metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: distilbert-base-uncased-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: 0.9253070709306186
- name: Recall
type: recall
value: 0.9354513927732409
- name: F1
type: f1
value: 0.9303515798842902
- name: Accuracy
type: accuracy
value: 0.9834305050280394
distilbert-base-uncased-finetuned-ner
This model is a fine-tuned version of distilbert-base-uncased on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0619
- Precision: 0.9253
- Recall: 0.9355
- F1: 0.9304
- Accuracy: 0.9834
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 439 | 0.0877 | 0.8779 | 0.8955 | 0.8866 | 0.9754 |
| 0.2182 | 2.0 | 878 | 0.0626 | 0.9193 | 0.9299 | 0.9245 | 0.9820 |
| 0.0557 | 3.0 | 1317 | 0.0612 | 0.9252 | 0.9323 | 0.9287 | 0.9829 |
| 0.0346 | 4.0 | 1756 | 0.0619 | 0.9253 | 0.9355 | 0.9304 | 0.9834 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2