metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- matthews_correlation
model-index:
- name: bert-base-uncased-finetuned-cola
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: glue
type: glue
args: cola
metrics:
- name: Matthews Correlation
type: matthews_correlation
value: 0.5864941797290588
bert-base-uncased-finetuned-cola
This model is a fine-tuned version of bert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.8385
- Matthews Correlation: 0.5865
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 |
|---|---|---|---|---|
| 0.4887 | 1.0 | 535 | 0.5016 | 0.5107 |
| 0.286 | 2.0 | 1070 | 0.5473 | 0.5399 |
| 0.1864 | 3.0 | 1605 | 0.7114 | 0.5706 |
| 0.1163 | 4.0 | 2140 | 0.8385 | 0.5865 |
| 0.0834 | 5.0 | 2675 | 0.9610 | 0.5786 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.0+cu111
- Datasets 1.18.3
- Tokenizers 0.11.0