Training in progress epoch 51

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: 0.0188
-- Train Dice Coef: 0.7813
-- Train Iou: 0.6529
-- Validation Loss: 0.0235
-- Validation Dice Coef: 0.8491
-- Validation Iou: 0.7418
+- Train Loss: 0.0186
+- Train Dice Coef: 0.7770
+- Train Iou: 0.6498
+- Validation Loss: 0.0229
+- Validation Dice Coef: 0.8504
+- Validation Iou: 0.7435
 - Train Lr: 1e-10
-- Epoch: 50
+- Epoch: 51
 
 ## Model description
 
@@ -98,6 +98,7 @@ The following hyperparameters were used during training:
 | 0.0187     | 0.7777          | 0.6497    | 0.0233          | 0.8493               | 0.7419         | 1e-10    | 48    |
 | 0.0187     | 0.7785          | 0.6498    | 0.0230          | 0.8502               | 0.7432         | 1e-10    | 49    |
 | 0.0188     | 0.7813          | 0.6529    | 0.0235          | 0.8491               | 0.7418         | 1e-10    | 50    |
+| 0.0186     | 0.7770          | 0.6498    | 0.0229          | 0.8504               | 0.7435         | 1e-10    | 51    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77fab49801629b9f3673fa7d9821459f74473a0cea26df3e99e21cd70c5850f1
+oid sha256:c9087016be6747f66facd29fe938779f1c5a9d76ee9ce2296ff9adb4208a109a
 size 15133664