badokorach/mobilebert-uncased-finetuned-agic-181223

This model is a fine-tuned version of csarron/mobilebert-uncased-squad-v2 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0491
• Validation Loss: 0.0
• Epoch: 19

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': 1e-05, 'decay_steps': 1840, '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
0.1160	0.0	0
0.0863	0.0	1
0.0862	0.0	2
0.0782	0.0	3
0.0763	0.0	4
0.0661	0.0	5
0.0767	0.0	6
0.0546	0.0	7
0.0602	0.0	8
0.0502	0.0	9
0.0542	0.0	10
0.0577	0.0	11
0.0439	0.0	12
0.0508	0.0	13
0.0402	0.0	14
0.0481	0.0	15
0.0462	0.0	16
0.0382	0.0	17
0.0404	0.0	18
0.0491	0.0	19

Framework versions

• Transformers 4.35.2
• TensorFlow 2.15.0
• Datasets 2.15.0
• Tokenizers 0.15.0