MariaDB5ALBERT_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: 0.2849
• Train Accuracy: 0.9021
• Validation Loss: 0.2701
• Validation Accuracy: 0.9271
• Epoch: 4

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
0.3276	0.8895	0.2502	0.9322	0
0.2859	0.8987	0.2446	0.9322	1
0.2878	0.9021	0.2468	0.9322	2
0.2651	0.9029	0.2862	0.9296	3
0.2849	0.9021	0.2701	0.9271	4

Framework versions

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