bert-base-multilingual-cased-FT-TyDiQA_SYNAUQ – AI Model by vnktrmnb | AlphaNeural AI

You can deploy this model and start earning money today!

vnktrmnb/
bert-base-multilingual-cased-FT-TyDiQA_SYNAUQ

like

0

question-answering

generated_from_keras_callback

google-bert/bert-base-multilingual-cased

endpoints_compatible

Views

No views yet

vnktrmnb/bert-base-multilingual-cased-FT-TyDiQA_SYNAUQ

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

Train Loss: 0.3527
Train End Logits Accuracy: 0.8850
Train Start Logits Accuracy: 0.9162
Validation Loss: 0.4966
Validation End Logits Accuracy: 0.8557
Validation Start Logits Accuracy: 0.9098
Epoch: 2

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': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2364, '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
1.2702	0.6758	0.7111	0.5035	0.8454	0.8866	0
0.5651	0.8308	0.8674	0.4656	0.8570	0.9046	1
0.3527	0.8850	0.9162	0.4966	0.8557	0.9098	2

Framework versions

Transformers 4.32.0
TensorFlow 2.12.0
Datasets 2.14.4
Tokenizers 0.13.3