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: 0.1907
• Accuracy: 0.9283
• F1: 0.7560

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
0.2057	1.0	1263	0.1581	0.9331	0.7544
0.1583	2.0	2526	0.1528	0.9345	0.7663
0.1502	3.0	3789	0.1528	0.9352	0.7711
0.1439	4.0	5052	0.1508	0.9356	0.7676
0.1394	5.0	6315	0.1538	0.9345	0.7692
0.1348	6.0	7578	0.1550	0.9329	0.7713
0.1307	7.0	8841	0.1584	0.9319	0.7708
0.1259	8.0	10104	0.1610	0.9339	0.7678
0.1222	9.0	11367	0.1643	0.9329	0.7687
0.1185	10.0	12630	0.1688	0.9290	0.7642
0.1150	11.0	13893	0.1682	0.9318	0.7644
0.1123	12.0	15156	0.1701	0.9303	0.7616
0.1099	13.0	16419	0.1750	0.9308	0.7608
0.1063	14.0	17682	0.1792	0.9295	0.7607
0.1039	15.0	18945	0.1817	0.9297	0.7593
0.1022	16.0	20208	0.1833	0.9294	0.7544
0.1004	17.0	21471	0.1867	0.9280	0.7570
0.0993	18.0	22734	0.1883	0.9290	0.7582
0.0982	19.0	23997	0.1903	0.9280	0.7552
0.0972	20.0	25260	0.1907	0.9283	0.7560

Framework versions

• Transformers 5.16.1
• Pytorch 2.11.0+cu128
• Datasets 4.8.5
• Tokenizers 0.23.1