metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- matthews_correlation
model-index:
- name: distilbert-base-uncased-finetuned-cola
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
config: cola
split: validation
args: cola
metrics:
- name: Matthews Correlation
type: matthews_correlation
value: 0.5347023887183993
distilbert-base-uncased-finetuned-cola
This model is a fine-tuned version of distilbert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.6320
- Matthews Correlation: 0.5347
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 |
|---|---|---|---|---|
| 0.5257 | 1.0 | 535 | 0.4682 | 0.4653 |
| 0.3475 | 2.0 | 1070 | 0.5694 | 0.4358 |
| 0.2408 | 3.0 | 1605 | 0.6320 | 0.5347 |
| 0.1615 | 4.0 | 2140 | 0.7114 | 0.5182 |
| 0.1168 | 5.0 | 2675 | 0.8500 | 0.5242 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.3
- Tokenizers 0.13.3