badokorach/bert-finetuned-squad-5

This model is a fine-tuned version of badokorach/bert-finetuned-squad-4 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0004
• Epoch: 29

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': 2e-05, 'decay_steps': 1950, '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': 0.01}
• training_precision: mixed_float16

Training results

Train Loss	Epoch
0.0028	0
0.0325	1
0.0314	2
0.0260	3
0.0092	4
0.0129	5
0.0074	6
0.0044	7
0.0036	8
0.0020	9
0.0009	10
0.0058	11
0.0312	12
0.0063	13
0.0041	14
0.0023	15
0.0014	16
0.0023	17
0.0038	18
0.0010	19
0.0018	20
0.0006	21
0.0010	22
0.0007	23
0.0012	24
0.0004	25
0.0013	26
0.0004	27
0.0015	28
0.0004	29

Framework versions

• Transformers 4.31.0
• TensorFlow 2.12.0
• Datasets 2.14.4
• Tokenizers 0.13.3