Training in progress epoch 64

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: 0.0522
-- Train Dice Coef: 0.8470
-- Train Iou: 0.7434
-- Validation Loss: 0.0445
-- Validation Dice Coef: 0.8859
-- Validation Iou: 0.7961
+- Train Loss: 0.0520
+- Train Dice Coef: 0.8375
+- Train Iou: 0.7356
+- Validation Loss: 0.0446
+- Validation Dice Coef: 0.8857
+- Validation Iou: 0.7958
 - Train Lr: 1e-10
-- Epoch: 63
+- Epoch: 64
 
 ## Model description
 
@@ -111,6 +111,7 @@ The following hyperparameters were used during training:
 | 0.0517     | 0.8436          | 0.7423    | 0.0444          | 0.8853               | 0.7951         | 1e-10    | 61    |
 | 0.0523     | 0.8467          | 0.7443    | 0.0455          | 0.8840               | 0.7932         | 1e-10    | 62    |
 | 0.0522     | 0.8470          | 0.7434    | 0.0445          | 0.8859               | 0.7961         | 1e-10    | 63    |
+| 0.0520     | 0.8375          | 0.7356    | 0.0446          | 0.8857               | 0.7958         | 1e-10    | 64    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcda66c5ca6f3de077bbf3f19a640367514a047d8693bca50694597a98f0d795
+oid sha256:2ace11a1080d4f4b8412f33bafe213c20affb7b47e0dd69bd36dd5b3c66fc215
 size 15133664