detr_finetuned_cppe5_comparison

This model is a fine-tuned version of Jesse020202/cppe5_setup_on_roadsign_test on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.3939

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	107	1.6000
No log	2.0	214	1.5764
No log	3.0	321	1.5325
No log	4.0	428	1.5211
1.3796	5.0	535	1.5157
1.3796	6.0	642	1.5043
1.3796	7.0	749	1.4820
1.3796	8.0	856	1.4862
1.3796	9.0	963	1.4591
1.2857	10.0	1070	1.4494
1.2857	11.0	1177	1.4363
1.2857	12.0	1284	1.4385
1.2857	13.0	1391	1.4152
1.2857	14.0	1498	1.4067
1.1868	15.0	1605	1.4171
1.1868	16.0	1712	1.3954
1.1868	17.0	1819	1.3961
1.1868	18.0	1926	1.3974
1.1187	19.0	2033	1.3943
1.1187	20.0	2140	1.3939

Framework versions

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