Training in progress epoch 0

README.md

@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.3204
-- Validation Loss: 0.7567
-- Epoch: 2
+- Train Loss: 0.3536
+- Validation Loss: 0.5007
+- Epoch: 0
 
 ## Model description
 
@@ -36,16 +36,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'learning_rate': 0.001, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 639, '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 |
 |:----------:|:---------------:|:-----:|
-| 0.4992     | 0.7276          | 0     |
-| 0.3220     | 0.7273          | 1     |
-| 0.3204     | 0.7567          | 2     |
+| 0.3536     | 0.5007          | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1dcaaa704e60bd953abe236f7fe4f226e853d29bd0bcd3c877d609ae8517afc
-size 431192060
+oid sha256:e64dece8d8890c5b51c42c7586f93956ecee9c76cf6e6722ea42d877dda1f421
+size 431204348