Training in progress epoch 86

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: 0.0520
-- Train Dice Coef: 0.8477
-- Train Iou: 0.7457
-- Validation Loss: 0.0447
-- Validation Dice Coef: 0.8844
-- Validation Iou: 0.7938
+- Train Loss: 0.0518
+- Train Dice Coef: 0.8410
+- Train Iou: 0.7387
+- Validation Loss: 0.0452
+- Validation Dice Coef: 0.8848
+- Validation Iou: 0.7944
 - Train Lr: 1e-10
-- Epoch: 85
+- Epoch: 86
 
 ## Model description
 
@@ -133,6 +133,7 @@ The following hyperparameters were used during training:
 | 0.0520     | 0.8492          | 0.7471    | 0.0449          | 0.8847               | 0.7943         | 1e-10    | 83    |
 | 0.0526     | 0.8384          | 0.7360    | 0.0445          | 0.8862               | 0.7968         | 1e-10    | 84    |
 | 0.0520     | 0.8477          | 0.7457    | 0.0447          | 0.8844               | 0.7938         | 1e-10    | 85    |
+| 0.0518     | 0.8410          | 0.7387    | 0.0452          | 0.8848               | 0.7944         | 1e-10    | 86    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:235516f3a4f393fc0499666023da6edc297a86bd6c879321cfa97ab8dbc36054
+oid sha256:baed308c59b43fff68dbdf22e6a52fbd0ac87e5c510c97eff27b2974769ca066
 size 15133664