new_hate_speech_test_8_90_mask

iTroned/new_hate_speech_test_8_90_mask

new_hate_speech_test_8_90_mask is a machine learning model from iTroned. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

Access

Public

Updated Apr 2, 2025

Parameters

186K

21.7 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors746 KB · 99%

At a glance

Library: transformers
License: apache-2.0
Access: Public
Created: Apr 2, 2025
Updated: Apr 2, 2025
SHA: cfdc457b

Base models

Model card

From the Hugging Face model README

new_hate_speech_test_8_90_mask

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.2393
Accuracy Offensive: 0.8965
F1 Offensive: 0.8912
Accuracy Targeted: 0.9505
F1 Targeted: 0.9281
Accuracy Stance: 0.8961
F1 Stance: 0.8635

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: 1e-05
train_batch_size: 8
eval_batch_size: 8
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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy Offensive	F1 Offensive	Accuracy Targeted	F1 Targeted	Accuracy Stance	F1 Stance
0.7444	1.0	1324	0.7296	0.6545	0.5178	0.6545	0.5178	0.7009	0.5777
0.6033	2.0	2648	0.5197	0.7262	0.6601	0.8252	0.7951	0.7953	0.7379
0.461	3.0	3972	0.3746	0.7980	0.7697	0.9290	0.9070	0.8807	0.8353
0.358	4.0	5296	0.3122	0.8410	0.8259	0.9464	0.9240	0.8882	0.8445
0.3119	5.0	6620	0.2804	0.8754	0.8671	0.9502	0.9277	0.8886	0.8454
0.2888	6.0	7944	0.2653	0.8693	0.8600	0.9494	0.9270	0.8920	0.8522
0.2754	7.0	9268	0.2532	0.8818	0.8745	0.9502	0.9277	0.8954	0.8619
0.2624	8.0	10592	0.2452	0.8897	0.8835	0.9505	0.9281	0.8950	0.8608
0.26	9.0	11916	0.2409	0.8958	0.8904	0.9505	0.9281	0.8958	0.8623
0.2491	10.0	13240	0.2393	0.8965	0.8912	0.9505	0.9281	0.8961	0.8635

Framework versions

Transformers 4.50.2
Pytorch 2.6.0+cu124
Datasets 3.0.1
Tokenizers 0.21.1

Library: transformers
License: apache-2.0
Created: Apr 2, 2025
Updated: Apr 2, 2025