---
library_name: transformers
license: apache-2.0
base_model: google/bert_uncased_L-4_H-512_A-8
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert_uncased_L-4_H-512_A-8_mnli
  results: []
---

<!-- 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_mnli

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 an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7132
- Accuracy: 0.7763

## 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 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.7086        | 1.0   | 1534  | 0.6315          | 0.7438   |
| 0.5704        | 2.0   | 3068  | 0.5782          | 0.7652   |
| 0.4967        | 3.0   | 4602  | 0.5685          | 0.7793   |
| 0.4356        | 4.0   | 6136  | 0.5847          | 0.7822   |
| 0.3809        | 5.0   | 7670  | 0.6004          | 0.7855   |
| 0.3341        | 6.0   | 9204  | 0.6375          | 0.7837   |
| 0.2922        | 7.0   | 10738 | 0.6666          | 0.7808   |
| 0.2565        | 8.0   | 12272 | 0.7132          | 0.7763   |


### Framework versions

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