Upload TFBertForSequenceClassification

README.md

@@ -1,19 +1,57 @@
 ---
 license: mit
+tags:
+- generated_from_keras_callback
 model-index:
 - name: indobert-abusive-language-classifier
   results: []
-tags:
-- text-classification
-- bert
-- indobert
 ---
 
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
 # indobert-abusive-language-classifier
 
+This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.1613
+- Train Sparse Categorical Accuracy: 0.9417
+- Validation Loss: 0.2973
+- Validation Sparse Categorical Accuracy: 0.8857
+- Epoch: 2
 
 ## Model description
 
-This model is an abusive language classifier for Bahasa Indonesia based on [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased).
-It was trained on a modified [Multi-label Hate Speech and Abusive Language Detection](https://github.com/okkyibrohim/id-multi-label-hate-speech-and-abusive-language-detection) dataset and achieves an evaluation accuracy of 90.17%.
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- optimizer: {'name': 'Adam', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
+|:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|
+| 0.4496     | 0.7811                            | 0.3146          | 0.8671                                 | 0     |
+| 0.2437     | 0.9026                            | 0.2959          | 0.8888                                 | 1     |
+| 0.1613     | 0.9417                            | 0.2973          | 0.8857                                 | 2     |
+
+
+### Framework versions
 
+- Transformers 4.30.2
+- TensorFlow 2.12.0
+- Datasets 2.13.1
+- Tokenizers 0.13.3

config.json

@@ -3,10 +3,6 @@
   "architectures": [
     "BertForSequenceClassification"
   ],
-  "id2label": {
-    "0": "SAFE", 
-    "1": "ABUSIVE"
-  },
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
   "classifier_dropout": null,
@@ -24,7 +20,7 @@
   "output_past": true,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.26.1",
+  "transformers_version": "4.30.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 31923

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac3258a051f140c5177d259514901171b920f1afc1c9e405a59a1999315f82cf
-size 442527064
+oid sha256:e3bc34ac5ee91dfa5142272b62d098cfa9f480ffbc329ddafd22d2674b4ffc4f
+size 442527000