ratish/DBERT_ZS_Desc_MAKE_v1.3.2

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: 0.0137
• Validation Loss: 0.0064
• Train Accuracy: 1.0
• Epoch: 16

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': 5840, '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
1.3970	0.8544	1.0	0
0.7415	0.3259	1.0	1
0.3675	0.1510	1.0	2
0.2087	0.0871	1.0	3
0.1323	0.0579	1.0	4
0.0931	0.0413	1.0	5
0.0695	0.0315	1.0	6
0.0544	0.0246	1.0	7
0.0428	0.0199	1.0	8
0.0355	0.0165	1.0	9
0.0298	0.0140	1.0	10
0.0259	0.0120	1.0	11
0.0219	0.0104	1.0	12
0.0194	0.0091	1.0	13
0.0176	0.0080	1.0	14
0.0152	0.0071	1.0	15
0.0137	0.0064	1.0	16

Framework versions

• Transformers 4.28.1
• TensorFlow 2.12.0
• Datasets 2.11.0
• Tokenizers 0.13.3