<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
my_wikilingua_t5small
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.6035
- Rouge1: 0.2226
- Rouge2: 0.0638
- Rougel: 0.1839
- Rougelsum: 0.1838
- Gen Len: 18.725
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: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 100 | 2.7179 | 0.2156 | 0.0579 | 0.1742 | 0.1741 | 18.835 |
| No log | 2.0 | 200 | 2.6370 | 0.2213 | 0.0637 | 0.1796 | 0.1794 | 18.805 |
| No log | 3.0 | 300 | 2.6105 | 0.2239 | 0.064 | 0.1834 | 0.1833 | 18.79 |
| No log | 4.0 | 400 | 2.6035 | 0.2226 | 0.0638 | 0.1839 | 0.1838 | 18.725 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
