|
--- |
|
license: apache-2.0 |
|
base_model: google/rembert |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: rembert-finetuned-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. --> |
|
|
|
# rembert-finetuned-ner |
|
|
|
This model is a fine-tuned version of [google/rembert](https://huggingface.co/google/rembert) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1419 |
|
- Precision: 0.9136 |
|
- Recall: 0.9285 |
|
- F1: 0.9210 |
|
- Accuracy: 0.9811 |
|
|
|
## 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: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.0644 | 1.0 | 1756 | 0.0819 | 0.9075 | 0.9154 | 0.9114 | 0.9837 | |
|
| 0.0261 | 2.0 | 3512 | 0.0440 | 0.9576 | 0.9605 | 0.9590 | 0.9906 | |
|
| 0.0121 | 3.0 | 5268 | 0.0415 | 0.9622 | 0.9682 | 0.9652 | 0.9917 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.15.0 |
|
|
