bart-base-bn-adapter-895K-snli-model2
This model is a fine-tuned version of facebook/bart-base on the snli dataset. It achieves the following results on the evaluation set:
- Loss: 0.3775
- Accuracy: 0.8572
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: 32
- seed: 54
- 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 |
---|---|---|---|---|
0.5209 | 1.0 | 8584 | 0.4159 | 0.8383 |
0.4809 | 2.0 | 17168 | 0.3858 | 0.8534 |
0.473 | 3.0 | 25752 | 0.3775 | 0.8572 |
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/bart-base-bn-adapter-895K-snli-model2
Base model
facebook/bart-base