neel-jotaniya's picture
Update README.md
5c9ddfc
metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - emotion
metrics:
  - accuracy
  - f1
model-index:
  - name: emotion-advance-classifier
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: emotion
          type: emotion
          config: split
          split: validation
          args: split
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.9325
          - name: F1
            type: f1
            value: 0.9327944704708324

emotion-advance-classifier

This model is a fine-tuned version of distilbert-base-uncased on the emotion dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1684
  • Accuracy: 0.9325
  • F1: 0.9328

This model is trained and evaluated using 'emotion' dataset. A great dataset from an article that explored how emotions are represented in English Twitter messages. Unlike most sentiment analysis datasets that involve just “positive” and “negative” polarities, this dataset con‐ tains six basic emotions: anger, love, fear, joy, sadness, and surprise.

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
0.1757 1.0 250 0.1891 0.93 0.9309
0.115 2.0 500 0.1684 0.9325 0.9328

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3