metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: spam-classifier
results: []
spam-classifier
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0614
- Accuracy: 0.9885
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: 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 | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 262 | 0.0968 | 0.9799 |
| 0.0573 | 2.0 | 524 | 0.0693 | 0.9856 |
| 0.0573 | 3.0 | 786 | 0.0599 | 0.9871 |
| 0.0111 | 4.0 | 1048 | 0.0551 | 0.9885 |
| 0.0111 | 5.0 | 1310 | 0.0614 | 0.9885 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2