roberta-base-finetuned-stationary-chatgptDS
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6459
- Accuracy: 0.7367
- F1: 0.7370
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: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.6374 | 1.0 | 75 | 0.6259 | 0.665 | 0.5312 |
| 0.5898 | 2.0 | 150 | 0.5705 | 0.7067 | 0.6957 |
| 0.5349 | 3.0 | 225 | 0.5607 | 0.725 | 0.6971 |
| 0.4875 | 4.0 | 300 | 0.6014 | 0.6717 | 0.6807 |
| 0.4353 | 5.0 | 375 | 0.5648 | 0.73 | 0.7188 |
| 0.414 | 6.0 | 450 | 0.6210 | 0.7383 | 0.7044 |
| 0.3587 | 7.0 | 525 | 0.6130 | 0.7367 | 0.7322 |
| 0.299 | 8.0 | 600 | 0.6070 | 0.7333 | 0.7319 |
| 0.2847 | 9.0 | 675 | 0.6725 | 0.7633 | 0.7519 |
| 0.268 | 10.0 | 750 | 0.6459 | 0.7367 | 0.7370 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0