Upload TFBertForSequenceClassification

README.md

@@ -15,10 +15,10 @@ 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: 0.0687
-- Validation Loss: 0.5956
-- Train F1: 0.8247
-- Epoch: 6
+- Train Loss: 0.0519
+- Validation Loss: 0.3378
+- Train F1: 0.9197
+- Epoch: 4
 
 ## Model description
 
@@ -37,20 +37,18 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- 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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1990, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- 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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 4790, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Train F1 | Epoch |
 |:----------:|:---------------:|:--------:|:-----:|
-| 0.6120     | 0.5211          | 0.7665   | 0     |
-| 0.4732     | 0.4611          | 0.8015   | 1     |
-| 0.3831     | 0.4360          | 0.8128   | 2     |
-| 0.2778     | 0.4354          | 0.8184   | 3     |
-| 0.1777     | 0.5129          | 0.8066   | 4     |
-| 0.1121     | 0.6392          | 0.7998   | 5     |
-| 0.0687     | 0.5956          | 0.8247   | 6     |
+| 0.3954     | 0.2818          | 0.9063   | 0     |
+| 0.2233     | 0.2334          | 0.9234   | 1     |
+| 0.1267     | 0.2836          | 0.8877   | 2     |
+| 0.0628     | 0.3938          | 0.8989   | 3     |
+| 0.0519     | 0.3378          | 0.9197   | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42121f9d852555534b6254aa0c176cbae7346457967efaccb31885e97ac9f0e4
+oid sha256:ae0040a811de6cd563e6226cffc7d895090d176aa56200b0550f7f0072f9eb49
 size 438223128