aadhistii/tsel-finetune-bert-base-multilingual-cased-2k-formal-v2

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

• Train Loss: 0.0457
• Validation Loss: 1.0705
• Train Precision: 0.7102
• Train Recall: 0.7104
• Train F1: 0.7103
• Train Accuracy: 0.7207
• Epoch: 9

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': 940, '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 Precision	Train Recall	Train F1	Train Accuracy	Epoch
0.9754	0.8980	0.7162	0.4951	0.4870	0.5824	0
0.8058	0.7559	0.6366	0.6478	0.6383	0.6516	1
0.5843	0.7703	0.6928	0.6737	0.6583	0.6809	2
0.4311	0.7745	0.7411	0.7075	0.7187	0.7340	3
0.2658	0.8264	0.6996	0.7133	0.7022	0.7154	4
0.1542	0.9036	0.7245	0.7195	0.7215	0.7367	5
0.1073	0.9961	0.7076	0.7278	0.7132	0.7261	6
0.0712	1.0520	0.7069	0.6980	0.7004	0.7181	7
0.0563	1.0643	0.7141	0.7032	0.7079	0.7234	8
0.0457	1.0705	0.7102	0.7104	0.7103	0.7207	9

Framework versions

• Transformers 4.42.3
• TensorFlow 2.15.0
• Datasets 2.20.0
• Tokenizers 0.19.1