ArabicNewSplits7_FineTuningAraBERT_run3_AugV5_k17_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: 0.6223
  • Qwk: 0.5261
  • Mse: 0.6223
  • Rmse: 0.7889

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 0.0465 2 4.0092 -0.0020 4.0092 2.0023
No log 0.0930 4 2.1554 0.1065 2.1554 1.4681
No log 0.1395 6 1.4637 0.0143 1.4637 1.2098
No log 0.1860 8 1.8026 0.1152 1.8026 1.3426
No log 0.2326 10 1.2285 0.0380 1.2285 1.1084
No log 0.2791 12 1.0905 0.1671 1.0905 1.0443
No log 0.3256 14 1.1919 0.0981 1.1919 1.0918
No log 0.3721 16 1.2533 0.0385 1.2533 1.1195
No log 0.4186 18 1.2420 0.0793 1.2420 1.1144
No log 0.4651 20 1.1915 0.0824 1.1915 1.0916
No log 0.5116 22 1.1351 0.1418 1.1351 1.0654
No log 0.5581 24 1.0957 0.1601 1.0957 1.0468
No log 0.6047 26 1.0759 0.2187 1.0759 1.0372
No log 0.6512 28 1.1177 0.1509 1.1177 1.0572
No log 0.6977 30 1.0984 0.1971 1.0984 1.0480
No log 0.7442 32 1.0804 0.2391 1.0804 1.0394
No log 0.7907 34 1.0726 0.2416 1.0726 1.0357
No log 0.8372 36 1.0759 0.1901 1.0759 1.0373
No log 0.8837 38 1.0795 0.0374 1.0795 1.0390
No log 0.9302 40 1.1480 0.0436 1.1480 1.0714
No log 0.9767 42 1.1301 0.0287 1.1301 1.0631
No log 1.0233 44 1.0533 0.0761 1.0533 1.0263
No log 1.0698 46 0.9975 0.2049 0.9975 0.9988
No log 1.1163 48 1.0267 0.3326 1.0267 1.0132
No log 1.1628 50 1.0568 0.1671 1.0568 1.0280
No log 1.2093 52 0.9544 0.3281 0.9544 0.9769
No log 1.2558 54 0.9292 0.3774 0.9292 0.9639
No log 1.3023 56 0.9664 0.3207 0.9664 0.9831
No log 1.3488 58 0.9662 0.3207 0.9662 0.9829
No log 1.3953 60 0.9357 0.3071 0.9357 0.9673
No log 1.4419 62 0.9386 0.3339 0.9386 0.9688
No log 1.4884 64 0.9960 0.3603 0.9960 0.9980
No log 1.5349 66 0.9739 0.3603 0.9739 0.9869
No log 1.5814 68 0.8631 0.4277 0.8631 0.9290
No log 1.6279 70 0.8544 0.4204 0.8544 0.9244
No log 1.6744 72 0.7868 0.4745 0.7868 0.8870
No log 1.7209 74 0.7658 0.4745 0.7658 0.8751
No log 1.7674 76 0.7627 0.4503 0.7627 0.8734
No log 1.8140 78 0.7809 0.4962 0.7809 0.8837
No log 1.8605 80 0.8620 0.4686 0.8620 0.9284
No log 1.9070 82 0.6949 0.5046 0.6949 0.8336
No log 1.9535 84 1.0246 0.4857 1.0246 1.0122
No log 2.0 86 1.4108 0.3096 1.4108 1.1878
No log 2.0465 88 1.0671 0.4857 1.0671 1.0330
No log 2.0930 90 0.6867 0.5088 0.6867 0.8286
No log 2.1395 92 0.6687 0.5847 0.6687 0.8177
No log 2.1860 94 0.6921 0.4847 0.6921 0.8320
No log 2.2326 96 0.9225 0.4560 0.9225 0.9605
No log 2.2791 98 1.0962 0.4103 1.0962 1.0470
No log 2.3256 100 1.0525 0.3787 1.0525 1.0259
No log 2.3721 102 0.8451 0.4456 0.8451 0.9193
No log 2.4186 104 0.8065 0.3651 0.8065 0.8981
No log 2.4651 106 0.8271 0.3503 0.8271 0.9094
No log 2.5116 108 0.8290 0.3765 0.8290 0.9105
No log 2.5581 110 0.8291 0.4012 0.8291 0.9105
No log 2.6047 112 0.8535 0.4713 0.8535 0.9238
No log 2.6512 114 0.7903 0.4145 0.7903 0.8890
No log 2.6977 116 0.7851 0.4691 0.7851 0.8861
No log 2.7442 118 0.8862 0.5690 0.8862 0.9414
No log 2.7907 120 1.1392 0.3609 1.1392 1.0673
No log 2.8372 122 0.9527 0.4982 0.9527 0.9761
No log 2.8837 124 0.7321 0.4644 0.7321 0.8556
No log 2.9302 126 0.8159 0.5355 0.8159 0.9033
No log 2.9767 128 0.9213 0.5 0.9213 0.9599
No log 3.0233 130 0.8378 0.4799 0.8378 0.9153
No log 3.0698 132 0.8076 0.4697 0.8076 0.8987
No log 3.1163 134 0.7848 0.3682 0.7848 0.8859
No log 3.1628 136 0.8079 0.3658 0.8079 0.8988
No log 3.2093 138 0.8502 0.3339 0.8502 0.9220
No log 3.2558 140 0.8697 0.3339 0.8697 0.9326
No log 3.3023 142 0.8417 0.3485 0.8417 0.9174
No log 3.3488 144 0.7924 0.3933 0.7924 0.8902
No log 3.3953 146 0.7640 0.5325 0.7640 0.8741
No log 3.4419 148 0.7326 0.5047 0.7326 0.8559
No log 3.4884 150 0.7471 0.5487 0.7471 0.8644
No log 3.5349 152 0.7508 0.5301 0.7508 0.8665
No log 3.5814 154 0.7848 0.4856 0.7848 0.8859
No log 3.6279 156 0.7795 0.4145 0.7795 0.8829
No log 3.6744 158 1.1217 0.4796 1.1217 1.0591
No log 3.7209 160 1.4129 0.3491 1.4129 1.1887
No log 3.7674 162 1.1278 0.3624 1.1278 1.0620
No log 3.8140 164 0.9094 0.3446 0.9094 0.9536
No log 3.8605 166 0.9663 0.2024 0.9663 0.9830
No log 3.9070 168 0.9715 0.2392 0.9715 0.9857
No log 3.9535 170 0.8600 0.3902 0.8600 0.9274
No log 4.0 172 0.7268 0.5259 0.7268 0.8525
No log 4.0465 174 0.7297 0.5459 0.7297 0.8542
No log 4.0930 176 0.6799 0.5419 0.6799 0.8246
No log 4.1395 178 0.7113 0.5054 0.7113 0.8434
No log 4.1860 180 0.8342 0.5208 0.8342 0.9133
No log 4.2326 182 0.7878 0.5006 0.7878 0.8876
No log 4.2791 184 0.6834 0.5079 0.6834 0.8267
No log 4.3256 186 0.6624 0.4843 0.6624 0.8139
No log 4.3721 188 0.6504 0.5103 0.6504 0.8064
No log 4.4186 190 0.6700 0.4847 0.6700 0.8185
No log 4.4651 192 0.7422 0.5059 0.7422 0.8615
No log 4.5116 194 0.7751 0.4797 0.7751 0.8804
No log 4.5581 196 0.7340 0.5059 0.7340 0.8567
No log 4.6047 198 0.6942 0.4327 0.6942 0.8332
No log 4.6512 200 0.6908 0.4597 0.6908 0.8311
No log 4.6977 202 0.7403 0.4928 0.7403 0.8604
No log 4.7442 204 0.7327 0.4928 0.7327 0.8560
No log 4.7907 206 0.6653 0.3922 0.6653 0.8157
No log 4.8372 208 0.6864 0.5933 0.6864 0.8285
No log 4.8837 210 0.7134 0.5586 0.7134 0.8446
No log 4.9302 212 0.6663 0.6028 0.6663 0.8163
No log 4.9767 214 0.6820 0.4630 0.6820 0.8258
No log 5.0233 216 0.8331 0.4902 0.8331 0.9127
No log 5.0698 218 0.8533 0.5343 0.8533 0.9237
No log 5.1163 220 0.7048 0.5188 0.7048 0.8395
No log 5.1628 222 0.7250 0.5870 0.7250 0.8515
No log 5.2093 224 0.7179 0.5667 0.7179 0.8473
No log 5.2558 226 0.6991 0.4743 0.6991 0.8361
No log 5.3023 228 0.8133 0.4057 0.8133 0.9018
No log 5.3488 230 0.9444 0.3846 0.9444 0.9718
No log 5.3953 232 0.9260 0.4439 0.9260 0.9623
No log 5.4419 234 0.7877 0.4102 0.7877 0.8875
No log 5.4884 236 0.6743 0.5510 0.6743 0.8212
No log 5.5349 238 0.6869 0.6099 0.6869 0.8288
No log 5.5814 240 0.6612 0.5890 0.6612 0.8131
No log 5.6279 242 0.6434 0.5234 0.6434 0.8021
No log 5.6744 244 0.6953 0.4102 0.6953 0.8338
No log 5.7209 246 0.7181 0.4075 0.7181 0.8474
No log 5.7674 248 0.6739 0.4473 0.6739 0.8209
No log 5.8140 250 0.6509 0.5570 0.6509 0.8068
No log 5.8605 252 0.6620 0.6238 0.6620 0.8136
No log 5.9070 254 0.6646 0.6238 0.6646 0.8152
No log 5.9535 256 0.6608 0.5485 0.6608 0.8129
No log 6.0 258 0.7754 0.4089 0.7754 0.8806
No log 6.0465 260 0.8789 0.3394 0.8789 0.9375
No log 6.0930 262 0.8222 0.3394 0.8222 0.9067
No log 6.1395 264 0.6994 0.4344 0.6994 0.8363
No log 6.1860 266 0.6379 0.5610 0.6379 0.7987
No log 6.2326 268 0.6305 0.5820 0.6305 0.7941
No log 6.2791 270 0.6474 0.5121 0.6474 0.8046
No log 6.3256 272 0.6914 0.5279 0.6914 0.8315
No log 6.3721 274 0.6871 0.5067 0.6871 0.8289
No log 6.4186 276 0.6234 0.5833 0.6234 0.7895
No log 6.4651 278 0.6026 0.6175 0.6026 0.7763
No log 6.5116 280 0.6001 0.6991 0.6001 0.7746
No log 6.5581 282 0.5775 0.6488 0.5775 0.7599
No log 6.6047 284 0.5626 0.6390 0.5626 0.7500
No log 6.6512 286 0.5583 0.6364 0.5583 0.7472
No log 6.6977 288 0.5796 0.6768 0.5796 0.7613
No log 6.7442 290 0.6205 0.6703 0.6205 0.7877
No log 6.7907 292 0.6411 0.5928 0.6411 0.8007
No log 6.8372 294 0.6354 0.6312 0.6354 0.7971
No log 6.8837 296 0.6217 0.6049 0.6217 0.7885
No log 6.9302 298 0.6207 0.6039 0.6207 0.7878
No log 6.9767 300 0.6326 0.6097 0.6326 0.7953
No log 7.0233 302 0.6433 0.5783 0.6433 0.8021
No log 7.0698 304 0.6494 0.6107 0.6494 0.8059
No log 7.1163 306 0.6768 0.4729 0.6768 0.8227
No log 7.1628 308 0.7279 0.4937 0.7279 0.8532
No log 7.2093 310 0.6955 0.4965 0.6955 0.8340
No log 7.2558 312 0.6532 0.5377 0.6532 0.8082
No log 7.3023 314 0.6516 0.5419 0.6516 0.8072
No log 7.3488 316 0.6429 0.5261 0.6429 0.8018
No log 7.3953 318 0.7094 0.5938 0.7094 0.8423
No log 7.4419 320 0.8209 0.5631 0.8209 0.9060
No log 7.4884 322 0.8171 0.5648 0.8171 0.9039
No log 7.5349 324 0.7878 0.4994 0.7878 0.8876
No log 7.5814 326 0.7035 0.4923 0.7035 0.8388
No log 7.6279 328 0.6425 0.4490 0.6425 0.8016
No log 7.6744 330 0.6584 0.4903 0.6584 0.8114
No log 7.7209 332 0.6920 0.4063 0.6920 0.8318
No log 7.7674 334 0.8222 0.4175 0.8222 0.9067
No log 7.8140 336 0.9480 0.4440 0.9480 0.9736
No log 7.8605 338 0.9251 0.4216 0.9251 0.9618
No log 7.9070 340 0.7796 0.4450 0.7796 0.8829
No log 7.9535 342 0.6851 0.5142 0.6851 0.8277
No log 8.0 344 0.6818 0.5441 0.6818 0.8257
No log 8.0465 346 0.7363 0.5708 0.7363 0.8581
No log 8.0930 348 0.7347 0.5486 0.7347 0.8571
No log 8.1395 350 0.6782 0.4691 0.6782 0.8235
No log 8.1860 352 0.6950 0.4473 0.6950 0.8337
No log 8.2326 354 0.6940 0.4729 0.6940 0.8331
No log 8.2791 356 0.6726 0.5121 0.6726 0.8201
No log 8.3256 358 0.6385 0.5112 0.6385 0.7991
No log 8.3721 360 0.6290 0.5552 0.6290 0.7931
No log 8.4186 362 0.6419 0.5330 0.6419 0.8012
No log 8.4651 364 0.6422 0.5346 0.6422 0.8014
No log 8.5116 366 0.6471 0.5121 0.6471 0.8045
No log 8.5581 368 0.6215 0.5121 0.6215 0.7883
No log 8.6047 370 0.6116 0.5357 0.6116 0.7821
No log 8.6512 372 0.6082 0.5450 0.6082 0.7799
No log 8.6977 374 0.6221 0.5599 0.6221 0.7887
No log 8.7442 376 0.6600 0.5688 0.6600 0.8124
No log 8.7907 378 0.6458 0.4969 0.6458 0.8036
No log 8.8372 380 0.6527 0.6154 0.6527 0.8079
No log 8.8837 382 0.7394 0.5706 0.7394 0.8599
No log 8.9302 384 0.8120 0.5512 0.8120 0.9011
No log 8.9767 386 0.7752 0.5240 0.7752 0.8805
No log 9.0233 388 0.7328 0.3878 0.7328 0.8560
No log 9.0698 390 0.7423 0.4078 0.7423 0.8615
No log 9.1163 392 0.7279 0.4981 0.7279 0.8532
No log 9.1628 394 0.6763 0.4304 0.6763 0.8224
No log 9.2093 396 0.6626 0.6087 0.6626 0.8140
No log 9.2558 398 0.6889 0.5553 0.6889 0.8300
No log 9.3023 400 0.6718 0.5553 0.6718 0.8197
No log 9.3488 402 0.6314 0.6429 0.6314 0.7946
No log 9.3953 404 0.6419 0.4757 0.6419 0.8012
No log 9.4419 406 0.6749 0.5442 0.6749 0.8215
No log 9.4884 408 0.6404 0.4757 0.6404 0.8003
No log 9.5349 410 0.6156 0.6087 0.6156 0.7846
No log 9.5814 412 0.6268 0.5492 0.6268 0.7917
No log 9.6279 414 0.6831 0.4742 0.6831 0.8265
No log 9.6744 416 0.7463 0.5516 0.7463 0.8639
No log 9.7209 418 0.7552 0.5718 0.7552 0.8690
No log 9.7674 420 0.6925 0.4742 0.6925 0.8322
No log 9.8140 422 0.6539 0.4869 0.6539 0.8086
No log 9.8605 424 0.6600 0.4869 0.6600 0.8124
No log 9.9070 426 0.6398 0.5234 0.6398 0.7999
No log 9.9535 428 0.6660 0.5425 0.6660 0.8161
No log 10.0 430 0.7625 0.5330 0.7625 0.8732
No log 10.0465 432 0.7604 0.5591 0.7604 0.8720
No log 10.0930 434 0.7173 0.4483 0.7173 0.8469
No log 10.1395 436 0.6367 0.5359 0.6367 0.7979
No log 10.1860 438 0.6093 0.6118 0.6093 0.7806
No log 10.2326 440 0.5958 0.6327 0.5958 0.7719
No log 10.2791 442 0.6127 0.6073 0.6127 0.7827
No log 10.3256 444 0.6246 0.6063 0.6246 0.7903
No log 10.3721 446 0.6127 0.5135 0.6127 0.7828
No log 10.4186 448 0.6279 0.6047 0.6279 0.7924
No log 10.4651 450 0.6369 0.5833 0.6369 0.7981
No log 10.5116 452 0.6342 0.5025 0.6342 0.7963
No log 10.5581 454 0.6461 0.4988 0.6461 0.8038
No log 10.6047 456 0.6541 0.4854 0.6541 0.8088
No log 10.6512 458 0.6174 0.5345 0.6174 0.7858
No log 10.6977 460 0.5824 0.6087 0.5824 0.7632
No log 10.7442 462 0.5959 0.6804 0.5959 0.7719
No log 10.7907 464 0.5782 0.6337 0.5782 0.7604
No log 10.8372 466 0.5900 0.5370 0.5900 0.7681
No log 10.8837 468 0.6529 0.5858 0.6529 0.8080
No log 10.9302 470 0.7557 0.5137 0.7557 0.8693
No log 10.9767 472 0.7686 0.4893 0.7686 0.8767
No log 11.0233 474 0.7075 0.5266 0.7075 0.8411
No log 11.0698 476 0.6543 0.5654 0.6543 0.8089
No log 11.1163 478 0.6469 0.4988 0.6469 0.8043
No log 11.1628 480 0.6350 0.5063 0.6350 0.7969
No log 11.2093 482 0.6436 0.5992 0.6436 0.8022
No log 11.2558 484 0.6327 0.6207 0.6327 0.7954
No log 11.3023 486 0.6104 0.5833 0.6104 0.7813
No log 11.3488 488 0.5957 0.5882 0.5957 0.7718
No log 11.3953 490 0.5947 0.5759 0.5947 0.7712
No log 11.4419 492 0.6055 0.6217 0.6055 0.7781
No log 11.4884 494 0.6460 0.6422 0.6460 0.8038
No log 11.5349 496 0.6549 0.6422 0.6549 0.8093
No log 11.5814 498 0.6193 0.5692 0.6193 0.7870
0.3083 11.6279 500 0.5990 0.5871 0.5990 0.7739
0.3083 11.6744 502 0.6053 0.5002 0.6053 0.7780
0.3083 11.7209 504 0.6560 0.5858 0.6560 0.8099
0.3083 11.7674 506 0.6390 0.5858 0.6390 0.7994
0.3083 11.8140 508 0.5912 0.5373 0.5912 0.7689
0.3083 11.8605 510 0.5891 0.5966 0.5891 0.7676
0.3083 11.9070 512 0.6011 0.5373 0.6011 0.7753
0.3083 11.9535 514 0.6528 0.5438 0.6528 0.8080
0.3083 12.0 516 0.6916 0.5304 0.6916 0.8316
0.3083 12.0465 518 0.7021 0.5875 0.7021 0.8379
0.3083 12.0930 520 0.6827 0.5626 0.6827 0.8263
0.3083 12.1395 522 0.6645 0.5455 0.6645 0.8152
0.3083 12.1860 524 0.6560 0.5234 0.6560 0.8099
0.3083 12.2326 526 0.6297 0.5373 0.6297 0.7936
0.3083 12.2791 528 0.6223 0.5261 0.6223 0.7889

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
7
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_run3_AugV5_k17_task5_organization

Finetuned
(4204)
this model