Training in progress epoch 13

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: 0.0259
-- Train Dice Coef: 0.7344
-- Train Iou: 0.5961
-- Validation Loss: 0.0357
-- Validation Dice Coef: 0.7986
-- Validation Iou: 0.6716
+- Train Loss: 0.0257
+- Train Dice Coef: 0.7405
+- Train Iou: 0.6010
+- Validation Loss: 0.0385
+- Validation Dice Coef: 0.7970
+- Validation Iou: 0.6702
 - Train Lr: 1e-04
-- Epoch: 12
+- Epoch: 13
 
 ## Model description
 
@@ -60,6 +60,7 @@ The following hyperparameters were used during training:
 | 0.0287     | 0.7245          | 0.5830    | 0.0357          | 0.7899               | 0.6630         | 1e-04    | 10    |
 | 0.0273     | 0.7228          | 0.5825    | 0.0659          | 0.6279               | 0.4914         | 1e-04    | 11    |
 | 0.0259     | 0.7344          | 0.5961    | 0.0357          | 0.7986               | 0.6716         | 1e-04    | 12    |
+| 0.0257     | 0.7405          | 0.6010    | 0.0385          | 0.7970               | 0.6702         | 1e-04    | 13    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9e56c9018ef07e4bdf49bea4dc7297ec758c150f63dd93cc8889b299a35de11
+oid sha256:7d836a2dce11b8ee03e7124b351bdb3b96ee1a13c083fd82ff106b72af157698
 size 15133664