detr-resnet-50-CD45RB-1000-att

This model is a fine-tuned version of facebook/detr-resnet-50 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.7065

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: 0.0001
• 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: 25

Training results

Training Loss	Epoch	Step	Validation Loss
3.4338	1.0	94	2.4137
2.9565	2.0	188	2.1738
2.7101	3.0	282	2.0122
2.7515	4.0	376	1.9646
2.724	5.0	470	2.1284
2.6193	6.0	564	1.9380
2.5032	7.0	658	1.9286
2.5342	8.0	752	1.9366
2.5519	9.0	846	1.9736
2.4988	10.0	940	1.8816
2.5101	11.0	1034	1.8454
2.4441	12.0	1128	1.8143
2.3857	13.0	1222	1.7919
2.2877	14.0	1316	1.7400
2.3013	15.0	1410	1.7409
2.3134	16.0	1504	1.7698
2.3423	17.0	1598	1.7581
2.3536	18.0	1692	1.7658
2.2957	19.0	1786	1.7329
2.274	20.0	1880	1.7335
2.2906	21.0	1974	1.7343
2.2492	22.0	2068	1.7080
2.2516	23.0	2162	1.7180
2.2574	24.0	2256	1.7081
2.2508	25.0	2350	1.7065

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.1+cu116
• Datasets 2.10.0
• Tokenizers 0.13.2