Training in progress epoch 81

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: 0.0161
-- Train Dice Coef: 0.8034
-- Train Iou: 0.6798
-- Validation Loss: 0.0227
-- Validation Dice Coef: 0.8559
-- Validation Iou: 0.7504
+- Train Loss: 0.0163
+- Train Dice Coef: 0.8076
+- Train Iou: 0.6850
+- Validation Loss: 0.0230
+- Validation Dice Coef: 0.8569
+- Validation Iou: 0.7517
 - Train Lr: 1e-10
-- Epoch: 80
+- Epoch: 81
 
 ## Model description
 
@@ -128,6 +128,7 @@ The following hyperparameters were used during training:
 | 0.0161     | 0.8060          | 0.6825    | 0.0225          | 0.8574               | 0.7525         | 1e-10    | 78    |
 | 0.0159     | 0.8051          | 0.6825    | 0.0227          | 0.8561               | 0.7506         | 1e-10    | 79    |
 | 0.0161     | 0.8034          | 0.6798    | 0.0227          | 0.8559               | 0.7504         | 1e-10    | 80    |
+| 0.0163     | 0.8076          | 0.6850    | 0.0230          | 0.8569               | 0.7517         | 1e-10    | 81    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:202637b9f12c6ddcbff803600ae23a6e31916c50aaba61565949adcafbfd1135
+oid sha256:c1ea120337c4c9443c0d89fd449c1fb36216726b6c5b45d24b85ccf0fa2ce4c1
 size 15133664