model_perturbations
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: 0.1463
- Precision: 0.4596
- Recall: 0.3968
- F1: 0.4259
- Accuracy: 0.9632
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 | 0.1769 | 0.2719 | 0.2810 | 0.2763 | 0.9532 |
No log | 2.0 | 410 | 0.1463 | 0.4596 | 0.3968 | 0.4259 | 0.9632 |
0.2289 | 3.0 | 615 | 0.1463 | 0.4382 | 0.4556 | 0.4467 | 0.9636 |
0.2289 | 4.0 | 820 | 0.1517 | 0.4951 | 0.4810 | 0.4879 | 0.9657 |
0.0817 | 5.0 | 1025 | 0.1540 | 0.5101 | 0.4825 | 0.4959 | 0.9663 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.0+cpu
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 3