<!-- 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-large-e12-b16
This model is a fine-tuned version of siebert/sentiment-roberta-large-english on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.8728
- F1: 0.7682
- Recall: 0.7682
- Precision: 0.7682
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: 12
Training results
Training Loss | Epoch | Step | Validation Loss | F1 | Recall | Precision |
---|---|---|---|---|---|---|
No log | 1.0 | 375 | 0.7403 | 0.7278 | 0.7278 | 0.7278 |
0.7133 | 2.0 | 750 | 0.7236 | 0.7709 | 0.7709 | 0.7709 |
0.3747 | 3.0 | 1125 | 0.9717 | 0.7601 | 0.7601 | 0.7601 |
0.2548 | 4.0 | 1500 | 1.1395 | 0.7628 | 0.7628 | 0.7628 |
0.2548 | 5.0 | 1875 | 1.3756 | 0.7709 | 0.7709 | 0.7709 |
0.1466 | 6.0 | 2250 | 1.5808 | 0.7790 | 0.7790 | 0.7790 |
0.1039 | 7.0 | 2625 | 1.7365 | 0.7412 | 0.7412 | 0.7412 |
0.0639 | 8.0 | 3000 | 1.8293 | 0.7547 | 0.7547 | 0.7547 |
0.0639 | 9.0 | 3375 | 1.8055 | 0.7628 | 0.7628 | 0.7628 |
0.0452 | 10.0 | 3750 | 1.7496 | 0.7682 | 0.7682 | 0.7682 |
0.0262 | 11.0 | 4125 | 1.8558 | 0.7655 | 0.7655 | 0.7655 |
0.0183 | 12.0 | 4500 | 1.8728 | 0.7682 | 0.7682 | 0.7682 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3