---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: bert-finetuned-toxic
  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-finetuned-toxic

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: 0.3207
- F1: 0.7032
- Roc Auc: 0.9143
- Accuracy: 0.9069

## 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: 256
- eval_batch_size: 256
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
| No log        | 1.0   | 499  | 0.1740          | 0.5646 | 0.9544  | 0.8619   |
| 0.2962        | 2.0   | 998  | 0.1595          | 0.5994 | 0.9551  | 0.8691   |
| 0.1545        | 3.0   | 1497 | 0.1715          | 0.6322 | 0.9509  | 0.8776   |
| 0.1218        | 4.0   | 1996 | 0.1883          | 0.6412 | 0.9467  | 0.8870   |
| 0.0976        | 5.0   | 2495 | 0.2497          | 0.6808 | 0.9265  | 0.9037   |
| 0.0807        | 6.0   | 2994 | 0.2411          | 0.6742 | 0.9331  | 0.8917   |
| 0.0682        | 7.0   | 3493 | 0.2955          | 0.6922 | 0.9183  | 0.8995   |
| 0.0597        | 8.0   | 3992 | 0.3207          | 0.7032 | 0.9143  | 0.9069   |
| 0.0533        | 9.0   | 4491 | 0.3207          | 0.6977 | 0.9158  | 0.9044   |
| 0.0487        | 10.0  | 4990 | 0.3407          | 0.7028 | 0.9091  | 0.9073   |


### Framework versions

- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1