 506 0.7442 -0.0030 0.7442 0.8627
0.243 28.2222 508 0.7627 0.0 0.7627 0.8733
0.243 28.3333 510 0.8487 0.0173 0.8487 0.9213
0.243 28.4444 512 0.9392 -0.0066 0.9392 0.9691
0.243 28.5556 514 0.9048 0.0733 0.9048 0.9512
0.243 28.6667 516 0.8137 0.1080 0.8137 0.9021
0.243 28.7778 518 0.7676 -0.0030 0.7676 0.8761
0.243 28.8889 520 0.7697 -0.0086 0.7697 0.8773
0.243 29.0 522 0.7769 -0.0163 0.7769 0.8814
0.243 29.1111 524 0.7736 -0.0163 0.7736 0.8796
0.243 29.2222 526 0.7612 -0.0599 0.7612 0.8725

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_usingWellWrittenEssays_FineTuningAraBERT_run1_AugV5_k7_task3_organization

Finetuned
(4019)
this model