{
  "schema": 1,
  "run_id": "2026-10-08-quick-card-prompts-2e5238",
  "status": "complete",
  "stop_reason": null,
  "suite": {
    "name": "embeddings",
    "tier": "quick",
    "suite_hash": "4c216f567e7755fcba7cd61c6ffe3e6ea2c399c52c3d2a2a6aedefb20066cf05",
    "ids": 66939
  },
  "subject": {
    "model": "embeddinggemma-300m",
    "checkpoint": {
      "hf": "google/embeddinggemma-300m",
      "revision": "57c266a740f537b4dc058e1b0cda161fd15afa75"
    },
    "quant": {
      "format": "fp32",
      "producer": "google",
      "repo": "google/embeddinggemma-300m",
      "revision": "57c266a740f537b4dc058e1b0cda161fd15afa75"
    },
    "engine": {
      "name": "sentence-transformers-torch-cuda",
      "version": "st6.1.0-torch2.14.1+cu126"
    },
    "key": "embeddinggemma-300m/hf-57c266a/fp32-google/sentence-transformers-torch-cuda-st6.1.0-torch2.14.1-cu126",
    "target": "recipe",
    "engine_visibility": "public",
    "verified_identity": true,
    "label": null
  },
  "mode": "native",
  "profile": "card-prompts",
  "harness": {
    "name": "bench",
    "commit": "86f9bc06d769c296ac09a88092b755d4bf22a912",
    "dirty": false,
    "suite_hash": "4c216f567e7755fcba7cd61c6ffe3e6ea2c399c52c3d2a2a6aedefb20066cf05",
    "scorer": {
      "name": "mteb",
      "version": "2.22.5"
    },
    "agent": null
  },
  "endpoint": "http://gpu-host-2/v1/embeddings",
  "dataset": {
    "tasks": [
      "NanoArguAnaRetrieval",
      "NanoClimateFeverRetrieval",
      "NanoDBPediaRetrieval",
      "NanoFEVERRetrieval",
      "NanoFiQA2018Retrieval",
      "NanoHotpotQARetrieval",
      "NanoMSMARCORetrieval",
      "NanoNFCorpusRetrieval",
      "NanoNQRetrieval",
      "NanoQuoraRetrieval",
      "NanoSCIDOCSRetrieval",
      "NanoSciFactRetrieval",
      "NanoTouche2020Retrieval",
      "STSBenchmark",
      "Banking77Classification"
    ],
    "manifest": ".artifacts/embeddings/manifests/670f8d38974312e2.jsonl",
    "manifest_sha256": "2d2ce7c3195335d3917cd3675666232777a4bdf38c110da28a72cac316470566",
    "texts": 66939,
    "prompts_sha256": "3d60d338d6b690bbd1eae200c329bfea91f1f669c5333ababdf2ffd41aa5d9b0"
  },
  "request_settings": {
    "batch_size": 32,
    "encoding_format": "base64",
    "order": "by text length, descending",
    "dims_scored": [
      768,
      512,
      256,
      128
    ],
    "width": 768
  },
  "dispatch": {
    "concurrency": 1,
    "requests_per_minute": null,
    "retries": 0
  },
  "budget": {
    "cap_usd": null,
    "spent_usd": 0,
    "price": null
  },
  "environment": {
    "node": "v24.21.0",
    "platform": "darwin",
    "arch": "arm64",
    "location": "America/Chicago"
  },
  "attempted": 2092,
  "completed": 2092,
  "started_at": "2026-10-08T21:34:13.945Z",
  "finished_at": "2026-10-08T21:53:03.432Z",
  "observed_models": {
    "embeddinggemma-300m": 2092
  },
  "engine": {
    "backend": "sentence-transformers",
    "device": "cuda",
    "dtype": "float32",
    "torch": "2.14.1+cu126",
    "cuda_arch_list": [
      "sm_50",
      "sm_60",
      "sm_70",
      "sm_75",
      "sm_80",
      "sm_86",
      "sm_90"
    ],
    "device_name": "Tesla P100-PCIE-16GB",
    "sentence_transformers": "6.1.0",
    "transformers": "5.19.0",
    "max_seq_length": 2048,
    "dimension": 768,
    "trust_remote_code": false,
    "unpadded": false,
    "triton_overrides": "disabled torch's native Triton op overrides (sm_60 is below Triton's sm_70 minimum)",
    "token_budget_per_forward": 16384,
    "python": "3.12.15",
    "platform": "Linux-7.0.0-34-generic-x86_64-with-glibc2.36",
    "machine": "x86_64",
    "numpy": "2.5.3"
  },
  "hardware": {
    "host": "gpu-host-2",
    "recipe": "embeddinggemma-300m/p100/st",
    "placements": [
      {
        "host": "gpu-host-2",
        "devices": [
          {
            "kind": "gpu",
            "label": "p100",
            "model": "P100",
            "vendor": "nvidia",
            "vram_gb": 16
          }
        ]
      }
    ]
  },
  "launcher": {
    "run_id": "2026-10-08T21-33-07-269Z",
    "profile": "st-fp32",
    "params": {
      "checkpoint": "google/embeddinggemma-300m",
      "checkpoint_rev": "57c266a740f537b4dc058e1b0cda161fd15afa75",
      "model_name": "embeddinggemma-300m",
      "max_len": "2048",
      "trust_remote_code": "false",
      "unpadded": "false",
      "stack": "",
      "engine_name": "sentence-transformers-torch-cuda",
      "engine_version": "st6.1.0-torch2.14.1+cu126",
      "producer": "google",
      "weights_repo": "google/embeddinggemma-300m",
      "weights_rev": "57c266a740f537b4dc058e1b0cda161fd15afa75",
      "backend": "st",
      "precision": "fp32"
    },
    "source": {
      "repo": "local mirror",
      "commit": "e6ceae95a5303653a7abbd1dff06d7ce6ce6d878",
      "override": false,
      "mirror": "https://github.com/iammrduncan/inference-engines"
    },
    "acknowledgments": [
      {
        "component": "google/embeddinggemma-300m",
        "hash": "f58fc42228e4ba242f03b95234afcfb7ca13fa57e5d757d02807a8b6f4508a34",
        "at": "2026-10-08T21:33:07.268Z"
      }
    ]
  },
  "reference": null,
  "vectors": {
    "path": ".artifacts/embeddings/vectors/embeddinggemma-300m__hf-57c266a__fp32-google__sentence-transformers-torch-cuda-st6.1.0-torch2.14.1-cu126__embeddings__2026-10-08-quick-card-prompts-2e5238.npy",
    "sha256": "047fd67edd0380aa4484faf0a32f0144a668954bc2eb18d40ebc0f65b9b96e81",
    "shape": [
      66939,
      768
    ],
    "dtype": "float32",
    "uploaded": false
  },
  "edits": [
    {
      "date": "2026-10-17",
      "note": "Edited for publication: lab host names replaced with aliases; engine ports and local file paths removed. Measurements, request bodies and outputs are unchanged."
    }
  ]
}