<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
FPC_model
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4029
- Accuracy: 0.9153
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 285 | 1.1683 | 0.7397 |
| 1.5827 | 2.0 | 570 | 0.6301 | 0.8481 |
| 1.5827 | 3.0 | 855 | 0.5046 | 0.8755 |
| 0.4453 | 4.0 | 1140 | 0.4156 | 0.8941 |
| 0.4453 | 5.0 | 1425 | 0.3790 | 0.9153 |
| 0.1964 | 6.0 | 1710 | 0.3949 | 0.9078 |
| 0.1964 | 7.0 | 1995 | 0.3969 | 0.9153 |
| 0.1072 | 8.0 | 2280 | 0.4002 | 0.9153 |
| 0.0611 | 9.0 | 2565 | 0.4027 | 0.9141 |
| 0.0611 | 10.0 | 2850 | 0.4029 | 0.9153 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3
