fine_tuned_3e-5
This model is a fine-tuned version of FacebookAI/roberta-large on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0369
- Accuracy: 0.9933
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: 3e-05
- 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: 3
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
Accuracy |
| 0.4112 |
0.15 |
100 |
0.2334 |
0.96 |
| 0.3366 |
0.3 |
200 |
0.2366 |
0.96 |
| 0.2548 |
0.44 |
300 |
0.3344 |
0.9233 |
| 0.1728 |
0.59 |
400 |
0.5630 |
0.9017 |
| 0.1559 |
0.74 |
500 |
0.1761 |
0.9733 |
| 0.1139 |
0.89 |
600 |
0.9891 |
0.835 |
| 0.1084 |
1.04 |
700 |
0.1377 |
0.9733 |
| 0.0551 |
1.19 |
800 |
0.0782 |
0.9833 |
| 0.0829 |
1.33 |
900 |
0.0325 |
0.9933 |
| 0.0411 |
1.48 |
1000 |
0.0369 |
0.9933 |
| 0.0274 |
1.63 |
1100 |
0.0144 |
0.9983 |
| 0.0242 |
1.78 |
1200 |
0.0524 |
0.9933 |
| 0.0261 |
1.93 |
1300 |
0.1679 |
0.9817 |
| 0.0115 |
2.07 |
1400 |
0.0870 |
0.9883 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.1+cu118
- Datasets 2.16.0
- Tokenizers 0.15.0
