segformer-b0-finetuned-brooks-or-dunn
This model is a fine-tuned version of nvidia/mit-b0 on the q2-jlbar/BrooksOrDunn dataset. It achieves the following results on the evaluation set:
- Loss: 0.1158
- Mean Iou: nan
- Mean Accuracy: nan
- Overall Accuracy: nan
- Per Category Iou: [nan, nan]
- Per Category Accuracy: [nan, nan]
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 | Per Category Iou | Per Category Accuracy |
---|---|---|---|---|---|---|---|---|
0.5153 | 4.0 | 20 | 0.5276 | nan | nan | nan | [nan, nan] | [nan, nan] |
0.4082 | 8.0 | 40 | 0.3333 | nan | nan | nan | [nan, nan] | [nan, nan] |
0.3157 | 12.0 | 60 | 0.2773 | nan | nan | nan | [nan, nan] | [nan, nan] |
0.2911 | 16.0 | 80 | 0.2389 | nan | nan | nan | [nan, nan] | [nan, nan] |
0.2395 | 20.0 | 100 | 0.1982 | nan | nan | nan | [nan, nan] | [nan, nan] |
0.2284 | 24.0 | 120 | 0.1745 | nan | nan | nan | [nan, nan] | [nan, nan] |
0.1818 | 28.0 | 140 | 0.1595 | nan | nan | nan | [nan, nan] | [nan, nan] |
0.1549 | 32.0 | 160 | 0.1556 | nan | nan | nan | [nan, nan] | [nan, nan] |
0.1351 | 36.0 | 180 | 0.1387 | nan | nan | nan | [nan, nan] | [nan, nan] |
0.1254 | 40.0 | 200 | 0.1263 | nan | nan | nan | [nan, nan] | [nan, nan] |
0.1412 | 44.0 | 220 | 0.1190 | nan | nan | nan | [nan, nan] | [nan, nan] |
0.1179 | 48.0 | 240 | 0.1158 | nan | nan | nan | [nan, nan] | [nan, nan] |
Framework versions
- Transformers 4.19.2
- Pytorch 1.11.0
- Datasets 2.2.2
- Tokenizers 0.12.1
- Downloads last month
- 7
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.