Skip to main content
GET
Get an evaluation

Authorizations

Authorization
string
header
required

Create an API key in the console.

Path Parameters

evaluation_id
string
required

Response

Successful Response

id
string
required
dataset_id
string
required
dataset_version
integer
required

The dataset version whose evaluation rows it scores.

model_id
string
required
model_sha256
string
required
model_label
string
required
model_name
string | null
required
version
integer | null
required
status
enum<string>
required
Available options:
queued,
running,
cancelling,
succeeded,
failed,
cancelled
created_at
number
required
updated_at
number
required
generation
integer
required
training_job_id
string | null
required
dataset_sha256
string
required
evaluation_sha256
string
required
method
enum<string>
required
Available options:
sft,
reward
evaluation_rows
integer
required
decisions
integer
required
completed_rows
integer
required
metrics
Metrics · object | null
required

Null until the evaluation succeeds. Then n, the decisions scored, with accuracy, loss, brier and ece for expected answers or expected_reward for rewards, and latency_ms, the median server milliseconds per request, when it was measured. A result taken from a fine-tune's own held-out scoring sends no request, so it has none.

error
Error · object | null
required
named
string

The family, or the model by its number, the request named, whose idle clock the run moves when it finishes.