metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- matthews_correlation
model-index:
- name: bert-base-uncased-finetuned-cola-batch-32
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: 0.5927736326773501
bert-base-uncased-finetuned-cola-batch-32
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: 0.8835
- Matthews Correlation: 0.5928
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| No log | 1.0 | 268 | 0.5093 | 0.5049 |
| 0.4202 | 2.0 | 536 | 0.4633 | 0.5600 |
| 0.4202 | 3.0 | 804 | 0.5369 | 0.5393 |
| 0.1814 | 4.0 | 1072 | 0.6271 | 0.5605 |
| 0.1814 | 5.0 | 1340 | 0.7427 | 0.5662 |
| 0.0947 | 6.0 | 1608 | 0.7794 | 0.5697 |
| 0.0947 | 7.0 | 1876 | 0.8835 | 0.5928 |
| 0.0566 | 8.0 | 2144 | 1.0182 | 0.5751 |
| 0.0566 | 9.0 | 2412 | 1.1300 | 0.5549 |
| 0.0296 | 10.0 | 2680 | 1.1266 | 0.5704 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3