<!-- 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. -->
100K_sample_model
This model is a fine-tuned version of t5-small on the wmt16 dataset. It achieves the following results on the evaluation set:
- Loss: 1.2624
- Bleu: 13.0723
- Gen Len: 17.5159
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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 1.2605 | 1.0 | 12500 | 1.2595 | 13.0452 | 17.503 |
| 1.2728 | 2.0 | 25000 | 1.2596 | 13.049 | 17.5154 |
| 1.2437 | 3.0 | 37500 | 1.2624 | 13.0723 | 17.5159 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu117
- Datasets 2.11.0
- Tokenizers 0.13.2
