Training in progress epoch 56

README.md

@@ -15,13 +15,13 @@ 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: 0.0523
-- Train Dice Coef: 0.8352
-- Train Iou: 0.7333
-- Validation Loss: 0.0440
-- Validation Dice Coef: 0.8867
-- Validation Iou: 0.7974
+- Train Dice Coef: 0.8376
+- Train Iou: 0.7347
+- Validation Loss: 0.0456
+- Validation Dice Coef: 0.8846
+- Validation Iou: 0.7940
 - Train Lr: 1e-10
-- Epoch: 55
+- Epoch: 56
 
 ## Model description
 
@@ -103,6 +103,7 @@ The following hyperparameters were used during training:
 | 0.0520     | 0.8447          | 0.7432    | 0.0443          | 0.8854               | 0.7954         | 1e-10    | 53    |
 | 0.0523     | 0.8359          | 0.7337    | 0.0442          | 0.8860               | 0.7962         | 1e-10    | 54    |
 | 0.0523     | 0.8352          | 0.7333    | 0.0440          | 0.8867               | 0.7974         | 1e-10    | 55    |
+| 0.0523     | 0.8376          | 0.7347    | 0.0456          | 0.8846               | 0.7940         | 1e-10    | 56    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6efc1ab5e225c841286cdbd14b1b4e55bbe61e7987e47d21ff2fc7d81762ebe5
+oid sha256:3f77f06b1f30302ffa11de0d9da9e947507dd0c388b316faf168f2562ff632d8
 size 15133664