nandysoham/Dell-theme-finetuned-overfinetuned

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

• Train Loss: 0.4305
• Train End Logits Accuracy: 0.7857
• Train Start Logits Accuracy: 0.8006
• Validation Loss: 2.3316
• Validation End Logits Accuracy: 0.1647
• Validation Start Logits Accuracy: 0.2118
• 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', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 210, '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
1.5691	0.5179	0.5119	1.2093	0.4588	0.4588	0
0.9333	0.6101	0.5833	1.2828	0.3176	0.3647	1
0.7924	0.6042	0.5982	1.4627	0.2824	0.2824	2
0.6858	0.6905	0.6786	1.5630	0.3059	0.2941	3
0.6562	0.6518	0.6815	1.7647	0.2235	0.2118	4
0.5996	0.7054	0.6994	2.0109	0.2118	0.2471	5
0.5277	0.7440	0.7589	2.1286	0.1765	0.2000	6
0.4810	0.7679	0.7798	2.2263	0.1529	0.2000	7
0.4488	0.8036	0.7887	2.2999	0.1529	0.1882	8
0.4305	0.7857	0.8006	2.3316	0.1647	0.2118	9

Framework versions

• Transformers 4.25.1
• TensorFlow 2.9.2
• Datasets 2.8.0
• Tokenizers 0.13.2