AmRevAnalysis-hf

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: 0.4643
• Train Accuracy: 0.8069
• Validation Loss: 0.6009
• Validation Accuracy: 0.7670
• Train Learning Rate: 0.0000
• Epoch: 17

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': np.float32(1.25e-07), 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Train Learning Rate	Epoch
0.4974	0.7946	0.5919	0.7662	0.0000	5
0.4898	0.7969	0.5929	0.7656	0.0000	6
0.4842	0.7989	0.5951	0.7652	0.0000	7
0.4810	0.8009	0.5968	0.7668	0.0000	8
0.4790	0.8004	0.5977	0.7670	0.0000	9
0.4746	0.8030	0.5978	0.7666	0.0000	10
0.4698	0.8069	0.6012	0.7674	0.0000	11
0.4720	0.8043	0.6003	0.7678	0.0000	12
0.4715	0.8050	0.6003	0.7678	0.0000	13
0.4651	0.8090	0.6008	0.7666	0.0000	14
0.4659	0.8089	0.6004	0.7672	0.0000	15
0.4633	0.8096	0.6015	0.7660	0.0000	16
0.4643	0.8069	0.6009	0.7670	0.0000	17

Framework versions

• Transformers 4.51.3
• TensorFlow 2.18.0
• Datasets 2.14.4
• Tokenizers 0.21.1