metadata

license: apache-2.0
base_model: google/electra-small-discriminator
tags:
  - generated_from_keras_callback
model-index:
  - name: nguyennghia0902/electra-small-discriminator_1e-05_32
    results: []

nguyennghia0902/electra-small-discriminator_1e-05_32

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: 2.5207
Train End Logits Accuracy: 0.4119
Train Start Logits Accuracy: 0.3790
Validation Loss: 2.3751
Validation End Logits Accuracy: 0.4375
Validation Start Logits Accuracy: 0.4154
Epoch: 9
{'name': 'project02_google/electra-small-discriminator_1e-05_32', 'lnr': 1e-05, 'epoch': 10, 'batch_size': 32, 'time': 14461.474628210068, 'accuracy': 0.32024509190946604, 'f1_score': 0.4362419993977412}

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': 1e-05, 'decay_steps': 15630, '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
4.0205	0.1761	0.1499	3.1750	0.2881	0.2533	0
3.1331	0.3100	0.2675	2.8517	0.3481	0.3184	1
2.9133	0.3429	0.3030	2.7096	0.3742	0.3479	2
2.7889	0.3674	0.3275	2.6031	0.3970	0.3685	3
2.7039	0.3811	0.3432	2.5304	0.4095	0.3853	4
2.6457	0.3903	0.3564	2.4704	0.4212	0.3956	5
2.5985	0.3968	0.3628	2.4328	0.4286	0.4026	6
2.5628	0.4050	0.3678	2.3987	0.4343	0.4117	7
2.5336	0.4085	0.3759	2.3774	0.4361	0.4142	8
2.5207	0.4119	0.3790	2.3751	0.4375	0.4154	9

Framework versions

Transformers 4.39.3
TensorFlow 2.15.0
Datasets 2.18.0
Tokenizers 0.15.2