ashhadahsan/amazon-theme-bert-base-finetuned-finetuned

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

• Train Loss: 0.0341
• Train Accuracy: 1.0
• Validation Loss: 1.5032
• Validation Accuracy: 0.6667
• Epoch: 16

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': 1.0, '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': 3e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
1.9295	0.4297	1.7895	0.4656	0
1.5562	0.5650	1.6742	0.4762	1
1.2099	0.6552	1.5047	0.5450	2
0.8859	0.7825	1.3883	0.6138	3
0.6078	0.8753	1.3384	0.5926	4
0.4276	0.9271	1.5709	0.5397	5
0.3208	0.9536	1.4246	0.6349	6
0.2201	0.9748	1.5447	0.6190	7
0.1663	0.9814	1.5030	0.6455	8
0.1302	0.9867	1.4468	0.6349	9
0.0990	0.9881	1.4503	0.6349	10
0.0812	0.9920	1.4135	0.6667	11
0.0655	0.9934	1.4341	0.6720	12
0.0560	0.9960	1.4613	0.6561	13
0.0468	0.9973	1.4622	0.6720	14
0.0403	0.9987	1.4927	0.6667	15
0.0341	1.0	1.5032	0.6667	16

Framework versions

• Transformers 4.34.1
• TensorFlow 2.12.0
• Datasets 2.14.5
• Tokenizers 0.14.1