metadata
license: apache-2.0
base_model: google-bert/bert-base-uncased
tags:
- generated_from_trainer
datasets:
- swag
metrics:
- accuracy
model-index:
- name: my_awesome_swag_model
results: []
my_awesome_swag_model
This model is a fine-tuned version of google-bert/bert-base-uncased on the swag dataset. It achieves the following results on the evaluation set:
- Loss: 0.7748
- Accuracy: 0.8005
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: 32
- eval_batch_size: 32
- seed: 42
- 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 |
|---|---|---|---|---|
| 0.7515 | 1.0 | 2299 | 0.5735 | 0.7783 |
| 0.3807 | 2.0 | 4598 | 0.5881 | 0.7972 |
| 0.1533 | 3.0 | 6897 | 0.7748 | 0.8005 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2