roberta-large-go-emotions
This model is a fine-tuned version of roberta-large on an go emotion dataset. It achieves the following results on the evaluation set:
- Loss: 0.0827
- Accuracy: 0.4589
- Precision: 0.5252
- Recall: 0.5203
- F1: 0.5142
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: 5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 679 | 0.0864 | 0.4412 | 0.4810 | 0.4637 | 0.4557 |
| 0.1012 | 2.0 | 1358 | 0.0810 | 0.4410 | 0.5468 | 0.5244 | 0.5147 |
| 0.1012 | 3.0 | 2037 | 0.0820 | 0.4493 | 0.5180 | 0.5262 | 0.5092 |
| 0.0659 | 4.0 | 2716 | 0.0827 | 0.4589 | 0.5252 | 0.5203 | 0.5142 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2
- Datasets 2.15.0
- Tokenizers 0.15.1