Training in progress epoch 0

README.md

@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0236
-- Validation Loss: 0.0591
-- Epoch: 2
+- Train Loss: 0.1270
+- Validation Loss: 0.0554
+- Epoch: 0
 
 ## Model description
 
@@ -35,21 +35,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1017, '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, 'weight_decay_rate': 0.01}
+- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1017, '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, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
 - training_precision: mixed_float16
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 0.1315     | 0.0597          | 0     |
-| 0.0397     | 0.0548          | 1     |
-| 0.0236     | 0.0591          | 2     |
+| 0.1270     | 0.0554          | 0     |
 
 
 ### Framework versions
 
 - Transformers 4.18.0
 - TensorFlow 2.8.0
-- Datasets 2.0.0
+- Datasets 2.1.0
 - Tokenizers 0.12.1

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52d740c4f62c8985388fdd9835c2d2fb68284cbf50c8abb66c45b27dfffec868
-size 435849236
+oid sha256:8299c698ee57eb89fe30d105a454a45e6a8d58a734ff48eebad026b69cf117ac
+size 435861524