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