Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
bert-finetuned-squad-v2 – AI Model by ksathur14 | AlphaNeural AI
You can deploy this model and start earning money today!
ksathur14
/
bert-finetuned-squad-v2
like
0
transformers
tf
bert
question-answering
generated_from_keras_callback
apache-2.0
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
ksathur14/bert-finetuned-squad-v2
This model is a fine-tuned version of
ksathur/bert-finetuned-squad-v2
on an unknown dataset. It achieves the following results on the evaluation set:
Train Loss: 0.0079
Epoch: 9
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': 54960, '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
0.0973
0
0.0788
1
0.0635
2
0.0491
3
0.0369
4
0.0291
5
0.0231
6
0.0147
7
0.0108
8
0.0079
9
Framework versions
Transformers 4.26.1
TensorFlow 2.9.1
Datasets 2.10.1
Tokenizers 0.13.2
