From db9d01aac17753383e2cce13c2a50dd157df9504 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Hakan=20Ta=C5=9Fk=C3=B6pr=C3=BC?= Date: Mon, 27 Jan 2025 09:45:49 +0300 Subject: [PATCH] Clarify MIPROv2 naming in docs to align with paper Update documentation to clarify that references to MIPRO in the paper correspond to MIPROv2, ensuring consistency with repository naming. --- docs/docs/deep-dive/optimizers/miprov2.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/docs/docs/deep-dive/optimizers/miprov2.md b/docs/docs/deep-dive/optimizers/miprov2.md index 9bf6481960..2e0cc8f0a8 100644 --- a/docs/docs/deep-dive/optimizers/miprov2.md +++ b/docs/docs/deep-dive/optimizers/miprov2.md @@ -217,4 +217,6 @@ These steps are broken down in more detail below: 3. **Find an Optimized Combination of Few-Shot Examples & Instructions**. Finally, now that we've created these few-shot examples and instructions, we use Bayesian Optimization to choose which set of these would work best for each predictor in our program. This works by running a series of `num_trials` trials, where a new set of prompts are evaluated over our validation set at each trial. This helps the Bayesian Optimizer learn which combination of prompts work best over time. If `minibatch` is set to `True` (which it is by default), then the new set of prompts are only evaluated on a minibatch of size `minibatch_size` at each trial which generally allows for more efficient exploration / exploitation. The best averaging set of prompts is then evaluated on the full validation set every `minibatch_full_eval_steps` get a less noisey performance benchmark. At the end of the optimization process, the LM program with the set of prompts that performed best on the full validation set is returned. -For those interested in more details, more information on `MIPROv2` along with a study on `MIPROv2` compared with other DSPy optimizers can be found in [this paper](https://arxiv.org/abs/2406.11695). +For those interested in more details, more information on `MIPROv2` along with a study on `MIPROv2` compared with other DSPy optimizers can be found in [this paper](https://arxiv.org/abs/2406.11695). + +**Note:** The paper refers to the algorithm as `MIPRO`, but it actually describes what is now called `MIPROv2`. The name `MIPROv2` was adopted in the repository to reflect the addition of features like mini-batching while ensuring backward compatibility with existing code built using the original `MIPRO`. This distinction might not be immediately clear in the paper, but all references to `MIPRO` in the paper correspond to `MIPROv2`.