---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: IMDB-Bert-CLSModel
  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. -->

# IMDB-Bert-CLSModel

This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2234
- Accuracy: 0.9404
- F1: 0.9404
- Precision: 0.9405
- Recall: 0.9404

## 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: 2e-05
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 3

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 0.3131        | 0.6394 | 500  | 0.1899          | 0.9253   | 0.9252 | 0.9265    | 0.9252 |
| 0.174         | 1.2788 | 1000 | 0.2016          | 0.9373   | 0.9373 | 0.9373    | 0.9373 |
| 0.1268        | 1.9182 | 1500 | 0.1880          | 0.9408   | 0.9408 | 0.9411    | 0.9408 |
| 0.0807        | 2.5575 | 2000 | 0.2234          | 0.9404   | 0.9404 | 0.9405    | 0.9404 |


### Framework versions

- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1