distilbert-fake-news-detector – AI Model by wildgeese25 | AlphaNeural AI

You can deploy this model and start earning money today!

wildgeese25/
distilbert-fake-news-detector

like

0

text-classification

generated_from_trainer

distilbert/distilbert-base-uncased

autotrain_compatible

endpoints_compatible

Views

No views yet

distilbert-fake-news-detector-TEST2

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

Loss: 0.2002
Accuracy: 0.9458
Precision: 0.9462
Recall: 0.9491
F1: 0.9477
Confusion Matrix: [[18318, 1124], [1059, 19759]]

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: 4e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 128
optimizer: Use 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: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Confusion Matrix
0.196	1.0	661	0.2187	0.9369	0.9263	0.9533	0.9396	[[4187, 367], [226, 4614]]
0.2123	2.0	1322	0.2012	0.9459	0.9435	0.9521	0.9478	[[4278, 276], [232, 4608]]
0.1429	3.0	1983	0.2020	0.9457	0.9447	0.9502	0.9475	[[4285, 269], [241, 4599]]
0.1636	3.9947	2640	0.2055	0.9449	0.9470	0.9459	0.9465	[[4298, 256], [262, 4578]]

Framework versions

Transformers 4.51.3
Pytorch 2.5.1
Datasets 3.5.0
Tokenizers 0.21.1