ASAP_FineTuningBERT_AugV4_k10_task1_organization_fold3

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7914
  • Qwk: 0.4017
  • Mse: 0.7914
  • Rmse: 0.8896

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: 32
  • eval_batch_size: 32
  • 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 0.002 2 10.7493 0.0040 10.7493 3.2786
No log 0.004 4 9.6829 -0.0011 9.6829 3.1117
No log 0.006 6 8.3238 0.0 8.3238 2.8851
No log 0.008 8 7.1708 0.0 7.1708 2.6778
No log 0.01 10 5.8370 0.0494 5.8370 2.4160
No log 0.012 12 4.7635 0.0137 4.7635 2.1826
No log 0.014 14 3.8240 0.0100 3.8240 1.9555
No log 0.016 16 3.0908 0.0076 3.0908 1.7581
No log 0.018 18 2.4161 0.1294 2.4161 1.5544
No log 0.02 20 1.8225 0.0432 1.8225 1.3500
No log 0.022 22 1.4312 0.0365 1.4312 1.1963
No log 0.024 24 1.2050 0.0202 1.2050 1.0977
No log 0.026 26 0.9904 0.0102 0.9904 0.9952
No log 0.028 28 0.8968 0.2267 0.8968 0.9470
No log 0.03 30 0.8551 0.0810 0.8551 0.9247
No log 0.032 32 0.8721 0.0570 0.8721 0.9339
No log 0.034 34 0.9169 0.0414 0.9169 0.9576
No log 0.036 36 1.0440 0.0314 1.0440 1.0218
No log 0.038 38 1.1137 0.0314 1.1137 1.0553
No log 0.04 40 1.0743 0.0 1.0743 1.0365
No log 0.042 42 1.0201 0.0004 1.0201 1.0100
No log 0.044 44 0.9651 0.0314 0.9651 0.9824
No log 0.046 46 0.9591 0.0414 0.9591 0.9794
No log 0.048 48 0.8483 0.0669 0.8483 0.9210
No log 0.05 50 0.9799 0.0504 0.9799 0.9899
No log 0.052 52 0.8969 0.0414 0.8969 0.9471
No log 0.054 54 1.0213 0.0571 1.0213 1.0106
No log 0.056 56 1.4258 0.1688 1.4258 1.1940
No log 0.058 58 1.3677 0.1888 1.3677 1.1695
No log 0.06 60 0.8972 0.0244 0.8972 0.9472
No log 0.062 62 0.9012 0.0087 0.9012 0.9493
No log 0.064 64 1.2113 0.0151 1.2113 1.1006
No log 0.066 66 1.3918 0.1202 1.3918 1.1797
No log 0.068 68 1.2457 -0.0047 1.2457 1.1161
No log 0.07 70 1.0970 0.0 1.0970 1.0474
No log 0.072 72 0.9605 0.0 0.9605 0.9800
No log 0.074 74 0.9415 0.0 0.9415 0.9703
No log 0.076 76 1.0869 0.0 1.0869 1.0425
No log 0.078 78 1.3325 0.0794 1.3325 1.1543
No log 0.08 80 1.2986 0.0006 1.2986 1.1396
No log 0.082 82 1.0482 0.0 1.0482 1.0238
No log 0.084 84 1.0073 0.0 1.0073 1.0036
No log 0.086 86 1.0936 0.0 1.0936 1.0457
No log 0.088 88 1.1003 0.0 1.1003 1.0489
No log 0.09 90 0.9262 0.0157 0.9262 0.9624
No log 0.092 92 0.9341 0.1966 0.9341 0.9665
No log 0.094 94 0.8601 0.0808 0.8601 0.9274
No log 0.096 96 1.1414 0.0 1.1414 1.0683
No log 0.098 98 1.3246 0.0145 1.3246 1.1509
No log 0.1 100 1.2639 -0.0017 1.2639 1.1242
No log 0.102 102 1.2556 -0.0101 1.2556 1.1205
No log 0.104 104 1.3104 0.0960 1.3104 1.1447
No log 0.106 106 1.3687 0.0834 1.3687 1.1699
No log 0.108 108 1.5005 0.0688 1.5005 1.2249
No log 0.11 110 1.7084 0.0659 1.7084 1.3071
No log 0.112 112 1.7534 0.0693 1.7534 1.3242
No log 0.114 114 1.3826 0.0995 1.3826 1.1759
No log 0.116 116 1.1347 0.1341 1.1347 1.0652
No log 0.118 118 1.2773 0.0766 1.2773 1.1302
No log 0.12 120 1.4127 0.0805 1.4127 1.1886
No log 0.122 122 1.2301 0.1206 1.2301 1.1091
No log 0.124 124 1.1998 0.1074 1.1998 1.0954
No log 0.126 126 1.1496 0.1306 1.1496 1.0722
No log 0.128 128 1.4341 0.0834 1.4341 1.1975
No log 0.13 130 1.5860 0.0680 1.5860 1.2594
No log 0.132 132 1.5379 0.0811 1.5379 1.2401
No log 0.134 134 1.4940 0.0806 1.4940 1.2223
No log 0.136 136 1.5541 0.0758 1.5541 1.2466
No log 0.138 138 1.6454 0.0856 1.6454 1.2827
No log 0.14 140 1.5299 0.0809 1.5299 1.2369
No log 0.142 142 1.3453 0.1096 1.3453 1.1599
No log 0.144 144 1.2226 0.1835 1.2226 1.1057
No log 0.146 146 1.2006 0.1785 1.2006 1.0957
No log 0.148 148 1.2392 0.1478 1.2392 1.1132
No log 0.15 150 1.3258 0.1252 1.3258 1.1514
No log 0.152 152 1.5230 0.1187 1.5230 1.2341
No log 0.154 154 1.6508 0.1204 1.6508 1.2848
No log 0.156 156 1.4150 0.1406 1.4150 1.1896
No log 0.158 158 0.9716 0.0533 0.9716 0.9857
No log 0.16 160 0.8905 0.0955 0.8905 0.9436
No log 0.162 162 1.0956 0.1853 1.0956 1.0467
No log 0.164 164 1.5174 0.1369 1.5174 1.2318
No log 0.166 166 1.6238 0.1230 1.6238 1.2743
No log 0.168 168 1.3760 0.1760 1.3760 1.1730
No log 0.17 170 1.0728 0.1454 1.0728 1.0357
No log 0.172 172 0.8328 0.1548 0.8328 0.9126
No log 0.174 174 0.9007 0.2032 0.9007 0.9491
No log 0.176 176 0.8910 0.1963 0.8910 0.9439
No log 0.178 178 0.8774 0.0740 0.8774 0.9367
No log 0.18 180 1.0257 0.1519 1.0257 1.0128
No log 0.182 182 1.0176 0.1426 1.0176 1.0088
No log 0.184 184 1.0454 0.1229 1.0454 1.0224
No log 0.186 186 1.0372 0.1489 1.0372 1.0184
No log 0.188 188 0.9263 0.1295 0.9263 0.9624
No log 0.19 190 0.8793 0.0442 0.8793 0.9377
No log 0.192 192 0.9104 0.0954 0.9104 0.9541
No log 0.194 194 1.0633 0.1467 1.0633 1.0312
No log 0.196 196 1.0470 0.1462 1.0470 1.0232
No log 0.198 198 0.9118 0.0323 0.9118 0.9549
No log 0.2 200 0.8348 0.0157 0.8348 0.9137
No log 0.202 202 0.8718 0.2239 0.8718 0.9337
No log 0.204 204 0.8531 0.1512 0.8531 0.9236
No log 0.206 206 0.8352 0.0157 0.8352 0.9139
No log 0.208 208 0.8420 0.0 0.8420 0.9176
No log 0.21 210 0.8602 0.0005 0.8602 0.9275
No log 0.212 212 0.8163 0.0307 0.8163 0.9035
No log 0.214 214 0.8016 0.2007 0.8016 0.8953
No log 0.216 216 0.8008 0.2007 0.8008 0.8949
No log 0.218 218 0.8049 0.0750 0.8049 0.8972
No log 0.22 220 0.9266 0.1209 0.9266 0.9626
No log 0.222 222 1.0983 0.2022 1.0983 1.0480
No log 0.224 224 1.1488 0.1884 1.1488 1.0718
No log 0.226 226 1.0022 0.1948 1.0022 1.0011
No log 0.228 228 0.8127 0.2900 0.8127 0.9015
No log 0.23 230 0.7665 0.2917 0.7665 0.8755
No log 0.232 232 0.8054 0.2342 0.8054 0.8974
No log 0.234 234 0.9782 0.2348 0.9782 0.9890
No log 0.236 236 1.0586 0.2128 1.0586 1.0289
No log 0.238 238 0.9769 0.2320 0.9769 0.9884
No log 0.24 240 0.8541 0.2670 0.8541 0.9242
No log 0.242 242 0.8089 0.2598 0.8089 0.8994
No log 0.244 244 0.7313 0.3444 0.7313 0.8552
No log 0.246 246 0.7872 0.3285 0.7872 0.8872
No log 0.248 248 0.7700 0.3333 0.7700 0.8775
No log 0.25 250 0.7248 0.3355 0.7248 0.8513
No log 0.252 252 0.7927 0.3231 0.7927 0.8904
No log 0.254 254 0.7353 0.3198 0.7353 0.8575
No log 0.256 256 0.7039 0.3270 0.7039 0.8390
No log 0.258 258 0.7069 0.3179 0.7069 0.8408
No log 0.26 260 0.7106 0.3118 0.7106 0.8430
No log 0.262 262 0.7200 0.2725 0.7200 0.8485
No log 0.264 264 0.7221 0.2714 0.7221 0.8498
No log 0.266 266 0.7297 0.3238 0.7297 0.8542
No log 0.268 268 0.7236 0.3201 0.7236 0.8506
No log 0.27 270 0.7341 0.3149 0.7341 0.8568
No log 0.272 272 0.7740 0.3232 0.7740 0.8798
No log 0.274 274 0.7947 0.3102 0.7947 0.8915
No log 0.276 276 0.8651 0.2274 0.8651 0.9301
No log 0.278 278 0.9148 0.2002 0.9148 0.9564
No log 0.28 280 0.8501 0.2568 0.8501 0.9220
No log 0.282 282 0.7522 0.3388 0.7522 0.8673
No log 0.284 284 0.7228 0.3446 0.7228 0.8502
No log 0.286 286 0.7180 0.2437 0.7180 0.8474
No log 0.288 288 0.8092 0.2166 0.8092 0.8995
No log 0.29 290 0.9961 0.3054 0.9961 0.9980
No log 0.292 292 0.8987 0.2592 0.8987 0.9480
No log 0.294 294 0.7143 0.2616 0.7143 0.8452
No log 0.296 296 0.7832 0.3455 0.7832 0.8850
No log 0.298 298 0.7516 0.3214 0.7516 0.8669
No log 0.3 300 0.6964 0.3299 0.6964 0.8345
No log 0.302 302 0.9143 0.3485 0.9143 0.9562
No log 0.304 304 0.9549 0.3416 0.9549 0.9772
No log 0.306 306 0.7522 0.3587 0.7522 0.8673
No log 0.308 308 0.6154 0.4361 0.6154 0.7845
No log 0.31 310 0.6062 0.4497 0.6062 0.7786
No log 0.312 312 0.6456 0.4433 0.6456 0.8035
No log 0.314 314 0.8019 0.3857 0.8019 0.8955
No log 0.316 316 0.7213 0.4212 0.7213 0.8493
No log 0.318 318 0.6095 0.4961 0.6095 0.7807
No log 0.32 320 0.6128 0.5070 0.6128 0.7828
No log 0.322 322 0.7160 0.4404 0.7160 0.8462
No log 0.324 324 0.8025 0.4158 0.8025 0.8958
No log 0.326 326 0.6298 0.4122 0.6298 0.7936
No log 0.328 328 0.5971 0.4372 0.5971 0.7727
No log 0.33 330 0.6095 0.4412 0.6095 0.7807
No log 0.332 332 0.6118 0.4954 0.6118 0.7822
No log 0.334 334 0.6420 0.4955 0.6420 0.8013
No log 0.336 336 0.6488 0.4509 0.6488 0.8055
No log 0.338 338 0.6171 0.4589 0.6171 0.7856
No log 0.34 340 0.6169 0.4365 0.6169 0.7854
No log 0.342 342 0.7108 0.4425 0.7108 0.8431
No log 0.344 344 0.8270 0.4050 0.8270 0.9094
No log 0.346 346 0.6992 0.4543 0.6992 0.8362
No log 0.348 348 0.7160 0.4564 0.7160 0.8462
No log 0.35 350 0.7815 0.4377 0.7815 0.8840
No log 0.352 352 0.9030 0.4082 0.9030 0.9503
No log 0.354 354 0.6855 0.4958 0.6855 0.8280
No log 0.356 356 0.6695 0.5104 0.6695 0.8182
No log 0.358 358 0.6726 0.5098 0.6726 0.8201
No log 0.36 360 0.6907 0.4826 0.6907 0.8311
No log 0.362 362 0.5979 0.4814 0.5979 0.7732
No log 0.364 364 0.5905 0.4853 0.5905 0.7685
No log 0.366 366 0.6405 0.5103 0.6405 0.8003
No log 0.368 368 0.6527 0.5194 0.6527 0.8079
No log 0.37 370 0.6401 0.5115 0.6401 0.8001
No log 0.372 372 0.6117 0.4518 0.6117 0.7821
No log 0.374 374 0.6061 0.4517 0.6061 0.7785
No log 0.376 376 0.6997 0.4859 0.6997 0.8365
No log 0.378 378 0.7658 0.4741 0.7658 0.8751
No log 0.38 380 0.6240 0.5079 0.6240 0.7900
No log 0.382 382 0.6095 0.4759 0.6095 0.7807
No log 0.384 384 0.6220 0.4998 0.6220 0.7887
No log 0.386 386 0.6525 0.5146 0.6525 0.8078
No log 0.388 388 0.6313 0.4874 0.6313 0.7945
No log 0.39 390 0.6418 0.5162 0.6418 0.8011
No log 0.392 392 0.7571 0.4955 0.7571 0.8701
No log 0.394 394 0.7026 0.4999 0.7026 0.8382
No log 0.396 396 0.6311 0.4969 0.6311 0.7944
No log 0.398 398 0.6961 0.4871 0.6961 0.8343
No log 0.4 400 0.6885 0.4793 0.6885 0.8298
No log 0.402 402 0.6702 0.4794 0.6702 0.8187
No log 0.404 404 0.7086 0.4689 0.7086 0.8418
No log 0.406 406 0.7166 0.4740 0.7166 0.8465
No log 0.408 408 0.8183 0.4502 0.8183 0.9046
No log 0.41 410 0.7186 0.4962 0.7186 0.8477
No log 0.412 412 0.7282 0.4894 0.7282 0.8533
No log 0.414 414 0.7047 0.4973 0.7047 0.8395
No log 0.416 416 0.6212 0.4480 0.6212 0.7882
No log 0.418 418 0.6159 0.4358 0.6159 0.7848
No log 0.42 420 0.6270 0.4954 0.6270 0.7918
No log 0.422 422 0.7330 0.4886 0.7330 0.8561
No log 0.424 424 0.6514 0.5094 0.6514 0.8071
No log 0.426 426 0.6307 0.4245 0.6307 0.7942
No log 0.428 428 0.6228 0.4377 0.6228 0.7892
No log 0.43 430 0.6566 0.5001 0.6566 0.8103
No log 0.432 432 0.7945 0.4416 0.7945 0.8913
No log 0.434 434 0.7081 0.4969 0.7081 0.8415
No log 0.436 436 0.6270 0.4507 0.6270 0.7918
No log 0.438 438 0.6416 0.4640 0.6416 0.8010
No log 0.44 440 0.7029 0.4884 0.7029 0.8384
No log 0.442 442 0.7041 0.4891 0.7041 0.8391
No log 0.444 444 0.6797 0.4641 0.6797 0.8244
No log 0.446 446 0.6911 0.4790 0.6911 0.8313
No log 0.448 448 0.8377 0.4570 0.8377 0.9153
No log 0.45 450 0.8680 0.4632 0.8680 0.9317
No log 0.452 452 0.9447 0.4044 0.9447 0.9720
No log 0.454 454 0.7932 0.4512 0.7932 0.8906
No log 0.456 456 0.8156 0.4360 0.8156 0.9031
No log 0.458 458 0.9904 0.3851 0.9904 0.9952
No log 0.46 460 0.9502 0.3924 0.9502 0.9748
No log 0.462 462 0.9343 0.3864 0.9343 0.9666
No log 0.464 464 0.9052 0.3906 0.9052 0.9514
No log 0.466 466 1.0362 0.3710 1.0362 1.0179
No log 0.468 468 0.8070 0.4403 0.8070 0.8983
No log 0.47 470 0.6795 0.4898 0.6795 0.8243
No log 0.472 472 0.7260 0.4798 0.7260 0.8520
No log 0.474 474 0.9754 0.4206 0.9754 0.9876
No log 0.476 476 0.7324 0.4989 0.7324 0.8558
No log 0.478 478 0.6448 0.4872 0.6448 0.8030
No log 0.48 480 0.7227 0.4797 0.7227 0.8501
No log 0.482 482 0.9849 0.4153 0.9849 0.9924
No log 0.484 484 0.7630 0.4781 0.7630 0.8735
No log 0.486 486 0.8156 0.4656 0.8156 0.9031
No log 0.488 488 0.8352 0.4501 0.8352 0.9139
No log 0.49 490 0.8500 0.4507 0.8500 0.9219
No log 0.492 492 0.8022 0.4525 0.8022 0.8957
No log 0.494 494 1.0262 0.4103 1.0262 1.0130
No log 0.496 496 0.9717 0.4273 0.9717 0.9858
No log 0.498 498 0.7782 0.4540 0.7782 0.8822
1.0247 0.5 500 0.9122 0.4515 0.9122 0.9551
1.0247 0.502 502 1.2111 0.3792 1.2111 1.1005
1.0247 0.504 504 0.8469 0.4674 0.8469 0.9203
1.0247 0.506 506 0.6521 0.4275 0.6521 0.8075
1.0247 0.508 508 0.6555 0.4439 0.6555 0.8096
1.0247 0.51 510 0.9985 0.4203 0.9985 0.9993
1.0247 0.512 512 1.1860 0.3861 1.1860 1.0890
1.0247 0.514 514 0.8301 0.4516 0.8301 0.9111
1.0247 0.516 516 0.6669 0.4434 0.6669 0.8167
1.0247 0.518 518 0.6880 0.4756 0.6880 0.8295
1.0247 0.52 520 0.9152 0.4654 0.9152 0.9567
1.0247 0.522 522 0.8087 0.4788 0.8087 0.8993
1.0247 0.524 524 0.7028 0.4743 0.7028 0.8383
1.0247 0.526 526 0.7358 0.4812 0.7358 0.8578
1.0247 0.528 528 0.9576 0.4079 0.9576 0.9786
1.0247 0.53 530 0.9196 0.4336 0.9196 0.9589
1.0247 0.532 532 0.8346 0.4860 0.8346 0.9136
1.0247 0.534 534 0.7685 0.4258 0.7685 0.8766
1.0247 0.536 536 0.7953 0.4675 0.7953 0.8918
1.0247 0.538 538 1.0800 0.4407 1.0800 1.0392
1.0247 0.54 540 1.2154 0.4011 1.2154 1.1025
1.0247 0.542 542 0.8162 0.4799 0.8162 0.9034
1.0247 0.544 544 0.6911 0.4614 0.6911 0.8313
1.0247 0.546 546 0.8036 0.4642 0.8036 0.8964
1.0247 0.548 548 0.9373 0.4156 0.9373 0.9681
1.0247 0.55 550 0.7630 0.4716 0.7630 0.8735
1.0247 0.552 552 0.7202 0.4721 0.7202 0.8487
1.0247 0.554 554 0.8472 0.4519 0.8472 0.9204
1.0247 0.556 556 0.7661 0.4725 0.7661 0.8752
1.0247 0.558 558 0.7026 0.4207 0.7026 0.8382
1.0247 0.56 560 0.7791 0.4241 0.7791 0.8827
1.0247 0.562 562 1.1233 0.3726 1.1233 1.0598
1.0247 0.564 564 0.9951 0.4248 0.9951 0.9975
1.0247 0.566 566 0.7914 0.4017 0.7914 0.8896

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
20
Safetensors
Model size
0.1B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for MayBashendy/ASAP_FineTuningBERT_AugV4_k10_task1_organization_fold3

Finetuned
(7,069)
this model