Training in progress epoch 85

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: 0.0162
-- Train Dice Coef: 0.8036
-- Train Iou: 0.6802
-- Validation Loss: 0.0224
-- Validation Dice Coef: 0.8563
-- Validation Iou: 0.7509
+- Train Loss: 0.0160
+- Train Dice Coef: 0.8045
+- Train Iou: 0.6816
+- Validation Loss: 0.0230
+- Validation Dice Coef: 0.8566
+- Validation Iou: 0.7514
 - Train Lr: 1e-10
-- Epoch: 84
+- Epoch: 85
 
 ## Model description
 
@@ -132,6 +132,7 @@ The following hyperparameters were used during training:
 | 0.0159     | 0.8068          | 0.6840    | 0.0234          | 0.8562               | 0.7506         | 1e-10    | 82    |
 | 0.0161     | 0.8047          | 0.6818    | 0.0228          | 0.8562               | 0.7508         | 1e-10    | 83    |
 | 0.0162     | 0.8036          | 0.6802    | 0.0224          | 0.8563               | 0.7509         | 1e-10    | 84    |
+| 0.0160     | 0.8045          | 0.6816    | 0.0230          | 0.8566               | 0.7514         | 1e-10    | 85    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b80bd9db00db9c58801a639f4193698b696ce588851125571dcee0cba20139ad
+oid sha256:7e734c3d977e416a2ddefbf91b7ec6eab6295fa618bc6dfafe0dff1c0070968d
 size 15133664