Training in progress epoch 23

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: 0.0222
-- Train Dice Coef: 0.7715
-- Train Iou: 0.6379
-- Validation Loss: 0.0242
-- Validation Dice Coef: 0.8543
-- Validation Iou: 0.7479
+- Train Loss: 0.0203
+- Train Dice Coef: 0.7810
+- Train Iou: 0.6500
+- Validation Loss: 0.0239
+- Validation Dice Coef: 0.8556
+- Validation Iou: 0.7499
 - Train Lr: 1e-04
-- Epoch: 22
+- Epoch: 23
 
 ## Model description
 
@@ -70,6 +70,7 @@ The following hyperparameters were used during training:
 | 0.0235     | 0.7619          | 0.6262    | 0.0264          | 0.8482               | 0.7394         | 1e-04    | 20    |
 | 0.0216     | 0.7718          | 0.6383    | 0.0257          | 0.8506               | 0.7425         | 1e-04    | 21    |
 | 0.0222     | 0.7715          | 0.6379    | 0.0242          | 0.8543               | 0.7479         | 1e-04    | 22    |
+| 0.0203     | 0.7810          | 0.6500    | 0.0239          | 0.8556               | 0.7499         | 1e-04    | 23    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06db86ee462364463c0e369ffc97ca1ecf540214271e878a5c94712ee273e2d8
+oid sha256:170580a4946a4a6c257c496b78afcf6bbff36063012f3e68c6ea3d731667cbe5
 size 15133664