Pretrained checkpoint: roberta-large-mnli
Traning hyperparameters:
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 24
- eval_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- prompt_format: sentence aspect - sentiment
Training results
| Epoch | Train loss | Subtask 3 f1 | Subtask 3 precision | Subtask 3 recall | Subtask4 accuracy |
|---|---|---|---|---|---|
| 1 | 331.22805924050044 | 0.8987603305785123 | 0.9549945115257958 | 0.848780487804878 | 0.848780487804878 |
| 2 | 143.6195309770701 | 0.9197224975222993 | 0.9345417925478349 | 0.9053658536585366 | 0.8887804878048781 |
| 3 | 58.553219705150696 | 0.923837784371909 | 0.9368104312938816 | 0.911219512195122 | 0.8760975609756098 |
