Training in progress epoch 24

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: 0.0192
-- Train Dice Coef: 0.7756
-- Train Iou: 0.6464
-- Validation Loss: 0.0236
-- Validation Dice Coef: 0.8482
-- Validation Iou: 0.7407
+- Train Loss: 0.0191
+- Train Dice Coef: 0.7741
+- Train Iou: 0.6447
+- Validation Loss: 0.0231
+- Validation Dice Coef: 0.8503
+- Validation Iou: 0.7435
 - Train Lr: 5e-06
-- Epoch: 23
+- Epoch: 24
 
 ## Model description
 
@@ -71,6 +71,7 @@ The following hyperparameters were used during training:
 | 0.0195     | 0.7738          | 0.6438    | 0.0231          | 0.8504               | 0.7440         | 5e-06    | 21    |
 | 0.0196     | 0.7749          | 0.6458    | 0.0234          | 0.8504               | 0.7436         | 5e-06    | 22    |
 | 0.0192     | 0.7756          | 0.6464    | 0.0236          | 0.8482               | 0.7407         | 5e-06    | 23    |
+| 0.0191     | 0.7741          | 0.6447    | 0.0231          | 0.8503               | 0.7435         | 5e-06    | 24    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c0bddd53c270fb88db0e4371fb0ea2e14ac0947e6b7dc3cafc5431a378043a3
+oid sha256:815e7c064aeb7e8e6e14b4d461bc2c950f58b14ae7dc0bd50c1bd2565dc37b6d
 size 15133664