grow_classification_five_class
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9699
- Accuracy: 0.8381
- F1: 0.8354
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: 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.5017 | 1.0 | 450 | 0.8314 | 0.7754 | 0.7695 |
| 0.144 | 2.0 | 900 | 0.7651 | 0.8155 | 0.8121 |
| 0.0718 | 3.0 | 1350 | 0.8483 | 0.8331 | 0.8296 |
| 0.0421 | 4.0 | 1800 | 1.0276 | 0.8320 | 0.8290 |
| 0.026 | 5.0 | 2250 | 0.9699 | 0.8381 | 0.8354 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3