metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-uncased-conll2003
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: test
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.8926710663424801
- name: Recall
type: recall
value: 0.910056657223796
- name: F1
type: f1
value: 0.9012800280554094
- name: Accuracy
type: accuracy
value: 0.9784860557768924
bert-base-uncased-conll2003
This model is a fine-tuned version of bert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1448
- Precision: 0.8927
- Recall: 0.9101
- F1: 0.9013
- Accuracy: 0.9785
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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.062 | 1.0 | 3922 | 0.1196 | 0.8913 | 0.9014 | 0.8963 | 0.9784 |
| 0.024 | 2.0 | 7844 | 0.1448 | 0.8927 | 0.9101 | 0.9013 | 0.9785 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.2.2
- Datasets 2.20.0
- Tokenizers 0.19.1