metadata
license: mit
base_model: camembert-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: RoBERTa-ner
results: []
RoBERTa-ner
This model is a fine-tuned version of camembert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1634
- Precision: 0.8634
- Recall: 0.8734
- F1: 0.8684
- Accuracy: 0.9791
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 294 | 0.2447 | 0.8248 | 0.8624 | 0.8432 | 0.9777 |
| 0.3867 | 2.0 | 588 | 0.1717 | 0.8558 | 0.8727 | 0.8642 | 0.9820 |
| 0.3867 | 3.0 | 882 | 0.1562 | 0.8605 | 0.8805 | 0.8704 | 0.9827 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.2
- Datasets 2.19.0
- Tokenizers 0.19.1