Training in progress epoch 40

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: 0.0189
-- Train Dice Coef: 0.7743
-- Train Iou: 0.6446
-- Validation Loss: 0.0237
-- Validation Dice Coef: 0.8501
-- Validation Iou: 0.7429
+- Train Dice Coef: 0.7770
+- Train Iou: 0.6491
+- Validation Loss: 0.0234
+- Validation Dice Coef: 0.8479
+- Validation Iou: 0.7402
 - Train Lr: 1.25e-08
-- Epoch: 39
+- Epoch: 40
 
 ## Model description
 
@@ -40,7 +40,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'learning_rate': 1.25e-08, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- optimizer: {'name': 'Adam', 'learning_rate': 6.25e-10, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
@@ -87,6 +87,7 @@ The following hyperparameters were used during training:
 | 0.0187     | 0.7774          | 0.6497    | 0.0232          | 0.8496               | 0.7423         | 1.25e-08 | 37    |
 | 0.0187     | 0.7791          | 0.6502    | 0.0234          | 0.8496               | 0.7424         | 1.25e-08 | 38    |
 | 0.0189     | 0.7743          | 0.6446    | 0.0237          | 0.8501               | 0.7429         | 1.25e-08 | 39    |
+| 0.0189     | 0.7770          | 0.6491    | 0.0234          | 0.8479               | 0.7402         | 1.25e-08 | 40    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02a78b316c062d656b45079334445a3a277cabe539c71a0654e966545de21346
+oid sha256:81f356ea8140621964b54eadb019276cedf3f20a0e16af8a9f39ff70f82f2624
 size 15133664