roberta-large-bn-adapter-3.17M-snli-model1
This model is a fine-tuned version of roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6213
- Accuracy: 0.804
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: 64
- eval_batch_size: 64
- seed: 15
- 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 | Accuracy |
|---|---|---|---|---|
| 0.3105 | 1.0 | 8584 | 0.2418 | 0.9176 |
| 0.2877 | 2.0 | 17168 | 0.2294 | 0.9223 |
| 0.2768 | 3.0 | 25752 | 0.2243 | 0.9240 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
Model tree for varun-v-rao/roberta-large-bn-adapter-3.17M-snli-model1
Base model
FacebookAI/roberta-large