emotion_classifier

This model is a fine-tuned version of abdeljalilELmajjodi/model on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.7268
• F1: {'f1': 0.4749679405113014}

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• 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
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	F1
6.8728	0.9950	100	1.8998	{'f1': 0.3554471709728371}
6.545	1.9851	200	1.7557	{'f1': 0.4311025882104702}
5.7745	2.9751	300	1.7189	{'f1': 0.45241170661760866}
5.1439	3.9652	400	1.7268	{'f1': 0.4629496833729773}
4.6931	4.9552	500	1.7268	{'f1': 0.4749679405113014}

Framework versions

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