Training in progress epoch 16

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: 0.0227
-- Train Dice Coef: 0.7532
-- Train Iou: 0.6192
-- Validation Loss: 0.0556
-- Validation Dice Coef: 0.6927
-- Validation Iou: 0.5449
-- Train Lr: 1e-04
-- Epoch: 15
+- Train Loss: 0.0225
+- Train Dice Coef: 0.7546
+- Train Iou: 0.6202
+- Validation Loss: 0.0242
+- Validation Dice Coef: 0.8446
+- Validation Iou: 0.7356
+- Train Lr: 5e-06
+- Epoch: 16
 
 ## Model description
 
@@ -63,6 +63,7 @@ The following hyperparameters were used during training:
 | 0.0257     | 0.7405          | 0.6010    | 0.0385          | 0.7970               | 0.6702         | 1e-04    | 13    |
 | 0.0237     | 0.7434          | 0.6076    | 0.0364          | 0.8060               | 0.6841         | 1e-04    | 14    |
 | 0.0227     | 0.7532          | 0.6192    | 0.0556          | 0.6927               | 0.5449         | 1e-04    | 15    |
+| 0.0225     | 0.7546          | 0.6202    | 0.0242          | 0.8446               | 0.7356         | 5e-06    | 16    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e926b0df7597e655a1c7cc97280346e82e2f2b43e712658e43e1c44ab6a6eb83
+oid sha256:531909fd951467b2c07565d235c1176d11cc4a238504b2bbba3942ccbb45c61f
 size 15133664