mt5-base-multi_news
This model is a fine-tuned version of google/mt5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.2565
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: 0.001
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.8534 | 1.0 | 5622 | 3.5584 |
| 3.58 | 2.0 | 11244 | 3.3606 |
| 3.4904 | 3.0 | 16866 | 3.3078 |
| 3.4461 | 4.0 | 22488 | 3.2863 |
| 3.408 | 5.0 | 28110 | 3.2724 |
| 3.3951 | 6.0 | 33732 | 3.2642 |
| 3.3854 | 7.0 | 39354 | 3.2602 |
| 3.3731 | 8.0 | 44976 | 3.2577 |
| 3.3803 | 9.0 | 50598 | 3.2563 |
| 3.3755 | 10.0 | 56220 | 3.2565 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2
- Downloads last month
- 0