Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,172 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: indolem/indobert-base-uncased
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: nerui-base-0
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# nerui-base-0
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.1036
|
| 19 |
+
- Location Precision: 0.9278
|
| 20 |
+
- Location Recall: 0.9574
|
| 21 |
+
- Location F1: 0.9424
|
| 22 |
+
- Location Number: 94
|
| 23 |
+
- Organization Precision: 0.95
|
| 24 |
+
- Organization Recall: 0.9102
|
| 25 |
+
- Organization F1: 0.9297
|
| 26 |
+
- Organization Number: 167
|
| 27 |
+
- Person Precision: 0.9851
|
| 28 |
+
- Person Recall: 0.9635
|
| 29 |
+
- Person F1: 0.9742
|
| 30 |
+
- Person Number: 137
|
| 31 |
+
- Overall Precision: 0.9565
|
| 32 |
+
- Overall Recall: 0.9397
|
| 33 |
+
- Overall F1: 0.9480
|
| 34 |
+
- Overall Accuracy: 0.9892
|
| 35 |
+
|
| 36 |
+
## Model description
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Intended uses & limitations
|
| 41 |
+
|
| 42 |
+
More information needed
|
| 43 |
+
|
| 44 |
+
## Training and evaluation data
|
| 45 |
+
|
| 46 |
+
More information needed
|
| 47 |
+
|
| 48 |
+
## Training procedure
|
| 49 |
+
|
| 50 |
+
### Training hyperparameters
|
| 51 |
+
|
| 52 |
+
The following hyperparameters were used during training:
|
| 53 |
+
- learning_rate: 5e-05
|
| 54 |
+
- train_batch_size: 16
|
| 55 |
+
- eval_batch_size: 64
|
| 56 |
+
- seed: 42
|
| 57 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 58 |
+
- lr_scheduler_type: linear
|
| 59 |
+
- num_epochs: 100.0
|
| 60 |
+
|
| 61 |
+
### Training results
|
| 62 |
+
|
| 63 |
+
| 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 |
|
| 64 |
+
|:-------------:|:-----:|:----:|:---------------:|:------------------:|:---------------:|:-----------:|:---------------:|:----------------------:|:-------------------:|:---------------:|:-------------------:|:----------------:|:-------------:|:---------:|:-------------:|:-----------------:|:--------------:|:----------:|:----------------:|
|
| 65 |
+
| 0.2611 | 1.0 | 96 | 0.0463 | 0.8969 | 0.9255 | 0.9110 | 94 | 0.8837 | 0.9102 | 0.8968 | 167 | 0.9854 | 0.9854 | 0.9854 | 137 | 0.9212 | 0.9397 | 0.9303 | 0.9865 |
|
| 66 |
+
| 0.0645 | 2.0 | 192 | 0.0678 | 0.7627 | 0.9574 | 0.8491 | 94 | 0.8758 | 0.8443 | 0.8598 | 167 | 0.9925 | 0.9708 | 0.9815 | 137 | 0.8814 | 0.9146 | 0.8977 | 0.9779 |
|
| 67 |
+
| 0.0354 | 3.0 | 288 | 0.0467 | 0.9 | 0.9574 | 0.9278 | 94 | 0.8935 | 0.9042 | 0.8988 | 167 | 0.9783 | 0.9854 | 0.9818 | 137 | 0.9238 | 0.9447 | 0.9342 | 0.9862 |
|
| 68 |
+
| 0.0232 | 4.0 | 384 | 0.0635 | 0.8911 | 0.9574 | 0.9231 | 94 | 0.9487 | 0.8862 | 0.9164 | 167 | 0.9771 | 0.9343 | 0.9552 | 137 | 0.9433 | 0.9196 | 0.9313 | 0.9845 |
|
| 69 |
+
| 0.0158 | 5.0 | 480 | 0.0530 | 0.8585 | 0.9681 | 0.91 | 94 | 0.9533 | 0.8563 | 0.9022 | 167 | 0.9854 | 0.9854 | 0.9854 | 137 | 0.9389 | 0.9271 | 0.9330 | 0.9862 |
|
| 70 |
+
| 0.011 | 6.0 | 576 | 0.0508 | 0.9175 | 0.9468 | 0.9319 | 94 | 0.9157 | 0.9102 | 0.9129 | 167 | 0.9853 | 0.9781 | 0.9817 | 137 | 0.9398 | 0.9422 | 0.9410 | 0.9878 |
|
| 71 |
+
| 0.0086 | 7.0 | 672 | 0.0657 | 0.9255 | 0.9255 | 0.9255 | 94 | 0.9017 | 0.9341 | 0.9176 | 167 | 0.9853 | 0.9781 | 0.9817 | 137 | 0.9355 | 0.9472 | 0.9413 | 0.9865 |
|
| 72 |
+
| 0.007 | 8.0 | 768 | 0.0754 | 0.8866 | 0.9149 | 0.9005 | 94 | 0.8935 | 0.9042 | 0.8988 | 167 | 0.9852 | 0.9708 | 0.9779 | 137 | 0.9227 | 0.9296 | 0.9262 | 0.9865 |
|
| 73 |
+
| 0.0061 | 9.0 | 864 | 0.0703 | 0.9231 | 0.8936 | 0.9081 | 94 | 0.8729 | 0.9461 | 0.9080 | 167 | 1.0 | 0.9781 | 0.9889 | 137 | 0.9261 | 0.9447 | 0.9353 | 0.9878 |
|
| 74 |
+
| 0.0058 | 10.0 | 960 | 0.0650 | 0.9130 | 0.8936 | 0.9032 | 94 | 0.8757 | 0.9281 | 0.9012 | 167 | 0.9708 | 0.9708 | 0.9708 | 137 | 0.9163 | 0.9347 | 0.9254 | 0.9867 |
|
| 75 |
+
| 0.0048 | 11.0 | 1056 | 0.0849 | 0.8812 | 0.9468 | 0.9128 | 94 | 0.9006 | 0.9222 | 0.9112 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9236 | 0.9422 | 0.9328 | 0.9859 |
|
| 76 |
+
| 0.0057 | 12.0 | 1152 | 0.0725 | 0.8969 | 0.9255 | 0.9110 | 94 | 0.8851 | 0.9222 | 0.9032 | 167 | 1.0 | 0.9781 | 0.9889 | 137 | 0.9259 | 0.9422 | 0.9340 | 0.9870 |
|
| 77 |
+
| 0.0052 | 13.0 | 1248 | 0.0872 | 0.9333 | 0.8936 | 0.9130 | 94 | 0.8869 | 0.8922 | 0.8896 | 167 | 0.9853 | 0.9781 | 0.9817 | 137 | 0.9315 | 0.9221 | 0.9268 | 0.9845 |
|
| 78 |
+
| 0.002 | 14.0 | 1344 | 0.0797 | 0.9121 | 0.8830 | 0.8973 | 94 | 0.9231 | 0.9341 | 0.9286 | 167 | 0.9853 | 0.9781 | 0.9817 | 137 | 0.9419 | 0.9372 | 0.9395 | 0.9881 |
|
| 79 |
+
| 0.0036 | 15.0 | 1440 | 0.0880 | 0.9451 | 0.9149 | 0.9297 | 94 | 0.9075 | 0.9401 | 0.9235 | 167 | 1.0 | 0.9781 | 0.9889 | 137 | 0.9472 | 0.9472 | 0.9472 | 0.9873 |
|
| 80 |
+
| 0.0026 | 16.0 | 1536 | 0.0871 | 0.8842 | 0.8936 | 0.8889 | 94 | 0.9390 | 0.9222 | 0.9305 | 167 | 0.9852 | 0.9708 | 0.9779 | 137 | 0.9416 | 0.9322 | 0.9369 | 0.9870 |
|
| 81 |
+
| 0.0028 | 17.0 | 1632 | 0.0821 | 0.89 | 0.9468 | 0.9175 | 94 | 0.9277 | 0.9222 | 0.9249 | 167 | 1.0 | 0.9708 | 0.9852 | 137 | 0.9424 | 0.9447 | 0.9435 | 0.9884 |
|
| 82 |
+
| 0.0024 | 18.0 | 1728 | 0.0746 | 0.8980 | 0.9362 | 0.9167 | 94 | 0.9394 | 0.9281 | 0.9337 | 167 | 0.9925 | 0.9635 | 0.9778 | 137 | 0.9470 | 0.9422 | 0.9446 | 0.9890 |
|
| 83 |
+
| 0.003 | 19.0 | 1824 | 0.0849 | 0.88 | 0.9362 | 0.9072 | 94 | 0.9207 | 0.9042 | 0.9124 | 167 | 0.9706 | 0.9635 | 0.9670 | 137 | 0.9275 | 0.9322 | 0.9298 | 0.9859 |
|
| 84 |
+
| 0.0035 | 20.0 | 1920 | 0.0830 | 0.87 | 0.9255 | 0.8969 | 94 | 0.9444 | 0.9162 | 0.9301 | 167 | 0.9925 | 0.9708 | 0.9815 | 137 | 0.9419 | 0.9372 | 0.9395 | 0.9876 |
|
| 85 |
+
| 0.0015 | 21.0 | 2016 | 0.0965 | 0.8947 | 0.9043 | 0.8995 | 94 | 0.9172 | 0.9281 | 0.9226 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9347 | 0.9347 | 0.9347 | 0.9865 |
|
| 86 |
+
| 0.0029 | 22.0 | 2112 | 0.1119 | 0.8947 | 0.9043 | 0.8995 | 94 | 0.9006 | 0.9222 | 0.9112 | 167 | 0.9496 | 0.9635 | 0.9565 | 137 | 0.9160 | 0.9322 | 0.9240 | 0.9831 |
|
| 87 |
+
| 0.0031 | 23.0 | 2208 | 0.1021 | 0.8932 | 0.9787 | 0.9340 | 94 | 0.9527 | 0.8443 | 0.8952 | 167 | 0.9638 | 0.9708 | 0.9673 | 137 | 0.9409 | 0.9196 | 0.9301 | 0.9843 |
|
| 88 |
+
| 0.0023 | 24.0 | 2304 | 0.0873 | 0.8725 | 0.9468 | 0.9082 | 94 | 0.9207 | 0.9042 | 0.9124 | 167 | 0.9779 | 0.9708 | 0.9744 | 137 | 0.9279 | 0.9372 | 0.9325 | 0.9865 |
|
| 89 |
+
| 0.0029 | 25.0 | 2400 | 0.1052 | 0.8571 | 0.9574 | 0.9045 | 94 | 0.9030 | 0.8922 | 0.8976 | 167 | 0.9781 | 0.9781 | 0.9781 | 137 | 0.9165 | 0.9372 | 0.9267 | 0.9856 |
|
| 90 |
+
| 0.0033 | 26.0 | 2496 | 0.1222 | 0.7946 | 0.9468 | 0.8641 | 94 | 0.9419 | 0.8743 | 0.9068 | 167 | 0.9708 | 0.9708 | 0.9708 | 137 | 0.9109 | 0.9246 | 0.9177 | 0.9829 |
|
| 91 |
+
| 0.0021 | 27.0 | 2592 | 0.1137 | 0.8641 | 0.9468 | 0.9036 | 94 | 0.9202 | 0.8982 | 0.9091 | 167 | 0.9708 | 0.9708 | 0.9708 | 137 | 0.9231 | 0.9347 | 0.9288 | 0.9854 |
|
| 92 |
+
| 0.0014 | 28.0 | 2688 | 0.0999 | 0.8854 | 0.9043 | 0.8947 | 94 | 0.8953 | 0.9222 | 0.9086 | 167 | 0.9850 | 0.9562 | 0.9704 | 137 | 0.9227 | 0.9296 | 0.9262 | 0.9862 |
|
| 93 |
+
| 0.0017 | 29.0 | 2784 | 0.0964 | 0.8854 | 0.9043 | 0.8947 | 94 | 0.8935 | 0.9042 | 0.8988 | 167 | 0.9571 | 0.9781 | 0.9675 | 137 | 0.9136 | 0.9296 | 0.9215 | 0.9843 |
|
| 94 |
+
| 0.0064 | 30.0 | 2880 | 0.0691 | 0.8854 | 0.9043 | 0.8947 | 94 | 0.9235 | 0.9401 | 0.9318 | 167 | 0.9925 | 0.9635 | 0.9778 | 137 | 0.9373 | 0.9397 | 0.9385 | 0.9876 |
|
| 95 |
+
| 0.0032 | 31.0 | 2976 | 0.0872 | 0.8980 | 0.9362 | 0.9167 | 94 | 0.9075 | 0.9401 | 0.9235 | 167 | 1.0 | 0.9708 | 0.9852 | 137 | 0.9356 | 0.9497 | 0.9426 | 0.9878 |
|
| 96 |
+
| 0.0027 | 32.0 | 3072 | 0.0921 | 0.8889 | 0.9362 | 0.9119 | 94 | 0.9118 | 0.9281 | 0.9199 | 167 | 0.9850 | 0.9562 | 0.9704 | 137 | 0.9303 | 0.9397 | 0.9350 | 0.9862 |
|
| 97 |
+
| 0.0017 | 33.0 | 3168 | 0.0955 | 0.8878 | 0.9255 | 0.9062 | 94 | 0.9448 | 0.9222 | 0.9333 | 167 | 0.9776 | 0.9562 | 0.9668 | 137 | 0.9418 | 0.9347 | 0.9382 | 0.9870 |
|
| 98 |
+
| 0.0027 | 34.0 | 3264 | 0.1089 | 0.8835 | 0.9681 | 0.9239 | 94 | 0.9509 | 0.9281 | 0.9394 | 167 | 0.9852 | 0.9708 | 0.9779 | 137 | 0.9451 | 0.9523 | 0.9487 | 0.9867 |
|
| 99 |
+
| 0.0024 | 35.0 | 3360 | 0.0920 | 0.8738 | 0.9574 | 0.9137 | 94 | 0.9451 | 0.9281 | 0.9366 | 167 | 0.9640 | 0.9781 | 0.9710 | 137 | 0.9335 | 0.9523 | 0.9428 | 0.9870 |
|
| 100 |
+
| 0.0022 | 36.0 | 3456 | 0.0792 | 0.9192 | 0.9681 | 0.9430 | 94 | 0.9625 | 0.9222 | 0.9419 | 167 | 0.9638 | 0.9708 | 0.9673 | 137 | 0.9521 | 0.9497 | 0.9509 | 0.9898 |
|
| 101 |
+
| 0.0013 | 37.0 | 3552 | 0.0962 | 0.8911 | 0.9574 | 0.9231 | 94 | 0.9509 | 0.9281 | 0.9394 | 167 | 0.9925 | 0.9708 | 0.9815 | 137 | 0.9497 | 0.9497 | 0.9497 | 0.9884 |
|
| 102 |
+
| 0.0028 | 38.0 | 3648 | 0.0811 | 0.9091 | 0.9574 | 0.9326 | 94 | 0.9123 | 0.9341 | 0.9231 | 167 | 0.9850 | 0.9562 | 0.9704 | 137 | 0.9355 | 0.9472 | 0.9413 | 0.9876 |
|
| 103 |
+
| 0.0022 | 39.0 | 3744 | 0.1019 | 0.8788 | 0.9255 | 0.9016 | 94 | 0.9162 | 0.9162 | 0.9162 | 167 | 0.9850 | 0.9562 | 0.9704 | 137 | 0.9298 | 0.9322 | 0.9310 | 0.9859 |
|
| 104 |
+
| 0.0012 | 40.0 | 3840 | 0.0960 | 0.8889 | 0.9362 | 0.9119 | 94 | 0.8971 | 0.9401 | 0.9181 | 167 | 0.9925 | 0.9635 | 0.9778 | 137 | 0.9263 | 0.9472 | 0.9366 | 0.9867 |
|
| 105 |
+
| 0.0008 | 41.0 | 3936 | 0.0964 | 0.8922 | 0.9681 | 0.9286 | 94 | 0.9682 | 0.9102 | 0.9383 | 167 | 0.9852 | 0.9708 | 0.9779 | 137 | 0.9543 | 0.9447 | 0.9495 | 0.9890 |
|
| 106 |
+
| 0.0015 | 42.0 | 4032 | 0.0783 | 0.9175 | 0.9468 | 0.9319 | 94 | 0.9048 | 0.9102 | 0.9075 | 167 | 0.9708 | 0.9708 | 0.9708 | 137 | 0.9303 | 0.9397 | 0.9350 | 0.9881 |
|
| 107 |
+
| 0.0019 | 43.0 | 4128 | 0.0777 | 0.8932 | 0.9787 | 0.9340 | 94 | 0.9387 | 0.9162 | 0.9273 | 167 | 0.9925 | 0.9708 | 0.9815 | 137 | 0.945 | 0.9497 | 0.9474 | 0.9884 |
|
| 108 |
+
| 0.0011 | 44.0 | 4224 | 0.0826 | 0.8762 | 0.9787 | 0.9246 | 94 | 0.9568 | 0.9281 | 0.9422 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9451 | 0.9523 | 0.9487 | 0.9892 |
|
| 109 |
+
| 0.0007 | 45.0 | 4320 | 0.0795 | 0.9020 | 0.9787 | 0.9388 | 94 | 0.9554 | 0.8982 | 0.9259 | 167 | 0.9778 | 0.9635 | 0.9706 | 137 | 0.9492 | 0.9397 | 0.9444 | 0.9867 |
|
| 110 |
+
| 0.0025 | 46.0 | 4416 | 0.0816 | 0.9109 | 0.9787 | 0.9436 | 94 | 0.9012 | 0.9281 | 0.9145 | 167 | 0.9924 | 0.9562 | 0.9740 | 137 | 0.9333 | 0.9497 | 0.9415 | 0.9878 |
|
| 111 |
+
| 0.0012 | 47.0 | 4512 | 0.0946 | 0.8692 | 0.9894 | 0.9254 | 94 | 0.9620 | 0.9102 | 0.9354 | 167 | 0.9925 | 0.9635 | 0.9778 | 137 | 0.9472 | 0.9472 | 0.9472 | 0.9876 |
|
| 112 |
+
| 0.0016 | 48.0 | 4608 | 0.0961 | 0.8762 | 0.9787 | 0.9246 | 94 | 0.9277 | 0.9222 | 0.9249 | 167 | 0.9925 | 0.9635 | 0.9778 | 137 | 0.9356 | 0.9497 | 0.9426 | 0.9873 |
|
| 113 |
+
| 0.001 | 49.0 | 4704 | 0.0995 | 0.9010 | 0.9681 | 0.9333 | 94 | 0.9231 | 0.9341 | 0.9286 | 167 | 0.9925 | 0.9708 | 0.9815 | 137 | 0.9406 | 0.9548 | 0.9476 | 0.9865 |
|
| 114 |
+
| 0.001 | 50.0 | 4800 | 0.0989 | 0.8932 | 0.9787 | 0.9340 | 94 | 0.9554 | 0.8982 | 0.9259 | 167 | 0.9850 | 0.9562 | 0.9704 | 137 | 0.9491 | 0.9372 | 0.9431 | 0.9870 |
|
| 115 |
+
| 0.0004 | 51.0 | 4896 | 0.1130 | 0.9020 | 0.9787 | 0.9388 | 94 | 0.9264 | 0.9042 | 0.9152 | 167 | 0.9779 | 0.9708 | 0.9744 | 137 | 0.9377 | 0.9447 | 0.9412 | 0.9870 |
|
| 116 |
+
| 0.0007 | 52.0 | 4992 | 0.1079 | 0.91 | 0.9681 | 0.9381 | 94 | 0.9325 | 0.9102 | 0.9212 | 167 | 0.9779 | 0.9708 | 0.9744 | 137 | 0.9424 | 0.9447 | 0.9435 | 0.9878 |
|
| 117 |
+
| 0.0011 | 53.0 | 5088 | 0.1021 | 0.9286 | 0.9681 | 0.9479 | 94 | 0.9437 | 0.9042 | 0.9235 | 167 | 0.9778 | 0.9635 | 0.9706 | 137 | 0.9517 | 0.9397 | 0.9456 | 0.9878 |
|
| 118 |
+
| 0.0009 | 54.0 | 5184 | 0.1243 | 0.8776 | 0.9149 | 0.8958 | 94 | 0.875 | 0.9222 | 0.8980 | 167 | 0.9778 | 0.9635 | 0.9706 | 137 | 0.9095 | 0.9347 | 0.9219 | 0.9826 |
|
| 119 |
+
| 0.0011 | 55.0 | 5280 | 0.0882 | 0.91 | 0.9681 | 0.9381 | 94 | 0.9162 | 0.9162 | 0.9162 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9377 | 0.9447 | 0.9412 | 0.9884 |
|
| 120 |
+
| 0.0004 | 56.0 | 5376 | 0.0880 | 0.9286 | 0.9681 | 0.9479 | 94 | 0.9437 | 0.9042 | 0.9235 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9541 | 0.9397 | 0.9468 | 0.9901 |
|
| 121 |
+
| 0.0006 | 57.0 | 5472 | 0.1010 | 0.9010 | 0.9681 | 0.9333 | 94 | 0.9059 | 0.9222 | 0.9139 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9309 | 0.9472 | 0.9390 | 0.9873 |
|
| 122 |
+
| 0.0006 | 58.0 | 5568 | 0.0980 | 0.9010 | 0.9681 | 0.9333 | 94 | 0.9112 | 0.9222 | 0.9167 | 167 | 0.9852 | 0.9708 | 0.9779 | 137 | 0.9333 | 0.9497 | 0.9415 | 0.9876 |
|
| 123 |
+
| 0.0003 | 59.0 | 5664 | 0.0993 | 0.9192 | 0.9681 | 0.9430 | 94 | 0.9497 | 0.9042 | 0.9264 | 167 | 0.9778 | 0.9635 | 0.9706 | 137 | 0.9517 | 0.9397 | 0.9456 | 0.9884 |
|
| 124 |
+
| 0.0003 | 60.0 | 5760 | 0.0983 | 0.9 | 0.9574 | 0.9278 | 94 | 0.9273 | 0.9162 | 0.9217 | 167 | 0.9852 | 0.9708 | 0.9779 | 137 | 0.94 | 0.9447 | 0.9424 | 0.9884 |
|
| 125 |
+
| 0.0003 | 61.0 | 5856 | 0.0937 | 0.91 | 0.9681 | 0.9381 | 94 | 0.9096 | 0.9042 | 0.9069 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.935 | 0.9397 | 0.9373 | 0.9887 |
|
| 126 |
+
| 0.0011 | 62.0 | 5952 | 0.1109 | 0.8835 | 0.9681 | 0.9239 | 94 | 0.9497 | 0.9042 | 0.9264 | 167 | 0.9925 | 0.9708 | 0.9815 | 137 | 0.9470 | 0.9422 | 0.9446 | 0.9867 |
|
| 127 |
+
| 0.0009 | 63.0 | 6048 | 0.0866 | 0.9286 | 0.9681 | 0.9479 | 94 | 0.9162 | 0.9162 | 0.9162 | 167 | 0.9925 | 0.9635 | 0.9778 | 137 | 0.9447 | 0.9447 | 0.9447 | 0.9898 |
|
| 128 |
+
| 0.0004 | 64.0 | 6144 | 0.1202 | 0.88 | 0.9362 | 0.9072 | 94 | 0.9222 | 0.9222 | 0.9222 | 167 | 0.9925 | 0.9635 | 0.9778 | 137 | 0.935 | 0.9397 | 0.9373 | 0.9848 |
|
| 129 |
+
| 0.0023 | 65.0 | 6240 | 0.0968 | 0.9293 | 0.9787 | 0.9534 | 94 | 0.9217 | 0.9162 | 0.9189 | 167 | 0.9926 | 0.9781 | 0.9853 | 137 | 0.9475 | 0.9523 | 0.9499 | 0.9884 |
|
| 130 |
+
| 0.0017 | 66.0 | 6336 | 0.1031 | 0.9192 | 0.9681 | 0.9430 | 94 | 0.9444 | 0.9162 | 0.9301 | 167 | 0.9925 | 0.9708 | 0.9815 | 137 | 0.9544 | 0.9472 | 0.9508 | 0.9876 |
|
| 131 |
+
| 0.0014 | 67.0 | 6432 | 0.1050 | 0.9091 | 0.9574 | 0.9326 | 94 | 0.9497 | 0.9042 | 0.9264 | 167 | 0.9925 | 0.9708 | 0.9815 | 137 | 0.9541 | 0.9397 | 0.9468 | 0.9881 |
|
| 132 |
+
| 0.0007 | 68.0 | 6528 | 0.1049 | 0.9192 | 0.9681 | 0.9430 | 94 | 0.9554 | 0.8982 | 0.9259 | 167 | 1.0 | 0.9708 | 0.9852 | 137 | 0.9614 | 0.9397 | 0.9504 | 0.9892 |
|
| 133 |
+
| 0.0005 | 69.0 | 6624 | 0.0997 | 0.9184 | 0.9574 | 0.9375 | 94 | 0.9112 | 0.9222 | 0.9167 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9377 | 0.9447 | 0.9412 | 0.9859 |
|
| 134 |
+
| 0.001 | 70.0 | 6720 | 0.1054 | 0.9184 | 0.9574 | 0.9375 | 94 | 0.9118 | 0.9281 | 0.9199 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9378 | 0.9472 | 0.9425 | 0.9876 |
|
| 135 |
+
| 0.0005 | 71.0 | 6816 | 0.0978 | 0.9192 | 0.9681 | 0.9430 | 94 | 0.9563 | 0.9162 | 0.9358 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9567 | 0.9447 | 0.9507 | 0.9901 |
|
| 136 |
+
| 0.0008 | 72.0 | 6912 | 0.0955 | 0.9271 | 0.9468 | 0.9368 | 94 | 0.9387 | 0.9162 | 0.9273 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9517 | 0.9397 | 0.9456 | 0.9887 |
|
| 137 |
+
| 0.0005 | 73.0 | 7008 | 0.1008 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.9503 | 0.9162 | 0.9329 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9566 | 0.9422 | 0.9494 | 0.9892 |
|
| 138 |
+
| 0.0004 | 74.0 | 7104 | 0.1033 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.95 | 0.9102 | 0.9297 | 167 | 0.9776 | 0.9562 | 0.9668 | 137 | 0.9540 | 0.9372 | 0.9455 | 0.9884 |
|
| 139 |
+
| 0.0005 | 75.0 | 7200 | 0.1130 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.9618 | 0.9042 | 0.9321 | 167 | 0.9850 | 0.9562 | 0.9704 | 137 | 0.9612 | 0.9347 | 0.9478 | 0.9887 |
|
| 140 |
+
| 0.0007 | 76.0 | 7296 | 0.1115 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.9329 | 0.9162 | 0.9245 | 167 | 0.9776 | 0.9562 | 0.9668 | 137 | 0.9468 | 0.9397 | 0.9433 | 0.9884 |
|
| 141 |
+
| 0.0006 | 77.0 | 7392 | 0.1130 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.9554 | 0.8982 | 0.9259 | 167 | 0.9852 | 0.9708 | 0.9779 | 137 | 0.9589 | 0.9372 | 0.9479 | 0.9890 |
|
| 142 |
+
| 0.0005 | 78.0 | 7488 | 0.1151 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.9371 | 0.8922 | 0.9141 | 167 | 0.9704 | 0.9562 | 0.9632 | 137 | 0.9463 | 0.9296 | 0.9379 | 0.9876 |
|
| 143 |
+
| 0.0003 | 79.0 | 7584 | 0.1110 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.9441 | 0.9102 | 0.9268 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9541 | 0.9397 | 0.9468 | 0.9887 |
|
| 144 |
+
| 0.0002 | 80.0 | 7680 | 0.1127 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.9441 | 0.9102 | 0.9268 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9541 | 0.9397 | 0.9468 | 0.9887 |
|
| 145 |
+
| 0.0003 | 81.0 | 7776 | 0.1135 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.9441 | 0.9102 | 0.9268 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9541 | 0.9397 | 0.9468 | 0.9887 |
|
| 146 |
+
| 0.0003 | 82.0 | 7872 | 0.1082 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.9441 | 0.9102 | 0.9268 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9541 | 0.9397 | 0.9468 | 0.9887 |
|
| 147 |
+
| 0.0006 | 83.0 | 7968 | 0.1155 | 0.9192 | 0.9681 | 0.9430 | 94 | 0.9742 | 0.9042 | 0.9379 | 167 | 0.9852 | 0.9708 | 0.9779 | 137 | 0.9640 | 0.9422 | 0.9530 | 0.9895 |
|
| 148 |
+
| 0.0003 | 84.0 | 8064 | 0.1072 | 0.9286 | 0.9681 | 0.9479 | 94 | 0.9623 | 0.9162 | 0.9387 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9616 | 0.9447 | 0.9531 | 0.9898 |
|
| 149 |
+
| 0.0007 | 85.0 | 8160 | 0.1013 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.9387 | 0.9162 | 0.9273 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9518 | 0.9422 | 0.9470 | 0.9895 |
|
| 150 |
+
| 0.0003 | 86.0 | 8256 | 0.1022 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.9444 | 0.9162 | 0.9301 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9542 | 0.9422 | 0.9482 | 0.9898 |
|
| 151 |
+
| 0.0002 | 87.0 | 8352 | 0.1026 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.9444 | 0.9162 | 0.9301 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9542 | 0.9422 | 0.9482 | 0.9898 |
|
| 152 |
+
| 0.0002 | 88.0 | 8448 | 0.1029 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.9444 | 0.9162 | 0.9301 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9542 | 0.9422 | 0.9482 | 0.9898 |
|
| 153 |
+
| 0.0003 | 89.0 | 8544 | 0.1034 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.9444 | 0.9162 | 0.9301 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9542 | 0.9422 | 0.9482 | 0.9898 |
|
| 154 |
+
| 0.0003 | 90.0 | 8640 | 0.1043 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.9563 | 0.9162 | 0.9358 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9591 | 0.9422 | 0.9506 | 0.9898 |
|
| 155 |
+
| 0.0002 | 91.0 | 8736 | 0.1045 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.95 | 0.9102 | 0.9297 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9565 | 0.9397 | 0.9480 | 0.9892 |
|
| 156 |
+
| 0.0002 | 92.0 | 8832 | 0.1047 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.9503 | 0.9162 | 0.9329 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9566 | 0.9422 | 0.9494 | 0.9895 |
|
| 157 |
+
| 0.0003 | 93.0 | 8928 | 0.1054 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.95 | 0.9102 | 0.9297 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9565 | 0.9397 | 0.9480 | 0.9898 |
|
| 158 |
+
| 0.0009 | 94.0 | 9024 | 0.1089 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.9560 | 0.9102 | 0.9325 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9590 | 0.9397 | 0.9492 | 0.9895 |
|
| 159 |
+
| 0.0004 | 95.0 | 9120 | 0.1033 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.9441 | 0.9102 | 0.9268 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9541 | 0.9397 | 0.9468 | 0.9895 |
|
| 160 |
+
| 0.0002 | 96.0 | 9216 | 0.1028 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.9441 | 0.9102 | 0.9268 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9541 | 0.9397 | 0.9468 | 0.9895 |
|
| 161 |
+
| 0.0002 | 97.0 | 9312 | 0.1030 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.9441 | 0.9102 | 0.9268 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9541 | 0.9397 | 0.9468 | 0.9895 |
|
| 162 |
+
| 0.0003 | 98.0 | 9408 | 0.1035 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.95 | 0.9102 | 0.9297 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9565 | 0.9397 | 0.9480 | 0.9892 |
|
| 163 |
+
| 0.0002 | 99.0 | 9504 | 0.1036 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.95 | 0.9102 | 0.9297 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9565 | 0.9397 | 0.9480 | 0.9892 |
|
| 164 |
+
| 0.0002 | 100.0 | 9600 | 0.1036 | 0.9278 | 0.9574 | 0.9424 | 94 | 0.95 | 0.9102 | 0.9297 | 167 | 0.9851 | 0.9635 | 0.9742 | 137 | 0.9565 | 0.9397 | 0.9480 | 0.9892 |
|
| 165 |
+
|
| 166 |
+
|
| 167 |
+
### Framework versions
|
| 168 |
+
|
| 169 |
+
- Transformers 4.39.3
|
| 170 |
+
- Pytorch 2.3.0+cu121
|
| 171 |
+
- Datasets 2.19.1
|
| 172 |
+
- Tokenizers 0.15.2
|