badokorach/distilbert-base-uncased-distilled-squad-17

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

• Train Loss: 0.4761
• Validation Loss: 0.0
• Epoch: 17

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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 13200, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.02}
• training_precision: mixed_float16

Training results

Train Loss	Validation Loss	Epoch
3.7877	0.0	0
3.5579	0.0	1
3.4117	0.0	2
3.2112	0.0	3
2.9211	0.0	4
2.5860	0.0	5
2.2459	0.0	6
1.9209	0.0	7
1.6627	0.0	8
1.3934	0.0	9
1.2150	0.0	10
1.0406	0.0	11
0.8977	0.0	12
0.7730	0.0	13
0.6944	0.0	14
0.6361	0.0	15
0.5495	0.0	16
0.4761	0.0	17

Framework versions

• Transformers 4.33.2
• TensorFlow 2.13.0
• Datasets 2.14.5
• Tokenizers 0.13.3