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
Training results
| Epoch | Train loss | Test loss | Subtask 3 f1 | Subtask 3 precision | Subtask 3 recall | Subtask4 accuracy |
|---|---|---|---|---|---|---|
| 1 | 342.2936071057338 | 57.76338505232707 | 0.9101978691019786 | 0.9482029598308668 | 0.8751219512195122 | 0.8517073170731707 |
| 2 | 158.99010239201016 | 40.69869995024055 | 0.9054122407688416 | 0.9401260504201681 | 0.8731707317073171 | 0.8780487804878049 |
| 3 | 68.2056962888746 | 32.117333286470966 | 0.9244444444444445 | 0.936 | 0.9131707317073171 | 0.8887804878048781 |
