Training in progress epoch 98

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: 0.0194
-- Train Dice Coef: 0.7756
-- Train Iou: 0.6476
-- Validation Loss: 0.0236
-- Validation Dice Coef: 0.8504
-- Validation Iou: 0.7433
+- Train Loss: 0.0187
+- Train Dice Coef: 0.7792
+- Train Iou: 0.6504
+- Validation Loss: 0.0231
+- Validation Dice Coef: 0.8502
+- Validation Iou: 0.7436
 - Train Lr: 1e-10
-- Epoch: 97
+- Epoch: 98
 
 ## Model description
 
@@ -145,6 +145,7 @@ The following hyperparameters were used during training:
 | 0.0188     | 0.7769          | 0.6477    | 0.0234          | 0.8492               | 0.7419         | 1e-10    | 95    |
 | 0.0188     | 0.7689          | 0.6415    | 0.0236          | 0.8487               | 0.7409         | 1e-10    | 96    |
 | 0.0194     | 0.7756          | 0.6476    | 0.0236          | 0.8504               | 0.7433         | 1e-10    | 97    |
+| 0.0187     | 0.7792          | 0.6504    | 0.0231          | 0.8502               | 0.7436         | 1e-10    | 98    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1930f4612d4625a9958f4aba51d8c1db058e3bdfff2de476ec11cae4babc6e75
+oid sha256:8b9b8741ec76acb83b917b33582ab2194e9f99202570861a65705160c841532f
 size 15133664