fine-tuned-bert-base-uncased-swag
This model is a fine-tuned version of bert-base-uncased on SWAG dataset. It achieves the following results on the evaluation set:
- Loss: 0.5259
- Accuracy: 0.8134
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: 1.5e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7736 | 1.0 | 1150 | 0.5534 | 0.7911 |
| 0.5913 | 2.0 | 2300 | 0.5009 | 0.8086 |
| 0.4462 | 3.0 | 3450 | 0.5014 | 0.8122 |
| 0.3695 | 4.0 | 4600 | 0.5259 | 0.8134 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 5
Inference API (serverless) does not yet support transformers models for this pipeline type.
Model tree for amritpuhan/fine-tuned-bert-base-uncased-swag
Base model
google-bert/bert-base-uncased