ayatsuri/academic-ai-detector

This model is a fine-tuned version of distilbert/distilbert-base-uncased on NicolaiSivesind/human-vs-machine dataset. It achieves the following best results on the evaluation set:

• Train Loss: 0.0910
• Validation Loss: 0.0326
• Train Accuracy: 0.9937
• Train Recall: 0.9927
• Train Precision: 0.9947
• Train F1: 0.9937
• Validation Accuracy: 0.99
• Validation Recall: 0.986
• Validation Precision: 0.9940
• Validation F1: 0.9900
• Epoch: 0

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:

• 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': 2625, '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

Set	Loss	Accuracy	Recall	Precision	F1
Train	0.0910	0.9937	0.9927	0.9947	0.9937
Validation	0.0326	0.99	0.986	0.9940	0.9900

Framework versions

• Transformers 4.41.1
• TensorFlow 2.15.0
• Datasets 2.19.1
• Tokenizers 0.19.1