Update README.md

README.md

@@ -1,47 +1,30 @@
 ---
-tags:
-- generated_from_keras_callback
-model-index:
-- name: organon-fallacy-classification
-  results: []
+language: eng
+license: mit
+dataset: Logical Fallacy Dataset
 ---
 
-<!-- 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. -->
-
-# organon-fallacy-classification
-
-This model is a fine-tuned version of [q3fer/fallacy_classifier_01](https://huggingface.co/q3fer/fallacy_classifier_01) on an unknown dataset.
-It achieves the following results on the evaluation set:
+# distilbert-base-fallacy-classification
 
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the [Logical Fallacy Dataset](https://github.com/causalNLP/logical-fallacy).
 
 ## Model description
 
-More information needed
-
-## Intended uses & limitations
-
-More information needed
+The model is fine-tuned for text classification of logical fallacies. There are a total of 14 classes: ad hominem, ad populum, appeal to emotion, circular reasoning, equivocation, fallacy of credibility, fallacy of extension, fallacy of logic, fallacy of relevance, false causality, false dilemma, faulty generalization, intentional, and miscellaneous.
 
 ## Training and evaluation data
 
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- optimizer: None
-- training_precision: float32
-
-### Training results
+The [Logical Fallacy Dataset](https://github.com/causalNLP/logical-fallacy) is used for training and evaluation.
 
+Jin, Z., Lalwani, A., Vaidhya, T., Shen, X., Ding, Y., Lyu, Z., ... Schölkopf, B. (2022). Logical Fallacy Detection. arXiv. https://doi.org/10.48550/arxiv.2202.13758
 
+## Training procedure
 
-### Framework versions
+The following hyperparameters were used during fine-tuning:
 
-- Transformers 4.25.1
-- TensorFlow 2.9.2
-- Datasets 2.8.0
-- Tokenizers 0.13.2
+- learning_rate : 2e-5
+- warmup steps : 0
+- batch_size: 16
+- num_epochs: 8
+- batches_per_epoch: 122
+- total_train_steps: 976