transforemr
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.3345
- Bleu: 5.098
- Gen Len: 7.9826
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
---|---|---|---|---|---|
2.6892 | 1.0 | 12709 | 2.4746 | 4.0486 | 7.9876 |
2.5757 | 2.0 | 25418 | 2.3936 | 4.8489 | 7.992 |
2.5445 | 3.0 | 38127 | 2.3565 | 5.0781 | 7.9899 |
2.501 | 4.0 | 50836 | 2.3388 | 5.095 | 7.9828 |
2.4785 | 5.0 | 63545 | 2.3345 | 5.098 | 7.9826 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.2.0
- Datasets 2.17.1
- Tokenizers 0.15.2
- Downloads last month
- 2