detr-r50-cd45rb-2ah-6l-corrected

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: 1.7676

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: 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: 25
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.4312	1.0	4606	2.4426
2.9035	2.0	9212	2.1671
2.6788	3.0	13818	2.0925
2.5847	4.0	18424	2.0215
2.5075	5.0	23030	1.9689
2.445	6.0	27636	1.9528
2.4078	7.0	32242	1.9058
2.3794	8.0	36848	1.8889
2.3572	9.0	41454	1.8751
2.3374	10.0	46060	1.8623
2.3423	11.0	50666	1.8636
2.3292	12.0	55272	1.8500
2.3078	13.0	59878	1.8354
2.2958	14.0	64484	1.8350
2.2779	15.0	69090	1.8243
2.3118	16.0	73696	1.8304
2.2927	17.0	78302	1.8243
2.2726	18.0	82908	1.8161
2.2546	19.0	87514	1.8106
2.2394	20.0	92120	1.7949
2.237	21.0	96726	1.7747
2.2158	22.0	101332	1.7796
2.2069	23.0	105938	1.7757
2.2061	24.0	110544	1.7746
2.1974	25.0	115150	1.7676

Framework versions

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