---
library_name: transformers
language:
- en
license: apache-2.0
base_model: google/bert_uncased_L-4_H-512_A-8
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: bert_uncased_L-4_H-512_A-8_qnli
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE QNLI
      type: glue
      args: qnli
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.8735127219476478
---

<!-- 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-512_A-8_qnli

This model is a fine-tuned version of [google/bert_uncased_L-4_H-512_A-8](https://huggingface.co/google/bert_uncased_L-4_H-512_A-8) on the GLUE QNLI dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3148
- Accuracy: 0.8735

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.437         | 1.0   | 410  | 0.3448          | 0.8521   |
| 0.3392        | 2.0   | 820  | 0.3215          | 0.8607   |
| 0.2746        | 3.0   | 1230 | 0.3148          | 0.8735   |
| 0.2175        | 4.0   | 1640 | 0.3549          | 0.8702   |
| 0.1712        | 5.0   | 2050 | 0.4000          | 0.8580   |
| 0.1311        | 6.0   | 2460 | 0.4335          | 0.8649   |
| 0.1065        | 7.0   | 2870 | 0.4819          | 0.8642   |
| 0.0849        | 8.0   | 3280 | 0.5127          | 0.8667   |


### Framework versions

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