train_on_perturbed
This model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1527
- Precision: 0.5130
- Recall: 0.5333
- F1: 0.5230
- Accuracy: 0.9671
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: 8
- eval_batch_size: 8
- 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 | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 205 | 0.1624 | 0.3868 | 0.3825 | 0.3847 | 0.9585 |
No log | 2.0 | 410 | 0.1387 | 0.4264 | 0.4825 | 0.4527 | 0.9620 |
0.1817 | 3.0 | 615 | 0.1465 | 0.5081 | 0.4968 | 0.5024 | 0.9664 |
0.1817 | 4.0 | 820 | 0.1507 | 0.5100 | 0.5238 | 0.5168 | 0.9667 |
0.0471 | 5.0 | 1025 | 0.1527 | 0.5130 | 0.5333 | 0.5230 | 0.9671 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.0+cpu
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 1