yolo_raccoon

This model is a fine-tuned version of hustvl/yolos-tiny on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.7699

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: 2
• 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: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
1.2306	1.0	70	2.0604
1.0982	2.0	140	1.8601
1.2858	3.0	210	1.9219
0.7918	4.0	280	1.7710
0.9235	5.0	350	1.7007
0.6908	6.0	420	1.8113
1.1367	7.0	490	1.7346
1.1563	8.0	560	1.6220
0.6276	9.0	630	0.8717
0.7245	10.0	700	0.8536
0.8999	11.0	770	0.8692
0.5880	12.0	840	0.8040
0.8655	13.0	910	0.7879
0.6180	14.0	980	0.7718
0.6380	15.0	1050	0.7577
0.5268	16.0	1120	0.7722
0.6078	17.0	1190	0.7728
0.7834	18.0	1260	0.7785
0.5730	19.0	1330	0.7668
0.6450	20.0	1400	0.7699

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2