<!-- 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. -->
platzi-distilroberta-base-mrpc-glue-oscar-moreno
This model is a fine-tuned version of distilroberta-base on the glue and the mrpc datasets. It achieves the following results on the evaluation set:
- Loss: 0.5426
- Accuracy: 0.8162
- F1: 0.8696
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 | F1 |
|---|---|---|---|---|---|
| 0.5255 | 1.09 | 500 | 0.5426 | 0.8162 | 0.8696 |
| 0.3669 | 2.18 | 1000 | 0.5466 | 0.8480 | 0.8869 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
