t5-small-finetuned-en-to-ro-fp16_off-lr_2e-7-weight_decay_0.001
This model is a fine-tuned version of t5-small on the wmt16 dataset. It achieves the following results on the evaluation set:
- Loss: 1.4943
- Bleu: 4.7258
- Gen Len: 18.7149
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-07
- 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 |
|---|---|---|---|---|---|
| 1.047 | 1.0 | 7629 | 1.4943 | 4.7258 | 18.7149 |
Framework versions
- Transformers 4.12.5
- Pytorch 1.10.0+cu111
- Datasets 1.16.1
- Tokenizers 0.10.3