Capybara
This model is training from scratch on the Self-GRIT/wikitext-2-raw-v1-preprocessed dataset. It achieves the following results on the evaluation set:
- Loss: 5.9824
- Accuracy: 0.2140
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: 3.0
Training results
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.1.2+cu118
- Datasets 3.0.0
- Tokenizers 0.19.1
- Downloads last month
- 6
Model tree for yue619/Capybara
Dataset used to train yue619/Capybara
Evaluation results
- Accuracy on Self-GRIT/wikitext-2-raw-v1-preprocessedself-reported0.214