metadata
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: camembert-ner-finetuned-ner
results: []
camembert-ner-finetuned-ner
This model is a fine-tuned version of Jean-Baptiste/camembert-ner on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0862
- Precision: 0.9925
- Recall: 0.9959
- F1: 0.9942
- Accuracy: 0.9896
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|---|---|---|
| 0.1364 | 1.0 | 769 | 0.0832 | 0.9828 | 0.9998 | 0.9912 | 0.9823 |
| 0.0533 | 2.0 | 1538 | 0.0631 | 0.9934 | 0.9923 | 0.9928 | 0.9871 |
| 0.0329 | 3.0 | 2307 | 0.0651 | 0.9912 | 0.9978 | 0.9945 | 0.9897 |
| 0.021 | 4.0 | 3076 | 0.0680 | 0.9937 | 0.9952 | 0.9945 | 0.9899 |
| 0.0171 | 5.0 | 3845 | 0.0628 | 0.9928 | 0.9969 | 0.9948 | 0.9906 |
| 0.0115 | 6.0 | 4614 | 0.0678 | 0.9930 | 0.9963 | 0.9947 | 0.9903 |
| 0.0075 | 7.0 | 5383 | 0.0854 | 0.9928 | 0.9956 | 0.9942 | 0.9896 |
| 0.0045 | 8.0 | 6152 | 0.0862 | 0.9919 | 0.9948 | 0.9934 | 0.9890 |
| 0.0031 | 9.0 | 6921 | 0.0839 | 0.9919 | 0.9958 | 0.9938 | 0.9896 |
| 0.0028 | 10.0 | 7690 | 0.0862 | 0.9925 | 0.9959 | 0.9942 | 0.9896 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.12.1+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1