metadata
license: apache-2.0
base_model: huggingface-course/bert-finetuned-ner
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner
results: []
bert-finetuned-ner
This model is a fine-tuned version of huggingface-course/bert-finetuned-ner on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0731
- Precision: 0.9344
- Recall: 0.9524
- F1: 0.9433
- Accuracy: 0.9867
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 |
|---|---|---|---|---|---|---|---|
| 0.0273 | 1.0 | 1756 | 0.0761 | 0.9250 | 0.9424 | 0.9336 | 0.9849 |
| 0.0183 | 2.0 | 3512 | 0.0671 | 0.9363 | 0.9505 | 0.9434 | 0.9865 |
| 0.0077 | 3.0 | 5268 | 0.0731 | 0.9344 | 0.9524 | 0.9433 | 0.9867 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0