detr-r101-cd45rb-8ah-6l-256d-4096ffn-correcetd

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

• Loss: 1.5819

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
2.3194	1.0	4606	1.7874
2.3461	2.0	9212	1.8376
2.3028	3.0	13818	1.9087
2.2979	4.0	18424	1.9066
2.273	5.0	23030	1.7689
2.2372	6.0	27636	1.8501
2.2429	7.0	32242	1.7625
2.2066	8.0	36848	1.7588
2.1914	9.0	41454	1.7062
2.1553	10.0	46060	1.7069
2.1302	11.0	50666	1.6863
2.1321	12.0	55272	1.7722
2.1227	13.0	59878	1.6639
2.087	14.0	64484	1.6486
2.0676	15.0	69090	1.6632
2.0604	16.0	73696	1.6429
2.0435	17.0	78302	1.6224
2.0241	18.0	82908	1.6321
2.0041	19.0	87514	1.5970
1.9966	20.0	92120	1.5943
2.0165	21.0	96726	1.6092
2.007	22.0	101332	1.5986
2.0009	23.0	105938	1.5931
1.992	24.0	110544	1.5898
1.9769	25.0	115150	1.5819

Framework versions

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