<!-- 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. -->
translate_fukkkiii
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2617
- Bleu: 9.6087
- Gen Len: 16.8535
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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 0.415 | 1.0 | 625 | 0.3097 | 0.0008 | 17.4795 |
| 0.325 | 2.0 | 1250 | 0.2851 | 1.2229 | 17.177 |
| 0.3016 | 3.0 | 1875 | 0.2745 | 5.8225 | 16.887 |
| 0.2826 | 4.0 | 2500 | 0.2689 | 7.9934 | 16.8085 |
| 0.2764 | 5.0 | 3125 | 0.2647 | 8.7039 | 16.822 |
| 0.2732 | 6.0 | 3750 | 0.2623 | 9.4137 | 16.831 |
| 0.2728 | 7.0 | 4375 | 0.2617 | 9.6087 | 16.8535 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
