detr_finetuned_roadsigns_poisoned

This model is a fine-tuned version of Jesse020202/detr_finetuned_roadsigns on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7780

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: 25

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	35	1.0743
No log	2.0	70	1.0560
No log	3.0	105	0.9479
No log	4.0	140	0.8907
No log	5.0	175	0.9357
No log	6.0	210	0.9149
No log	7.0	245	0.9574
No log	8.0	280	0.9942
No log	9.0	315	0.8970
No log	10.0	350	0.8994
No log	11.0	385	0.8997
No log	12.0	420	0.8442
No log	13.0	455	0.8805
No log	14.0	490	0.8440
0.9464	15.0	525	0.8098
0.9464	16.0	560	0.8108
0.9464	17.0	595	0.8385
0.9464	18.0	630	0.8016
0.9464	19.0	665	0.8070
0.9464	20.0	700	0.7925
0.9464	21.0	735	0.7861
0.9464	22.0	770	0.7869
0.9464	23.0	805	0.7721
0.9464	24.0	840	0.7776
0.9464	25.0	875	0.7780

Framework versions

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