dfine-xl_sku110k

This model is a fine-tuned version of ustc-community/dfine-xlarge-obj365 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.3555
• Map: 0.2955
• Map 50: 0.4836
• Map 75: 0.3305
• Map Small: 0.1282
• Map Medium: 0.339
• Map Large: 0.2481
• Mar 1: 0.0027
• Mar 10: 0.0365
• Mar 100: 0.3884
• Mar Small: 0.1743
• Mar Medium: 0.4291
• Mar Large: 0.4861
• Map Object: 0.2955
• Mar 100 Object: 0.3884

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• 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: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Map	Map 50	Map 75	Map Small	Map Medium	Map Large	Mar 1	Mar 10	Mar 100	Mar Small	Mar Medium	Mar Large	Map Object	Mar 100 Object
24.8322	1.0	1028	2.3555	0.2955	0.4836	0.3305	0.1282	0.339	0.2481	0.0027	0.0365	0.3884	0.1743	0.4291	0.4861	0.2955	0.3884

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.0+cu126
• Datasets 4.5.0
• Tokenizers 0.22.2