Training in progress epoch 17

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: 0.0225
-- Train Dice Coef: 0.7546
-- Train Iou: 0.6202
-- Validation Loss: 0.0242
-- Validation Dice Coef: 0.8446
-- Validation Iou: 0.7356
+- Train Loss: 0.0207
+- Train Dice Coef: 0.7614
+- Train Iou: 0.6312
+- Validation Loss: 0.0235
+- Validation Dice Coef: 0.8482
+- Validation Iou: 0.7406
 - Train Lr: 5e-06
-- Epoch: 16
+- Epoch: 17
 
 ## Model description
 
@@ -64,6 +64,7 @@ The following hyperparameters were used during training:
 | 0.0237     | 0.7434          | 0.6076    | 0.0364          | 0.8060               | 0.6841         | 1e-04    | 14    |
 | 0.0227     | 0.7532          | 0.6192    | 0.0556          | 0.6927               | 0.5449         | 1e-04    | 15    |
 | 0.0225     | 0.7546          | 0.6202    | 0.0242          | 0.8446               | 0.7356         | 5e-06    | 16    |
+| 0.0207     | 0.7614          | 0.6312    | 0.0235          | 0.8482               | 0.7406         | 5e-06    | 17    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:531909fd951467b2c07565d235c1176d11cc4a238504b2bbba3942ccbb45c61f
+oid sha256:d4c1d5ef6654844d5cde7d767adec929d088a251ee7085433673f75e00cca504
 size 15133664