metadata
license: mit
base_model: microsoft/deberta-v3-small
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: deberta-v3-small-finetuned-mnli
results: []
deberta-v3-small-finetuned-mnli
This model is a fine-tuned version of microsoft/deberta-v3-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6370
- Accuracy: 0.8776
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: 2e-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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3771 | 1.0 | 24544 | 0.3509 | 0.8689 |
| 0.2918 | 2.0 | 49088 | 0.3752 | 0.8720 |
| 0.2278 | 3.0 | 73632 | 0.4424 | 0.8756 |
| 0.1727 | 4.0 | 98176 | 0.5483 | 0.8768 |
| 0.1413 | 5.0 | 122720 | 0.6370 | 0.8776 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2