Modelpublic

shahidul034/chatGPT_classifier

sourceHugging Faceapache-2.0updated 4y agoView on Hugging Face

0likes52downloads

Model Card

chatGPT_classifier

This model is a fine-tuned version of distilbert-base-uncased-finetuned-sst-2-english on an unknown dataset. It achieves the following results on the evaluation set:

—Train Loss: 0.0721
—Train Accuracy: 0.9805
—Validation Loss: 0.2447
—Validation Accuracy: 0.9114
—Epoch: 9

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', 'learningrate': {'classname': 'PolynomialDecay', 'config': {'initiallearningrate': 5e-05, 'decaysteps': 1929, 'endlearningrate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
—training_precision: float32

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
0.4382	0.7957	0.3053	0.8745	0
0.2381	0.9120	0.2671	0.8967	1
0.1154	0.9617	0.2447	0.9114	2
0.0701	0.9817	0.2447	0.9114	3
0.0723	0.9796	0.2447	0.9114	4
0.0730	0.9802	0.2447	0.9114	5
0.0706	0.9813	0.2447	0.9114	6
0.0711	0.9811	0.2447	0.9114	7
0.0697	0.9817	0.2447	0.9114	8
0.0721	0.9805	0.2447	0.9114	9

Framework versions

—Transformers 4.26.0
—TensorFlow 2.9.2
—Datasets 2.9.0
—Tokenizers 0.13.2