<!-- 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. -->
roberta_multiple_choice
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2868
- Accuracy: 0.58
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: linear
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.4619 | 1.0 | 3207 | 1.2367 | 0.51 |
| 1.3209 | 2.0 | 6414 | 1.1911 | 0.525 |
| 1.2195 | 3.0 | 9621 | 1.1396 | 0.525 |
| 1.1211 | 4.0 | 12828 | 1.1321 | 0.53 |
| 1.0221 | 5.0 | 16035 | 1.2210 | 0.535 |
| 0.9262 | 6.0 | 19242 | 1.2008 | 0.555 |
| 0.8418 | 7.0 | 22449 | 1.2451 | 0.555 |
| 0.7691 | 8.0 | 25656 | 1.2793 | 0.555 |
| 0.6981 | 9.0 | 28863 | 1.2868 | 0.58 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3
