kasrahabib/bert-base-cased-finetuned-iso29148-req-detector

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

• Train Loss: 0.0299
• Validation Loss: 0.4860
• Epoch: 29

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': 3570, '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	Epoch
2.4480	1.6442	0
1.3378	0.9792	1
0.8492	0.7320	2
0.5922	0.6017	3
0.4316	0.5206	4
0.3071	0.5053	5
0.2353	0.5071	6
0.1666	0.4643	7
0.1324	0.4386	8
0.1098	0.4460	9
0.0923	0.4525	10
0.0808	0.4382	11
0.0676	0.4699	12
0.0581	0.4628	13
0.0627	0.4889	14
0.0534	0.4837	15
0.0482	0.4609	16
0.0459	0.4586	17
0.0474	0.4725	18
0.0419	0.4758	19
0.0391	0.4964	20
0.0387	0.4799	21
0.0375	0.4705	22
0.0347	0.4780	23
0.0349	0.4844	24
0.0335	0.4862	25
0.0308	0.4862	26
0.0291	0.4903	27
0.0293	0.4886	28
0.0299	0.4860	29

Framework versions

• Transformers 4.40.1
• TensorFlow 2.15.0
• Datasets 2.19.1
• Tokenizers 0.19.1