metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- matthews_correlation
model-index:
- name: bert-finetuned-mrpc
results: []
datasets:
- glue
language:
- en
bert-finetuned-mrpc
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: 1.1927
- Matthews Correlation: 0.4810
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
glue cola dataset
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-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: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|---|---|---|---|---|
| 0.2742 | 1.0 | 1069 | 0.8391 | 0.4810 |
| 0.2018 | 2.0 | 2138 | 1.0347 | 0.4674 |
| 0.0966 | 3.0 | 3207 | 1.1927 | 0.4810 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1