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: 0.0189
-- Validation Loss: 0.0104
-- Epoch: 2
+- Train Loss: 0.3378
+- Validation Loss: 0.0268
+- Epoch: 0
 
 ## Model description
 
@@ -36,16 +36,14 @@ 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': 849, '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: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1077, '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}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 0.3846     | 0.0465          | 0     |
-| 0.0412     | 0.0145          | 1     |
-| 0.0189     | 0.0104          | 2     |
+| 0.3378     | 0.0268          | 0     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c88b5e8985daa8f5f90d82e154c3f494879476b2ed61633cdf9efde302e04663
+oid sha256:f5bbf4d362deecfebde2834b792a49056c6b81e2e83bc66d5c585bb6fa4e86a5
 size 431321252

tokenizer_config.json

@@ -1,4 +1,5 @@
 {
+  "add_prefix_space": false,
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": false,