Upload README.md with huggingface_hub

README.md

@@ -1,6 +1,9 @@
+
 ---
 language:
+- en
 - ms
+- zh
 tags:
 - sentiment-analysis
 - text-classification
@@ -8,6 +11,8 @@ tags:
 license: apache-2.0
 datasets:
 - tyqiangz/multilingual-sentiments
+- scfengv/TVL_Sentiment_Analysis
+- argilla/twitter-coronavirus
 metrics:
 - accuracy
 model-index:
@@ -16,15 +21,10 @@ model-index:
   - task:
       type: text-classification
       name: Text Classification
-    dataset:
-      chinese: scfengv/TVL_Sentiment_Analysis
-      malay  : tyqiangz/multilingual-sentiments", "malay"
-      english: "argilla/twitter-coronavirus"
-
     metrics:
     - type: accuracy
-      value:  0.7841 
-
+      value: 0.8444
+---
 # xlm-roberta-base-sentiment-multilingual-finetuned
 
 ## Model description
@@ -33,11 +33,11 @@ This is a fine-tuned version of the [cardiffnlp/twitter-xlm-roberta-base-sentime
 
 ## Intended uses & limitations
 
-This model is intended for sentiment analysis tasks in Malay. It can classify text into three sentiment categories: positive, negative, and neutral.
+This model is intended for sentiment analysis tasks in English, Malay, and Chinese. It can classify text into three sentiment categories: positive, negative, and neutral.
 
 ## Training and evaluation data
 
-The model was trained and evaluated on the [tyqiangz/multilingual-sentiments](https://huggingface.co/datasets/tyqiangz/multilingual-sentiments) dataset.
+The model was trained and evaluated on the [tyqiangz/multilingual-sentiments](https://huggingface.co/datasets/tyqiangz/multilingual-sentiments)[TVL_Sentiment_Analysis](https://huggingface.co/datasets/scfengv/TVL_Sentiment_Analysis) , [argilla/twitter-coronavirus](https://huggingface.co/datasets/argilla/twitter-coronavirus) datasets, which includes data in English, Malay, and Chinese.
 
 ## Training procedure
 
@@ -59,10 +59,9 @@ training_args = TrainingArguments(
 
 ## Evaluation results
 
-Test results: {'eval_loss': 0.5505692958831787, 'eval_accuracy': 0.7840796019900498, 'eval_f1': 0.7831398165701241, 'eval_precision': 0.7831755325873082, 'eval_recall': 0.7840796019900498, 'eval_runtime': 4.2769, 'eval_samples_per_second': 234.982, 'eval_steps_per_second': 3.741, 'epoch': 2.0}
+Test results: {'eval_loss': 0.5881872177124023, 'eval_accuracy': 0.8443683409436834, 'eval_f1': 0.8438625655671501, 'eval_precision': 0.8438352235376211, 'eval_recall': 0.8443683409436834}
 
 ## Environmental impact
 
 Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
 
-