Shadowgraph
TrendingBuzzTop stargazers
Chrome extension
Sign in

ungjus/Fake_News_BERT_Classifier

Model

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

0

9 commits

1 linked in READMEs

updated May 30, 2023

See the code

README

Fake_News_BERT_Classifier

This model is a fine-tuned version of distilbert-base-uncased trained on a Fake News Dataset It achieves the following results on the evaluation set:

  • Loss: 0.2542

  • Accuracy: 0.9688

  • LABEL_0 = Fake news

  • LABEL_1 = Real News

Model description

More information needed

Intended uses & limitations

This model was created for the purposes of UW IMT 575 project.

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training LossEpochStepValidation LossAccuracy
0.12841.044900.14880.9582
0.122.089800.17040.9627
0.07413.0134700.19710.9674
0.02024.0179600.22650.9677
0.04655.0224500.25420.9688

Framework versions

  • Transformers 4.28.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.12.0
  • Tokenizers 0.13.3
distilbert
endpoints_compatible
generated_from_trainer
pytorch
tensorboard
text-classification
text-embeddings-inference
transformers

Similar repos

fabriceyhc/bert-base-uncased-ag_news

Model

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

0

lvwerra/distilbert-imdb

Model

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

25

Pra-tham/results

Model

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

0

pile-of-law/distilbert-base-uncased-finetuned-eoir_privacy

Model

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

5

joelito/legal-irish-roberta-base

Model

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

0

joelito/legal-polish-roberta-base

Model

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

2

gyr66/RoBERTa-ext-large-crf-chinese-finetuned-ner-v2

Model

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

1

joelito/legal-danish-roberta-base

Model

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

0

Linked in READMEs

styxsys0927/Med-MMHL

Med-MMHL dataset

15

README badge

ungjus/Fake_News_BERT_Classifier

Model

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

0

9 commits

1 linked in READMEs

updated May 30, 2023

See the code

README

Fake_News_BERT_Classifier

This model is a fine-tuned version of distilbert-base-uncased trained on a Fake News Dataset It achieves the following results on the evaluation set:

  • Loss: 0.2542

  • Accuracy: 0.9688

  • LABEL_0 = Fake news

  • LABEL_1 = Real News

Model description

More information needed

Intended uses & limitations

This model was created for the purposes of UW IMT 575 project.

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training LossEpochStepValidation LossAccuracy
0.12841.044900.14880.9582
0.122.089800.17040.9627
0.07413.0134700.19710.9674
0.02024.0179600.22650.9677
0.04655.0224500.25420.9688

Framework versions

  • Transformers 4.28.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.12.0
  • Tokenizers 0.13.3
distilbert
endpoints_compatible
generated_from_trainer
pytorch
tensorboard
text-classification
text-embeddings-inference
transformers

Similar repos

fabriceyhc/bert-base-uncased-ag_news

Model

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

0

lvwerra/distilbert-imdb

Model

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

25

Pra-tham/results

Model

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

0

pile-of-law/distilbert-base-uncased-finetuned-eoir_privacy

Model

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

5

joelito/legal-irish-roberta-base

Model

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

0

joelito/legal-polish-roberta-base

Model

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

2

gyr66/RoBERTa-ext-large-crf-chinese-finetuned-ner-v2

Model

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

1

joelito/legal-danish-roberta-base

Model

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

0

Linked in READMEs

styxsys0927/Med-MMHL

Med-MMHL dataset

15

README badge