You can deploy this model and start earning money today!

nguyennghia0902/
electra-small-discriminator_0.0005_16

Name: electra-small-discriminator_0.0005_16
Availability: InStock

transformers

electra

question-answering

generated_from_keras_callback

google/electra-small-discriminator

finetune

apache-2.0

endpoints_compatible

Views

No views yet

nguyennghia0902/electra-small-discriminator_0.0005_16

This model is a fine-tuned version of google/electra-small-discriminator on an unknown dataset. It achieves the following results on the evaluation set:

Train Loss: 1.2099
Train End Logits Accuracy: 0.6982
Train Start Logits Accuracy: 0.6666
Validation Loss: 0.7830
Validation End Logits Accuracy: 0.7964
Validation Start Logits Accuracy: 0.7852
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: {'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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0005, 'decay_steps': 31270, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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
3.8593	0.1838	0.1690	2.9074	0.3506	0.3319	0
3.0501	0.3257	0.2954	2.5522	0.4171	0.3859	1
2.7183	0.3845	0.3534	2.2123	0.4803	0.4547	2
2.4780	0.4325	0.4004	1.9826	0.5248	0.5046	3
2.2672	0.4747	0.4389	1.8034	0.5660	0.5425	4
2.0640	0.5162	0.4814	1.5610	0.6207	0.6037	5
1.8439	0.5608	0.5265	1.3128	0.6811	0.6639	6
1.6214	0.6104	0.5736	1.0714	0.7326	0.7206	7
1.3990	0.6574	0.6232	0.8891	0.7744	0.7630	8
1.2099	0.6982	0.6666	0.7830	0.7964	0.7852	9

Framework versions

Transformers 4.39.3
TensorFlow 2.15.0
Datasets 2.18.0
Tokenizers 0.15.2