rubakha/bert2

This model is a fine-tuned version of Vasanth/bert-base-uncased-finetuned-emotion on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.1018
• Train Accuracy: 0.945
• Validation Loss: 0.1530
• Validation Accuracy: 0.9450
• Train Precision: 0.9466
• Train Recall: 0.945
• Train F1: 0.9446
• Epoch: 2

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': 5000, '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 Accuracy	Validation Loss	Validation Accuracy	Train Precision	Train Recall	Train F1	Epoch
0.2174	0.941	0.1580	0.9410	0.9423	0.941	0.9406	0
0.1314	0.9435	0.1506	0.9435	0.9463	0.9435	0.9428	1
0.1018	0.945	0.1530	0.9450	0.9466	0.945	0.9446	2

Framework versions

• Transformers 4.38.2
• TensorFlow 2.15.0
• Datasets 2.18.0
• Tokenizers 0.15.2