metadata
license: mit
base_model: tgsc/debertina-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: debertina-base-finetuned-deberta
results: []
debertina-base-finetuned-deberta
This model is a fine-tuned version of tgsc/debertina-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3760
- Accuracy: 0.8760
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 442 | 0.3181 | 0.8708 |
| 0.5097 | 2.0 | 884 | 0.3760 | 0.8760 |
| 0.2858 | 3.0 | 1326 | 0.5142 | 0.8656 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1