Training in progress epoch 0

README.md

@@ -14,11 +14,11 @@ 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: 0.6131
-- Validation Loss: 0.4901
-- Train Matthews Correlation: 0.5370
-- Train F1: 0.7500
-- Train Accuracy: 0.7660
+- Train Loss: 0.6338
+- Validation Loss: 0.5099
+- Train Matthews Correlation: 0.5313
+- Train F1: 0.7560
+- Train Accuracy: 0.7642
 - Epoch: 0
 
 ## Model description
@@ -38,19 +38,19 @@ 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': 1e-05, 'decay_steps': 3922, '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': 1e-05, 'decay_steps': 9805, '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 | Train F1 | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------------------:|:--------:|:--------------:|:-----:|
-| 0.6131     | 0.4901          | 0.5370                     | 0.7500   | 0.7660         | 0     |
+| 0.6338     | 0.5099          | 0.5313                     | 0.7560   | 0.7642         | 0     |
 
 
 ### Framework versions
 
-- Transformers 4.38.2
+- Transformers 4.40.2
 - TensorFlow 2.15.0
-- Datasets 2.19.0
-- Tokenizers 0.15.2
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -26,7 +26,7 @@
   "output_past": true,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.40.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 35000

logs/train/events.out.tfevents.1716130157.4b0d0dc2f2b4.3485.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:647aa61aa9f3253ddafd75ef73d9b68d6faeafd419c47acdde6dd629cc5c915c
+size 3541055

logs/validation/events.out.tfevents.1716130290.4b0d0dc2f2b4.3485.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3034a9b6691d446edb54ba253f46f3dd2f99bee323141efa34d08733426c007
+size 231

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:935b1fbdea39b5219575ea33f425130570b0763b9ab24cf3125efd6c9818ed44
+oid sha256:f8a9a096e33afe42a3156d447eb0c8d9cd96d7c25bde463ef655276a3907d16e
 size 451979544