Training in progress epoch 27

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: 0.0191
-- Train Dice Coef: 0.7890
-- Train Iou: 0.6608
-- Validation Loss: 0.0239
+- Train Loss: 0.0180
+- Train Dice Coef: 0.7930
+- Train Iou: 0.6662
+- Validation Loss: 0.0236
 - Validation Dice Coef: 0.8574
-- Validation Iou: 0.7525
+- Validation Iou: 0.7524
 - Train Lr: 1e-04
-- Epoch: 26
+- Epoch: 27
 
 ## Model description
 
@@ -74,6 +74,7 @@ The following hyperparameters were used during training:
 | 0.0196     | 0.7853          | 0.6556    | 0.0241          | 0.8552               | 0.7494         | 1e-04    | 24    |
 | 0.0197     | 0.7813          | 0.6512    | 0.0236          | 0.8529               | 0.7464         | 1e-04    | 25    |
 | 0.0191     | 0.7890          | 0.6608    | 0.0239          | 0.8574               | 0.7525         | 1e-04    | 26    |
+| 0.0180     | 0.7930          | 0.6662    | 0.0236          | 0.8574               | 0.7524         | 1e-04    | 27    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38739f7f9f0816ef031d8b7f7b27a0c585e43eb66dcacbaed780f56eb0d93ca1
+oid sha256:a66dc5a9a4d6de591cb2f0fd0ea29ceb0757bd1af4b2b3d6561746c0e5b977d3
 size 15133664