Training in progress epoch 31

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: 0.0529
-- Train Dice Coef: 0.8404
-- Train Iou: 0.7376
-- Validation Loss: 0.0460
-- Validation Dice Coef: 0.8820
-- Validation Iou: 0.7900
+- Train Loss: 0.0525
+- Train Dice Coef: 0.8396
+- Train Iou: 0.7379
+- Validation Loss: 0.0444
+- Validation Dice Coef: 0.8855
+- Validation Iou: 0.7954
 - Train Lr: 5e-06
-- Epoch: 30
+- Epoch: 31
 
 ## 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
@@ -78,6 +78,7 @@ The following hyperparameters were used during training:
 | 0.0543     | 0.8443          | 0.7406    | 0.0468          | 0.8803               | 0.7877         | 5e-06    | 28    |
 | 0.0535     | 0.8350          | 0.7324    | 0.0459          | 0.8833               | 0.7919         | 5e-06    | 29    |
 | 0.0529     | 0.8404          | 0.7376    | 0.0460          | 0.8820               | 0.7900         | 5e-06    | 30    |
+| 0.0525     | 0.8396          | 0.7379    | 0.0444          | 0.8855               | 0.7954         | 5e-06    | 31    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d19dc39a5c65b14c04781c01427cd9824f841e8ff7a60b6caed71e58c42c92b2
+oid sha256:9428e0d983528f7418241d075977383a068b1fbdab83d3eafa16e99337c018bd
 size 15133664