Upload TFBertForSequenceClassification

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-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0839
-- Validation Loss: 0.7750
-- Train F1: 0.7755
+- Train Loss: 0.0955
+- Validation Loss: 0.5721
+- Train F1: 0.8418
 - Epoch: 4
 
 ## Model description
@@ -37,18 +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 |
 |:----------:|:---------------:|:--------:|:-----:|
-| 0.5526     | 0.6443          | 0.7416   | 0     |
-| 0.3883     | 0.5055          | 0.7648   | 1     |
-| 0.2366     | 0.5839          | 0.7772   | 2     |
-| 0.1339     | 0.6715          | 0.7726   | 3     |
-| 0.0839     | 0.7750          | 0.7755   | 4     |
+| 0.5128     | 0.3961          | 0.8342   | 0     |
+| 0.3615     | 0.3747          | 0.8513   | 1     |
+| 0.2357     | 0.5269          | 0.8243   | 2     |
+| 0.1609     | 0.4436          | 0.8184   | 3     |
+| 0.0955     | 0.5721          | 0.8418   | 4     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:767f0b35ee36f1df3f908b534aaa228cd259bd44e64e3772b87fc7fd394abdf6
+oid sha256:ea37ec7d9165724e2655a68d7cf1997ed2da981f1b3135a4e1f45c6301cb11c7
 size 438223128