EricPeter/bert-finetuned-squad-v22

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

• Train Loss: 0.0121
• 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: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'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}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
• training_precision: mixed_float16

Training results

Train Loss	Epoch
2.6826	0
1.9953	1
1.5543	2
1.2287	3
0.8953	4
0.6043	5
0.3745	6
0.2298	7
0.1536	8
0.1098	9
0.0987	10
0.0683	11
0.0609	12
0.0473	13
0.0345	14
0.0353	15
0.0294	16
0.0232	17
0.0243	18
0.0170	19
0.0190	20
0.0111	21
0.0138	22
0.0078	23
0.0143	24
0.0095	25
0.0112	26
0.0092	27
0.0116	28
0.0121	29

Framework versions

• Transformers 4.31.0
• TensorFlow 2.12.0
• Datasets 2.14.0
• Tokenizers 0.13.3