Training in progress epoch 58

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: 0.0186
-- Train Dice Coef: 0.7814
-- Train Iou: 0.6531
-- Validation Loss: 0.0235
-- Validation Dice Coef: 0.8486
-- Validation Iou: 0.7408
+- Train Loss: 0.0189
+- Train Dice Coef: 0.7772
+- Train Iou: 0.6480
+- Validation Loss: 0.0237
+- Validation Dice Coef: 0.8482
+- Validation Iou: 0.7405
 - Train Lr: 1e-10
-- Epoch: 57
+- Epoch: 58
 
 ## Model description
 
@@ -105,6 +105,7 @@ The following hyperparameters were used during training:
 | 0.0188     | 0.7767          | 0.6485    | 0.0233          | 0.8499               | 0.7429         | 1e-10    | 55    |
 | 0.0189     | 0.7729          | 0.6441    | 0.0234          | 0.8488               | 0.7413         | 1e-10    | 56    |
 | 0.0186     | 0.7814          | 0.6531    | 0.0235          | 0.8486               | 0.7408         | 1e-10    | 57    |
+| 0.0189     | 0.7772          | 0.6480    | 0.0237          | 0.8482               | 0.7405         | 1e-10    | 58    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:276f61e9b7b3cc39c212e80d5aaac3f4792f4dc6c5335cbab533edf082cf5404
+oid sha256:0d427018c4f51843e49cf765d665c7a4b5b9a102471df77022552ad907918e2f
 size 15133664