Training in progress epoch 10

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: 0.0315
-- Train Dice Coef: 0.7137
-- Train Iou: 0.5680
-- Validation Loss: 0.0307
-- Validation Dice Coef: 0.8333
-- Validation Iou: 0.7169
+- Train Loss: 0.0292
+- Train Dice Coef: 0.7341
+- Train Iou: 0.5908
+- Validation Loss: 0.0296
+- Validation Dice Coef: 0.8400
+- Validation Iou: 0.7266
 - Train Lr: 1e-04
-- Epoch: 9
+- Epoch: 10
 
 ## Model description
 
@@ -57,6 +57,7 @@ The following hyperparameters were used during training:
 | 0.0340     | 0.7019          | 0.5531    | 0.0327          | 0.8297               | 0.7113         | 1e-04    | 7     |
 | 0.0339     | 0.7002          | 0.5530    | 0.0319          | 0.8344               | 0.7182         | 1e-04    | 8     |
 | 0.0315     | 0.7137          | 0.5680    | 0.0307          | 0.8333               | 0.7169         | 1e-04    | 9     |
+| 0.0292     | 0.7341          | 0.5908    | 0.0296          | 0.8400               | 0.7266         | 1e-04    | 10    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4892ea4dbd15ed57b7b237acdf5e8a584c7e109bbb706cce905ca107011ac0bf
+oid sha256:4a132e101e39213ede8f381969789a377d9fcd64ebe1e6f74e2929a5ca3257a3
 size 15133664