Training in progress epoch 80

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: 0.0188
-- Train Dice Coef: 0.7771
-- Train Iou: 0.6489
+- Train Dice Coef: 0.7766
+- Train Iou: 0.6480
 - Validation Loss: 0.0235
-- Validation Dice Coef: 0.8488
-- Validation Iou: 0.7414
+- Validation Dice Coef: 0.8487
+- Validation Iou: 0.7411
 - Train Lr: 1e-10
-- Epoch: 79
+- Epoch: 80
 
 ## Model description
 
@@ -127,6 +127,7 @@ The following hyperparameters were used during training:
 | 0.0188     | 0.7760          | 0.6479    | 0.0235          | 0.8494               | 0.7418         | 1e-10    | 77    |
 | 0.0187     | 0.7828          | 0.6538    | 0.0231          | 0.8518               | 0.7456         | 1e-10    | 78    |
 | 0.0188     | 0.7771          | 0.6489    | 0.0235          | 0.8488               | 0.7414         | 1e-10    | 79    |
+| 0.0188     | 0.7766          | 0.6480    | 0.0235          | 0.8487               | 0.7411         | 1e-10    | 80    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa6b594b574a40639530118afdb19e138797e87408edb9236c47e7804b83ddc5
+oid sha256:2ffcece9b2bc23554fda950e05f45a24210c481378175c3b1f4184ab51294a01
 size 15133664