metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: t5-small-finetuned-en-to-pt
results: []
t5-small-finetuned-en-to-pt
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4025
- Bleu: 5.1591
- Gen Len: 18.6818
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: 0.005
- 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: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 0.6566 | 0.16 | 1000 | 0.5401 | 3.797 | 18.6912 |
| 0.5868 | 0.32 | 2000 | 0.4865 | 4.3681 | 18.6722 |
| 0.5369 | 0.48 | 3000 | 0.4504 | 4.6045 | 18.6858 |
| 0.5055 | 0.64 | 4000 | 0.4240 | 4.9816 | 18.6754 |
| 0.4693 | 0.8 | 5000 | 0.4058 | 5.1477 | 18.6782 |
| 0.4631 | 0.96 | 6000 | 0.4025 | 5.1591 | 18.6818 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.0+cu111
- Datasets 1.17.0
- Tokenizers 0.10.3