Training in progress epoch 4

README.md

@@ -15,9 +15,9 @@ 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: 0.5149
-- Validation Loss: 0.7493
-- Epoch: 3
+- Train Loss: 0.4889
+- Validation Loss: 0.7936
+- Epoch: 4
 
 ## Model description
 
@@ -36,7 +36,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'learning_rate': 4.444909e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- optimizer: {'name': 'Adam', 'learning_rate': 4.02192e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
 | 0.4938     | 0.6734          | 1     |
 | 0.4921     | 0.6814          | 2     |
 | 0.5149     | 0.7493          | 3     |
+| 0.4889     | 0.7936          | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae412d04859e895e5206c190ebd0d38249c0c9d488dbf8a92d22fcfb88094759
+oid sha256:a96e8548ac2d075d98155e447570b47a1b69d3c8871be0b93626ece3a2410563
 size 15133552