bertbaseuncasedny

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

• Train Loss: 0.3901
• Train End Logits Accuracy: 0.8823
• Train Start Logits Accuracy: 0.8513
• Validation Loss: 1.2123
• Validation End Logits Accuracy: 0.7291
• Validation Start Logits Accuracy: 0.6977
• Epoch: 3

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': 29508, '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	Train End Logits Accuracy	Train Start Logits Accuracy	Validation Loss	Validation End Logits Accuracy	Validation Start Logits Accuracy	Epoch
1.2597	0.6683	0.6277	1.0151	0.7214	0.6860	0
0.7699	0.7820	0.7427	1.0062	0.7342	0.6996	1
0.5343	0.8425	0.8064	1.1162	0.7321	0.7010	2
0.3901	0.8823	0.8513	1.2123	0.7291	0.6977	3

Framework versions

• Transformers 4.20.1
• TensorFlow 2.6.4
• Datasets 2.1.0
• Tokenizers 0.12.1