Create README.md

README.md

@@ -0,0 +1,26 @@
+---
+datasets:
+- utkarsharora100/google_go_emotions_hindi_translated
+language:
+- hi
+- en
+metrics:
+- accuracy 0.6997
+- f1 0.6750
+- precision 0.6761
+- recall 0.6997
+- roc_auc 0.8207
+base_model:
+- ai4bharat/indic-bert
+pipeline_tag: text-classification
+---
+Summary
+The model achieved its best performance on Epoch 5, with an accuracy of 0.6997, F1 score of 0.6750, precision of 0.6761, recall of 0.6997, and ROC AUC of 0.8207.
+The model shows stable performance across later epochs, with slight fluctuations in metrics but generally consistent results.
+Training Details
+Model: ai4bharat/indic-bert
+Dataset: Google Go Emotions Hindi Translated
+Labels: Anger, Disgust, Fear, Joy, Neutral, Sadness, Surprise
+Epochs: 10
+Batch Size: 16
+Learning Rate: 1e-5