metadata
license: mit
base_model: MoritzLaurer/deberta-v3-large-zeroshot-v2.0
tags:
- generated_from_trainer
datasets:
- swag
metrics:
- accuracy
model-index:
- name: fine-tuned-MoritzLaurer-deberta-v3-large-zeroshot-v2.0-swag
results: []
fine-tuned-MoritzLaurer-deberta-v3-large-zeroshot-v2.0-swag
This model is a fine-tuned version of MoritzLaurer/deberta-v3-large-zeroshot-v2.0 on the swag dataset. It achieves the following results on the evaluation set:
- Loss: 0.5968
- Accuracy: 0.9142
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: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4957 | 1.0 | 4597 | 0.2545 | 0.9058 |
| 0.2768 | 2.0 | 9194 | 0.2780 | 0.9089 |
| 0.1333 | 3.0 | 13791 | 0.4016 | 0.9126 |
| 0.0599 | 4.0 | 18388 | 0.5968 | 0.9142 |
Framework versions
- Transformers 4.41.2
- Pytorch 1.11.0
- Datasets 2.19.1
- Tokenizers 0.19.1