multilabel_emotion_classification_finetuned_multimodal

This model is a fine-tuned version of lupobricco/feel_it_finetuned_pro_emit_multilabel2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2439
• F1: 0.5642
• Roc Auc: 0.7425
• Accuracy: 0.4087

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Roc Auc	Accuracy
No log	1.0	22	0.2472	0.4520	0.6658	0.3391
No log	2.0	44	0.2445	0.4927	0.6909	0.3507
No log	3.0	66	0.2439	0.5	0.6941	0.3594
No log	4.0	88	0.2436	0.5297	0.7209	0.3652
No log	5.0	110	0.2424	0.5400	0.7313	0.3710
No log	6.0	132	0.2409	0.5450	0.7276	0.3768
No log	7.0	154	0.2432	0.5286	0.7191	0.3652
No log	8.0	176	0.2433	0.5501	0.7336	0.3942
No log	9.0	198	0.2439	0.5642	0.7425	0.4087
No log	10.0	220	0.2434	0.5594	0.7406	0.4029

Framework versions

• Transformers 4.39.3
• Pytorch 1.11.0
• Datasets 2.18.0
• Tokenizers 0.15.2