| --- |
| license: apache-2.0 |
| base_model: google-bert/bert-base-cased |
| tags: |
| - generated_from_trainer |
| metrics: |
| - precision |
| - recall |
| - f1 |
| - accuracy |
| model-index: |
| - name: bert-base-case-ner |
| 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. --> |
|
|
| # bert-base-case-ner |
|
|
| This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.1741 |
| - Precision: 0.7713 |
| - Recall: 0.8081 |
| - F1: 0.7893 |
| - Accuracy: 0.9675 |
|
|
| ## 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: 8 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - num_epochs: 5 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
| |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
| | 0.1035 | 1.0 | 1041 | 0.1460 | 0.7285 | 0.7590 | 0.7434 | 0.9614 | |
| | 0.0684 | 2.0 | 2082 | 0.1438 | 0.7017 | 0.7767 | 0.7373 | 0.9631 | |
| | 0.0423 | 3.0 | 3123 | 0.1504 | 0.7591 | 0.7978 | 0.7780 | 0.9670 | |
| | 0.0278 | 4.0 | 4164 | 0.1606 | 0.7683 | 0.8008 | 0.7842 | 0.9670 | |
| | 0.0207 | 5.0 | 5205 | 0.1741 | 0.7713 | 0.8081 | 0.7893 | 0.9675 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.40.1 |
| - Pytorch 2.0.1+cu117 |
| - Datasets 2.18.0 |
| - Tokenizers 0.19.1 |
|
|
