<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
sentiment-roberta-latest-e8-b16-data2
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: 2.0416
- F1: 0.7439
- Recall: 0.7439
- Precision: 0.7439
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
Training Loss | Epoch | Step | Validation Loss | F1 | Recall | Precision |
---|---|---|---|---|---|---|
No log | 1.0 | 375 | 0.8354 | 0.7278 | 0.7278 | 0.7278 |
0.446 | 2.0 | 750 | 1.0641 | 0.7655 | 0.7655 | 0.7655 |
0.1559 | 3.0 | 1125 | 1.4651 | 0.7278 | 0.7278 | 0.7278 |
0.0812 | 4.0 | 1500 | 1.8105 | 0.7412 | 0.7412 | 0.7412 |
0.0812 | 5.0 | 1875 | 1.9380 | 0.7358 | 0.7358 | 0.7358 |
0.0254 | 6.0 | 2250 | 2.0327 | 0.7412 | 0.7412 | 0.7412 |
0.0125 | 7.0 | 2625 | 2.1059 | 0.7412 | 0.7412 | 0.7412 |
0.0071 | 8.0 | 3000 | 2.0416 | 0.7439 | 0.7439 | 0.7439 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3