metadata
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
metrics:
- matthews_correlation
model-index:
- name: deberta-v3-base-hyper-finetuned-cola-midterm
results: []
deberta-v3-base-hyper-finetuned-cola-midterm
This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7604
- Matthews Correlation: 0.6799
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: 8.402773307129759e-06
- train_batch_size: 4
- eval_batch_size: 16
- seed: 3
- 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 | Matthews Correlation |
|---|---|---|---|---|
| 0.4745 | 1.0 | 2138 | 0.6074 | 0.6563 |
| 0.3523 | 2.0 | 4276 | 0.7403 | 0.6752 |
| 0.2013 | 3.0 | 6414 | 0.7604 | 0.6799 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2