Training in progress epoch 90

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: 0.0526
-- Train Dice Coef: 0.8328
-- Train Iou: 0.7291
-- Validation Loss: 0.0446
-- Validation Dice Coef: 0.8853
-- Validation Iou: 0.7952
+- Train Loss: 0.0528
+- Train Dice Coef: 0.8435
+- Train Iou: 0.7408
+- Validation Loss: 0.0449
+- Validation Dice Coef: 0.8855
+- Validation Iou: 0.7954
 - Train Lr: 1e-10
-- Epoch: 89
+- Epoch: 90
 
 ## Model description
 
@@ -137,6 +137,7 @@ The following hyperparameters were used during training:
 | 0.0523     | 0.8443          | 0.7421    | 0.0443          | 0.8865               | 0.7971         | 1e-10    | 87    |
 | 0.0519     | 0.8429          | 0.7402    | 0.0465          | 0.8813               | 0.7891         | 1e-10    | 88    |
 | 0.0526     | 0.8328          | 0.7291    | 0.0446          | 0.8853               | 0.7952         | 1e-10    | 89    |
+| 0.0528     | 0.8435          | 0.7408    | 0.0449          | 0.8855               | 0.7954         | 1e-10    | 90    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cefd4ba88562b64f8dd8d501d97615da890456b73a8d101da67ea06bf05c090f
+oid sha256:d58d883b3a1b81774e28d1974ea9a125af1e2f5163d7a2bd2c7fcd39ed9e728e
 size 15133664