JuniorLeao/distilbert-base-uncased-finetuned-cola

This model is a fine-tuned version of Rocketknight1/distilbert-base-uncased-finetuned-cola on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0136
• Validation Loss: 1.0190
• Train Matthews Correlation: 0.5356
• 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': 5340, '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 Matthews Correlation	Epoch
0.2286	0.4897	0.5350	0
0.1543	0.5944	0.5301	1
0.0980	0.7309	0.4940	2
0.0704	0.7793	0.5260	3
0.0555	0.7871	0.5393	4
0.0373	0.8914	0.5318	5
0.0286	0.8742	0.5440	6
0.0242	0.9097	0.5455	7
0.0165	1.0051	0.5330	8
0.0136	1.0190	0.5356	9

Framework versions

• Transformers 4.30.2
• TensorFlow 2.12.0
• Datasets 2.13.1
• Tokenizers 0.13.3