bert-base-uncased-finetuned-stationary-chatgptDS
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7019
- Accuracy: 0.84
- F1: 0.8367
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 |
|---|---|---|---|---|---|
| 0.5554 | 1.0 | 75 | 0.4860 | 0.7867 | 0.7674 |
| 0.3768 | 2.0 | 150 | 0.4438 | 0.8117 | 0.8103 |
| 0.2551 | 3.0 | 225 | 0.4781 | 0.8333 | 0.8284 |
| 0.1581 | 4.0 | 300 | 0.4850 | 0.8383 | 0.8334 |
| 0.1051 | 5.0 | 375 | 0.5698 | 0.845 | 0.8381 |
| 0.0726 | 6.0 | 450 | 0.6293 | 0.845 | 0.8439 |
| 0.05 | 7.0 | 525 | 0.6414 | 0.8417 | 0.8396 |
| 0.031 | 8.0 | 600 | 0.7114 | 0.8483 | 0.8474 |
| 0.026 | 9.0 | 675 | 0.6890 | 0.8467 | 0.8433 |
| 0.0198 | 10.0 | 750 | 0.7019 | 0.84 | 0.8367 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0