End of training

README.md

@@ -14,12 +14,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0442
-- Mean Iou: 0.9324
-- Mean Accuracy: 0.9633
-- Overall Accuracy: 0.9704
-- Per Category Iou: [0.9492969014052214, 0.8833148832537979, 0.9646684118247586]
-- Per Category Accuracy: [0.97225521704602, 0.9314524772776496, 0.9862309492005294]
+- Loss: 0.0450
+- Mean Iou: 0.9318
+- Mean Accuracy: 0.9627
+- Overall Accuracy: 0.9702
+- Per Category Iou: [0.9495813672432459, 0.8813317337391693, 0.9644023822119229]
+- Per Category Accuracy: [0.9727012766324794, 0.9289302189435307, 0.9865368010395725]
 
 ## Model description
 
@@ -49,9 +49,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Per Category Iou                                             | Per Category Accuracy                                      |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------------------------------------------------:|:----------------------------------------------------------:|
-| 0.0545        | 1.0   | 2926 | 0.0442          | 0.9324   | 0.9633        | 0.9704           | [0.9492969014052214, 0.8833148832537979, 0.9646684118247586] | [0.97225521704602, 0.9314524772776496, 0.9862309492005294] |
+| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Per Category Iou                                             | Per Category Accuracy                                        |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------------------------------------------------:|:------------------------------------------------------------:|
+| 0.055         | 1.0   | 2926 | 0.0450          | 0.9318   | 0.9627        | 0.9702           | [0.9495813672432459, 0.8813317337391693, 0.9644023822119229] | [0.9727012766324794, 0.9289302189435307, 0.9865368010395725] |
 
 
 ### Framework versions

config.json

@@ -6,7 +6,7 @@
   "classifier_dropout_prob": 0.1,
   "decoder_hidden_size": 1024,
   "depths": [
-    3,
+    6,
     8,
     18,
     3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adce41dec636ed35d4784899d571b42c638c43799c97f9cd49963408e480706d
-size 369691932
+oid sha256:d1a8064070e889bebaaa6a7c3b650e56afa12901be4a9a985a40a76c816bbcab
+size 384728188