distilbert-sst2
This model is a fine-tuned version of distilbert-base-uncased on the SST-2 (Stanford Sentiment Treebank) dataset. It achieves the following results on the evaluation set:
- Loss: 0.1952
- Accuracy: 0.9047
- F1 Macro: 0.9048
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: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|---|---|---|---|---|---|
| 0.1787 | 1.0 | 1895 | 0.1652 | 0.9451 | 0.9447 |
| 0.0943 | 2.0 | 3790 | 0.1779 | 0.9486 | 0.9483 |
| 0.0636 | 3.0 | 5685 | 0.1952 | 0.9495 | 0.9490 |
Framework versions
- Transformers 5.14.1
- Pytorch 2.11.0+cu128
- Datasets 5.0.1
- Tokenizers 0.22.2