DIALOGUE_overfit_check

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1840
• Precision: 0.9762
• Recall: 0.9737
• F1: 0.9736
• Accuracy: 0.9737

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: 3e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
1.0266	0.62	30	0.5087	1.0	1.0	1.0	1.0
0.4009	1.25	60	0.1389	0.9762	0.9737	0.9736	0.9737
0.1301	1.88	90	0.1436	0.9637	0.9605	0.9604	0.9605
0.0342	2.5	120	0.1055	0.9762	0.9737	0.9736	0.9737
0.0288	3.12	150	0.1395	0.9762	0.9737	0.9736	0.9737
0.0099	3.75	180	0.1259	0.9762	0.9737	0.9736	0.9737
0.0057	4.38	210	0.1315	0.9762	0.9737	0.9736	0.9737
0.0042	5.0	240	0.1338	0.9762	0.9737	0.9736	0.9737
0.0033	5.62	270	0.1373	0.9762	0.9737	0.9736	0.9737
0.0027	6.25	300	0.1403	0.9762	0.9737	0.9736	0.9737
0.0024	6.88	330	0.1457	0.9762	0.9737	0.9736	0.9737
0.002	7.5	360	0.1483	0.9762	0.9737	0.9736	0.9737
0.0017	8.12	390	0.1483	0.9762	0.9737	0.9736	0.9737
0.0016	8.75	420	0.1503	0.9762	0.9737	0.9736	0.9737
0.0014	9.38	450	0.1535	0.9762	0.9737	0.9736	0.9737
0.0013	10.0	480	0.1546	0.9762	0.9737	0.9736	0.9737
0.0012	10.62	510	0.1576	0.9762	0.9737	0.9736	0.9737
0.0011	11.25	540	0.1593	0.9762	0.9737	0.9736	0.9737
0.001	11.88	570	0.1672	0.9762	0.9737	0.9736	0.9737
0.0009	12.5	600	0.1686	0.9762	0.9737	0.9736	0.9737
0.0008	13.12	630	0.1696	0.9762	0.9737	0.9736	0.9737
0.0008	13.75	660	0.1696	0.9762	0.9737	0.9736	0.9737
0.0007	14.38	690	0.1702	0.9762	0.9737	0.9736	0.9737
0.0007	15.0	720	0.1711	0.9762	0.9737	0.9736	0.9737
0.0006	15.62	750	0.1716	0.9762	0.9737	0.9736	0.9737
0.0006	16.25	780	0.1726	0.9762	0.9737	0.9736	0.9737
0.0006	16.88	810	0.1731	0.9762	0.9737	0.9736	0.9737
0.0006	17.5	840	0.1744	0.9762	0.9737	0.9736	0.9737
0.0006	18.12	870	0.1762	0.9762	0.9737	0.9736	0.9737
0.0005	18.75	900	0.1773	0.9762	0.9737	0.9736	0.9737
0.0005	19.38	930	0.1777	0.9762	0.9737	0.9736	0.9737
0.0005	20.0	960	0.1781	0.9762	0.9737	0.9736	0.9737
0.0005	20.62	990	0.1785	0.9762	0.9737	0.9736	0.9737
0.0004	21.25	1020	0.1795	0.9762	0.9737	0.9736	0.9737
0.0004	21.88	1050	0.1801	0.9762	0.9737	0.9736	0.9737
0.0004	22.5	1080	0.1805	0.9762	0.9737	0.9736	0.9737
0.0004	23.12	1110	0.1812	0.9762	0.9737	0.9736	0.9737
0.0004	23.75	1140	0.1818	0.9762	0.9737	0.9736	0.9737
0.0004	24.38	1170	0.1821	0.9762	0.9737	0.9736	0.9737
0.0004	25.0	1200	0.1824	0.9762	0.9737	0.9736	0.9737
0.0004	25.62	1230	0.1827	0.9762	0.9737	0.9736	0.9737
0.0004	26.25	1260	0.1831	0.9762	0.9737	0.9736	0.9737
0.0004	26.88	1290	0.1833	0.9762	0.9737	0.9736	0.9737
0.0004	27.5	1320	0.1836	0.9762	0.9737	0.9736	0.9737
0.0004	28.12	1350	0.1838	0.9762	0.9737	0.9736	0.9737
0.0004	28.75	1380	0.1839	0.9762	0.9737	0.9736	0.9737
0.0004	29.38	1410	0.1840	0.9762	0.9737	0.9736	0.9737
0.0004	30.0	1440	0.1840	0.9762	0.9737	0.9736	0.9737

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0