vedantjumle/bert-2

This model is a fine-tuned version of bert-large-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 4.4459
• Validation Loss: 4.3669
• Train Accuracy: 0.0233
• Epoch: 25

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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 6000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_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
5.1229	5.0343	0.0067	0
5.0629	5.0547	0.0033	1
5.0585	5.0239	0.0167	2
5.0530	5.0257	0.0167	3
5.0545	5.0207	0.01	4
5.0549	5.0104	0.01	5
5.0401	5.0240	0.0067	6
5.0400	5.0121	0.01	7
5.0372	5.0030	0.0167	8
5.0326	5.0256	0.0067	9
5.0382	4.9992	0.01	10
5.0144	4.9976	0.01	11
5.0152	4.9783	0.0167	12
4.9700	4.9433	0.0067	13
4.9206	4.9482	0.0067	14
4.9153	4.8727	0.0067	15
4.9287	4.7980	0.0167	16
4.8014	4.7452	0.0167	17
4.7477	4.6429	0.01	18
4.6939	4.6035	0.02	19
4.6607	4.5406	0.02	20
4.6075	4.5490	0.0167	21
4.5748	4.5086	0.0333	22
4.5383	4.3940	0.0333	23
4.4965	4.3748	0.0233	24
4.4459	4.3669	0.0233	25

Framework versions

• Transformers 4.34.0
• TensorFlow 2.13.0
• Datasets 2.14.5
• Tokenizers 0.14.1