Training in progress epoch 49

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: 0.0518
-- Train Dice Coef: 0.8456
-- Train Iou: 0.7438
-- Validation Loss: 0.0448
-- Validation Dice Coef: 0.8847
-- Validation Iou: 0.7943
+- 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 Lr: 1e-10
-- Epoch: 48
+- Epoch: 49
 
 ## Model description
 
@@ -96,6 +96,7 @@ The following hyperparameters were used during training:
 | 0.0519     | 0.8445          | 0.7434    | 0.0446          | 0.8858               | 0.7959         | 6.25e-10 | 46    |
 | 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    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00ebd3f7f720c9fa4aba0af94ff52c2a50026456136ed32c40c4ca0e94cf32d6
+oid sha256:5dd1dab4305adf6c630fffd20cdc61ebd74295296a88a3e26cce23a74ac2222c
 size 15133664