Training in progress epoch 6

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: 0.0374
-- Train Dice Coef: 0.6569
-- Train Iou: 0.5086
-- Validation Loss: 0.0719
-- Validation Dice Coef: 0.5267
-- Validation Iou: 0.3854
+- Train Loss: 0.0336
+- Train Dice Coef: 0.6770
+- Train Iou: 0.5307
+- Validation Loss: 0.0540
+- Validation Dice Coef: 0.6264
+- Validation Iou: 0.4881
 - Train Lr: 1e-04
-- Epoch: 5
+- Epoch: 6
 
 ## Model description
 
@@ -53,6 +53,7 @@ The following hyperparameters were used during training:
 | 0.0432     | 0.6204          | 0.4699    | 0.1085          | 0.3757               | 0.2479         | 1e-04    | 3     |
 | 0.0413     | 0.6306          | 0.4831    | 0.0771          | 0.5239               | 0.3646         | 1e-04    | 4     |
 | 0.0374     | 0.6569          | 0.5086    | 0.0719          | 0.5267               | 0.3854         | 1e-04    | 5     |
+| 0.0336     | 0.6770          | 0.5307    | 0.0540          | 0.6264               | 0.4881         | 1e-04    | 6     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cd9f7843429b637de09600ca07e8ef3b816313ac8a3f1c61220322fe3133c94
+oid sha256:925ccfe58c222e5c07f4df4f4e99e7d9b7609dbf8a5b2c65f9f6cf014be87cd5
 size 15133664