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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.6773
-- Validation Loss: 0.6928
-- Train Accuracy: 0.6119
-- Epoch: 4
+- Train Loss: 0.7233
+- Validation Loss: 0.7199
+- Train Accuracy: 0.3881
+- Epoch: 0
 
 ## Model description
 
@@ -36,18 +36,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adamax', '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': 0.001, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07}
+- 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': 0.001, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.6936     | 0.6678          | 0.6119         | 0     |
-| 0.6691     | 0.6658          | 0.6119         | 1     |
-| 0.6757     | 0.6684          | 0.6119         | 2     |
-| 0.6825     | 0.6848          | 0.6119         | 3     |
-| 0.6773     | 0.6928          | 0.6119         | 4     |
+| 0.7233     | 0.7199          | 0.3881         | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c4e2c02236f028f8ac4ebe395954618edcab7b819fb5ede1816021d2b736d8c
+oid sha256:ca55a33503e48ef0396a77a405c26b6f82222027c3f486cab96167a26d88d830
 size 438223192