Training in progress epoch 25

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: 0.0548
-- Train Dice Coef: 0.8254
-- Train Iou: 0.7212
-- Validation Loss: 0.0459
-- Validation Dice Coef: 0.8832
-- Validation Iou: 0.7919
+- Train Loss: 0.0552
+- Train Dice Coef: 0.8331
+- Train Iou: 0.7281
+- Validation Loss: 0.0452
+- Validation Dice Coef: 0.8833
+- Validation Iou: 0.7920
 - Train Lr: 5e-06
-- Epoch: 24
+- Epoch: 25
 
 ## Model description
 
@@ -72,6 +72,7 @@ The following hyperparameters were used during training:
 | 0.0560     | 0.8245          | 0.7188    | 0.0461          | 0.8830               | 0.7916         | 5e-06    | 22    |
 | 0.0554     | 0.8259          | 0.7208    | 0.0463          | 0.8811               | 0.7885         | 5e-06    | 23    |
 | 0.0548     | 0.8254          | 0.7212    | 0.0459          | 0.8832               | 0.7919         | 5e-06    | 24    |
+| 0.0552     | 0.8331          | 0.7281    | 0.0452          | 0.8833               | 0.7920         | 5e-06    | 25    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3f4ceff52ea080f6c0ec297b3e57ee82bd1b27f5b06466295408692e7940c3
+oid sha256:31047e22a18ea30edf78e592efb1059c5cdbd60a768f0529b7d75afc5fbd0512
 size 15133664