ratish/DBERT_CleanDesc_MAKE_v10.1

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

• Train Loss: 0.1668
• Validation Loss: 0.7903
• Train Accuracy: 0.8
• 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': 3090, '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
2.2016	1.9470	0.425	0
1.6623	1.5632	0.575	1
1.2367	1.2743	0.575	2
0.9547	1.1049	0.75	3
0.7787	1.0268	0.725	4
0.6138	0.8950	0.75	5
0.5122	0.9161	0.75	6
0.4713	0.8417	0.8	7
0.4282	0.7698	0.75	8
0.3625	0.7982	0.75	9
0.2912	0.8342	0.775	10
0.2440	0.7864	0.775	11
0.2136	0.7688	0.775	12
0.1914	0.7626	0.8	13
0.1668	0.7903	0.8	14

Framework versions

• Transformers 4.28.1
• TensorFlow 2.12.0
• Datasets 2.12.0
• Tokenizers 0.13.3