cdetr-r50-cd45rb-all-4ah

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

• Loss: 1.7969

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: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.165	1.0	2303	2.0257
1.9843	2.0	4606	1.9742
1.9296	3.0	6909	1.9123
1.8949	4.0	9212	1.8928
1.8751	5.0	11515	1.9116
1.854	6.0	13818	1.8909
1.8354	7.0	16121	1.8533
1.8257	8.0	18424	1.8407
1.8101	9.0	20727	1.8453
1.8025	10.0	23030	1.8344
1.8177	11.0	25333	1.8496
1.8092	12.0	27636	1.8584
1.8016	13.0	29939	1.8277
1.7961	14.0	32242	1.8230
1.7853	15.0	34545	1.8130
1.7769	16.0	36848	1.8098
1.7708	17.0	39151	1.8030
1.7626	18.0	41454	1.7994
1.7596	19.0	43757	1.8018
1.7547	20.0	46060	1.7969

Framework versions

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