metadata

license: other
base_model: nvidia/mit-b5
tags:
  - generated_from_trainer
model-index:
  - name: Test-SegFormer_Mixed_Set2_788images_mit-b5_RGB
    results: []

Test-SegFormer_Mixed_Set2_788images_mit-b5_RGB

This model is a fine-tuned version of nvidia/mit-b5 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1661
Mean Iou: 0.7900
Mean Accuracy: 0.8412
Overall Accuracy: 0.9471
Accuracy Background: 0.9799
Accuracy Melt: 0.5677
Accuracy Substrate: 0.9760
Iou Background: 0.9430
Iou Melt: 0.4987
Iou Substrate: 0.9285

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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Mean Iou	Mean Accuracy	Overall Accuracy	Accuracy Background	Accuracy Melt	Accuracy Substrate	Iou Background	Iou Melt	Iou Substrate
0.1897	0.7042	50	0.1661	0.7900	0.8412	0.9471	0.9799	0.5677	0.9760	0.9430	0.4987	0.9285

Framework versions

Transformers 4.41.2
Pytorch 2.0.1+cu117
Datasets 2.19.2
Tokenizers 0.19.1