metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: distilroberta-base-finetuned-squad
results: []
distilroberta-base-finetuned-squad
This model is a fine-tuned version of distilroberta-base on the squad dataset. It achieves the following results on the evaluation set:
Loss: 1.0021
Exact Match: 81.33396404919584
F1-score: 88.41135855065653
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 |
|---|---|---|---|
| 1.0897 | 1.0 | 5536 | 1.0352 |
| 0.8719 | 2.0 | 11072 | 0.9679 |
| 0.7331 | 3.0 | 16608 | 1.0021 |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0+cu113
- Datasets 2.2.2
- Tokenizers 0.12.1