Training in progress epoch 36

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: 0.0168
-- Train Dice Coef: 0.8006
-- Train Iou: 0.6759
+- Train Loss: 0.0167
+- Train Dice Coef: 0.7984
+- Train Iou: 0.6739
 - Validation Loss: 0.0232
-- Validation Dice Coef: 0.8561
-- Validation Iou: 0.7507
+- Validation Dice Coef: 0.8543
+- Validation Iou: 0.7480
 - Train Lr: 5e-06
-- Epoch: 35
+- Epoch: 36
 
 ## Model description
 
@@ -83,6 +83,7 @@ The following hyperparameters were used during training:
 | 0.0175     | 0.7964          | 0.6703    | 0.0232          | 0.8547               | 0.7489         | 5e-06    | 33    |
 | 0.0173     | 0.7972          | 0.6719    | 0.0225          | 0.8556               | 0.7499         | 5e-06    | 34    |
 | 0.0168     | 0.8006          | 0.6759    | 0.0232          | 0.8561               | 0.7507         | 5e-06    | 35    |
+| 0.0167     | 0.7984          | 0.6739    | 0.0232          | 0.8543               | 0.7480         | 5e-06    | 36    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd3a2099bca94f0bfbb3f9cc2638d2e408de15ef0698542f72c22be5f0d398c0
+oid sha256:5b8f66f97dbf5e88bf8f1e0c4c73a81564354c944c1c9f1d29c342b29c529cb4
 size 15133664