Training in progress epoch 52

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: 0.0161
-- Train Dice Coef: 0.8029
-- Train Iou: 0.6802
-- Validation Loss: 0.0227
-- Validation Dice Coef: 0.8570
-- Validation Iou: 0.7519
+- Train Loss: 0.0160
+- Train Dice Coef: 0.8069
+- Train Iou: 0.6843
+- Validation Loss: 0.0231
+- Validation Dice Coef: 0.8556
+- Validation Iou: 0.7498
 - Train Lr: 1.25e-08
-- Epoch: 51
+- Epoch: 52
 
 ## Model description
 
@@ -99,6 +99,7 @@ The following hyperparameters were used during training:
 | 0.0161     | 0.8041          | 0.6811    | 0.0225          | 0.8576               | 0.7528         | 1.25e-08 | 49    |
 | 0.0162     | 0.8060          | 0.6832    | 0.0233          | 0.8555               | 0.7498         | 1.25e-08 | 50    |
 | 0.0161     | 0.8029          | 0.6802    | 0.0227          | 0.8570               | 0.7519         | 1.25e-08 | 51    |
+| 0.0160     | 0.8069          | 0.6843    | 0.0231          | 0.8556               | 0.7498         | 1.25e-08 | 52    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d54b59392b0fd602098e7d6fe4ddc271fab214bc89c72065905ddf02da9056c5
+oid sha256:278eecb5b51af2c746c6ca1c3ee658fc1d26ecdc5e4f74ffc8765340d9b255ca
 size 15133664