segformer-finetuned-TMSL21_Sunlit_Tomatoes

This model is a fine-tuned version of nvidia/mit-b0 on the janakipanneerselvam/TMSL21_Sunlit_Tomatoes dataset. It achieves the following results on the evaluation set:

• Loss: 0.0197
• Mean Iou: 0.0
• Mean Accuracy: nan
• Overall Accuracy: nan
• Accuracy Sunlit: nan
• Iou Sunlit: 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: 8
• eval_batch_size: 8
• seed: 1337
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: polynomial
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Sunlit	Iou Sunlit
0.0164	0.24	100	0.0197	0.0	nan	nan	nan	0.0

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0