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: 0.0038
-- Validation Loss: 0.2972
-- Train Recall: 0.8810
-- Epoch: 6
+- Train Loss: 0.1358
+- Validation Loss: 0.4493
+- Train F1: 0.8396
+- Epoch: 5
 
 ## Model description
 
@@ -37,20 +37,19 @@ 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': 1500, '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': 1380, '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 Recall | Epoch |
-|:----------:|:---------------:|:------------:|:-----:|
-| 0.4802     | 0.2870          | 0.8651       | 0     |
-| 0.2311     | 0.2565          | 0.8413       | 1     |
-| 0.1166     | 0.2448          | 0.9206       | 2     |
-| 0.0348     | 0.2807          | 0.9286       | 3     |
-| 0.0123     | 0.3176          | 0.9444       | 4     |
-| 0.0210     | 0.2646          | 0.9206       | 5     |
-| 0.0038     | 0.2972          | 0.8810       | 6     |
+| Train Loss | Validation Loss | Train F1 | Epoch |
+|:----------:|:---------------:|:--------:|:-----:|
+| 0.5762     | 0.4273          | 0.8516   | 0     |
+| 0.4188     | 0.3844          | 0.8395   | 1     |
+| 0.3173     | 0.3647          | 0.8649   | 2     |
+| 0.2289     | 0.4059          | 0.8413   | 3     |
+| 0.1810     | 0.3937          | 0.8520   | 4     |
+| 0.1358     | 0.4493          | 0.8396   | 5     |
 
 
 ### Framework versions

config.json

@@ -10,14 +10,14 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "id2label": {
-    "0": "0",
-    "1": "1"
+    "0": "Other",
+    "1": "Africa"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "0": 0,
-    "1": 1
+    "Africa": 1,
+    "Other": 0
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dddca07851753356d05135f6e8419ea5a3429676dc500bc03a24211b4f7d37d
+oid sha256:f2f96df1a35925959623bf65f5f4793b6e66af08de4ca003d46b78d6bd411731
 size 438223128