kasrahabib/roberta-base-finetuned-iso29148-sward-on-promise-km-labels-f-nf-cls

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: 0.0025
• Validation Loss: 0.4430
• 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': 123645, '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
0.3370	0.2402	0
0.1937	0.2777	1
0.1167	0.2346	2
0.0819	0.2329	3
0.0624	0.2889	4
0.0458	0.2796	5
0.0330	0.3695	6
0.0234	0.3125	7
0.0174	0.4382	8
0.0142	0.3535	9
0.0098	0.4172	10
0.0085	0.3862	11
0.0053	0.3860	12
0.0040	0.4372	13
0.0025	0.4430	14

Framework versions

• Transformers 4.42.3
• TensorFlow 2.15.0
• Datasets 2.19.1
• Tokenizers 0.19.1