---
library_name: transformers
language:
- en
license: apache-2.0
base_model: google-bert/bert-base-uncased
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: bert-base-uncased_mnli
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE MNLI
      type: glue
      args: mnli
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.8429617575264443
---

<!-- 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-base-uncased_mnli

This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the GLUE MNLI dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4225
- Accuracy: 0.8430

## 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 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.5389        | 1.0   | 1534  | 0.4533          | 0.8247   |
| 0.3569        | 2.0   | 3068  | 0.4376          | 0.8365   |
| 0.2471        | 3.0   | 4602  | 0.4777          | 0.8365   |
| 0.1699        | 4.0   | 6136  | 0.5418          | 0.8380   |
| 0.1239        | 5.0   | 7670  | 0.6041          | 0.8287   |
| 0.095         | 6.0   | 9204  | 0.6809          | 0.8275   |
| 0.0784        | 7.0   | 10738 | 0.7138          | 0.8342   |


### Framework versions

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