metadata
library_name: transformers
license: apache-2.0
base_model: distilbert/distilbert-base-german-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
model-index:
- name: flausch_span_distilbert-base-german-cased_non_labeled_spans
results: []
flausch_span_distilbert-base-german-cased_non_labeled_spans
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: 0.2139
- Model Preparation Time: 0.0025
- Precision: 0.5524
- Recall: 0.6267
- F1: 0.5872
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 | Model Preparation Time | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.3169 | 0.4233 | 750 | 0.2247 | 0.0025 | 0.3873 | 0.4623 | 0.4215 |
| 0.2218 | 0.8465 | 1500 | 0.2164 | 0.0025 | 0.4657 | 0.5182 | 0.4906 |
| 0.1831 | 1.2698 | 2250 | 0.2090 | 0.0025 | 0.4974 | 0.5964 | 0.5424 |
| 0.1564 | 1.6930 | 3000 | 0.2038 | 0.0025 | 0.5212 | 0.6172 | 0.5652 |
| 0.1535 | 2.1163 | 3750 | 0.2118 | 0.0025 | 0.5447 | 0.6087 | 0.5749 |
| 0.1206 | 2.5395 | 4500 | 0.2106 | 0.0025 | 0.5418 | 0.6262 | 0.5810 |
| 0.1182 | 2.9628 | 5250 | 0.2139 | 0.0025 | 0.5524 | 0.6267 | 0.5872 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1