|
--- |
|
language: |
|
- id |
|
license: mit |
|
base_model: indolem/indobert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: nerui-unipelt-4 |
|
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-unipelt-4 |
|
|
|
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: 0.0644 |
|
- Location Precision: 0.9091 |
|
- Location Recall: 0.9709 |
|
- Location F1: 0.9390 |
|
- Location Number: 103 |
|
- Organization Precision: 0.9281 |
|
- Organization Recall: 0.9064 |
|
- Organization F1: 0.9172 |
|
- Organization Number: 171 |
|
- Person Precision: 0.9771 |
|
- Person Recall: 0.9771 |
|
- Person F1: 0.9771 |
|
- Person Number: 131 |
|
- Overall Precision: 0.9387 |
|
- Overall Recall: 0.9457 |
|
- Overall F1: 0.9422 |
|
- Overall Accuracy: 0.9878 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------------------:|:---------------:|:-----------:|:---------------:|:----------------------:|:-------------------:|:---------------:|:-------------------:|:----------------:|:-------------:|:---------:|:-------------:|:-----------------:|:--------------:|:----------:|:----------------:| |
|
| 0.8815 | 1.0 | 96 | 0.5185 | 0.0 | 0.0 | 0.0 | 103 | 0.0 | 0.0 | 0.0 | 171 | 0.0 | 0.0 | 0.0 | 131 | 0.0 | 0.0 | 0.0 | 0.8379 | |
|
| 0.3991 | 2.0 | 192 | 0.2479 | 0.3233 | 0.4175 | 0.3644 | 103 | 0.4848 | 0.5614 | 0.5203 | 171 | 0.5056 | 0.6947 | 0.5852 | 131 | 0.4501 | 0.5679 | 0.5022 | 0.9238 | |
|
| 0.2071 | 3.0 | 288 | 0.1065 | 0.7447 | 0.6796 | 0.7107 | 103 | 0.7606 | 0.8363 | 0.7967 | 171 | 0.9481 | 0.9771 | 0.9624 | 131 | 0.8177 | 0.8420 | 0.8297 | 0.9685 | |
|
| 0.1278 | 4.0 | 384 | 0.0769 | 0.8529 | 0.8447 | 0.8488 | 103 | 0.8 | 0.8889 | 0.8421 | 171 | 0.9624 | 0.9771 | 0.9697 | 131 | 0.8635 | 0.9062 | 0.8843 | 0.9762 | |
|
| 0.1026 | 5.0 | 480 | 0.0683 | 0.8812 | 0.8641 | 0.8725 | 103 | 0.8580 | 0.8480 | 0.8529 | 171 | 0.9407 | 0.9695 | 0.9549 | 131 | 0.8914 | 0.8914 | 0.8914 | 0.9785 | |
|
| 0.087 | 6.0 | 576 | 0.0551 | 0.7881 | 0.9029 | 0.8416 | 103 | 0.9145 | 0.8129 | 0.8607 | 171 | 0.9697 | 0.9771 | 0.9734 | 131 | 0.8955 | 0.8889 | 0.8922 | 0.9815 | |
|
| 0.0744 | 7.0 | 672 | 0.0487 | 0.9082 | 0.8641 | 0.8856 | 103 | 0.9070 | 0.9123 | 0.9096 | 171 | 0.9697 | 0.9771 | 0.9734 | 131 | 0.9279 | 0.9210 | 0.9244 | 0.9854 | |
|
| 0.0709 | 8.0 | 768 | 0.0468 | 0.8205 | 0.9320 | 0.8727 | 103 | 0.9177 | 0.8480 | 0.8815 | 171 | 0.9621 | 0.9695 | 0.9658 | 131 | 0.9042 | 0.9086 | 0.9064 | 0.9845 | |
|
| 0.0659 | 9.0 | 864 | 0.0453 | 0.8376 | 0.9515 | 0.8909 | 103 | 0.9057 | 0.8421 | 0.8727 | 171 | 0.9552 | 0.9771 | 0.9660 | 131 | 0.9024 | 0.9136 | 0.9080 | 0.9845 | |
|
| 0.0584 | 10.0 | 960 | 0.0402 | 0.8879 | 0.9223 | 0.9048 | 103 | 0.9128 | 0.9181 | 0.9155 | 171 | 0.9624 | 0.9771 | 0.9697 | 131 | 0.9223 | 0.9383 | 0.9302 | 0.9887 | |
|
| 0.0525 | 11.0 | 1056 | 0.0395 | 0.9417 | 0.9417 | 0.9417 | 103 | 0.9176 | 0.9123 | 0.9150 | 171 | 0.9697 | 0.9771 | 0.9734 | 131 | 0.9407 | 0.9407 | 0.9407 | 0.9884 | |
|
| 0.0482 | 12.0 | 1152 | 0.0438 | 0.8909 | 0.9515 | 0.9202 | 103 | 0.9146 | 0.8772 | 0.8955 | 171 | 0.9549 | 0.9695 | 0.9621 | 131 | 0.9214 | 0.9259 | 0.9236 | 0.9862 | |
|
| 0.0441 | 13.0 | 1248 | 0.0445 | 0.9065 | 0.9417 | 0.9238 | 103 | 0.9048 | 0.8889 | 0.8968 | 171 | 0.9624 | 0.9771 | 0.9697 | 131 | 0.9240 | 0.9309 | 0.9274 | 0.9862 | |
|
| 0.0401 | 14.0 | 1344 | 0.0480 | 0.8889 | 0.9320 | 0.9100 | 103 | 0.9182 | 0.8538 | 0.8848 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9296 | 0.9136 | 0.9215 | 0.9845 | |
|
| 0.0382 | 15.0 | 1440 | 0.0410 | 0.9159 | 0.9515 | 0.9333 | 103 | 0.9118 | 0.9064 | 0.9091 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9338 | 0.9407 | 0.9373 | 0.9884 | |
|
| 0.0371 | 16.0 | 1536 | 0.0426 | 0.8991 | 0.9515 | 0.9245 | 103 | 0.9048 | 0.8889 | 0.8968 | 171 | 0.9621 | 0.9695 | 0.9658 | 131 | 0.9218 | 0.9309 | 0.9263 | 0.9870 | |
|
| 0.0323 | 17.0 | 1632 | 0.0440 | 0.9065 | 0.9417 | 0.9238 | 103 | 0.9123 | 0.9123 | 0.9123 | 171 | 0.9549 | 0.9695 | 0.9621 | 131 | 0.9246 | 0.9383 | 0.9314 | 0.9865 | |
|
| 0.0304 | 18.0 | 1728 | 0.0447 | 0.8839 | 0.9612 | 0.9209 | 103 | 0.9157 | 0.8889 | 0.9021 | 171 | 0.9697 | 0.9771 | 0.9734 | 131 | 0.9244 | 0.9358 | 0.9301 | 0.9865 | |
|
| 0.0277 | 19.0 | 1824 | 0.0439 | 0.8868 | 0.9126 | 0.8995 | 103 | 0.9030 | 0.8713 | 0.8869 | 171 | 0.9621 | 0.9695 | 0.9658 | 131 | 0.9181 | 0.9136 | 0.9158 | 0.9856 | |
|
| 0.0276 | 20.0 | 1920 | 0.0466 | 0.9065 | 0.9417 | 0.9238 | 103 | 0.9059 | 0.9006 | 0.9032 | 171 | 0.9697 | 0.9771 | 0.9734 | 131 | 0.9267 | 0.9358 | 0.9312 | 0.9865 | |
|
| 0.0264 | 21.0 | 2016 | 0.0508 | 0.8761 | 0.9612 | 0.9167 | 103 | 0.9430 | 0.8713 | 0.9058 | 171 | 0.9621 | 0.9695 | 0.9658 | 131 | 0.9305 | 0.9259 | 0.9282 | 0.9854 | |
|
| 0.0249 | 22.0 | 2112 | 0.0477 | 0.9009 | 0.9709 | 0.9346 | 103 | 0.9333 | 0.9006 | 0.9167 | 171 | 0.9697 | 0.9771 | 0.9734 | 131 | 0.9363 | 0.9432 | 0.9397 | 0.9865 | |
|
| 0.0233 | 23.0 | 2208 | 0.0485 | 0.8929 | 0.9709 | 0.9302 | 103 | 0.9157 | 0.8889 | 0.9021 | 171 | 0.9624 | 0.9771 | 0.9697 | 131 | 0.9246 | 0.9383 | 0.9314 | 0.9865 | |
|
| 0.0224 | 24.0 | 2304 | 0.0427 | 0.8919 | 0.9612 | 0.9252 | 103 | 0.9448 | 0.9006 | 0.9222 | 171 | 0.9624 | 0.9771 | 0.9697 | 131 | 0.9361 | 0.9407 | 0.9384 | 0.9873 | |
|
| 0.0205 | 25.0 | 2400 | 0.0468 | 0.8559 | 0.9806 | 0.9140 | 103 | 0.9367 | 0.8655 | 0.8997 | 171 | 0.9552 | 0.9771 | 0.9660 | 131 | 0.9195 | 0.9309 | 0.9252 | 0.9867 | |
|
| 0.0196 | 26.0 | 2496 | 0.0419 | 0.9167 | 0.9612 | 0.9384 | 103 | 0.9394 | 0.9064 | 0.9226 | 171 | 0.9697 | 0.9771 | 0.9734 | 131 | 0.9432 | 0.9432 | 0.9432 | 0.9876 | |
|
| 0.0185 | 27.0 | 2592 | 0.0421 | 0.8938 | 0.9806 | 0.9352 | 103 | 0.8941 | 0.8889 | 0.8915 | 171 | 0.9624 | 0.9771 | 0.9697 | 131 | 0.9159 | 0.9407 | 0.9281 | 0.9865 | |
|
| 0.0183 | 28.0 | 2688 | 0.0463 | 0.9429 | 0.9612 | 0.9519 | 103 | 0.9034 | 0.9298 | 0.9164 | 171 | 0.9697 | 0.9771 | 0.9734 | 131 | 0.9346 | 0.9531 | 0.9438 | 0.9878 | |
|
| 0.0168 | 29.0 | 2784 | 0.0491 | 0.8879 | 0.9223 | 0.9048 | 103 | 0.9268 | 0.8889 | 0.9075 | 171 | 0.9474 | 0.9618 | 0.9545 | 131 | 0.9233 | 0.9210 | 0.9221 | 0.9865 | |
|
| 0.0176 | 30.0 | 2880 | 0.0450 | 0.9143 | 0.9320 | 0.9231 | 103 | 0.8757 | 0.9064 | 0.8908 | 171 | 0.9697 | 0.9771 | 0.9734 | 131 | 0.9155 | 0.9358 | 0.9255 | 0.9856 | |
|
| 0.0149 | 31.0 | 2976 | 0.0507 | 0.8909 | 0.9515 | 0.9202 | 103 | 0.9187 | 0.8596 | 0.8882 | 171 | 0.9549 | 0.9695 | 0.9621 | 131 | 0.9231 | 0.9185 | 0.9208 | 0.9859 | |
|
| 0.017 | 32.0 | 3072 | 0.0449 | 0.9 | 0.9612 | 0.9296 | 103 | 0.9217 | 0.8947 | 0.9080 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9337 | 0.9383 | 0.9360 | 0.9878 | |
|
| 0.0142 | 33.0 | 3168 | 0.0454 | 0.8919 | 0.9612 | 0.9252 | 103 | 0.8976 | 0.8713 | 0.8843 | 171 | 0.9621 | 0.9695 | 0.9658 | 131 | 0.9169 | 0.9259 | 0.9214 | 0.9865 | |
|
| 0.0142 | 34.0 | 3264 | 0.0512 | 0.9074 | 0.9515 | 0.9289 | 103 | 0.9141 | 0.8713 | 0.8922 | 171 | 0.9621 | 0.9695 | 0.9658 | 131 | 0.9280 | 0.9235 | 0.9257 | 0.9865 | |
|
| 0.013 | 35.0 | 3360 | 0.0532 | 0.9099 | 0.9806 | 0.9439 | 103 | 0.9427 | 0.8655 | 0.9024 | 171 | 0.9621 | 0.9695 | 0.9658 | 131 | 0.94 | 0.9284 | 0.9342 | 0.9876 | |
|
| 0.0136 | 36.0 | 3456 | 0.0513 | 0.8919 | 0.9612 | 0.9252 | 103 | 0.925 | 0.8655 | 0.8943 | 171 | 0.9621 | 0.9695 | 0.9658 | 131 | 0.9280 | 0.9235 | 0.9257 | 0.9867 | |
|
| 0.012 | 37.0 | 3552 | 0.0502 | 0.96 | 0.9320 | 0.9458 | 103 | 0.9172 | 0.9064 | 0.9118 | 171 | 0.9621 | 0.9695 | 0.9658 | 131 | 0.9426 | 0.9333 | 0.9380 | 0.9881 | |
|
| 0.0116 | 38.0 | 3648 | 0.0532 | 0.9009 | 0.9709 | 0.9346 | 103 | 0.925 | 0.8655 | 0.8943 | 171 | 0.9621 | 0.9695 | 0.9658 | 131 | 0.9305 | 0.9259 | 0.9282 | 0.9856 | |
|
| 0.0113 | 39.0 | 3744 | 0.0485 | 0.9 | 0.9612 | 0.9296 | 103 | 0.9091 | 0.8772 | 0.8929 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9286 | 0.9309 | 0.9297 | 0.9873 | |
|
| 0.0111 | 40.0 | 3840 | 0.0514 | 0.9074 | 0.9515 | 0.9289 | 103 | 0.9162 | 0.8947 | 0.9053 | 171 | 0.9695 | 0.9695 | 0.9695 | 131 | 0.9310 | 0.9333 | 0.9322 | 0.9867 | |
|
| 0.0103 | 41.0 | 3936 | 0.0545 | 0.9083 | 0.9612 | 0.9340 | 103 | 0.9264 | 0.8830 | 0.9042 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9380 | 0.9333 | 0.9356 | 0.9873 | |
|
| 0.0098 | 42.0 | 4032 | 0.0525 | 0.9252 | 0.9612 | 0.9429 | 103 | 0.9059 | 0.9006 | 0.9032 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9338 | 0.9407 | 0.9373 | 0.9873 | |
|
| 0.0102 | 43.0 | 4128 | 0.0489 | 0.9151 | 0.9417 | 0.9282 | 103 | 0.9128 | 0.9181 | 0.9155 | 171 | 0.9621 | 0.9695 | 0.9658 | 131 | 0.9293 | 0.9407 | 0.9350 | 0.9876 | |
|
| 0.0086 | 44.0 | 4224 | 0.0611 | 0.875 | 0.9515 | 0.9116 | 103 | 0.9152 | 0.8830 | 0.8988 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9240 | 0.9309 | 0.9274 | 0.9862 | |
|
| 0.0099 | 45.0 | 4320 | 0.0527 | 0.8739 | 0.9417 | 0.9065 | 103 | 0.9217 | 0.8947 | 0.9080 | 171 | 0.9621 | 0.9695 | 0.9658 | 131 | 0.9218 | 0.9309 | 0.9263 | 0.9859 | |
|
| 0.0079 | 46.0 | 4416 | 0.0527 | 0.8761 | 0.9612 | 0.9167 | 103 | 0.9064 | 0.9064 | 0.9064 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9205 | 0.9432 | 0.9317 | 0.9867 | |
|
| 0.0094 | 47.0 | 4512 | 0.0539 | 0.9151 | 0.9417 | 0.9282 | 103 | 0.8814 | 0.9123 | 0.8966 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9203 | 0.9407 | 0.9304 | 0.9862 | |
|
| 0.0088 | 48.0 | 4608 | 0.0595 | 0.9091 | 0.9709 | 0.9390 | 103 | 0.9371 | 0.8713 | 0.9030 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9425 | 0.9309 | 0.9366 | 0.9873 | |
|
| 0.0071 | 49.0 | 4704 | 0.0539 | 0.8981 | 0.9417 | 0.9194 | 103 | 0.9059 | 0.9006 | 0.9032 | 171 | 0.9621 | 0.9695 | 0.9658 | 131 | 0.9220 | 0.9333 | 0.9276 | 0.9862 | |
|
| 0.0079 | 50.0 | 4800 | 0.0529 | 0.8991 | 0.9515 | 0.9245 | 103 | 0.9167 | 0.9006 | 0.9086 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9314 | 0.9383 | 0.9348 | 0.9867 | |
|
| 0.0075 | 51.0 | 4896 | 0.0543 | 0.8909 | 0.9515 | 0.9202 | 103 | 0.9226 | 0.9064 | 0.9145 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9315 | 0.9407 | 0.9361 | 0.9870 | |
|
| 0.0078 | 52.0 | 4992 | 0.0541 | 0.8909 | 0.9515 | 0.9202 | 103 | 0.8953 | 0.9006 | 0.8980 | 171 | 0.9695 | 0.9695 | 0.9695 | 131 | 0.9177 | 0.9358 | 0.9267 | 0.9870 | |
|
| 0.0075 | 53.0 | 5088 | 0.0543 | 0.9151 | 0.9417 | 0.9282 | 103 | 0.9172 | 0.9064 | 0.9118 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9360 | 0.9383 | 0.9371 | 0.9878 | |
|
| 0.0081 | 54.0 | 5184 | 0.0503 | 0.9 | 0.9612 | 0.9296 | 103 | 0.9176 | 0.9123 | 0.9150 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9319 | 0.9457 | 0.9387 | 0.9878 | |
|
| 0.006 | 55.0 | 5280 | 0.0562 | 0.9083 | 0.9612 | 0.9340 | 103 | 0.9398 | 0.9123 | 0.9258 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9433 | 0.9457 | 0.9445 | 0.9881 | |
|
| 0.0071 | 56.0 | 5376 | 0.0554 | 0.9083 | 0.9612 | 0.9340 | 103 | 0.9273 | 0.8947 | 0.9107 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9383 | 0.9383 | 0.9383 | 0.9873 | |
|
| 0.0073 | 57.0 | 5472 | 0.0639 | 0.9083 | 0.9612 | 0.9340 | 103 | 0.9367 | 0.8655 | 0.8997 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9422 | 0.9259 | 0.9340 | 0.9867 | |
|
| 0.0048 | 58.0 | 5568 | 0.0563 | 0.9083 | 0.9612 | 0.9340 | 103 | 0.9394 | 0.9064 | 0.9226 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9432 | 0.9432 | 0.9432 | 0.9887 | |
|
| 0.0067 | 59.0 | 5664 | 0.0551 | 0.9333 | 0.9515 | 0.9423 | 103 | 0.9240 | 0.9240 | 0.9240 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9435 | 0.9481 | 0.9458 | 0.9881 | |
|
| 0.0063 | 60.0 | 5760 | 0.0597 | 0.9167 | 0.9612 | 0.9384 | 103 | 0.9394 | 0.9064 | 0.9226 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9455 | 0.9432 | 0.9444 | 0.9887 | |
|
| 0.0061 | 61.0 | 5856 | 0.0535 | 0.9083 | 0.9612 | 0.9340 | 103 | 0.9070 | 0.9123 | 0.9096 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9296 | 0.9457 | 0.9376 | 0.9878 | |
|
| 0.0043 | 62.0 | 5952 | 0.0623 | 0.9 | 0.9612 | 0.9296 | 103 | 0.9212 | 0.8889 | 0.9048 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9335 | 0.9358 | 0.9346 | 0.9865 | |
|
| 0.0052 | 63.0 | 6048 | 0.0562 | 0.9245 | 0.9515 | 0.9378 | 103 | 0.9118 | 0.9064 | 0.9091 | 171 | 0.9695 | 0.9695 | 0.9695 | 131 | 0.9337 | 0.9383 | 0.9360 | 0.9881 | |
|
| 0.0054 | 64.0 | 6144 | 0.0590 | 0.9074 | 0.9515 | 0.9289 | 103 | 0.9167 | 0.9006 | 0.9086 | 171 | 0.9695 | 0.9695 | 0.9695 | 131 | 0.9312 | 0.9358 | 0.9335 | 0.9865 | |
|
| 0.0045 | 65.0 | 6240 | 0.0523 | 0.9065 | 0.9417 | 0.9238 | 103 | 0.9034 | 0.9298 | 0.9164 | 171 | 0.9773 | 0.9847 | 0.9810 | 131 | 0.9277 | 0.9506 | 0.9390 | 0.9878 | |
|
| 0.0044 | 66.0 | 6336 | 0.0595 | 0.9167 | 0.9612 | 0.9384 | 103 | 0.9029 | 0.9240 | 0.9133 | 171 | 0.9773 | 0.9847 | 0.9810 | 131 | 0.9301 | 0.9531 | 0.9415 | 0.9878 | |
|
| 0.0049 | 67.0 | 6432 | 0.0597 | 0.9091 | 0.9709 | 0.9390 | 103 | 0.9277 | 0.9006 | 0.9139 | 171 | 0.9773 | 0.9847 | 0.9810 | 131 | 0.9387 | 0.9457 | 0.9422 | 0.9876 | |
|
| 0.0043 | 68.0 | 6528 | 0.0664 | 0.9167 | 0.9612 | 0.9384 | 103 | 0.9152 | 0.8830 | 0.8988 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9356 | 0.9333 | 0.9345 | 0.9865 | |
|
| 0.0047 | 69.0 | 6624 | 0.0610 | 0.9159 | 0.9515 | 0.9333 | 103 | 0.9059 | 0.9006 | 0.9032 | 171 | 0.9695 | 0.9695 | 0.9695 | 131 | 0.9289 | 0.9358 | 0.9323 | 0.9859 | |
|
| 0.0048 | 70.0 | 6720 | 0.0642 | 0.9252 | 0.9612 | 0.9429 | 103 | 0.9176 | 0.9123 | 0.9150 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9387 | 0.9457 | 0.9422 | 0.9876 | |
|
| 0.0045 | 71.0 | 6816 | 0.0592 | 0.9245 | 0.9515 | 0.9378 | 103 | 0.8983 | 0.9298 | 0.9138 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9300 | 0.9506 | 0.9402 | 0.9881 | |
|
| 0.0037 | 72.0 | 6912 | 0.0623 | 0.9083 | 0.9612 | 0.9340 | 103 | 0.9281 | 0.9064 | 0.9172 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9386 | 0.9432 | 0.9409 | 0.9873 | |
|
| 0.0052 | 73.0 | 7008 | 0.0650 | 0.9083 | 0.9612 | 0.9340 | 103 | 0.9059 | 0.9006 | 0.9032 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9293 | 0.9407 | 0.9350 | 0.9867 | |
|
| 0.0037 | 74.0 | 7104 | 0.0595 | 0.9245 | 0.9515 | 0.9378 | 103 | 0.9070 | 0.9123 | 0.9096 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9340 | 0.9432 | 0.9386 | 0.9873 | |
|
| 0.0028 | 75.0 | 7200 | 0.0637 | 0.9091 | 0.9709 | 0.9390 | 103 | 0.9387 | 0.8947 | 0.9162 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9431 | 0.9407 | 0.9419 | 0.9881 | |
|
| 0.0035 | 76.0 | 7296 | 0.0613 | 0.9083 | 0.9612 | 0.9340 | 103 | 0.9017 | 0.9123 | 0.9070 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9274 | 0.9457 | 0.9364 | 0.9878 | |
|
| 0.0038 | 77.0 | 7392 | 0.0655 | 0.9 | 0.9612 | 0.9296 | 103 | 0.9217 | 0.8947 | 0.9080 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9337 | 0.9383 | 0.9360 | 0.9876 | |
|
| 0.0046 | 78.0 | 7488 | 0.0635 | 0.9 | 0.9612 | 0.9296 | 103 | 0.9167 | 0.9006 | 0.9086 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9315 | 0.9407 | 0.9361 | 0.9876 | |
|
| 0.0036 | 79.0 | 7584 | 0.0615 | 0.9083 | 0.9612 | 0.9340 | 103 | 0.9277 | 0.9006 | 0.9139 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9384 | 0.9407 | 0.9396 | 0.9881 | |
|
| 0.0042 | 80.0 | 7680 | 0.0579 | 0.8991 | 0.9515 | 0.9245 | 103 | 0.9070 | 0.9123 | 0.9096 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9272 | 0.9432 | 0.9351 | 0.9878 | |
|
| 0.0037 | 81.0 | 7776 | 0.0585 | 0.9074 | 0.9515 | 0.9289 | 103 | 0.9118 | 0.9064 | 0.9091 | 171 | 0.9769 | 0.9695 | 0.9732 | 131 | 0.9314 | 0.9383 | 0.9348 | 0.9876 | |
|
| 0.0035 | 82.0 | 7872 | 0.0573 | 0.9174 | 0.9709 | 0.9434 | 103 | 0.9290 | 0.9181 | 0.9235 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9413 | 0.9506 | 0.9459 | 0.9887 | |
|
| 0.0031 | 83.0 | 7968 | 0.0624 | 0.9174 | 0.9709 | 0.9434 | 103 | 0.9281 | 0.9064 | 0.9172 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9410 | 0.9457 | 0.9433 | 0.9881 | |
|
| 0.003 | 84.0 | 8064 | 0.0637 | 0.9091 | 0.9709 | 0.9390 | 103 | 0.9226 | 0.9064 | 0.9145 | 171 | 0.9697 | 0.9771 | 0.9734 | 131 | 0.9341 | 0.9457 | 0.9399 | 0.9878 | |
|
| 0.0036 | 85.0 | 8160 | 0.0644 | 0.9009 | 0.9709 | 0.9346 | 103 | 0.9290 | 0.9181 | 0.9235 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9367 | 0.9506 | 0.9436 | 0.9878 | |
|
| 0.0035 | 86.0 | 8256 | 0.0636 | 0.9009 | 0.9709 | 0.9346 | 103 | 0.9273 | 0.8947 | 0.9107 | 171 | 0.9697 | 0.9771 | 0.9734 | 131 | 0.9338 | 0.9407 | 0.9373 | 0.9876 | |
|
| 0.0032 | 87.0 | 8352 | 0.0619 | 0.9091 | 0.9709 | 0.9390 | 103 | 0.9281 | 0.9064 | 0.9172 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9387 | 0.9457 | 0.9422 | 0.9881 | |
|
| 0.0029 | 88.0 | 8448 | 0.0604 | 0.9091 | 0.9709 | 0.9390 | 103 | 0.9075 | 0.9181 | 0.9128 | 171 | 0.9769 | 0.9695 | 0.9732 | 131 | 0.9298 | 0.9481 | 0.9389 | 0.9878 | |
|
| 0.0031 | 89.0 | 8544 | 0.0640 | 0.9083 | 0.9612 | 0.9340 | 103 | 0.9023 | 0.9181 | 0.9101 | 171 | 0.9769 | 0.9695 | 0.9732 | 131 | 0.9274 | 0.9457 | 0.9364 | 0.9878 | |
|
| 0.0028 | 90.0 | 8640 | 0.0659 | 0.9009 | 0.9709 | 0.9346 | 103 | 0.9277 | 0.9006 | 0.9139 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9363 | 0.9432 | 0.9397 | 0.9881 | |
|
| 0.0028 | 91.0 | 8736 | 0.0627 | 0.9167 | 0.9612 | 0.9384 | 103 | 0.9235 | 0.9181 | 0.9208 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9389 | 0.9481 | 0.9435 | 0.9887 | |
|
| 0.0032 | 92.0 | 8832 | 0.0658 | 0.9091 | 0.9709 | 0.9390 | 103 | 0.9281 | 0.9064 | 0.9172 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9387 | 0.9457 | 0.9422 | 0.9878 | |
|
| 0.0023 | 93.0 | 8928 | 0.0636 | 0.9174 | 0.9709 | 0.9434 | 103 | 0.9231 | 0.9123 | 0.9176 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9389 | 0.9481 | 0.9435 | 0.9884 | |
|
| 0.0024 | 94.0 | 9024 | 0.0651 | 0.9174 | 0.9709 | 0.9434 | 103 | 0.9394 | 0.9064 | 0.9226 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9457 | 0.9457 | 0.9457 | 0.9878 | |
|
| 0.0029 | 95.0 | 9120 | 0.0632 | 0.9167 | 0.9612 | 0.9384 | 103 | 0.9118 | 0.9064 | 0.9091 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9340 | 0.9432 | 0.9386 | 0.9876 | |
|
| 0.0021 | 96.0 | 9216 | 0.0634 | 0.9091 | 0.9709 | 0.9390 | 103 | 0.9231 | 0.9123 | 0.9176 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9366 | 0.9481 | 0.9423 | 0.9884 | |
|
| 0.0027 | 97.0 | 9312 | 0.0650 | 0.9091 | 0.9709 | 0.9390 | 103 | 0.9394 | 0.9064 | 0.9226 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9433 | 0.9457 | 0.9445 | 0.9878 | |
|
| 0.0019 | 98.0 | 9408 | 0.0640 | 0.9091 | 0.9709 | 0.9390 | 103 | 0.9394 | 0.9064 | 0.9226 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9433 | 0.9457 | 0.9445 | 0.9878 | |
|
| 0.0026 | 99.0 | 9504 | 0.0646 | 0.9091 | 0.9709 | 0.9390 | 103 | 0.9394 | 0.9064 | 0.9226 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9433 | 0.9457 | 0.9445 | 0.9878 | |
|
| 0.0027 | 100.0 | 9600 | 0.0644 | 0.9091 | 0.9709 | 0.9390 | 103 | 0.9281 | 0.9064 | 0.9172 | 171 | 0.9771 | 0.9771 | 0.9771 | 131 | 0.9387 | 0.9457 | 0.9422 | 0.9878 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.15.2 |
|
|
