Training in progress epoch 68

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: 0.0524
-- Train Dice Coef: 0.8461
-- Train Iou: 0.7438
-- Validation Loss: 0.0452
-- Validation Dice Coef: 0.8838
-- Validation Iou: 0.7928
+- Train Loss: 0.0523
+- Train Dice Coef: 0.8374
+- Train Iou: 0.7361
+- Validation Loss: 0.0453
+- Validation Dice Coef: 0.8849
+- Validation Iou: 0.7947
 - Train Lr: 1e-10
-- Epoch: 67
+- Epoch: 68
 
 ## Model description
 
@@ -115,6 +115,7 @@ The following hyperparameters were used during training:
 | 0.0515     | 0.8416          | 0.7396    | 0.0440          | 0.8862               | 0.7966         | 1e-10    | 65    |
 | 0.0526     | 0.8364          | 0.7346    | 0.0449          | 0.8848               | 0.7944         | 1e-10    | 66    |
 | 0.0524     | 0.8461          | 0.7438    | 0.0452          | 0.8838               | 0.7928         | 1e-10    | 67    |
+| 0.0523     | 0.8374          | 0.7361    | 0.0453          | 0.8849               | 0.7947         | 1e-10    | 68    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a04a5b3815722e9c80497f7e4761b1b9a8bc892ebb2de07a1d8d3faf633fb2a
+oid sha256:991e5afe292c1a8266386335776fa2524bed5e2c0239b38451dcd3142b0ea8d3
 size 15133664