Further Revision on Prompts

rdagent/components/proposal/prompts.yaml

@@ -10,7 +10,7 @@ hypothesis_gen:
     Here are the specifications: {{ hypothesis_specification }}
   user_prompt: |-
     The user has made several hypothesis on this scenario and did several evaluation on them.
-    The former hypothesis and the corresponding feedbacks are as follows:
+    The former hypothesis and the corresponding feedbacks are as follows (focus on the last one & the new hypothesis that it provides and reasoning to see if you agree):
     {{ hypothesis_and_feedback }}
     To help you generate new {{targets}}, we have prepared the following information for you:
     {{ RAG }}

rdagent/scenarios/qlib/experiment/model_template/conf.yaml

@@ -62,7 +62,7 @@ task:
             metric: loss
             loss: mse
             n_jobs: 20
-            GPU: 3
+            GPU: 2
             # loss: mse
             # lr: 0.002
             # optimizer: adam

rdagent/scenarios/qlib/experiment/prompts.yaml

@@ -48,7 +48,7 @@ qlib_factor_simulator: |-
 
 qlib_model_background: |-
   The model is a machine learning or deep learning structure used in quantitative investment to predict the returns and risks of a portfolio or a single asset. Models are employed by investors to generate forecasts based on historical data and identified factors, which are central to many quantitative investment strategies.
-  Each model takes the factors as input and predicts the future returns.
+  Each model takes the factors as input and predicts the future returns. Usually, the bigger the model is, the better the performance would be.
   The model is defined in the following parts:
   1. Name: The name of the model.
   2. Description: The description of the model.

rdagent/scenarios/qlib/prompts.yaml

@@ -152,6 +152,8 @@ model_feedback_generation:
       "Reasoning": "Provide reasoning for the hypothesis here.",
       "Decision": <true or false>,
     }
+
+    Focus on the changes in hypothesis and justify why do hypothesis evolve like this. Also, increase complexity as the hypothesis evolves  (give more layers, more neurons, and etc)
     
     Logic for generating a new hypothesis: If the previous hypothesis works, try to inherit from it and grow deeper. If the previous hypotheis doesn't work, try to make changes in the current level.