flausch_task1_classification_distilbert-base-german-cased_lehre
This model is a fine-tuned version of distilbert/distilbert-base-german-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2186
- Model Preparation Time: 0.0029
- Accuracy: 0.9298
- F1: 0.9296
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_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Accuracy | F1 |
|---|---|---|---|---|---|---|
| 0.2978 | 0.4233 | 750 | 0.2598 | 0.0029 | 0.9033 | 0.8995 |
| 0.2371 | 0.8465 | 1500 | 0.2213 | 0.0029 | 0.9232 | 0.9216 |
| 0.1913 | 1.2698 | 2250 | 0.2198 | 0.0029 | 0.9298 | 0.9294 |
| 0.1781 | 1.6930 | 3000 | 0.2184 | 0.0029 | 0.9262 | 0.9263 |
| 0.1781 | 2.0 | 3544 | 0.2186 | 0.0029 | 0.9298 | 0.9296 |
Framework versions
- Transformers 5.10.2
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2