README.md

metadata

library_name: transformers
base_model: michellejieli/emotion_text_classifier
tags:
  - generated_from_trainer
metrics:
  - f1
model-index:
  - name: results
    results: []

results

This model is a fine-tuned version of michellejieli/emotion_text_classifier on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2828
• F1: 0.7879
• Roc Auc: nan
• Hamming: 0.1039

Model description

This model uses a lightweight RoBERTa checkpoint that has been fine-tuned on evaluating emotions to further be trained on recognizing climate disinformation.

Intended uses & limitations

To be used as a submission for the Frugal AI competition

Training and evaluation data

Dataset of text and labels available on Frugal AI competition page.

Training procedure

Used a binarizer to tokenize the text and found a seemingly suitable model checkpoint as a good place to start!

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.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

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0