INTENT

This is intent classification for enquiry of customer order service,

Features such as placing, Tracking and managment of orders, -
Handles payment issues such as making and refund of payment -
Options for delivery , address for shipping and also account management like editing, update account and delete account - -
Options for contacting human agent -

You can also sends complaints here -

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

• Train Loss: 0.0084
• Train Accuracy: 0.9987
• Validation Loss: 0.0019
• Validation Accuracy: 0.9995
• Epoch: 1

Model description

Enter intent , you will get the label number depicting the intent

• 'get_refund': 0,
• 'change_order': 1,
• 'contact_customer_service': 2,
• 'recover_password': 3,
• 'create_account': 4,
• 'check_invoices': 5,
• 'payment_issue': 6,
• 'place_order': 7,
• 'delete_account': 8,
• 'set_up_shipping_address': 9,
• 'delivery_options': 10,
• 'track_order': 11,
• 'change_shipping_address': 12,
• 'track_refund': 13,
• 'check_refund_policy': 14,
• 'review': 15,
• 'contact_human_agent': 16,
• 'delivery_period': 17,
• 'edit_account': 18,
• 'registration_problems': 19,
• 'get_invoice': 20,
• 'switch_account': 21,
• 'cancel_order': 22,
• 'check_payment_methods': 23,
• 'check_cancellation_fee': 24,
• 'newsletter_subscription': 25,
• 'complaint': 26

Training hyperparameters

The following hyperparameters were used during training:

• optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2690, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
0.2113	0.9544	0.0056	0.9995	0
0.0084	0.9987	0.0019	0.9995	1

Framework versions

• Transformers 4.35.2
• TensorFlow 2.15.0
• Datasets 2.16.0
• Tokenizers 0.15.0