czigopis/bert-base-greek-uncased-v1-finetuned-on-OGTDv1

This model is a fine-tuned version of nlpaueb/bert-base-greek-uncased-v1 on the Offensive Greek Tweet Dataset (OGTD). It achieves the following results on the evaluation set:

• Train Loss: 0.1390
• Validation Loss: 0.4815
• Train Matthews Correlation: 0.6669
• Train F1: 0.8385
• Train Accuracy: 0.8333
• 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': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 9805, '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 Matthews Correlation	Train F1	Train Accuracy	Epoch
0.6338	0.5099	0.5313	0.7560	0.7642	0
0.4309	0.3983	0.6669	0.8339	0.8333	1
0.3024	0.4196	0.6594	0.8220	0.8280	2
0.2222	0.4432	0.6666	0.8374	0.8333	3
0.1390	0.4815	0.6669	0.8385	0.8333	4

Framework versions

• Transformers 4.40.2
• TensorFlow 2.15.0
• Datasets 2.19.1
• Tokenizers 0.19.1