metadata
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: []
bert-base-case-ner
This model is a fine-tuned version of 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