kasrahabib/roberta-base-finetuned-iso29148-km_propogated_nf_subs_label_req

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

• Train Loss: 0.0107
• Validation Loss: 0.2354
• 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': 2295, '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
1.4530	0.5649	0
0.3927	0.3094	1
0.1669	0.2982	2
0.1159	0.2857	3
0.0808	0.2869	4
0.0503	0.3065	5
0.0272	0.2469	6
0.0270	0.2287	7
0.0221	0.2295	8
0.0173	0.2659	9
0.0298	0.2489	10
0.0123	0.2287	11
0.0104	0.2285	12
0.0096	0.2302	13
0.0107	0.2354	14

Framework versions

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