Training in progress epoch 32

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: 0.0185
-- Train Dice Coef: 0.7715
-- Train Iou: 0.6440
-- Validation Loss: 0.0232
-- Validation Dice Coef: 0.8505
-- Validation Iou: 0.7437
-- Train Lr: 2.5e-07
-- Epoch: 31
+- Train Loss: 0.0186
+- Train Dice Coef: 0.7764
+- Train Iou: 0.6488
+- Validation Loss: 0.0233
+- Validation Dice Coef: 0.8487
+- Validation Iou: 0.7416
+- Train Lr: 1.25e-08
+- Epoch: 32
 
 ## Model description
 
@@ -79,6 +79,7 @@ The following hyperparameters were used during training:
 | 0.0188     | 0.7786          | 0.6501    | 0.0241          | 0.8484               | 0.7406         | 2.5e-07  | 29    |
 | 0.0189     | 0.7815          | 0.6520    | 0.0232          | 0.8507               | 0.7439         | 2.5e-07  | 30    |
 | 0.0185     | 0.7715          | 0.6440    | 0.0232          | 0.8505               | 0.7437         | 2.5e-07  | 31    |
+| 0.0186     | 0.7764          | 0.6488    | 0.0233          | 0.8487               | 0.7416         | 1.25e-08 | 32    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8548f40fd5cedd5f2ac5a01dc1fb2ff14bd0da63ee473c2d4e07bf3f634660b2
+oid sha256:f5208cd8c273cf9c81e054eff26d6908a628db6afcf21f591bd48279d722607e
 size 15133664