metadata
license: mit
base_model: microsoft/deberta-v3-large
tags:
- generated_from_trainer
metrics:
- matthews_correlation
model-index:
- name: deberta-v3-large-finetuned-cola-midterm
results: []
deberta-v3-large-finetuned-cola-midterm
This model is a fine-tuned version of microsoft/deberta-v3-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6555
- Matthews Correlation: 0.7173
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 | Matthews Correlation |
|---|---|---|---|---|
| 0.3739 | 1.0 | 535 | 0.3250 | 0.7041 |
| 0.2223 | 2.0 | 1070 | 0.4253 | 0.6893 |
| 0.1459 | 3.0 | 1605 | 0.5346 | 0.7065 |
| 0.0878 | 4.0 | 2140 | 0.6422 | 0.7112 |
| 0.0466 | 5.0 | 2675 | 0.6555 | 0.7173 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2