Training in progress epoch 47

README.md

@@ -15,13 +15,13 @@ 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: 0.0519
-- Train Dice Coef: 0.8445
-- Train Iou: 0.7434
-- Validation Loss: 0.0446
-- Validation Dice Coef: 0.8858
-- Validation Iou: 0.7959
-- Train Lr: 6.25e-10
-- Epoch: 46
+- Train Dice Coef: 0.8388
+- Train Iou: 0.7368
+- Validation Loss: 0.0447
+- Validation Dice Coef: 0.8839
+- Validation Iou: 0.7929
+- Train Lr: 1e-10
+- Epoch: 47
 
 ## Model description
 
@@ -94,6 +94,7 @@ The following hyperparameters were used during training:
 | 0.0519     | 0.8427          | 0.7402    | 0.0449          | 0.8854               | 0.7952         | 6.25e-10 | 44    |
 | 0.0523     | 0.8445          | 0.7413    | 0.0453          | 0.8839               | 0.7930         | 6.25e-10 | 45    |
 | 0.0519     | 0.8445          | 0.7434    | 0.0446          | 0.8858               | 0.7959         | 6.25e-10 | 46    |
+| 0.0519     | 0.8388          | 0.7368    | 0.0447          | 0.8839               | 0.7929         | 1e-10    | 47    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a55ce834b35619c6053df27d0f6bd7d60f47df638fcdc8304c3dbcafd59a6986
+oid sha256:00576a56bf28d26da814ae726f6dc61056d09b7f3440238720ba556ffbddd215
 size 15133664