Training in progress epoch 96

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: 0.0162
+- Train Loss: 0.0160
 - Train Dice Coef: 0.8037
-- Train Iou: 0.6804
-- Validation Loss: 0.0228
-- Validation Dice Coef: 0.8558
-- Validation Iou: 0.7502
+- Train Iou: 0.6805
+- Validation Loss: 0.0226
+- Validation Dice Coef: 0.8568
+- Validation Iou: 0.7517
 - Train Lr: 1e-10
-- Epoch: 95
+- Epoch: 96
 
 ## Model description
 
@@ -143,6 +143,7 @@ The following hyperparameters were used during training:
 | 0.0159     | 0.8058          | 0.6833    | 0.0223          | 0.8560               | 0.7505         | 1e-10    | 93    |
 | 0.0161     | 0.8032          | 0.6796    | 0.0223          | 0.8566               | 0.7514         | 1e-10    | 94    |
 | 0.0162     | 0.8037          | 0.6804    | 0.0228          | 0.8558               | 0.7502         | 1e-10    | 95    |
+| 0.0160     | 0.8037          | 0.6805    | 0.0226          | 0.8568               | 0.7517         | 1e-10    | 96    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d71e87c6dab723960bb2ca1e4720618e42f18b3e729a6536cc2f7f153a2fa55a
+oid sha256:2b1f3a1b32bb898e37c648d93053e85d2024dc9990018db6629c96ef77ff3222
 size 15133664