bert-base-uncased-intent-booking

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: 2.1797
• Accuracy: 0.1937
• F1: 0.1715
• Precision: 0.3099
• Recall: 0.1937

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: 5e-05
• train_batch_size: 16
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 64
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
2.3533	1.0	65	2.3007	0.0946	0.0338	0.0281	0.0946
2.2868	2.0	130	2.1968	0.1351	0.0632	0.0472	0.1351
2.2299	3.0	195	2.1730	0.1847	0.1151	0.1020	0.1847
2.1909	4.0	260	2.1719	0.1937	0.1687	0.3112	0.1937
2.1657	5.0	325	2.1376	0.2027	0.1567	0.2069	0.2027
2.1437	6.0	390	2.1459	0.1757	0.1461	0.1909	0.1757
2.1342	7.0	455	2.1581	0.1667	0.1418	0.2867	0.1667
2.1025	8.0	520	2.1425	0.1892	0.1504	0.2449	0.1892
2.0749	9.0	585	2.1277	0.1847	0.1641	0.3096	0.1847
2.0482	10.0	650	2.1283	0.2117	0.1895	0.3519	0.2117
2.0654	11.0	715	2.1253	0.2117	0.1886	0.3004	0.2117
2.0443	12.0	780	2.1200	0.1937	0.1770	0.2982	0.1937
2.0345	13.0	845	2.1252	0.1937	0.1791	0.3098	0.1937
2.0148	14.0	910	2.1113	0.1982	0.1783	0.2804	0.1982
2.0112	15.0	975	2.1372	0.1892	0.1702	0.2746	0.1892
2.0022	16.0	1040	2.1254	0.1892	0.1696	0.2710	0.1892
1.9913	17.0	1105	2.1221	0.1892	0.1696	0.2710	0.1892
1.9827	18.0	1170	2.1090	0.1982	0.1758	0.2910	0.1982
1.9871	19.0	1235	2.1111	0.1982	0.1789	0.2756	0.1982
1.9824	20.0	1300	2.1132	0.1892	0.1705	0.2665	0.1892

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1