---
library_name: transformers
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: wk3ex_bert_imdb_sentiment
  results: []
datasets:
Kaggle imdb dataseg

# wk3ex_bert_imdb_sentiment

This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2804
- Accuracy: 0.9201
- Precision: 0.9201
- Recall: 0.9201
- F1: 0.9201

## Model description

Exercise for University course. Finetuning for sentiment analysis with imdb Kaggle dataset

## Intended uses & limitations

Sentiment analysis

## Training and evaluation data

finetuning with imdb dataset

## Training procedure

2 epochs

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.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: 2

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| 0.2405        | 1.0   | 2500 | 0.2392          | 0.9093   | 0.9107    | 0.9093 | 0.9092 |
| 0.1183        | 2.0   | 5000 | 0.2804          | 0.9201   | 0.9201    | 0.9201 | 0.9201 |


### Framework versions

- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0