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: 0.0905
-- Validation Loss: 0.5628
-- Train F1: 0.8333
+- Train Loss: 0.1439
+- Validation Loss: 0.6405
+- Train F1: 0.7929
 - 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': 2060, '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': 2000, '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 |
 |:----------:|:---------------:|:--------:|:-----:|
-| 0.5688     | 0.4114          | 0.8360   | 0     |
-| 0.3845     | 0.3774          | 0.8471   | 1     |
-| 0.2700     | 0.4031          | 0.8474   | 2     |
-| 0.1751     | 0.4856          | 0.8140   | 3     |
-| 0.0905     | 0.5628          | 0.8333   | 4     |
+| 0.5683     | 0.4794          | 0.7730   | 0     |
+| 0.3997     | 0.4386          | 0.8343   | 1     |
+| 0.2829     | 0.4851          | 0.8106   | 2     |
+| 0.2183     | 0.5251          | 0.7931   | 3     |
+| 0.1439     | 0.6405          | 0.7929   | 4     |
 
 
 ### 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 sha256:144f7e7df3e7198bf6599bbe345ff14f085248085b640479d6c92149ecaa546b
+oid sha256:56fd8bd71225404e839129c6cc387da8ee97fbc7cc48bd78a06f3a0c0a245423
 size 438223128