Upload model

README.md

@@ -13,9 +13,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.9587
-- Validation Loss: 1.0293
-- Epoch: 2
+- Train Loss: 0.9950
+- Validation Loss: 1.0009
+- Epoch: 0
 
 ## Model description
 
@@ -34,16 +34,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 0.0003, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.99, 'epsilon': 1e-07, 'amsgrad': True, 'weight_decay_rate': 0.01}
+- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': 1e-04, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.99, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
 - training_precision: mixed_float16
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 1.0271     | 1.0225          | 0     |
-| 0.9868     | 1.0228          | 1     |
-| 0.9587     | 1.0293          | 2     |
+| 0.9950     | 1.0009          | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3e4b1aa835f111eb47926a71bab2ea3582552dba35a532c26d062908c51a09c
+oid sha256:83e601828c59b437277a94c8139b1a63fe8180cca2fe56bbb2c077c6401bdbb2
 size 370269264