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: 0.0647
-- Validation Loss: 0.4583
-- Train Matthews Correlation: 0.6642
-- Epoch: 4
+- Train Loss: 0.2560
+- Validation Loss: 0.3284
+- Train Accuracy: 0.8711
+- Epoch: 0
 
 ## Model description
 
@@ -36,18 +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': 1045, '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': 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}
 - training_precision: float32
 
 ### Training results
 
-| Train Loss | Validation Loss | Train Matthews Correlation | Epoch |
-|:----------:|:---------------:|:--------------------------:|:-----:|
-| 0.4426     | 0.3855          | 0.6342                     | 0     |
-| 0.2729     | 0.3549          | 0.6901                     | 1     |
-| 0.1718     | 0.3977          | 0.6504                     | 2     |
-| 0.0976     | 0.4412          | 0.6738                     | 3     |
-| 0.0647     | 0.4583          | 0.6642                     | 4     |
+| Train Loss | Validation Loss | Train Accuracy | Epoch |
+|:----------:|:---------------:|:--------------:|:-----:|
+| 0.2560     | 0.3284          | 0.8711         | 0     |
 
 
 ### Framework versions

logs/train/events.out.tfevents.1704565419.c34734224c8f.5052.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:911dd1f9a5e445cc92469c7e150fa10ef97e7251579c1b99b78139207bd2eb28
+size 3529912

logs/train/events.out.tfevents.1704565641.c34734224c8f.5052.2.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7c7030a255cd84cfbe6155b8c47cb39d69831b060178753822109a733b71321
+size 3530123

logs/validation/events.out.tfevents.1704565529.c34734224c8f.5052.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee42928c2267c2acb589d0bcf5260825fe3f94e3d59923fb1a89f56eb5bf2add
+size 166

logs/validation/events.out.tfevents.1704565698.c34734224c8f.5052.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6904648c7dc183e8aaec19d39b57267fd8b8c4d7a8eb00ef2716c25658bcc0ca
+size 232

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a635595156398fb6926139d2cfcfbc3f389ed39a133e7825bf586bb0916d3911
+oid sha256:cd9cd2760eac67e73db40eebeb169c7298ffb72eea0b0c9301a7c5f383ba6feb
 size 451979544