Training in progress epoch 99

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: 0.0161
-- Train Dice Coef: 0.8059
-- Train Iou: 0.6832
-- Validation Loss: 0.0218
-- Validation Dice Coef: 0.8608
-- Validation Iou: 0.7577
+- Train Loss: 0.0159
+- Train Dice Coef: 0.8034
+- Train Iou: 0.6803
+- Validation Loss: 0.0223
+- Validation Dice Coef: 0.8606
+- Validation Iou: 0.7573
 - Train Lr: 1e-10
-- Epoch: 98
+- Epoch: 99
 
 ## Model description
 
@@ -146,6 +146,7 @@ The following hyperparameters were used during training:
 | 0.0158     | 0.8051          | 0.6832    | 0.0219          | 0.8615               | 0.7587         | 1e-10    | 96    |
 | 0.0161     | 0.8053          | 0.6826    | 0.0220          | 0.8593               | 0.7555         | 1e-10    | 97    |
 | 0.0161     | 0.8059          | 0.6832    | 0.0218          | 0.8608               | 0.7577         | 1e-10    | 98    |
+| 0.0159     | 0.8034          | 0.6803    | 0.0223          | 0.8606               | 0.7573         | 1e-10    | 99    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88ee467b77773644d7895843c2f867adb76bdc6ddef9565e886415120f44c9c1
+oid sha256:5e744021bc8eeeb75958e29b8c636a5529d1b360245cf93a260811dbb9755201
 size 15133664