Training in progress epoch 0

README.md

@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-german-cased](https://huggingface.co/distilbert-base-german-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.6953
-- Validation Loss: 0.7070
-- Train Accuracy: 0.45
+- Train Loss: 0.7433
+- Validation Loss: 0.7673
+- Train Accuracy: 0.3333
 - Epoch: 0
 
 ## Model description
@@ -36,14 +36,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.00016, 'decay_steps': 3, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- optimizer: {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.00032, 'decay_steps': 12, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.6953     | 0.7070          | 0.45           | 0     |
+| 0.7433     | 0.7673          | 0.3333         | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea8b02d6393754f141c326e754138ce81f518e0f326910e287ef2bbd7239431
-size 269733656
+oid sha256:99ca606ef4c71b4657a6ead4a7c54e184157833e4814af4f7ef95dd6bd650abf
+size 269738152