bert-finetuned-ner / README.md
ronenh24's picture
Training complete
ec9de91 verified
---
license: apache-2.0
base_model: bert-base-cased
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: validation
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.9337628014535844
- name: Recall
type: recall
value: 0.9513631773813531
- name: F1
type: f1
value: 0.9424808269423142
- name: Accuracy
type: accuracy
value: 0.9862689115205746
---
<!-- 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: 0.0629
- Precision: 0.9338
- Recall: 0.9514
- F1: 0.9425
- Accuracy: 0.9863
## 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 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.0738 | 1.0 | 1756 | 0.0695 | 0.8962 | 0.9286 | 0.9121 | 0.9807 |
| 0.0354 | 2.0 | 3512 | 0.0628 | 0.9358 | 0.9487 | 0.9422 | 0.9860 |
| 0.0224 | 3.0 | 5268 | 0.0629 | 0.9338 | 0.9514 | 0.9425 | 0.9863 |
### Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1