detr-r50-cd45rb-8ah-4l-auxiliary_loss

This model is a fine-tuned version of facebook/detr-resnet-50 on the cd45rb_nan_xywh dataset. It achieves the following results on the evaluation set:

• Loss: 8.7759

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: 1e-06
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
14.0935	1.0	4606	10.4579
12.8064	2.0	9212	9.8350
12.2489	3.0	13818	9.4135
11.9486	4.0	18424	9.1927
11.7307	5.0	23030	9.0325
11.5563	6.0	27636	8.9349
11.4443	7.0	32242	8.8621
11.3564	8.0	36848	8.8135
11.3138	9.0	41454	8.7909
11.294	10.0	46060	8.7759

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1
• Datasets 2.12.0
• Tokenizers 0.13.3