detr-r50-cd45rb-7k-8ah

This model is a fine-tuned version of facebook/detr-resnet-50 on the cd45rb dataset. It achieves the following results on the evaluation set:

• Loss: 1.7164

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-05
• train_batch_size: 8
• 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
2.5817	1.0	896	1.9431
2.2882	2.0	1792	1.8638
2.2236	3.0	2688	1.8089
2.1649	4.0	3584	1.7843
2.1275	5.0	4480	1.7593
2.1176	6.0	5376	1.7542
2.1037	7.0	6272	1.7386
2.0969	8.0	7168	1.7242
2.0794	9.0	8064	1.7200
2.0792	10.0	8960	1.7164

The training took 3 hours 15 minutes on NVIDIA GPU.

Framework versions

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