byt5_3k_4d
This model is a fine-tuned version of google/byt5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0734
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: 5e-05
- train_batch_size: 800
- eval_batch_size: 800
- 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 |
|---|---|---|---|
| No log | 1.0 | 4 | 0.0858 |
| No log | 2.0 | 8 | 0.0784 |
| 0.2758 | 3.0 | 12 | 0.0821 |
| 0.2758 | 4.0 | 16 | 0.0756 |
| 0.2665 | 5.0 | 20 | 0.0801 |
| 0.2665 | 6.0 | 24 | 0.0745 |
| 0.2665 | 7.0 | 28 | 0.0699 |
| 0.2578 | 8.0 | 32 | 0.0731 |
| 0.2578 | 9.0 | 36 | 0.0740 |
| 0.254 | 10.0 | 40 | 0.0734 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 1