nerui-base-2 / README.md
apwic's picture
End of training
d1dc70a verified
|
raw
history blame
36.4 kB
---
language:
- id
license: mit
base_model: indolem/indobert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: nerui-base-2
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# nerui-base-2
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co./indolem/indobert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1114
- Location Precision: 0.9381
- Location Recall: 0.9785
- Location F1: 0.9579
- Location Number: 93
- Organization Precision: 0.9509
- Organization Recall: 0.9337
- Organization F1: 0.9422
- Organization Number: 166
- Person Precision: 0.9787
- Person Recall: 0.9718
- Person F1: 0.9753
- Person Number: 142
- Overall Precision: 0.9576
- Overall Recall: 0.9576
- Overall F1: 0.9576
- Overall Accuracy: 0.9893
## 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: 5e-05
- train_batch_size: 16
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100.0
### Training results
| Training Loss | Epoch | Step | Validation Loss | Location Precision | Location Recall | Location F1 | Location Number | Organization Precision | Organization Recall | Organization F1 | Organization Number | Person Precision | Person Recall | Person F1 | Person Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:------------------:|:---------------:|:-----------:|:---------------:|:----------------------:|:-------------------:|:---------------:|:-------------------:|:----------------:|:-------------:|:---------:|:-------------:|:-----------------:|:--------------:|:----------:|:----------------:|
| 0.2635 | 1.0 | 96 | 0.0630 | 0.8182 | 0.9677 | 0.8867 | 93 | 0.8639 | 0.8795 | 0.8716 | 166 | 0.9580 | 0.9648 | 0.9614 | 142 | 0.8839 | 0.9302 | 0.9064 | 0.9813 |
| 0.0557 | 2.0 | 192 | 0.0601 | 0.8182 | 0.9677 | 0.8867 | 93 | 0.8994 | 0.8614 | 0.8800 | 166 | 0.9716 | 0.9648 | 0.9682 | 142 | 0.9024 | 0.9227 | 0.9125 | 0.9813 |
| 0.0324 | 3.0 | 288 | 0.0582 | 0.9263 | 0.9462 | 0.9362 | 93 | 0.8814 | 0.9398 | 0.9096 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.9249 | 0.9526 | 0.9386 | 0.9866 |
| 0.0198 | 4.0 | 384 | 0.0648 | 0.9326 | 0.8925 | 0.9121 | 93 | 0.8960 | 0.9337 | 0.9145 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.9330 | 0.9377 | 0.9353 | 0.9871 |
| 0.0138 | 5.0 | 480 | 0.0616 | 0.9 | 0.9677 | 0.9326 | 93 | 0.9198 | 0.8976 | 0.9085 | 166 | 0.9716 | 0.9648 | 0.9682 | 142 | 0.9330 | 0.9377 | 0.9353 | 0.9879 |
| 0.0105 | 6.0 | 576 | 0.0742 | 0.8812 | 0.9570 | 0.9175 | 93 | 0.9226 | 0.8614 | 0.8910 | 166 | 0.9720 | 0.9789 | 0.9754 | 142 | 0.9298 | 0.9252 | 0.9275 | 0.9860 |
| 0.0057 | 7.0 | 672 | 0.0728 | 0.9263 | 0.9462 | 0.9362 | 93 | 0.9337 | 0.9337 | 0.9337 | 166 | 0.9857 | 0.9718 | 0.9787 | 142 | 0.9501 | 0.9501 | 0.9501 | 0.9888 |
| 0.0047 | 8.0 | 768 | 0.0829 | 0.8273 | 0.9785 | 0.8966 | 93 | 0.94 | 0.8494 | 0.8924 | 166 | 0.9789 | 0.9789 | 0.9789 | 142 | 0.9229 | 0.9252 | 0.9240 | 0.9841 |
| 0.0054 | 9.0 | 864 | 0.0838 | 0.8667 | 0.9785 | 0.9192 | 93 | 0.9470 | 0.8614 | 0.9022 | 166 | 0.9858 | 0.9789 | 0.9823 | 142 | 0.9395 | 0.9302 | 0.9348 | 0.9863 |
| 0.0034 | 10.0 | 960 | 0.0743 | 0.9091 | 0.9677 | 0.9375 | 93 | 0.8994 | 0.9157 | 0.9075 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.9291 | 0.9476 | 0.9383 | 0.9871 |
| 0.0034 | 11.0 | 1056 | 0.0750 | 0.9192 | 0.9785 | 0.9479 | 93 | 0.9096 | 0.9096 | 0.9096 | 166 | 0.9858 | 0.9789 | 0.9823 | 142 | 0.9384 | 0.9501 | 0.9442 | 0.9874 |
| 0.0032 | 12.0 | 1152 | 0.0745 | 0.9082 | 0.9570 | 0.9319 | 93 | 0.9070 | 0.9398 | 0.9231 | 166 | 0.9856 | 0.9648 | 0.9751 | 142 | 0.9340 | 0.9526 | 0.9432 | 0.9879 |
| 0.003 | 13.0 | 1248 | 0.0792 | 0.9175 | 0.9570 | 0.9368 | 93 | 0.9509 | 0.9337 | 0.9422 | 166 | 0.9716 | 0.9648 | 0.9682 | 142 | 0.9501 | 0.9501 | 0.9501 | 0.9890 |
| 0.0027 | 14.0 | 1344 | 0.0748 | 0.9271 | 0.9570 | 0.9418 | 93 | 0.9444 | 0.9217 | 0.9329 | 166 | 0.9786 | 0.9648 | 0.9716 | 142 | 0.9523 | 0.9451 | 0.9487 | 0.9882 |
| 0.0025 | 15.0 | 1440 | 0.0770 | 0.9082 | 0.9570 | 0.9319 | 93 | 0.9281 | 0.9337 | 0.9309 | 166 | 0.9786 | 0.9648 | 0.9716 | 142 | 0.9407 | 0.9501 | 0.9454 | 0.9882 |
| 0.0034 | 16.0 | 1536 | 0.0877 | 0.8824 | 0.9677 | 0.9231 | 93 | 0.9484 | 0.8855 | 0.9159 | 166 | 0.9379 | 0.9577 | 0.9477 | 142 | 0.9279 | 0.9302 | 0.9290 | 0.9860 |
| 0.0026 | 17.0 | 1632 | 0.0913 | 0.9167 | 0.9462 | 0.9312 | 93 | 0.9264 | 0.9096 | 0.9179 | 166 | 0.9856 | 0.9648 | 0.9751 | 142 | 0.9447 | 0.9377 | 0.9412 | 0.9866 |
| 0.0036 | 18.0 | 1728 | 0.0982 | 0.9278 | 0.9677 | 0.9474 | 93 | 0.9325 | 0.9157 | 0.9240 | 166 | 0.9514 | 0.9648 | 0.9580 | 142 | 0.9381 | 0.9451 | 0.9416 | 0.9866 |
| 0.0048 | 19.0 | 1824 | 0.0963 | 0.9192 | 0.9785 | 0.9479 | 93 | 0.9673 | 0.8916 | 0.9279 | 166 | 0.9718 | 0.9718 | 0.9718 | 142 | 0.9569 | 0.9401 | 0.9484 | 0.9868 |
| 0.003 | 20.0 | 1920 | 0.0739 | 0.8585 | 0.9785 | 0.9146 | 93 | 0.9542 | 0.8795 | 0.9154 | 166 | 0.9720 | 0.9789 | 0.9754 | 142 | 0.9353 | 0.9377 | 0.9365 | 0.9885 |
| 0.0014 | 21.0 | 2016 | 0.0913 | 0.8571 | 0.9677 | 0.9091 | 93 | 0.9497 | 0.9096 | 0.9292 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.9358 | 0.9451 | 0.9404 | 0.9866 |
| 0.0013 | 22.0 | 2112 | 0.0791 | 0.9375 | 0.9677 | 0.9524 | 93 | 0.9695 | 0.9578 | 0.9636 | 166 | 0.9857 | 0.9718 | 0.9787 | 142 | 0.9675 | 0.9651 | 0.9663 | 0.9912 |
| 0.0028 | 23.0 | 2208 | 0.0864 | 0.9 | 0.9677 | 0.9326 | 93 | 0.9620 | 0.9157 | 0.9383 | 166 | 0.9856 | 0.9648 | 0.9751 | 142 | 0.9547 | 0.9451 | 0.9499 | 0.9882 |
| 0.0019 | 24.0 | 2304 | 0.0859 | 0.9271 | 0.9570 | 0.9418 | 93 | 0.9506 | 0.9277 | 0.9390 | 166 | 0.9858 | 0.9789 | 0.9823 | 142 | 0.9574 | 0.9526 | 0.955 | 0.9898 |
| 0.0021 | 25.0 | 2400 | 0.0820 | 0.9551 | 0.9140 | 0.9341 | 93 | 0.9455 | 0.9398 | 0.9426 | 166 | 0.9718 | 0.9718 | 0.9718 | 142 | 0.9571 | 0.9451 | 0.9511 | 0.9888 |
| 0.0031 | 26.0 | 2496 | 0.1160 | 0.9184 | 0.9677 | 0.9424 | 93 | 0.9610 | 0.8916 | 0.9250 | 166 | 0.9784 | 0.9577 | 0.9680 | 142 | 0.9565 | 0.9327 | 0.9444 | 0.9852 |
| 0.0024 | 27.0 | 2592 | 0.0789 | 0.9167 | 0.9462 | 0.9312 | 93 | 0.9563 | 0.9217 | 0.9387 | 166 | 0.9583 | 0.9718 | 0.9650 | 142 | 0.9475 | 0.9451 | 0.9463 | 0.9885 |
| 0.003 | 28.0 | 2688 | 0.0781 | 0.9263 | 0.9462 | 0.9362 | 93 | 0.9571 | 0.9398 | 0.9483 | 166 | 0.9857 | 0.9718 | 0.9787 | 142 | 0.9598 | 0.9526 | 0.9562 | 0.9896 |
| 0.0024 | 29.0 | 2784 | 0.0830 | 0.9043 | 0.9140 | 0.9091 | 93 | 0.9518 | 0.9518 | 0.9518 | 166 | 0.9786 | 0.9648 | 0.9716 | 142 | 0.95 | 0.9476 | 0.9488 | 0.9893 |
| 0.0017 | 30.0 | 2880 | 0.1060 | 0.8713 | 0.9462 | 0.9072 | 93 | 0.9503 | 0.9217 | 0.9358 | 166 | 0.9857 | 0.9718 | 0.9787 | 142 | 0.9428 | 0.9451 | 0.9440 | 0.9868 |
| 0.0013 | 31.0 | 2976 | 0.0892 | 0.9271 | 0.9570 | 0.9418 | 93 | 0.9565 | 0.9277 | 0.9419 | 166 | 0.9648 | 0.9648 | 0.9648 | 142 | 0.9524 | 0.9476 | 0.95 | 0.9893 |
| 0.0013 | 32.0 | 3072 | 0.1206 | 0.8922 | 0.9785 | 0.9333 | 93 | 0.9610 | 0.8916 | 0.9250 | 166 | 0.9517 | 0.9718 | 0.9617 | 142 | 0.9401 | 0.9401 | 0.9401 | 0.9849 |
| 0.0029 | 33.0 | 3168 | 0.0824 | 0.9158 | 0.9355 | 0.9255 | 93 | 0.9515 | 0.9458 | 0.9486 | 166 | 0.9784 | 0.9577 | 0.9680 | 142 | 0.9524 | 0.9476 | 0.95 | 0.9901 |
| 0.0024 | 34.0 | 3264 | 0.0859 | 0.89 | 0.9570 | 0.9223 | 93 | 0.9571 | 0.9398 | 0.9483 | 166 | 0.9784 | 0.9577 | 0.9680 | 142 | 0.9478 | 0.9501 | 0.9489 | 0.9893 |
| 0.0008 | 35.0 | 3360 | 0.0747 | 0.9091 | 0.9677 | 0.9375 | 93 | 0.9634 | 0.9518 | 0.9576 | 166 | 0.9714 | 0.9577 | 0.9645 | 142 | 0.9529 | 0.9576 | 0.9552 | 0.9918 |
| 0.0007 | 36.0 | 3456 | 0.0777 | 0.9468 | 0.9570 | 0.9519 | 93 | 0.9755 | 0.9578 | 0.9666 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.9698 | 0.9626 | 0.9662 | 0.9920 |
| 0.0012 | 37.0 | 3552 | 0.0848 | 0.9278 | 0.9677 | 0.9474 | 93 | 0.9691 | 0.9458 | 0.9573 | 166 | 0.9856 | 0.9648 | 0.9751 | 142 | 0.9648 | 0.9576 | 0.9612 | 0.9909 |
| 0.0017 | 38.0 | 3648 | 0.0790 | 0.9375 | 0.9677 | 0.9524 | 93 | 0.9812 | 0.9458 | 0.9632 | 166 | 0.9858 | 0.9789 | 0.9823 | 142 | 0.9723 | 0.9626 | 0.9674 | 0.9918 |
| 0.0014 | 39.0 | 3744 | 0.0866 | 0.9 | 0.9677 | 0.9326 | 93 | 0.9212 | 0.9157 | 0.9184 | 166 | 0.9858 | 0.9789 | 0.9823 | 142 | 0.9384 | 0.9501 | 0.9442 | 0.9890 |
| 0.0011 | 40.0 | 3840 | 0.0883 | 0.9375 | 0.9677 | 0.9524 | 93 | 0.9560 | 0.9157 | 0.9354 | 166 | 0.9858 | 0.9789 | 0.9823 | 142 | 0.9621 | 0.9501 | 0.9561 | 0.9901 |
| 0.0012 | 41.0 | 3936 | 0.0860 | 0.8835 | 0.9785 | 0.9286 | 93 | 0.9375 | 0.9036 | 0.9202 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.9381 | 0.9451 | 0.9416 | 0.9901 |
| 0.0009 | 42.0 | 4032 | 0.0790 | 0.9362 | 0.9462 | 0.9412 | 93 | 0.9630 | 0.9398 | 0.9512 | 166 | 0.9789 | 0.9789 | 0.9789 | 142 | 0.9623 | 0.9551 | 0.9587 | 0.9909 |
| 0.0008 | 43.0 | 4128 | 0.0831 | 0.9570 | 0.9570 | 0.9570 | 93 | 0.9176 | 0.9398 | 0.9286 | 166 | 0.9858 | 0.9789 | 0.9823 | 142 | 0.9505 | 0.9576 | 0.9540 | 0.9904 |
| 0.0015 | 44.0 | 4224 | 0.0857 | 0.9271 | 0.9570 | 0.9418 | 93 | 0.9451 | 0.9337 | 0.9394 | 166 | 0.9786 | 0.9648 | 0.9716 | 142 | 0.9525 | 0.9501 | 0.9513 | 0.9904 |
| 0.0009 | 45.0 | 4320 | 0.0915 | 0.9167 | 0.9462 | 0.9312 | 93 | 0.9571 | 0.9398 | 0.9483 | 166 | 0.9857 | 0.9718 | 0.9787 | 142 | 0.9574 | 0.9526 | 0.955 | 0.9901 |
| 0.0009 | 46.0 | 4416 | 0.0775 | 0.9278 | 0.9677 | 0.9474 | 93 | 0.9571 | 0.9398 | 0.9483 | 166 | 0.9858 | 0.9789 | 0.9823 | 142 | 0.9601 | 0.9601 | 0.9601 | 0.9915 |
| 0.0016 | 47.0 | 4512 | 0.0854 | 0.9368 | 0.9570 | 0.9468 | 93 | 0.9693 | 0.9518 | 0.9605 | 166 | 0.9858 | 0.9789 | 0.9823 | 142 | 0.9674 | 0.9626 | 0.965 | 0.9912 |
| 0.001 | 48.0 | 4608 | 0.0885 | 0.9175 | 0.9570 | 0.9368 | 93 | 0.9691 | 0.9458 | 0.9573 | 166 | 0.9856 | 0.9648 | 0.9751 | 142 | 0.9623 | 0.9551 | 0.9587 | 0.9907 |
| 0.0021 | 49.0 | 4704 | 0.0764 | 0.9192 | 0.9785 | 0.9479 | 93 | 0.9506 | 0.9277 | 0.9390 | 166 | 0.9858 | 0.9789 | 0.9823 | 142 | 0.9552 | 0.9576 | 0.9564 | 0.9907 |
| 0.0015 | 50.0 | 4800 | 0.0824 | 0.9474 | 0.9677 | 0.9574 | 93 | 0.9627 | 0.9337 | 0.9480 | 166 | 0.9789 | 0.9789 | 0.9789 | 142 | 0.9648 | 0.9576 | 0.9612 | 0.9907 |
| 0.0013 | 51.0 | 4896 | 0.0942 | 0.9091 | 0.9677 | 0.9375 | 93 | 0.9448 | 0.9277 | 0.9362 | 166 | 0.9857 | 0.9718 | 0.9787 | 142 | 0.9502 | 0.9526 | 0.9514 | 0.9885 |
| 0.0006 | 52.0 | 4992 | 0.0899 | 0.9184 | 0.9677 | 0.9424 | 93 | 0.9568 | 0.9337 | 0.9451 | 166 | 0.9857 | 0.9718 | 0.9787 | 142 | 0.9575 | 0.9551 | 0.9563 | 0.9901 |
| 0.0022 | 53.0 | 5088 | 0.0872 | 0.9167 | 0.9462 | 0.9312 | 93 | 0.9455 | 0.9398 | 0.9426 | 166 | 0.9857 | 0.9718 | 0.9787 | 142 | 0.9526 | 0.9526 | 0.9526 | 0.9890 |
| 0.0012 | 54.0 | 5184 | 0.0873 | 0.9271 | 0.9570 | 0.9418 | 93 | 0.9506 | 0.9277 | 0.9390 | 166 | 0.9858 | 0.9789 | 0.9823 | 142 | 0.9574 | 0.9526 | 0.955 | 0.9896 |
| 0.0006 | 55.0 | 5280 | 0.0995 | 0.9175 | 0.9570 | 0.9368 | 93 | 0.9444 | 0.9217 | 0.9329 | 166 | 0.9784 | 0.9577 | 0.9680 | 142 | 0.9497 | 0.9426 | 0.9462 | 0.9885 |
| 0.0002 | 56.0 | 5376 | 0.0965 | 0.9278 | 0.9677 | 0.9474 | 93 | 0.9383 | 0.9157 | 0.9268 | 166 | 0.9720 | 0.9789 | 0.9754 | 142 | 0.9478 | 0.9501 | 0.9489 | 0.9893 |
| 0.0005 | 57.0 | 5472 | 0.1086 | 0.9082 | 0.9570 | 0.9319 | 93 | 0.9677 | 0.9036 | 0.9346 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.9569 | 0.9401 | 0.9484 | 0.9879 |
| 0.0003 | 58.0 | 5568 | 0.1007 | 0.9474 | 0.9677 | 0.9574 | 93 | 0.9444 | 0.9217 | 0.9329 | 166 | 0.9789 | 0.9789 | 0.9789 | 142 | 0.9574 | 0.9526 | 0.955 | 0.9893 |
| 0.0002 | 59.0 | 5664 | 0.0988 | 0.9474 | 0.9677 | 0.9574 | 93 | 0.9390 | 0.9277 | 0.9333 | 166 | 0.9720 | 0.9789 | 0.9754 | 142 | 0.9527 | 0.9551 | 0.9539 | 0.9893 |
| 0.0005 | 60.0 | 5760 | 0.0942 | 0.9362 | 0.9462 | 0.9412 | 93 | 0.9565 | 0.9277 | 0.9419 | 166 | 0.9720 | 0.9789 | 0.9754 | 142 | 0.9573 | 0.9501 | 0.9537 | 0.9904 |
| 0.0014 | 61.0 | 5856 | 0.1181 | 0.9175 | 0.9570 | 0.9368 | 93 | 0.9437 | 0.9096 | 0.9264 | 166 | 0.9718 | 0.9718 | 0.9718 | 142 | 0.9474 | 0.9426 | 0.9450 | 0.9877 |
| 0.0009 | 62.0 | 5952 | 0.0939 | 0.9375 | 0.9677 | 0.9524 | 93 | 0.9448 | 0.9277 | 0.9362 | 166 | 0.9789 | 0.9789 | 0.9789 | 142 | 0.9551 | 0.9551 | 0.9551 | 0.9904 |
| 0.0003 | 63.0 | 6048 | 0.0859 | 0.9375 | 0.9677 | 0.9524 | 93 | 0.9455 | 0.9398 | 0.9426 | 166 | 0.9858 | 0.9789 | 0.9823 | 142 | 0.9577 | 0.9601 | 0.9589 | 0.9909 |
| 0.0008 | 64.0 | 6144 | 0.0942 | 0.9479 | 0.9785 | 0.9630 | 93 | 0.9448 | 0.9277 | 0.9362 | 166 | 0.9653 | 0.9789 | 0.9720 | 142 | 0.9529 | 0.9576 | 0.9552 | 0.9904 |
| 0.0005 | 65.0 | 6240 | 0.0939 | 0.9278 | 0.9677 | 0.9474 | 93 | 0.9387 | 0.9217 | 0.9301 | 166 | 0.9720 | 0.9789 | 0.9754 | 142 | 0.9479 | 0.9526 | 0.9502 | 0.9896 |
| 0.0002 | 66.0 | 6336 | 0.0949 | 0.9278 | 0.9677 | 0.9474 | 93 | 0.9387 | 0.9217 | 0.9301 | 166 | 0.9720 | 0.9789 | 0.9754 | 142 | 0.9479 | 0.9526 | 0.9502 | 0.9896 |
| 0.0003 | 67.0 | 6432 | 0.0882 | 0.9474 | 0.9677 | 0.9574 | 93 | 0.9333 | 0.9277 | 0.9305 | 166 | 0.9720 | 0.9789 | 0.9754 | 142 | 0.9504 | 0.9551 | 0.9527 | 0.9904 |
| 0.0013 | 68.0 | 6528 | 0.0922 | 0.9286 | 0.9785 | 0.9529 | 93 | 0.9444 | 0.9217 | 0.9329 | 166 | 0.9789 | 0.9789 | 0.9789 | 142 | 0.9527 | 0.9551 | 0.9539 | 0.9901 |
| 0.0004 | 69.0 | 6624 | 0.0925 | 0.9375 | 0.9677 | 0.9524 | 93 | 0.9455 | 0.9398 | 0.9426 | 166 | 0.9858 | 0.9789 | 0.9823 | 142 | 0.9577 | 0.9601 | 0.9589 | 0.9904 |
| 0.0014 | 70.0 | 6720 | 0.0978 | 0.9381 | 0.9785 | 0.9579 | 93 | 0.9398 | 0.9398 | 0.9398 | 166 | 0.9858 | 0.9789 | 0.9823 | 142 | 0.9554 | 0.9626 | 0.9590 | 0.9898 |
| 0.0003 | 71.0 | 6816 | 0.0987 | 0.9375 | 0.9677 | 0.9524 | 93 | 0.9277 | 0.9277 | 0.9277 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.9479 | 0.9526 | 0.9502 | 0.9888 |
| 0.0002 | 72.0 | 6912 | 0.1066 | 0.9381 | 0.9785 | 0.9579 | 93 | 0.9448 | 0.9277 | 0.9362 | 166 | 0.9718 | 0.9718 | 0.9718 | 142 | 0.9527 | 0.9551 | 0.9539 | 0.9885 |
| 0.0002 | 73.0 | 7008 | 0.1091 | 0.9381 | 0.9785 | 0.9579 | 93 | 0.9390 | 0.9277 | 0.9333 | 166 | 0.9718 | 0.9718 | 0.9718 | 142 | 0.9504 | 0.9551 | 0.9527 | 0.9888 |
| 0.0002 | 74.0 | 7104 | 0.1119 | 0.9278 | 0.9677 | 0.9474 | 93 | 0.9325 | 0.9157 | 0.9240 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.9476 | 0.9476 | 0.9476 | 0.9879 |
| 0.0003 | 75.0 | 7200 | 0.1084 | 0.9381 | 0.9785 | 0.9579 | 93 | 0.9273 | 0.9217 | 0.9245 | 166 | 0.9789 | 0.9789 | 0.9789 | 142 | 0.9480 | 0.9551 | 0.9516 | 0.9893 |
| 0.0011 | 76.0 | 7296 | 0.1087 | 0.9375 | 0.9677 | 0.9524 | 93 | 0.9390 | 0.9277 | 0.9333 | 166 | 0.9789 | 0.9789 | 0.9789 | 142 | 0.9527 | 0.9551 | 0.9539 | 0.9890 |
| 0.0002 | 77.0 | 7392 | 0.1093 | 0.9375 | 0.9677 | 0.9524 | 93 | 0.9509 | 0.9337 | 0.9422 | 166 | 0.9789 | 0.9789 | 0.9789 | 142 | 0.9576 | 0.9576 | 0.9576 | 0.9893 |
| 0.0002 | 78.0 | 7488 | 0.1095 | 0.9375 | 0.9677 | 0.9524 | 93 | 0.9509 | 0.9337 | 0.9422 | 166 | 0.9789 | 0.9789 | 0.9789 | 142 | 0.9576 | 0.9576 | 0.9576 | 0.9893 |
| 0.0004 | 79.0 | 7584 | 0.1074 | 0.9381 | 0.9785 | 0.9579 | 93 | 0.9390 | 0.9277 | 0.9333 | 166 | 0.9789 | 0.9789 | 0.9789 | 142 | 0.9529 | 0.9576 | 0.9552 | 0.9893 |
| 0.0003 | 80.0 | 7680 | 0.1161 | 0.9278 | 0.9677 | 0.9474 | 93 | 0.9444 | 0.9217 | 0.9329 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.9525 | 0.9501 | 0.9513 | 0.9885 |
| 0.0002 | 81.0 | 7776 | 0.1176 | 0.9278 | 0.9677 | 0.9474 | 93 | 0.9448 | 0.9277 | 0.9362 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.9526 | 0.9526 | 0.9526 | 0.9888 |
| 0.0003 | 82.0 | 7872 | 0.1145 | 0.9375 | 0.9677 | 0.9524 | 93 | 0.9509 | 0.9337 | 0.9422 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.9575 | 0.9551 | 0.9563 | 0.9890 |
| 0.0002 | 83.0 | 7968 | 0.1036 | 0.9271 | 0.9570 | 0.9418 | 93 | 0.9408 | 0.9578 | 0.9493 | 166 | 0.9716 | 0.9648 | 0.9682 | 142 | 0.9483 | 0.9601 | 0.9542 | 0.9893 |
| 0.0004 | 84.0 | 8064 | 0.1039 | 0.9278 | 0.9677 | 0.9474 | 93 | 0.9461 | 0.9518 | 0.9489 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.9531 | 0.9626 | 0.9578 | 0.9896 |
| 0.0008 | 85.0 | 8160 | 0.1043 | 0.9278 | 0.9677 | 0.9474 | 93 | 0.9401 | 0.9458 | 0.9429 | 166 | 0.9716 | 0.9648 | 0.9682 | 142 | 0.9481 | 0.9576 | 0.9529 | 0.9890 |
| 0.0003 | 86.0 | 8256 | 0.1141 | 0.9381 | 0.9785 | 0.9579 | 93 | 0.9444 | 0.9217 | 0.9329 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.955 | 0.9526 | 0.9538 | 0.9885 |
| 0.0002 | 87.0 | 8352 | 0.1169 | 0.9381 | 0.9785 | 0.9579 | 93 | 0.9568 | 0.9337 | 0.9451 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.96 | 0.9576 | 0.9588 | 0.9890 |
| 0.0002 | 88.0 | 8448 | 0.1167 | 0.9381 | 0.9785 | 0.9579 | 93 | 0.9568 | 0.9337 | 0.9451 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.96 | 0.9576 | 0.9588 | 0.9890 |
| 0.0002 | 89.0 | 8544 | 0.1165 | 0.9381 | 0.9785 | 0.9579 | 93 | 0.9568 | 0.9337 | 0.9451 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.96 | 0.9576 | 0.9588 | 0.9890 |
| 0.0002 | 90.0 | 8640 | 0.1125 | 0.9381 | 0.9785 | 0.9579 | 93 | 0.9568 | 0.9337 | 0.9451 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.96 | 0.9576 | 0.9588 | 0.9890 |
| 0.0001 | 91.0 | 8736 | 0.1115 | 0.9381 | 0.9785 | 0.9579 | 93 | 0.9568 | 0.9337 | 0.9451 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.96 | 0.9576 | 0.9588 | 0.9890 |
| 0.0001 | 92.0 | 8832 | 0.1116 | 0.9381 | 0.9785 | 0.9579 | 93 | 0.9568 | 0.9337 | 0.9451 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.96 | 0.9576 | 0.9588 | 0.9890 |
| 0.0001 | 93.0 | 8928 | 0.1115 | 0.9381 | 0.9785 | 0.9579 | 93 | 0.9568 | 0.9337 | 0.9451 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.96 | 0.9576 | 0.9588 | 0.9890 |
| 0.0002 | 94.0 | 9024 | 0.1121 | 0.9381 | 0.9785 | 0.9579 | 93 | 0.9568 | 0.9337 | 0.9451 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.96 | 0.9576 | 0.9588 | 0.9890 |
| 0.0002 | 95.0 | 9120 | 0.1112 | 0.9381 | 0.9785 | 0.9579 | 93 | 0.9509 | 0.9337 | 0.9422 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.9576 | 0.9576 | 0.9576 | 0.9893 |
| 0.0002 | 96.0 | 9216 | 0.1113 | 0.9381 | 0.9785 | 0.9579 | 93 | 0.9509 | 0.9337 | 0.9422 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.9576 | 0.9576 | 0.9576 | 0.9893 |
| 0.0001 | 97.0 | 9312 | 0.1112 | 0.9381 | 0.9785 | 0.9579 | 93 | 0.9509 | 0.9337 | 0.9422 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.9576 | 0.9576 | 0.9576 | 0.9893 |
| 0.0002 | 98.0 | 9408 | 0.1113 | 0.9381 | 0.9785 | 0.9579 | 93 | 0.9509 | 0.9337 | 0.9422 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.9576 | 0.9576 | 0.9576 | 0.9893 |
| 0.0002 | 99.0 | 9504 | 0.1114 | 0.9381 | 0.9785 | 0.9579 | 93 | 0.9509 | 0.9337 | 0.9422 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.9576 | 0.9576 | 0.9576 | 0.9893 |
| 0.0001 | 100.0 | 9600 | 0.1114 | 0.9381 | 0.9785 | 0.9579 | 93 | 0.9509 | 0.9337 | 0.9422 | 166 | 0.9787 | 0.9718 | 0.9753 | 142 | 0.9576 | 0.9576 | 0.9576 | 0.9893 |
### Framework versions
- Transformers 4.39.3
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.15.2