metadata
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
datasets:
- lener_br
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-base-cased_LeNER-Br
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: lener_br
type: lener_br
config: lener_br
split: validation
args: lener_br
metrics:
- name: Precision
type: precision
value: 0.6604303086997194
- name: Recall
type: recall
value: 0.7771051183269125
- name: F1
type: f1
value: 0.7140328697850823
- name: Accuracy
type: accuracy
value: 0.964795971887129
bert-base-cased_LeNER-Br
This model is a fine-tuned version of bert-base-cased on the lener_br dataset. It achieves the following results on the evaluation set:
- Loss: nan
- Precision: 0.6604
- Recall: 0.7771
- F1: 0.7140
- Accuracy: 0.9648
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.2605 | 1.0 | 979 | nan | 0.5248 | 0.6918 | 0.5969 | 0.9538 |
0.0541 | 2.0 | 1958 | nan | 0.5968 | 0.7193 | 0.6524 | 0.9574 |
0.0327 | 3.0 | 2937 | nan | 0.5566 | 0.7413 | 0.6358 | 0.9584 |
0.0216 | 4.0 | 3916 | nan | 0.6642 | 0.7534 | 0.7060 | 0.9624 |
0.0175 | 5.0 | 4895 | nan | 0.6391 | 0.7711 | 0.6989 | 0.9659 |
0.0095 | 6.0 | 5874 | nan | 0.6099 | 0.7744 | 0.6823 | 0.9585 |
0.0099 | 7.0 | 6853 | nan | 0.6474 | 0.7942 | 0.7133 | 0.9642 |
0.0056 | 8.0 | 7832 | nan | 0.6606 | 0.7925 | 0.7205 | 0.9655 |
0.0038 | 9.0 | 8811 | nan | 0.6547 | 0.7859 | 0.7144 | 0.9660 |
0.0035 | 10.0 | 9790 | nan | 0.6604 | 0.7771 | 0.7140 | 0.9648 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
Testing results
metrics={'test_loss': 0.11072904616594315, 'test_precision': 0.7897691827822833, 'test_recall': 0.8423153692614771, 'test_f1': 0.8151963940759821, 'test_accuracy': 0.9825182903350019, 'test_runtime': 18.686, 'test_samples_per_second': 74.387, 'test_steps_per_second': 9.312})