Greek_Emotions_v02

This model is a fine-tuned version of gsar78/HellenicSentimentAI on a custom emotions dataset. It achieves the following results on the evaluation set:

• Loss: 0.1866
• F1: 0.6305
• Precision: 0.6569
• Recall: 0.6155
• Roc Auc: 0.8750
• Hamming: 0.0586
• Lrap: 0.7413
• Lrloss: 0.2037

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1