Training in progress epoch 78

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: 0.0525
-- Train Dice Coef: 0.8467
-- Train Iou: 0.7449
-- Validation Loss: 0.0456
-- Validation Dice Coef: 0.8836
-- Validation Iou: 0.7925
+- Train Loss: 0.0522
+- Train Dice Coef: 0.8436
+- Train Iou: 0.7397
+- Validation Loss: 0.0445
+- Validation Dice Coef: 0.8847
+- Validation Iou: 0.7942
 - Train Lr: 1e-10
-- Epoch: 77
+- Epoch: 78
 
 ## Model description
 
@@ -125,6 +125,7 @@ The following hyperparameters were used during training:
 | 0.0519     | 0.8351          | 0.7330    | 0.0445          | 0.8852               | 0.7948         | 1e-10    | 75    |
 | 0.0521     | 0.8423          | 0.7406    | 0.0453          | 0.8849               | 0.7945         | 1e-10    | 76    |
 | 0.0525     | 0.8467          | 0.7449    | 0.0456          | 0.8836               | 0.7925         | 1e-10    | 77    |
+| 0.0522     | 0.8436          | 0.7397    | 0.0445          | 0.8847               | 0.7942         | 1e-10    | 78    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97fcf3d84717f0acd4a2aed7b7e948490fe24638779b8780dbadd51e46d2bcc6
+oid sha256:5d9dd069528c3d0177770113d3ead232c7d6d6214188d0bc568e93b5f0a0391f
 size 15133664