Training in progress epoch 32

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: 0.0525
-- Train Dice Coef: 0.8396
-- Train Iou: 0.7379
-- Validation Loss: 0.0444
-- Validation Dice Coef: 0.8855
-- Validation Iou: 0.7954
-- Train Lr: 5e-06
-- Epoch: 31
+- Train Dice Coef: 0.8347
+- Train Iou: 0.7322
+- Validation Loss: 0.0458
+- Validation Dice Coef: 0.8833
+- Validation Iou: 0.7921
+- Train Lr: 2.5e-07
+- Epoch: 32
 
 ## Model description
 
@@ -79,6 +79,7 @@ The following hyperparameters were used during training:
 | 0.0535     | 0.8350          | 0.7324    | 0.0459          | 0.8833               | 0.7919         | 5e-06    | 29    |
 | 0.0529     | 0.8404          | 0.7376    | 0.0460          | 0.8820               | 0.7900         | 5e-06    | 30    |
 | 0.0525     | 0.8396          | 0.7379    | 0.0444          | 0.8855               | 0.7954         | 5e-06    | 31    |
+| 0.0525     | 0.8347          | 0.7322    | 0.0458          | 0.8833               | 0.7921         | 2.5e-07  | 32    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9428e0d983528f7418241d075977383a068b1fbdab83d3eafa16e99337c018bd
+oid sha256:1511db61f48883ea873f1886cca974d5629a73a9c169c7ea0553f68331d73f3f
 size 15133664