Locutusque commited on
Commit
54181ec
1 Parent(s): 777f7fe

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -32,4 +32,4 @@ The model architecture used in this model is GPT-2, a transformer-based language
32
  The model is evaluated based on several metrics, including loss, reward, penalty, BLEU score, and perplexity. The loss metric is calculated during training and reflects the difference between the predicted output and the actual output. The reward metric is based on the number of correct words generated by the model, while the penalty metric penalizes the model for repeating words consecutively. The BLEU score measures the similarity between the generated text and the ground truth text, while the perplexity metric measures how well the model is able to predict the next word in a sequence.
33
 
34
  ## Limitations and Bias
35
- Because I have a rather weak computer for machine learning, I was not able to train this model for too long. The model may output irrelevant answers, or even sometimes the responses can be nonsensical.
 
32
  The model is evaluated based on several metrics, including loss, reward, penalty, BLEU score, and perplexity. The loss metric is calculated during training and reflects the difference between the predicted output and the actual output. The reward metric is based on the number of correct words generated by the model, while the penalty metric penalizes the model for repeating words consecutively. The BLEU score measures the similarity between the generated text and the ground truth text, while the perplexity metric measures how well the model is able to predict the next word in a sequence.
33
 
34
  ## Limitations and Bias
35
+ Because I have a rather weak computer for machine learning, I was not able to train this model for too long. The model may output irrelevant answers, or even sometimes the responses can be nonsensical. The Interface API is not a recommended place to test the model because this model requires a input format.