metadata
library_name: transformers
license: mit
base_model: camembert-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: results
results: []
results
This model is a fine-tuned version of camembert-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4448
- Accuracy: 0.9239
- F1: 0.9226
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: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.2178 | 1.0 | 992 | 0.2705 | 0.9143 | 0.9160 |
| 0.1932 | 2.0 | 1984 | 0.2340 | 0.9340 | 0.9323 |
| 0.157 | 3.0 | 2976 | 0.2491 | 0.9266 | 0.9262 |
| 0.1432 | 4.0 | 3968 | 0.2768 | 0.9261 | 0.9251 |
| 0.0788 | 5.0 | 4960 | 0.3313 | 0.9254 | 0.9246 |
| 0.0669 | 6.0 | 5952 | 0.3403 | 0.9271 | 0.9263 |
| 0.0934 | 7.0 | 6944 | 0.4120 | 0.9239 | 0.9224 |
| 0.0579 | 8.0 | 7936 | 0.4046 | 0.9231 | 0.9226 |
| 0.0364 | 9.0 | 8928 | 0.4379 | 0.9234 | 0.9221 |
| 0.0985 | 10.0 | 9920 | 0.4448 | 0.9239 | 0.9226 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1