patent-classification-gpu
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: 1.4168
- Accuracy: 0.5800
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.5695 | 1.0 | 2384 | 1.4698 | 0.5400 |
| 1.2985 | 2.0 | 4768 | 1.3742 | 0.5705 |
| 1.117 | 3.0 | 7152 | 1.3588 | 0.5792 |
| 0.924 | 4.0 | 9536 | 1.3985 | 0.5816 |
| 0.7839 | 5.0 | 11920 | 1.4168 | 0.5800 |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 9
Model tree for zgurney/patent-classification-gpu
Base model
distilbert/distilbert-base-uncased