early_fusion_sentiment_True_hate_speech_True_extra_layer_True

iTroned/early_fusion_sentiment_True_hate_speech_True_extra_layer_True

early_fusion_sentiment_True_hate_speech_True_extra_layer_True 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.

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

Downloads · 30 days

Access

Public

Updated Apr 17, 2025

Parameters

498K

37.9 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors2 MB · 99%

At a glance

Library: transformers
Access: Public
Created: Apr 17, 2025
Updated: Apr 17, 2025
SHA: e11ef910

Model card

From the Hugging Face model README

early_fusion_sentiment_True_hate_speech_True_extra_layer_True

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

Loss: 0.6361
Accuracy Offensive: 0.7458
F1 Offensive: 0.7275
Accuracy Targeted: 0.7311
F1 Targeted: 0.7067
Accuracy Stance: 0.7232
F1 Stance: 0.6711

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: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy Offensive	F1 Offensive	Accuracy Targeted	F1 Targeted	Accuracy Stance	F1 Stance
0.7872	1.0	1324	0.7659	0.6545	0.5178	0.6545	0.5178	0.7009	0.5777
0.7576	2.0	2648	0.7524	0.6545	0.5178	0.6545	0.5178	0.7009	0.5777
0.7515	3.0	3972	0.7368	0.6548	0.5186	0.6545	0.5178	0.7009	0.5777
0.7358	4.0	5296	0.7200	0.6684	0.5556	0.6545	0.5178	0.7009	0.5777
0.7182	5.0	6620	0.7027	0.6949	0.6379	0.6862	0.6297	0.7009	0.5777
0.7087	6.0	7944	0.6987	0.6934	0.6146	0.6869	0.6161	0.7009	0.5777
0.7043	7.0	9268	0.6827	0.7100	0.6623	0.6983	0.6579	0.7013	0.5787
0.6937	8.0	10592	0.6790	0.7054	0.6452	0.6979	0.6479	0.7051	0.5979
0.6806	9.0	11916	0.6864	0.6979	0.6211	0.6971	0.6345	0.7062	0.6007
0.6762	10.0	13240	0.6626	0.7266	0.6911	0.7153	0.6902	0.7122	0.6474
0.668	11.0	14564	0.6576	0.7243	0.6887	0.7183	0.6885	0.7149	0.6397
0.6688	12.0	15888	0.6569	0.7266	0.6873	0.7209	0.6856	0.7160	0.6439
0.6576	13.0	17212	0.6512	0.7458	0.7317	0.7149	0.6988	0.7092	0.6612
0.6516	14.0	18536	0.6453	0.7443	0.7262	0.7247	0.7024	0.7145	0.6631
0.655	15.0	19860	0.6410	0.7477	0.7315	0.7277	0.7066	0.7179	0.6678
0.6368	16.0	21184	0.6429	0.7390	0.7102	0.7277	0.6975	0.7236	0.6620
0.6639	17.0	22508	0.6361	0.7458	0.7275	0.7311	0.7067	0.7232	0.6711
0.6319	18.0	23832	0.6392	0.7406	0.7115	0.7266	0.6945	0.7228	0.6556
0.6341	19.0	25156	0.6364	0.7402	0.7157	0.7300	0.7008	0.7285	0.6675

Framework versions

Transformers 4.50.2
Pytorch 2.6.0+cu124
Datasets 3.0.1
Tokenizers 0.21.1

Library: transformers
Created: Apr 17, 2025
Updated: Apr 17, 2025