metadata
library_name: transformers
license: mit
base_model: microsoft/deberta-large-mnli
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: roberta-classifier_batch32
results: []
roberta-classifier_batch32
This model is a fine-tuned version of microsoft/deberta-large-mnli on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1474
- Accuracy: 0.941
- Auc: 0.988
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: 0.0002
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc |
|---|---|---|---|---|---|
| 0.2918 | 1.0 | 161 | 0.2840 | 0.889 | 0.976 |
| 0.2151 | 2.0 | 322 | 0.1792 | 0.923 | 0.984 |
| 0.193 | 3.0 | 483 | 0.1571 | 0.938 | 0.986 |
| 0.1756 | 4.0 | 644 | 0.1434 | 0.943 | 0.988 |
| 0.1623 | 5.0 | 805 | 0.1474 | 0.941 | 0.988 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1