You can deploy this model and start earning money today!

PaceKW/
distilbert-base-uncased-multilabel-indonesian-hate-speech-modified

Name: distilbert-base-uncased-multilabel-indonesian-hate-speech-modified
Availability: InStock

transformers

safetensors

generated_from_trainer

distilbert/distilbert-base-uncased

finetune

apache-2.0

endpoints_compatible

Views

No views yet

distilbert-base-uncased-multilabel-indonesian-hate-speech-modified

This model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.2353
F1: 0.7785
Roc Auc: 0.8627
Accuracy: 0.6917

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: 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: 15

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
0.2806	1.0	1317	0.2349	0.7100	0.8086	0.6188
0.2104	2.0	2634	0.2219	0.7349	0.8377	0.5968
0.1752	3.0	3951	0.2169	0.7448	0.8310	0.6682
0.1378	4.0	5268	0.2240	0.7575	0.8379	0.6743
0.1062	5.0	6585	0.2353	0.7785	0.8627	0.6917
0.0825	6.0	7902	0.2544	0.7597	0.8421	0.6902
0.0635	7.0	9219	0.2729	0.7686	0.8535	0.6910
0.0508	8.0	10536	0.2927	0.7675	0.8453	0.7024
0.0315	9.0	11853	0.3046	0.7712	0.8617	0.6834
0.0269	10.0	13170	0.3269	0.7684	0.8550	0.7016
0.019	11.0	14487	0.3464	0.7623	0.8470	0.6887
0.0162	12.0	15804	0.3564	0.7643	0.8499	0.6925
0.014	13.0	17121	0.3589	0.7680	0.8570	0.6925
0.01	14.0	18438	0.3632	0.7700	0.8588	0.6986
0.0089	15.0	19755	0.3651	0.7714	0.8577	0.6993

Framework versions

Transformers 4.51.3
Pytorch 2.7.0+cu128
Datasets 3.6.0
Tokenizers 0.21.1

PaceKW/distilbert-base-uncased-multilabel-indonesian-hate-speech-modified

distilbert-base-uncased-multilabel-indonesian-hate-speech-modified

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

PaceKW/
distilbert-base-uncased-multilabel-indonesian-hate-speech-modified