metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: roberta-base-squad2-distilled-small-cuad-1
results: []
roberta-base-squad2-distilled-small-cuad-1
This model is a fine-tuned version of distilroberta-base on the squad dataset. It achieves the following results on the evaluation set:
- Loss: 1.3798
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 282 | 1.5628 |
| 2.0814 | 2.0 | 564 | 1.3975 |
| 2.0814 | 3.0 | 846 | 1.3798 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3