metadata
license: mit
tags:
- generated_from_trainer
datasets:
- xnli
metrics:
- accuracy
model-index:
- name: bert-xnli-de-classifier
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: xnli
type: xnli
config: de
split: validation
args: de
metrics:
- name: Accuracy
type: accuracy
value: 0.7807228915662651
bert-xnli-de-classifier
This model is a fine-tuned version of bert-base-german-cased on the xnli dataset. It achieves the following results on the evaluation set:
- Loss: 0.5897
- Accuracy: 0.7807
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.554 | 1.0 | 6136 | 0.5783 | 0.7675 |
| 0.4946 | 2.0 | 12272 | 0.5471 | 0.7892 |
| 0.3416 | 3.0 | 18408 | 0.5897 | 0.7807 |
Framework versions
- Transformers 4.27.3
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2