Commit
•
36e549f
1
Parent(s):
efaf00f
Update README.md
Browse files
README.md
CHANGED
@@ -72,9 +72,10 @@ The model architecture used in this model is GPT-2, a transformer-based language
|
|
72 |
## Evaluation Metrics
|
73 |
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. During validation, the model achieved the following metrics:
|
74 |
|
75 |
-
-
|
76 |
-
- Average perplexity:
|
77 |
-
-
|
|
|
78 |
|
79 |
## Limitations and Bias
|
80 |
This model is not suitable for all use cases due to its limited training time on a weak computer. As a result, it may produce irrelevant or nonsensical responses. Additionally, it has not been fine-tuned to remember the chat history, is unable to provide follow-up responses, and it does not know the answer to many questions (it was only fine-tuned to respond in a conversational way). For optimal performance, we recommend using a GPU with at least 4GB of VRAM and downloading the model manually instead of using the Transformers library. Here's how you should deploy the model:
|
|
|
72 |
## Evaluation Metrics
|
73 |
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. During validation, the model achieved the following metrics:
|
74 |
|
75 |
+
- BLEU Score: 9
|
76 |
+
- Average perplexity: 49
|
77 |
+
- Loss: 1.7
|
78 |
+
Although these metrics seem mediocre, it's actually better because that way the model is able to make open-ended responses, but is still coherent to the user's input.
|
79 |
|
80 |
## Limitations and Bias
|
81 |
This model is not suitable for all use cases due to its limited training time on a weak computer. As a result, it may produce irrelevant or nonsensical responses. Additionally, it has not been fine-tuned to remember the chat history, is unable to provide follow-up responses, and it does not know the answer to many questions (it was only fine-tuned to respond in a conversational way). For optimal performance, we recommend using a GPU with at least 4GB of VRAM and downloading the model manually instead of using the Transformers library. Here's how you should deploy the model:
|