Upload TFBertForSequenceClassification

README.md

@@ -16,11 +16,11 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [klue/bert-base](https://huggingface.co/klue/bert-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0251
-- Train Accuracy: 0.9928
-- Validation Loss: 0.5767
-- Validation Accuracy: 0.8752
-- Epoch: 4
+- Train Loss: 0.1942
+- Train Accuracy: 0.9247
+- Validation Loss: 0.3159
+- Validation Accuracy: 0.8760
+- Epoch: 1
 
 ## Model description
 
@@ -39,22 +39,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 1058, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 117, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': np.float32(0.9), 'beta_2': np.float32(0.999), 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.1}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 423, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 47, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': np.float32(0.9), 'beta_2': np.float32(0.999), 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.1}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
-| 0.4002     | 0.8104         | 0.3196          | 0.8654              | 0     |
-| 0.2221     | 0.9113         | 0.3135          | 0.8688              | 1     |
-| 0.1053     | 0.9627         | 0.4027          | 0.8730              | 2     |
-| 0.0459     | 0.9857         | 0.5210          | 0.8700              | 3     |
-| 0.0251     | 0.9928         | 0.5767          | 0.8752              | 4     |
+| 0.3708     | 0.8309         | 0.3033          | 0.8726              | 0     |
+| 0.1942     | 0.9247         | 0.3159          | 0.8760              | 1     |
 
 
 ### Framework versions
 
-- Transformers 4.51.1
+- Transformers 4.51.3
 - TensorFlow 2.18.0
 - Tokenizers 0.21.1

config.json

@@ -7,10 +7,6 @@
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
-  "id2label": {
-    "0": "\ubd80\uc815",
-    "1": "\uae0d\uc815"
-  },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
@@ -20,7 +16,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.51.1",
+  "transformers_version": "4.51.3",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 32000

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85244e4e7fa75f557ecb247ac692b6cc858274cd503f1fd5b9d057a8146c6e09
+oid sha256:025ab30214618f00c36e6d3992506b42f0d6e34f02715c88ac37837578e6f3bb
 size 442763544