metadata
library_name: transformers
license: mit
base_model: google-bert/bert-base-german-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: cleaned_dataset_v2_08
results: []
cleaned_dataset_v2_08
This model is a fine-tuned version of google-bert/bert-base-german-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0678
- Precision: 0.908
- Recall: 0.9478
- F1: 0.9275
- Accuracy: 0.9940
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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0439 | 1.0 | 368 | 0.0240 | 0.8777 | 0.9436 | 0.9095 | 0.9933 |
| 0.0264 | 2.0 | 736 | 0.0678 | 0.908 | 0.9478 | 0.9275 | 0.9940 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.8.0+cu126
- Datasets 4.2.0
- Tokenizers 0.21.4