my_awesome_model
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: 0.3714
- Accuracy: 0.933
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 |
---|---|---|---|---|
0.3279 | 0.32 | 500 | 0.2746 | 0.899 |
0.2474 | 0.64 | 1000 | 0.2127 | 0.919 |
0.2296 | 0.96 | 1500 | 0.2596 | 0.907 |
0.1642 | 1.28 | 2000 | 0.2009 | 0.935 |
0.1571 | 1.6 | 2500 | 0.2683 | 0.907 |
0.1523 | 1.92 | 3000 | 0.1838 | 0.948 |
0.1032 | 2.24 | 3500 | 0.2117 | 0.948 |
0.0831 | 2.56 | 4000 | 0.2541 | 0.945 |
0.0898 | 2.88 | 4500 | 0.3497 | 0.923 |
0.0644 | 3.2 | 5000 | 0.3443 | 0.927 |
0.0467 | 3.52 | 5500 | 0.3266 | 0.937 |
0.0526 | 3.84 | 6000 | 0.2849 | 0.946 |
0.0426 | 4.16 | 6500 | 0.3319 | 0.938 |
0.0253 | 4.48 | 7000 | 0.3558 | 0.932 |
0.0188 | 4.8 | 7500 | 0.3714 | 0.933 |
Framework versions
- Transformers 4.37.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2
- Downloads last month
- 5