detr_finetuned_cppe5

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

• Loss: 1.1909

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	107	1.9270
No log	2.0	214	1.7725
No log	3.0	321	1.6696
No log	4.0	428	1.6196
2.6515	5.0	535	1.5855
2.6515	6.0	642	1.5091
2.6515	7.0	749	1.4790
2.6515	8.0	856	1.4786
2.6515	9.0	963	1.3819
1.3311	10.0	1070	1.3668
1.3311	11.0	1177	1.3966
1.3311	12.0	1284	1.3492
1.3311	13.0	1391	1.3223
1.3311	14.0	1498	1.2781
1.1672	15.0	1605	1.2749
1.1672	16.0	1712	1.2671
1.1672	17.0	1819	1.2488
1.1672	18.0	1926	1.2500
1.0429	19.0	2033	1.2274
1.0429	20.0	2140	1.2308
1.0429	21.0	2247	1.2249
1.0429	22.0	2354	1.2157
1.0429	23.0	2461	1.2147
0.9595	24.0	2568	1.1956
0.9595	25.0	2675	1.1880
0.9595	26.0	2782	1.1912
0.9595	27.0	2889	1.1916
0.9595	28.0	2996	1.1921
0.9097	29.0	3103	1.1912
0.9097	30.0	3210	1.1909

Framework versions

• Transformers 4.56.2
• Pytorch 2.8.0
• Datasets 4.1.1
• Tokenizers 0.22.1