results
This model is a fine-tuned version of distilbert-base-uncased-finetuned-sst-2-english on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4273
- Accuracy: 0.8299
- Precision: 0.8297
- Recall: 0.8299
- F1: 0.8296
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: 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 | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 194 | 0.3885 | 0.8428 | 0.8423 | 0.8428 | 0.8422 |
| No log | 2.0 | 388 | 0.4115 | 0.8479 | 0.8497 | 0.8479 | 0.8467 |
| 0.3661 | 3.0 | 582 | 0.4147 | 0.8466 | 0.8462 | 0.8466 | 0.8464 |
Framework versions
- Transformers 5.13.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2