athrado/bert-finetuned-nli

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

• Train Loss: 0.0641
• Train Accuracy: 0.9797
• Validation Loss: 0.4812
• Validation Accuracy: 0.8586
• 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': None, 'clipnorm': None, '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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 2775, '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-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
0.5572	0.7599	0.4802	0.8020	0
0.3324	0.8795	0.3869	0.8444	1
0.2057	0.9272	0.3933	0.8646	2
0.1212	0.9597	0.4413	0.8747	3
0.0641	0.9797	0.4812	0.8586	4

Framework versions

• Transformers 4.31.0
• TensorFlow 2.13.0
• Datasets 2.14.1
• Tokenizers 0.13.3