textming_proj01_electra

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

• Train Loss: 0.4494
• Train Accuracy: 0.7976
• Validation Loss: 0.5521
• Validation Accuracy: 0.7456
• Epoch: 5
• Batch size: 32

Model description

This model is fine-tuned by 19120600@student.hcmus.edu.vn in Kaggle

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• optimizer: {'name': 'Adam', 'learning_rate': 5e-05, 'epsilon': 1e-08}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
0.5951	0.6936	0.5818	0.6966	1
0.5484	0.7291	0.5681	0.7054	2
0.5119	0.7543	0.5284	0.7423	3
0.4769	0.7800	0.5306	0.7432	4
0.4494	0.7976	0.5521	0.7456	5

Framework versions

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