distilbert-base-uncased__sst2__train-16-8
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6895
- Accuracy: 0.5222
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.6899 | 1.0 | 7 | 0.7055 | 0.2857 |
0.6793 | 2.0 | 14 | 0.7205 | 0.2857 |
0.6291 | 3.0 | 21 | 0.7460 | 0.2857 |
0.5659 | 4.0 | 28 | 0.8041 | 0.2857 |
0.5607 | 5.0 | 35 | 0.7785 | 0.4286 |
0.3349 | 6.0 | 42 | 0.8163 | 0.4286 |
0.2436 | 7.0 | 49 | 0.9101 | 0.2857 |
0.1734 | 8.0 | 56 | 0.8632 | 0.5714 |
0.1122 | 9.0 | 63 | 0.9851 | 0.5714 |
0.0661 | 10.0 | 70 | 1.0835 | 0.5714 |
0.0407 | 11.0 | 77 | 1.1656 | 0.5714 |
Framework versions
- Transformers 4.15.0
- Pytorch 1.10.2+cu102
- Datasets 1.18.2
- Tokenizers 0.10.3
- Downloads last month
- 14
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.