Training in progress epoch 9

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: 0.0306
-- Train Dice Coef: 0.7010
-- Train Iou: 0.5582
-- Validation Loss: 0.0704
-- Validation Dice Coef: 0.5946
-- Validation Iou: 0.4483
+- Train Loss: 0.0285
+- Train Dice Coef: 0.7160
+- Train Iou: 0.5744
+- Validation Loss: 0.0504
+- Validation Dice Coef: 0.6951
+- Validation Iou: 0.5568
 - Train Lr: 1e-04
-- Epoch: 8
+- Epoch: 9
 
 ## Model description
 
@@ -56,6 +56,7 @@ The following hyperparameters were used during training:
 | 0.0336     | 0.6770          | 0.5307    | 0.0540          | 0.6264               | 0.4881         | 1e-04    | 6     |
 | 0.0302     | 0.7029          | 0.5592    | 0.0518          | 0.6516               | 0.5234         | 1e-04    | 7     |
 | 0.0306     | 0.7010          | 0.5582    | 0.0704          | 0.5946               | 0.4483         | 1e-04    | 8     |
+| 0.0285     | 0.7160          | 0.5744    | 0.0504          | 0.6951               | 0.5568         | 1e-04    | 9     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d30b420a665e8bdfca0642c5df4834e5132f2d0a547f863bc510935e93ca2e9
+oid sha256:b188b9f19ca82b080080fbe11761fdce0421dcc229ce6c2589f23eea5a5afd45
 size 15133664