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 [nlpaueb/bert-base-greek-uncased-v1](https://huggingface.co/nlpaueb/bert-base-greek-uncased-v1) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.1566
-- Validation Loss: 0.3953
-- Train Accuracy: 0.8502
-- Epoch: 2
+- Train Loss: 0.4533
+- Validation Loss: 0.3342
+- Train Matthews Correlation: 0.6698
+- Epoch: 0
 
 ## Model description
 
@@ -36,16 +36,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 10752, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 10035, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, '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 |
-|:----------:|:---------------:|:--------------:|:-----:|
-| 0.4256     | 0.3462          | 0.8552         | 0     |
-| 0.2512     | 0.3395          | 0.8703         | 1     |
-| 0.1566     | 0.3953          | 0.8502         | 2     |
+| Train Loss | Validation Loss | Train Matthews Correlation | Epoch |
+|:----------:|:---------------:|:--------------------------:|:-----:|
+| 0.4533     | 0.3342          | 0.6698                     | 0     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1704632235.86bb3fd0cfc1.153.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:343df63b946b12d5293838bf3e4f8ca62351202ef268e4ab5a2bdf6aa9c899d9
+size 3530135

logs/validation/events.out.tfevents.1704632354.86bb3fd0cfc1.153.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6769f6cf95859cc9e010063e4d78c75b9694bc6f1576b16ded7c4ed239b70e5f
+size 232

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56e88147a447b474d254eea1dcb7b1c36f365ac2502d0208294713680dba4a58
+oid sha256:1b4617fc43934f054dd9c293462eb5e253c5a0d07973a00c6b43103626e9f34b
 size 451979544