camembert-keyword-extractor
This model is a fine-tuned version of camembert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2199
- Precision: 0.6743
- Recall: 0.6979
- Accuracy: 0.9346
- F1: 0.6859
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: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Accuracy | F1 |
|---|---|---|---|---|---|---|---|
| 0.1747 | 1.0 | 1875 | 0.1780 | 0.5935 | 0.7116 | 0.9258 | 0.6472 |
| 0.1375 | 2.0 | 3750 | 0.1588 | 0.6505 | 0.7032 | 0.9334 | 0.6759 |
| 0.1147 | 3.0 | 5625 | 0.1727 | 0.6825 | 0.6689 | 0.9355 | 0.6756 |
| 0.0969 | 4.0 | 7500 | 0.1759 | 0.6886 | 0.6621 | 0.9350 | 0.6751 |
| 0.0837 | 5.0 | 9375 | 0.1967 | 0.6688 | 0.7112 | 0.9348 | 0.6893 |
| 0.0746 | 6.0 | 11250 | 0.2088 | 0.6646 | 0.7114 | 0.9334 | 0.6872 |
| 0.0666 | 7.0 | 13125 | 0.2169 | 0.6713 | 0.7054 | 0.9347 | 0.6879 |
| 0.0634 | 8.0 | 15000 | 0.2199 | 0.6743 | 0.6979 | 0.9346 | 0.6859 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1