ratish/DBERT_CleanDesc_MAKE_v10

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: 0.3182
• Validation Loss: 0.8903
• Train Accuracy: 0.75
• Epoch: 9

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
2.2603	2.0505	0.45	0
1.7907	1.6987	0.475	1
1.3820	1.4044	0.6	2
1.0496	1.2057	0.6	3
0.8393	1.0784	0.725	4
0.6652	0.9779	0.725	5
0.5508	0.9018	0.725	6
0.4662	0.8226	0.75	7
0.3664	0.8913	0.725	8
0.3182	0.8903	0.75	9

Framework versions

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