iiRecord
Agentic AI Atlas · eval-run:mmlu.phi-3-medium.2024-05
eval-run:mmlu.phi-3-medium.2024-05a5c.ai
II.
EvalRun JSON

eval-run:mmlu.phi-3-medium.2024-05

Structured · live

eval-run:mmlu.phi-3-medium.2024-05 json

Inspect the normalized record payload exactly as the atlas UI reads it.

File · benchmarks/eval-runs/eval-runs-other-oss.yamlCluster · benchmarks
Record JSON
{
  "id": "eval-run:mmlu.phi-3-medium.2024-05",
  "_kind": "EvalRun",
  "_file": "benchmarks/eval-runs/eval-runs-other-oss.yaml",
  "_cluster": "benchmarks",
  "attributes": {
    "target": "model:phi-3-medium@current",
    "benchmarkId": "benchmark:mmlu",
    "targetId": "model:phi-3-medium@current",
    "runAt": "2024-05-21T00:00:00Z",
    "runBy": "microsoft",
    "configHash": "sha256:placeholder-phi-3-medium-mmlu"
  },
  "outgoingEdges": [
    {
      "from": "eval-run:mmlu.phi-3-medium.2024-05",
      "to": "model:phi-3-medium@current",
      "kind": "evaluates_target"
    },
    {
      "from": "eval-run:mmlu.phi-3-medium.2024-05",
      "to": "benchmark:mmlu",
      "kind": "for_benchmark"
    }
  ],
  "incomingEdges": [
    {
      "from": "eval-result:mmlu.phi-3-medium.001",
      "to": "eval-run:mmlu.phi-3-medium.2024-05",
      "kind": "belongs_to_eval_run"
    }
  ]
}