metadata
license: apache-2.0
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
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.9214944042132982
- name: Recall
type: recall
value: 0.9422753281723325
- name: F1
type: f1
value: 0.9317690131469462
- name: Accuracy
type: accuracy
value: 0.9849738034967916
bert-finetuned-ner
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: 0.0569
- Precision: 0.9215
- Recall: 0.9423
- F1: 0.9318
- Accuracy: 0.9850
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 439 | 0.0702 | 0.8847 | 0.9170 | 0.9006 | 0.9795 |
| 0.183 | 2.0 | 878 | 0.0599 | 0.9161 | 0.9391 | 0.9274 | 0.9842 |
| 0.0484 | 3.0 | 1317 | 0.0569 | 0.9215 | 0.9423 | 0.9318 | 0.9850 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.1
- Datasets 1.17.0
- Tokenizers 0.10.3