metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: english2german
results: []
english to german translator
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7882
- Bleu: 41.8343
- Gen Len: 11.2308
Model description
For Translation:
- translate English to German: [text]
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 0.9638 | 1.0 | 11077 | 0.8045 | 41.2212 | 11.2169 |
| 0.94 | 2.0 | 22154 | 0.7882 | 41.8343 | 11.2308 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1