metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - tweets_hate_speech_detection
metrics:
  - accuracy
  - f1
model-index:
  - name: Hate-Speech-Detection-mpnet-basev2
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: tweets_hate_speech_detection
          type: tweets_hate_speech_detection
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9749726263100266
          - name: F1
            type: f1
            value: 0.8029556650246304

Hate-Speech-Detection-mpnet-basev2

This model is a fine-tuned version of sentence-transformers/all-mpnet-base-v2 on the tweets_hate_speech_detection dataset. It achieves the following results on the evaluation set:

Loss: 0.0849
Accuracy: 0.9750
F1: 0.8030

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
0.1144	1.0	1599	0.0955	0.9693	0.7337
0.072	2.0	3198	0.0849	0.9750	0.8030
0.0458	3.0	4797	0.0841	0.9764	0.8011
0.0156	4.0	6396	0.1829	0.9689	0.7762
0.012	5.0	7995	0.1904	0.9745	0.7758
0.0157	6.0	9594	0.1622	0.9758	0.7914
0.0068	7.0	11193	0.1741	0.9736	0.8005

Framework versions

Transformers 4.26.1
Pytorch 2.0.1
Datasets 2.10.1
Tokenizers 0.13.3