Training in progress epoch 49

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: 0.0423
-- Train Dice Coef: 0.8823
-- Train Iou: 0.7912
-- Validation Loss: 0.0431
-- Validation Dice Coef: 0.8897
-- Validation Iou: 0.8024
+- Train Dice Coef: 0.8826
+- Train Iou: 0.7916
+- Validation Loss: 0.0433
+- Validation Dice Coef: 0.8895
+- Validation Iou: 0.8021
 - Train Lr: 6.25e-10
-- Epoch: 48
+- Epoch: 49
 
 ## Model description
 
@@ -40,7 +40,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'learning_rate': 6.25e-10, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- optimizer: {'name': 'Adam', 'learning_rate': 1e-10, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
@@ -96,6 +96,7 @@ The following hyperparameters were used during training:
 | 0.0427     | 0.8817          | 0.7901    | 0.0431          | 0.8896               | 0.8023         | 6.25e-10 | 46    |
 | 0.0422     | 0.8825          | 0.7916    | 0.0433          | 0.8895               | 0.8022         | 6.25e-10 | 47    |
 | 0.0423     | 0.8823          | 0.7912    | 0.0431          | 0.8897               | 0.8024         | 6.25e-10 | 48    |
+| 0.0423     | 0.8826          | 0.7916    | 0.0433          | 0.8895               | 0.8021         | 6.25e-10 | 49    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c55633305121e16927c4664637ea532e64767a0d009059e5b0dbb8dbd73414cb
+oid sha256:3ad14a877d571c32be4420800ad283cefaadd246f7353a4e9128dce3a37262fa
 size 15133664