Training in progress epoch 22

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: 0.0562
-- Train Dice Coef: 0.8252
-- Train Iou: 0.7182
-- Validation Loss: 0.0455
-- Validation Dice Coef: 0.8850
-- Validation Iou: 0.7947
+- Train Loss: 0.0560
+- Train Dice Coef: 0.8245
+- Train Iou: 0.7188
+- Validation Loss: 0.0461
+- Validation Dice Coef: 0.8830
+- Validation Iou: 0.7916
 - Train Lr: 5e-06
-- Epoch: 21
+- Epoch: 22
 
 ## Model description
 
@@ -69,6 +69,7 @@ The following hyperparameters were used during training:
 | 0.0564     | 0.8310          | 0.7242    | 0.0461          | 0.8830               | 0.7915         | 5e-06    | 19    |
 | 0.0567     | 0.8330          | 0.7271    | 0.0455          | 0.8828               | 0.7910         | 5e-06    | 20    |
 | 0.0562     | 0.8252          | 0.7182    | 0.0455          | 0.8850               | 0.7947         | 5e-06    | 21    |
+| 0.0560     | 0.8245          | 0.7188    | 0.0461          | 0.8830               | 0.7916         | 5e-06    | 22    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f391497119106c54c273962d6526e298ce152e2003bab01bb7b45bf98cbabc45
+oid sha256:8414d30e369a6aa484b238b353db52c54285da84c494f252cbbd2b35c22ef0f7
 size 15133664