elvish-translator-sindarin-t5-base
This model is a fine-tuned version of google-t5/t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.7904
- Bleu: 1.0092
- Gen Len: 14.775
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: 0.002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
---|---|---|---|---|---|
4.5672 | 1.0 | 40 | 4.0168 | 0.5041 | 15.25 |
3.898 | 2.0 | 80 | 3.8542 | 0.9997 | 12.35 |
3.5914 | 3.0 | 120 | 3.7813 | 1.1689 | 13.875 |
3.3466 | 4.0 | 160 | 3.7551 | 0.941 | 14.95 |
3.0903 | 5.0 | 200 | 3.7904 | 1.0092 | 14.775 |
Framework versions
- PEFT 0.12.1.dev0
- Transformers 4.45.0.dev0
- Pytorch 2.4.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 5
Model tree for Oysiyl/elvish-translator-sindarin-t5-base
Base model
google-t5/t5-base