metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: Hate-Speech-Detection-mpnet-basev2
results: []
Hate-Speech-Detection-mpnet-basev2
This model is a fine-tuned version of sentence-transformers/all-mpnet-base-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1518
- Accuracy: 0.9809
- F1: 0.9778
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: 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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.0866 | 1.0 | 2558 | 0.0748 | 0.9778 | 0.9742 |
| 0.0634 | 2.0 | 5116 | 0.1144 | 0.9751 | 0.9704 |
| 0.031 | 3.0 | 7674 | 0.1222 | 0.9799 | 0.9765 |
| 0.0301 | 4.0 | 10232 | 0.1427 | 0.9735 | 0.9696 |
| 0.01 | 5.0 | 12790 | 0.1413 | 0.9806 | 0.9773 |
| 0.0133 | 6.0 | 15348 | 0.1543 | 0.9801 | 0.9767 |
| 0.0086 | 7.0 | 17906 | 0.1672 | 0.9798 | 0.9766 |
| 0.0059 | 8.0 | 20464 | 0.1518 | 0.9809 | 0.9778 |
| 0.002 | 9.0 | 23022 | 0.1726 | 0.9782 | 0.9747 |
| 0.0034 | 10.0 | 25580 | 0.1799 | 0.9798 | 0.9764 |
| 0.001 | 11.0 | 28138 | 0.2018 | 0.9785 | 0.9750 |
| 0.0004 | 12.0 | 30696 | 0.1957 | 0.9794 | 0.9759 |
| 0.0008 | 13.0 | 33254 | 0.2166 | 0.9788 | 0.9754 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1
- Datasets 2.10.1
- Tokenizers 0.13.3