-
Notifications
You must be signed in to change notification settings - Fork 398
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
What magnitude of avg loss indicates a relatively good result for a quantization model #649
Comments
My rule of thumb is if your losses are > 1.0 for early [1-3] layers, calibration data is off or tokenizer is not properly configured. Each module in each layer has it's own loss trend in my experience. Some modules just are harder to quantize. MOE models are the worst-case for gptq due the gating/router layer.
|
Thanks for your quick reply! @Qubitium |
@Qubitium I have finished the two tests you mentioned above, and found that the result for test 1 is reasonable, but the result of human eval test falls about 50% after quantization, do you have any advice to fix it? thanks |
What is your PPL before and after quantization? |
My PPL before quantization on wiki2 is 5.334, while after quantization the PPL is 5.415, my model is a finetuned version of qwen1.5-72b |
5.33 for pre-quant PPL is already very suspect in my opinion for such a huge model. Forget quant, troubleshoot your PPL/inference pre-quant. Make sure your PPL is not using same dataset as calibration but real use-case. |
When i quantize a model, the avg loss is lower in earlier layers(0.02) than the loss in later layers(2.0), i'm curious that if the quantization is failed due to a large avg loss?
And for experience, what magnitude of avg loss is good for a quantization model?
The text was updated successfully, but these errors were encountered: