Update README.md

README.md

@@ -4,6 +4,8 @@ license: apache-2.0
 base_model: samchain/econo-sentence-v2
 tags:
 - generated_from_trainer
+- economics
+- finance
 metrics:
 - accuracy
 - f1
@@ -12,6 +14,11 @@ metrics:
 model-index:
 - name: EconoDetect
   results: []
+datasets:
+- samchain/economics-relevance
+language:
+- en
+pipeline_tag: text-classification
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -19,7 +26,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # EconoDetect
 
-This model is a fine-tuned version of [samchain/econo-sentence-v2](https://huggingface.co/samchain/econo-sentence-v2) on the None dataset.
+This model is a fine-tuned version of [samchain/econo-sentence-v2](https://huggingface.co/samchain/econo-sentence-v2) on the economics-relevance dataset.
+The base model is kept frozen during training, only the classification head is updated.
+
 It achieves the following results on the evaluation set:
 - Loss: 0.3973
 - Accuracy: 0.8211
@@ -29,16 +38,15 @@ It achieves the following results on the evaluation set:
 
 ## Model description
 
-More information needed
+This model is designed to detect whether a text discusses topics related to economics.
 
 ## Intended uses & limitations
 
-More information needed
+The model can be used as a screening tool to remove texts that are not related to economics.
+The dataset used for the training is strongly focused on US economy, hence a bias might occur as other regions are under represented.
 
 ## Training and evaluation data
 
-More information needed
-
 ## Training procedure
 
 ### Training hyperparameters
@@ -67,4 +75,4 @@ The following hyperparameters were used during training:
 - Transformers 4.50.0
 - Pytorch 2.1.0+cu118
 - Datasets 3.4.1
-- Tokenizers 0.21.1
+- Tokenizers 0.21.1