Training in progress epoch 54

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: 0.0189
-- Train Dice Coef: 0.7764
-- Train Iou: 0.6480
-- Validation Loss: 0.0233
-- Validation Dice Coef: 0.8500
-- Validation Iou: 0.7430
+- Train Dice Coef: 0.7744
+- Train Iou: 0.6461
+- Validation Loss: 0.0231
+- Validation Dice Coef: 0.8516
+- Validation Iou: 0.7449
 - Train Lr: 1e-10
-- Epoch: 53
+- Epoch: 54
 
 ## Model description
 
@@ -101,6 +101,7 @@ The following hyperparameters were used during training:
 | 0.0186     | 0.7770          | 0.6498    | 0.0229          | 0.8504               | 0.7435         | 1e-10    | 51    |
 | 0.0190     | 0.7764          | 0.6483    | 0.0232          | 0.8503               | 0.7437         | 1e-10    | 52    |
 | 0.0189     | 0.7764          | 0.6480    | 0.0233          | 0.8500               | 0.7430         | 1e-10    | 53    |
+| 0.0189     | 0.7744          | 0.6461    | 0.0231          | 0.8516               | 0.7449         | 1e-10    | 54    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eed5a06b9d75f15a085a726d600e039c9c27a5f2a9e753a24d58aed7220f025
+oid sha256:d2fea6bfe274bbb6be47002c1450a76faa2a972941bdc9e42ce7dde933f21bfd
 size 15133664