<!-- 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-e6-b16-v2-w0.01
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: 1.2099
- F1: 0.7898
- Recall: 0.7898
- Precision: 0.7898
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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Recall | Precision |
|---|---|---|---|---|---|---|
| No log | 1.0 | 375 | 0.8152 | 0.7251 | 0.7251 | 0.7251 |
| 0.7707 | 2.0 | 750 | 0.7114 | 0.7817 | 0.7817 | 0.7817 |
| 0.4129 | 3.0 | 1125 | 0.9667 | 0.7763 | 0.7763 | 0.7763 |
| 0.2466 | 4.0 | 1500 | 0.9866 | 0.7763 | 0.7763 | 0.7763 |
| 0.2466 | 5.0 | 1875 | 1.2385 | 0.7871 | 0.7871 | 0.7871 |
| 0.139 | 6.0 | 2250 | 1.2099 | 0.7898 | 0.7898 | 0.7898 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
