gewerke
This model is a fine-tuned version of svalabs/gbert-large-zeroshot-nli on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0089
- F1: 0.9974
Label-Übersetzung
- 0 Abwasser-Wasser-Gasanlagen
- 1 Andere Anlagen
- 2 Gebäudeautomation
- 3 Kälteanlagen
- 4 Lufttechnische Anlagen
- 5 Starkstromanlagen
- 6 Wärmeversorungsanlagen
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | F1 |
---|---|---|---|---|
No log | 0.99 | 90 | 0.0444 | 0.9886 |
No log | 1.99 | 180 | 0.0182 | 0.9947 |
No log | 2.99 | 270 | 0.0103 | 0.9974 |
No log | 3.99 | 360 | 0.0152 | 0.9946 |
No log | 4.99 | 450 | 0.0089 | 0.9974 |
Framework versions
- Transformers 4.22.2
- Pytorch 1.12.1+cu113
- Datasets 2.5.1
- Tokenizers 0.12.1
- Downloads last month
- 2