Training in progress epoch 68

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: 0.0163
-- Train Dice Coef: 0.8046
-- Train Iou: 0.6813
-- Validation Loss: 0.0223
-- Validation Dice Coef: 0.8579
-- Validation Iou: 0.7534
+- Train Loss: 0.0161
+- Train Dice Coef: 0.8047
+- Train Iou: 0.6812
+- Validation Loss: 0.0226
+- Validation Dice Coef: 0.8566
+- Validation Iou: 0.7513
 - Train Lr: 1e-10
-- Epoch: 67
+- Epoch: 68
 
 ## Model description
 
@@ -115,6 +115,7 @@ The following hyperparameters were used during training:
 | 0.0159     | 0.8084          | 0.6865    | 0.0225          | 0.8561               | 0.7508         | 1e-10    | 65    |
 | 0.0161     | 0.8030          | 0.6795    | 0.0226          | 0.8570               | 0.7520         | 1e-10    | 66    |
 | 0.0163     | 0.8046          | 0.6813    | 0.0223          | 0.8579               | 0.7534         | 1e-10    | 67    |
+| 0.0161     | 0.8047          | 0.6812    | 0.0226          | 0.8566               | 0.7513         | 1e-10    | 68    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaf7f03fb15983a44846c1fb1ba393587f8fc50b7e7aa757692744cdc3151224
+oid sha256:1b14c369568a39cba4ec809d60a02fcca6adcdfabc6c59abc9818e68b7ea613b
 size 15133664