showvikdbz/toxifcity-classifier-tf

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

• Train Loss: 0.0161
• Validation Loss: 0.0759
• Train Accuracy: 0.9835
• Train F1: 0.9684
• Train Precision: 0.9742
• Train Recall: 0.9627
• 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': 23256, '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	Validation Loss	Train Accuracy	Train F1	Train Precision	Train Recall	Epoch
0.0951	0.0606	0.9825	0.9661	0.9823	0.9504	0
0.0406	0.0665	0.9828	0.9667	0.9882	0.9460	1
0.0161	0.0759	0.9835	0.9684	0.9742	0.9627	2

Framework versions

• Transformers 4.44.2
• TensorFlow 2.17.0
• Datasets 2.21.0
• Tokenizers 0.19.1