metadata
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: translation-en-pt-t5-finetuned-Duolingo
results: []
translation-en-pt-t5-finetuned-Duolingo
This model is a fine-tuned version of unicamp-dl/translation-en-pt-t5 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7436
- Bleu: 39.7994
- Gen Len: 8.978
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 0.7259 | 0.24 | 9000 | 0.7897 | 39.2919 | 8.912 |
| 0.6407 | 0.48 | 18000 | 0.7575 | 39.9964 | 8.898 |
| 0.614 | 0.72 | 27000 | 0.7465 | 39.725 | 8.952 |
| 0.6 | 0.96 | 36000 | 0.7436 | 39.7994 | 8.978 |
Framework versions
- Transformers 4.12.5
- Pytorch 1.10.0+cu111
- Datasets 1.16.1
- Tokenizers 0.10.3