metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: distilbert/distilbert-base-uncased
datasets:
- swag
metrics:
- accuracy
model-index:
- name: fine-tuned-distilbert-base-uncased-swag-peft
results: []
fine-tuned-distilbert-base-uncased-swag-peft
This model is a fine-tuned version of distilbert/distilbert-base-uncased on the swag dataset. It achieves the following results on the evaluation set:
- Loss: 0.7733
- Accuracy: 0.6858
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0103 | 1.0 | 4597 | 0.8978 | 0.6370 |
| 0.9591 | 2.0 | 9194 | 0.8498 | 0.6568 |
| 0.9401 | 3.0 | 13791 | 0.8270 | 0.6626 |
| 0.9265 | 4.0 | 18388 | 0.8105 | 0.6713 |
| 0.9202 | 5.0 | 22985 | 0.8001 | 0.6759 |
| 0.8921 | 6.0 | 27582 | 0.7894 | 0.6790 |
| 0.894 | 7.0 | 32179 | 0.7836 | 0.6823 |
| 0.8695 | 8.0 | 36776 | 0.7803 | 0.6835 |
| 0.8684 | 9.0 | 41373 | 0.7753 | 0.6845 |
| 0.8696 | 10.0 | 45970 | 0.7733 | 0.6858 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1