cptanalatriste/request-for-help

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: 0.1342
• Train Sparse Categorical Accuracy: 1.0
• Validation Loss: 0.1514
• Validation Sparse Categorical Accuracy: 0.9796
• Epoch: 19

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', 'learning_rate': 3e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Train Sparse Categorical Accuracy	Validation Loss	Validation Sparse Categorical Accuracy	Epoch
0.8291	0.375	0.7483	0.3673	0
0.7470	0.375	0.6302	0.8163	1
0.6504	0.625	0.6079	0.9184	2
0.6128	0.7812	0.5882	0.8980	3
0.5939	0.8125	0.5639	0.9184	4
0.5300	0.9688	0.5378	0.9184	5
0.5306	0.9688	0.5098	0.9388	6
0.4963	1.0	0.4806	0.9388	7
0.4683	0.9688	0.4434	0.9592	8
0.3959	1.0	0.4070	0.9796	9
0.3807	1.0	0.3762	0.9796	10
0.3509	1.0	0.3439	0.9796	11
0.3013	1.0	0.3064	0.9796	12
0.2848	1.0	0.2931	0.9796	13
0.2587	1.0	0.2681	0.9796	14
0.2510	1.0	0.2295	0.9796	15
0.1867	1.0	0.2000	0.9796	16
0.1652	1.0	0.1793	0.9796	17
0.1297	1.0	0.1637	0.9796	18
0.1342	1.0	0.1514	0.9796	19

Framework versions

• Transformers 4.17.0
• TensorFlow 2.6.2
• Datasets 1.18.4
• Tokenizers 0.11.6