t5-large_wic_dense_epochs-5
This model is a fine-tuned version of t5-large on the super_glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.7106
- Accuracy: 0.6599
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: 64
- eval_batch_size: 64
- seed: 0
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 20
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6058 | 2.35 | 50 | 0.7125 | 0.6176 |
| 0.4662 | 4.71 | 100 | 0.7054 | 0.6614 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 7
Model tree for thrunlab/t5-large_wic_dense_epochs-5
Base model
google-t5/t5-largeDataset used to train thrunlab/t5-large_wic_dense_epochs-5
Evaluation results
- Accuracy on super_gluevalidation set self-reported0.660