bert_intent

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

• Loss: 0.0169
• Accuracy: 0.9982

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:

• learning_rate: 1e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2615	1.0	692	0.0516	0.9809
0.0191	2.0	1384	0.0231	0.9947
0.0083	3.0	2076	0.0140	0.9982
0.0051	4.0	2768	0.0101	0.9975
0.0028	5.0	3460	0.0075	0.9979
0.0013	6.0	4152	0.0064	0.9979
0.0008	7.0	4844	0.0073	0.9979
0.0004	8.0	5536	0.0069	0.9979
0.0003	9.0	6228	0.0072	0.9979
0.0002	10.0	6920	0.0075	0.9979
0.0002	11.0	7612	0.0077	0.9979
0.0001	12.0	8304	0.0080	0.9979
0.0001	13.0	8996	0.0083	0.9979
0.0001	14.0	9688	0.0087	0.9979
0.0	15.0	10380	0.0093	0.9979
0.0	16.0	11072	0.0097	0.9982
0.0	17.0	11764	0.0096	0.9979
0.0	18.0	12456	0.0106	0.9979
0.0	19.0	13148	0.0108	0.9979
0.0	20.0	13840	0.0110	0.9979
0.0	21.0	14532	0.0111	0.9979
0.0	22.0	15224	0.0116	0.9979
0.0	23.0	15916	0.0116	0.9979
0.0	24.0	16608	0.0125	0.9982
0.0	25.0	17300	0.0130	0.9982
0.0	26.0	17992	0.0124	0.9979
0.0	27.0	18684	0.0129	0.9979
0.0	28.0	19376	0.0138	0.9982
0.0	29.0	20068	0.0140	0.9982
0.0	30.0	20760	0.0145	0.9982
0.0	31.0	21452	0.0144	0.9982
0.0	32.0	22144	0.0146	0.9982
0.0	33.0	22836	0.0152	0.9982
0.0	34.0	23528	0.0151	0.9982
0.0	35.0	24220	0.0151	0.9982
0.0	36.0	24912	0.0153	0.9982
0.0	37.0	25604	0.0155	0.9982
0.0	38.0	26296	0.0158	0.9982
0.0	39.0	26988	0.0159	0.9982
0.0	40.0	27680	0.0163	0.9982
0.0	41.0	28372	0.0168	0.9982
0.0	42.0	29064	0.0167	0.9982
0.0	43.0	29756	0.0167	0.9982
0.0	44.0	30448	0.0168	0.9982
0.0	45.0	31140	0.0168	0.9982
0.0	46.0	31832	0.0168	0.9982
0.0	47.0	32524	0.0168	0.9982
0.0	48.0	33216	0.0168	0.9982
0.0	49.0	33908	0.0169	0.9982
0.0	50.0	34600	0.0169	0.9982

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.1
• Datasets 2.19.2
• Tokenizers 0.19.1