Training in progress epoch 50

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: 0.0521
-- Train Dice Coef: 0.8447
-- Train Iou: 0.7433
-- Validation Loss: 0.0442
-- Validation Dice Coef: 0.8859
-- Validation Iou: 0.7961
+- Train Loss: 0.0520
+- Train Dice Coef: 0.8382
+- Train Iou: 0.7359
+- Validation Loss: 0.0453
+- Validation Dice Coef: 0.8838
+- Validation Iou: 0.7929
 - Train Lr: 1e-10
-- Epoch: 49
+- Epoch: 50
 
 ## Model description
 
@@ -97,6 +97,7 @@ The following hyperparameters were used during training:
 | 0.0519     | 0.8388          | 0.7368    | 0.0447          | 0.8839               | 0.7929         | 1e-10    | 47    |
 | 0.0518     | 0.8456          | 0.7438    | 0.0448          | 0.8847               | 0.7943         | 1e-10    | 48    |
 | 0.0521     | 0.8447          | 0.7433    | 0.0442          | 0.8859               | 0.7961         | 1e-10    | 49    |
+| 0.0520     | 0.8382          | 0.7359    | 0.0453          | 0.8838               | 0.7929         | 1e-10    | 50    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dd1dab4305adf6c630fffd20cdc61ebd74295296a88a3e26cce23a74ac2222c
+oid sha256:e9c49bbc1c0636dfd741320b903f6f3840de46d642263a2d08d47213b3e070b3
 size 15133664