<!-- 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. -->
aak-distilroberta-base-mrpc-glue-ricardo-talavera
This model is a fine-tuned version of distilroberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 15.1968
- Accuracy: 0.0
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0253 | 0.28 | 500 | 12.0296 | 0.0 |
| 0.0 | 0.56 | 1000 | 12.9787 | 0.0 |
| 0.0 | 0.84 | 1500 | 13.5657 | 0.0 |
| 0.0 | 1.11 | 2000 | 13.9849 | 0.0 |
| 0.0 | 1.39 | 2500 | 14.3131 | 0.0 |
| 0.0 | 1.67 | 3000 | 14.5808 | 0.0 |
| 0.0 | 1.95 | 3500 | 14.8001 | 0.0 |
| 0.0 | 2.23 | 4000 | 14.9771 | 0.0 |
| 0.0 | 2.51 | 4500 | 15.1107 | 0.0 |
| 0.0 | 2.79 | 5000 | 15.1968 | 0.0 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
