large-plain
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8970
- Accuracy: 0.4756
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.0028 | 1.0 | 183 | 0.8731 | 0.4721 |
0.9623 | 2.0 | 366 | 0.8744 | 0.4721 |
0.9408 | 3.0 | 549 | 0.8663 | 0.4595 |
0.901 | 4.0 | 732 | 0.8700 | 0.4784 |
0.8642 | 5.0 | 915 | 0.9221 | 0.4378 |
0.8422 | 6.0 | 1098 | 0.8799 | 0.4856 |
0.8234 | 7.0 | 1281 | 0.8884 | 0.4730 |
0.8076 | 8.0 | 1464 | 0.8973 | 0.4802 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 1