Add comprehensive model card

README.md

@@ -1,3 +1,4 @@
+
 ---
 language:
 - km
@@ -10,9 +11,9 @@ tags:
 - pytorch
 - transformers
 widget:
-- text: ខ្ញុំចង់<mask>ភាសាខ្មែរ
-- text: ប្រទេសកម្ពុជាមាន<mask>ខេត្ត
-- text: រាជធានីភ្នំពេញគឺជ<mask>របស់ប្រទេសកម្ពុជា
+- text: "ខ្ញុំចង់<mask>ភាសាខ្មែរ"
+- text: "ប្រទេសកម្ពុជាមាន<mask>ខេត្ត"
+- text: "រាជធានីភ្នំពេញគឺជ<mask>របស់ប្រទេសកម្ពុជា"
 metrics:
 - perplexity
 base_model: xlm-roberta-base
@@ -31,7 +32,7 @@ This is a Pretrain Language Model using XLM-RoBERTa Architecture for Khmer & Eng
 - **Training Data**: Khmer & English dataset with 31M examples with total 6Billion characters 
 - **Parameters**: 163M trainable parameters
 - **Training Steps**: 1,122,978
-- **Final Checkpoint**: Step 1950500
+- **Final Checkpoint**: Step 2064000
 
 ## Training Details
 
@@ -45,10 +46,10 @@ This is a Pretrain Language Model using XLM-RoBERTa Architecture for Khmer & Eng
 - **Training time**: I trained this model for 10 Days
 
 ## Training Metrics
-- **Final Training Loss**: 2.3641
-- **Final Learning Rate**: 1.73e-05
-- **Final Gradient Norm**: 5.9456
-- **Training Epoch**: 13.44
+- **Final Training Loss**: 2.3435
+- **Final Learning Rate**: 1.72e-05
+- **Final Gradient Norm**: 5.9683
+- **Training Epoch**: 14.23
 
 
 ## Usage