|
--- |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- wikiann |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model_index: |
|
- name: bert-srb-ner |
|
results: |
|
- task: |
|
name: Token Classification |
|
type: token-classification |
|
dataset: |
|
name: wikiann |
|
type: wikiann |
|
args: sr |
|
metric: |
|
name: Accuracy |
|
type: accuracy |
|
value: 0.9542715764169646 |
|
--- |
|
|
|
<!-- 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-srb-ner |
|
|
|
This model was trained from scratch on the wikiann dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3045 |
|
- Precision: 0.8922 |
|
- Recall: 0.9050 |
|
- F1: 0.8986 |
|
- Accuracy: 0.9543 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 0.276 | 1.0 | 1250 | 0.2359 | 0.8355 | 0.8334 | 0.8344 | 0.9276 | |
|
| 0.1722 | 2.0 | 2500 | 0.2016 | 0.8731 | 0.8685 | 0.8708 | 0.9426 | |
|
| 0.1155 | 3.0 | 3750 | 0.1897 | 0.8707 | 0.8860 | 0.8783 | 0.9463 | |
|
| 0.0849 | 4.0 | 5000 | 0.2151 | 0.8755 | 0.8980 | 0.8866 | 0.9494 | |
|
| 0.0554 | 5.0 | 6250 | 0.2373 | 0.8820 | 0.8923 | 0.8871 | 0.9495 | |
|
| 0.039 | 6.0 | 7500 | 0.2644 | 0.8808 | 0.8953 | 0.8880 | 0.9505 | |
|
| 0.0286 | 7.0 | 8750 | 0.2737 | 0.8915 | 0.8961 | 0.8938 | 0.9520 | |
|
| 0.018 | 8.0 | 10000 | 0.2879 | 0.8860 | 0.9039 | 0.8948 | 0.9526 | |
|
| 0.0116 | 9.0 | 11250 | 0.2973 | 0.8930 | 0.9032 | 0.8981 | 0.9542 | |
|
| 0.0079 | 10.0 | 12500 | 0.3045 | 0.8922 | 0.9050 | 0.8986 | 0.9543 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.9.2 |
|
- Pytorch 1.9.0 |
|
- Datasets 1.11.0 |
|
- Tokenizers 0.10.1 |
|
|
