metadata
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner_NLP-course-chapter7-section1
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: 0.9348437241607409
- name: Recall
type: recall
value: 0.9513631773813531
- name: F1
type: f1
value: 0.9430311118525316
- name: Accuracy
type: accuracy
value: 0.9864749514334491
bert-finetuned-ner_NLP-course-chapter7-section1
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: 0.0603
- Precision: 0.9348
- Recall: 0.9514
- F1: 0.9430
- Accuracy: 0.9865
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 |
|---|---|---|---|---|---|---|---|
| 0.078 | 1.0 | 1756 | 0.0766 | 0.9111 | 0.9313 | 0.9211 | 0.9804 |
| 0.0408 | 2.0 | 3512 | 0.0621 | 0.9234 | 0.9436 | 0.9334 | 0.9846 |
| 0.0252 | 3.0 | 5268 | 0.0603 | 0.9348 | 0.9514 | 0.9430 | 0.9865 |
Framework versions
- Transformers 4.35.2
- Pytorch 1.11.0+cu102
- Datasets 2.15.0
- Tokenizers 0.15.0