<!-- 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. -->
distilroberta-base-finetuned-question-v-statement-finetuned-custom-v2
This model is a fine-tuned version of mafwalter/distilroberta-base-finetuned-question-v-statement on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1148
- Accuracy: 0.9874
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 438 | 0.0654 | 0.9860 |
| 0.0894 | 2.0 | 876 | 0.0945 | 0.9845 |
| 0.039 | 3.0 | 1314 | 0.1134 | 0.9845 |
| 0.0215 | 4.0 | 1752 | 0.1148 | 0.9874 |
| 0.0079 | 5.0 | 2190 | 0.1175 | 0.9852 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
