bert-base-uncased-finetuned-cola-batch-64
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: 0.7651
- Matthews Correlation: 0.5836
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: 64
- eval_batch_size: 64
- 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 | 134 | 0.4344 | 0.5367 |
No log | 2.0 | 268 | 0.4313 | 0.5650 |
No log | 3.0 | 402 | 0.5034 | 0.5495 |
0.3177 | 4.0 | 536 | 0.5733 | 0.5293 |
0.3177 | 5.0 | 670 | 0.6364 | 0.5498 |
0.3177 | 6.0 | 804 | 0.7316 | 0.5600 |
0.3177 | 7.0 | 938 | 0.7651 | 0.5836 |
0.0846 | 8.0 | 1072 | 0.8575 | 0.5625 |
0.0846 | 9.0 | 1206 | 0.8820 | 0.5573 |
0.0846 | 10.0 | 1340 | 0.8854 | 0.5704 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 13
Dataset used to train cansurav/bert-base-uncased-finetuned-cola-batch-64
Evaluation results
- Matthews Correlation on gluevalidation set self-reported0.584