metadata
license: apache-2.0
base_model: bert-base-cased
tags:
- generated_from_trainer
metrics:
- matthews_correlation
model-index:
- name: test-bert-finetuned-cola
results: []
datasets:
- glue
test-bert-finetuned-cola
This model is a fine-tuned version of bert-base-cased on the glue/cola dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7912
- Matthews Correlation: 0.5700
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: 8
- eval_batch_size: 8
- seed: 42
- 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 |
|---|---|---|---|---|
| 0.4544 | 1.0 | 1069 | 0.4632 | 0.4992 |
| 0.3314 | 2.0 | 2138 | 0.5560 | 0.5731 |
| 0.1905 | 3.0 | 3207 | 0.7912 | 0.5700 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.1