Transformers
Safetensors
English
ocbyram commited on
Commit
bd85a36
·
verified ·
1 Parent(s): 21e6212

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -8
README.md CHANGED
@@ -61,14 +61,9 @@ Optimal Answer: I developed a predictive model using Python and scikit-learn to
61
  After creating this dataset, I uploaded it to my project notebook. Then, I modified the dataset to reformat it and make it easier to train. I created an 'Instruct' column with each row's job title,
62
  description, applicant profile, and the prompt 'Generate a relevant interview question and
63
  provide an optimal answer using the information from this applicant's profile. Interview Question and Optimal Answer:'. Then I combined the interview question/ optimal answer
64
- into one column labeled 'Answer'.
65
-
66
- I established a training, validation, and testing split using scikit-learn's train_test_split function and pandas .sample() method for shuffling. The proportions are as follows:
67
-
68
- Training: 3,200 examples (64% of total)
69
- Validation: 800 examples (16% of total)
70
- Testing: 1,000 examples (20% of total)
71
- Random seed: 42
72
 
73
 
74
  ## Methodology
 
61
  After creating this dataset, I uploaded it to my project notebook. Then, I modified the dataset to reformat it and make it easier to train. I created an 'Instruct' column with each row's job title,
62
  description, applicant profile, and the prompt 'Generate a relevant interview question and
63
  provide an optimal answer using the information from this applicant's profile. Interview Question and Optimal Answer:'. Then I combined the interview question/ optimal answer
64
+ into one column labeled 'Answer'. Finally, I established a training, validation, and testing split using scikit-learn's train_test_split function and pandas .sample()
65
+ method for shuffling. The proportions are as follows: Training: 3,200 examples (64% of total), Validation: 800 examples (16% of total), Testing: 1,000 examples (20% of total),
66
+ with Random seed: 42.
 
 
 
 
 
67
 
68
 
69
  ## Methodology