---
library_name: transformers
language:
- en
license: apache-2.0
base_model: google/bert_uncased_L-4_H-256_A-4
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert_uncased_L-4_H-256_A-4_mrpc
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE MRPC
      type: glue
      args: mrpc
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.7720588235294118
    - name: F1
      type: f1
      value: 0.8393782383419689
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# bert_uncased_L-4_H-256_A-4_mrpc

This model is a fine-tuned version of [google/bert_uncased_L-4_H-256_A-4](https://huggingface.co/google/bert_uncased_L-4_H-256_A-4) on the GLUE MRPC dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5071
- Accuracy: 0.7721
- F1: 0.8394
- Combined Score: 0.8057

## 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: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Combined Score |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
| 0.6375        | 1.0   | 15   | 0.6024          | 0.6936   | 0.8170 | 0.7553         |
| 0.594         | 2.0   | 30   | 0.5776          | 0.6985   | 0.8167 | 0.7576         |
| 0.5504        | 3.0   | 45   | 0.5475          | 0.7279   | 0.8274 | 0.7777         |
| 0.5155        | 4.0   | 60   | 0.5083          | 0.7598   | 0.8345 | 0.7971         |
| 0.4668        | 5.0   | 75   | 0.5116          | 0.7598   | 0.8345 | 0.7971         |
| 0.4292        | 6.0   | 90   | 0.5237          | 0.7696   | 0.8433 | 0.8065         |
| 0.3859        | 7.0   | 105  | 0.5071          | 0.7721   | 0.8394 | 0.8057         |
| 0.3455        | 8.0   | 120  | 0.5300          | 0.7721   | 0.8426 | 0.8073         |
| 0.3049        | 9.0   | 135  | 0.5408          | 0.7721   | 0.8410 | 0.8065         |
| 0.2735        | 10.0  | 150  | 0.5337          | 0.7745   | 0.8425 | 0.8085         |
| 0.2454        | 11.0  | 165  | 0.5962          | 0.7647   | 0.84   | 0.8024         |
| 0.2117        | 12.0  | 180  | 0.5756          | 0.7794   | 0.8469 | 0.8132         |


### Framework versions

- Transformers 4.46.3
- Pytorch 2.2.1+cu118
- Datasets 2.17.0
- Tokenizers 0.20.3