imagine0711/distilbert-base-uncased-finetuned-lmattack

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: 2.6773
• Validation Loss: 2.4384
• Epoch: 10

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': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': -982, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: mixed_float16

Training results

Train Loss	Validation Loss	Epoch
3.3001	3.1024	0
3.2506	3.0665	1
3.1464	2.8486	2
3.0678	2.7576	3
2.9267	2.9328	4
2.8851	2.7800	5
2.7620	2.6846	6
2.7398	2.4412	7
2.6492	2.4846	8
2.6842	2.5684	9
2.6773	2.4384	10

Framework versions

• Transformers 4.41.2
• TensorFlow 2.15.0
• Datasets 2.19.2
• Tokenizers 0.19.1