datadome-slider-b0-finetuned-segments-missing-puzzle-mar-1

This model is a fine-tuned version of nvidia/mit-b0 on the bfwggggg/image-with-puzzle dataset. It achieves the following results on the evaluation set:

• Loss: 0.2458
• Mean Iou: 0.0
• Mean Accuracy: nan
• Overall Accuracy: nan
• Accuracy Missing-puzzle: nan
• Iou Missing-puzzle: 0.0

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: 6e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Missing-puzzle	Iou Missing-puzzle
0.4987	5.0	20	0.6323	0.0	nan	nan	nan	0.0
0.388	10.0	40	0.4734	0.0	nan	nan	nan	0.0
0.3014	15.0	60	0.3631	0.0	nan	nan	nan	0.0
0.3179	20.0	80	0.3405	0.0	nan	nan	nan	0.0
0.2963	25.0	100	0.2696	0.0	nan	nan	nan	0.0
0.2458	30.0	120	0.2803	0.0	nan	nan	nan	0.0
0.2757	35.0	140	0.2635	0.0	nan	nan	nan	0.0
0.2519	40.0	160	0.2522	0.0	nan	nan	nan	0.0
0.2349	45.0	180	0.2474	0.0	nan	nan	nan	0.0
0.212	50.0	200	0.2458	0.0	nan	nan	nan	0.0

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2