--- license: other tags: - generated_from_trainer model-index: - name: segformer-b0-finetuned-segments-toolwear results: [] --- # segformer-b0-finetuned-segments-toolwear This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co./nvidia/mit-b0) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0332 - Mean Iou: 0.4969 - Mean Accuracy: 0.9938 - Overall Accuracy: 0.9938 - Accuracy Unlabeled: nan - Accuracy Tool: 0.9938 - Iou Unlabeled: 0.0 - Iou Tool: 0.9938 ## 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 Unlabeled | Accuracy Tool | Iou Unlabeled | Iou Tool | |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:-------------:|:-------------:|:--------:| | 0.1957 | 1.82 | 20 | 0.3708 | 0.4995 | 0.9991 | 0.9991 | nan | 0.9991 | 0.0 | 0.9991 | | 0.1896 | 3.64 | 40 | 0.1768 | 0.4985 | 0.9970 | 0.9970 | nan | 0.9970 | 0.0 | 0.9970 | | 0.1022 | 5.45 | 60 | 0.0996 | 0.4966 | 0.9933 | 0.9933 | nan | 0.9933 | 0.0 | 0.9933 | | 0.0855 | 7.27 | 80 | 0.0863 | 0.4767 | 0.9535 | 0.9535 | nan | 0.9535 | 0.0 | 0.9535 | | 0.1223 | 9.09 | 100 | 0.0677 | 0.4964 | 0.9927 | 0.9927 | nan | 0.9927 | 0.0 | 0.9927 | | 0.0791 | 10.91 | 120 | 0.0583 | 0.4948 | 0.9896 | 0.9896 | nan | 0.9896 | 0.0 | 0.9896 | | 0.0521 | 12.73 | 140 | 0.0500 | 0.4938 | 0.9876 | 0.9876 | nan | 0.9876 | 0.0 | 0.9876 | | 0.0397 | 14.55 | 160 | 0.0443 | 0.4958 | 0.9916 | 0.9916 | nan | 0.9916 | 0.0 | 0.9916 | | 0.0283 | 16.36 | 180 | 0.0594 | 0.4972 | 0.9943 | 0.9943 | nan | 0.9943 | 0.0 | 0.9943 | | 0.0378 | 18.18 | 200 | 0.0485 | 0.4987 | 0.9974 | 0.9974 | nan | 0.9974 | 0.0 | 0.9974 | | 0.0347 | 20.0 | 220 | 0.0382 | 0.4971 | 0.9941 | 0.9941 | nan | 0.9941 | 0.0 | 0.9941 | | 0.0245 | 21.82 | 240 | 0.0346 | 0.4966 | 0.9932 | 0.9932 | nan | 0.9932 | 0.0 | 0.9932 | | 0.0425 | 23.64 | 260 | 0.0393 | 0.4961 | 0.9921 | 0.9921 | nan | 0.9921 | 0.0 | 0.9921 | | 0.0293 | 25.45 | 280 | 0.0336 | 0.4973 | 0.9946 | 0.9946 | nan | 0.9946 | 0.0 | 0.9946 | | 0.0247 | 27.27 | 300 | 0.0368 | 0.4972 | 0.9944 | 0.9944 | nan | 0.9944 | 0.0 | 0.9944 | | 0.0287 | 29.09 | 320 | 0.0317 | 0.4958 | 0.9915 | 0.9915 | nan | 0.9915 | 0.0 | 0.9915 | | 0.0254 | 30.91 | 340 | 0.0408 | 0.4966 | 0.9932 | 0.9932 | nan | 0.9932 | 0.0 | 0.9932 | | 0.0347 | 32.73 | 360 | 0.0291 | 0.4965 | 0.9930 | 0.9930 | nan | 0.9930 | 0.0 | 0.9930 | | 0.0174 | 34.55 | 380 | 0.0361 | 0.4978 | 0.9955 | 0.9955 | nan | 0.9955 | 0.0 | 0.9955 | | 0.0191 | 36.36 | 400 | 0.0417 | 0.4972 | 0.9944 | 0.9944 | nan | 0.9944 | 0.0 | 0.9944 | | 0.0234 | 38.18 | 420 | 0.0373 | 0.4974 | 0.9947 | 0.9947 | nan | 0.9947 | 0.0 | 0.9947 | | 0.0306 | 40.0 | 440 | 0.0370 | 0.4969 | 0.9938 | 0.9938 | nan | 0.9938 | 0.0 | 0.9938 | | 0.0178 | 41.82 | 460 | 0.0407 | 0.4973 | 0.9946 | 0.9946 | nan | 0.9946 | 0.0 | 0.9946 | | 0.0152 | 43.64 | 480 | 0.0323 | 0.4968 | 0.9935 | 0.9935 | nan | 0.9935 | 0.0 | 0.9935 | | 0.0181 | 45.45 | 500 | 0.0346 | 0.4974 | 0.9947 | 0.9947 | nan | 0.9947 | 0.0 | 0.9947 | | 0.0155 | 47.27 | 520 | 0.0338 | 0.4971 | 0.9942 | 0.9942 | nan | 0.9942 | 0.0 | 0.9942 | | 0.0223 | 49.09 | 540 | 0.0332 | 0.4969 | 0.9938 | 0.9938 | nan | 0.9938 | 0.0 | 0.9938 | ### Framework versions - Transformers 4.28.0 - Pytorch 2.0.1+cu118 - Datasets 2.14.5 - Tokenizers 0.13.3