Training in progress epoch 86

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: 0.0189
-- Train Dice Coef: 0.7758
-- Train Iou: 0.6472
+- Train Loss: 0.0185
+- Train Dice Coef: 0.7735
+- Train Iou: 0.6460
 - Validation Loss: 0.0234
-- Validation Dice Coef: 0.8484
-- Validation Iou: 0.7414
+- Validation Dice Coef: 0.8492
+- Validation Iou: 0.7417
 - Train Lr: 1e-10
-- Epoch: 85
+- Epoch: 86
 
 ## Model description
 
@@ -133,6 +133,7 @@ The following hyperparameters were used during training:
 | 0.0190     | 0.7805          | 0.6507    | 0.0237          | 0.8494               | 0.7418         | 1e-10    | 83    |
 | 0.0187     | 0.7752          | 0.6473    | 0.0231          | 0.8502               | 0.7431         | 1e-10    | 84    |
 | 0.0189     | 0.7758          | 0.6472    | 0.0234          | 0.8484               | 0.7414         | 1e-10    | 85    |
+| 0.0185     | 0.7735          | 0.6460    | 0.0234          | 0.8492               | 0.7417         | 1e-10    | 86    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13743de504d9554a95e51b18c2f7be3a3ad0eaf99868af4a595c8969ffd10c6f
+oid sha256:df64164a677020abc3ef4283c138d6128a46c1e5ddd8327fdc6a2a9c8a87b566
 size 15133664