ASAP_FineTuningBERT_Aug_k40_task1_organization_fold4

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: 0.6750
  • Qwk: 0.4932
  • Mse: 0.6750
  • Rmse: 0.8216

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 7.3131 0.0015 7.3131 2.7043
No log 0.0067 4 6.0732 0.0037 6.0732 2.4644
No log 0.01 6 4.6700 0.0018 4.6700 2.1610
No log 0.0133 8 3.9073 0.0454 3.9073 1.9767
No log 0.0167 10 3.1212 0.0118 3.1212 1.7667
No log 0.02 12 2.5938 0.0118 2.5938 1.6105
No log 0.0233 14 2.1413 0.0079 2.1413 1.4633
No log 0.0267 16 1.7464 0.0040 1.7464 1.3215
No log 0.03 18 1.3867 0.0585 1.3867 1.1776
No log 0.0333 20 1.1445 0.0420 1.1445 1.0698
No log 0.0367 22 0.9659 0.0420 0.9659 0.9828
No log 0.04 24 0.8905 0.0316 0.8905 0.9437
No log 0.0433 26 0.8760 0.0212 0.8760 0.9360
No log 0.0467 28 0.9395 0.0212 0.9395 0.9693
No log 0.05 30 1.0418 0.0212 1.0418 1.0207
No log 0.0533 32 0.9041 0.0212 0.9041 0.9509
No log 0.0567 34 0.8627 0.0212 0.8627 0.9288
No log 0.06 36 0.9394 0.0420 0.9394 0.9692
No log 0.0633 38 0.8766 0.0316 0.8766 0.9363
No log 0.0667 40 0.9057 0.0107 0.9057 0.9517
No log 0.07 42 0.9885 0.0107 0.9885 0.9942
No log 0.0733 44 0.9730 0.0107 0.9730 0.9864
No log 0.0767 46 0.9117 0.0107 0.9117 0.9548
No log 0.08 48 0.8938 0.0212 0.8938 0.9454
No log 0.0833 50 0.8796 0.0212 0.8796 0.9378
No log 0.0867 52 0.8934 0.0212 0.8934 0.9452
No log 0.09 54 0.9174 0.0316 0.9174 0.9578
No log 0.0933 56 0.9195 0.0316 0.9195 0.9589
No log 0.0967 58 0.8815 0.0316 0.8815 0.9389
No log 0.1 60 0.8647 0.0212 0.8647 0.9299
No log 0.1033 62 0.8747 0.0212 0.8747 0.9352
No log 0.1067 64 0.9259 0.0107 0.9259 0.9622
No log 0.11 66 0.9265 0.0107 0.9265 0.9625
No log 0.1133 68 0.8933 0.0107 0.8933 0.9451
No log 0.1167 70 0.8919 0.0107 0.8919 0.9444
No log 0.12 72 0.8852 0.0107 0.8852 0.9409
No log 0.1233 74 0.8580 0.0212 0.8580 0.9263
No log 0.1267 76 0.8493 0.0212 0.8493 0.9216
No log 0.13 78 0.8469 0.0212 0.8469 0.9202
No log 0.1333 80 0.8510 0.0212 0.8510 0.9225
No log 0.1367 82 0.8575 0.0212 0.8575 0.9260
No log 0.14 84 0.8614 0.0212 0.8614 0.9281
No log 0.1433 86 0.8503 0.0212 0.8503 0.9221
No log 0.1467 88 0.8522 0.0212 0.8522 0.9231
No log 0.15 90 0.8491 0.0107 0.8491 0.9214
No log 0.1533 92 0.8588 0.0107 0.8588 0.9267
No log 0.1567 94 0.8521 0.0107 0.8521 0.9231
No log 0.16 96 0.8458 0.0107 0.8458 0.9197
No log 0.1633 98 0.8452 0.0107 0.8452 0.9193
No log 0.1667 100 0.8429 0.0212 0.8429 0.9181
No log 0.17 102 0.8426 0.0212 0.8426 0.9179
No log 0.1733 104 0.8686 0.0212 0.8686 0.9320
No log 0.1767 106 0.8806 0.0381 0.8806 0.9384
No log 0.18 108 0.8405 0.0212 0.8405 0.9168
No log 0.1833 110 0.8689 0.0212 0.8689 0.9322
No log 0.1867 112 0.9865 0.0316 0.9865 0.9932
No log 0.19 114 0.9393 0.0212 0.9393 0.9692
No log 0.1933 116 0.8434 0.0212 0.8434 0.9184
No log 0.1967 118 0.8380 0.0212 0.8380 0.9154
No log 0.2 120 0.8515 0.0212 0.8515 0.9228
No log 0.2033 122 0.8620 0.0212 0.8620 0.9284
No log 0.2067 124 0.8568 0.0107 0.8568 0.9257
No log 0.21 126 0.8838 0.0107 0.8838 0.9401
No log 0.2133 128 0.9296 0.0107 0.9296 0.9642
No log 0.2167 130 0.8976 0.0107 0.8976 0.9474
No log 0.22 132 0.8677 0.0107 0.8677 0.9315
No log 0.2233 134 0.8436 0.0107 0.8436 0.9185
No log 0.2267 136 0.8434 0.0158 0.8434 0.9184
No log 0.23 138 0.8393 0.0158 0.8393 0.9161
No log 0.2333 140 0.8301 0.0107 0.8301 0.9111
No log 0.2367 142 0.8184 0.0107 0.8184 0.9047
No log 0.24 144 0.8100 0.0107 0.8100 0.9000
No log 0.2433 146 0.8190 0.0204 0.8190 0.9050
No log 0.2467 148 0.8428 0.0481 0.8428 0.9180
No log 0.25 150 0.8246 0.0158 0.8246 0.9081
No log 0.2533 152 0.8060 0.0107 0.8060 0.8978
No log 0.2567 154 0.8161 0.0107 0.8161 0.9034
No log 0.26 156 0.8413 0.0107 0.8413 0.9173
No log 0.2633 158 0.8286 0.0107 0.8286 0.9103
No log 0.2667 160 0.7882 0.0107 0.7882 0.8878
No log 0.27 162 0.7730 0.0213 0.7730 0.8792
No log 0.2733 164 0.7714 0.0213 0.7714 0.8783
No log 0.2767 166 0.7634 0.0598 0.7634 0.8737
No log 0.28 168 0.7709 0.2138 0.7709 0.8780
No log 0.2833 170 0.8030 0.3367 0.8030 0.8961
No log 0.2867 172 0.8432 0.2980 0.8432 0.9183
No log 0.29 174 0.8204 0.1221 0.8204 0.9058
No log 0.2933 176 0.8118 0.0236 0.8118 0.9010
No log 0.2967 178 0.7966 0.0224 0.7966 0.8925
No log 0.3 180 0.8065 0.0213 0.8065 0.8980
No log 0.3033 182 0.8312 0.0448 0.8312 0.9117
No log 0.3067 184 0.8560 0.1947 0.8560 0.9252
No log 0.31 186 0.8333 0.3438 0.8333 0.9129
No log 0.3133 188 0.8173 0.2360 0.8173 0.9041
No log 0.3167 190 0.7963 0.1626 0.7963 0.8924
No log 0.32 192 0.8080 0.2154 0.8080 0.8989
No log 0.3233 194 0.8426 0.3594 0.8426 0.9179
No log 0.3267 196 0.8119 0.3679 0.8119 0.9010
No log 0.33 198 0.7726 0.2310 0.7726 0.8790
No log 0.3333 200 0.7566 0.1696 0.7566 0.8698
No log 0.3367 202 0.7511 0.1236 0.7511 0.8667
No log 0.34 204 0.7644 0.1118 0.7644 0.8743
No log 0.3433 206 0.7687 0.0773 0.7687 0.8768
No log 0.3467 208 0.7929 0.0806 0.7929 0.8904
No log 0.35 210 0.7920 0.1751 0.7920 0.8899
No log 0.3533 212 0.7883 0.1882 0.7883 0.8879
No log 0.3567 214 0.8249 0.3179 0.8249 0.9082
No log 0.36 216 0.9258 0.2607 0.9258 0.9622
No log 0.3633 218 1.0299 0.2091 1.0299 1.0149
No log 0.3667 220 1.0075 0.1964 1.0075 1.0038
No log 0.37 222 0.9025 0.3529 0.9025 0.9500
No log 0.3733 224 0.8133 0.0125 0.8133 0.9018
No log 0.3767 226 0.7937 0.0224 0.7937 0.8909
No log 0.38 228 0.7690 0.0090 0.7690 0.8769
No log 0.3833 230 0.7605 0.0633 0.7605 0.8721
No log 0.3867 232 0.7822 0.2699 0.7822 0.8844
No log 0.39 234 0.7766 0.2693 0.7766 0.8813
No log 0.3933 236 0.7611 0.2494 0.7611 0.8724
No log 0.3967 238 0.7399 0.1246 0.7399 0.8602
No log 0.4 240 0.7357 0.1193 0.7357 0.8577
No log 0.4033 242 0.7560 0.3054 0.7560 0.8695
No log 0.4067 244 0.8292 0.3290 0.8292 0.9106
No log 0.41 246 0.8625 0.3210 0.8625 0.9287
No log 0.4133 248 0.8183 0.3341 0.8183 0.9046
No log 0.4167 250 0.7649 0.2267 0.7649 0.8746
No log 0.42 252 0.7639 0.2294 0.7639 0.8740
No log 0.4233 254 0.7788 0.2840 0.7788 0.8825
No log 0.4267 256 0.7749 0.2926 0.7749 0.8803
No log 0.43 258 0.7554 0.2521 0.7554 0.8691
No log 0.4333 260 0.7252 0.1566 0.7252 0.8516
No log 0.4367 262 0.7283 0.0949 0.7283 0.8534
No log 0.44 264 0.7220 0.1131 0.7220 0.8497
No log 0.4433 266 0.7139 0.1459 0.7139 0.8449
No log 0.4467 268 0.7078 0.1877 0.7078 0.8413
No log 0.45 270 0.6962 0.1416 0.6962 0.8344
No log 0.4533 272 0.6988 0.0744 0.6988 0.8359
No log 0.4567 274 0.6863 0.1265 0.6863 0.8284
No log 0.46 276 0.6852 0.1749 0.6852 0.8278
No log 0.4633 278 0.6920 0.1942 0.6920 0.8318
No log 0.4667 280 0.7117 0.2115 0.7117 0.8436
No log 0.47 282 0.7206 0.2308 0.7206 0.8489
No log 0.4733 284 0.7534 0.3935 0.7534 0.8680
No log 0.4767 286 0.7274 0.3525 0.7274 0.8529
No log 0.48 288 0.7100 0.2481 0.7100 0.8426
No log 0.4833 290 0.7153 0.1361 0.7153 0.8458
No log 0.4867 292 0.7219 0.2007 0.7219 0.8496
No log 0.49 294 0.7683 0.3862 0.7683 0.8766
No log 0.4933 296 0.7886 0.4004 0.7886 0.8880
No log 0.4967 298 0.7592 0.3468 0.7592 0.8713
No log 0.5 300 0.7272 0.2133 0.7272 0.8527
No log 0.5033 302 0.7531 0.0616 0.7531 0.8678
No log 0.5067 304 0.7916 0.0193 0.7916 0.8897
No log 0.51 306 0.7451 0.0629 0.7451 0.8632
No log 0.5133 308 0.7059 0.2679 0.7059 0.8402
No log 0.5167 310 0.7755 0.4216 0.7755 0.8806
No log 0.52 312 0.7614 0.4039 0.7614 0.8726
No log 0.5233 314 0.6995 0.2251 0.6995 0.8364
No log 0.5267 316 0.6953 0.2286 0.6953 0.8338
No log 0.53 318 0.6996 0.3513 0.6996 0.8364
No log 0.5333 320 0.7480 0.4213 0.7480 0.8649
No log 0.5367 322 0.7448 0.4225 0.7448 0.8630
No log 0.54 324 0.6537 0.3370 0.6537 0.8085
No log 0.5433 326 0.6507 0.2499 0.6507 0.8067
No log 0.5467 328 0.6435 0.2750 0.6435 0.8022
No log 0.55 330 0.6476 0.3451 0.6476 0.8047
No log 0.5533 332 0.6487 0.3439 0.6487 0.8054
No log 0.5567 334 0.6618 0.2035 0.6618 0.8135
No log 0.56 336 0.7544 0.1291 0.7544 0.8686
No log 0.5633 338 0.7557 0.1070 0.7557 0.8693
No log 0.5667 340 0.6914 0.1524 0.6914 0.8315
No log 0.57 342 0.6949 0.2960 0.6949 0.8336
No log 0.5733 344 0.7091 0.3344 0.7091 0.8421
No log 0.5767 346 0.6873 0.2147 0.6873 0.8290
No log 0.58 348 0.7099 0.1077 0.7099 0.8426
No log 0.5833 350 0.7245 0.0999 0.7245 0.8511
No log 0.5867 352 0.6814 0.1515 0.6814 0.8255
No log 0.59 354 0.7034 0.3931 0.7034 0.8387
No log 0.5933 356 0.7782 0.4201 0.7782 0.8822
No log 0.5967 358 0.7965 0.4124 0.7965 0.8925
No log 0.6 360 0.7162 0.4443 0.7162 0.8463
No log 0.6033 362 0.6457 0.2474 0.6457 0.8036
No log 0.6067 364 0.6688 0.1789 0.6688 0.8178
No log 0.61 366 0.6679 0.1621 0.6679 0.8173
No log 0.6133 368 0.6582 0.2699 0.6582 0.8113
No log 0.6167 370 0.7196 0.4078 0.7196 0.8483
No log 0.62 372 0.7616 0.4385 0.7616 0.8727
No log 0.6233 374 0.7211 0.4016 0.7211 0.8492
No log 0.6267 376 0.6690 0.2619 0.6690 0.8179
No log 0.63 378 0.6942 0.1122 0.6942 0.8332
No log 0.6333 380 0.7067 0.0982 0.7067 0.8406
No log 0.6367 382 0.6656 0.1372 0.6656 0.8158
No log 0.64 384 0.6711 0.3856 0.6711 0.8192
No log 0.6433 386 0.7158 0.4286 0.7158 0.8460
No log 0.6467 388 0.6916 0.4115 0.6916 0.8316
No log 0.65 390 0.6578 0.3889 0.6578 0.8111
No log 0.6533 392 0.6439 0.2094 0.6439 0.8024
No log 0.6567 394 0.6534 0.1648 0.6534 0.8083
No log 0.66 396 0.6221 0.2588 0.6221 0.7887
No log 0.6633 398 0.6233 0.4330 0.6233 0.7895
No log 0.6667 400 0.7200 0.4843 0.7200 0.8485
No log 0.67 402 0.7278 0.4802 0.7278 0.8531
No log 0.6733 404 0.6295 0.4902 0.6295 0.7934
No log 0.6767 406 0.5816 0.3392 0.5816 0.7626
No log 0.68 408 0.6468 0.2483 0.6468 0.8042
No log 0.6833 410 0.6077 0.2707 0.6077 0.7796
No log 0.6867 412 0.6084 0.3203 0.6084 0.7800
No log 0.69 414 0.6433 0.4046 0.6433 0.8020
No log 0.6933 416 0.6523 0.3986 0.6523 0.8076
No log 0.6967 418 0.6532 0.4020 0.6532 0.8082
No log 0.7 420 0.6878 0.4356 0.6878 0.8293
No log 0.7033 422 0.7720 0.4379 0.7720 0.8786
No log 0.7067 424 0.7797 0.4357 0.7797 0.8830
No log 0.71 426 0.7150 0.4068 0.7150 0.8456
No log 0.7133 428 0.6683 0.4089 0.6683 0.8175
No log 0.7167 430 0.6520 0.3329 0.6520 0.8075
No log 0.72 432 0.6700 0.3704 0.6700 0.8185
No log 0.7233 434 0.7807 0.3934 0.7807 0.8836
No log 0.7267 436 0.8701 0.4149 0.8701 0.9328
No log 0.73 438 0.7700 0.4296 0.7700 0.8775
No log 0.7333 440 0.6237 0.4095 0.6237 0.7897
No log 0.7367 442 0.6289 0.2332 0.6289 0.7930
No log 0.74 444 0.6250 0.2347 0.6250 0.7905
No log 0.7433 446 0.6318 0.4003 0.6318 0.7949
No log 0.7467 448 0.7334 0.4287 0.7334 0.8564
No log 0.75 450 0.7679 0.4229 0.7679 0.8763
No log 0.7533 452 0.7023 0.4073 0.7023 0.8380
No log 0.7567 454 0.6267 0.3620 0.6267 0.7917
No log 0.76 456 0.6293 0.2289 0.6293 0.7933
No log 0.7633 458 0.6167 0.2680 0.6167 0.7853
No log 0.7667 460 0.6275 0.4411 0.6275 0.7921
No log 0.77 462 0.6390 0.4447 0.6390 0.7994
No log 0.7733 464 0.6114 0.4320 0.6114 0.7819
No log 0.7767 466 0.5903 0.3767 0.5903 0.7683
No log 0.78 468 0.5836 0.4418 0.5836 0.7640
No log 0.7833 470 0.5668 0.4720 0.5668 0.7529
No log 0.7867 472 0.6012 0.4784 0.6012 0.7754
No log 0.79 474 0.5954 0.4751 0.5954 0.7716
No log 0.7933 476 0.5706 0.4377 0.5706 0.7554
No log 0.7967 478 0.5834 0.4529 0.5834 0.7638
No log 0.8 480 0.6041 0.4572 0.6041 0.7772
No log 0.8033 482 0.6819 0.4828 0.6819 0.8257
No log 0.8067 484 0.6376 0.4715 0.6376 0.7985
No log 0.81 486 0.5855 0.4521 0.5855 0.7652
No log 0.8133 488 0.5836 0.4562 0.5836 0.7639
No log 0.8167 490 0.6106 0.4894 0.6106 0.7814
No log 0.82 492 0.6098 0.4961 0.6098 0.7809
No log 0.8233 494 0.5488 0.4700 0.5488 0.7408
No log 0.8267 496 0.5307 0.4096 0.5307 0.7285
No log 0.83 498 0.5289 0.4667 0.5289 0.7273
0.4697 0.8333 500 0.5734 0.5133 0.5734 0.7572
0.4697 0.8367 502 0.5398 0.4779 0.5398 0.7347
0.4697 0.84 504 0.5314 0.4118 0.5314 0.7290
0.4697 0.8433 506 0.5274 0.4090 0.5274 0.7262
0.4697 0.8467 508 0.5753 0.5105 0.5753 0.7585
0.4697 0.85 510 0.6750 0.4932 0.6750 0.8216

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu118
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
5
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_Aug_k40_task1_organization_fold4

Finetuned
(7010)
this model