Removed prompt tags in Atla template

prompts.py

@@ -90,64 +90,10 @@ Score 5: {score5_desc}
 ###Feedback:
 """
 
-# Define the Flow Judge prompt
-FLOW_JUDGE_PROMPT = """# GOAL
-Your job is to evaluate a task carried out by an AI system powered by a large \
-language model.
-
-You will be provided with the inputs and output of the task, as well as the evaluation criteria \
-and scoring rubric. Your task is to evaluate the output of the AI system based on the evaluation \
-criteria and scoring rubric provided.
-
-# INPUT
-Below are the inputs required for performing the task:
-<inputs>
-{INPUTS}
-</inputs>
-
-# OUTPUT
-Below is the output of the task:
-<output>
-{OUTPUT}
-</output>
-
-# EVALUATION CRITERIA AND SCORING RUBRIC
-Here are the evaluation criteria and the rubric that you need to use for evaluating the task:
-<evaluation_criteria>
-{EVALUATION_CRITERIA}
-</evaluation_criteria>
-
-<scoring_rubric>
-{RUBRIC}
-</scoring_rubric>
-
-# INSTRUCTIONS FOR THE EVALUATION
-1. Understand the task and criteria: Familiarize yourself with the task to be evaluated. \
-Review the evaluation criteria and scoring rubric to understand the different levels of \
-performance and the descriptions for each score.
-2. Review the inputs and output: Look at the inputs provided for the task. Examine the output \
-generated from completing the task.
-3. Compare output to score descriptions: Compare the output against the criteria and score \
-descriptions in the scoring rubric. For each criterion,decide which description best matches the \
-output.
-4. After comparing the output to the score descriptions, pay attention to the small details that \
-might impact the final score that you assign. Sometimes a small difference can dictate the final \
-score.
-5. Write verbal feedback justifying your evaluation that includes a detailed rationale, referring \
-to specific aspects of the output and comparing them to the rubric.
-6. Assign a final score based on the scoring rubric.
-
-## FORMAT FOR THE EVALUATION
-- Write the verbal feedback inside <feedback> tags without any additional surrounding text.
-- Write the numeric score inside <score> tags, without any additional surrounding text and always \
-after the feedback.
-
-Please accurately evaluate the task. Strictly adhere to the evaluation criteria and rubric."""
-
 # Judge system prompt for non-Prometheus models
 JUDGE_SYSTEM_PROMPT = """Please act as an impartial judge and evaluate based on the user's instruction. Your output format should strictly adhere to JSON as follows: {"feedback": "<write feedback>", "result": <numerical score>}. Ensure the output is valid JSON, without additional formatting or explanations.""" 
 
-ATLA_PROMPT = """<|begin_of_text|><|start_header_id|>user<|end_header_id|> You are tasked with evaluating a response based on a given instruction (which may contain an Input) and a scoring rubric that serve as the evaluation standard. Provide a comprehensive feedback on the response quality strictly adhering to the scoring rubric, without any general evaluation. Follow this with a score between 1 and 5, referring to the scoring rubric. Avoid generating any additional opening, closing, or explanations.
+ATLA_PROMPT = """You are tasked with evaluating a response based on a given instruction (which may contain an Input) and a scoring rubric that serve as the evaluation standard. Provide a comprehensive feedback on the response quality strictly adhering to the scoring rubric, without any general evaluation. Follow this with a score between 1 and 5, referring to the scoring rubric. Avoid generating any additional opening, closing, or explanations.
   Here are some rules of the evaluation:
   (1) You should prioritize evaluating whether the response satisfies the provided rubric. The basis of your score should depend exactly on the rubric. However, the response does not need to explicitly address points raised in the rubric. Rather, evaluate the response based on the criteria outlined in the rubric.
 
@@ -174,8 +120,7 @@ ATLA_PROMPT = """<|begin_of_text|><|start_header_id|>user<|end_header_id|> You a
   Score 2: {score2_desc}
   Score 3: {score3_desc}
   Score 4: {score4_desc}
-  Score 5: {score5_desc}
-  <|eot_id|><|start_header_id|>assistant<|end_header_id|>"""
+  Score 5: {score5_desc}"""
 
 ATLA_PROMPT_WITH_REFERENCE = """You are tasked with evaluating a response based on a given instruction (which may contain an Input) and a scoring rubric and reference answer that serve as the evaluation standard. Provide a comprehensive feedback on the response quality strictly adhering to the scoring rubric, without any general evaluation. Follow this with a score between 1 and 5, referring to the scoring rubric. Avoid generating any additional opening, closing, or explanations.
 
@@ -208,4 +153,58 @@ ATLA_PROMPT_WITH_REFERENCE = """You are tasked with evaluating a response based
   Score 5: {score5_desc}
 
   Reference answer:
-  {ground_truth_input}"""
+  {ground_truth_input}"""
+
+# Define the Flow Judge prompt
+FLOW_JUDGE_PROMPT = """# GOAL
+Your job is to evaluate a task carried out by an AI system powered by a large \
+language model.
+
+You will be provided with the inputs and output of the task, as well as the evaluation criteria \
+and scoring rubric. Your task is to evaluate the output of the AI system based on the evaluation \
+criteria and scoring rubric provided.
+
+# INPUT
+Below are the inputs required for performing the task:
+<inputs>
+{INPUTS}
+</inputs>
+
+# OUTPUT
+Below is the output of the task:
+<output>
+{OUTPUT}
+</output>
+
+# EVALUATION CRITERIA AND SCORING RUBRIC
+Here are the evaluation criteria and the rubric that you need to use for evaluating the task:
+<evaluation_criteria>
+{EVALUATION_CRITERIA}
+</evaluation_criteria>
+
+<scoring_rubric>
+{RUBRIC}
+</scoring_rubric>
+
+# INSTRUCTIONS FOR THE EVALUATION
+1. Understand the task and criteria: Familiarize yourself with the task to be evaluated. \
+Review the evaluation criteria and scoring rubric to understand the different levels of \
+performance and the descriptions for each score.
+2. Review the inputs and output: Look at the inputs provided for the task. Examine the output \
+generated from completing the task.
+3. Compare output to score descriptions: Compare the output against the criteria and score \
+descriptions in the scoring rubric. For each criterion,decide which description best matches the \
+output.
+4. After comparing the output to the score descriptions, pay attention to the small details that \
+might impact the final score that you assign. Sometimes a small difference can dictate the final \
+score.
+5. Write verbal feedback justifying your evaluation that includes a detailed rationale, referring \
+to specific aspects of the output and comparing them to the rubric.
+6. Assign a final score based on the scoring rubric.
+
+## FORMAT FOR THE EVALUATION
+- Write the verbal feedback inside <feedback> tags without any additional surrounding text.
+- Write the numeric score inside <score> tags, without any additional surrounding text and always \
+after the feedback.
+
+Please accurately evaluate the task. Strictly adhere to the evaluation criteria and rubric."""