ASAP_FineTuningBERT_AugV4_k5_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: 0.7141
  • Qwk: 0.5246
  • Mse: 0.7141
  • Rmse: 0.8451

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 0.0039 2 10.3231 0.0012 10.3231 3.2130
No log 0.0079 4 9.0408 0.0 9.0408 3.0068
No log 0.0118 6 7.4538 0.0 7.4538 2.7302
No log 0.0157 8 6.6306 0.0 6.6306 2.5750
No log 0.0196 10 5.7346 0.0349 5.7346 2.3947
No log 0.0236 12 4.7638 0.0115 4.7638 2.1826
No log 0.0275 14 3.9586 0.0039 3.9586 1.9896
No log 0.0314 16 3.1861 0.0 3.1861 1.7850
No log 0.0354 18 2.6209 0.0080 2.6209 1.6189
No log 0.0393 20 2.0064 0.0372 2.0064 1.4165
No log 0.0432 22 1.4451 0.0344 1.4451 1.2021
No log 0.0472 24 1.0854 0.0212 1.0854 1.0418
No log 0.0511 26 0.8846 0.1124 0.8846 0.9405
No log 0.0550 28 0.7862 0.1360 0.7862 0.8867
No log 0.0589 30 0.7806 0.0521 0.7806 0.8835
No log 0.0629 32 0.8402 0.0521 0.8402 0.9166
No log 0.0668 34 0.8707 0.0521 0.8707 0.9331
No log 0.0707 36 0.9418 0.0348 0.9418 0.9705
No log 0.0747 38 0.9589 0.0348 0.9589 0.9793
No log 0.0786 40 0.8128 0.0521 0.8128 0.9016
No log 0.0825 42 0.7976 0.0521 0.7976 0.8931
No log 0.0864 44 0.8807 0.0348 0.8807 0.9385
No log 0.0904 46 0.8433 0.0348 0.8433 0.9183
No log 0.0943 48 0.8589 0.0348 0.8589 0.9268
No log 0.0982 50 0.7681 0.0444 0.7681 0.8764
No log 0.1022 52 0.8269 0.3320 0.8269 0.9093
No log 0.1061 54 0.9483 0.1476 0.9483 0.9738
No log 0.1100 56 0.7166 0.3553 0.7166 0.8465
No log 0.1139 58 0.7334 0.0657 0.7334 0.8564
No log 0.1179 60 0.7373 0.0796 0.7373 0.8587
No log 0.1218 62 0.6761 0.2314 0.6761 0.8223
No log 0.1257 64 0.6584 0.3490 0.6584 0.8114
No log 0.1297 66 0.7923 0.3240 0.7923 0.8901
No log 0.1336 68 0.8229 0.3175 0.8229 0.9071
No log 0.1375 70 0.6617 0.3712 0.6617 0.8134
No log 0.1415 72 0.6208 0.3498 0.6208 0.7879
No log 0.1454 74 0.6182 0.3672 0.6182 0.7863
No log 0.1493 76 0.6346 0.3624 0.6346 0.7966
No log 0.1532 78 0.6647 0.3749 0.6647 0.8153
No log 0.1572 80 0.6462 0.3865 0.6462 0.8039
No log 0.1611 82 0.6135 0.3485 0.6135 0.7832
No log 0.1650 84 0.6242 0.2779 0.6242 0.7901
No log 0.1690 86 0.6501 0.2764 0.6501 0.8063
No log 0.1729 88 0.6378 0.3621 0.6378 0.7986
No log 0.1768 90 0.6523 0.3949 0.6523 0.8076
No log 0.1807 92 0.7601 0.4141 0.7601 0.8718
No log 0.1847 94 1.2787 0.3443 1.2787 1.1308
No log 0.1886 96 1.2864 0.3438 1.2864 1.1342
No log 0.1925 98 0.8078 0.3996 0.8078 0.8988
No log 0.1965 100 0.7401 0.3452 0.7401 0.8603
No log 0.2004 102 0.8650 0.3899 0.8650 0.9300
No log 0.2043 104 0.8730 0.3770 0.8730 0.9343
No log 0.2083 106 0.8568 0.3901 0.8568 0.9256
No log 0.2122 108 0.7161 0.4354 0.7161 0.8462
No log 0.2161 110 0.6627 0.4625 0.6627 0.8141
No log 0.2200 112 0.6573 0.4769 0.6573 0.8107
No log 0.2240 114 0.6558 0.4547 0.6558 0.8098
No log 0.2279 116 0.6909 0.4471 0.6909 0.8312
No log 0.2318 118 0.8626 0.4188 0.8626 0.9288
No log 0.2358 120 0.9443 0.4074 0.9443 0.9717
No log 0.2397 122 0.8417 0.4634 0.8417 0.9175
No log 0.2436 124 0.7527 0.4861 0.7527 0.8676
No log 0.2475 126 0.6732 0.4896 0.6732 0.8205
No log 0.2515 128 0.6308 0.4966 0.6308 0.7943
No log 0.2554 130 0.6427 0.4266 0.6427 0.8017
No log 0.2593 132 0.6440 0.4176 0.6440 0.8025
No log 0.2633 134 0.5872 0.4610 0.5872 0.7663
No log 0.2672 136 0.6025 0.5151 0.6025 0.7762
No log 0.2711 138 0.6107 0.4808 0.6107 0.7815
No log 0.2750 140 0.5828 0.4926 0.5828 0.7634
No log 0.2790 142 0.5725 0.5058 0.5725 0.7566
No log 0.2829 144 0.5811 0.5155 0.5811 0.7623
No log 0.2868 146 0.5923 0.5485 0.5923 0.7696
No log 0.2908 148 0.6674 0.5389 0.6674 0.8170
No log 0.2947 150 0.6884 0.5404 0.6884 0.8297
No log 0.2986 152 0.7312 0.5577 0.7312 0.8551
No log 0.3026 154 1.0047 0.4597 1.0047 1.0023
No log 0.3065 156 1.1639 0.4227 1.1639 1.0788
No log 0.3104 158 0.8552 0.5034 0.8552 0.9248
No log 0.3143 160 0.6546 0.5589 0.6546 0.8091
No log 0.3183 162 0.7863 0.4637 0.7863 0.8867
No log 0.3222 164 0.7504 0.4751 0.7504 0.8662
No log 0.3261 166 0.5994 0.5534 0.5994 0.7742
No log 0.3301 168 0.6171 0.5565 0.6171 0.7856
No log 0.3340 170 0.5929 0.5538 0.5929 0.7700
No log 0.3379 172 0.6902 0.5037 0.6902 0.8308
No log 0.3418 174 0.6827 0.5006 0.6827 0.8263
No log 0.3458 176 0.5947 0.5273 0.5947 0.7712
No log 0.3497 178 0.5617 0.5424 0.5617 0.7494
No log 0.3536 180 0.6162 0.4913 0.6162 0.7850
No log 0.3576 182 0.5855 0.5312 0.5855 0.7652
No log 0.3615 184 0.5703 0.5639 0.5703 0.7552
No log 0.3654 186 0.6961 0.4779 0.6961 0.8343
No log 0.3694 188 0.6509 0.5181 0.6509 0.8068
No log 0.3733 190 0.5579 0.5099 0.5579 0.7470
No log 0.3772 192 0.5679 0.5019 0.5679 0.7536
No log 0.3811 194 0.6860 0.4627 0.6860 0.8282
No log 0.3851 196 0.7463 0.4276 0.7463 0.8639
No log 0.3890 198 0.8966 0.3631 0.8966 0.9469
No log 0.3929 200 0.8602 0.3978 0.8602 0.9274
No log 0.3969 202 0.7300 0.4685 0.7300 0.8544
No log 0.4008 204 0.6137 0.5175 0.6137 0.7834
No log 0.4047 206 0.5479 0.5300 0.5479 0.7402
No log 0.4086 208 0.5463 0.5099 0.5463 0.7391
No log 0.4126 210 0.5403 0.5238 0.5403 0.7350
No log 0.4165 212 0.5658 0.5234 0.5658 0.7522
No log 0.4204 214 0.5604 0.5408 0.5604 0.7486
No log 0.4244 216 0.5489 0.5526 0.5489 0.7409
No log 0.4283 218 0.5559 0.5608 0.5559 0.7456
No log 0.4322 220 0.5958 0.5252 0.5958 0.7719
No log 0.4361 222 0.6170 0.5246 0.6170 0.7855
No log 0.4401 224 0.6408 0.5182 0.6408 0.8005
No log 0.4440 226 0.7574 0.4841 0.7574 0.8703
No log 0.4479 228 0.7367 0.4999 0.7367 0.8583
No log 0.4519 230 0.6436 0.5132 0.6436 0.8022
No log 0.4558 232 0.5999 0.5387 0.5999 0.7746
No log 0.4597 234 0.5861 0.5099 0.5861 0.7655
No log 0.4637 236 0.6685 0.4689 0.6685 0.8176
No log 0.4676 238 0.7280 0.4626 0.7280 0.8532
No log 0.4715 240 0.5494 0.5188 0.5494 0.7412
No log 0.4754 242 0.7816 0.4666 0.7816 0.8841
No log 0.4794 244 1.1087 0.3485 1.1087 1.0530
No log 0.4833 246 0.9545 0.3859 0.9545 0.9770
No log 0.4872 248 0.6046 0.5192 0.6046 0.7776
No log 0.4912 250 0.5730 0.4962 0.5730 0.7570
No log 0.4951 252 0.5686 0.4883 0.5686 0.7540
No log 0.4990 254 0.6106 0.5163 0.6106 0.7814
No log 0.5029 256 1.0541 0.3511 1.0541 1.0267
No log 0.5069 258 1.6691 0.1710 1.6691 1.2919
No log 0.5108 260 1.7808 0.1390 1.7808 1.3345
No log 0.5147 262 1.5876 0.1774 1.5876 1.2600
No log 0.5187 264 1.1397 0.2915 1.1397 1.0676
No log 0.5226 266 0.6917 0.4401 0.6917 0.8317
No log 0.5265 268 0.5828 0.4461 0.5828 0.7634
No log 0.5305 270 0.5857 0.4337 0.5857 0.7653
No log 0.5344 272 0.6264 0.3944 0.6264 0.7915
No log 0.5383 274 0.6073 0.4193 0.6073 0.7793
No log 0.5422 276 0.5751 0.4298 0.5751 0.7583
No log 0.5462 278 0.6149 0.4635 0.6149 0.7841
No log 0.5501 280 0.7149 0.4445 0.7149 0.8455
No log 0.5540 282 0.7590 0.4356 0.7590 0.8712
No log 0.5580 284 0.6405 0.4662 0.6405 0.8003
No log 0.5619 286 0.5324 0.5198 0.5324 0.7297
No log 0.5658 288 0.6382 0.4461 0.6382 0.7989
No log 0.5697 290 0.6764 0.4435 0.6764 0.8224
No log 0.5737 292 0.5711 0.5131 0.5711 0.7557
No log 0.5776 294 0.5716 0.5181 0.5716 0.7561
No log 0.5815 296 0.7283 0.4508 0.7283 0.8534
No log 0.5855 298 0.7408 0.4325 0.7408 0.8607
No log 0.5894 300 0.6252 0.5008 0.6252 0.7907
No log 0.5933 302 0.5663 0.4872 0.5663 0.7525
No log 0.5972 304 0.5704 0.4694 0.5704 0.7553
No log 0.6012 306 0.5728 0.4800 0.5728 0.7568
No log 0.6051 308 0.6282 0.4896 0.6282 0.7926
No log 0.6090 310 0.7343 0.4440 0.7343 0.8569
No log 0.6130 312 0.7665 0.4291 0.7665 0.8755
No log 0.6169 314 0.8875 0.4086 0.8875 0.9421
No log 0.6208 316 0.8607 0.4269 0.8607 0.9277
No log 0.6248 318 0.7242 0.4866 0.7242 0.8510
No log 0.6287 320 0.8130 0.4448 0.8130 0.9017
No log 0.6326 322 0.9201 0.4199 0.9201 0.9592
No log 0.6365 324 0.7647 0.4658 0.7647 0.8745
No log 0.6405 326 0.7136 0.4873 0.7136 0.8448
No log 0.6444 328 0.7888 0.4693 0.7888 0.8881
No log 0.6483 330 0.7451 0.4882 0.7451 0.8632
No log 0.6523 332 0.7011 0.5056 0.7011 0.8373
No log 0.6562 334 0.5923 0.5559 0.5923 0.7696
No log 0.6601 336 0.5742 0.6040 0.5742 0.7578
No log 0.6640 338 0.5899 0.5929 0.5899 0.7680
No log 0.6680 340 0.6451 0.5865 0.6451 0.8032
No log 0.6719 342 0.6178 0.6050 0.6178 0.7860
No log 0.6758 344 0.6106 0.5990 0.6106 0.7814
No log 0.6798 346 0.6417 0.5831 0.6417 0.8011
No log 0.6837 348 0.5981 0.6068 0.5981 0.7734
No log 0.6876 350 0.7151 0.5565 0.7151 0.8457
No log 0.6916 352 0.8198 0.5009 0.8198 0.9054
No log 0.6955 354 0.7023 0.5547 0.7023 0.8381
No log 0.6994 356 0.5672 0.5999 0.5672 0.7531
No log 0.7033 358 0.5502 0.5976 0.5502 0.7417
No log 0.7073 360 0.5651 0.5861 0.5651 0.7517
No log 0.7112 362 0.6006 0.6039 0.6006 0.7750
No log 0.7151 364 0.6753 0.5583 0.6753 0.8217
No log 0.7191 366 0.6400 0.5829 0.6400 0.8000
No log 0.7230 368 0.6157 0.6054 0.6157 0.7847
No log 0.7269 370 0.6384 0.5853 0.6384 0.7990
No log 0.7308 372 0.6248 0.5891 0.6248 0.7905
No log 0.7348 374 0.6583 0.5703 0.6583 0.8113
No log 0.7387 376 0.7277 0.5057 0.7277 0.8531
No log 0.7426 378 0.7087 0.5086 0.7087 0.8418
No log 0.7466 380 0.6053 0.5827 0.6053 0.7780
No log 0.7505 382 0.5966 0.5845 0.5966 0.7724
No log 0.7544 384 0.5991 0.5865 0.5991 0.7740
No log 0.7583 386 0.6060 0.5957 0.6060 0.7784
No log 0.7623 388 0.6487 0.5538 0.6487 0.8054
No log 0.7662 390 0.6608 0.5504 0.6608 0.8129
No log 0.7701 392 0.6188 0.5820 0.6188 0.7867
No log 0.7741 394 0.5998 0.5842 0.5998 0.7744
No log 0.7780 396 0.6283 0.5552 0.6283 0.7926
No log 0.7819 398 0.6070 0.5508 0.6070 0.7791
No log 0.7859 400 0.5820 0.5878 0.5820 0.7629
No log 0.7898 402 0.5990 0.5731 0.5990 0.7740
No log 0.7937 404 0.6110 0.5749 0.6110 0.7817
No log 0.7976 406 0.6228 0.6023 0.6228 0.7892
No log 0.8016 408 0.6472 0.5911 0.6472 0.8045
No log 0.8055 410 0.6487 0.5774 0.6487 0.8054
No log 0.8094 412 0.6591 0.5898 0.6591 0.8118
No log 0.8134 414 0.6468 0.5911 0.6468 0.8042
No log 0.8173 416 0.6412 0.5703 0.6412 0.8007
No log 0.8212 418 0.6636 0.5504 0.6636 0.8146
No log 0.8251 420 0.7726 0.4895 0.7726 0.8790
No log 0.8291 422 0.8024 0.4558 0.8024 0.8958
No log 0.8330 424 0.6757 0.4668 0.6757 0.8220
No log 0.8369 426 0.6662 0.4783 0.6662 0.8162
No log 0.8409 428 0.8380 0.4234 0.8380 0.9154
No log 0.8448 430 0.8901 0.4233 0.8901 0.9435
No log 0.8487 432 0.7660 0.4595 0.7660 0.8752
No log 0.8527 434 0.8330 0.4376 0.8330 0.9127
No log 0.8566 436 0.8657 0.4454 0.8657 0.9304
No log 0.8605 438 0.6664 0.5531 0.6664 0.8163
No log 0.8644 440 0.5784 0.5633 0.5784 0.7605
No log 0.8684 442 0.5777 0.5691 0.5777 0.7601
No log 0.8723 444 0.6182 0.5646 0.6182 0.7863
No log 0.8762 446 0.6933 0.5540 0.6933 0.8327
No log 0.8802 448 0.6178 0.5839 0.6178 0.7860
No log 0.8841 450 0.6198 0.5529 0.6198 0.7873
No log 0.8880 452 0.6139 0.5537 0.6139 0.7835
No log 0.8919 454 0.5982 0.5798 0.5982 0.7734
No log 0.8959 456 0.6105 0.5663 0.6105 0.7813
No log 0.8998 458 0.6302 0.5139 0.6302 0.7939
No log 0.9037 460 0.5832 0.5504 0.5832 0.7637
No log 0.9077 462 0.6067 0.5125 0.6067 0.7789
No log 0.9116 464 0.6535 0.5163 0.6535 0.8084
No log 0.9155 466 0.5842 0.5314 0.5842 0.7643
No log 0.9194 468 0.5946 0.5250 0.5946 0.7711
No log 0.9234 470 0.6609 0.4881 0.6609 0.8129
No log 0.9273 472 0.6493 0.5099 0.6493 0.8058
No log 0.9312 474 0.5665 0.5381 0.5665 0.7527
No log 0.9352 476 0.5726 0.5304 0.5726 0.7567
No log 0.9391 478 0.5761 0.5374 0.5761 0.7590
No log 0.9430 480 0.5789 0.5268 0.5789 0.7609
No log 0.9470 482 0.6424 0.5279 0.6424 0.8015
No log 0.9509 484 0.5988 0.5374 0.5988 0.7738
No log 0.9548 486 0.5865 0.5202 0.5865 0.7658
No log 0.9587 488 0.7806 0.4822 0.7806 0.8835
No log 0.9627 490 0.8265 0.4772 0.8265 0.9091
No log 0.9666 492 0.6493 0.5071 0.6493 0.8058
No log 0.9705 494 0.5550 0.5493 0.5550 0.7450
No log 0.9745 496 0.6054 0.5583 0.6054 0.7781
No log 0.9784 498 0.5999 0.5900 0.5999 0.7745
0.9447 0.9823 500 0.5681 0.5709 0.5681 0.7537
0.9447 0.9862 502 0.6701 0.5117 0.6701 0.8186
0.9447 0.9902 504 0.6511 0.5218 0.6511 0.8069
0.9447 0.9941 506 0.5562 0.5944 0.5562 0.7458
0.9447 0.9980 508 0.5509 0.6022 0.5509 0.7422
0.9447 1.0020 510 0.5610 0.5930 0.5610 0.7490
0.9447 1.0059 512 0.5687 0.5833 0.5687 0.7541
0.9447 1.0098 514 0.5593 0.5880 0.5593 0.7479
0.9447 1.0138 516 0.5692 0.5916 0.5692 0.7544
0.9447 1.0177 518 0.5750 0.5742 0.5750 0.7583
0.9447 1.0216 520 0.6603 0.5358 0.6603 0.8126
0.9447 1.0255 522 0.6876 0.5147 0.6876 0.8292
0.9447 1.0295 524 0.6107 0.5474 0.6107 0.7815
0.9447 1.0334 526 0.6010 0.5567 0.6010 0.7752
0.9447 1.0373 528 0.7141 0.5246 0.7141 0.8451

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_AugV4_k5_task1_organization_fold0

Finetuned
(7018)
this model