{
  "model": "ayushadarsh7/kayak_v2",
  "model_revision": "8f741f994f694670d47330488e90f5c835cec2fa",
  "model_dtype": "float32",
  "weight_hashes_verified": true,
  "weights_source": "local export identical by SHA-256 to public model shards",
  "test_sha256": "fab178212b171cc35e45ff1f9fa350f6a21138f869103c64d6ef8d3c43684a7b",
  "train_sha256": "86b71f7712c8c8194e67ead954d259de1649a45d5237ca52382fb95588bc46ab",
  "examples": 147,
  "episodes": 8,
  "seed": 1,
  "attention": "sdpa",
  "tf32": true,
  "deterministic_algorithms": true,
  "do_sample": false,
  "max_new_tokens": 128,
  "min_pixels": 262144,
  "max_pixels": 524288,
  "teacher_forced_loss": "Assistant-token-weighted negative log likelihood; includes assistant end-of-turn tokens",
  "success_rule": "Parsed action matches; valid xywh box; predicted box center lies inside target; exact fill value or press key when applicable. IoU has no threshold in this success rule.",
  "json_ok_rule": "Existing grounding parser can extract a JSON object from surrounding text; strict_json_ok additionally requires the entire response to be one JSON object.",
  "bbox_valid_rule": "Finite numeric normalized xywh; x/y>=0; w/h>0; components<=1000; right/bottom<=1001 (inherited scorer tolerance).",
  "seen_box_rule": "Exact normalized bbox tuple occurs in the training set; this is not semantic element familiarity.",
  "scenario_status_rule": "all_evaluated_steps_passed only if every held-out eligible click/fill example in that episode passes independently; this is not end-to-end browser success.",
  "limitations": [
    "One shared browser session.",
    "Nine cross-split similar-image pairs flagged by the split audit.",
    "Only eligible click/fill steps evaluated; scroll, wait, drag, press and excluded captures are outside this test.",
    "No model selection or tuning performed on this test set.",
    "Inference limit 128 matches published helper; legacy study evaluator default is 64, so settings are not identical to older runs."
  ],
  "versions": {
    "torch": "2.9.0+cu128",
    "transformers": "4.57.1",
    "accelerate": "1.11.0",
    "Pillow": "12.3.0"
  },
  "started_utc": "2026-10-24T19:24:13Z",
  "script_sha256": "c7b4a2443c0e1446df81e22452dc23b7ddc05664d970d21828c255081a30440f"
}