| --- |
| library_name: transformers |
| license: mit |
| base_model: camembert-base |
| tags: |
| - generated_from_trainer |
| metrics: |
| - precision |
| - recall |
| - f1 |
| - accuracy |
| model-index: |
| - name: ner-model-camembert |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # ner-model-camembert |
|
|
| This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.1642 |
| - Precision: 0.8721 |
| - Recall: 0.7732 |
| - F1: 0.8197 |
| - Accuracy: 0.9571 |
|
|
| ## 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: 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: 25 |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
| |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
| | No log | 1.0 | 24 | 0.3640 | 0.0 | 0.0 | 0.0 | 0.8739 | |
| | No log | 2.0 | 48 | 0.2640 | 0.6884 | 0.4312 | 0.5303 | 0.9037 | |
| | No log | 3.0 | 72 | 0.2248 | 0.6976 | 0.6431 | 0.6692 | 0.9198 | |
| | No log | 4.0 | 96 | 0.2163 | 0.8182 | 0.6022 | 0.6938 | 0.9330 | |
| | No log | 5.0 | 120 | 0.1690 | 0.7336 | 0.8086 | 0.7692 | 0.9388 | |
| | No log | 6.0 | 144 | 0.1768 | 0.8558 | 0.6840 | 0.7603 | 0.9456 | |
| | No log | 7.0 | 168 | 0.1838 | 0.8578 | 0.6952 | 0.7680 | 0.9470 | |
| | No log | 8.0 | 192 | 0.1591 | 0.8158 | 0.8067 | 0.8112 | 0.9526 | |
| | No log | 9.0 | 216 | 0.1688 | 0.8571 | 0.7584 | 0.8047 | 0.9536 | |
| | No log | 10.0 | 240 | 0.1596 | 0.8431 | 0.7993 | 0.8206 | 0.9559 | |
| | No log | 11.0 | 264 | 0.1599 | 0.8563 | 0.7751 | 0.8137 | 0.9552 | |
| | No log | 12.0 | 288 | 0.1713 | 0.8515 | 0.7565 | 0.8012 | 0.9526 | |
| | No log | 13.0 | 312 | 0.1646 | 0.8394 | 0.7770 | 0.8069 | 0.9531 | |
| | No log | 14.0 | 336 | 0.1705 | 0.8367 | 0.7807 | 0.8077 | 0.9531 | |
| | No log | 15.0 | 360 | 0.1717 | 0.8236 | 0.7900 | 0.8065 | 0.9522 | |
| | No log | 16.0 | 384 | 0.1689 | 0.8631 | 0.7732 | 0.8157 | 0.9559 | |
| | No log | 17.0 | 408 | 0.1608 | 0.8835 | 0.7751 | 0.8257 | 0.9587 | |
| | No log | 18.0 | 432 | 0.1499 | 0.8849 | 0.7862 | 0.8327 | 0.9602 | |
| | No log | 19.0 | 456 | 0.1614 | 0.8846 | 0.7695 | 0.8231 | 0.9583 | |
| | No log | 20.0 | 480 | 0.1688 | 0.8448 | 0.7788 | 0.8104 | 0.9541 | |
| | 0.0983 | 21.0 | 504 | 0.1672 | 0.8482 | 0.7788 | 0.8120 | 0.9545 | |
| | 0.0983 | 22.0 | 528 | 0.1668 | 0.8563 | 0.7751 | 0.8137 | 0.9552 | |
| | 0.0983 | 23.0 | 552 | 0.1678 | 0.8545 | 0.7751 | 0.8129 | 0.9550 | |
| | 0.0983 | 24.0 | 576 | 0.1645 | 0.8703 | 0.7732 | 0.8189 | 0.9569 | |
| | 0.0983 | 25.0 | 600 | 0.1642 | 0.8721 | 0.7732 | 0.8197 | 0.9571 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 4.47.1 |
| - Pytorch 2.5.1+cu121 |
| - Datasets 3.2.0 |
| - Tokenizers 0.21.0 |
|
|
