metadata
license: apache-2.0
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
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.9299878143347735
- name: Recall
type: recall
value: 0.9391430808815304
- name: F1
type: f1
value: 0.93454302571524
- name: Accuracy
type: accuracy
value: 0.9841453921553053
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: 0.0635
- Precision: 0.9300
- Recall: 0.9391
- F1: 0.9345
- Accuracy: 0.9841
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 |
|---|---|---|---|---|---|---|---|
| 0.0886 | 1.0 | 1756 | 0.0676 | 0.9198 | 0.9233 | 0.9215 | 0.9809 |
| 0.0382 | 2.0 | 3512 | 0.0605 | 0.9271 | 0.9360 | 0.9315 | 0.9836 |
| 0.0247 | 3.0 | 5268 | 0.0635 | 0.9300 | 0.9391 | 0.9345 | 0.9841 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.9.0
- Datasets 2.0.0
- Tokenizers 0.11.6