NER / README.md
shed-e's picture
update model card README.md
1d0276c
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: train
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.9335207540929387
- name: Recall
type: recall
value: 0.9500168293503871
- name: F1
type: f1
value: 0.9416965551755777
- name: Accuracy
type: accuracy
value: 0.986210042974039
---
<!-- 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-finetuned-ner
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0637
- Precision: 0.9335
- Recall: 0.9500
- F1: 0.9417
- Accuracy: 0.9862
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.0888 | 1.0 | 1756 | 0.0636 | 0.9195 | 0.9366 | 0.9280 | 0.9830 |
| 0.0331 | 2.0 | 3512 | 0.0667 | 0.9272 | 0.9490 | 0.9380 | 0.9855 |
| 0.0167 | 3.0 | 5268 | 0.0637 | 0.9335 | 0.9500 | 0.9417 | 0.9862 |
### Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1