Training in progress epoch 73

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: 0.0161
-- Train Dice Coef: 0.8074
-- Train Iou: 0.6852
-- Validation Loss: 0.0222
-- Validation Dice Coef: 0.8575
-- Validation Iou: 0.7527
+- Train Dice Coef: 0.7989
+- Train Iou: 0.6748
+- Validation Loss: 0.0228
+- Validation Dice Coef: 0.8563
+- Validation Iou: 0.7509
 - Train Lr: 1e-10
-- Epoch: 72
+- Epoch: 73
 
 ## Model description
 
@@ -120,6 +120,7 @@ The following hyperparameters were used during training:
 | 0.0164     | 0.8049          | 0.6820    | 0.0231          | 0.8553               | 0.7493         | 1e-10    | 70    |
 | 0.0160     | 0.8041          | 0.6812    | 0.0227          | 0.8574               | 0.7525         | 1e-10    | 71    |
 | 0.0161     | 0.8074          | 0.6852    | 0.0222          | 0.8575               | 0.7527         | 1e-10    | 72    |
+| 0.0161     | 0.7989          | 0.6748    | 0.0228          | 0.8563               | 0.7509         | 1e-10    | 73    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6890f13013fb642c48682c8a32481cf5434411339cd5a6281532d7c25bc6fed4
+oid sha256:20a544536f4dbb8b4bbfca43ee1066b540bbbcc0f2858e4aee60d45a27f766c7
 size 15133664