sentiment-analysis-whatsapp

This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2229
• Accuracy: {'accuracy': 0.929}
• F1 Macro: 0.9285

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: 5e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 99
• gradient_accumulation_steps: 5
• total_train_batch_size: 320
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro
No log	1.0	50	0.6396	{'accuracy': 0.7845}	0.7828
No log	2.0	100	0.2665	{'accuracy': 0.915}	0.9145
No log	3.0	150	0.2229	{'accuracy': 0.929}	0.9285

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2