ASAP_FineTuningBERT_AugV3_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: 0.9502
  • Qwk: 0.2125
  • Mse: 0.9502
  • Rmse: 0.9748

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 0.0017 2 10.5345 0.0 10.5345 3.2457
No log 0.0034 4 8.9519 -0.0027 8.9519 2.9920
No log 0.0052 6 7.1550 0.0068 7.1550 2.6749
No log 0.0069 8 5.7392 0.0 5.7392 2.3957
No log 0.0086 10 4.7937 0.0 4.7937 2.1894
No log 0.0103 12 3.7973 0.0598 3.7973 1.9487
No log 0.0120 14 3.0378 0.0157 3.0378 1.7429
No log 0.0137 16 2.9018 0.0076 2.9018 1.7035
No log 0.0155 18 4.2997 -0.0563 4.2997 2.0736
No log 0.0172 20 3.0733 -0.0037 3.0733 1.7531
No log 0.0189 22 2.2047 0.0 2.2047 1.4848
No log 0.0206 24 1.9538 0.0 1.9538 1.3978
No log 0.0223 26 2.0099 0.0 2.0099 1.4177
No log 0.0241 28 2.4490 0.0 2.4490 1.5649
No log 0.0258 30 1.9922 0.0 1.9922 1.4115
No log 0.0275 32 1.6940 0.0 1.6940 1.3015
No log 0.0292 34 1.8786 0.0 1.8786 1.3706
No log 0.0309 36 2.3669 0.0 2.3669 1.5385
No log 0.0326 38 2.3616 0.0 2.3616 1.5368
No log 0.0344 40 2.4495 0.0 2.4495 1.5651
No log 0.0361 42 2.6362 0.0 2.6362 1.6236
No log 0.0378 44 2.3456 0.0 2.3456 1.5315
No log 0.0395 46 1.8947 0.0 1.8947 1.3765
No log 0.0412 48 1.7101 0.0 1.7101 1.3077
No log 0.0430 50 1.6172 0.0048 1.6172 1.2717
No log 0.0447 52 1.7332 0.0 1.7332 1.3165
No log 0.0464 54 2.1304 0.0 2.1304 1.4596
No log 0.0481 56 2.2389 0.0 2.2389 1.4963
No log 0.0498 58 1.8386 0.0 1.8386 1.3559
No log 0.0515 60 1.6118 0.0082 1.6118 1.2696
No log 0.0533 62 1.6272 0.0020 1.6272 1.2756
No log 0.0550 64 1.7835 0.0 1.7835 1.3355
No log 0.0567 66 1.9920 0.0 1.9920 1.4114
No log 0.0584 68 2.2769 0.0 2.2769 1.5089
No log 0.0601 70 2.0964 0.0 2.0964 1.4479
No log 0.0619 72 1.8649 0.0 1.8649 1.3656
No log 0.0636 74 1.8765 0.0 1.8765 1.3698
No log 0.0653 76 2.0191 0.0 2.0191 1.4210
No log 0.0670 78 2.1713 0.0 2.1713 1.4735
No log 0.0687 80 2.7846 -0.0017 2.7846 1.6687
No log 0.0704 82 2.8685 -0.0020 2.8685 1.6937
No log 0.0722 84 3.2740 -0.0062 3.2740 1.8094
No log 0.0739 86 2.9305 -0.0020 2.9305 1.7119
No log 0.0756 88 2.5984 0.0 2.5984 1.6120
No log 0.0773 90 2.2076 0.0 2.2076 1.4858
No log 0.0790 92 1.9943 0.0 1.9943 1.4122
No log 0.0808 94 1.9669 0.0 1.9669 1.4025
No log 0.0825 96 1.9458 0.0 1.9458 1.3949
No log 0.0842 98 1.7498 0.0 1.7498 1.3228
No log 0.0859 100 1.7322 0.0 1.7322 1.3161
No log 0.0876 102 1.7476 0.0 1.7476 1.3220
No log 0.0893 104 1.6456 0.0051 1.6456 1.2828
No log 0.0911 106 1.8305 0.0 1.8305 1.3530
No log 0.0928 108 1.9510 0.0 1.9510 1.3968
No log 0.0945 110 2.1976 0.0 2.1976 1.4824
No log 0.0962 112 2.2431 0.0 2.2431 1.4977
No log 0.0979 114 1.9160 0.0 1.9160 1.3842
No log 0.0997 116 1.8657 0.0 1.8657 1.3659
No log 0.1014 118 1.8815 0.0 1.8815 1.3717
No log 0.1031 120 1.9188 0.0 1.9188 1.3852
No log 0.1048 122 1.9257 0.0 1.9257 1.3877
No log 0.1065 124 1.8319 0.0 1.8319 1.3535
No log 0.1082 126 1.7375 0.0 1.7375 1.3181
No log 0.1100 128 1.6104 0.0074 1.6104 1.2690
No log 0.1117 130 1.6060 0.0081 1.6060 1.2673
No log 0.1134 132 1.6098 0.0081 1.6098 1.2688
No log 0.1151 134 1.7361 0.0 1.7361 1.3176
No log 0.1168 136 1.9969 0.0 1.9969 1.4131
No log 0.1186 138 2.4719 0.0035 2.4719 1.5722
No log 0.1203 140 2.4206 0.0035 2.4206 1.5558
No log 0.1220 142 2.0564 0.0 2.0564 1.4340
No log 0.1237 144 1.8190 0.0 1.8190 1.3487
No log 0.1254 146 1.6021 0.0019 1.6021 1.2657
No log 0.1271 148 1.5096 0.0576 1.5096 1.2287
No log 0.1289 150 1.5493 0.0180 1.5493 1.2447
No log 0.1306 152 1.6772 0.0 1.6772 1.2951
No log 0.1323 154 1.9411 0.0 1.9411 1.3932
No log 0.1340 156 2.2027 0.0 2.2027 1.4842
No log 0.1357 158 2.1599 0.0 2.1599 1.4697
No log 0.1375 160 1.9253 0.0 1.9253 1.3875
No log 0.1392 162 1.7175 0.0 1.7175 1.3105
No log 0.1409 164 1.5814 0.0023 1.5814 1.2576
No log 0.1426 166 1.4958 0.0853 1.4958 1.2230
No log 0.1443 168 1.4590 0.0945 1.4590 1.2079
No log 0.1460 170 1.4957 0.0839 1.4957 1.2230
No log 0.1478 172 1.5474 0.0540 1.5474 1.2439
No log 0.1495 174 1.6455 0.0029 1.6455 1.2828
No log 0.1512 176 1.8179 0.0 1.8179 1.3483
No log 0.1529 178 1.7962 0.0 1.7962 1.3402
No log 0.1546 180 1.6419 0.0078 1.6419 1.2814
No log 0.1564 182 1.5014 0.0736 1.5014 1.2253
No log 0.1581 184 1.3914 0.0922 1.3914 1.1796
No log 0.1598 186 1.3188 0.0903 1.3188 1.1484
No log 0.1615 188 1.2604 0.0558 1.2604 1.1227
No log 0.1632 190 1.2181 0.0609 1.2181 1.1037
No log 0.1649 192 1.2532 0.0682 1.2532 1.1195
No log 0.1667 194 1.3077 0.0926 1.3077 1.1436
No log 0.1684 196 1.4059 0.0898 1.4059 1.1857
No log 0.1701 198 1.4483 0.1093 1.4483 1.2035
No log 0.1718 200 1.3740 0.0975 1.3740 1.1722
No log 0.1735 202 1.2520 0.0724 1.2520 1.1189
No log 0.1753 204 1.2176 0.0634 1.2176 1.1035
No log 0.1770 206 1.2505 0.0702 1.2505 1.1183
No log 0.1787 208 1.3673 0.0752 1.3673 1.1693
No log 0.1804 210 1.4856 0.0652 1.4856 1.2188
No log 0.1821 212 1.4848 0.0636 1.4848 1.2185
No log 0.1838 214 1.3903 0.0798 1.3903 1.1791
No log 0.1856 216 1.2767 0.0769 1.2767 1.1299
No log 0.1873 218 1.2113 0.0576 1.2113 1.1006
No log 0.1890 220 1.1479 0.0525 1.1479 1.0714
No log 0.1907 222 1.1114 0.0436 1.1114 1.0542
No log 0.1924 224 1.1052 0.0379 1.1052 1.0513
No log 0.1942 226 1.0558 0.0402 1.0558 1.0275
No log 0.1959 228 1.0053 0.0382 1.0053 1.0026
No log 0.1976 230 1.0157 0.0465 1.0157 1.0078
No log 0.1993 232 1.0995 0.0469 1.0995 1.0486
No log 0.2010 234 1.2326 0.0746 1.2326 1.1102
No log 0.2027 236 1.2515 0.0788 1.2515 1.1187
No log 0.2045 238 1.1501 0.0613 1.1501 1.0724
No log 0.2062 240 1.0444 0.0379 1.0444 1.0220
No log 0.2079 242 1.0168 0.0388 1.0168 1.0084
No log 0.2096 244 1.0185 0.0436 1.0185 1.0092
No log 0.2113 246 1.0634 0.0528 1.0634 1.0312
No log 0.2131 248 1.0689 0.0490 1.0689 1.0339
No log 0.2148 250 1.0253 0.0499 1.0253 1.0126
No log 0.2165 252 0.9643 0.0426 0.9643 0.9820
No log 0.2182 254 0.9200 0.0364 0.9200 0.9592
No log 0.2199 256 0.9101 0.0319 0.9101 0.9540
No log 0.2216 258 0.9084 0.0343 0.9084 0.9531
No log 0.2234 260 0.9067 0.0340 0.9067 0.9522
No log 0.2251 262 0.9188 0.0412 0.9188 0.9586
No log 0.2268 264 0.9414 0.0436 0.9414 0.9703
No log 0.2285 266 0.9687 0.0482 0.9687 0.9842
No log 0.2302 268 0.9970 0.0492 0.9970 0.9985
No log 0.2320 270 0.9863 0.0422 0.9863 0.9931
No log 0.2337 272 0.9503 0.0337 0.9503 0.9748
No log 0.2354 274 0.9064 0.0319 0.9064 0.9521
No log 0.2371 276 0.8894 0.0319 0.8894 0.9431
No log 0.2388 278 0.8765 0.0319 0.8765 0.9362
No log 0.2405 280 0.8727 0.0331 0.8727 0.9342
No log 0.2423 282 0.8842 0.0334 0.8842 0.9403
No log 0.2440 284 0.9199 0.0469 0.9199 0.9591
No log 0.2457 286 0.8936 0.0412 0.8936 0.9453
No log 0.2474 288 0.8824 0.0412 0.8824 0.9393
No log 0.2491 290 0.9086 0.0436 0.9086 0.9532
No log 0.2509 292 0.9241 0.0436 0.9241 0.9613
No log 0.2526 294 0.8998 0.0436 0.8998 0.9486
No log 0.2543 296 0.8849 0.0445 0.8849 0.9407
No log 0.2560 298 0.8826 0.0331 0.8826 0.9395
No log 0.2577 300 0.8811 0.0319 0.8811 0.9387
No log 0.2595 302 0.8795 0.0319 0.8795 0.9378
No log 0.2612 304 0.8792 0.0319 0.8792 0.9377
No log 0.2629 306 0.8755 0.0306 0.8755 0.9357
No log 0.2646 308 0.8810 0.0407 0.8810 0.9386
No log 0.2663 310 0.8970 0.0388 0.8970 0.9471
No log 0.2680 312 0.9230 0.0383 0.9230 0.9607
No log 0.2698 314 0.9953 0.0379 0.9953 0.9976
No log 0.2715 316 1.1603 0.0208 1.1603 1.0772
No log 0.2732 318 0.9573 0.0325 0.9573 0.9784
No log 0.2749 320 0.8895 0.0319 0.8895 0.9431
No log 0.2766 322 0.8831 0.0335 0.8831 0.9397
No log 0.2784 324 0.8818 0.0376 0.8818 0.9390
No log 0.2801 326 0.9089 0.0340 0.9089 0.9534
No log 0.2818 328 1.0045 0.0492 1.0045 1.0022
No log 0.2835 330 1.1485 0.0660 1.1485 1.0717
No log 0.2852 332 1.1518 0.0660 1.1518 1.0732
No log 0.2869 334 1.0386 0.0492 1.0386 1.0191
No log 0.2887 336 0.9861 0.0412 0.9861 0.9930
No log 0.2904 338 0.9455 0.0412 0.9455 0.9724
No log 0.2921 340 0.9308 0.0469 0.9308 0.9648
No log 0.2938 342 0.9416 0.0669 0.9416 0.9703
No log 0.2955 344 0.9503 0.0669 0.9503 0.9748
No log 0.2973 346 0.9169 0.0669 0.9169 0.9575
No log 0.2990 348 0.8956 0.0412 0.8956 0.9464
No log 0.3007 350 0.9430 0.0359 0.9430 0.9711
No log 0.3024 352 0.9593 0.0441 0.9593 0.9794
No log 0.3041 354 0.9791 0.0387 0.9791 0.9895
No log 0.3058 356 1.0326 0.0355 1.0326 1.0162
No log 0.3076 358 1.0554 0.0379 1.0554 1.0273
No log 0.3093 360 1.0667 0.0379 1.0667 1.0328
No log 0.3110 362 1.0684 0.0379 1.0684 1.0336
No log 0.3127 364 1.0203 0.0379 1.0203 1.0101
No log 0.3144 366 0.9720 0.0379 0.9720 0.9859
No log 0.3162 368 1.0077 0.0379 1.0077 1.0038
No log 0.3179 370 0.9566 0.0379 0.9566 0.9780
No log 0.3196 372 0.9046 0.0355 0.9046 0.9511
No log 0.3213 374 0.8972 0.0325 0.8972 0.9472
No log 0.3230 376 0.8928 0.0566 0.8928 0.9449
No log 0.3247 378 0.8820 0.0379 0.8820 0.9392
No log 0.3265 380 0.8778 0.0379 0.8778 0.9369
No log 0.3282 382 0.8795 0.0436 0.8795 0.9378
No log 0.3299 384 0.8725 0.0379 0.8725 0.9341
No log 0.3316 386 0.8728 0.0953 0.8728 0.9342
No log 0.3333 388 0.9087 0.2229 0.9087 0.9532
No log 0.3351 390 0.9313 0.2204 0.9313 0.9650
No log 0.3368 392 0.9278 0.1962 0.9278 0.9632
No log 0.3385 394 0.9231 0.1793 0.9231 0.9608
No log 0.3402 396 0.9091 0.0698 0.9091 0.9535
No log 0.3419 398 0.8989 0.0300 0.8989 0.9481
No log 0.3436 400 0.9001 0.0431 0.9001 0.9487
No log 0.3454 402 0.9281 0.0436 0.9281 0.9634
No log 0.3471 404 0.9502 0.0436 0.9502 0.9748
No log 0.3488 406 0.9804 0.0436 0.9804 0.9902
No log 0.3505 408 0.9970 0.0436 0.9970 0.9985
No log 0.3522 410 0.9826 0.0436 0.9826 0.9913
No log 0.3540 412 0.9472 0.0412 0.9472 0.9732
No log 0.3557 414 0.9268 0.0436 0.9268 0.9627
No log 0.3574 416 0.8909 0.0355 0.8909 0.9439
No log 0.3591 418 0.8837 0.0374 0.8837 0.9400
No log 0.3608 420 0.8812 0.0374 0.8812 0.9387
No log 0.3625 422 0.8956 0.0573 0.8956 0.9464
No log 0.3643 424 0.9074 0.1369 0.9074 0.9526
No log 0.3660 426 0.9191 0.1926 0.9191 0.9587
No log 0.3677 428 0.9224 0.1667 0.9224 0.9604
No log 0.3694 430 0.9101 0.0951 0.9101 0.9540
No log 0.3711 432 0.9288 0.0925 0.9288 0.9637
No log 0.3729 434 1.0162 0.0644 1.0162 1.0081
No log 0.3746 436 0.9749 0.0906 0.9749 0.9874
No log 0.3763 438 0.9267 0.1089 0.9267 0.9626
No log 0.3780 440 0.9579 0.1900 0.9579 0.9787
No log 0.3797 442 0.9741 0.1693 0.9741 0.9870
No log 0.3814 444 0.9646 0.1639 0.9646 0.9822
No log 0.3832 446 0.9564 0.1538 0.9564 0.9780
No log 0.3849 448 0.9455 0.1824 0.9455 0.9723
No log 0.3866 450 0.9316 0.2004 0.9316 0.9652
No log 0.3883 452 0.9157 0.1090 0.9157 0.9569
No log 0.3900 454 0.9069 0.0537 0.9069 0.9523
No log 0.3918 456 0.9088 0.1323 0.9088 0.9533
No log 0.3935 458 0.9043 0.1413 0.9043 0.9510
No log 0.3952 460 0.8940 0.0387 0.8940 0.9455
No log 0.3969 462 0.8877 0.0512 0.8877 0.9422
No log 0.3986 464 0.8803 0.0448 0.8803 0.9382
No log 0.4003 466 0.8743 0.0383 0.8743 0.9350
No log 0.4021 468 0.8698 0.0364 0.8698 0.9326
No log 0.4038 470 0.8681 0.0858 0.8681 0.9317
No log 0.4055 472 0.8733 0.1267 0.8733 0.9345
No log 0.4072 474 0.8771 0.2166 0.8771 0.9365
No log 0.4089 476 0.8801 0.2504 0.8801 0.9381
No log 0.4107 478 0.8827 0.2629 0.8827 0.9395
No log 0.4124 480 0.8864 0.2660 0.8864 0.9415
No log 0.4141 482 0.8901 0.2767 0.8901 0.9434
No log 0.4158 484 0.8850 0.2627 0.8850 0.9408
No log 0.4175 486 0.8802 0.1794 0.8802 0.9382
No log 0.4192 488 0.8760 0.1100 0.8760 0.9359
No log 0.4210 490 0.8757 0.0907 0.8757 0.9358
No log 0.4227 492 0.8760 0.0996 0.8760 0.9360
No log 0.4244 494 0.8823 0.2158 0.8823 0.9393
No log 0.4261 496 0.8895 0.2724 0.8895 0.9431
No log 0.4278 498 0.8944 0.2792 0.8944 0.9457
1.4476 0.4296 500 0.9084 0.2968 0.9084 0.9531
1.4476 0.4313 502 0.9197 0.3201 0.9197 0.9590
1.4476 0.4330 504 0.9333 0.2672 0.9333 0.9661
1.4476 0.4347 506 0.9225 0.2840 0.9225 0.9604
1.4476 0.4364 508 0.9144 0.2860 0.9144 0.9562
1.4476 0.4381 510 0.9223 0.2919 0.9223 0.9604
1.4476 0.4399 512 0.9502 0.2125 0.9502 0.9748

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_k10_task1_organization_fold3

Finetuned
(7020)
this model