Training in progress epoch 72

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: 0.0188
-- Train Dice Coef: 0.7734
-- Train Iou: 0.6452
-- Validation Loss: 0.0230
-- Validation Dice Coef: 0.8508
-- Validation Iou: 0.7442
+- Train Loss: 0.0186
+- Train Dice Coef: 0.7784
+- Train Iou: 0.6516
+- Validation Loss: 0.0234
+- Validation Dice Coef: 0.8484
+- Validation Iou: 0.7414
 - Train Lr: 1e-10
-- Epoch: 71
+- Epoch: 72
 
 ## Model description
 
@@ -119,6 +119,7 @@ The following hyperparameters were used during training:
 | 0.0188     | 0.7767          | 0.6486    | 0.0233          | 0.8502               | 0.7433         | 1e-10    | 69    |
 | 0.0189     | 0.7819          | 0.6535    | 0.0231          | 0.8504               | 0.7436         | 1e-10    | 70    |
 | 0.0188     | 0.7734          | 0.6452    | 0.0230          | 0.8508               | 0.7442         | 1e-10    | 71    |
+| 0.0186     | 0.7784          | 0.6516    | 0.0234          | 0.8484               | 0.7414         | 1e-10    | 72    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a47d6149f6ea671e89a5280d30b9ed0797d43e1da3e2d648b7f48f7b097663c2
+oid sha256:4a98ae53f5be44894eae28a0f94cd4e88fd582f7cf974bb324a9567fb9b7daaa
 size 15133664