bert-base-uncased-twitter-sentiment
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7032
- Model Preparation Time: 0.0061
- Accuracy: 0.6833
- F1: 0.6703
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: 8
- 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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Accuracy | F1 |
|---|---|---|---|---|---|---|
| 1.1191 | 1.0 | 30 | 1.0922 | 0.0061 | 0.3917 | 0.3296 |
| 1.0822 | 2.0 | 60 | 1.0806 | 0.0061 | 0.35 | 0.2673 |
| 0.9598 | 3.0 | 90 | 0.9128 | 0.0061 | 0.5833 | 0.5264 |
| 0.6824 | 4.0 | 120 | 0.7486 | 0.0061 | 0.7 | 0.6841 |
| 0.4703 | 5.0 | 150 | 0.7414 | 0.0061 | 0.6583 | 0.6494 |
| 0.4013 | 6.0 | 180 | 0.7032 | 0.0061 | 0.6833 | 0.6703 |
Framework versions
- Transformers 5.17.0
- Pytorch 2.14.0+cpu
- Datasets 5.0.1
- Tokenizers 0.23.2