Training in progress epoch 7

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: 0.0384
-- Train Dice Coef: 0.6728
-- Train Iou: 0.5223
-- Validation Loss: 0.0355
-- Validation Dice Coef: 0.8240
-- Validation Iou: 0.7031
+- Train Loss: 0.0340
+- Train Dice Coef: 0.7019
+- Train Iou: 0.5531
+- Validation Loss: 0.0327
+- Validation Dice Coef: 0.8297
+- Validation Iou: 0.7113
 - Train Lr: 1e-04
-- Epoch: 6
+- Epoch: 7
 
 ## Model description
 
@@ -54,6 +54,7 @@ The following hyperparameters were used during training:
 | 0.0443     | 0.6379          | 0.4837    | 0.0393          | 0.8008               | 0.6709         | 1e-04    | 4     |
 | 0.0417     | 0.6535          | 0.5011    | 0.0363          | 0.8131               | 0.6882         | 1e-04    | 5     |
 | 0.0384     | 0.6728          | 0.5223    | 0.0355          | 0.8240               | 0.7031         | 1e-04    | 6     |
+| 0.0340     | 0.7019          | 0.5531    | 0.0327          | 0.8297               | 0.7113         | 1e-04    | 7     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5866fee15dd3aa3f0fc33f1661f92f0dcad5a19fbc593bca45068cf8d3cfb804
+oid sha256:f55142cdf562da5aabf3592b2272a523e7fa774152a84e27af98419c7624e704
 size 15133664