transforemr_16
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4841
- Bleu: 8.6082
- Gen Len: 17.5647
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 1.8767 | 1.0 | 6355 | 1.6443 | 7.2826 | 17.6214 |
| 1.7864 | 2.0 | 12710 | 1.5863 | 7.7743 | 17.5883 |
| 1.7465 | 3.0 | 19065 | 1.5544 | 8.0399 | 17.5689 |
| 1.7034 | 4.0 | 25420 | 1.5304 | 8.1983 | 17.5708 |
| 1.6912 | 5.0 | 31775 | 1.5148 | 8.3483 | 17.5603 |
| 1.6652 | 6.0 | 38130 | 1.5022 | 8.4549 | 17.5658 |
| 1.6534 | 7.0 | 44485 | 1.4951 | 8.5235 | 17.563 |
| 1.6615 | 8.0 | 50840 | 1.4884 | 8.562 | 17.5624 |
| 1.6426 | 9.0 | 57195 | 1.4854 | 8.5932 | 17.5643 |
| 1.6451 | 10.0 | 63550 | 1.4841 | 8.6082 | 17.5647 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.2.0
- Datasets 2.17.1
- Tokenizers 0.15.2
- Downloads last month
- 3