Electro98/my_awesome_model_v2

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

• Train Loss: 0.1620
• Validation Loss: 0.1617
• Train F1: 0.0731
• Train Accuracy: 0.1217
• Epoch: 12

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', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1056100, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train F1	Train Accuracy	Epoch
0.1841	0.1586	0.0441	0.0484	0
0.1733	0.1553	0.0447	0.0537	1
0.1628	0.1516	0.0757	0.0990	2
0.1600	0.1559	0.0700	0.1263	3
0.1634	0.1549	0.0662	0.0956	4
0.1620	0.1526	0.0611	0.0777	5
0.1622	0.1718	0.0809	0.0865	6
0.1625	0.1577	0.0498	0.0942	7
0.1649	0.1566	0.0799	0.1404	8
0.1684	0.1585	0.0700	0.1262	9
0.1628	0.1582	0.0802	0.1112	10
0.1605	0.1614	0.0651	0.1065	11
0.1620	0.1617	0.0731	0.1217	12

Framework versions

• Transformers 4.27.4
• TensorFlow 2.10.0
• Datasets 2.18.0
• Tokenizers 0.13.3