bert-base-arabic-emotion-analysis-v2.model

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

• Loss: 0.5681
• Accuracy: 0.8025
• F1: 0.8032

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: 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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.9804	1.0	102	0.6430	0.7804	0.7823
0.5684	2.0	204	0.5897	0.7901	0.7899
0.4309	3.0	306	0.5681	0.8025	0.8032

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0