Hyperledger10ALBERT_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: 0.2119
• Train Accuracy: 0.9222
• Validation Loss: 0.4662
• Validation Accuracy: 0.8278
• Epoch: 5

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
0.3679	0.8765	0.3703	0.8600	0
0.3423	0.8834	0.3732	0.8600	1
0.3296	0.8841	0.3646	0.8600	2
0.3009	0.8824	0.3789	0.8548	3
0.2480	0.9038	0.4060	0.8039	4
0.2119	0.9222	0.4662	0.8278	5

Framework versions

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