ArabicNewSplits7_usingALLEssays_FineTuningAraBERT_run3_AugV5_k10_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: 0.6465
  • Qwk: 0.7286
  • Mse: 0.6465
  • Rmse: 0.8041

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 7.1092 -0.0056 7.1092 2.6663
No log 0.0833 4 4.7202 0.0650 4.7202 2.1726
No log 0.125 6 3.7504 -0.0625 3.7504 1.9366
No log 0.1667 8 2.8176 -0.0290 2.8176 1.6786
No log 0.2083 10 1.8623 0.2439 1.8623 1.3647
No log 0.25 12 1.7086 0.3946 1.7086 1.3071
No log 0.2917 14 2.1281 0.3030 2.1281 1.4588
No log 0.3333 16 2.0295 0.3418 2.0295 1.4246
No log 0.375 18 1.5977 0.4265 1.5977 1.2640
No log 0.4167 20 1.4924 0.2759 1.4924 1.2216
No log 0.4583 22 1.4243 0.2906 1.4243 1.1935
No log 0.5 24 1.3952 0.3361 1.3952 1.1812
No log 0.5417 26 1.4237 0.4478 1.4237 1.1932
No log 0.5833 28 2.0990 0.2420 2.0990 1.4488
No log 0.625 30 2.4197 0.2073 2.4197 1.5555
No log 0.6667 32 2.1095 0.2548 2.1095 1.4524
No log 0.7083 34 1.6181 0.4 1.6181 1.2721
No log 0.75 36 1.5950 0.3607 1.5950 1.2629
No log 0.7917 38 1.7574 0.4 1.7574 1.3257
No log 0.8333 40 1.9696 0.2571 1.9696 1.4034
No log 0.875 42 2.0632 0.2603 2.0632 1.4364
No log 0.9167 44 2.1488 0.2533 2.1488 1.4659
No log 0.9583 46 2.0972 0.2516 2.0972 1.4482
No log 1.0 48 2.3491 0.2604 2.3491 1.5327
No log 1.0417 50 2.5196 0.2947 2.5196 1.5873
No log 1.0833 52 2.1018 0.3294 2.1018 1.4498
No log 1.125 54 1.7972 0.4268 1.7972 1.3406
No log 1.1667 56 1.9035 0.4 1.9035 1.3797
No log 1.2083 58 1.9711 0.3735 1.9711 1.4040
No log 1.25 60 2.2989 0.2395 2.2989 1.5162
No log 1.2917 62 2.3410 0.2012 2.3410 1.5300
No log 1.3333 64 2.0027 0.3117 2.0027 1.4152
No log 1.375 66 1.2317 0.5255 1.2317 1.1098
No log 1.4167 68 0.9899 0.6176 0.9899 0.9949
No log 1.4583 70 1.0857 0.5909 1.0857 1.0420
No log 1.5 72 1.0289 0.6294 1.0289 1.0143
No log 1.5417 74 1.1017 0.6538 1.1017 1.0496
No log 1.5833 76 1.2838 0.5093 1.2838 1.1330
No log 1.625 78 1.0498 0.675 1.0498 1.0246
No log 1.6667 80 0.8400 0.6968 0.8400 0.9165
No log 1.7083 82 0.8151 0.7355 0.8151 0.9028
No log 1.75 84 0.8163 0.7484 0.8163 0.9035
No log 1.7917 86 0.8151 0.7059 0.8151 0.9028
No log 1.8333 88 0.7971 0.7451 0.7971 0.8928
No log 1.875 90 0.8046 0.7383 0.8046 0.8970
No log 1.9167 92 0.8181 0.7448 0.8181 0.9045
No log 1.9583 94 0.8422 0.6759 0.8422 0.9177
No log 2.0 96 0.8685 0.6849 0.8685 0.9319
No log 2.0417 98 0.8768 0.6939 0.8768 0.9364
No log 2.0833 100 0.9096 0.6939 0.9096 0.9537
No log 2.125 102 1.0181 0.625 1.0181 1.0090
No log 2.1667 104 0.9991 0.6623 0.9991 0.9995
No log 2.2083 106 0.9997 0.6443 0.9997 0.9999
No log 2.25 108 1.0211 0.6475 1.0211 1.0105
No log 2.2917 110 1.0913 0.5588 1.0913 1.0447
No log 2.3333 112 0.9184 0.6475 0.9184 0.9583
No log 2.375 114 0.8202 0.7092 0.8202 0.9056
No log 2.4167 116 0.7603 0.6950 0.7603 0.8720
No log 2.4583 118 0.7237 0.7042 0.7237 0.8507
No log 2.5 120 0.7305 0.7534 0.7305 0.8547
No log 2.5417 122 1.0791 0.5882 1.0791 1.0388
No log 2.5833 124 1.2395 0.5109 1.2395 1.1133
No log 2.625 126 0.8350 0.6809 0.8350 0.9138
No log 2.6667 128 0.8286 0.7123 0.8286 0.9103
No log 2.7083 130 0.6803 0.7613 0.6803 0.8248
No log 2.75 132 0.6392 0.7692 0.6392 0.7995
No log 2.7917 134 0.5722 0.8221 0.5722 0.7564
No log 2.8333 136 0.6054 0.8293 0.6054 0.7781
No log 2.875 138 0.6364 0.8101 0.6364 0.7977
No log 2.9167 140 0.6987 0.7403 0.6987 0.8359
No log 2.9583 142 0.7070 0.7320 0.7070 0.8408
No log 3.0 144 0.7148 0.7320 0.7148 0.8455
No log 3.0417 146 0.8502 0.7239 0.8502 0.9221
No log 3.0833 148 0.8292 0.7283 0.8292 0.9106
No log 3.125 150 0.6671 0.7799 0.6671 0.8168
No log 3.1667 152 0.9650 0.6667 0.9650 0.9823
No log 3.2083 154 1.1387 0.4848 1.1387 1.0671
No log 3.25 156 0.7834 0.7211 0.7834 0.8851
No log 3.2917 158 0.6509 0.8070 0.6509 0.8068
No log 3.3333 160 0.9872 0.7282 0.9872 0.9936
No log 3.375 162 0.9003 0.7576 0.9003 0.9489
No log 3.4167 164 0.6928 0.8287 0.6928 0.8323
No log 3.4583 166 0.9555 0.6788 0.9555 0.9775
No log 3.5 168 1.6767 0.3429 1.6767 1.2949
No log 3.5417 170 1.5285 0.4286 1.5285 1.2363
No log 3.5833 172 1.0191 0.6259 1.0191 1.0095
No log 3.625 174 0.6971 0.75 0.6971 0.8349
No log 3.6667 176 0.6567 0.7853 0.6567 0.8104
No log 3.7083 178 0.6748 0.7771 0.6748 0.8215
No log 3.75 180 0.7057 0.7403 0.7057 0.8401
No log 3.7917 182 0.7782 0.7260 0.7782 0.8822
No log 3.8333 184 0.8044 0.7324 0.8044 0.8969
No log 3.875 186 0.7651 0.7042 0.7651 0.8747
No log 3.9167 188 0.8063 0.6621 0.8063 0.8979
No log 3.9583 190 0.8693 0.6389 0.8693 0.9323
No log 4.0 192 0.8635 0.6711 0.8635 0.9292
No log 4.0417 194 0.7799 0.7342 0.7799 0.8831
No log 4.0833 196 0.7026 0.8121 0.7026 0.8382
No log 4.125 198 0.6761 0.8047 0.6761 0.8223
No log 4.1667 200 0.6593 0.7907 0.6593 0.8120
No log 4.2083 202 0.6560 0.8092 0.6560 0.8100
No log 4.25 204 0.7756 0.7412 0.7756 0.8807
No log 4.2917 206 0.8526 0.7349 0.8526 0.9234
No log 4.3333 208 0.7755 0.7237 0.7755 0.8806
No log 4.375 210 0.7892 0.72 0.7892 0.8884
No log 4.4167 212 0.7750 0.6980 0.7750 0.8804
No log 4.4583 214 0.7815 0.7067 0.7815 0.8840
No log 4.5 216 0.7749 0.7097 0.7749 0.8803
No log 4.5417 218 0.6747 0.7547 0.6747 0.8214
No log 4.5833 220 0.6119 0.7947 0.6119 0.7823
No log 4.625 222 0.6324 0.7651 0.6324 0.7952
No log 4.6667 224 0.6259 0.7785 0.6259 0.7911
No log 4.7083 226 0.6277 0.7682 0.6277 0.7923
No log 4.75 228 0.7309 0.7643 0.7309 0.8549
No log 4.7917 230 0.9055 0.6710 0.9055 0.9516
No log 4.8333 232 0.9765 0.6494 0.9765 0.9882
No log 4.875 234 0.9581 0.6494 0.9581 0.9789
No log 4.9167 236 0.7724 0.7547 0.7724 0.8789
No log 4.9583 238 0.6605 0.7403 0.6605 0.8127
No log 5.0 240 0.6551 0.7722 0.6551 0.8094
No log 5.0417 242 0.7697 0.7738 0.7697 0.8773
No log 5.0833 244 0.9975 0.6848 0.9975 0.9988
No log 5.125 246 1.2129 0.6316 1.2129 1.1013
No log 5.1667 248 1.0851 0.6524 1.0851 1.0417
No log 5.2083 250 0.7501 0.7738 0.7501 0.8661
No log 5.25 252 0.6082 0.7792 0.6082 0.7799
No log 5.2917 254 0.6859 0.7413 0.6859 0.8282
No log 5.3333 256 0.7477 0.7143 0.7477 0.8647
No log 5.375 258 0.6946 0.7413 0.6946 0.8334
No log 5.4167 260 0.6497 0.7973 0.6497 0.8060
No log 5.4583 262 0.6693 0.7895 0.6693 0.8181
No log 5.5 264 0.7097 0.7237 0.7097 0.8424
No log 5.5417 266 0.7493 0.7105 0.7493 0.8656
No log 5.5833 268 0.7073 0.7613 0.7073 0.8410
No log 5.625 270 0.6350 0.7742 0.6350 0.7969
No log 5.6667 272 0.6357 0.7484 0.6357 0.7973
No log 5.7083 274 0.6042 0.7875 0.6042 0.7773
No log 5.75 276 0.6190 0.8118 0.6190 0.7868
No log 5.7917 278 0.6885 0.7811 0.6885 0.8298
No log 5.8333 280 0.8016 0.7514 0.8016 0.8953
No log 5.875 282 0.8415 0.7305 0.8415 0.9173
No log 5.9167 284 0.7907 0.7143 0.7907 0.8892
No log 5.9583 286 0.7519 0.7067 0.7519 0.8671
No log 6.0 288 0.8038 0.6345 0.8038 0.8966
No log 6.0417 290 0.8068 0.6301 0.8068 0.8982
No log 6.0833 292 0.7920 0.6301 0.7920 0.8899
No log 6.125 294 0.7761 0.6755 0.7761 0.8810
No log 6.1667 296 0.8738 0.6982 0.8738 0.9348
No log 6.2083 298 0.8287 0.7024 0.8287 0.9103
No log 6.25 300 0.6141 0.7848 0.6141 0.7837
No log 6.2917 302 0.5524 0.8075 0.5524 0.7433
No log 6.3333 304 0.5662 0.8 0.5662 0.7524
No log 6.375 306 0.5703 0.8101 0.5703 0.7552
No log 6.4167 308 0.5969 0.8129 0.5969 0.7726
No log 6.4583 310 0.6885 0.7643 0.6885 0.8297
No log 6.5 312 0.7873 0.7 0.7873 0.8873
No log 6.5417 314 0.7569 0.7143 0.7569 0.8700
No log 6.5833 316 0.6582 0.7922 0.6582 0.8113
No log 6.625 318 0.6458 0.7922 0.6458 0.8036
No log 6.6667 320 0.6435 0.8052 0.6435 0.8022
No log 6.7083 322 0.6574 0.7550 0.6574 0.8108
No log 6.75 324 0.6582 0.7613 0.6582 0.8113
No log 6.7917 326 0.6206 0.7925 0.6206 0.7878
No log 6.8333 328 0.5981 0.8 0.5981 0.7733
No log 6.875 330 0.5719 0.8 0.5719 0.7562
No log 6.9167 332 0.5386 0.8228 0.5386 0.7339
No log 6.9583 334 0.5329 0.8228 0.5329 0.7300
No log 7.0 336 0.5956 0.8121 0.5956 0.7718
No log 7.0417 338 0.6806 0.7904 0.6806 0.8250
No log 7.0833 340 0.6994 0.7927 0.6994 0.8363
No log 7.125 342 0.5990 0.7848 0.5990 0.7739
No log 7.1667 344 0.5902 0.7632 0.5902 0.7682
No log 7.2083 346 0.6015 0.7550 0.6015 0.7756
No log 7.25 348 0.7048 0.7547 0.7048 0.8395
No log 7.2917 350 0.7527 0.7089 0.7527 0.8676
No log 7.3333 352 0.6495 0.7643 0.6495 0.8059
No log 7.375 354 0.5539 0.7632 0.5539 0.7442
No log 7.4167 356 0.5564 0.8 0.5564 0.7459
No log 7.4583 358 0.6071 0.7397 0.6071 0.7792
No log 7.5 360 0.5991 0.7724 0.5991 0.7740
No log 7.5417 362 0.6012 0.7550 0.6012 0.7753
No log 7.5833 364 0.6680 0.7333 0.6680 0.8173
No log 7.625 366 0.7116 0.6901 0.7116 0.8436
No log 7.6667 368 0.6897 0.7286 0.6897 0.8305
No log 7.7083 370 0.7449 0.7368 0.7449 0.8631
No log 7.75 372 0.7624 0.6815 0.7624 0.8732
No log 7.7917 374 0.6968 0.7234 0.6968 0.8347
No log 7.8333 376 0.5967 0.7724 0.5967 0.7725
No log 7.875 378 0.6069 0.7925 0.6069 0.7791
No log 7.9167 380 0.6031 0.8 0.6031 0.7766
No log 7.9583 382 0.5995 0.7857 0.5995 0.7742
No log 8.0 384 0.5815 0.8 0.5815 0.7626
No log 8.0417 386 0.5594 0.7922 0.5594 0.7479
No log 8.0833 388 0.5766 0.7919 0.5766 0.7594
No log 8.125 390 0.5942 0.8052 0.5942 0.7709
No log 8.1667 392 0.6121 0.8 0.6121 0.7823
No log 8.2083 394 0.6855 0.7205 0.6855 0.8279
No log 8.25 396 0.7798 0.6538 0.7798 0.8831
No log 8.2917 398 0.7664 0.6709 0.7664 0.8755
No log 8.3333 400 0.6932 0.7468 0.6932 0.8326
No log 8.375 402 0.6373 0.7568 0.6373 0.7983
No log 8.4167 404 0.6316 0.7671 0.6316 0.7947
No log 8.4583 406 0.6239 0.7785 0.6239 0.7899
No log 8.5 408 0.5941 0.7867 0.5941 0.7707
No log 8.5417 410 0.6319 0.7651 0.6319 0.7949
No log 8.5833 412 0.6466 0.7733 0.6466 0.8041
No log 8.625 414 0.6321 0.7733 0.6321 0.7951
No log 8.6667 416 0.6374 0.7733 0.6374 0.7984
No log 8.7083 418 0.7144 0.7027 0.7144 0.8452
No log 8.75 420 0.8403 0.7013 0.8403 0.9167
No log 8.7917 422 1.0090 0.6706 1.0090 1.0045
No log 8.8333 424 0.9416 0.6897 0.9416 0.9703
No log 8.875 426 0.7600 0.7416 0.7600 0.8718
No log 8.9167 428 0.6803 0.7529 0.6803 0.8248
No log 8.9583 430 0.7161 0.7630 0.7161 0.8462
No log 9.0 432 0.7183 0.7558 0.7183 0.8476
No log 9.0417 434 0.6717 0.7927 0.6717 0.8196
No log 9.0833 436 0.6114 0.7742 0.6114 0.7819
No log 9.125 438 0.6077 0.7724 0.6077 0.7796
No log 9.1667 440 0.6169 0.7724 0.6169 0.7854
No log 9.2083 442 0.6333 0.7785 0.6333 0.7958
No log 9.25 444 0.6640 0.7517 0.6640 0.8149
No log 9.2917 446 0.7057 0.7368 0.7057 0.8401
No log 9.3333 448 0.7073 0.7368 0.7073 0.8410
No log 9.375 450 0.6759 0.7248 0.6759 0.8221
No log 9.4167 452 0.6883 0.7075 0.6883 0.8296
No log 9.4583 454 0.6666 0.7532 0.6666 0.8164
No log 9.5 456 0.6502 0.7516 0.6502 0.8064
No log 9.5417 458 0.6882 0.7730 0.6882 0.8296
No log 9.5833 460 0.6298 0.7613 0.6298 0.7936
No log 9.625 462 0.5833 0.7763 0.5833 0.7637
No log 9.6667 464 0.5952 0.8054 0.5952 0.7715
No log 9.7083 466 0.6265 0.7324 0.6265 0.7915
No log 9.75 468 0.6769 0.7143 0.6769 0.8227
No log 9.7917 470 0.6961 0.6950 0.6961 0.8343
No log 9.8333 472 0.6641 0.7310 0.6641 0.8149
No log 9.875 474 0.6349 0.7483 0.6349 0.7968
No log 9.9167 476 0.6300 0.7333 0.6300 0.7937
No log 9.9583 478 0.6305 0.7974 0.6305 0.7940
No log 10.0 480 0.6474 0.7763 0.6474 0.8046
No log 10.0417 482 0.7616 0.6974 0.7616 0.8727
No log 10.0833 484 0.9025 0.6667 0.9025 0.9500
No log 10.125 486 0.9375 0.6531 0.9375 0.9682
No log 10.1667 488 0.7865 0.6712 0.7865 0.8869
No log 10.2083 490 0.6339 0.7517 0.6339 0.7962
No log 10.25 492 0.5802 0.7534 0.5802 0.7617
No log 10.2917 494 0.5836 0.7582 0.5836 0.7640
No log 10.3333 496 0.5573 0.7898 0.5573 0.7465
No log 10.375 498 0.5619 0.7925 0.5619 0.7496
0.3732 10.4167 500 0.6174 0.7901 0.6174 0.7858
0.3732 10.4583 502 0.6244 0.7692 0.6244 0.7902
0.3732 10.5 504 0.6114 0.7564 0.6114 0.7819
0.3732 10.5417 506 0.6451 0.7297 0.6451 0.8032
0.3732 10.5833 508 0.6527 0.7338 0.6527 0.8079
0.3732 10.625 510 0.6465 0.7286 0.6465 0.8041

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/ArabicNewSplits7_usingALLEssays_FineTuningAraBERT_run3_AugV5_k10_task1_organization

Finetuned
(4040)
this model