metadata
license: mit
base_model: microsoft/deberta-base
tags:
- generated_from_trainer
model-index:
- name: deberta-base-finetuned-wikitext2-kaggle
results: []
deberta-base-finetuned-wikitext2-kaggle
This model is a fine-tuned version of microsoft/deberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.4651
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: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.7156 | 1.0 | 1203 | 3.0922 |
| 2.9586 | 2.0 | 2406 | 2.5911 |
| 2.6402 | 3.0 | 3609 | 2.4872 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.14.1