metadata
license: mit
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: roberta-base-finetuned-scrambled-squad-5-new
results: []
roberta-base-finetuned-scrambled-squad-5-new
This model is a fine-tuned version of roberta-base on the squad dataset. It achieves the following results on the evaluation set:
- Loss: 0.9098
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: 7e-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: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.941 | 1.0 | 5536 | 0.9098 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.2.0
- Tokenizers 0.12.1