Training in progress epoch 66

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: 0.0189
-- Train Dice Coef: 0.7851
-- Train Iou: 0.6566
-- Validation Loss: 0.0230
-- Validation Dice Coef: 0.8518
-- Validation Iou: 0.7455
+- Train Loss: 0.0187
+- Train Dice Coef: 0.7795
+- Train Iou: 0.6515
+- Validation Loss: 0.0237
+- Validation Dice Coef: 0.8494
+- Validation Iou: 0.7420
 - Train Lr: 1e-10
-- Epoch: 65
+- Epoch: 66
 
 ## Model description
 
@@ -113,6 +113,7 @@ The following hyperparameters were used during training:
 | 0.0185     | 0.7784          | 0.6504    | 0.0232          | 0.8496               | 0.7422         | 1e-10    | 63    |
 | 0.0188     | 0.7797          | 0.6519    | 0.0234          | 0.8484               | 0.7406         | 1e-10    | 64    |
 | 0.0189     | 0.7851          | 0.6566    | 0.0230          | 0.8518               | 0.7455         | 1e-10    | 65    |
+| 0.0187     | 0.7795          | 0.6515    | 0.0237          | 0.8494               | 0.7420         | 1e-10    | 66    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5c21fc99ee213660354b062355b08ffaa57ceaaa0e31e411c18d287b86bd744
+oid sha256:e2d819aba5741f335b0132a3fd7b7a910b19d750d62f2ca32d66361de6d9a72f
 size 15133664