NER NER-finetuning-BERT
Este es el modelo de BERt-cased para NER google-bert/bert-base-cased con el dataset conll2002 los resultados fueron los siguientes:
- Loss: 0.072613
- Precision: 0.7831
- Recall: 0.8317
- F1: 0.8066
- Accuracy: 0.9783
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:
- evaluation_strategy="epoch",
- save_strategy="epoch",
- learning_rate=2e-5,
- num_train_epochs=4,
- per_device_train_batch_size=8,
- weight_decay=0.01,
Training results
Epoch | Training Loss | Validation Loss |
---|---|---|
1 | 0.103300 | 0.158746 |
2 | 0.068200 | 0.138820 |
3 | 0.041300 | 0.136353 |
4 | 0.027400 | 0.153431 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 4