NAME

OpenAPI::Client::OpenAI::Path::fine_tuning-alpha-graders-run - Documentation for the /fine_tuning/alpha/graders/run path.

OPERATIONS

POST /fine_tuning/alpha/graders/run

runGrader

$client->run_grader({
    body => { ... },
});

Run a grader.

Request body

Content-Type: application/json

Example:

{
   "metadata" : {
      "errors" : {
         "formula_parse_error" : false,
         "invalid_variable_error" : false,
         "model_grader_parse_error" : false,
         "model_grader_refusal_error" : false,
         "model_grader_server_error" : false,
         "model_grader_server_error_details" : null,
         "other_error" : false,
         "python_grader_runtime_error" : false,
         "python_grader_runtime_error_details" : null,
         "python_grader_server_error" : false,
         "python_grader_server_error_type" : null,
         "sample_parse_error" : false,
         "truncated_observation_error" : false,
         "unresponsive_reward_error" : false
      },
      "execution_time" : 4.36523842811584,
      "name" : "Example score model grader",
      "sampled_model_name" : "gpt-4o-2024-08-06",
      "scores" : {},
      "token_usage" : {
         "cached_tokens" : 0,
         "completion_tokens" : 134,
         "prompt_tokens" : 190,
         "total_tokens" : 324
      },
      "type" : "score_model"
   },
   "model_grader_token_usage_per_model" : {
      "gpt-4o-2024-08-06" : {
         "cached_tokens" : 0,
         "completion_tokens" : 134,
         "prompt_tokens" : 190,
         "total_tokens" : 324
      }
   },
   "reward" : 1,
   "sub_rewards" : {}
}

Responses

200 - OK

Content-Type: application/json

Example:

{
   "metadata" : {
      "errors" : {
         "formula_parse_error" : false,
         "invalid_variable_error" : false,
         "model_grader_parse_error" : false,
         "model_grader_refusal_error" : false,
         "model_grader_server_error" : false,
         "model_grader_server_error_details" : null,
         "other_error" : false,
         "python_grader_runtime_error" : false,
         "python_grader_runtime_error_details" : null,
         "python_grader_server_error" : false,
         "python_grader_server_error_type" : null,
         "sample_parse_error" : false,
         "truncated_observation_error" : false,
         "unresponsive_reward_error" : false
      },
      "execution_time" : 4.36523842811584,
      "name" : "Example score model grader",
      "sampled_model_name" : "gpt-4o-2024-08-06",
      "scores" : {},
      "token_usage" : {
         "cached_tokens" : 0,
         "completion_tokens" : 134,
         "prompt_tokens" : 190,
         "total_tokens" : 324
      },
      "type" : "score_model"
   },
   "model_grader_token_usage_per_model" : {
      "gpt-4o-2024-08-06" : {
         "cached_tokens" : 0,
         "completion_tokens" : 134,
         "prompt_tokens" : 190,
         "total_tokens" : 324
      }
   },
   "reward" : 1,
   "sub_rewards" : {}
}

SCHEMAS

RunGraderRequest

Properties:

• grader (object, required) - The grader used for the fine-tuning job.

• item (object) - The dataset item provided to the grader. This will be used to populate the item namespace. See the guide for more details.

• model_sample (string, required) - The model sample to be evaluated. This value will be used to populate the sample namespace. See the guide for more details. The output_json variable will be populated if the model sample is a valid JSON string.

RunGraderResponse

Properties:

• metadata (object, required)

• model_grader_token_usage_per_model (object, required)

• reward (number, required)

• sub_rewards (object, required)

SEE ALSO

OpenAPI::Client::OpenAI::Path

COPYRIGHT AND LICENSE

Copyright (C) 2023-2026 by Nelson Ferraz

This library is free software; you can redistribute it and/or modify it under the same terms as Perl itself, either Perl version 5.14.0 or, at your option, any later version of Perl 5 you may have available.