nli-finetune-model
This model is a fine-tuned version of bert-large-uncased on the multi_nli dataset. It achieves the following results on the evaluation set:
- Loss: 1.2551
- Accuracy: 0.7793
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6813 | 1.0 | 2500 | 0.6655 | 0.7657 |
| 0.5632 | 2.0 | 5000 | 1.0409 | 0.778 |
| 0.3753 | 3.0 | 7500 | 1.2551 | 0.7793 |
Framework versions
- Transformers 4.28.0
- Pytorch 1.13.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3