ASAP_FineTuningBERT_AugV3_k15_task1_organization_fold0

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: 1.1017
  • Qwk: 0.0690
  • Mse: 1.1017
  • Rmse: 1.0496

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 0.0012 2 9.7922 0.0 9.7922 3.1293
No log 0.0024 4 8.3633 0.0066 8.3633 2.8919
No log 0.0035 6 7.3005 0.0054 7.3005 2.7019
No log 0.0047 8 6.5811 0.0018 6.5811 2.5654
No log 0.0059 10 5.8750 0.0 5.8750 2.4238
No log 0.0071 12 5.0157 0.0 5.0157 2.2396
No log 0.0083 14 4.2316 0.0 4.2316 2.0571
No log 0.0095 16 3.5184 0.0184 3.5184 1.8757
No log 0.0106 18 2.8545 0.0115 2.8545 1.6895
No log 0.0118 20 2.3672 0.0115 2.3672 1.5386
No log 0.0130 22 1.9819 0.0077 1.9819 1.4078
No log 0.0142 24 1.9985 0.0077 1.9985 1.4137
No log 0.0154 26 1.8437 0.0039 1.8437 1.3578
No log 0.0166 28 1.6585 0.0039 1.6585 1.2878
No log 0.0177 30 1.9056 0.0039 1.9056 1.3804
No log 0.0189 32 1.8559 0.0 1.8559 1.3623
No log 0.0201 34 1.8400 0.0 1.8400 1.3565
No log 0.0213 36 2.0710 0.0 2.0710 1.4391
No log 0.0225 38 2.0871 0.0 2.0871 1.4447
No log 0.0237 40 2.0154 0.0 2.0154 1.4197
No log 0.0248 42 2.0855 0.0 2.0855 1.4441
No log 0.0260 44 2.2494 0.0 2.2494 1.4998
No log 0.0272 46 2.0510 0.0 2.0510 1.4321
No log 0.0284 48 1.6863 -0.0011 1.6863 1.2986
No log 0.0296 50 1.4258 0.0966 1.4258 1.1941
No log 0.0308 52 1.4741 0.0344 1.4741 1.2141
No log 0.0319 54 1.8984 0.0077 1.8984 1.3778
No log 0.0331 56 3.4487 0.0096 3.4487 1.8571
No log 0.0343 58 4.0329 -0.0067 4.0329 2.0082
No log 0.0355 60 3.3736 0.0077 3.3736 1.8367
No log 0.0367 62 2.1979 0.0077 2.1979 1.4825
No log 0.0378 64 1.7435 0.0039 1.7435 1.3204
No log 0.0390 66 1.8201 0.0 1.8201 1.3491
No log 0.0402 68 1.8705 0.0 1.8705 1.3677
No log 0.0414 70 2.0534 0.0 2.0534 1.4330
No log 0.0426 72 2.3136 0.0 2.3136 1.5210
No log 0.0438 74 2.5474 0.0 2.5474 1.5961
No log 0.0449 76 2.6250 0.0 2.6250 1.6202
No log 0.0461 78 2.5749 0.0 2.5749 1.6047
No log 0.0473 80 2.4346 0.0 2.4346 1.5603
No log 0.0485 82 2.1389 0.0 2.1389 1.4625
No log 0.0497 84 1.8366 0.0 1.8366 1.3552
No log 0.0509 86 1.7317 0.0 1.7317 1.3160
No log 0.0520 88 1.8697 0.0 1.8697 1.3674
No log 0.0532 90 2.2164 0.0 2.2164 1.4888
No log 0.0544 92 2.5257 0.0 2.5257 1.5892
No log 0.0556 94 2.3605 0.0 2.3605 1.5364
No log 0.0568 96 1.9557 0.0 1.9557 1.3985
No log 0.0580 98 1.8506 0.0 1.8506 1.3604
No log 0.0591 100 1.9645 0.0 1.9645 1.4016
No log 0.0603 102 2.2756 0.0 2.2756 1.5085
No log 0.0615 104 2.6493 0.0 2.6493 1.6277
No log 0.0627 106 2.8137 0.0 2.8137 1.6774
No log 0.0639 108 3.0804 0.0 3.0804 1.7551
No log 0.0651 110 2.9559 0.0 2.9559 1.7193
No log 0.0662 112 2.6341 0.0 2.6341 1.6230
No log 0.0674 114 2.3558 0.0 2.3558 1.5349
No log 0.0686 116 2.1704 0.0 2.1704 1.4732
No log 0.0698 118 2.1065 0.0 2.1065 1.4514
No log 0.0710 120 2.0668 0.0 2.0668 1.4376
No log 0.0721 122 2.0841 0.0 2.0841 1.4436
No log 0.0733 124 2.1650 0.0 2.1650 1.4714
No log 0.0745 126 2.2221 0.0 2.2221 1.4907
No log 0.0757 128 2.1989 0.0 2.1989 1.4829
No log 0.0769 130 2.1231 0.0 2.1231 1.4571
No log 0.0781 132 2.1187 0.0 2.1187 1.4556
No log 0.0792 134 2.0821 0.0 2.0821 1.4429
No log 0.0804 136 2.1637 0.0 2.1637 1.4710
No log 0.0816 138 2.1701 0.0 2.1701 1.4731
No log 0.0828 140 2.0405 0.0 2.0405 1.4285
No log 0.0840 142 1.9347 0.0 1.9347 1.3909
No log 0.0852 144 1.8471 0.0 1.8471 1.3591
No log 0.0863 146 1.7597 0.0 1.7597 1.3266
No log 0.0875 148 1.6885 0.0 1.6885 1.2994
No log 0.0887 150 1.7089 0.0 1.7089 1.3072
No log 0.0899 152 1.7694 0.0 1.7694 1.3302
No log 0.0911 154 1.9460 0.0 1.9460 1.3950
No log 0.0923 156 2.1538 0.0 2.1538 1.4676
No log 0.0934 158 2.2936 0.0 2.2936 1.5145
No log 0.0946 160 2.2876 0.0 2.2876 1.5125
No log 0.0958 162 2.2865 0.0 2.2865 1.5121
No log 0.0970 164 2.2326 0.0 2.2326 1.4942
No log 0.0982 166 2.0642 0.0 2.0642 1.4367
No log 0.0993 168 1.9325 0.0 1.9325 1.3901
No log 0.1005 170 1.8205 0.0 1.8205 1.3492
No log 0.1017 172 1.7071 0.0 1.7071 1.3066
No log 0.1029 174 1.7461 0.0 1.7461 1.3214
No log 0.1041 176 1.9165 0.0 1.9165 1.3844
No log 0.1053 178 2.1815 0.0 2.1815 1.4770
No log 0.1064 180 2.2627 0.0 2.2627 1.5042
No log 0.1076 182 2.1492 0.0 2.1492 1.4660
No log 0.1088 184 1.9769 0.0 1.9769 1.4060
No log 0.1100 186 1.9287 0.0 1.9287 1.3888
No log 0.1112 188 1.9737 0.0 1.9737 1.4049
No log 0.1124 190 1.9281 0.0 1.9281 1.3886
No log 0.1135 192 1.8398 0.0 1.8398 1.3564
No log 0.1147 194 1.8626 0.0 1.8626 1.3648
No log 0.1159 196 1.8595 0.0 1.8595 1.3636
No log 0.1171 198 1.6805 0.0 1.6805 1.2964
No log 0.1183 200 1.6063 0.0 1.6063 1.2674
No log 0.1195 202 1.6822 0.0 1.6822 1.2970
No log 0.1206 204 1.8672 0.0 1.8672 1.3664
No log 0.1218 206 2.1024 0.0 2.1024 1.4500
No log 0.1230 208 2.1563 0.0 2.1563 1.4684
No log 0.1242 210 2.0730 0.0 2.0730 1.4398
No log 0.1254 212 1.8601 0.0 1.8601 1.3639
No log 0.1266 214 1.6940 0.0 1.6940 1.3015
No log 0.1277 216 1.6001 0.0 1.6001 1.2649
No log 0.1289 218 1.5926 0.0 1.5926 1.2620
No log 0.1301 220 1.6390 0.0 1.6390 1.2802
No log 0.1313 222 1.6213 0.0 1.6213 1.2733
No log 0.1325 224 1.6566 0.0 1.6566 1.2871
No log 0.1336 226 1.7349 0.0 1.7349 1.3172
No log 0.1348 228 1.8279 0.0 1.8279 1.3520
No log 0.1360 230 1.8429 0.0 1.8429 1.3575
No log 0.1372 232 1.7444 0.0 1.7444 1.3208
No log 0.1384 234 1.5934 0.0 1.5934 1.2623
No log 0.1396 236 1.4677 0.0959 1.4677 1.2115
No log 0.1407 238 1.3951 0.1050 1.3951 1.1812
No log 0.1419 240 1.3196 0.1002 1.3196 1.1487
No log 0.1431 242 1.2767 0.0806 1.2767 1.1299
No log 0.1443 244 1.2225 0.0789 1.2225 1.1057
No log 0.1455 246 1.2069 0.0813 1.2069 1.0986
No log 0.1467 248 1.2236 0.0809 1.2236 1.1062
No log 0.1478 250 1.1960 0.0889 1.1960 1.0936
No log 0.1490 252 1.2219 0.0851 1.2219 1.1054
No log 0.1502 254 1.1505 0.0788 1.1505 1.0726
No log 0.1514 256 1.1610 0.0783 1.1610 1.0775
No log 0.1526 258 1.2426 0.0817 1.2426 1.1147
No log 0.1538 260 1.3298 0.0869 1.3298 1.1532
No log 0.1549 262 1.4879 0.0086 1.4879 1.2198
No log 0.1561 264 1.5971 -0.0035 1.5971 1.2638
No log 0.1573 266 1.6279 -0.0052 1.6279 1.2759
No log 0.1585 268 1.3140 0.0870 1.3140 1.1463
No log 0.1597 270 1.1588 0.0876 1.1588 1.0765
No log 0.1609 272 1.1083 0.0738 1.1083 1.0527
No log 0.1620 274 1.1083 0.0701 1.1083 1.0527
No log 0.1632 276 1.1845 0.0770 1.1845 1.0884
No log 0.1644 278 1.2443 0.0783 1.2443 1.1155
No log 0.1656 280 1.2871 0.0820 1.2871 1.1345
No log 0.1668 282 1.1852 0.0770 1.1852 1.0887
No log 0.1679 284 1.0893 0.0746 1.0893 1.0437
No log 0.1691 286 0.9850 0.0746 0.9850 0.9925
No log 0.1703 288 0.9296 0.0746 0.9296 0.9641
No log 0.1715 290 0.9065 0.0746 0.9065 0.9521
No log 0.1727 292 0.9126 0.0746 0.9126 0.9553
No log 0.1739 294 0.9074 0.0746 0.9074 0.9526
No log 0.1750 296 0.9182 0.0746 0.9182 0.9582
No log 0.1762 298 0.9521 0.0701 0.9521 0.9757
No log 0.1774 300 0.9936 0.0701 0.9936 0.9968
No log 0.1786 302 1.0099 0.0635 1.0099 1.0049
No log 0.1798 304 1.0068 0.0635 1.0068 1.0034
No log 0.1810 306 0.9779 0.0690 0.9779 0.9889
No log 0.1821 308 0.9293 0.0701 0.9293 0.9640
No log 0.1833 310 0.9126 0.0701 0.9126 0.9553
No log 0.1845 312 0.8956 0.0701 0.8956 0.9464
No log 0.1857 314 0.8850 0.0746 0.8850 0.9407
No log 0.1869 316 0.8663 0.0746 0.8663 0.9308
No log 0.1881 318 0.8648 0.0746 0.8648 0.9300
No log 0.1892 320 0.8876 0.0690 0.8876 0.9421
No log 0.1904 322 0.9221 0.0683 0.9221 0.9603
No log 0.1916 324 0.9127 0.0683 0.9127 0.9553
No log 0.1928 326 0.9042 0.0683 0.9042 0.9509
No log 0.1940 328 0.8696 0.0690 0.8696 0.9325
No log 0.1952 330 0.8408 0.0746 0.8408 0.9170
No log 0.1963 332 0.8273 0.0722 0.8273 0.9095
No log 0.1975 334 0.8354 0.0522 0.8354 0.9140
No log 0.1987 336 0.8521 0.0569 0.8521 0.9231
No log 0.1999 338 0.8826 0.0709 0.8826 0.9395
No log 0.2011 340 0.9144 0.0746 0.9144 0.9562
No log 0.2022 342 0.9512 0.0701 0.9512 0.9753
No log 0.2034 344 0.9469 0.0683 0.9469 0.9731
No log 0.2046 346 0.9191 0.0719 0.9191 0.9587
No log 0.2058 348 0.8707 0.0673 0.8707 0.9331
No log 0.2070 350 0.8775 0.0656 0.8775 0.9367
No log 0.2082 352 1.0094 0.0746 1.0094 1.0047
No log 0.2093 354 1.2635 0.0317 1.2635 1.1241
No log 0.2105 356 1.5385 -0.0062 1.5385 1.2404
No log 0.2117 358 1.7844 -0.0170 1.7844 1.3358
No log 0.2129 360 1.0801 0.0746 1.0801 1.0393
No log 0.2141 362 0.9459 0.0656 0.9459 0.9726
No log 0.2153 364 0.9864 0.0696 0.9864 0.9932
No log 0.2164 366 1.0173 0.0686 1.0173 1.0086
No log 0.2176 368 0.9302 0.0656 0.9302 0.9645
No log 0.2188 370 0.8413 0.0746 0.8413 0.9172
No log 0.2200 372 0.7944 0.0746 0.7944 0.8913
No log 0.2212 374 0.7817 0.0733 0.7817 0.8842
No log 0.2224 376 0.7808 0.0733 0.7808 0.8836
No log 0.2235 378 0.7899 0.0746 0.7899 0.8888
No log 0.2247 380 0.8138 0.0746 0.8138 0.9021
No log 0.2259 382 0.8464 0.0680 0.8464 0.9200
No log 0.2271 384 0.8887 0.0786 0.8887 0.9427
No log 0.2283 386 0.8942 0.0686 0.8942 0.9456
No log 0.2295 388 0.8892 0.0683 0.8892 0.9430
No log 0.2306 390 0.8751 0.0680 0.8751 0.9355
No log 0.2318 392 0.8607 0.0701 0.8607 0.9278
No log 0.2330 394 0.8397 0.0746 0.8397 0.9163
No log 0.2342 396 0.8287 0.0746 0.8287 0.9103
No log 0.2354 398 0.7796 0.0746 0.7796 0.8829
No log 0.2365 400 0.7629 0.0746 0.7629 0.8734
No log 0.2377 402 0.7552 0.0746 0.7552 0.8690
No log 0.2389 404 0.7499 0.0746 0.7499 0.8660
No log 0.2401 406 0.7488 0.0746 0.7488 0.8653
No log 0.2413 408 0.7556 0.0746 0.7556 0.8692
No log 0.2425 410 0.7673 0.0746 0.7673 0.8759
No log 0.2436 412 0.7953 0.0701 0.7953 0.8918
No log 0.2448 414 0.8158 0.0806 0.8158 0.9032
No log 0.2460 416 0.8611 0.0699 0.8611 0.9280
No log 0.2472 418 0.8819 0.0795 0.8819 0.9391
No log 0.2484 420 0.8115 0.0746 0.8115 0.9008
No log 0.2496 422 0.7853 0.0746 0.7853 0.8862
No log 0.2507 424 0.7810 0.0746 0.7810 0.8838
No log 0.2519 426 0.7971 0.0746 0.7971 0.8928
No log 0.2531 428 0.8184 0.0746 0.8184 0.9047
No log 0.2543 430 0.8294 0.0746 0.8294 0.9107
No log 0.2555 432 0.8439 0.0746 0.8439 0.9186
No log 0.2567 434 0.8974 0.0746 0.8974 0.9473
No log 0.2578 436 0.9385 0.0746 0.9385 0.9688
No log 0.2590 438 1.1166 0.0581 1.1166 1.0567
No log 0.2602 440 0.9992 0.0746 0.9992 0.9996
No log 0.2614 442 0.9520 0.0746 0.9520 0.9757
No log 0.2626 444 0.9066 0.0746 0.9066 0.9522
No log 0.2637 446 0.8954 0.0746 0.8954 0.9463
No log 0.2649 448 0.8983 0.0746 0.8983 0.9478
No log 0.2661 450 0.8928 0.0746 0.8928 0.9449
No log 0.2673 452 0.8592 0.0746 0.8592 0.9269
No log 0.2685 454 0.8394 0.0746 0.8394 0.9162
No log 0.2697 456 0.8569 0.0746 0.8569 0.9257
No log 0.2708 458 0.8970 0.0746 0.8970 0.9471
No log 0.2720 460 0.8199 0.0746 0.8199 0.9055
No log 0.2732 462 0.7764 0.0746 0.7764 0.8811
No log 0.2744 464 0.7795 0.0746 0.7795 0.8829
No log 0.2756 466 0.7788 0.0746 0.7788 0.8825
No log 0.2768 468 0.7811 0.0746 0.7811 0.8838
No log 0.2779 470 0.7873 0.0568 0.7873 0.8873
No log 0.2791 472 0.7931 0.0492 0.7931 0.8905
No log 0.2803 474 0.8013 0.0447 0.8013 0.8951
No log 0.2815 476 0.8028 0.0463 0.8028 0.8960
No log 0.2827 478 0.8023 0.0619 0.8023 0.8957
No log 0.2839 480 0.8007 0.0473 0.8007 0.8948
No log 0.2850 482 0.8002 0.0448 0.8002 0.8946
No log 0.2862 484 0.7997 0.0462 0.7997 0.8942
No log 0.2874 486 0.7980 0.0377 0.7980 0.8933
No log 0.2886 488 0.8070 0.0351 0.8070 0.8983
No log 0.2898 490 0.8196 0.0409 0.8196 0.9053
No log 0.2910 492 0.8602 0.0409 0.8602 0.9275
No log 0.2921 494 0.9250 0.0746 0.9250 0.9617
No log 0.2933 496 0.8174 0.0746 0.8174 0.9041
No log 0.2945 498 0.7835 0.0768 0.7835 0.8852
1.4709 0.2957 500 0.7676 0.0746 0.7676 0.8761
1.4709 0.2969 502 0.7693 0.0746 0.7693 0.8771
1.4709 0.2980 504 0.8349 0.0532 0.8349 0.9137
1.4709 0.2992 506 0.9607 0.0584 0.9607 0.9802
1.4709 0.3004 508 1.0548 0.0746 1.0548 1.0270
1.4709 0.3016 510 1.1017 0.0690 1.1017 1.0496

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
27
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_AugV3_k15_task1_organization_fold0

Finetuned
(7066)
this model