roberta-base-20percent-noise-finetuned-iso29148-req-detector – AI Model by kasrahabib | AlphaNeural AI

You can deploy this model and start earning money today!

kasrahabib/
roberta-base-20percent-noise-finetuned-iso29148-req-detector

like

0

generated_from_keras_callback

FacebookAI/roberta-base

Views

No views yet

kasrahabib/roberta-base-20percent-noise-finetuned-iso29148-req-detector

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: 0.0868
Validation Loss: 1.0125
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
2.5723	1.4996	0
1.6997	0.9136	1
1.4006	0.7730	2
1.2196	0.7395	3
1.0725	0.6734	4
0.9041	0.6372	5
0.7533	0.6858	6
0.6478	0.7963	7
0.5352	0.7934	8
0.4663	0.8283	9
0.3845	0.8826	10
0.3229	0.8893	11
0.2736	0.9161	12
0.2358	0.9648	13
0.2144	0.8873	14
0.1906	0.9425	15
0.1681	0.9258	16
0.1527	0.9550	17
0.1447	0.9275	18
0.1283	1.0025	19
0.1293	1.0154	20
0.1100	0.9796	21
0.1183	0.9903	22
0.1052	0.9893	23
0.1029	0.9824	24
0.0991	1.0102	25
0.0920	1.0106	26
0.0962	1.0068	27
0.0887	1.0154	28
0.0868	1.0125	29

Framework versions

Transformers 4.42.3
TensorFlow 2.15.0
Datasets 2.19.1
Tokenizers 0.19.1