camembert_ccnet_classification_tools_fr
This model is a fine-tuned version of camembert/camembert-base-ccnet on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5125
- Accuracy: 0.9
- Learning Rate: 0.0001
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: 0.0001
- train_batch_size: 24
- eval_batch_size: 192
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 60
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Rate |
---|---|---|---|---|---|
No log | 1.0 | 7 | 1.8894 | 0.525 | 0.0001 |
No log | 2.0 | 14 | 1.4269 | 0.675 | 0.0001 |
No log | 3.0 | 21 | 1.1038 | 0.75 | 0.0001 |
No log | 4.0 | 28 | 0.8014 | 0.85 | 0.0001 |
No log | 5.0 | 35 | 0.6406 | 0.85 | 0.0001 |
No log | 6.0 | 42 | 0.6220 | 0.875 | 9e-05 |
No log | 7.0 | 49 | 0.4642 | 0.875 | 0.0001 |
No log | 8.0 | 56 | 0.5596 | 0.85 | 0.0001 |
No log | 9.0 | 63 | 0.5648 | 0.85 | 0.0001 |
No log | 10.0 | 70 | 0.5025 | 0.9 | 0.0001 |
No log | 11.0 | 77 | 0.5263 | 0.9 | 0.0001 |
No log | 12.0 | 84 | 0.5062 | 0.9 | 8e-05 |
No log | 13.0 | 91 | 0.4950 | 0.9 | 0.0001 |
No log | 14.0 | 98 | 0.4981 | 0.9 | 0.0001 |
No log | 15.0 | 105 | 0.5036 | 0.9 | 0.0001 |
No log | 16.0 | 112 | 0.5075 | 0.9 | 0.0001 |
No log | 17.0 | 119 | 0.5125 | 0.9 | 0.0001 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.1
- Downloads last month
- 3