ru_propaganda_opposition_model_distilbert-base-multilingual-cased

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

• Train Loss: 0.0003
• Validation Loss: 0.2582
• 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': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 7695, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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
0.2994	0.2306	0.9091	0
0.1127	0.1394	0.9540	1
0.0485	0.1417	0.9485	2
0.0256	0.1394	0.9562	3
0.0158	0.1835	0.9617	4
0.0106	0.1984	0.9617	5
0.0082	0.2812	0.9376	6
0.0030	0.2452	0.9562	7
0.0033	0.2022	0.9595	8
0.0052	0.2328	0.9529	9
0.0022	0.2302	0.9573	10
0.0019	0.2552	0.9529	11
0.0019	0.2461	0.9584	12
0.0006	0.2569	0.9551	13
0.0003	0.2582	0.9551	14

Framework versions

• Transformers 4.29.1
• TensorFlow 2.12.0
• Datasets 2.12.0
• Tokenizers 0.13.3