distilbert-arabe-eou-detector

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

distilbert-arabe-eou-detector

This model is a fine-tuned version of distilbert-base-multilingual-cased on a conversational Arabic dataset. It achieves the following results on the evaluation set:

• Loss: 0.2881
• Accuracy: 0.8925
• F1: 0.9071

🧠 Model Description Base model: distilbert-base-multilingual-cased Language: Saudi Arabia Task: Binary Classification — End of Utterance Detection Labels: 1: End of Utterance (EOU) 0: Not End of Utterance (NOT_EOU)

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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.0+cu126
• Datasets 4.4.1
• Tokenizers 0.22.1