hubert_mosa

This model is a fine-tuned version of omarxadel/hubert-large-arabic-egyptian on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7918
• Accuracy: 0.6304

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use 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: 0.2
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	104	1.0925	0.3207
No log	2.0	208	0.8980	0.5652
No log	3.0	312	0.8091	0.6196
No log	4.0	416	0.7918	0.6304
0.9267	4.9565	515	0.7845	0.625

Framework versions

• Transformers 4.47.0.dev0
• Pytorch 2.5.1
• Datasets 3.1.1.dev0
• Tokenizers 0.20.3