test-trainer-persian

This model is a fine-tuned version of sileod/mdeberta-v3-base-tasksource-nli on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1753
• Accuracy: 0.9463

{'قانون': 3241, 'ادبیات': 18297, 'دارو': 708, 'شعر': 256, 'سیاست': 5720, 'دین': 911, 'علم': 4546, 'گفتگو': 2882}

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.514	1.0	1708	0.3680	0.8829
0.3639	2.0	3416	0.2282	0.9263
0.2534	3.0	5124	0.1753	0.9463

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1