Training in progress epoch 34

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: 0.0427
-- Train Dice Coef: 0.8812
-- Train Iou: 0.7894
-- Validation Loss: 0.0432
-- Validation Dice Coef: 0.8892
-- Validation Iou: 0.8016
+- Train Loss: 0.0431
+- Train Dice Coef: 0.8798
+- Train Iou: 0.7875
+- Validation Loss: 0.0433
+- Validation Dice Coef: 0.8895
+- Validation Iou: 0.8022
 - Train Lr: 5e-06
-- Epoch: 33
+- Epoch: 34
 
 ## Model description
 
@@ -40,7 +40,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'learning_rate': 5e-06, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- optimizer: {'name': 'Adam', 'learning_rate': 2.5e-07, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
@@ -81,6 +81,7 @@ The following hyperparameters were used during training:
 | 0.0436     | 0.8800          | 0.7876    | 0.0429          | 0.8902               | 0.8032         | 5e-06    | 31    |
 | 0.0430     | 0.8809          | 0.7890    | 0.0439          | 0.8876               | 0.7992         | 5e-06    | 32    |
 | 0.0427     | 0.8812          | 0.7894    | 0.0432          | 0.8892               | 0.8016         | 5e-06    | 33    |
+| 0.0431     | 0.8798          | 0.7875    | 0.0433          | 0.8895               | 0.8022         | 5e-06    | 34    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5c8dce0d911f877eef47465ff04e02590bdb6e77d70f874fcc9722cd9f22965
+oid sha256:fef00409eff4f7c843c3b31c1e2666f7b7a57e77a7b3d813c3aa9f312a141fd5
 size 15133664