Training in progress epoch 75

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: 0.8455
-- Train Iou: 0.7441
-- Validation Loss: 0.0449
-- Validation Dice Coef: 0.8846
-- Validation Iou: 0.7940
+- Train Loss: 0.0519
+- Train Dice Coef: 0.8351
+- Train Iou: 0.7330
+- Validation Loss: 0.0445
+- Validation Dice Coef: 0.8852
+- Validation Iou: 0.7948
 - Train Lr: 1e-10
-- Epoch: 74
+- Epoch: 75
 
 ## Model description
 
@@ -122,6 +122,7 @@ The following hyperparameters were used during training:
 | 0.0520     | 0.8364          | 0.7345    | 0.0454          | 0.8841               | 0.7933         | 1e-10    | 72    |
 | 0.0528     | 0.8468          | 0.7431    | 0.0452          | 0.8846               | 0.7939         | 1e-10    | 73    |
 | 0.0518     | 0.8455          | 0.7441    | 0.0449          | 0.8846               | 0.7940         | 1e-10    | 74    |
+| 0.0519     | 0.8351          | 0.7330    | 0.0445          | 0.8852               | 0.7948         | 1e-10    | 75    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abaef83581439d42689f19cc59036757b40d24d6cded992b91da5be784b8d2b9
+oid sha256:d173285ed1c6af6dd0e399b0142b8ee5f251002a9d68dca435df2140c5e6ce18
 size 15133664