results

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

• Loss: 1.7669

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss
12.8436	1.0	4	11.5652
12.8436	2.0	8	8.6499
12.8436	3.0	12	6.6430
12.8436	4.0	16	5.4425
12.8436	5.0	20	4.4521
12.8436	6.0	24	3.9127
12.8436	7.0	28	3.3273
12.8436	8.0	32	3.0743
12.8436	9.0	36	2.8087
12.8436	10.0	40	2.5618
12.8436	11.0	44	2.4515
12.8436	12.0	48	2.3580
12.8436	13.0	52	2.2749
12.8436	14.0	56	2.1216
12.8436	15.0	60	2.0890
12.8436	16.0	64	2.0283
12.8436	17.0	68	2.0358
12.8436	18.0	72	1.9374
12.8436	19.0	76	1.9090
12.8436	20.0	80	1.8779
12.8436	21.0	84	1.8474
12.8436	22.0	88	1.8371
12.8436	23.0	92	1.8247
12.8436	24.0	96	1.8031
12.8436	25.0	100	1.7836
12.8436	26.0	104	1.7500
12.8436	27.0	108	1.7332
12.8436	28.0	112	1.7477
12.8436	29.0	116	1.7634
12.8436	30.0	120	1.7669

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cpu
• Datasets 3.3.2
• Tokenizers 0.21.0