Shadowgraph
TrendingBuzzTop stargazers
Chrome extension
Sign in

nickmuchi/finbert-tone-finetuned-fintwitter-classification

Model

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

13

28 commits

1 linked in READMEs

updated Mar 19, 2023

See the code

README

finbert-tone-finetuned-fintwitter-classification

This model is a fine-tuned version of yiyanghkust/finbert-tone on Twitter Financial News dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4078
  • Accuracy: 0.8840
  • F1: 0.8838
  • Precision: 0.8838
  • Recall: 0.8840

Model description

Model determines the financial sentiment of given tweets. Given the unbalanced distribution of the class labels, the weights were adjusted to pay attention to the less sampled labels which should increase overall performance..

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 20
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossAccuracyF1PrecisionRecall
0.63851.05970.36880.86680.86930.87440.8668
0.30442.011940.39940.87440.87260.87390.8744
0.18333.017910.62120.87810.87640.87620.8781
0.11894.023880.83700.87400.87430.87480.8740
0.07595.029850.91070.88070.87980.87960.8807
0.02916.035820.97110.88360.88250.88210.8836
0.03147.041791.13050.88190.88110.88120.8819
0.02178.047761.01900.88110.88130.88160.8811
0.02279.053731.19400.88440.88320.88380.8844
0.015610.059701.25950.87520.87680.88010.8752
0.013511.065671.19310.87600.87680.87800.8760
0.00912.071641.21540.88570.88520.88480.8857
0.005813.077611.38740.87480.87590.87760.8748
0.00914.083581.41930.87400.87540.87800.8740
0.004215.089551.29990.88070.88000.87960.8807
0.002816.095521.34280.88020.88050.88170.8802
0.002917.0101491.39590.88070.88070.88100.8807
0.002218.0107461.41490.88270.88230.88240.8827
0.003719.0113431.40780.88400.88380.88380.8840
0.00120.0119401.42360.88230.88230.88250.8823

Framework versions

  • Transformers 4.25.1
  • Pytorch 1.13.0+cu116
  • Datasets 2.8.0
  • Tokenizers 0.13.2
bert
endpoints_compatible
financial
financial-tweets-sentiment-analysis
generated_from_trainer
model-index
pytorch
safetensors
sentiment
sentiment-analysis
stocks
tensorboard
text-classification
text-embeddings-inference
transformers

Similar repos

tabularisai/ModernFinBERT

Model

ModernFinBERT

13

FFZG-cleopatra/M2SA-text-only

Model

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

0

kenhktsui/setfit_test_twitter_news

Model

SetFit with sentence-transformers/paraphrase-mpnet-base-v2

0

cardiffnlp/twitter-roberta-base-2021-124m-sentiment

Model

cardiffnlp/twitter-roberta-base-2021-124m-sentiment

0

ProsusAI/finbert

Model

FinBERT is a pre-trained NLP model to analyze sentiment of financial text. It is built by further…

1,277

FFZG-cleopatra/M2SA

Model

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

1

cardiffnlp/twitter-roberta-base-2021-124m-emotion

Model

cardiffnlp/twitter-roberta-base-2021-124m-emotion

0

ungjus/Fake_News_BERT_Classifier

Model

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

0

Linked in READMEs

kenhktsui/anyclassifier

One Line To Build Zero-Data Classifiers in Minutes

64

README badge

nickmuchi/finbert-tone-finetuned-fintwitter-classification

Model

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

13

28 commits

1 linked in READMEs

updated Mar 19, 2023

See the code

README

finbert-tone-finetuned-fintwitter-classification

This model is a fine-tuned version of yiyanghkust/finbert-tone on Twitter Financial News dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4078
  • Accuracy: 0.8840
  • F1: 0.8838
  • Precision: 0.8838
  • Recall: 0.8840

Model description

Model determines the financial sentiment of given tweets. Given the unbalanced distribution of the class labels, the weights were adjusted to pay attention to the less sampled labels which should increase overall performance..

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 20
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossAccuracyF1PrecisionRecall
0.63851.05970.36880.86680.86930.87440.8668
0.30442.011940.39940.87440.87260.87390.8744
0.18333.017910.62120.87810.87640.87620.8781
0.11894.023880.83700.87400.87430.87480.8740
0.07595.029850.91070.88070.87980.87960.8807
0.02916.035820.97110.88360.88250.88210.8836
0.03147.041791.13050.88190.88110.88120.8819
0.02178.047761.01900.88110.88130.88160.8811
0.02279.053731.19400.88440.88320.88380.8844
0.015610.059701.25950.87520.87680.88010.8752
0.013511.065671.19310.87600.87680.87800.8760
0.00912.071641.21540.88570.88520.88480.8857
0.005813.077611.38740.87480.87590.87760.8748
0.00914.083581.41930.87400.87540.87800.8740
0.004215.089551.29990.88070.88000.87960.8807
0.002816.095521.34280.88020.88050.88170.8802
0.002917.0101491.39590.88070.88070.88100.8807
0.002218.0107461.41490.88270.88230.88240.8827
0.003719.0113431.40780.88400.88380.88380.8840
0.00120.0119401.42360.88230.88230.88250.8823

Framework versions

  • Transformers 4.25.1
  • Pytorch 1.13.0+cu116
  • Datasets 2.8.0
  • Tokenizers 0.13.2
bert
endpoints_compatible
financial
financial-tweets-sentiment-analysis
generated_from_trainer
model-index
pytorch
safetensors
sentiment
sentiment-analysis
stocks
tensorboard
text-classification
text-embeddings-inference
transformers

Similar repos

tabularisai/ModernFinBERT

Model

ModernFinBERT

13

FFZG-cleopatra/M2SA-text-only

Model

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

0

kenhktsui/setfit_test_twitter_news

Model

SetFit with sentence-transformers/paraphrase-mpnet-base-v2

0

cardiffnlp/twitter-roberta-base-2021-124m-sentiment

Model

cardiffnlp/twitter-roberta-base-2021-124m-sentiment

0

ProsusAI/finbert

Model

FinBERT is a pre-trained NLP model to analyze sentiment of financial text. It is built by further…

1,277

FFZG-cleopatra/M2SA

Model

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

1

cardiffnlp/twitter-roberta-base-2021-124m-emotion

Model

cardiffnlp/twitter-roberta-base-2021-124m-emotion

0

ungjus/Fake_News_BERT_Classifier

Model

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

0

Linked in READMEs

kenhktsui/anyclassifier

One Line To Build Zero-Data Classifiers in Minutes

64

README badge