bloom-NER-fr
This model is a fine-tuned version of roberta-large-mnli on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2930
- Precision: 0.5423
- Recall: 0.6361
- F1: 0.5854
- Accuracy: 0.9004
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: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.7569 | 1.0 | 47 | 0.4836 | 0.3709 | 0.3924 | 0.3813 | 0.8604 |
0.4348 | 2.0 | 94 | 0.3771 | 0.4395 | 0.5443 | 0.4863 | 0.8687 |
0.3607 | 3.0 | 141 | 0.3232 | 0.5115 | 0.6086 | 0.5559 | 0.8953 |
0.2913 | 4.0 | 188 | 0.2918 | 0.5527 | 0.6255 | 0.5868 | 0.8974 |
0.2602 | 5.0 | 235 | 0.2835 | 0.5485 | 0.6445 | 0.5926 | 0.9028 |
0.2332 | 6.0 | 282 | 0.2930 | 0.5423 | 0.6361 | 0.5854 | 0.9004 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 8