Training in progress epoch 90

README.md

@@ -14,14 +14,14 @@ probably proofread and complete it, then remove this comment. -->
 
 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:
-- Train Loss: 0.0164
-- Train Dice Coef: 0.8041
-- Train Iou: 0.6809
-- Validation Loss: 0.0227
-- Validation Dice Coef: 0.8564
-- Validation Iou: 0.7509
+- Train Loss: 0.0163
+- Train Dice Coef: 0.8029
+- Train Iou: 0.6797
+- Validation Loss: 0.0232
+- Validation Dice Coef: 0.8552
+- Validation Iou: 0.7493
 - Train Lr: 1e-10
-- Epoch: 89
+- Epoch: 90
 
 ## Model description
 
@@ -137,6 +137,7 @@ The following hyperparameters were used during training:
 | 0.0161     | 0.8036          | 0.6806    | 0.0228          | 0.8562               | 0.7507         | 1e-10    | 87    |
 | 0.0160     | 0.8026          | 0.6791    | 0.0230          | 0.8556               | 0.7497         | 1e-10    | 88    |
 | 0.0164     | 0.8041          | 0.6809    | 0.0227          | 0.8564               | 0.7509         | 1e-10    | 89    |
+| 0.0163     | 0.8029          | 0.6797    | 0.0232          | 0.8552               | 0.7493         | 1e-10    | 90    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97c069d6c10ad822347cf917fdc99220fa88b03feb198d14495c05b5a8a1cf52
+oid sha256:10ddb0af5a9203ea53ea1709ace51c717b72f5dfdf9c3bee452ac1a5a820a7b8
 size 15133664