Training in progress epoch 0

README.md

@@ -15,8 +15,8 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [dbmdz/bert-base-french-europeana-cased](https://huggingface.co/dbmdz/bert-base-french-europeana-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0051
-- Epoch: 9
+- Train Loss: 0.2157
+- Epoch: 0
 
 ## Model description
 
@@ -35,23 +35,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 9480, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 47400, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Epoch |
 |:----------:|:-----:|
-| 0.2015     | 0     |
-| 0.0863     | 1     |
-| 0.0484     | 2     |
-| 0.0310     | 3     |
-| 0.0196     | 4     |
-| 0.0141     | 5     |
-| 0.0102     | 6     |
-| 0.0072     | 7     |
-| 0.0065     | 8     |
-| 0.0051     | 9     |
+| 0.2157     | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1874b2478e918c74709b191a0b67ac10fe5df566b7169228df2f94de5a3139d
+oid sha256:2e62bbdf5a06f81e924f41f83b4bffa2afd13c5b3d958d30d4f44011b32c7587
 size 440395740