metadata
license: mit
tags:
- generated_from_trainer
datasets:
- tiagoblima/punctuation-tedtalk2012-full-text-bert
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: punctuation-tedtalk2012-bert-base-full-text-bert
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: tiagoblima/punctuation-tedtalk2012-full-text-bert
type: tiagoblima/punctuation-tedtalk2012-full-text-bert
metrics:
- name: Precision
type: precision
value: 0.7178729689807977
- name: Recall
type: recall
value: 0.7416073245167853
- name: F1
type: f1
value: 0.7295471603702777
- name: Accuracy
type: accuracy
value: 0.9416717510677243
punctuation-tedtalk2012-bert-base-full-text-bert
This model is a fine-tuned version of neuralmind/bert-base-portuguese-cased on the tiagoblima/punctuation-tedtalk2012-full-text-bert dataset. It achieves the following results on the evaluation set:
- Loss: 0.1495
- Precision: 0.7179
- Recall: 0.7416
- F1: 0.7295
- Accuracy: 0.9417
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: 5e-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: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 197 | 0.1495 | 0.7179 | 0.7416 | 0.7295 | 0.9417 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2