metadata
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: MoritzLaurer/deberta-v3-large-zeroshot-v2.0
metrics:
- accuracy
model-index:
- name: fine-tuned-MoritzLaurer-deberta-v3-large-zeroshot-v2.0-swag-peft
results: []
datasets:
- allenai/swag
fine-tuned-MoritzLaurer-deberta-v3-large-zeroshot-v2.0-swag-peft
This model is a fine-tuned version of MoritzLaurer/deberta-v3-large-zeroshot-v2.0 on SWAG dataset. It achieves the following results on the evaluation set:
- Loss: 0.2169
- Accuracy: 0.9193
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: 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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5756 | 1.0 | 4597 | 0.2941 | 0.8993 |
| 0.5186 | 2.0 | 9194 | 0.2538 | 0.9115 |
| 0.5139 | 3.0 | 13791 | 0.2399 | 0.9136 |
| 0.4933 | 4.0 | 18388 | 0.2282 | 0.9158 |
| 0.4786 | 5.0 | 22985 | 0.2278 | 0.9165 |
| 0.4657 | 6.0 | 27582 | 0.2215 | 0.9182 |
| 0.4685 | 7.0 | 32179 | 0.2199 | 0.9189 |
| 0.4631 | 8.0 | 36776 | 0.2188 | 0.9188 |
| 0.4629 | 9.0 | 41373 | 0.2186 | 0.9188 |
| 0.4556 | 10.0 | 45970 | 0.2169 | 0.9193 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1