distilbert-base-uncased-finetuned-Sentiment
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: 0.0021
- Accuracy: 1.0
- F1: 1.0
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.0043 | 1.0 | 29 | 0.0040 | 1.0 | 1.0 |
| 0.0032 | 2.0 | 58 | 0.0034 | 1.0 | 1.0 |
| 0.0025 | 3.0 | 87 | 0.0032 | 1.0 | 1.0 |
| 0.0021 | 4.0 | 116 | 0.0025 | 1.0 | 1.0 |
| 0.0019 | 5.0 | 145 | 0.0023 | 1.0 | 1.0 |
| 0.0017 | 6.0 | 174 | 0.0023 | 1.0 | 1.0 |
| 0.0016 | 7.0 | 203 | 0.0022 | 1.0 | 1.0 |
| 0.0015 | 8.0 | 232 | 0.0022 | 1.0 | 1.0 |
| 0.0014 | 9.0 | 261 | 0.0021 | 1.0 | 1.0 |
| 0.0014 | 10.0 | 290 | 0.0021 | 1.0 | 1.0 |
Framework versions
- Transformers 4.52.2
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1