early_fusion_sentiment_True_hate_speech_False_extra_layer_False

iTroned/early_fusion_sentiment_True_hate_speech_False_extra_layer_False

early_fusion_sentiment_True_hate_speech_False_extra_layer_False 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

482K

36.7 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.9 MB · 99%

At a glance

Library: transformers
Access: Public
Created: Apr 17, 2025
Updated: Apr 17, 2025
SHA: 4ca3406a

Model card

From the Hugging Face model README

early_fusion_sentiment_True_hate_speech_False_extra_layer_False

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

Loss: 0.5078
Accuracy Offensive: 0.8187
F1 Offensive: 0.8084
Accuracy Targeted: 0.8187
F1 Targeted: 0.7972
Accuracy Stance: 0.7798
F1 Stance: 0.7353

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
0.7749	1.0	1324	0.7476	0.6545	0.5178	0.6545	0.5178	0.7009	0.5777
0.7179	2.0	2648	0.7035	0.6911	0.6029	0.6609	0.5326	0.7009	0.5777
0.6854	3.0	3972	0.6557	0.7232	0.6740	0.7251	0.6828	0.7028	0.5836
0.6539	4.0	5296	0.6435	0.7130	0.6442	0.7270	0.6749	0.7209	0.6329
0.637	5.0	6620	0.6033	0.7504	0.7128	0.7613	0.7312	0.7413	0.6786
0.6257	6.0	7944	0.6013	0.7436	0.6972	0.7621	0.7284	0.7440	0.6805
0.612	7.0	9268	0.5766	0.7825	0.7650	0.7851	0.7666	0.7489	0.7088
0.6053	8.0	10592	0.5653	0.7840	0.7610	0.7908	0.7662	0.7647	0.7166
0.5894	9.0	11916	0.5526	0.7723	0.7416	0.7987	0.7721	0.7632	0.7114
0.5787	10.0	13240	0.5415	0.8059	0.7932	0.8017	0.7807	0.7715	0.7266
0.58	11.0	14564	0.5382	0.7946	0.7746	0.8044	0.7836	0.7742	0.7290
0.5828	12.0	15888	0.5302	0.7953	0.7759	0.8100	0.7859	0.7696	0.7196
0.5656	13.0	17212	0.5292	0.8176	0.8086	0.8070	0.7894	0.7768	0.7380
0.5602	14.0	18536	0.5215	0.8078	0.7932	0.8100	0.7888	0.7753	0.7321
0.5623	15.0	19860	0.5133	0.8206	0.8112	0.8138	0.7940	0.7787	0.7370
0.5465	16.0	21184	0.5286	0.8044	0.7873	0.8093	0.7842	0.7772	0.7276
0.5624	17.0	22508	0.5027	0.8312	0.8222	0.8206	0.7992	0.7881	0.7426
0.5416	18.0	23832	0.5235	0.8063	0.7896	0.8066	0.7815	0.7783	0.7285
0.5442	19.0	25156	0.5141	0.8142	0.8001	0.8089	0.7841	0.7825	0.7306

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