Training in progress epoch 39

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: 0.0420
-- Train Dice Coef: 0.8833
-- Train Iou: 0.7929
-- Validation Loss: 0.0430
-- Validation Dice Coef: 0.8895
-- Validation Iou: 0.8023
+- Train Loss: 0.0424
+- Train Dice Coef: 0.8832
+- Train Iou: 0.7924
+- Validation Loss: 0.0437
+- Validation Dice Coef: 0.8890
+- Validation Iou: 0.8013
 - Train Lr: 2.5e-07
-- Epoch: 38
+- Epoch: 39
 
 ## Model description
 
@@ -40,7 +40,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'learning_rate': 2.5e-07, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- optimizer: {'name': 'Adam', 'learning_rate': 1.25e-08, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
@@ -86,6 +86,7 @@ The following hyperparameters were used during training:
 | 0.0420     | 0.8826          | 0.7917    | 0.0433          | 0.8894               | 0.8021         | 2.5e-07  | 36    |
 | 0.0423     | 0.8833          | 0.7926    | 0.0429          | 0.8893               | 0.8018         | 2.5e-07  | 37    |
 | 0.0420     | 0.8833          | 0.7929    | 0.0430          | 0.8895               | 0.8023         | 2.5e-07  | 38    |
+| 0.0424     | 0.8832          | 0.7924    | 0.0437          | 0.8890               | 0.8013         | 2.5e-07  | 39    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a86e5c5bb8aaeeb3df98daa551783eb41fe29642771df80f4e55b8a18a862b0
+oid sha256:888b46fe0722df5f0f40bf6d42ee4b2717ace295eb0c0318c363657adda406be
 size 15133664