Skip to main content
POST
/
fine_tuning
/
alpha
/
graders
/
run
Error
A valid request URL is required to generate request examples
{
  "reward": 123,
  "metadata": {
    "name": "<string>",
    "type": "<string>",
    "errors": {
      "formula_parse_error": true,
      "sample_parse_error": true,
      "truncated_observation_error": true,
      "unresponsive_reward_error": true,
      "invalid_variable_error": true,
      "other_error": true,
      "python_grader_server_error": true,
      "python_grader_server_error_type": "<string>",
      "python_grader_runtime_error": true,
      "python_grader_runtime_error_details": "<string>",
      "model_grader_server_error": true,
      "model_grader_refusal_error": true,
      "model_grader_parse_error": true,
      "model_grader_server_error_details": "<string>"
    },
    "execution_time": 123,
    "scores": "<unknown>",
    "token_usage": 123,
    "sampled_model_name": "<string>"
  },
  "sub_rewards": "<unknown>",
  "model_grader_token_usage_per_model": "<unknown>"
}

Authorizations

​
api-key
string
header
required

Query Parameters

​
api-version
enum<string>
default:v1

The explicit Azure AI Foundry Models API version to use for this request. v1 if not otherwise specified.

Available options:
v1,
preview

Body

application/json
​
grader
object
required

The grader used for the fine-tuning job.

​
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.

​
item
any

The dataset item provided to the grader. This will be used to populate the item namespace. See the guide for more details.

Response

The request has succeeded.

​
reward
number<float>
required
​
metadata
object
required
​
sub_rewards
any
required
​
model_grader_token_usage_per_model
any
required