ratish/DBERT_CleanDesc_Collision_v2.5

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: 0.4855
• Validation Loss: 1.0752
• Train Accuracy: 0.6410
• 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': 3040, '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
1.5849	1.6211	0.3333	0
1.4751	1.5922	0.3333	1
1.3947	1.4869	0.4359	2
1.2663	1.3455	0.5641	3
1.0385	1.2647	0.5897	4
0.9351	1.2546	0.5897	5
0.8036	1.2566	0.5897	6
0.7181	1.1101	0.6154	7
0.6027	1.1042	0.6410	8
0.4855	1.0752	0.6410	9

Framework versions

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