Training in progress epoch 15

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: 0.0237
-- Train Dice Coef: 0.7434
-- Train Iou: 0.6076
-- Validation Loss: 0.0364
-- Validation Dice Coef: 0.8060
-- Validation Iou: 0.6841
+- Train Loss: 0.0227
+- Train Dice Coef: 0.7532
+- Train Iou: 0.6192
+- Validation Loss: 0.0556
+- Validation Dice Coef: 0.6927
+- Validation Iou: 0.5449
 - Train Lr: 1e-04
-- Epoch: 14
+- Epoch: 15
 
 ## Model description
 
@@ -40,7 +40,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'learning_rate': 1e-04, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- optimizer: {'name': 'Adam', 'learning_rate': 5e-06, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
@@ -62,6 +62,7 @@ The following hyperparameters were used during training:
 | 0.0259     | 0.7344          | 0.5961    | 0.0357          | 0.7986               | 0.6716         | 1e-04    | 12    |
 | 0.0257     | 0.7405          | 0.6010    | 0.0385          | 0.7970               | 0.6702         | 1e-04    | 13    |
 | 0.0237     | 0.7434          | 0.6076    | 0.0364          | 0.8060               | 0.6841         | 1e-04    | 14    |
+| 0.0227     | 0.7532          | 0.6192    | 0.0556          | 0.6927               | 0.5449         | 1e-04    | 15    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a004e2064e2e89d72e6830c42a0b6d61418ae88d2d2a9293e7ccca3d5a841190
+oid sha256:e926b0df7597e655a1c7cc97280346e82e2f2b43e712658e43e1c44ab6a6eb83
 size 15133664