cppe5_setup_on_roadsign_test

This model is a fine-tuned version of microsoft/conditional-detr-resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.4669

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: 8
• eval_batch_size: 8
• 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: cosine
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	107	2.1197
No log	2.0	214	2.1379
No log	3.0	321	1.9321
No log	4.0	428	1.8901
2.718	5.0	535	1.8736
2.718	6.0	642	1.8040
2.718	7.0	749	1.7457
2.718	8.0	856	1.7353
2.718	9.0	963	1.7223
1.6615	10.0	1070	1.6739
1.6615	11.0	1177	1.7112
1.6615	12.0	1284	1.6121
1.6615	13.0	1391	1.6118
1.6615	14.0	1498	1.5623
1.5122	15.0	1605	1.5774
1.5122	16.0	1712	1.5583
1.5122	17.0	1819	1.5591
1.5122	18.0	1926	1.5253
1.4095	19.0	2033	1.5523
1.4095	20.0	2140	1.5213
1.4095	21.0	2247	1.5017
1.4095	22.0	2354	1.5023
1.4095	23.0	2461	1.4772
1.3312	24.0	2568	1.4792
1.3312	25.0	2675	1.4729
1.3312	26.0	2782	1.4712
1.3312	27.0	2889	1.4693
1.3312	28.0	2996	1.4683
1.2782	29.0	3103	1.4671
1.2782	30.0	3210	1.4669

Framework versions

• Transformers 4.56.2
• Pytorch 2.8.0
• Datasets 4.1.1
• Tokenizers 0.22.1