roberta-base_brkfst
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1920
- Accuracy: 0.9717
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: 32
- eval_batch_size: 32
- seed: 27
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.5456 | 0.67 | 10 | 0.2031 | 0.9340 |
0.211 | 1.33 | 20 | 0.1873 | 0.9245 |
0.221 | 2.0 | 30 | 0.1245 | 0.9623 |
0.1246 | 2.67 | 40 | 0.0487 | 0.9906 |
0.06 | 3.33 | 50 | 0.0593 | 0.9811 |
0.0892 | 4.0 | 60 | 0.3926 | 0.9245 |
0.1056 | 4.67 | 70 | 0.1237 | 0.9528 |
0.0387 | 5.33 | 80 | 0.2616 | 0.9434 |
0.0678 | 6.0 | 90 | 0.1895 | 0.9717 |
0.0239 | 6.67 | 100 | 0.2132 | 0.9623 |
0.0218 | 7.33 | 110 | 0.2018 | 0.9717 |
0.0007 | 8.0 | 120 | 0.1460 | 0.9811 |
0.0009 | 8.67 | 130 | 0.1429 | 0.9811 |
0.0003 | 9.33 | 140 | 0.1541 | 0.9717 |
0.0002 | 10.0 | 150 | 0.1558 | 0.9717 |
0.0135 | 10.67 | 160 | 0.1545 | 0.9717 |
0.0002 | 11.33 | 170 | 0.1529 | 0.9717 |
0.0002 | 12.0 | 180 | 0.1661 | 0.9717 |
0.0002 | 12.67 | 190 | 0.1850 | 0.9717 |
0.0002 | 13.33 | 200 | 0.1900 | 0.9717 |
0.0002 | 14.0 | 210 | 0.1915 | 0.9717 |
0.0002 | 14.67 | 220 | 0.1920 | 0.9717 |
Framework versions
- Transformers 4.39.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 29