metadata
language:
- en
license: mit
base_model: microsoft/deberta-v3-large
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- matthews_correlation
model-index:
- name: output
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE COLA
type: glue
config: cola
split: validation
args: cola
metrics:
- name: Matthews Correlation
type: matthews_correlation
value: 0.7060783174788182
output
This model is a fine-tuned version of microsoft/deberta-v3-large on the GLUE COLA dataset. It achieves the following results on the evaluation set:
- Loss: 0.3123
- Matthews Correlation: 0.7061
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: 1e-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: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.3546 | 1.0 | 535 | 0.3123 | 0.7061 |
| 0.2078 | 2.0 | 1070 | 0.3618 | 0.7311 |
| 0.1313 | 3.0 | 1605 | 0.5145 | 0.7160 |
| 0.087 | 4.0 | 2140 | 0.5819 | 0.7230 |
| 0.0597 | 5.0 | 2675 | 0.6325 | 0.7397 |
| 0.0435 | 6.0 | 3210 | 0.6152 | 0.7332 |
| 0.0268 | 7.0 | 3745 | 0.7296 | 0.7327 |
| 0.0304 | 8.0 | 4280 | 0.7672 | 0.7287 |
| 0.015 | 9.0 | 4815 | 0.8067 | 0.7264 |
| 0.0133 | 10.0 | 5350 | 0.8079 | 0.7246 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.15.0