distilbert-base-uncased-finetuned-discharge
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: 0.9049
- Accuracy: 0.7425
- F1: 0.7419
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: 5e-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: 6
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
No log | 1.0 | 814 | 0.5448 | 0.7052 | 0.7020 |
0.5626 | 2.0 | 1628 | 0.5420 | 0.7323 | 0.7322 |
0.5626 | 3.0 | 2442 | 0.5337 | 0.7535 | 0.7516 |
0.3498 | 4.0 | 3256 | 0.6277 | 0.7491 | 0.7482 |
0.3498 | 5.0 | 4070 | 0.7642 | 0.7432 | 0.7421 |
0.2189 | 6.0 | 4884 | 0.9049 | 0.7425 | 0.7419 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.15.0
- Downloads last month
- 6