ASAP_FineTuningBERT_AugV3_k5_task1_organization_fold1

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: 0.9294
  • Qwk: 0.3609
  • Mse: 0.9294
  • Rmse: 0.9641

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 0.0033 2 9.6140 0.0 9.6140 3.1006
No log 0.0065 4 8.7259 0.0 8.7259 2.9540
No log 0.0098 6 8.2950 -0.0047 8.2950 2.8801
No log 0.0130 8 7.8875 0.0 7.8875 2.8085
No log 0.0163 10 7.4017 0.0 7.4017 2.7206
No log 0.0195 12 6.7560 0.0 6.7560 2.5992
No log 0.0228 14 5.8698 0.0 5.8698 2.4228
No log 0.0261 16 4.9635 0.0 4.9635 2.2279
No log 0.0293 18 4.2735 0.0 4.2735 2.0673
No log 0.0326 20 3.6491 0.0503 3.6491 1.9103
No log 0.0358 22 3.1627 0.0104 3.1627 1.7784
No log 0.0391 24 2.7113 0.0079 2.7113 1.6466
No log 0.0423 26 2.2363 0.0 2.2363 1.4954
No log 0.0456 28 1.8612 0.0 1.8612 1.3643
No log 0.0489 30 1.6641 0.0 1.6641 1.2900
No log 0.0521 32 1.6504 0.0 1.6504 1.2847
No log 0.0554 34 1.7557 0.0 1.7557 1.3250
No log 0.0586 36 1.9434 0.0 1.9434 1.3941
No log 0.0619 38 2.4072 0.0 2.4072 1.5515
No log 0.0651 40 2.5614 0.0 2.5614 1.6004
No log 0.0684 42 2.3610 0.0 2.3610 1.5365
No log 0.0717 44 2.1133 0.0 2.1133 1.4537
No log 0.0749 46 1.9946 0.0 1.9946 1.4123
No log 0.0782 48 2.0201 0.0 2.0201 1.4213
No log 0.0814 50 1.8936 0.0 1.8936 1.3761
No log 0.0847 52 1.8029 0.0 1.8029 1.3427
No log 0.0879 54 1.8006 0.0 1.8006 1.3419
No log 0.0912 56 1.8592 0.0 1.8592 1.3635
No log 0.0945 58 1.8380 0.0 1.8380 1.3557
No log 0.0977 60 1.8292 0.0 1.8292 1.3525
No log 0.1010 62 1.9889 0.0 1.9889 1.4103
No log 0.1042 64 2.4499 0.0 2.4499 1.5652
No log 0.1075 66 2.7045 0.0 2.7045 1.6445
No log 0.1107 68 2.3949 0.0 2.3949 1.5476
No log 0.1140 70 2.0035 0.0 2.0035 1.4155
No log 0.1173 72 1.8302 0.0 1.8302 1.3529
No log 0.1205 74 1.8040 0.0 1.8040 1.3431
No log 0.1238 76 1.7613 0.0 1.7613 1.3271
No log 0.1270 78 1.8426 0.0 1.8426 1.3574
No log 0.1303 80 1.9789 0.0 1.9789 1.4067
No log 0.1336 82 2.0843 0.0 2.0843 1.4437
No log 0.1368 84 2.0706 0.0 2.0706 1.4389
No log 0.1401 86 1.9499 0.0 1.9499 1.3964
No log 0.1433 88 1.7851 0.0 1.7851 1.3361
No log 0.1466 90 1.6054 0.0 1.6054 1.2670
No log 0.1498 92 1.4898 0.0 1.4898 1.2206
No log 0.1531 94 1.4104 0.0712 1.4104 1.1876
No log 0.1564 96 1.3918 0.1030 1.3918 1.1797
No log 0.1596 98 1.3858 0.1012 1.3858 1.1772
No log 0.1629 100 1.5173 -0.0085 1.5173 1.2318
No log 0.1661 102 1.6835 -0.0044 1.6835 1.2975
No log 0.1694 104 1.6097 -0.0135 1.6097 1.2687
No log 0.1726 106 1.3596 0.0792 1.3596 1.1660
No log 0.1759 108 1.1996 0.1023 1.1996 1.0953
No log 0.1792 110 1.1195 0.0921 1.1195 1.0580
No log 0.1824 112 1.0825 0.0881 1.0825 1.0405
No log 0.1857 114 1.0694 0.0881 1.0694 1.0341
No log 0.1889 116 1.0690 0.0921 1.0690 1.0339
No log 0.1922 118 1.0796 0.0921 1.0796 1.0390
No log 0.1954 120 1.1058 0.0921 1.1058 1.0516
No log 0.1987 122 1.1494 0.0974 1.1494 1.0721
No log 0.2020 124 1.2223 0.1117 1.2223 1.1056
No log 0.2052 126 1.2695 0.1223 1.2695 1.1267
No log 0.2085 128 1.1884 0.1110 1.1884 1.0901
No log 0.2117 130 1.1241 0.0906 1.1241 1.0602
No log 0.2150 132 1.1219 0.1010 1.1219 1.0592
No log 0.2182 134 1.1572 0.1010 1.1572 1.0758
No log 0.2215 136 1.1598 0.1010 1.1598 1.0769
No log 0.2248 138 1.1398 0.1010 1.1398 1.0676
No log 0.2280 140 1.0846 0.1010 1.0846 1.0414
No log 0.2313 142 0.9659 0.0921 0.9659 0.9828
No log 0.2345 144 0.9108 0.0921 0.9108 0.9543
No log 0.2378 146 0.8885 0.0921 0.8885 0.9426
No log 0.2410 148 0.8740 0.0921 0.8740 0.9349
No log 0.2443 150 0.8657 0.0921 0.8657 0.9305
No log 0.2476 152 0.8629 0.0921 0.8629 0.9289
No log 0.2508 154 0.8675 0.0921 0.8675 0.9314
No log 0.2541 156 0.8705 0.0921 0.8705 0.9330
No log 0.2573 158 0.8729 0.0921 0.8729 0.9343
No log 0.2606 160 0.8787 0.0840 0.8787 0.9374
No log 0.2638 162 0.8859 0.0798 0.8859 0.9412
No log 0.2671 164 0.8824 0.0916 0.8824 0.9394
No log 0.2704 166 0.8848 0.0777 0.8848 0.9406
No log 0.2736 168 0.8735 0.0916 0.8735 0.9346
No log 0.2769 170 0.8599 0.0921 0.8599 0.9273
No log 0.2801 172 0.8518 0.0921 0.8518 0.9229
No log 0.2834 174 0.8479 0.0921 0.8479 0.9208
No log 0.2866 176 0.8472 0.0936 0.8472 0.9204
No log 0.2899 178 0.8486 0.0860 0.8486 0.9212
No log 0.2932 180 0.8538 0.0777 0.8538 0.9240
No log 0.2964 182 0.8531 0.0777 0.8531 0.9236
No log 0.2997 184 0.8487 0.0921 0.8487 0.9212
No log 0.3029 186 0.8513 0.0921 0.8513 0.9227
No log 0.3062 188 0.8629 0.0921 0.8629 0.9289
No log 0.3094 190 0.8632 0.0921 0.8632 0.9291
No log 0.3127 192 0.8639 0.0921 0.8639 0.9295
No log 0.3160 194 0.8532 0.0921 0.8532 0.9237
No log 0.3192 196 0.8472 0.0921 0.8472 0.9205
No log 0.3225 198 0.8467 0.0921 0.8467 0.9201
No log 0.3257 200 0.8454 0.0921 0.8454 0.9195
No log 0.3290 202 0.8486 0.0921 0.8486 0.9212
No log 0.3322 204 0.8550 0.0921 0.8550 0.9246
No log 0.3355 206 0.8407 0.0921 0.8407 0.9169
No log 0.3388 208 0.8268 0.0921 0.8268 0.9093
No log 0.3420 210 0.8186 0.0921 0.8186 0.9048
No log 0.3453 212 0.8138 0.0921 0.8138 0.9021
No log 0.3485 214 0.8475 0.0984 0.8475 0.9206
No log 0.3518 216 0.8660 0.0984 0.8660 0.9306
No log 0.3550 218 0.8456 0.0965 0.8456 0.9196
No log 0.3583 220 0.8137 0.0921 0.8137 0.9021
No log 0.3616 222 0.8288 0.0921 0.8288 0.9104
No log 0.3648 224 0.8619 0.0921 0.8619 0.9284
No log 0.3681 226 0.8825 0.0916 0.8825 0.9394
No log 0.3713 228 0.8974 0.0916 0.8974 0.9473
No log 0.3746 230 0.9156 0.0896 0.9156 0.9569
No log 0.3779 232 0.8499 0.0901 0.8499 0.9219
No log 0.3811 234 0.8244 0.0921 0.8244 0.9080
No log 0.3844 236 0.8159 0.0921 0.8159 0.9033
No log 0.3876 238 0.8137 0.0921 0.8137 0.9020
No log 0.3909 240 0.8109 0.0921 0.8109 0.9005
No log 0.3941 242 0.8162 0.0921 0.8162 0.9034
No log 0.3974 244 0.8172 0.0921 0.8172 0.9040
No log 0.4007 246 0.8142 0.0896 0.8142 0.9023
No log 0.4039 248 0.8124 0.0855 0.8124 0.9013
No log 0.4072 250 0.8145 0.0631 0.8145 0.9025
No log 0.4104 252 0.8213 0.0638 0.8213 0.9063
No log 0.4137 254 0.8153 0.0638 0.8153 0.9029
No log 0.4169 256 0.8300 0.0638 0.8300 0.9110
No log 0.4202 258 0.8733 0.0779 0.8733 0.9345
No log 0.4235 260 0.8837 0.0901 0.8837 0.9400
No log 0.4267 262 0.8426 0.0921 0.8426 0.9179
No log 0.4300 264 0.8124 0.0921 0.8124 0.9013
No log 0.4332 266 0.7867 0.0921 0.7867 0.8870
No log 0.4365 268 0.7779 0.0921 0.7779 0.8820
No log 0.4397 270 0.7645 0.0921 0.7645 0.8743
No log 0.4430 272 0.7549 0.0921 0.7549 0.8689
No log 0.4463 274 0.7471 0.0921 0.7471 0.8644
No log 0.4495 276 0.7422 0.0921 0.7422 0.8615
No log 0.4528 278 0.7392 0.0875 0.7392 0.8598
No log 0.4560 280 0.7606 0.2395 0.7606 0.8721
No log 0.4593 282 0.7975 0.4193 0.7975 0.8931
No log 0.4625 284 0.8665 0.4624 0.8665 0.9308
No log 0.4658 286 0.8741 0.4615 0.8741 0.9350
No log 0.4691 288 0.8578 0.3897 0.8578 0.9262
No log 0.4723 290 0.8369 0.2220 0.8369 0.9148
No log 0.4756 292 0.8222 0.1193 0.8222 0.9067
No log 0.4788 294 0.8118 0.1027 0.8118 0.9010
No log 0.4821 296 0.8046 0.0855 0.8046 0.8970
No log 0.4853 298 0.8587 0.0646 0.8587 0.9267
No log 0.4886 300 0.9968 0.0956 0.9968 0.9984
No log 0.4919 302 0.9082 0.0941 0.9082 0.9530
No log 0.4951 304 0.8267 0.0860 0.8267 0.9093
No log 0.4984 306 0.7782 0.0804 0.7782 0.8821
No log 0.5016 308 0.7684 0.0887 0.7684 0.8766
No log 0.5049 310 0.7518 0.0983 0.7518 0.8671
No log 0.5081 312 0.7322 0.1135 0.7322 0.8557
No log 0.5114 314 0.7201 0.1266 0.7201 0.8486
No log 0.5147 316 0.7136 0.1818 0.7136 0.8447
No log 0.5179 318 0.7151 0.2711 0.7151 0.8456
No log 0.5212 320 0.7115 0.1438 0.7115 0.8435
No log 0.5244 322 0.7123 0.0921 0.7123 0.8440
No log 0.5277 324 0.7105 0.0921 0.7105 0.8429
No log 0.5309 326 0.6992 0.1143 0.6992 0.8362
No log 0.5342 328 0.7353 0.3891 0.7353 0.8575
No log 0.5375 330 0.8402 0.4454 0.8402 0.9166
No log 0.5407 332 0.9197 0.3463 0.9197 0.9590
No log 0.5440 334 0.9559 0.2454 0.9559 0.9777
No log 0.5472 336 0.9688 0.2361 0.9688 0.9843
No log 0.5505 338 0.9590 0.2485 0.9590 0.9793
No log 0.5537 340 0.9484 0.2845 0.9484 0.9738
No log 0.5570 342 0.9371 0.3476 0.9371 0.9680
No log 0.5603 344 0.9213 0.3678 0.9213 0.9598
No log 0.5635 346 0.8818 0.4034 0.8818 0.9391
No log 0.5668 348 0.8304 0.0988 0.8304 0.9113
No log 0.5700 350 0.7943 0.0866 0.7943 0.8913
No log 0.5733 352 0.8366 0.0866 0.8366 0.9146
No log 0.5765 354 0.9344 0.0840 0.9344 0.9667
No log 0.5798 356 0.9919 0.0905 0.9919 0.9959
No log 0.5831 358 1.0125 0.0905 1.0125 1.0062
No log 0.5863 360 1.0020 0.0991 1.0020 1.0010
No log 0.5896 362 0.9705 0.0975 0.9705 0.9851
No log 0.5928 364 0.8979 0.0975 0.8979 0.9476
No log 0.5961 366 0.8032 0.0975 0.8032 0.8962
No log 0.5993 368 0.7616 0.0921 0.7616 0.8727
No log 0.6026 370 0.7803 0.0921 0.7803 0.8834
No log 0.6059 372 0.8244 0.1403 0.8244 0.9079
No log 0.6091 374 0.8780 0.2177 0.8780 0.9370
No log 0.6124 376 0.9096 0.2871 0.9096 0.9537
No log 0.6156 378 0.9264 0.3275 0.9264 0.9625
No log 0.6189 380 0.9274 0.3373 0.9274 0.9630
No log 0.6221 382 0.9188 0.3513 0.9188 0.9586
No log 0.6254 384 0.9187 0.3582 0.9187 0.9585
No log 0.6287 386 0.8888 0.4070 0.8888 0.9428
No log 0.6319 388 0.8807 0.4147 0.8807 0.9384
No log 0.6352 390 0.8844 0.3984 0.8844 0.9404
No log 0.6384 392 0.8716 0.4209 0.8716 0.9336
No log 0.6417 394 0.8548 0.4385 0.8548 0.9246
No log 0.6450 396 0.8344 0.4569 0.8344 0.9135
No log 0.6482 398 0.8034 0.4148 0.8034 0.8963
No log 0.6515 400 0.7681 0.3813 0.7681 0.8764
No log 0.6547 402 0.7479 0.3027 0.7479 0.8648
No log 0.6580 404 0.7342 0.1131 0.7342 0.8569
No log 0.6612 406 0.7323 0.0921 0.7323 0.8558
No log 0.6645 408 0.7215 0.2325 0.7215 0.8494
No log 0.6678 410 0.7139 0.3819 0.7139 0.8449
No log 0.6710 412 0.6997 0.4149 0.6997 0.8365
No log 0.6743 414 0.6914 0.4532 0.6914 0.8315
No log 0.6775 416 0.7006 0.4987 0.7006 0.8370
No log 0.6808 418 0.7365 0.4859 0.7365 0.8582
No log 0.6840 420 0.8140 0.4447 0.8140 0.9022
No log 0.6873 422 0.8848 0.4183 0.8848 0.9406
No log 0.6906 424 0.8722 0.4304 0.8722 0.9339
No log 0.6938 426 0.7551 0.5162 0.7551 0.8689
No log 0.6971 428 0.6371 0.4729 0.6371 0.7982
No log 0.7003 430 0.5860 0.4107 0.5860 0.7655
No log 0.7036 432 0.6528 0.4087 0.6528 0.8080
No log 0.7068 434 0.7610 0.3614 0.7610 0.8724
No log 0.7101 436 0.7706 0.3469 0.7706 0.8778
No log 0.7134 438 0.6672 0.4366 0.6672 0.8168
No log 0.7166 440 0.6143 0.4690 0.6143 0.7838
No log 0.7199 442 0.5969 0.4944 0.5969 0.7726
No log 0.7231 444 0.6025 0.4895 0.6025 0.7762
No log 0.7264 446 0.6345 0.4988 0.6345 0.7966
No log 0.7296 448 0.6751 0.4998 0.6751 0.8216
No log 0.7329 450 0.6893 0.4818 0.6893 0.8302
No log 0.7362 452 0.7341 0.4761 0.7341 0.8568
No log 0.7394 454 0.7492 0.4728 0.7492 0.8655
No log 0.7427 456 0.7664 0.4768 0.7664 0.8754
No log 0.7459 458 0.7417 0.4767 0.7417 0.8612
No log 0.7492 460 0.7344 0.4956 0.7344 0.8570
No log 0.7524 462 0.7158 0.5190 0.7158 0.8460
No log 0.7557 464 0.7007 0.4858 0.7007 0.8371
No log 0.7590 466 0.6773 0.4247 0.6773 0.8230
No log 0.7622 468 0.6559 0.2726 0.6559 0.8099
No log 0.7655 470 0.6524 0.0947 0.6524 0.8077
No log 0.7687 472 0.7080 0.1531 0.7080 0.8414
No log 0.7720 474 0.7787 0.2015 0.7787 0.8825
No log 0.7752 476 0.7403 0.2038 0.7403 0.8604
No log 0.7785 478 0.6566 0.2015 0.6566 0.8103
No log 0.7818 480 0.6067 0.2569 0.6067 0.7789
No log 0.7850 482 0.5877 0.4430 0.5877 0.7666
No log 0.7883 484 0.5799 0.4612 0.5799 0.7615
No log 0.7915 486 0.5814 0.4669 0.5814 0.7625
No log 0.7948 488 0.6061 0.4630 0.6061 0.7785
No log 0.7980 490 0.6510 0.4667 0.6510 0.8068
No log 0.8013 492 0.7329 0.4132 0.7329 0.8561
No log 0.8046 494 0.7517 0.4037 0.7517 0.8670
No log 0.8078 496 0.6852 0.4482 0.6852 0.8278
No log 0.8111 498 0.5815 0.4676 0.5815 0.7626
1.485 0.8143 500 0.5725 0.4837 0.5725 0.7566
1.485 0.8176 502 0.5919 0.4902 0.5919 0.7694
1.485 0.8208 504 0.6935 0.5244 0.6935 0.8328
1.485 0.8241 506 0.7953 0.4627 0.7953 0.8918
1.485 0.8274 508 0.8814 0.4009 0.8814 0.9388
1.485 0.8306 510 0.9434 0.3642 0.9434 0.9713
1.485 0.8339 512 0.9820 0.3073 0.9820 0.9910
1.485 0.8371 514 0.9294 0.3609 0.9294 0.9641

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/ASAP_FineTuningBERT_AugV3_k5_task1_organization_fold1

Finetuned
(7009)
this model