roberta
This model is a fine-tuned version of bert-base-multilingual-cased on the nsmc dataset. It achieves the following results on the evaluation set:
- Loss: 0.3346
- Accuracy: 0.8661
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-06
- 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: cosine
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3619 | 1.0 | 9375 | 0.3406 | 0.8516 |
| 0.2989 | 2.0 | 18750 | 0.3243 | 0.8644 |
| 0.2655 | 3.0 | 28125 | 0.3346 | 0.8661 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 2