small_dataset
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9543
- Sacrebleu: 5.2846
- Gen Len: 16.5238
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: 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Sacrebleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 5 | 0.9781 | 5.2846 | 16.5238 |
| No log | 2.0 | 10 | 0.9681 | 5.2846 | 16.5238 |
| No log | 3.0 | 15 | 0.9602 | 5.2846 | 16.5238 |
| No log | 4.0 | 20 | 0.9560 | 5.2846 | 16.5238 |
| No log | 5.0 | 25 | 0.9543 | 5.2846 | 16.5238 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cpu
- Datasets 2.13.0
- Tokenizers 0.13.3