ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k16_task5_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: 0.9004
  • Qwk: 0.4434
  • Mse: 0.9004
  • Rmse: 0.9489

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 0.0488 2 4.1074 0.0069 4.1074 2.0267
No log 0.0976 4 2.0961 0.1002 2.0961 1.4478
No log 0.1463 6 1.4143 0.0143 1.4143 1.1892
No log 0.1951 8 1.0876 0.2221 1.0876 1.0429
No log 0.2439 10 1.0962 0.1725 1.0962 1.0470
No log 0.2927 12 1.4127 -0.0278 1.4127 1.1886
No log 0.3415 14 1.7442 -0.0398 1.7442 1.3207
No log 0.3902 16 1.5107 -0.0560 1.5107 1.2291
No log 0.4390 18 1.1483 0.1119 1.1483 1.0716
No log 0.4878 20 1.0804 0.2140 1.0804 1.0394
No log 0.5366 22 1.2017 0.1658 1.2017 1.0962
No log 0.5854 24 1.5324 0.0 1.5324 1.2379
No log 0.6341 26 1.5029 0.0 1.5029 1.2259
No log 0.6829 28 1.2931 0.0380 1.2931 1.1371
No log 0.7317 30 1.1481 0.1148 1.1481 1.0715
No log 0.7805 32 1.0776 0.1989 1.0776 1.0381
No log 0.8293 34 1.0707 0.1891 1.0707 1.0347
No log 0.8780 36 1.0672 0.1131 1.0672 1.0331
No log 0.9268 38 1.0589 0.1755 1.0589 1.0290
No log 0.9756 40 1.0625 0.1713 1.0625 1.0308
No log 1.0244 42 1.1155 0.1509 1.1155 1.0562
No log 1.0732 44 1.1576 0.2004 1.1576 1.0759
No log 1.1220 46 1.0573 0.2367 1.0573 1.0283
No log 1.1707 48 0.9751 0.2390 0.9751 0.9875
No log 1.2195 50 1.1348 0.2632 1.1348 1.0653
No log 1.2683 52 1.1737 0.0888 1.1737 1.0834
No log 1.3171 54 1.1011 0.1233 1.1011 1.0493
No log 1.3659 56 1.0346 0.1962 1.0346 1.0171
No log 1.4146 58 1.0134 0.4186 1.0134 1.0067
No log 1.4634 60 1.0019 0.3272 1.0019 1.0009
No log 1.5122 62 0.9739 0.2716 0.9739 0.9869
No log 1.5610 64 0.9885 0.1989 0.9885 0.9942
No log 1.6098 66 1.0444 0.1699 1.0444 1.0220
No log 1.6585 68 1.0804 0.1826 1.0804 1.0394
No log 1.7073 70 1.0548 0.3278 1.0548 1.0270
No log 1.7561 72 0.9483 0.2932 0.9483 0.9738
No log 1.8049 74 0.9363 0.3896 0.9363 0.9676
No log 1.8537 76 1.0326 0.3119 1.0326 1.0162
No log 1.9024 78 1.2722 0.2149 1.2722 1.1279
No log 1.9512 80 1.3866 0.1790 1.3866 1.1775
No log 2.0 82 1.1932 0.3310 1.1932 1.0923
No log 2.0488 84 0.9046 0.3973 0.9046 0.9511
No log 2.0976 86 0.8300 0.3642 0.8300 0.9111
No log 2.1463 88 0.8375 0.4628 0.8375 0.9152
No log 2.1951 90 1.0469 0.4222 1.0469 1.0232
No log 2.2439 92 1.4173 0.2424 1.4173 1.1905
No log 2.2927 94 1.3344 0.2381 1.3344 1.1552
No log 2.3415 96 0.9723 0.4563 0.9723 0.9861
No log 2.3902 98 0.8815 0.3957 0.8815 0.9389
No log 2.4390 100 0.9373 0.4681 0.9373 0.9681
No log 2.4878 102 1.0961 0.3283 1.0961 1.0469
No log 2.5366 104 1.2547 0.2970 1.2547 1.1201
No log 2.5854 106 1.1644 0.3478 1.1644 1.0791
No log 2.6341 108 0.9187 0.4291 0.9187 0.9585
No log 2.6829 110 0.8502 0.2742 0.8502 0.9220
No log 2.7317 112 0.8317 0.3052 0.8317 0.9120
No log 2.7805 114 0.8840 0.4115 0.8840 0.9402
No log 2.8293 116 1.2435 0.2863 1.2435 1.1151
No log 2.8780 118 1.5097 0.2396 1.5097 1.2287
No log 2.9268 120 1.3055 0.2898 1.3055 1.1426
No log 2.9756 122 0.9309 0.4455 0.9309 0.9648
No log 3.0244 124 0.7905 0.4547 0.7905 0.8891
No log 3.0732 126 0.8068 0.5425 0.8068 0.8982
No log 3.1220 128 0.7926 0.4676 0.7926 0.8903
No log 3.1707 130 0.8776 0.4943 0.8776 0.9368
No log 3.2195 132 1.0752 0.3724 1.0752 1.0369
No log 3.2683 134 1.1722 0.2934 1.1722 1.0827
No log 3.3171 136 1.0457 0.4186 1.0457 1.0226
No log 3.3659 138 0.9205 0.4423 0.9205 0.9594
No log 3.4146 140 0.8029 0.4759 0.8029 0.8960
No log 3.4634 142 0.8065 0.4759 0.8065 0.8980
No log 3.5122 144 0.9074 0.4575 0.9074 0.9526
No log 3.5610 146 1.1225 0.3385 1.1225 1.0595
No log 3.6098 148 1.0858 0.3984 1.0858 1.0420
No log 3.6585 150 0.9129 0.4807 0.9129 0.9554
No log 3.7073 152 0.8006 0.4898 0.8006 0.8948
No log 3.7561 154 0.7975 0.4557 0.7975 0.8930
No log 3.8049 156 0.7982 0.4557 0.7982 0.8934
No log 3.8537 158 0.8152 0.4660 0.8152 0.9029
No log 3.9024 160 0.8552 0.4511 0.8552 0.9248
No log 3.9512 162 0.9506 0.4478 0.9506 0.9750
No log 4.0 164 1.1274 0.3461 1.1274 1.0618
No log 4.0488 166 1.1434 0.3569 1.1434 1.0693
No log 4.0976 168 1.0798 0.4255 1.0798 1.0391
No log 4.1463 170 1.0036 0.3775 1.0036 1.0018
No log 4.1951 172 1.0440 0.3846 1.0440 1.0218
No log 4.2439 174 1.0140 0.4151 1.0140 1.0070
No log 4.2927 176 0.9079 0.3902 0.9079 0.9529
No log 4.3415 178 0.7848 0.5113 0.7848 0.8859
No log 4.3902 180 0.7548 0.5156 0.7548 0.8688
No log 4.4390 182 0.7603 0.5002 0.7603 0.8720
No log 4.4878 184 0.8239 0.4815 0.8239 0.9077
No log 4.5366 186 0.8955 0.4581 0.8955 0.9463
No log 4.5854 188 0.8806 0.4807 0.8806 0.9384
No log 4.6341 190 0.8228 0.5366 0.8228 0.9071
No log 4.6829 192 0.7402 0.5135 0.7402 0.8604
No log 4.7317 194 0.7452 0.5069 0.7452 0.8632
No log 4.7805 196 0.8098 0.3577 0.8098 0.8999
No log 4.8293 198 0.7750 0.3537 0.7750 0.8803
No log 4.8780 200 0.7765 0.4743 0.7765 0.8812
No log 4.9268 202 0.8982 0.4695 0.8982 0.9478
No log 4.9756 204 0.9659 0.4167 0.9659 0.9828
No log 5.0244 206 1.0791 0.4162 1.0791 1.0388
No log 5.0732 208 1.1067 0.4152 1.1067 1.0520
No log 5.1220 210 0.9508 0.3959 0.9508 0.9751
No log 5.1707 212 0.9138 0.3897 0.9138 0.9559
No log 5.2195 214 0.9379 0.3862 0.9379 0.9685
No log 5.2683 216 1.0930 0.3928 1.0930 1.0455
No log 5.3171 218 1.1947 0.3493 1.1947 1.0930
No log 5.3659 220 1.1248 0.3810 1.1248 1.0606
No log 5.4146 222 0.9458 0.3207 0.9458 0.9725
No log 5.4634 224 0.8479 0.3940 0.8479 0.9208
No log 5.5122 226 0.8147 0.4973 0.8147 0.9026
No log 5.5610 228 0.8478 0.4584 0.8478 0.9207
No log 5.6098 230 0.9371 0.4794 0.9371 0.9680
No log 5.6585 232 1.0297 0.4668 1.0297 1.0147
No log 5.7073 234 0.9622 0.4779 0.9622 0.9809
No log 5.7561 236 0.8791 0.5131 0.8791 0.9376
No log 5.8049 238 0.8202 0.5504 0.8202 0.9056
No log 5.8537 240 0.8103 0.5153 0.8103 0.9001
No log 5.9024 242 0.8829 0.5318 0.8829 0.9396
No log 5.9512 244 0.8116 0.5439 0.8116 0.9009
No log 6.0 246 0.8111 0.5549 0.8111 0.9006
No log 6.0488 248 0.7693 0.5383 0.7693 0.8771
No log 6.0976 250 0.6927 0.4888 0.6927 0.8323
No log 6.1463 252 0.6873 0.5368 0.6873 0.8290
No log 6.1951 254 0.7349 0.5885 0.7349 0.8573
No log 6.2439 256 0.7963 0.5532 0.7963 0.8924
No log 6.2927 258 0.8166 0.5746 0.8166 0.9036
No log 6.3415 260 0.7788 0.5267 0.7788 0.8825
No log 6.3902 262 0.8472 0.5255 0.8472 0.9204
No log 6.4390 264 0.9718 0.4894 0.9718 0.9858
No log 6.4878 266 1.0546 0.4191 1.0546 1.0269
No log 6.5366 268 0.9806 0.4585 0.9806 0.9903
No log 6.5854 270 0.8364 0.4584 0.8364 0.9146
No log 6.6341 272 0.7811 0.5135 0.7811 0.8838
No log 6.6829 274 0.7749 0.4802 0.7749 0.8803
No log 6.7317 276 0.7763 0.4789 0.7763 0.8811
No log 6.7805 278 0.8047 0.4478 0.8047 0.8970
No log 6.8293 280 0.8227 0.4344 0.8227 0.9070
No log 6.8780 282 0.8465 0.4839 0.8465 0.9201
No log 6.9268 284 0.8072 0.4727 0.8072 0.8984
No log 6.9756 286 0.7630 0.4417 0.7630 0.8735
No log 7.0244 288 0.7611 0.4417 0.7611 0.8724
No log 7.0732 290 0.7722 0.5107 0.7722 0.8788
No log 7.1220 292 0.7758 0.4739 0.7758 0.8808
No log 7.1707 294 0.7371 0.4903 0.7371 0.8585
No log 7.2195 296 0.7614 0.5438 0.7614 0.8726
No log 7.2683 298 0.7417 0.5879 0.7417 0.8612
No log 7.3171 300 0.7171 0.4903 0.7171 0.8468
No log 7.3659 302 0.7230 0.5010 0.7230 0.8503
No log 7.4146 304 0.7310 0.5002 0.7310 0.8550
No log 7.4634 306 0.7409 0.5450 0.7409 0.8608
No log 7.5122 308 0.7356 0.5261 0.7356 0.8577
No log 7.5610 310 0.7292 0.5796 0.7292 0.8539
No log 7.6098 312 0.7323 0.5700 0.7323 0.8557
No log 7.6585 314 0.7527 0.5054 0.7527 0.8676
No log 7.7073 316 0.7282 0.5565 0.7282 0.8533
No log 7.7561 318 0.7281 0.5774 0.7281 0.8533
No log 7.8049 320 0.7641 0.5618 0.7641 0.8741
No log 7.8537 322 0.7974 0.5505 0.7974 0.8930
No log 7.9024 324 0.7993 0.5614 0.7993 0.8940
No log 7.9512 326 0.8369 0.5170 0.8369 0.9148
No log 8.0 328 0.8053 0.4456 0.8053 0.8974
No log 8.0488 330 0.7841 0.5002 0.7841 0.8855
No log 8.0976 332 0.7978 0.4473 0.7978 0.8932
No log 8.1463 334 0.8856 0.4586 0.8856 0.9411
No log 8.1951 336 0.9433 0.5241 0.9433 0.9713
No log 8.2439 338 0.8725 0.5041 0.8725 0.9341
No log 8.2927 340 0.8114 0.5103 0.8114 0.9008
No log 8.3415 342 0.8031 0.5010 0.8031 0.8962
No log 8.3902 344 0.8346 0.4581 0.8346 0.9136
No log 8.4390 346 0.8363 0.4060 0.8363 0.9145
No log 8.4878 348 0.8392 0.4060 0.8392 0.9161
No log 8.5366 350 0.8091 0.3922 0.8091 0.8995
No log 8.5854 352 0.7982 0.4063 0.7982 0.8934
No log 8.6341 354 0.8055 0.4713 0.8055 0.8975
No log 8.6829 356 0.8303 0.4579 0.8303 0.9112
No log 8.7317 358 0.8448 0.5041 0.8448 0.9191
No log 8.7805 360 0.7790 0.4850 0.7790 0.8826
No log 8.8293 362 0.7333 0.5774 0.7333 0.8564
No log 8.8780 364 0.7219 0.5809 0.7219 0.8497
No log 8.9268 366 0.7398 0.5361 0.7398 0.8601
No log 8.9756 368 0.7843 0.4579 0.7843 0.8856
No log 9.0244 370 0.7884 0.4579 0.7884 0.8879
No log 9.0732 372 0.7400 0.4839 0.7400 0.8602
No log 9.1220 374 0.6948 0.5346 0.6948 0.8336
No log 9.1707 376 0.6910 0.5546 0.6910 0.8312
No log 9.2195 378 0.6979 0.5751 0.6979 0.8354
No log 9.2683 380 0.6895 0.5645 0.6895 0.8304
No log 9.3171 382 0.6811 0.5221 0.6811 0.8253
No log 9.3659 384 0.6792 0.5357 0.6792 0.8241
No log 9.4146 386 0.6910 0.5010 0.6910 0.8313
No log 9.4634 388 0.6946 0.5017 0.6946 0.8334
No log 9.5122 390 0.6922 0.5345 0.6922 0.8320
No log 9.5610 392 0.7140 0.5221 0.7140 0.8450
No log 9.6098 394 0.7120 0.5528 0.7120 0.8438
No log 9.6585 396 0.6612 0.6441 0.6612 0.8132
No log 9.7073 398 0.6551 0.6581 0.6551 0.8094
No log 9.7561 400 0.6453 0.6500 0.6453 0.8033
No log 9.8049 402 0.6428 0.5712 0.6428 0.8017
No log 9.8537 404 0.6668 0.5345 0.6668 0.8166
No log 9.9024 406 0.6668 0.5185 0.6668 0.8166
No log 9.9512 408 0.6714 0.5185 0.6714 0.8194
No log 10.0 410 0.6443 0.5602 0.6443 0.8027
No log 10.0488 412 0.6591 0.5786 0.6591 0.8119
No log 10.0976 414 0.6899 0.5740 0.6899 0.8306
No log 10.1463 416 0.6630 0.6389 0.6630 0.8143
No log 10.1951 418 0.6614 0.5887 0.6614 0.8133
No log 10.2439 420 0.6604 0.6518 0.6604 0.8127
No log 10.2927 422 0.6680 0.5945 0.6680 0.8173
No log 10.3415 424 0.6614 0.6154 0.6614 0.8133
No log 10.3902 426 0.6576 0.6154 0.6576 0.8109
No log 10.4390 428 0.6610 0.5955 0.6610 0.8130
No log 10.4878 430 0.6617 0.6426 0.6617 0.8135
No log 10.5366 432 0.6640 0.6306 0.6640 0.8148
No log 10.5854 434 0.6738 0.6341 0.6738 0.8208
No log 10.6341 436 0.6879 0.6491 0.6879 0.8294
No log 10.6829 438 0.6796 0.6491 0.6796 0.8244
No log 10.7317 440 0.6795 0.6175 0.6795 0.8243
No log 10.7805 442 0.6688 0.5928 0.6688 0.8178
No log 10.8293 444 0.6682 0.5317 0.6682 0.8175
No log 10.8780 446 0.7127 0.5622 0.7127 0.8442
No log 10.9268 448 0.7745 0.5385 0.7745 0.8801
No log 10.9756 450 0.7761 0.5070 0.7761 0.8810
No log 11.0244 452 0.7627 0.5084 0.7627 0.8733
No log 11.0732 454 0.7096 0.5093 0.7096 0.8424
No log 11.1220 456 0.6618 0.5234 0.6618 0.8135
No log 11.1707 458 0.6699 0.5221 0.6699 0.8185
No log 11.2195 460 0.7182 0.5614 0.7182 0.8474
No log 11.2683 462 0.7973 0.5697 0.7973 0.8929
No log 11.3171 464 0.7958 0.5697 0.7958 0.8921
No log 11.3659 466 0.7892 0.5173 0.7892 0.8884
No log 11.4146 468 0.7633 0.5291 0.7633 0.8737
No log 11.4634 470 0.7322 0.5305 0.7322 0.8557
No log 11.5122 472 0.7319 0.5923 0.7319 0.8555
No log 11.5610 474 0.7737 0.5560 0.7737 0.8796
No log 11.6098 476 0.7174 0.5821 0.7174 0.8470
No log 11.6585 478 0.6805 0.5763 0.6805 0.8249
No log 11.7073 480 0.6798 0.5558 0.6798 0.8245
No log 11.7561 482 0.6941 0.5558 0.6941 0.8331
No log 11.8049 484 0.6832 0.5822 0.6832 0.8266
No log 11.8537 486 0.6648 0.5046 0.6648 0.8154
No log 11.9024 488 0.6710 0.5174 0.6710 0.8191
No log 11.9512 490 0.6647 0.5046 0.6647 0.8153
No log 12.0 492 0.6936 0.6269 0.6936 0.8328
No log 12.0488 494 0.8245 0.5658 0.8245 0.9080
No log 12.0976 496 0.8437 0.5639 0.8437 0.9185
No log 12.1463 498 0.7823 0.5852 0.7823 0.8845
0.3056 12.1951 500 0.7689 0.5494 0.7689 0.8769
0.3056 12.2439 502 0.7838 0.5048 0.7838 0.8853
0.3056 12.2927 504 0.7746 0.5173 0.7746 0.8801
0.3056 12.3415 506 0.7501 0.5317 0.7501 0.8661
0.3056 12.3902 508 0.7469 0.5330 0.7469 0.8642
0.3056 12.4390 510 0.7556 0.5626 0.7556 0.8692
0.3056 12.4878 512 0.8046 0.5923 0.8046 0.8970
0.3056 12.5366 514 0.8939 0.5305 0.8939 0.9455
0.3056 12.5854 516 0.8613 0.5726 0.8613 0.9281
0.3056 12.6341 518 0.7784 0.5923 0.7784 0.8823
0.3056 12.6829 520 0.7529 0.4660 0.7529 0.8677
0.3056 12.7317 522 0.7648 0.4388 0.7648 0.8746
0.3056 12.7805 524 0.7718 0.4371 0.7718 0.8785
0.3056 12.8293 526 0.8177 0.4581 0.8177 0.9043
0.3056 12.8780 528 0.9004 0.4434 0.9004 0.9489

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
6
Safetensors
Model size
135M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for MayBashendy/ArabicNewSplits7_FineTuningAraBERT_run1_AugV5_k16_task5_organization

Finetuned
(4205)
this model