Training in progress epoch 28

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: 0.0538
-- Train Dice Coef: 0.8350
-- Train Iou: 0.7310
-- Validation Loss: 0.0447
-- Validation Dice Coef: 0.8846
-- Validation Iou: 0.7941
+- Train Loss: 0.0543
+- Train Dice Coef: 0.8443
+- Train Iou: 0.7406
+- Validation Loss: 0.0468
+- Validation Dice Coef: 0.8803
+- Validation Iou: 0.7877
 - Train Lr: 5e-06
-- Epoch: 27
+- Epoch: 28
 
 ## Model description
 
@@ -75,6 +75,7 @@ The following hyperparameters were used during training:
 | 0.0552     | 0.8331          | 0.7281    | 0.0452          | 0.8833               | 0.7920         | 5e-06    | 25    |
 | 0.0534     | 0.8391          | 0.7355    | 0.0438          | 0.8872               | 0.7982         | 5e-06    | 26    |
 | 0.0538     | 0.8350          | 0.7310    | 0.0447          | 0.8846               | 0.7941         | 5e-06    | 27    |
+| 0.0543     | 0.8443          | 0.7406    | 0.0468          | 0.8803               | 0.7877         | 5e-06    | 28    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52b055274cb40ee848f8ec4584319dc170f98c9b488b2769fcff74d9a0b3120
+oid sha256:0dd85ef4b8c72939afb76a3b735c8135f963f9888acd4d3833010637774a4c3b
 size 15133664