fold_1
This model is a fine-tuned version of austin/Austin-MeDeBERTa on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0106
- Precision: 0.7077
- Recall: 0.7188
- F1: 0.7132
- Accuracy: 0.9971
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: 5
- eval_batch_size: 5
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.0405 | 1.0 | 708 | 0.0124 | 0.6111 | 0.6302 | 0.6205 | 0.9964 |
0.0096 | 2.0 | 1416 | 0.0100 | 0.8311 | 0.6406 | 0.7235 | 0.9973 |
0.0037 | 3.0 | 2124 | 0.0106 | 0.7077 | 0.7188 | 0.7132 | 0.9971 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2
- Downloads last month
- 5