router

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

• Loss: 0.2080
• Accuracy: 0.9221
• F1: 0.7601

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-06
• train_batch_size: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.2283	1.0	990	0.1792	0.9208	0.7547
0.1719	2.0	1980	0.1717	0.9256	0.7648
0.1621	3.0	2970	0.1695	0.9285	0.7747
0.1555	4.0	3960	0.1708	0.9261	0.7695
0.1496	5.0	4950	0.1696	0.9271	0.7673
0.1455	6.0	5940	0.1716	0.9268	0.7648
0.1400	7.0	6930	0.1727	0.9257	0.7681
0.1351	8.0	7920	0.1756	0.9268	0.7700
0.1309	9.0	8910	0.1812	0.9249	0.7667
0.1273	10.0	9900	0.1817	0.9244	0.7654
0.1225	11.0	10890	0.1868	0.9216	0.7629
0.1192	12.0	11880	0.1903	0.9258	0.7687
0.1160	13.0	12870	0.1921	0.9225	0.7638
0.1134	14.0	13860	0.1955	0.9228	0.7604
0.1115	15.0	14850	0.2012	0.9238	0.7625
0.1085	16.0	15840	0.2024	0.9238	0.7598
0.1073	17.0	16830	0.2047	0.9228	0.7618
0.1049	18.0	17820	0.2059	0.9225	0.7613
0.1049	19.0	18810	0.2063	0.9229	0.7641
0.1041	20.0	19800	0.2080	0.9221	0.7601

Framework versions

• Transformers 5.12.1
• Pytorch 2.11.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2