Hugging Face's logo

badokorach
/
bert-finetuned-squad-3

Question Answering
Transformers
TensorFlow
bert
generated_from_keras_callback
Inference Endpoints
Model card Files Community
bert-finetuned-squad-3 / README.md
badokorach's picture
badokorach
Training in progress epoch 29
eb36c11
preview code
|
raw
history blame contribute delete
2.3 kB
metadata
license: apache-2.0
base_model: badokorach/bert-finetuned-squad-2
tags:
  - generated_from_keras_callback
model-index:
  - name: badokorach/bert-finetuned-squad-3
    results: []

badokorach/bert-finetuned-squad-3

This model is a fine-tuned version of badokorach/bert-finetuned-squad-2 on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 0.0034
  • 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
0.0755 0
0.0927 1
0.0885 2
0.0539 3
0.0717 4
0.0455 5
0.0365 6
0.0212 7
0.0204 8
0.0235 9
0.0159 10
0.0128 11
0.0098 12
0.0134 13
0.0131 14
0.0156 15
0.0060 16
0.0090 17
0.0065 18
0.0069 19
0.0062 20
0.0078 21
0.0121 22
0.0031 23
0.0040 24
0.0037 25
0.0040 26
0.0021 27
0.0031 28
0.0034 29

Framework versions

  • Transformers 4.31.0
  • TensorFlow 2.12.0
  • Datasets 2.14.3
  • Tokenizers 0.13.3