Update README.md

README.md

@@ -9,11 +9,10 @@ pipeline_tag: text-classification
 
 # Model Card for orYx-models/finetuned-roberta-leadership-sentiment-analysis 
 
-- This model is a finetuned version of, roberta text classifier.
-- The finetuning has been done on the dataset which includes inputs from corporate executives to their therapist.
-- The sole purpose of the model is to determine wether the statement made from the corporate executives is "Positive, Negative, or Neutral" with which we will also see "Confidence level, i.e the percentage of the sentiment involved in a statement.
-- The sentiment analysis tool has been particularly built for our client firm called "LDS".
-- Since it is prototype tool by orYx Models, all the feedback and insights from LDS will be used to finetune the model further.
+- This model is a finetuned version of, roberta text classifier. The finetuning has been done on the dataset which includes inputs from corporate executives to their therapist.
+  The sole purpose of the model is to determine wether the statement made from the corporate executives is "Positive, Negative, or Neutral" with which we will also see "Confidence level, i.e the percentage of the sentiment involved in a statement.
+  The sentiment analysis tool has been particularly built for our client firm called "LDS".
+  Since it is prototype tool by orYx Models, all the feedback and insights from LDS will be used to finetune the model further.
 
 
 
@@ -22,8 +21,8 @@ pipeline_tag: text-classification
 ### Model Description
 
 - This model is finetuned on a RoBERTa-base model trained on ~124M tweets from January 2018 to December 2021,and finetuned for sentiment analysis with the TweetEval benchmark.
-- The original Twitter-based RoBERTa model can be found here and the original reference paper is TweetEval.
-- This model is suitable for English.
+  The original Twitter-based RoBERTa model can be found here and the original reference paper is TweetEval.
+  This model is suitable for English.
 
 
 
@@ -74,7 +73,7 @@ Out[7]: [{'label': 'Positive', 'score': 0.9996090531349182}]
 X_train, X_val, y_train, y_val = train_test_split(X,y, test_size = 0.2, stratify = y)
 
 - **Train data:** 80% of 4396 records = 3516
-- **Test data:** 20% of 4396 records = 789
+- **Test data:** 20% of 4396 records = 879
 
 
 ### Training Procedure
@@ -90,97 +89,73 @@ X_train, X_val, y_train, y_val = train_test_split(X,y, test_size = 0.2, stratify
 
 #### Training Hyperparameters
 
-- args = TrainingArguments(
-    output_dir="output",
-    do_train = True,
-    do_eval = True,
-    num_train_epochs = 1,
-    per_device_train_batch_size = 4,
-    per_device_eval_batch_size = 8,
-    warmup_steps = 50,
-    weight_decay = 0.01,
-    logging_strategy= "steps",
-    logging_dir= "logging",
-    logging_steps = 50,
-    eval_steps = 50,
-    save_strategy = "steps",
-    fp16 = True,
-    #load_best_model_at_end = True
-)
+- **TrainingArguments**
+- output_dir="output",
+- do_train = True,
+- do_eval = True,
+- num_train_epochs = 1,
+- per_device_train_batch_size = 4,
+- per_device_eval_batch_size = 8,
+- warmup_steps = 50,
+- weight_decay = 0.01,
+- logging_strategy= "steps",
+- logging_dir= "logging",
+- logging_steps = 50,
+- eval_steps = 50,
+- save_strategy = "steps",
+- fp16 = True,
+- load_best_model_at_end = True
 
 #### Speeds, Sizes, Times [optional]
 
-TrainOutput(global_step=879, 
-training_loss=0.1825900522650848, 
-metrics={'train_runtime': 101.6309, 
-'train_samples_per_second': 34.596, 
-'train_steps_per_second': 8.649, 
-'total_flos': 346915041274368.0, 
-'train_loss': 0.1825900522650848, 
-'epoch': 1.0})
-
-### Testing Data
-
-20%, 789 points off 4396 population of the Dataset.
-
+- **TrainOutput**
+- global_step=879,
+- training_loss=0.1825900522650848,
+- **Metrics**
+- 'train_runtime': 101.6309,
+- 'train_samples_per_second': 34.596,
+- 'train_steps_per_second': 8.649,
+- 'total_flos': 346915041274368.0,
+- 'train_loss': 0.1825900522650848,
+- 'epoch': 1.0
 
 #### Metrics
 
-Accuracy
-F1 Score
-Precision
-Recall
+- Accuracy
+- F1 Score
+- Precision
+- Recall
 
 
 ## Evaluation Results
 
 
-loss  
-train   0.049349       
-val     0.108378 
-
-Accuracy 
-train  0.988908  
-val    0.976136  
-
-F1  
-train 0.987063       
-val   0.972464 
-
-
-Precision  
-train 0.982160    
-val   0.965982 
-
-Recall
-train  0.992357
-val    0.979861
+**loss**  
+- train   0.049349        
+- val     0.108378 
 
+**Accuracy** 
+- train  0.988908   - **98.8%**
+- val    0.976136   - **97.6%**
 
-#### Summary
+**F1**  
+- train 0.987063    - **98.7%**   
+- val   0.972464    - **97.2%**
 
-Accuracy 
-train  98.8% 
-val    97.6%  
 
-F1  
-train  98.7%      
-val    97.2% 
+**Precision**  
+- train 0.982160    - **98.2%**
+- val   0.965982    - **96.5%**
 
-Precision  
-train  98.2%    
-val    96.5% 
+**Recall**
+- train  0.992357   - **99.2%**
+- val    0.979861   - **97.9%**
 
-Recall
-train  99.2%
-val    97.9%
 
 
-{{ model_examination | default("[More Information Needed]", true)}}
 
 ## Environmental Impact
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
 
 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).