Training in progress epoch 83

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: 0.0522
-- Train Dice Coef: 0.8417
-- Train Iou: 0.7396
-- Validation Loss: 0.0451
-- Validation Dice Coef: 0.8844
-- Validation Iou: 0.7939
+- Train Loss: 0.0520
+- Train Dice Coef: 0.8492
+- Train Iou: 0.7471
+- Validation Loss: 0.0449
+- Validation Dice Coef: 0.8847
+- Validation Iou: 0.7943
 - Train Lr: 1e-10
-- Epoch: 82
+- Epoch: 83
 
 ## Model description
 
@@ -130,6 +130,7 @@ The following hyperparameters were used during training:
 | 0.0513     | 0.8439          | 0.7415    | 0.0454          | 0.8837               | 0.7926         | 1e-10    | 80    |
 | 0.0520     | 0.8433          | 0.7422    | 0.0445          | 0.8843               | 0.7937         | 1e-10    | 81    |
 | 0.0522     | 0.8417          | 0.7396    | 0.0451          | 0.8844               | 0.7939         | 1e-10    | 82    |
+| 0.0520     | 0.8492          | 0.7471    | 0.0449          | 0.8847               | 0.7943         | 1e-10    | 83    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea89fe87b47f06dffcabbbea65990af97507f0405ea925705c451bcef8ee244c
+oid sha256:a7cdb8cc29a6c1cfd648cfce9f5f4f925bc816542743be4b5009ee2a98906183
 size 15133664