Training in progress epoch 0

README.md

@@ -14,10 +14,10 @@ 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: 0.4775
-- Validation Loss: 0.5258
-- Train Accuracy: 0.7367
-- Epoch: 2
+- Train Loss: 0.6782
+- Validation Loss: 0.6667
+- Train Accuracy: 0.5867
+- Epoch: 0
 
 ## Model description
 
@@ -36,16 +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': 2e-05, 'decay_steps': 215, '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': 2e-05, 'decay_steps': 435, '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 |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.5923     | 0.5516          | 0.7467         | 0     |
-| 0.5425     | 0.5372          | 0.7467         | 1     |
-| 0.4775     | 0.5258          | 0.7367         | 2     |
+| 0.6782     | 0.6667          | 0.5867         | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:857362f50d9ce52792c4f1892811e43e09cbcef0a66bfc313ed5d507a161288d
+oid sha256:68c2404f3876fba44af3d0ed3cc1966081cfccbca3daf6fda9f6f9caa8b20cbc
 size 269733656