CMSC_473_t5_ja
This model is a fine-tuned version of google-t5/t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.4437
- Bleu: 1.4633
- Gen Len: 13.1495
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: 0.0001
- 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: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
---|---|---|---|---|---|
3.5392 | 1.0 | 3125 | 3.4776 | 1.478 | 13.0325 |
3.4769 | 2.0 | 6250 | 3.4510 | 1.2928 | 9.9785 |
3.4403 | 3.0 | 9375 | 3.4437 | 1.4633 | 13.1495 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 7