nguyennghia0902's picture
Training in progress epoch 9
1291072
metadata
license: apache-2.0
base_model: google/electra-small-discriminator
tags:
  - generated_from_keras_callback
model-index:
  - name: nguyennghia0902/electra-small-discriminator_2e-05_16
    results: []

nguyennghia0902/electra-small-discriminator_2e-05_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: 1.8204
  • Train End Logits Accuracy: 0.5584
  • Train Start Logits Accuracy: 0.5303
  • Validation Loss: 1.5543
  • Validation End Logits Accuracy: 0.6127
  • Validation Start Logits Accuracy: 0.5972
  • 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': 2e-05, '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
3.3122 0.2821 0.2485 2.6648 0.3797 0.3553 0
2.6687 0.3873 0.3537 2.3167 0.4510 0.4297 1
2.4256 0.4356 0.4051 2.1007 0.4965 0.4787 2
2.2600 0.4678 0.4373 1.9512 0.5271 0.5112 3
2.1384 0.4927 0.4626 1.8342 0.5512 0.5353 4
2.0404 0.5101 0.4814 1.7279 0.5752 0.5598 5
1.9575 0.5275 0.4978 1.6628 0.5890 0.5718 6
1.8962 0.5405 0.5127 1.5958 0.6047 0.5877 7
1.8478 0.5503 0.5211 1.5622 0.6112 0.5964 8
1.8204 0.5584 0.5303 1.5543 0.6127 0.5972 9

Framework versions

  • Transformers 4.39.3
  • TensorFlow 2.15.0
  • Datasets 2.18.0
  • Tokenizers 0.15.2