bert-base-uncased-finetuned-cola_HW2_sepehr_bakhshi_dropout_05_16
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: 0.7283
- Matthews Correlation: 0.5905
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: 1.0356344528514278e-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 |
|---|---|---|---|---|
| 0.5012 | 1.0 | 535 | 0.4807 | 0.4912 |
| 0.3376 | 2.0 | 1070 | 0.4363 | 0.5882 |
| 0.2395 | 3.0 | 1605 | 0.6192 | 0.5351 |
| 0.1814 | 4.0 | 2140 | 0.6754 | 0.5931 |
| 0.1554 | 5.0 | 2675 | 0.7283 | 0.5905 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 5
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Dataset used to train sepehrbakhshi/bert-base-uncased-finetuned-cola_HW2_sepehr_bakhshi_dropout_05_16
Evaluation results
- Matthews Correlation on gluevalidation set self-reported0.591