metadata
base_model: Liberty-L/swag_pretrained
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Multiple_Choice_swag_lr
results: []
Multiple_Choice_swag_lr
This model is a fine-tuned version of Liberty-L/swag_pretrained on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6283
- Accuracy: 0.6483
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: 7e-05
- train_batch_size: 5
- eval_batch_size: 5
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 20
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1115 | 1.0 | 1271 | 1.0120 | 0.5954 |
| 0.7999 | 2.0 | 2542 | 1.0345 | 0.6267 |
| 0.4649 | 3.0 | 3813 | 1.2207 | 0.6428 |
| 0.2354 | 4.0 | 5084 | 1.6283 | 0.6483 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0