ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run1_AugV5_k7_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: 0.8116
  • Qwk: 0.6542
  • Mse: 0.8116
  • Rmse: 0.9009

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 0.0571 2 4.8301 -0.0139 4.8301 2.1977
No log 0.1143 4 3.4755 0.0557 3.4755 1.8643
No log 0.1714 6 1.9547 0.0903 1.9547 1.3981
No log 0.2286 8 1.7802 0.0012 1.7802 1.3343
No log 0.2857 10 1.7813 -0.0415 1.7813 1.3347
No log 0.3429 12 1.3205 0.1558 1.3205 1.1491
No log 0.4 14 1.2643 0.1397 1.2643 1.1244
No log 0.4571 16 1.2486 0.1838 1.2486 1.1174
No log 0.5143 18 1.3135 0.1341 1.3135 1.1461
No log 0.5714 20 1.5843 0.0512 1.5843 1.2587
No log 0.6286 22 1.9644 0.1145 1.9644 1.4016
No log 0.6857 24 1.8388 0.1134 1.8388 1.3560
No log 0.7429 26 1.3855 0.1613 1.3855 1.1771
No log 0.8 28 1.1668 0.2863 1.1668 1.0802
No log 0.8571 30 1.1128 0.3951 1.1128 1.0549
No log 0.9143 32 1.0642 0.3158 1.0642 1.0316
No log 0.9714 34 1.0518 0.3260 1.0518 1.0256
No log 1.0286 36 1.0338 0.3342 1.0338 1.0168
No log 1.0857 38 1.1622 0.3109 1.1622 1.0781
No log 1.1429 40 1.5363 0.2225 1.5363 1.2395
No log 1.2 42 1.9840 0.1969 1.9840 1.4085
No log 1.2571 44 1.6018 0.2368 1.6018 1.2656
No log 1.3143 46 1.0869 0.3716 1.0869 1.0425
No log 1.3714 48 1.0029 0.3903 1.0029 1.0014
No log 1.4286 50 0.9969 0.3434 0.9969 0.9984
No log 1.4857 52 1.0069 0.3618 1.0069 1.0035
No log 1.5429 54 0.9901 0.3618 0.9901 0.9951
No log 1.6 56 0.9612 0.3701 0.9612 0.9804
No log 1.6571 58 0.9418 0.4229 0.9418 0.9705
No log 1.7143 60 1.0318 0.4319 1.0318 1.0158
No log 1.7714 62 1.1839 0.3525 1.1839 1.0881
No log 1.8286 64 1.4545 0.3231 1.4545 1.2060
No log 1.8857 66 1.7645 0.3329 1.7645 1.3283
No log 1.9429 68 1.5304 0.3259 1.5304 1.2371
No log 2.0 70 1.1144 0.4215 1.1144 1.0557
No log 2.0571 72 0.8173 0.5083 0.8173 0.9040
No log 2.1143 74 0.8264 0.4342 0.8264 0.9091
No log 2.1714 76 0.9104 0.4135 0.9104 0.9541
No log 2.2286 78 0.7911 0.4945 0.7911 0.8894
No log 2.2857 80 0.8557 0.5591 0.8557 0.9250
No log 2.3429 82 0.8289 0.5651 0.8289 0.9104
No log 2.4 84 0.7993 0.5390 0.7993 0.8940
No log 2.4571 86 0.7523 0.5980 0.7523 0.8673
No log 2.5143 88 0.7797 0.6565 0.7797 0.8830
No log 2.5714 90 0.8498 0.6094 0.8498 0.9218
No log 2.6286 92 0.7474 0.6595 0.7474 0.8645
No log 2.6857 94 0.7802 0.6745 0.7802 0.8833
No log 2.7429 96 0.7969 0.6910 0.7969 0.8927
No log 2.8 98 0.8034 0.6680 0.8034 0.8963
No log 2.8571 100 0.7433 0.6851 0.7433 0.8621
No log 2.9143 102 0.7495 0.6430 0.7495 0.8657
No log 2.9714 104 0.7427 0.6791 0.7427 0.8618
No log 3.0286 106 0.8639 0.6236 0.8639 0.9295
No log 3.0857 108 0.9621 0.5550 0.9621 0.9809
No log 3.1429 110 0.8497 0.5826 0.8497 0.9218
No log 3.2 112 0.7488 0.6477 0.7488 0.8653
No log 3.2571 114 0.7292 0.6570 0.7292 0.8539
No log 3.3143 116 0.7213 0.6736 0.7213 0.8493
No log 3.3714 118 0.6914 0.6522 0.6914 0.8315
No log 3.4286 120 0.7076 0.6699 0.7076 0.8412
No log 3.4857 122 0.7127 0.6608 0.7127 0.8442
No log 3.5429 124 0.7295 0.6704 0.7295 0.8541
No log 3.6 126 0.8055 0.6690 0.8055 0.8975
No log 3.6571 128 0.7538 0.7118 0.7538 0.8682
No log 3.7143 130 0.8400 0.6518 0.8400 0.9165
No log 3.7714 132 0.9945 0.6286 0.9944 0.9972
No log 3.8286 134 0.8132 0.6811 0.8132 0.9018
No log 3.8857 136 0.6831 0.7206 0.6831 0.8265
No log 3.9429 138 0.6602 0.7015 0.6602 0.8125
No log 4.0 140 0.7395 0.6951 0.7395 0.8599
No log 4.0571 142 0.9001 0.6188 0.9001 0.9487
No log 4.1143 144 0.8719 0.6348 0.8719 0.9338
No log 4.1714 146 0.7081 0.6972 0.7081 0.8415
No log 4.2286 148 0.7051 0.7054 0.7051 0.8397
No log 4.2857 150 0.6755 0.6966 0.6755 0.8219
No log 4.3429 152 0.6308 0.7105 0.6308 0.7942
No log 4.4 154 0.7352 0.6636 0.7352 0.8574
No log 4.4571 156 0.8099 0.6448 0.8099 0.9000
No log 4.5143 158 0.7122 0.6636 0.7122 0.8439
No log 4.5714 160 0.6455 0.6843 0.6455 0.8034
No log 4.6286 162 0.6263 0.7245 0.6263 0.7914
No log 4.6857 164 0.7009 0.6926 0.7009 0.8372
No log 4.7429 166 0.7947 0.6577 0.7947 0.8915
No log 4.8 168 0.8201 0.6379 0.8201 0.9056
No log 4.8571 170 0.7023 0.6547 0.7023 0.8380
No log 4.9143 172 0.6705 0.6460 0.6705 0.8188
No log 4.9714 174 0.6775 0.6740 0.6775 0.8231
No log 5.0286 176 0.6694 0.6758 0.6694 0.8182
No log 5.0857 178 0.7257 0.6825 0.7257 0.8519
No log 5.1429 180 1.1062 0.5257 1.1062 1.0518
No log 5.2 182 1.1936 0.5160 1.1936 1.0925
No log 5.2571 184 0.9440 0.6344 0.9440 0.9716
No log 5.3143 186 0.7273 0.6852 0.7273 0.8528
No log 5.3714 188 0.7048 0.7105 0.7048 0.8395
No log 5.4286 190 0.6827 0.7206 0.6827 0.8262
No log 5.4857 192 0.6858 0.6863 0.6858 0.8282
No log 5.5429 194 0.7571 0.6971 0.7571 0.8701
No log 5.6 196 0.6803 0.7009 0.6803 0.8248
No log 5.6571 198 0.7350 0.6971 0.7350 0.8573
No log 5.7143 200 0.8878 0.6759 0.8878 0.9423
No log 5.7714 202 0.8525 0.6586 0.8525 0.9233
No log 5.8286 204 0.7487 0.6530 0.7487 0.8653
No log 5.8857 206 0.6488 0.7076 0.6488 0.8055
No log 5.9429 208 0.6085 0.6994 0.6085 0.7801
No log 6.0 210 0.6375 0.7042 0.6375 0.7984
No log 6.0571 212 0.7392 0.6655 0.7392 0.8597
No log 6.1143 214 0.7819 0.6712 0.7819 0.8842
No log 6.1714 216 0.7494 0.6990 0.7494 0.8657
No log 6.2286 218 0.6622 0.6847 0.6622 0.8137
No log 6.2857 220 0.6383 0.6952 0.6383 0.7989
No log 6.3429 222 0.6474 0.7015 0.6474 0.8046
No log 6.4 224 0.6356 0.7132 0.6356 0.7973
No log 6.4571 226 0.6563 0.7113 0.6563 0.8101
No log 6.5143 228 0.6213 0.7003 0.6213 0.7882
No log 6.5714 230 0.6230 0.6993 0.6230 0.7893
No log 6.6286 232 0.6707 0.6958 0.6707 0.8189
No log 6.6857 234 0.8410 0.6304 0.8410 0.9171
No log 6.7429 236 0.7864 0.6788 0.7864 0.8868
No log 6.8 238 0.6725 0.6651 0.6725 0.8201
No log 6.8571 240 0.6736 0.6630 0.6736 0.8207
No log 6.9143 242 0.8180 0.6534 0.8180 0.9044
No log 6.9714 244 0.9064 0.6257 0.9064 0.9520
No log 7.0286 246 0.8212 0.6324 0.8212 0.9062
No log 7.0857 248 0.6904 0.6641 0.6904 0.8309
No log 7.1429 250 0.6820 0.6595 0.6820 0.8258
No log 7.2 252 0.6807 0.6564 0.6807 0.8251
No log 7.2571 254 0.7066 0.6312 0.7066 0.8406
No log 7.3143 256 0.7081 0.6674 0.7081 0.8415
No log 7.3714 258 0.6700 0.6701 0.6700 0.8186
No log 7.4286 260 0.6726 0.7034 0.6726 0.8201
No log 7.4857 262 0.7003 0.6860 0.7003 0.8368
No log 7.5429 264 0.8004 0.6495 0.8004 0.8946
No log 7.6 266 1.0405 0.5982 1.0405 1.0200
No log 7.6571 268 1.0666 0.5777 1.0666 1.0328
No log 7.7143 270 0.8685 0.6425 0.8685 0.9319
No log 7.7714 272 0.6737 0.6871 0.6737 0.8208
No log 7.8286 274 0.6709 0.6826 0.6709 0.8191
No log 7.8857 276 0.7025 0.6749 0.7025 0.8382
No log 7.9429 278 0.6827 0.7053 0.6827 0.8263
No log 8.0 280 0.7475 0.6841 0.7475 0.8646
No log 8.0571 282 0.8746 0.6587 0.8746 0.9352
No log 8.1143 284 0.7985 0.6658 0.7985 0.8936
No log 8.1714 286 0.6629 0.6942 0.6629 0.8142
No log 8.2286 288 0.6400 0.6700 0.6400 0.8000
No log 8.2857 290 0.6417 0.6689 0.6417 0.8011
No log 8.3429 292 0.6454 0.7196 0.6454 0.8034
No log 8.4 294 0.8452 0.6349 0.8452 0.9193
No log 8.4571 296 1.0301 0.5867 1.0301 1.0149
No log 8.5143 298 0.9487 0.6123 0.9487 0.9740
No log 8.5714 300 0.7453 0.6795 0.7453 0.8633
No log 8.6286 302 0.6595 0.7259 0.6595 0.8121
No log 8.6857 304 0.6642 0.7183 0.6642 0.8150
No log 8.7429 306 0.7183 0.7193 0.7183 0.8475
No log 8.8 308 0.8504 0.6546 0.8504 0.9222
No log 8.8571 310 0.8367 0.6546 0.8367 0.9147
No log 8.9143 312 0.7985 0.6610 0.7985 0.8936
No log 8.9714 314 0.6772 0.7023 0.6772 0.8229
No log 9.0286 316 0.5933 0.7196 0.5933 0.7703
No log 9.0857 318 0.5790 0.7053 0.5790 0.7609
No log 9.1429 320 0.5990 0.7293 0.5990 0.7740
No log 9.2 322 0.6239 0.6830 0.6239 0.7899
No log 9.2571 324 0.6174 0.6893 0.6174 0.7857
No log 9.3143 326 0.5910 0.7034 0.5910 0.7688
No log 9.3714 328 0.6374 0.6919 0.6374 0.7984
No log 9.4286 330 0.6819 0.6642 0.6819 0.8258
No log 9.4857 332 0.6000 0.7215 0.6000 0.7746
No log 9.5429 334 0.6715 0.7018 0.6715 0.8194
No log 9.6 336 0.8892 0.6180 0.8892 0.9430
No log 9.6571 338 1.0110 0.5788 1.0110 1.0055
No log 9.7143 340 0.9714 0.5763 0.9714 0.9856
No log 9.7714 342 0.8665 0.5985 0.8665 0.9308
No log 9.8286 344 0.9075 0.5801 0.9075 0.9526
No log 9.8857 346 1.0438 0.5838 1.0438 1.0217
No log 9.9429 348 1.0561 0.5949 1.0561 1.0277
No log 10.0 350 1.0550 0.5879 1.0550 1.0271
No log 10.0571 352 0.9804 0.5982 0.9804 0.9901
No log 10.1143 354 0.8249 0.6601 0.8249 0.9082
No log 10.1714 356 0.7217 0.7160 0.7217 0.8495
No log 10.2286 358 0.7092 0.7338 0.7092 0.8421
No log 10.2857 360 0.7646 0.7300 0.7646 0.8744
No log 10.3429 362 0.8642 0.6544 0.8642 0.9296
No log 10.4 364 1.1553 0.6075 1.1553 1.0749
No log 10.4571 366 1.2836 0.5888 1.2836 1.1330
No log 10.5143 368 1.0709 0.6084 1.0709 1.0349
No log 10.5714 370 0.7992 0.7146 0.7992 0.8940
No log 10.6286 372 0.6880 0.7421 0.6880 0.8294
No log 10.6857 374 0.6724 0.7416 0.6724 0.8200
No log 10.7429 376 0.7194 0.7411 0.7194 0.8482
No log 10.8 378 0.9553 0.6076 0.9553 0.9774
No log 10.8571 380 1.0846 0.5576 1.0846 1.0414
No log 10.9143 382 1.0100 0.5926 1.0100 1.0050
No log 10.9714 384 0.7840 0.6399 0.7840 0.8854
No log 11.0286 386 0.6650 0.7253 0.6650 0.8154
No log 11.0857 388 0.6463 0.7414 0.6463 0.8039
No log 11.1429 390 0.6626 0.7470 0.6626 0.8140
No log 11.2 392 0.7289 0.6791 0.7289 0.8538
No log 11.2571 394 0.9057 0.5991 0.9057 0.9517
No log 11.3143 396 1.0542 0.5799 1.0542 1.0267
No log 11.3714 398 0.9802 0.5868 0.9802 0.9901
No log 11.4286 400 0.7504 0.6617 0.7504 0.8663
No log 11.4857 402 0.6263 0.6869 0.6263 0.7914
No log 11.5429 404 0.6129 0.7022 0.6129 0.7829
No log 11.6 406 0.6488 0.6581 0.6488 0.8055
No log 11.6571 408 0.6942 0.6834 0.6942 0.8332
No log 11.7143 410 0.6626 0.6665 0.6626 0.8140
No log 11.7714 412 0.5985 0.7217 0.5985 0.7737
No log 11.8286 414 0.5931 0.7002 0.5931 0.7701
No log 11.8857 416 0.6042 0.6961 0.6042 0.7773
No log 11.9429 418 0.6289 0.6916 0.6289 0.7930
No log 12.0 420 0.6676 0.6947 0.6676 0.8170
No log 12.0571 422 0.7116 0.6666 0.7116 0.8435
No log 12.1143 424 0.7618 0.6461 0.7618 0.8728
No log 12.1714 426 0.7217 0.6767 0.7217 0.8495
No log 12.2286 428 0.6289 0.7391 0.6289 0.7930
No log 12.2857 430 0.6071 0.7494 0.6071 0.7792
No log 12.3429 432 0.6084 0.7355 0.6084 0.7800
No log 12.4 434 0.6301 0.7237 0.6301 0.7938
No log 12.4571 436 0.6936 0.6958 0.6936 0.8328
No log 12.5143 438 0.7948 0.6173 0.7948 0.8915
No log 12.5714 440 0.8495 0.6216 0.8495 0.9217
No log 12.6286 442 0.8352 0.6392 0.8352 0.9139
No log 12.6857 444 0.7069 0.6713 0.7069 0.8408
No log 12.7429 446 0.6868 0.6665 0.6868 0.8287
No log 12.8 448 0.7151 0.6656 0.7151 0.8456
No log 12.8571 450 0.6995 0.6785 0.6995 0.8363
No log 12.9143 452 0.6578 0.6974 0.6578 0.8111
No log 12.9714 454 0.6883 0.7006 0.6883 0.8296
No log 13.0286 456 0.7646 0.6414 0.7646 0.8744
No log 13.0857 458 0.8025 0.6315 0.8025 0.8958
No log 13.1429 460 0.9974 0.6023 0.9974 0.9987
No log 13.2 462 1.0335 0.6031 1.0335 1.0166
No log 13.2571 464 0.9294 0.6023 0.9294 0.9641
No log 13.3143 466 0.7351 0.6773 0.7351 0.8574
No log 13.3714 468 0.6300 0.7269 0.6300 0.7937
No log 13.4286 470 0.6144 0.7459 0.6144 0.7838
No log 13.4857 472 0.6473 0.7340 0.6473 0.8046
No log 13.5429 474 0.7348 0.7020 0.7348 0.8572
No log 13.6 476 0.7177 0.7041 0.7177 0.8472
No log 13.6571 478 0.6397 0.7373 0.6397 0.7998
No log 13.7143 480 0.6154 0.7269 0.6154 0.7845
No log 13.7714 482 0.6101 0.7068 0.6101 0.7811
No log 13.8286 484 0.6104 0.7113 0.6104 0.7813
No log 13.8857 486 0.6444 0.7230 0.6444 0.8027
No log 13.9429 488 0.6945 0.7498 0.6945 0.8334
No log 14.0 490 0.7431 0.7213 0.7431 0.8620
No log 14.0571 492 0.7322 0.7461 0.7322 0.8557
No log 14.1143 494 0.7281 0.7333 0.7281 0.8533
No log 14.1714 496 0.7668 0.6629 0.7668 0.8757
No log 14.2286 498 0.7195 0.6928 0.7195 0.8482
0.4271 14.2857 500 0.7281 0.6655 0.7281 0.8533
0.4271 14.3429 502 0.7123 0.6856 0.7123 0.8440
0.4271 14.4 504 0.6463 0.6727 0.6463 0.8039
0.4271 14.4571 506 0.6245 0.6902 0.6245 0.7902
0.4271 14.5143 508 0.6548 0.7051 0.6548 0.8092
0.4271 14.5714 510 0.7349 0.6723 0.7349 0.8573
0.4271 14.6286 512 0.7369 0.6896 0.7369 0.8584
0.4271 14.6857 514 0.7155 0.7067 0.7155 0.8459
0.4271 14.7429 516 0.7064 0.7002 0.7064 0.8405
0.4271 14.8 518 0.7446 0.6877 0.7446 0.8629
0.4271 14.8571 520 0.8687 0.6235 0.8687 0.9320
0.4271 14.9143 522 1.0104 0.5849 1.0104 1.0052
0.4271 14.9714 524 0.9634 0.5983 0.9634 0.9815
0.4271 15.0286 526 0.8250 0.6552 0.8250 0.9083
0.4271 15.0857 528 0.6603 0.6760 0.6603 0.8126
0.4271 15.1429 530 0.6177 0.6915 0.6177 0.7859
0.4271 15.2 532 0.5955 0.7012 0.5955 0.7717
0.4271 15.2571 534 0.5926 0.6919 0.5926 0.7698
0.4271 15.3143 536 0.5882 0.6977 0.5882 0.7670
0.4271 15.3714 538 0.6306 0.6904 0.6306 0.7941
0.4271 15.4286 540 0.7249 0.7198 0.7249 0.8514
0.4271 15.4857 542 0.8072 0.6378 0.8072 0.8984
0.4271 15.5429 544 0.7721 0.6535 0.7721 0.8787
0.4271 15.6 546 0.6770 0.7415 0.6770 0.8228
0.4271 15.6571 548 0.6223 0.7102 0.6223 0.7889
0.4271 15.7143 550 0.6337 0.7231 0.6337 0.7960
0.4271 15.7714 552 0.6394 0.7438 0.6394 0.7997
0.4271 15.8286 554 0.7297 0.6979 0.7297 0.8542
0.4271 15.8857 556 0.8968 0.6815 0.8968 0.9470
0.4271 15.9429 558 0.9812 0.6469 0.9812 0.9906
0.4271 16.0 560 0.8834 0.6785 0.8834 0.9399
0.4271 16.0571 562 0.7555 0.7161 0.7555 0.8692
0.4271 16.1143 564 0.7052 0.7053 0.7052 0.8397
0.4271 16.1714 566 0.7340 0.6886 0.7340 0.8567
0.4271 16.2286 568 0.8057 0.6667 0.8057 0.8976
0.4271 16.2857 570 0.8040 0.6780 0.8040 0.8966
0.4271 16.3429 572 0.7244 0.7272 0.7244 0.8511
0.4271 16.4 574 0.6203 0.7422 0.6203 0.7876
0.4271 16.4571 576 0.6021 0.7135 0.6021 0.7760
0.4271 16.5143 578 0.6215 0.7137 0.6215 0.7883
0.4271 16.5714 580 0.6222 0.7004 0.6222 0.7888
0.4271 16.6286 582 0.5968 0.7135 0.5968 0.7725
0.4271 16.6857 584 0.6055 0.7316 0.6055 0.7781
0.4271 16.7429 586 0.6504 0.7470 0.6504 0.8065
0.4271 16.8 588 0.6662 0.7315 0.6662 0.8162
0.4271 16.8571 590 0.6639 0.7278 0.6639 0.8148
0.4271 16.9143 592 0.6190 0.7511 0.6190 0.7868
0.4271 16.9714 594 0.5915 0.7485 0.5915 0.7691
0.4271 17.0286 596 0.5766 0.7356 0.5766 0.7593
0.4271 17.0857 598 0.5866 0.7300 0.5866 0.7659
0.4271 17.1429 600 0.6419 0.7159 0.6419 0.8012
0.4271 17.2 602 0.8159 0.6317 0.8159 0.9033
0.4271 17.2571 604 0.9227 0.6215 0.9227 0.9606
0.4271 17.3143 606 0.8521 0.6258 0.8521 0.9231
0.4271 17.3714 608 0.7038 0.7006 0.7038 0.8389
0.4271 17.4286 610 0.6186 0.7323 0.6186 0.7865
0.4271 17.4857 612 0.6048 0.7202 0.6048 0.7777
0.4271 17.5429 614 0.6098 0.7377 0.6098 0.7809
0.4271 17.6 616 0.6798 0.7490 0.6798 0.8245
0.4271 17.6571 618 0.8164 0.6509 0.8164 0.9036
0.4271 17.7143 620 0.8772 0.6496 0.8772 0.9366
0.4271 17.7714 622 0.9485 0.6204 0.9485 0.9739
0.4271 17.8286 624 0.9022 0.6337 0.9022 0.9498
0.4271 17.8857 626 0.8116 0.6542 0.8116 0.9009

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
3
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/ArabicNewSplits8_usingALLEssays_FineTuningAraBERT_run1_AugV5_k7_task1_organization

Finetuned
(4040)
this model