ashhadahsan/amazon-subtheme-bert-base-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: 0.0792
• Train Accuracy: 1.0
• Validation Loss: 2.4572
• Validation Accuracy: 0.5641
• Epoch: 12

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
3.5410	0.2497	3.0774	0.3333	0
2.3876	0.4804	2.5436	0.4103	1
1.5296	0.6930	2.3390	0.5128	2
1.0298	0.8158	2.3983	0.4615	3
0.7194	0.8971	2.4036	0.4615	4
0.5206	0.9362	2.4724	0.4359	5
0.3701	0.9669	2.4493	0.4872	6
0.2738	0.9841	2.3969	0.5641	7
0.2040	0.9929	2.4391	0.5641	8
0.1544	0.9966	2.4575	0.5641	9
0.1210	0.9993	2.4725	0.5385	10
0.0968	1.0	2.4445	0.5385	11
0.0792	1.0	2.4572	0.5641	12

Framework versions

• Transformers 4.33.0
• TensorFlow 2.12.0
• Datasets 2.1.0
• Tokenizers 0.13.3