detr-resnet-101_adafactor_finetuned_food-roboflow

This model is a fine-tuned version of facebook/detr-resnet-101 on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 3.1003

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: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
6.5311	0.77	50	6.4188
5.6597	1.54	100	5.8132
5.1568	2.31	150	5.1265
4.4672	3.08	200	4.3264
3.8033	3.85	250	3.9444
3.2053	4.62	300	3.6319
3.127	5.38	350	3.3079
2.9082	6.15	400	3.1760
2.8546	6.92	450	3.1659
2.8393	7.69	500	3.0233
2.6973	8.46	550	3.0817
2.7047	9.23	600	3.0849
2.673	10.0	650	3.1122
2.6781	10.77	700	3.0709
2.5901	11.54	750	3.0382
2.6568	12.31	800	3.0246
2.5929	13.08	850	3.0384
2.5709	13.85	900	2.9862
2.5784	14.62	950	3.1003

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1