distilbert-base-uncased-distilled-clinc

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

• Loss: 0.2846
• Accuracy: 0.9494

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: 2e-05
• train_batch_size: 48
• eval_batch_size: 48
• 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	Accuracy
2.8274	1.0	318	2.0336	0.7442
1.5283	2.0	636	0.9644	0.8735
0.7339	3.0	954	0.5207	0.9219
0.4104	4.0	1272	0.3852	0.9371
0.2922	5.0	1590	0.3389	0.9452
0.2433	6.0	1908	0.3266	0.9423
0.2211	7.0	2226	0.3079	0.9497
0.208	8.0	2544	0.3068	0.9490
0.2006	9.0	2862	0.3003	0.9497
0.1955	10.0	3180	0.2963	0.9503
0.1917	11.0	3498	0.2938	0.95
0.1885	12.0	3816	0.2913	0.9487
0.1862	13.0	4134	0.2903	0.9503
0.1846	14.0	4452	0.2927	0.9474
0.1829	15.0	4770	0.2927	0.9490
0.1823	16.0	5088	0.2894	0.9484
0.1807	17.0	5406	0.2894	0.9455
0.1795	18.0	5724	0.2884	0.9477
0.1788	19.0	6042	0.2862	0.9494
0.1781	20.0	6360	0.2868	0.9494
0.1775	21.0	6678	0.2871	0.9484
0.1767	22.0	6996	0.2908	0.9490
0.1758	23.0	7314	0.2845	0.95
0.1758	24.0	7632	0.2893	0.9497
0.1756	25.0	7950	0.2855	0.9490
0.175	26.0	8268	0.2867	0.9481
0.1748	27.0	8586	0.2846	0.9477
0.1745	28.0	8904	0.2847	0.9490
0.1742	29.0	9222	0.2842	0.9490
0.1743	30.0	9540	0.2846	0.9494

Framework versions

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