metadata
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: finetuned-ner-conll
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: validation
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.9285243741765481
- name: Recall
type: recall
value: 0.9488387748232918
- name: F1
type: f1
value: 0.9385716663892125
- name: Accuracy
type: accuracy
value: 0.9862247601106728
pipeline_tag: token-classification
widget:
- text: Saketh Lives in India
example_title: Classification
- text: Apollo hospitals is in India
example_title: Classification
- text: Saketh works for Apollo
example_title: Classification
finetuned-ner-conll
This model is a fine-tuned version of bert-base-cased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: nan
- Precision: 0.9285
- Recall: 0.9488
- F1: 0.9386
- 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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|---|---|---|
| 0.218 | 1.0 | 878 | nan | 0.9080 | 0.9367 | 0.9221 | 0.9827 |
| 0.0449 | 2.0 | 1756 | nan | 0.9277 | 0.9485 | 0.9380 | 0.9857 |
| 0.0232 | 3.0 | 2634 | nan | 0.9285 | 0.9488 | 0.9386 | 0.9862 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.1