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-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 3.7859
-- Validation Loss: 3.5411
-- Epoch: 5
+- Train Loss: 4.1670
+- Validation Loss: 3.7536
+- Epoch: 0
 
 ## Model description
 
@@ -35,19 +35,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'learning_rate': 3e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- optimizer: {'name': 'Adam', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 4.1588     | 3.7905          | 0     |
-| 3.9986     | 3.6851          | 1     |
-| 3.9911     | 3.6327          | 2     |
-| 3.8780     | 3.5841          | 3     |
-| 3.7760     | 3.5799          | 4     |
-| 3.7859     | 3.5411          | 5     |
+| 4.1670     | 3.7536          | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1232fefa831914ee8fd491a1d59be87471cf13e7d3b5bfb42de78b85be1b2756
+oid sha256:35d8494d213315753a91407d173ec798d50293686a7f04a51ce1a73d76de758f
 size 524305768