distilbert-base-uncased-finetuned-emotion-tweets

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

distilbert-base-uncased-finetuned-emotion-tweets

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

• Loss: 0.2112
• Accuracy: 0.928
• F1: 0.9280

Model description

The model is used to classify 6 basic emotions : Anger, Disgust, Fear, Joy, Sadness and Suprise. The model is finetuned by previously trained DistilBert classification model.

Intended uses & limitations

There are multiple ways to use this model in Huggingface Transformers. Possibly the simplest is using a pipeline:

from transformers import pipeline

model_id = "Lokeshwaran/distilbert-base-uncased-finetuned-emotion-tweets"
classifier = pipeline("text-classification", model = model_id)
custom_tweet = "The movie was very good"
preds = classifier(custom_tweet, return_all_scores=True)
print(preds[0)
# produces a list of dicts for each of the labels

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: 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

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1