twitter-roberta_stanfordnlp_imdb_SetFit_tweet_ep2_bs16_lr2e-05_v3
This model is a fine-tuned version of cardiffnlp/twitter-roberta-base-sentiment-latest on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2471
- Accuracy: 0.922
- Precision: 0.9213
- Recall: 0.922
- F1: 0.9216
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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.4417 | 1.0 | 250 | 0.2661 | 0.915 | 0.9152 | 0.915 | 0.9145 |
| 0.3656 | 2.0 | 500 | 0.2471 | 0.922 | 0.9213 | 0.922 | 0.9216 |
Framework versions
- Transformers 5.9.0
- Pytorch 2.12.0+cu126
- Datasets 4.8.5
- Tokenizers 0.22.2