Training in progress epoch 20

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: 0.0221
-- Train Dice Coef: 0.7701
-- Train Iou: 0.6359
-- Validation Loss: 0.0251
-- Validation Dice Coef: 0.8491
-- Validation Iou: 0.7411
+- Train Loss: 0.0235
+- Train Dice Coef: 0.7619
+- Train Iou: 0.6262
+- Validation Loss: 0.0264
+- Validation Dice Coef: 0.8482
+- Validation Iou: 0.7394
 - Train Lr: 1e-04
-- Epoch: 19
+- Epoch: 20
 
 ## Model description
 
@@ -67,6 +67,7 @@ The following hyperparameters were used during training:
 | 0.0227     | 0.7682          | 0.6339    | 0.0264          | 0.8467               | 0.7368         | 1e-04    | 17    |
 | 0.0236     | 0.7639          | 0.6281    | 0.0273          | 0.8450               | 0.7356         | 1e-04    | 18    |
 | 0.0221     | 0.7701          | 0.6359    | 0.0251          | 0.8491               | 0.7411         | 1e-04    | 19    |
+| 0.0235     | 0.7619          | 0.6262    | 0.0264          | 0.8482               | 0.7394         | 1e-04    | 20    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad37b54a4caa04478e372eb66fd431e371dc5558c00482ee60a97f3627cf7227
+oid sha256:be3cbdddfc4ac966f97a47fc7cc14625db2917b3cf7b18ebf9cd8d13672726ab
 size 15133664