Training in progress epoch 61

README.md

@@ -15,13 +15,13 @@ 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: 0.0159
-- Train Dice Coef: 0.8085
-- Train Iou: 0.6859
+- Train Dice Coef: 0.8046
+- Train Iou: 0.6815
 - Validation Loss: 0.0223
-- Validation Dice Coef: 0.8572
-- Validation Iou: 0.7522
+- Validation Dice Coef: 0.8578
+- Validation Iou: 0.7533
 - Train Lr: 1e-10
-- Epoch: 60
+- Epoch: 61
 
 ## Model description
 
@@ -108,6 +108,7 @@ The following hyperparameters were used during training:
 | 0.0160     | 0.8062          | 0.6833    | 0.0231          | 0.8560               | 0.7505         | 6.25e-10 | 58    |
 | 0.0159     | 0.8037          | 0.6810    | 0.0227          | 0.8557               | 0.7500         | 1e-10    | 59    |
 | 0.0159     | 0.8085          | 0.6859    | 0.0223          | 0.8572               | 0.7522         | 1e-10    | 60    |
+| 0.0159     | 0.8046          | 0.6815    | 0.0223          | 0.8578               | 0.7533         | 1e-10    | 61    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b2ef77591dec1a612495c3642bc1e4af6a3d83e77ba8635fd3f99d12188ebb7
+oid sha256:0c01b95fdaf19ddd0bc1c48ecbdf2321b464174241481534df6e82721925e8cc
 size 15133664