detr-output

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

• Loss: 1.1673

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 22

Training results

Training Loss	Epoch	Step	Validation Loss
1.8638	1.0	375	1.7503
1.6596	2.0	750	1.5301
1.5249	3.0	1125	1.4235
1.4242	4.0	1500	1.3329
1.4742	5.0	1875	1.2970
1.4456	6.0	2250	1.2932
1.3141	7.0	2625	1.2498
1.324	8.0	3000	1.2866
1.2409	9.0	3375	1.2176
1.2627	10.0	3750	1.2144
1.2766	11.0	4125	1.2022
1.1991	12.0	4500	1.2160
1.2742	13.0	4875	1.1897
1.1589	14.0	5250	1.1766
1.2242	15.0	5625	1.1663
1.1877	16.0	6000	1.1514
1.1424	17.0	6375	1.1267
1.0781	18.0	6750	1.1135
1.1314	19.0	7125	1.1248
1.1174	20.0	7500	1.1034
1.0465	21.0	7875	1.1073
1.1111	22.0	8250	1.1166

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1