HASAN55/bert-finetuned-for-distil

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

• Train Loss: 0.8322
• Train End Logits Accuracy: 0.7636
• Train Start Logits Accuracy: 0.7311
• Validation Loss: 1.1398
• Validation End Logits Accuracy: 0.7014
• Validation Start Logits Accuracy: 0.6678
• 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': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 25124, '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, 'weight_decay_rate': 0.001}
• training_precision: mixed_float16

Training results

Train Loss	Train End Logits Accuracy	Train Start Logits Accuracy	Validation Loss	Validation End Logits Accuracy	Validation Start Logits Accuracy	Epoch
1.7468	0.5488	0.5204	1.2282	0.6706	0.6367	0
1.1198	0.6922	0.6597	1.1548	0.6880	0.6558	1
0.9378	0.7370	0.7038	1.1243	0.6965	0.6631	2
0.8322	0.7636	0.7311	1.1398	0.7014	0.6678	3

Framework versions

• Transformers 4.27.4
• TensorFlow 2.12.0
• Datasets 2.11.0
• Tokenizers 0.13.3