bert-base-uncased-finetuned-stationary-update
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: 0.8082
- Accuracy: 0.7967
- F1: 0.7872
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 |
|---|---|---|---|---|---|
| 0.5673 | 1.0 | 38 | 0.5049 | 0.7667 | 0.7453 |
| 0.4018 | 2.0 | 76 | 0.4605 | 0.79 | 0.7853 |
| 0.3074 | 3.0 | 114 | 0.4991 | 0.7967 | 0.7941 |
| 0.2065 | 4.0 | 152 | 0.5517 | 0.7967 | 0.7914 |
| 0.1347 | 5.0 | 190 | 0.7082 | 0.7833 | 0.7655 |
| 0.1008 | 6.0 | 228 | 0.7469 | 0.7967 | 0.7811 |
| 0.0799 | 7.0 | 266 | 0.7609 | 0.7933 | 0.7823 |
| 0.0558 | 8.0 | 304 | 0.8108 | 0.7967 | 0.7853 |
| 0.0526 | 9.0 | 342 | 0.7988 | 0.79 | 0.7821 |
| 0.0426 | 10.0 | 380 | 0.8082 | 0.7967 | 0.7872 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0