Lolimorimorf/propaganda_opposition_model_bert_base_multilingual_cased

ru_propaganda_opposition_model_bert-base-multilingual-cased

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: 0.0004
• Validation Loss: 0.2406
• Train Accuracy: 0.9551
• Epoch: 14

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': 7695, '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	Epoch
0.2769	0.1252	0.9474	0
0.0922	0.1174	0.9573	1
0.0506	0.1379	0.9507	2
0.0280	0.1858	0.9463	3
0.0204	0.1518	0.9584	4
0.0148	0.1745	0.9496	5
0.0091	0.2365	0.9419	6
0.0054	0.1793	0.9606	7
0.0057	0.1874	0.9595	8
0.0032	0.2165	0.9540	9
0.0020	0.6815	0.8970	10
0.0061	0.2158	0.9496	11
0.0007	0.2652	0.9452	12
0.0002	0.2304	0.9595	13
0.0004	0.2406	0.9551	14

Framework versions

• Transformers 4.44.2
• TensorFlow 2.17.0
• Datasets 3.1.0
• Tokenizers 0.19.1