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: 0.1644
-- Validation Loss: 0.7249
-- Train F1: 0.7388
-- Epoch: 5
+- Train Loss: 0.1172
+- Validation Loss: 0.5493
+- Train F1: 0.8137
+- Epoch: 4
 
 ## Model description
 
@@ -37,19 +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': 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}
+- 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': 4030, '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 |
 |:----------:|:---------------:|:--------:|:-----:|
-| 0.6653     | 0.5726          | 0.7255   | 0     |
-| 0.5481     | 0.5550          | 0.7296   | 1     |
-| 0.4503     | 0.5308          | 0.7469   | 2     |
-| 0.3473     | 0.5723          | 0.7359   | 3     |
-| 0.2440     | 0.6400          | 0.7355   | 4     |
-| 0.1644     | 0.7249          | 0.7388   | 5     |
+| 0.5556     | 0.4472          | 0.7965   | 0     |
+| 0.3877     | 0.4268          | 0.8107   | 1     |
+| 0.2931     | 0.4459          | 0.8165   | 2     |
+| 0.1734     | 0.5071          | 0.8223   | 3     |
+| 0.1172     | 0.5493          | 0.8137   | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eed93917e20886209fd54839d62281794f51957bd8943db4c462dbf81caf3163
+oid sha256:8e4d8e42745ffeefcc6dd8e22d74f5cd35bfc59c3b353d94d22186f54ec6abbd
 size 438223128