---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert_multiple_choice
  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_multiple_choice

This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3676
- Accuracy: 0.45

## 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-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log        | 1.0   | 12   | 1.6011          | 0.2      |
| No log        | 2.0   | 24   | 1.6026          | 0.2      |
| No log        | 3.0   | 36   | 1.5957          | 0.3      |
| No log        | 4.0   | 48   | 1.5885          | 0.35     |
| No log        | 5.0   | 60   | 1.5782          | 0.4      |
| No log        | 6.0   | 72   | 1.5609          | 0.45     |
| No log        | 7.0   | 84   | 1.5448          | 0.45     |
| No log        | 8.0   | 96   | 1.5432          | 0.45     |
| No log        | 9.0   | 108  | 1.5166          | 0.5      |
| No log        | 10.0  | 120  | 1.5045          | 0.5      |
| No log        | 11.0  | 132  | 1.5056          | 0.5      |
| No log        | 12.0  | 144  | 1.5011          | 0.5      |
| No log        | 13.0  | 156  | 1.5010          | 0.4      |
| No log        | 14.0  | 168  | 1.4879          | 0.4      |
| No log        | 15.0  | 180  | 1.4721          | 0.5      |
| No log        | 16.0  | 192  | 1.4582          | 0.45     |
| No log        | 17.0  | 204  | 1.4659          | 0.5      |
| No log        | 18.0  | 216  | 1.4445          | 0.4      |
| No log        | 19.0  | 228  | 1.4404          | 0.45     |
| No log        | 20.0  | 240  | 1.4322          | 0.45     |
| No log        | 21.0  | 252  | 1.4284          | 0.4      |
| No log        | 22.0  | 264  | 1.4045          | 0.45     |
| No log        | 23.0  | 276  | 1.3910          | 0.5      |
| No log        | 24.0  | 288  | 1.4120          | 0.45     |
| No log        | 25.0  | 300  | 1.3679          | 0.5      |
| No log        | 26.0  | 312  | 1.3662          | 0.5      |
| No log        | 27.0  | 324  | 1.3865          | 0.55     |
| No log        | 28.0  | 336  | 1.4005          | 0.5      |
| No log        | 29.0  | 348  | 1.3866          | 0.45     |
| No log        | 30.0  | 360  | 1.3676          | 0.45     |


### Framework versions

- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3