BERT-finetuned-squad – AI Model by tyavika | AlphaNeural AI

You can deploy this model and start earning money today!

tyavika/
BERT-finetuned-squad

like

0

question-answering

generated_from_keras_callback

endpoints_compatible

Views

No views yet

tyavika/BERT-finetuned-squad

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

Train Loss: 0.8112
Train End Logits Accuracy: 0.7752
Train Start Logits Accuracy: 0.7328
Validation Loss: 0.9437
Validation End Logits Accuracy: 0.7438
Validation Start Logits Accuracy: 0.7038
Epoch: 1

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': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 11696, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
training_precision: float32

Training results

Train Loss	Train End Logits Accuracy	Train Start Logits Accuracy	Validation Loss	Validation End Logits Accuracy	Validation Start Logits Accuracy	Epoch
1.3238	0.6565	0.6133	0.9733	0.7373	0.6892	0
0.8112	0.7752	0.7328	0.9437	0.7438	0.7038	1

Framework versions

Transformers 4.26.1
TensorFlow 2.11.0
Datasets 2.12.0
Tokenizers 0.13.2