End of training

README.md

@@ -15,17 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [nvidia/mit-b3](https://huggingface.co/nvidia/mit-b3) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.0537
-- eval_mean_iou: 0.7604
-- eval_mean_accuracy: 0.8281
-- eval_overall_accuracy: 0.9788
-- eval_per_category_iou: [0.9782807410260149, 0.5424475354128461]
-- eval_per_category_accuracy: [0.9911386477455301, 0.6649739140722758]
-- eval_runtime: 1877.8784
-- eval_samples_per_second: 1.459
-- eval_steps_per_second: 0.365
-- epoch: 1.0
-- step: 1370
+- Loss: 0.0487
+- Mean Iou: 0.7770
+- Mean Accuracy: 0.8378
+- Overall Accuracy: 0.9803
+- Per Category Iou: [0.9797338315128605, 0.5741766454919031]
+- Per Category Accuracy: [0.9922972168222592, 0.683379436844461]
 
 ## Model description
 
@@ -44,14 +39,30 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 6e-05
+- learning_rate: 3e-05
 - train_batch_size: 8
-- eval_batch_size: 4
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 10
 
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Per Category Iou                         | Per Category Accuracy                    |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:-------------:|:----------------:|:----------------------------------------:|:----------------------------------------:|
+| 0.0651        | 1.0   | 1541  | 0.0557          | 0.7543   | 0.8089        | 0.9785           | [0.9779508845325062, 0.5306877773356943] | [0.9928050418870356, 0.6249652426334233] |
+| 0.0491        | 2.0   | 3082  | 0.0522          | 0.7629   | 0.8195        | 0.9792           | [0.9786365168660656, 0.547127323866261]  | [0.9926515789371488, 0.6463984572343288] |
+| 0.047         | 3.0   | 4623  | 0.0546          | 0.7519   | 0.7995        | 0.9787           | [0.9782301112609909, 0.5255903669562288] | [0.9938779990669149, 0.6050380673194482] |
+| 0.0456        | 4.0   | 6164  | 0.0510          | 0.7671   | 0.8248        | 0.9795           | [0.9789779157265575, 0.5552760281623849] | [0.9925739681553413, 0.6570897409273347] |
+| 0.0442        | 5.0   | 7705  | 0.0509          | 0.7714   | 0.8373        | 0.9794           | [0.978875460970978, 0.5639303830124743]  | [0.9914357800230804, 0.6831791371245445] |
+| 0.0439        | 6.0   | 9246  | 0.0502          | 0.7701   | 0.8254        | 0.9799           | [0.9794166328395213, 0.5607787508694683] | [0.9929877378064772, 0.6578722690116804] |
+| 0.0433        | 7.0   | 10787 | 0.0500          | 0.7738   | 0.8361        | 0.9799           | [0.979329611841869, 0.5681732097856239]  | [0.9920131586953994, 0.6802192080134767] |
+| 0.0427        | 8.0   | 12328 | 0.0499          | 0.7775   | 0.8406        | 0.9802           | [0.9796585654955907, 0.575368007293997]  | [0.9919935734749642, 0.6891110848654891] |
+| 0.0424        | 9.0   | 13869 | 0.0495          | 0.7780   | 0.8411        | 0.9802           | [0.9797042588379468, 0.5763456606457494] | [0.9919931330972266, 0.6902882749336847] |
+| 0.042         | 10.0  | 15410 | 0.0487          | 0.7770   | 0.8378        | 0.9803           | [0.9797338315128605, 0.5741766454919031] | [0.9922972168222592, 0.683379436844461]  |
+
+
 ### Framework versions
 
 - Transformers 4.33.1

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34d1ca6848dddb932d7f24f5d9c066fcab1f7d012f68818f200111b69fddcd07
+oid sha256:817ac2ebc6bba833b6fdce9530046c9ab9993db31fd44455a540eb8d4089dea4
 size 189125277

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbdeaefe28fc1effadbeca870adbda871399536242068435c3521d48031c0fd6
+oid sha256:edfea9e34d43dc2ec84e7ca6674ac47703473a2bf4b27c130c429c320439637c
 size 4027