ASAP_FineTuningBERT_Aug_k40_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: 0.4952
  • Qwk: 0.4642
  • Mse: 0.4952
  • Rmse: 0.7037

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 0.0032 2 12.2594 0.0 12.2594 3.5013
No log 0.0063 4 10.9154 0.0 10.9154 3.3039
No log 0.0095 6 9.3746 0.0 9.3746 3.0618
No log 0.0127 8 8.3476 -0.0097 8.3476 2.8892
No log 0.0159 10 6.8701 0.0018 6.8701 2.6211
No log 0.0190 12 6.6368 0.0093 6.6368 2.5762
No log 0.0222 14 5.2431 0.0012 5.2431 2.2898
No log 0.0254 16 4.5330 0.0012 4.5330 2.1291
No log 0.0286 18 4.2204 0.0301 4.2204 2.0544
No log 0.0317 20 3.5047 0.0484 3.5047 1.8721
No log 0.0349 22 2.6052 0.0233 2.6052 1.6141
No log 0.0381 24 2.0564 0.0171 2.0564 1.4340
No log 0.0413 26 1.7207 0.0128 1.7207 1.3118
No log 0.0444 28 1.3506 0.0720 1.3506 1.1622
No log 0.0476 30 1.0613 0.1056 1.0613 1.0302
No log 0.0508 32 0.9309 0.0841 0.9309 0.9648
No log 0.0540 34 0.8418 0.0607 0.8418 0.9175
No log 0.0571 36 0.8464 0.0443 0.8464 0.9200
No log 0.0603 38 0.7116 0.1244 0.7116 0.8436
No log 0.0635 40 1.1430 0.1915 1.1430 1.0691
No log 0.0667 42 0.6533 0.1623 0.6533 0.8083
No log 0.0698 44 0.7883 0.1425 0.7883 0.8878
No log 0.0730 46 0.7902 0.0768 0.7902 0.8889
No log 0.0762 48 0.9975 0.0482 0.9975 0.9988
No log 0.0794 50 1.0406 0.0482 1.0406 1.0201
No log 0.0825 52 0.7711 0.1027 0.7711 0.8781
No log 0.0857 54 0.8698 0.2058 0.8698 0.9326
No log 0.0889 56 0.6579 0.1386 0.6579 0.8111
No log 0.0921 58 0.8834 0.0506 0.8834 0.9399
No log 0.0952 60 0.9820 0.0379 0.9820 0.9910
No log 0.0984 62 0.9574 0.0669 0.9574 0.9785
No log 0.1016 64 0.7527 0.0965 0.7527 0.8676
No log 0.1048 66 0.7512 0.1924 0.7512 0.8667
No log 0.1079 68 0.8568 0.1986 0.8568 0.9256
No log 0.1111 70 0.6964 0.1525 0.6964 0.8345
No log 0.1143 72 0.7862 0.0669 0.7862 0.8867
No log 0.1175 74 0.8339 0.0545 0.8339 0.9132
No log 0.1206 76 0.8832 0.0730 0.8832 0.9398
No log 0.1238 78 0.9106 0.0969 0.9106 0.9543
No log 0.1270 80 0.8277 0.0828 0.8277 0.9098
No log 0.1302 82 0.7543 0.0828 0.7543 0.8685
No log 0.1333 84 0.7285 0.0910 0.7285 0.8535
No log 0.1365 86 0.7469 0.0910 0.7469 0.8642
No log 0.1397 88 0.8428 0.1479 0.8428 0.9180
No log 0.1429 90 0.7873 0.0828 0.7873 0.8873
No log 0.1460 92 0.8082 0.0828 0.8082 0.8990
No log 0.1492 94 0.8519 0.0443 0.8519 0.9230
No log 0.1524 96 0.9068 0.0276 0.9068 0.9522
No log 0.1556 98 0.8958 0.0276 0.8958 0.9465
No log 0.1587 100 0.9076 0.0276 0.9076 0.9527
No log 0.1619 102 0.8783 0.0276 0.8783 0.9372
No log 0.1651 104 0.8290 0.0379 0.8290 0.9105
No log 0.1683 106 0.7695 0.0443 0.7695 0.8772
No log 0.1714 108 0.7279 0.0931 0.7279 0.8531
No log 0.1746 110 0.8010 0.1632 0.8010 0.8950
No log 0.1778 112 0.7560 0.1548 0.7560 0.8695
No log 0.1810 114 0.7033 0.1354 0.7033 0.8386
No log 0.1841 116 0.7801 0.0828 0.7801 0.8832
No log 0.1873 118 0.9491 0.0482 0.9491 0.9742
No log 0.1905 120 0.9811 0.0172 0.9811 0.9905
No log 0.1937 122 0.9072 0.0246 0.9072 0.9525
No log 0.1968 124 0.8357 0.1824 0.8357 0.9142
No log 0.2 126 0.8289 0.1784 0.8289 0.9105
No log 0.2032 128 0.9202 0.0398 0.9202 0.9593
No log 0.2063 130 0.9682 0.0379 0.9682 0.9840
No log 0.2095 132 0.8427 0.0730 0.8427 0.9180
No log 0.2127 134 0.6949 0.1610 0.6949 0.8336
No log 0.2159 136 0.6926 0.2026 0.6926 0.8322
No log 0.2190 138 1.2134 0.2115 1.2134 1.1016
No log 0.2222 140 1.7551 0.1915 1.7551 1.3248
No log 0.2254 142 1.6033 0.2100 1.6033 1.2662
No log 0.2286 144 0.9752 0.2352 0.9752 0.9875
No log 0.2317 146 0.7935 0.2075 0.7935 0.8908
No log 0.2349 148 0.7262 0.2063 0.7262 0.8521
No log 0.2381 150 0.6784 0.2349 0.6784 0.8236
No log 0.2413 152 0.6807 0.3710 0.6807 0.8250
No log 0.2444 154 0.7121 0.2131 0.7121 0.8438
No log 0.2476 156 0.7727 0.0894 0.7727 0.8790
No log 0.2508 158 0.7833 0.0915 0.7833 0.8850
No log 0.2540 160 0.7359 0.1329 0.7359 0.8578
No log 0.2571 162 0.7866 0.2122 0.7866 0.8869
No log 0.2603 164 0.7383 0.2377 0.7383 0.8592
No log 0.2635 166 0.7281 0.2490 0.7281 0.8533
No log 0.2667 168 0.7187 0.2454 0.7187 0.8478
No log 0.2698 170 0.7635 0.0799 0.7635 0.8738
No log 0.2730 172 0.8458 0.0431 0.8458 0.9197
No log 0.2762 174 0.8298 0.0743 0.8298 0.9109
No log 0.2794 176 0.8758 0.0477 0.8758 0.9358
No log 0.2825 178 0.8873 0.1198 0.8873 0.9420
No log 0.2857 180 0.9508 -0.0151 0.9508 0.9751
No log 0.2889 182 0.9959 -0.0927 0.9959 0.9979
No log 0.2921 184 0.9386 0.0221 0.9386 0.9688
No log 0.2952 186 0.9026 0.1276 0.9026 0.9501
No log 0.2984 188 0.8776 0.1440 0.8776 0.9368
No log 0.3016 190 0.8099 0.3126 0.8099 0.9000
No log 0.3048 192 0.7992 0.0823 0.7992 0.8940
No log 0.3079 194 0.7431 0.1343 0.7431 0.8620
No log 0.3111 196 0.7283 0.1741 0.7283 0.8534
No log 0.3143 198 0.7285 0.1887 0.7285 0.8535
No log 0.3175 200 0.7717 0.2528 0.7717 0.8785
No log 0.3206 202 0.8260 0.2249 0.8260 0.9089
No log 0.3238 204 0.8520 0.2336 0.8520 0.9231
No log 0.3270 206 0.9359 0.2234 0.9359 0.9674
No log 0.3302 208 0.9125 0.2090 0.9125 0.9552
No log 0.3333 210 0.8220 0.2378 0.8220 0.9067
No log 0.3365 212 0.7994 0.2520 0.7994 0.8941
No log 0.3397 214 0.7958 0.3027 0.7958 0.8921
No log 0.3429 216 0.7992 0.3082 0.7992 0.8940
No log 0.3460 218 0.7747 0.3299 0.7747 0.8802
No log 0.3492 220 0.7234 0.2453 0.7234 0.8505
No log 0.3524 222 0.7195 0.2427 0.7195 0.8483
No log 0.3556 224 0.7247 0.3185 0.7247 0.8513
No log 0.3587 226 0.6652 0.2842 0.6652 0.8156
No log 0.3619 228 0.6471 0.3628 0.6471 0.8044
No log 0.3651 230 0.6265 0.3877 0.6265 0.7915
No log 0.3683 232 0.6183 0.3918 0.6183 0.7863
No log 0.3714 234 0.6456 0.3938 0.6456 0.8035
No log 0.3746 236 0.6189 0.3849 0.6189 0.7867
No log 0.3778 238 0.6588 0.3639 0.6588 0.8116
No log 0.3810 240 0.6038 0.4060 0.6038 0.7771
No log 0.3841 242 0.6123 0.3955 0.6123 0.7825
No log 0.3873 244 0.6186 0.3963 0.6186 0.7865
No log 0.3905 246 0.6456 0.3477 0.6456 0.8035
No log 0.3937 248 0.7257 0.3406 0.7257 0.8519
No log 0.3968 250 0.7817 0.3216 0.7817 0.8842
No log 0.4 252 0.7872 0.3163 0.7872 0.8872
No log 0.4032 254 0.8015 0.3276 0.8015 0.8953
No log 0.4063 256 0.7854 0.2851 0.7854 0.8862
No log 0.4095 258 0.7603 0.2279 0.7603 0.8719
No log 0.4127 260 0.7258 0.2454 0.7258 0.8519
No log 0.4159 262 0.6799 0.2819 0.6799 0.8245
No log 0.4190 264 0.6609 0.2014 0.6609 0.8130
No log 0.4222 266 0.6232 0.3182 0.6232 0.7894
No log 0.4254 268 0.6346 0.3877 0.6346 0.7966
No log 0.4286 270 0.5952 0.3662 0.5952 0.7715
No log 0.4317 272 0.6841 0.2060 0.6841 0.8271
No log 0.4349 274 0.7760 0.2167 0.7760 0.8809
No log 0.4381 276 0.6053 0.2764 0.6053 0.7780
No log 0.4413 278 0.5824 0.3723 0.5824 0.7631
No log 0.4444 280 0.6779 0.4142 0.6779 0.8233
No log 0.4476 282 0.6912 0.3548 0.6912 0.8314
No log 0.4508 284 0.7316 0.2459 0.7316 0.8554
No log 0.4540 286 0.7680 0.1852 0.7680 0.8764
No log 0.4571 288 0.8018 0.0594 0.8018 0.8954
No log 0.4603 290 0.7691 0.1896 0.7691 0.8770
No log 0.4635 292 0.8408 0.3526 0.8408 0.9169
No log 0.4667 294 0.8727 0.3355 0.8727 0.9342
No log 0.4698 296 0.7884 0.3433 0.7884 0.8879
No log 0.4730 298 0.7770 0.1148 0.7770 0.8815
No log 0.4762 300 0.7694 0.1369 0.7694 0.8772
No log 0.4794 302 0.7730 0.3393 0.7730 0.8792
No log 0.4825 304 1.0773 0.2918 1.0773 1.0379
No log 0.4857 306 1.0864 0.2985 1.0864 1.0423
No log 0.4889 308 0.8038 0.3421 0.8038 0.8965
No log 0.4921 310 0.7242 0.2522 0.7242 0.8510
No log 0.4952 312 0.7287 0.1731 0.7287 0.8537
No log 0.4984 314 0.7115 0.3421 0.7115 0.8435
No log 0.5016 316 0.7679 0.3560 0.7679 0.8763
No log 0.5048 318 0.9157 0.3237 0.9157 0.9569
No log 0.5079 320 0.8716 0.3458 0.8716 0.9336
No log 0.5111 322 0.6857 0.3926 0.6857 0.8281
No log 0.5143 324 0.6317 0.2943 0.6317 0.7948
No log 0.5175 326 0.6340 0.2838 0.6340 0.7963
No log 0.5206 328 0.6227 0.3659 0.6227 0.7891
No log 0.5238 330 0.6551 0.4008 0.6551 0.8094
No log 0.5270 332 0.7438 0.4170 0.7438 0.8624
No log 0.5302 334 0.7567 0.4035 0.7567 0.8699
No log 0.5333 336 0.7921 0.3383 0.7921 0.8900
No log 0.5365 338 0.7993 0.3196 0.7993 0.8940
No log 0.5397 340 0.8297 0.3024 0.8297 0.9109
No log 0.5429 342 0.8678 0.2890 0.8678 0.9315
No log 0.5460 344 0.9000 0.3046 0.9000 0.9487
No log 0.5492 346 0.8038 0.3338 0.8038 0.8966
No log 0.5524 348 0.7061 0.3307 0.7061 0.8403
No log 0.5556 350 0.6763 0.2413 0.6763 0.8224
No log 0.5587 352 0.6470 0.2703 0.6470 0.8044
No log 0.5619 354 0.6028 0.3868 0.6028 0.7764
No log 0.5651 356 0.5800 0.4365 0.5800 0.7616
No log 0.5683 358 0.5284 0.3981 0.5284 0.7269
No log 0.5714 360 0.5611 0.3483 0.5611 0.7491
No log 0.5746 362 0.5365 0.3871 0.5365 0.7325
No log 0.5778 364 0.5369 0.4503 0.5369 0.7328
No log 0.5810 366 0.6141 0.4906 0.6141 0.7837
No log 0.5841 368 0.5754 0.5156 0.5754 0.7586
No log 0.5873 370 0.5328 0.4831 0.5328 0.7299
No log 0.5905 372 0.5312 0.5205 0.5312 0.7288
No log 0.5937 374 0.5390 0.5344 0.5390 0.7341
No log 0.5968 376 0.5080 0.5453 0.5080 0.7128
No log 0.6 378 0.4836 0.4994 0.4836 0.6954
No log 0.6032 380 0.4764 0.5056 0.4764 0.6903
No log 0.6063 382 0.4710 0.5291 0.4710 0.6863
No log 0.6095 384 0.4764 0.5278 0.4764 0.6902
No log 0.6127 386 0.5233 0.4758 0.5233 0.7234
No log 0.6159 388 0.5255 0.4312 0.5255 0.7249
No log 0.6190 390 0.5870 0.3653 0.5870 0.7662
No log 0.6222 392 0.5382 0.3765 0.5382 0.7336
No log 0.6254 394 0.5466 0.5011 0.5466 0.7393
No log 0.6286 396 0.7364 0.5201 0.7364 0.8582
No log 0.6317 398 0.8088 0.4859 0.8088 0.8994
No log 0.6349 400 0.6923 0.4458 0.6923 0.8321
No log 0.6381 402 0.6499 0.4079 0.6499 0.8062
No log 0.6413 404 0.6510 0.2981 0.6510 0.8068
No log 0.6444 406 0.5799 0.3712 0.5799 0.7615
No log 0.6476 408 0.5404 0.5066 0.5404 0.7352
No log 0.6508 410 0.5529 0.5153 0.5529 0.7436
No log 0.6540 412 0.5204 0.5214 0.5204 0.7214
No log 0.6571 414 0.5124 0.4443 0.5124 0.7158
No log 0.6603 416 0.5499 0.3820 0.5499 0.7416
No log 0.6635 418 0.5485 0.3834 0.5485 0.7406
No log 0.6667 420 0.5095 0.4395 0.5095 0.7138
No log 0.6698 422 0.5194 0.5306 0.5194 0.7207
No log 0.6730 424 0.6538 0.5553 0.6538 0.8086
No log 0.6762 426 0.5926 0.5565 0.5926 0.7698
No log 0.6794 428 0.4746 0.5538 0.4746 0.6889
No log 0.6825 430 0.4624 0.4936 0.4624 0.6800
No log 0.6857 432 0.4696 0.4875 0.4696 0.6853
No log 0.6889 434 0.4804 0.5239 0.4804 0.6931
No log 0.6921 436 0.5134 0.4897 0.5134 0.7165
No log 0.6952 438 0.5277 0.4585 0.5277 0.7265
No log 0.6984 440 0.5514 0.4653 0.5514 0.7425
No log 0.7016 442 0.6007 0.4915 0.6007 0.7751
No log 0.7048 444 0.6558 0.4798 0.6558 0.8098
No log 0.7079 446 0.7143 0.4590 0.7143 0.8452
No log 0.7111 448 0.7287 0.4563 0.7287 0.8536
No log 0.7143 450 0.7835 0.4519 0.7835 0.8852
No log 0.7175 452 0.7573 0.4478 0.7573 0.8702
No log 0.7206 454 0.6686 0.4437 0.6686 0.8177
No log 0.7238 456 0.6465 0.4758 0.6465 0.8040
No log 0.7270 458 0.5933 0.5326 0.5933 0.7703
No log 0.7302 460 0.5047 0.5342 0.5047 0.7104
No log 0.7333 462 0.4686 0.5084 0.4686 0.6845
No log 0.7365 464 0.4809 0.4889 0.4809 0.6934
No log 0.7397 466 0.4928 0.4718 0.4928 0.7020
No log 0.7429 468 0.5207 0.5043 0.5207 0.7216
No log 0.7460 470 0.6976 0.5591 0.6976 0.8353
No log 0.7492 472 0.7096 0.5501 0.7096 0.8424
No log 0.7524 474 0.6096 0.5106 0.6096 0.7807
No log 0.7556 476 0.5403 0.4616 0.5403 0.7351
No log 0.7587 478 0.5200 0.4767 0.5200 0.7211
No log 0.7619 480 0.5276 0.5647 0.5276 0.7264
No log 0.7651 482 0.4956 0.5839 0.4956 0.7040
No log 0.7683 484 0.4303 0.5495 0.4303 0.6560
No log 0.7714 486 0.4270 0.5508 0.4270 0.6535
No log 0.7746 488 0.4671 0.5832 0.4671 0.6834
No log 0.7778 490 0.4509 0.5411 0.4509 0.6715
No log 0.7810 492 0.4543 0.5276 0.4543 0.6740
No log 0.7841 494 0.4764 0.5376 0.4764 0.6902
No log 0.7873 496 0.4925 0.5210 0.4925 0.7018
No log 0.7905 498 0.5070 0.5008 0.5070 0.7121
0.6292 0.7937 500 0.5413 0.5062 0.5413 0.7357
0.6292 0.7968 502 0.5340 0.5120 0.5340 0.7308
0.6292 0.8 504 0.5202 0.4976 0.5202 0.7213
0.6292 0.8032 506 0.4973 0.4866 0.4973 0.7052
0.6292 0.8063 508 0.4584 0.4809 0.4584 0.6771
0.6292 0.8095 510 0.4525 0.4849 0.4525 0.6727
0.6292 0.8127 512 0.4407 0.5140 0.4407 0.6638
0.6292 0.8159 514 0.4345 0.5110 0.4345 0.6592
0.6292 0.8190 516 0.4602 0.4757 0.4602 0.6784
0.6292 0.8222 518 0.4409 0.5150 0.4409 0.6640
0.6292 0.8254 520 0.4801 0.5634 0.4801 0.6929
0.6292 0.8286 522 0.5027 0.5306 0.5027 0.7090
0.6292 0.8317 524 0.4951 0.5398 0.4951 0.7037
0.6292 0.8349 526 0.4882 0.4763 0.4882 0.6987
0.6292 0.8381 528 0.4680 0.5335 0.4680 0.6841
0.6292 0.8413 530 0.4481 0.5237 0.4481 0.6694
0.6292 0.8444 532 0.4580 0.4754 0.4580 0.6767
0.6292 0.8476 534 0.4757 0.4750 0.4757 0.6897
0.6292 0.8508 536 0.5345 0.4316 0.5345 0.7311
0.6292 0.8540 538 0.5105 0.4500 0.5105 0.7145
0.6292 0.8571 540 0.4952 0.4642 0.4952 0.7037

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
25
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_Aug_k40_task1_organization_fold1

Finetuned
(7052)
this model