Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · bhadresh-savani

bert-base-go-emotion

bert-base-go-emotion is a text-classification model from bhadresh-savani. According to the model card, it is a Bert-Base-Uncased-Go-Emotion release with documented training and evaluation figures.

Publisher
bhadresh-savani
Task
text-classification
Model type
bert
License
apache-2.0
Library
transformers
Publication status
Approved for indexing

Model overview

bert-base-go-emotion is published by bhadresh-savani as a text-classification model. The captured configuration identifies DistilBertForMultilabelSequenceClassification with model type bert. According to the model card, it is described as Bert-Base-Uncased-Go-Emotion, and hub tags associate it with go-emotion data.

Recorded capabilities

GoEmotions classification

Hub tags record text-classification, go-emotion, and dataset go_emotions for emotion-label workflows.

Documented training run

According to the model card, the publisher reports examples, epochs, batch size, optimization steps, train loss, and evaluation accuracy and loss.

Transformers compatibility

Hub records list transformers and pytorch with endpoints compatibility for text-classification use.

Use cases in the source record

  • Emotion-label classification of English text using the record's text-classification task and GoEmotions association.
  • Reproduction or comparison of the publisher's reported training and evaluation setup documented in the model card.

Limitations and unknowns

  • No parameter count was extracted from this record.
  • No context-window value was extracted from this record.
  • Training and evaluation figures are publisher claims and were not independently verified.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: bhadresh-savani/bert-base-go-emotion

Captured: Unknown. Processed: 2026-09-07T19:34:41.442346+00:00.

Bert-Base-Uncased-Go-Emotion Model description: Training Parameters: Num examples = 169208 Num Epochs = 3 Instantaneous batch size per device = 16 Total train batch size (w. parallel, distributed & accumulation) = 16 Gradient Accumulation steps = 1 Total optimization steps = 31728 TrainOutput: 'train_loss': 0.12085497042373672, Evalution Output: 'eval_accuracy_thresh': 0.9614765048027039, 'eval_loss': 0.1164659634232521 Colab Notebook: Notebook

F001F002F003F004F005F006F007F008F009F010