metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- matthews_correlation
model-index:
- name: bert-base-uncased-finetuned-cola
results: []
bert-base-uncased-finetuned-cola
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9759
- Matthews Correlation: 0.4561
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: 3.3551737277474504e-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 26
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| No log | 1.0 | 54 | 0.8857 | 0.4395 |
| No log | 2.0 | 108 | 0.9560 | 0.4472 |
| No log | 3.0 | 162 | 0.9759 | 0.4561 |
| No log | 4.0 | 216 | 0.9886 | 0.4561 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2