Qt20ALBERT_Unbalance

This model is a fine-tuned version of albert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.1378
• Train Accuracy: 0.9559
• Validation Loss: 0.2005
• Validation Accuracy: 0.9359
• 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': 0.001, 'clipnorm': 1.0, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
0.2122	0.9454	0.1637	0.9586	0
0.2095	0.9462	0.1649	0.9586	1
0.2104	0.9462	0.1704	0.9586	2
0.2064	0.9462	0.1593	0.9586	3
0.1982	0.9462	0.1824	0.9586	4
0.2003	0.9462	0.1635	0.9586	5
0.1947	0.9456	0.1591	0.9586	6
0.1852	0.9459	0.1772	0.9586	7
0.1650	0.9467	0.1982	0.9586	8
0.1378	0.9559	0.2005	0.9359	9

Framework versions

• Transformers 4.29.2
• TensorFlow 2.12.0
• Datasets 2.12.0
• Tokenizers 0.13.3