ArabicNewSplits6_WithDuplicationsForScore5_FineTuningAraBERT_run3_AugV5_k11_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: 0.8249
  • Qwk: 0.6521
  • Mse: 0.8249
  • Rmse: 0.9083

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: 10

Training results

Training Loss Epoch Step Validation Loss Qwk Mse Rmse
No log 0.0323 2 5.0567 -0.0152 5.0567 2.2487
No log 0.0645 4 2.9508 0.1111 2.9508 1.7178
No log 0.0968 6 1.6439 0.1058 1.6439 1.2822
No log 0.1290 8 1.4839 0.1658 1.4839 1.2182
No log 0.1613 10 1.2515 0.1576 1.2515 1.1187
No log 0.1935 12 1.4895 0.0142 1.4895 1.2205
No log 0.2258 14 1.5868 0.0630 1.5868 1.2597
No log 0.2581 16 1.2907 0.2022 1.2907 1.1361
No log 0.2903 18 1.0856 0.3942 1.0856 1.0419
No log 0.3226 20 1.0403 0.3916 1.0403 1.0200
No log 0.3548 22 1.1656 0.3462 1.1656 1.0796
No log 0.3871 24 1.3089 0.3715 1.3089 1.1441
No log 0.4194 26 1.1492 0.4474 1.1492 1.0720
No log 0.4516 28 0.9374 0.5119 0.9374 0.9682
No log 0.4839 30 1.0002 0.4975 1.0002 1.0001
No log 0.5161 32 1.0049 0.5317 1.0049 1.0025
No log 0.5484 34 1.1785 0.4474 1.1785 1.0856
No log 0.5806 36 1.2075 0.4207 1.2075 1.0989
No log 0.6129 38 1.0566 0.4727 1.0566 1.0279
No log 0.6452 40 0.9928 0.5283 0.9928 0.9964
No log 0.6774 42 1.1224 0.4362 1.1224 1.0594
No log 0.7097 44 1.0223 0.4745 1.0223 1.0111
No log 0.7419 46 1.0054 0.5231 1.0054 1.0027
No log 0.7742 48 0.8982 0.5813 0.8982 0.9477
No log 0.8065 50 0.8975 0.6001 0.8975 0.9474
No log 0.8387 52 0.8536 0.5934 0.8536 0.9239
No log 0.8710 54 0.8016 0.6613 0.8016 0.8953
No log 0.9032 56 0.9272 0.5877 0.9272 0.9629
No log 0.9355 58 1.0661 0.5548 1.0661 1.0325
No log 0.9677 60 1.3051 0.5030 1.3051 1.1424
No log 1.0 62 1.1340 0.5801 1.1340 1.0649
No log 1.0323 64 0.7867 0.6598 0.7867 0.8870
No log 1.0645 66 0.8351 0.6433 0.8351 0.9138
No log 1.0968 68 0.8937 0.5872 0.8937 0.9453
No log 1.1290 70 0.8869 0.5601 0.8869 0.9418
No log 1.1613 72 0.7489 0.6474 0.7489 0.8654
No log 1.1935 74 0.9742 0.5625 0.9742 0.9870
No log 1.2258 76 1.4659 0.4869 1.4659 1.2108
No log 1.2581 78 1.5792 0.4643 1.5792 1.2567
No log 1.2903 80 1.2169 0.5435 1.2169 1.1031
No log 1.3226 82 0.7295 0.7130 0.7295 0.8541
No log 1.3548 84 0.8194 0.6299 0.8194 0.9052
No log 1.3871 86 0.9072 0.6114 0.9072 0.9525
No log 1.4194 88 0.7207 0.6999 0.7207 0.8489
No log 1.4516 90 0.6983 0.7093 0.6983 0.8356
No log 1.4839 92 1.0138 0.6571 1.0138 1.0069
No log 1.5161 94 1.3576 0.5824 1.3576 1.1652
No log 1.5484 96 1.3504 0.5859 1.3504 1.1621
No log 1.5806 98 1.0731 0.6689 1.0731 1.0359
No log 1.6129 100 0.9836 0.6936 0.9836 0.9918
No log 1.6452 102 0.8788 0.7130 0.8788 0.9374
No log 1.6774 104 0.8924 0.6713 0.8924 0.9447
No log 1.7097 106 0.8412 0.6833 0.8412 0.9172
No log 1.7419 108 0.8438 0.7148 0.8438 0.9186
No log 1.7742 110 0.9104 0.6966 0.9104 0.9542
No log 1.8065 112 1.0346 0.6606 1.0346 1.0172
No log 1.8387 114 1.1691 0.6130 1.1691 1.0812
No log 1.8710 116 1.0712 0.6231 1.0712 1.0350
No log 1.9032 118 0.8627 0.6942 0.8627 0.9288
No log 1.9355 120 0.7510 0.7535 0.7510 0.8666
No log 1.9677 122 0.7896 0.7278 0.7896 0.8886
No log 2.0 124 0.9671 0.7037 0.9671 0.9834
No log 2.0323 126 1.4450 0.5693 1.4450 1.2021
No log 2.0645 128 1.8585 0.5551 1.8585 1.3633
No log 2.0968 130 1.9999 0.5160 1.9999 1.4142
No log 2.1290 132 1.7287 0.5735 1.7287 1.3148
No log 2.1613 134 1.2949 0.5916 1.2949 1.1379
No log 2.1935 136 0.8878 0.6767 0.8878 0.9422
No log 2.2258 138 0.7435 0.7248 0.7435 0.8623
No log 2.2581 140 0.8060 0.7201 0.8060 0.8978
No log 2.2903 142 0.8422 0.7315 0.8422 0.9177
No log 2.3226 144 0.9039 0.7012 0.9039 0.9508
No log 2.3548 146 0.9411 0.6677 0.9411 0.9701
No log 2.3871 148 0.8990 0.7008 0.8990 0.9482
No log 2.4194 150 0.8014 0.7167 0.8014 0.8952
No log 2.4516 152 0.8402 0.6950 0.8402 0.9166
No log 2.4839 154 1.0180 0.6812 1.0180 1.0090
No log 2.5161 156 1.1977 0.6330 1.1977 1.0944
No log 2.5484 158 1.2736 0.6121 1.2736 1.1285
No log 2.5806 160 1.0275 0.6669 1.0275 1.0137
No log 2.6129 162 0.9096 0.6802 0.9096 0.9537
No log 2.6452 164 1.0622 0.6678 1.0622 1.0306
No log 2.6774 166 1.0896 0.6645 1.0896 1.0438
No log 2.7097 168 0.8827 0.6842 0.8827 0.9395
No log 2.7419 170 0.8315 0.7007 0.8315 0.9119
No log 2.7742 172 0.9426 0.7027 0.9426 0.9709
No log 2.8065 174 0.8297 0.7064 0.8297 0.9109
No log 2.8387 176 0.7089 0.7499 0.7089 0.8420
No log 2.8710 178 0.6411 0.7713 0.6411 0.8007
No log 2.9032 180 0.6836 0.7582 0.6836 0.8268
No log 2.9355 182 0.9468 0.6833 0.9468 0.9731
No log 2.9677 184 1.1381 0.6464 1.1381 1.0668
No log 3.0 186 1.1685 0.6420 1.1685 1.0810
No log 3.0323 188 1.1409 0.6523 1.1409 1.0681
No log 3.0645 190 0.9152 0.6869 0.9152 0.9566
No log 3.0968 192 0.7896 0.7160 0.7896 0.8886
No log 3.1290 194 0.9372 0.6930 0.9372 0.9681
No log 3.1613 196 1.0885 0.6708 1.0885 1.0433
No log 3.1935 198 0.9645 0.7017 0.9645 0.9821
No log 3.2258 200 0.7367 0.7350 0.7367 0.8583
No log 3.2581 202 0.7157 0.7190 0.7157 0.8460
No log 3.2903 204 0.7320 0.7238 0.7320 0.8556
No log 3.3226 206 0.8496 0.7176 0.8496 0.9217
No log 3.3548 208 0.8821 0.6931 0.8821 0.9392
No log 3.3871 210 0.8668 0.6971 0.8668 0.9310
No log 3.4194 212 0.7745 0.7504 0.7745 0.8801
No log 3.4516 214 0.7241 0.7492 0.7241 0.8509
No log 3.4839 216 0.8572 0.7265 0.8572 0.9259
No log 3.5161 218 1.1845 0.6582 1.1845 1.0884
No log 3.5484 220 1.5127 0.6021 1.5127 1.2299
No log 3.5806 222 1.6544 0.5751 1.6544 1.2862
No log 3.6129 224 1.4717 0.5788 1.4717 1.2131
No log 3.6452 226 1.0680 0.6330 1.0680 1.0334
No log 3.6774 228 0.8007 0.6893 0.8007 0.8948
No log 3.7097 230 0.7036 0.7236 0.7036 0.8388
No log 3.7419 232 0.7728 0.7041 0.7728 0.8791
No log 3.7742 234 0.8911 0.6973 0.8911 0.9440
No log 3.8065 236 0.9104 0.6648 0.9104 0.9541
No log 3.8387 238 0.8559 0.6757 0.8559 0.9252
No log 3.8710 240 0.6636 0.7405 0.6636 0.8146
No log 3.9032 242 0.6162 0.7470 0.6162 0.7850
No log 3.9355 244 0.6542 0.7360 0.6542 0.8088
No log 3.9677 246 0.8051 0.6926 0.8051 0.8973
No log 4.0 248 0.9489 0.6894 0.9489 0.9741
No log 4.0323 250 0.8865 0.7120 0.8865 0.9415
No log 4.0645 252 0.9212 0.7154 0.9212 0.9598
No log 4.0968 254 1.0586 0.6656 1.0586 1.0289
No log 4.1290 256 1.0062 0.6827 1.0062 1.0031
No log 4.1613 258 0.9231 0.7072 0.9231 0.9608
No log 4.1935 260 0.9662 0.6798 0.9662 0.9829
No log 4.2258 262 1.1180 0.6047 1.1180 1.0574
No log 4.2581 264 1.3081 0.5727 1.3081 1.1437
No log 4.2903 266 1.2687 0.5643 1.2687 1.1264
No log 4.3226 268 1.0639 0.5747 1.0639 1.0315
No log 4.3548 270 0.8160 0.6625 0.8160 0.9033
No log 4.3871 272 0.7309 0.7042 0.7309 0.8549
No log 4.4194 274 0.7990 0.6755 0.7990 0.8939
No log 4.4516 276 0.9591 0.6610 0.9591 0.9794
No log 4.4839 278 1.1475 0.6434 1.1475 1.0712
No log 4.5161 280 1.2178 0.6377 1.2178 1.1035
No log 4.5484 282 1.0606 0.6655 1.0606 1.0299
No log 4.5806 284 0.8671 0.7084 0.8671 0.9312
No log 4.6129 286 0.7308 0.7217 0.7308 0.8549
No log 4.6452 288 0.7443 0.7196 0.7443 0.8627
No log 4.6774 290 0.8712 0.6967 0.8712 0.9334
No log 4.7097 292 0.9989 0.6570 0.9989 0.9995
No log 4.7419 294 0.9281 0.6715 0.9281 0.9634
No log 4.7742 296 0.8980 0.6697 0.8980 0.9476
No log 4.8065 298 0.7960 0.7080 0.7960 0.8922
No log 4.8387 300 0.7223 0.7256 0.7223 0.8499
No log 4.8710 302 0.7283 0.7354 0.7283 0.8534
No log 4.9032 304 0.7715 0.7074 0.7715 0.8783
No log 4.9355 306 0.9077 0.6942 0.9077 0.9527
No log 4.9677 308 1.1219 0.6170 1.1219 1.0592
No log 5.0 310 1.2450 0.5967 1.2450 1.1158
No log 5.0323 312 1.1983 0.6082 1.1983 1.0947
No log 5.0645 314 1.0901 0.6522 1.0901 1.0441
No log 5.0968 316 0.9870 0.6904 0.9870 0.9935
No log 5.1290 318 0.7797 0.7047 0.7797 0.8830
No log 5.1613 320 0.7145 0.7252 0.7145 0.8453
No log 5.1935 322 0.7855 0.6830 0.7855 0.8863
No log 5.2258 324 0.8798 0.6909 0.8798 0.9380
No log 5.2581 326 0.8283 0.6863 0.8283 0.9101
No log 5.2903 328 0.7357 0.7064 0.7357 0.8577
No log 5.3226 330 0.7571 0.6646 0.7571 0.8701
No log 5.3548 332 0.8135 0.6782 0.8135 0.9019
No log 5.3871 334 0.9488 0.6568 0.9488 0.9741
No log 5.4194 336 0.9982 0.6292 0.9982 0.9991
No log 5.4516 338 0.9116 0.6834 0.9116 0.9548
No log 5.4839 340 0.8157 0.6664 0.8157 0.9032
No log 5.5161 342 0.8589 0.6597 0.8589 0.9268
No log 5.5484 344 0.9103 0.6459 0.9103 0.9541
No log 5.5806 346 1.0512 0.6212 1.0512 1.0253
No log 5.6129 348 1.0333 0.6193 1.0333 1.0165
No log 5.6452 350 0.9659 0.6472 0.9659 0.9828
No log 5.6774 352 0.9489 0.6584 0.9489 0.9741
No log 5.7097 354 0.9592 0.6827 0.9592 0.9794
No log 5.7419 356 0.9192 0.6899 0.9192 0.9587
No log 5.7742 358 0.9168 0.6785 0.9168 0.9575
No log 5.8065 360 0.8927 0.6804 0.8927 0.9448
No log 5.8387 362 0.8289 0.6960 0.8289 0.9105
No log 5.8710 364 0.6963 0.7130 0.6963 0.8345
No log 5.9032 366 0.6037 0.7609 0.6037 0.7770
No log 5.9355 368 0.6036 0.7609 0.6036 0.7769
No log 5.9677 370 0.6612 0.7260 0.6612 0.8131
No log 6.0 372 0.8493 0.7054 0.8493 0.9216
No log 6.0323 374 1.1452 0.6174 1.1452 1.0702
No log 6.0645 376 1.2547 0.6096 1.2547 1.1201
No log 6.0968 378 1.1632 0.6074 1.1632 1.0785
No log 6.1290 380 1.0180 0.6193 1.0180 1.0089
No log 6.1613 382 0.8546 0.6840 0.8546 0.9245
No log 6.1935 384 0.7520 0.7251 0.7520 0.8672
No log 6.2258 386 0.7247 0.7355 0.7247 0.8513
No log 6.2581 388 0.7784 0.6987 0.7784 0.8823
No log 6.2903 390 0.9127 0.6461 0.9127 0.9554
No log 6.3226 392 1.0702 0.6021 1.0702 1.0345
No log 6.3548 394 1.1989 0.5852 1.1989 1.0950
No log 6.3871 396 1.2136 0.5887 1.2136 1.1016
No log 6.4194 398 1.1066 0.6033 1.1066 1.0520
No log 6.4516 400 0.9399 0.6468 0.9399 0.9695
No log 6.4839 402 0.8191 0.7005 0.8191 0.9050
No log 6.5161 404 0.8013 0.7055 0.8013 0.8952
No log 6.5484 406 0.8335 0.6782 0.8335 0.9130
No log 6.5806 408 0.9430 0.6311 0.9430 0.9711
No log 6.6129 410 0.9938 0.6093 0.9938 0.9969
No log 6.6452 412 0.9424 0.6257 0.9424 0.9708
No log 6.6774 414 0.8689 0.6449 0.8689 0.9321
No log 6.7097 416 0.8162 0.6632 0.8162 0.9034
No log 6.7419 418 0.7766 0.7027 0.7766 0.8812
No log 6.7742 420 0.8025 0.7021 0.8025 0.8958
No log 6.8065 422 0.8014 0.7101 0.8014 0.8952
No log 6.8387 424 0.7986 0.6939 0.7986 0.8936
No log 6.8710 426 0.8054 0.6961 0.8054 0.8975
No log 6.9032 428 0.8256 0.6916 0.8256 0.9086
No log 6.9355 430 0.8707 0.6610 0.8707 0.9331
No log 6.9677 432 0.9280 0.6631 0.9280 0.9633
No log 7.0 434 0.9415 0.6598 0.9415 0.9703
No log 7.0323 436 0.8906 0.6598 0.8906 0.9437
No log 7.0645 438 0.8427 0.6725 0.8427 0.9180
No log 7.0968 440 0.8125 0.6664 0.8125 0.9014
No log 7.1290 442 0.8107 0.6544 0.8107 0.9004
No log 7.1613 444 0.7815 0.6844 0.7815 0.8840
No log 7.1935 446 0.7483 0.7148 0.7483 0.8650
No log 7.2258 448 0.7414 0.7265 0.7414 0.8611
No log 7.2581 450 0.7390 0.7211 0.7390 0.8596
No log 7.2903 452 0.7754 0.7338 0.7754 0.8806
No log 7.3226 454 0.8189 0.6986 0.8189 0.9050
No log 7.3548 456 0.8136 0.6922 0.8136 0.9020
No log 7.3871 458 0.7556 0.7343 0.7556 0.8693
No log 7.4194 460 0.6876 0.7445 0.6876 0.8292
No log 7.4516 462 0.6763 0.7374 0.6763 0.8224
No log 7.4839 464 0.6854 0.7315 0.6854 0.8279
No log 7.5161 466 0.7132 0.7324 0.7132 0.8445
No log 7.5484 468 0.7648 0.7299 0.7648 0.8746
No log 7.5806 470 0.8096 0.6796 0.8096 0.8998
No log 7.6129 472 0.7972 0.6995 0.7972 0.8929
No log 7.6452 474 0.7463 0.7148 0.7463 0.8639
No log 7.6774 476 0.6833 0.7234 0.6833 0.8266
No log 7.7097 478 0.6494 0.7495 0.6494 0.8058
No log 7.7419 480 0.6471 0.7495 0.6471 0.8044
No log 7.7742 482 0.6679 0.7455 0.6679 0.8173
No log 7.8065 484 0.7055 0.7166 0.7055 0.8399
No log 7.8387 486 0.7412 0.7382 0.7412 0.8609
No log 7.8710 488 0.7530 0.7381 0.7530 0.8678
No log 7.9032 490 0.7943 0.7089 0.7943 0.8912
No log 7.9355 492 0.8488 0.6779 0.8488 0.9213
No log 7.9677 494 0.8532 0.6832 0.8532 0.9237
No log 8.0 496 0.8320 0.6986 0.8320 0.9122
No log 8.0323 498 0.7924 0.7023 0.7924 0.8902
0.4333 8.0645 500 0.7211 0.7315 0.7211 0.8492
0.4333 8.0968 502 0.6617 0.7374 0.6617 0.8134
0.4333 8.1290 504 0.6236 0.7450 0.6236 0.7897
0.4333 8.1613 506 0.6192 0.7445 0.6192 0.7869
0.4333 8.1935 508 0.6359 0.7371 0.6359 0.7974
0.4333 8.2258 510 0.6648 0.7261 0.6648 0.8154
0.4333 8.2581 512 0.7183 0.7031 0.7183 0.8475
0.4333 8.2903 514 0.7875 0.6844 0.7875 0.8874
0.4333 8.3226 516 0.8444 0.6574 0.8444 0.9189
0.4333 8.3548 518 0.9108 0.6507 0.9108 0.9544
0.4333 8.3871 520 0.9489 0.6643 0.9489 0.9741
0.4333 8.4194 522 0.9464 0.6554 0.9464 0.9728
0.4333 8.4516 524 0.9272 0.6713 0.9272 0.9629
0.4333 8.4839 526 0.9078 0.6631 0.9078 0.9528
0.4333 8.5161 528 0.9278 0.6713 0.9278 0.9632
0.4333 8.5484 530 0.9490 0.6635 0.9490 0.9742
0.4333 8.5806 532 0.9454 0.6783 0.9454 0.9723
0.4333 8.6129 534 0.9526 0.6682 0.9526 0.9760
0.4333 8.6452 536 0.9717 0.6538 0.9717 0.9857
0.4333 8.6774 538 0.9816 0.6538 0.9816 0.9908
0.4333 8.7097 540 0.9659 0.6690 0.9659 0.9828
0.4333 8.7419 542 0.9539 0.6690 0.9539 0.9767
0.4333 8.7742 544 0.9224 0.6682 0.9224 0.9604
0.4333 8.8065 546 0.8754 0.6701 0.8754 0.9356
0.4333 8.8387 548 0.8312 0.6676 0.8312 0.9117
0.4333 8.8710 550 0.8169 0.6766 0.8169 0.9038
0.4333 8.9032 552 0.7996 0.6789 0.7996 0.8942
0.4333 8.9355 554 0.8026 0.6789 0.8026 0.8959
0.4333 8.9677 556 0.8121 0.6724 0.8121 0.9012
0.4333 9.0 558 0.8349 0.6691 0.8349 0.9137
0.4333 9.0323 560 0.8549 0.6561 0.8549 0.9246
0.4333 9.0645 562 0.8831 0.6614 0.8831 0.9398
0.4333 9.0968 564 0.8813 0.6582 0.8813 0.9388
0.4333 9.1290 566 0.8739 0.6582 0.8739 0.9348
0.4333 9.1613 568 0.8493 0.6740 0.8493 0.9216
0.4333 9.1935 570 0.8144 0.6859 0.8144 0.9024
0.4333 9.2258 572 0.7746 0.7003 0.7746 0.8801
0.4333 9.2581 574 0.7568 0.6981 0.7568 0.8699
0.4333 9.2903 576 0.7443 0.6981 0.7443 0.8627
0.4333 9.3226 578 0.7472 0.6981 0.7472 0.8644
0.4333 9.3548 580 0.7605 0.6940 0.7605 0.8721
0.4333 9.3871 582 0.7880 0.6722 0.7880 0.8877
0.4333 9.4194 584 0.8198 0.6521 0.8198 0.9054
0.4333 9.4516 586 0.8464 0.6505 0.8464 0.9200
0.4333 9.4839 588 0.8576 0.6505 0.8576 0.9261
0.4333 9.5161 590 0.8683 0.6388 0.8683 0.9318
0.4333 9.5484 592 0.8724 0.6510 0.8724 0.9340
0.4333 9.5806 594 0.8678 0.6592 0.8678 0.9315
0.4333 9.6129 596 0.8651 0.6592 0.8651 0.9301
0.4333 9.6452 598 0.8661 0.6592 0.8661 0.9307
0.4333 9.6774 600 0.8641 0.6505 0.8641 0.9296
0.4333 9.7097 602 0.8619 0.6718 0.8619 0.9284
0.4333 9.7419 604 0.8571 0.6551 0.8571 0.9258
0.4333 9.7742 606 0.8496 0.6505 0.8496 0.9217
0.4333 9.8065 608 0.8440 0.6505 0.8440 0.9187
0.4333 9.8387 610 0.8375 0.6521 0.8375 0.9151
0.4333 9.8710 612 0.8328 0.6521 0.8328 0.9126
0.4333 9.9032 614 0.8286 0.6521 0.8286 0.9103
0.4333 9.9355 616 0.8265 0.6521 0.8265 0.9091
0.4333 9.9677 618 0.8258 0.6521 0.8258 0.9087
0.4333 10.0 620 0.8249 0.6521 0.8249 0.9083

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/ArabicNewSplits6_WithDuplicationsForScore5_FineTuningAraBERT_run3_AugV5_k11_task1_organization

Finetuned
(4040)
this model