Blame for eval/preds_board_sampled.json

{"370818": {"text": "<ref>potted plant</ref><box>None</box><|im_end|>", "sec": 5.38, "stats": {"steps": 3, "total_s": 2.56, "npu_llm_s": 2.43, "ar_switches": 0, "tokens": 9}}, "343453": {"text": "<ref>person</ref><box><405><124><681><998></box><|im_end|>", "sec": 4.89, "stats": {"steps": 3, "total_s": 2.22, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "119828": {"text": "<ref>cat</ref><box>None</box><|im_end|>", "sec": 4.84, "stats": {"steps": 3, "total_s": 2.18, "npu_llm_s": 2.08, "ar_switches": 0, "tokens": 7}}, "47769": {"text": "<ref>chair</ref><box>None</box><|im_end|>", "sec": 5.17, "stats": {"steps": 5, "total_s": 2.5, "npu_llm_s": 2.35, "ar_switches": 1, "tokens": 7}}, "438907": {"text": "<ref>person</ref><box><114><269><255><782></box><box><275><44><622><637></box><|im_end|>", "sec": 5.08, "stats": {"steps": 4, "total_s": 2.41, "npu_llm_s": 2.26, "ar_switches": 0, "tokens": 16}}, "27972": {"text": "<ref>person</ref><box><562><200><755><564></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.2, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "64499": {"text": "<ref>zebra</ref><box><0><312><580><1000></box><|im_end|>", "sec": 4.9, "stats": {"steps": 3, "total_s": 2.23, "npu_llm_s": 2.11, "ar_switches": 0, "tokens": 11}}, "49810": {"text": "<ref>cat</ref><box><177><342><997><998></box><|im_end|>", "sec": 5.56, "stats": {"steps": 8, "total_s": 2.89, "npu_llm_s": 2.75, "ar_switches": 1, "tokens": 10}}, "334530": {"text": "<ref>surfboard</ref><box><414><560><573><608></box><|im_end|>", "sec": 4.9, "stats": {"steps": 3, "total_s": 2.22, "npu_llm_s": 2.11, "ar_switches": 0, "tokens": 11}}, "65350": {"text": "<ref>bicycle</ref><box><297><0><998><224></box><|im_end|>", "sec": 4.9, "stats": {"steps": 3, "total_s": 2.23, "npu_llm_s": 2.1, "ar_switches": 0, "tokens": 11}}, "210030": {"text": "<ref>fork</ref><box><488><432><759><903></box><|im_end|>", "sec": 5.45, "stats": {"steps": 7, "total_s": 2.78, "npu_llm_s": 2.65, "ar_switches": 1, "tokens": 10}}, "227985": {"text": "<ref>sandwich</ref><box><104><239><456><706></box><box><541><271><896><745></box><|im_end|>", "sec": 5.66, "stats": {"steps": 8, "total_s": 2.98, "npu_llm_s": 2.82, "ar_switches": 1, "tokens": 17}}, "27932": {"text": "<ref>baseball glove</ref><box><120><148><878><868></box><|im_end|>", "sec": 5.46, "stats": {"steps": 7, "total_s": 2.79, "npu_llm_s": 2.66, "ar_switches": 1, "tokens": 12}}, "185292": {"text": "<ref>person</ref><box><419><668><475><745></box><|im_end|>", "sec": 4.89, "stats": {"steps": 3, "total_s": 2.22, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "207728": {"text": "<ref>sheep</ref><box><133><705><588><998></box><box><209><150><756><998></box><|im_end|>", "sec": 5.09, "stats": {"steps": 4, "total_s": 2.42, "npu_llm_s": 2.27, "ar_switches": 0, "tokens": 17}}, "165518": {"text": "<ref>motorcycle</ref><box><422><429><700><844></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 11}}, "179285": {"text": "<ref>sports ball</ref><box><484><357><854><635></box><|im_end|>", "sec": 4.9, "stats": {"steps": 3, "total_s": 2.23, "npu_llm_s": 2.11, "ar_switches": 0, "tokens": 11}}, "326541": {"text": "<ref>person</ref><box><0><0><421><1000></box><box><256><409><410><1000></box><box><408><0><1000><1000></box><box><526><407><756><1000></box><|im_end|>", "sec": 7.38, "stats": {"steps": 19, "total_s": 4.72, "npu_llm_s": 4.41, "ar_switches": 3, "tokens": 28}}, "312586": {"text": "<ref>bear</ref><box><278><559><684><908></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.2, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "512194": {"text": "<ref>vase</ref><box><492><622><831><998></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 11}}, "344100": {"text": "<ref>sandwich</ref><box><594><431><806><703></box><|im_end|>", "sec": 4.9, "stats": {"steps": 3, "total_s": 2.23, "npu_llm_s": 2.11, "ar_switches": 0, "tokens": 11}}, "527784": {"text": "<ref>sandwich</ref><box><561><418><869><685></box><|im_end|>", "sec": 5.56, "stats": {"steps": 8, "total_s": 2.89, "npu_llm_s": 2.76, "ar_switches": 1, "tokens": 11}}, "231879": {"text": "<ref>person</ref><box><89><312><523><1000></box><box><340><290><524><1000></box><box><444><0><788><1000></box><box><637><0><876><1000></box><|im_end|>", "sec": 6.07, "stats": {"steps": 10, "total_s": 3.4, "npu_llm_s": 3.17, "ar_switches": 1, "tokens": 28}}, "348045": {"text": "<ref>toilet</ref><box><0><633><216><1000></box><box><402><636><604><1000></box><box><778><627><998><1000></box><|im_end|>", "sec": 5.3, "stats": {"steps": 5, "total_s": 2.63, "npu_llm_s": 2.45, "ar_switches": 0, "tokens": 23}}, "33104": {"text": "<ref>person</ref><box><0><0><130><923></box><box><102><0><433><909></box><box><508><0><698><908></box><box><700><0><998><888></box><|im_end|>", "sec": 6.5, "stats": {"steps": 13, "total_s": 3.83, "npu_llm_s": 3.59, "ar_switches": 2, "tokens": 28}}, "263860": {"text": "<ref>elephant</ref><box><0><122><998><998></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 11}}, "367818": {"text": "<ref>horse</ref><box><247><138><832><908></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "448365": {"text": "<ref>person</ref><box><211><77><574><748></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.2, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "163640": {"text": "<ref>person</ref><box><125><294><458><1000></box><box><685><295><944><1000></box><|im_end|>", "sec": 5.08, "stats": {"steps": 4, "total_s": 2.41, "npu_llm_s": 2.26, "ar_switches": 0, "tokens": 16}}, "556158": {"text": "<ref>person</ref><box><349><218><581><672></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "80413": {"text": "<ref>teddy bear</ref><box><364><238><567><525></box><|im_end|>", "sec": 4.89, "stats": {"steps": 3, "total_s": 2.22, "npu_llm_s": 2.11, "ar_switches": 0, "tokens": 12}}, "110359": {"text": "<ref>airplane</ref><box><348><324><659><897></box><|im_end|>", "sec": 4.89, "stats": {"steps": 3, "total_s": 2.22, "npu_llm_s": 2.11, "ar_switches": 0, "tokens": 11}}, "99810": {"text": "<ref>donut</ref><box>None</box><|im_end|>", "sec": 4.87, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.1, "ar_switches": 0, "tokens": 8}}, "147518": {"text": "<ref>toilet</ref><box><222><492><658><998></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 11}}, "80659": {"text": "<ref>horse</ref><box><0><219><999><902></box><|im_end|>", "sec": 4.87, "stats": {"steps": 3, "total_s": 2.2, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "41635": {"text": "<ref>cow</ref><box><0><322><998><685></box><|im_end|>", "sec": 4.9, "stats": {"steps": 3, "total_s": 2.22, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "448448": {"text": "<ref>giraffe</ref><box><188><0><999><999></box><|im_end|>", "sec": 4.89, "stats": {"steps": 3, "total_s": 2.22, "npu_llm_s": 2.1, "ar_switches": 0, "tokens": 12}}, "80273": {"text": "<ref>person</ref><box><262><101><581><998></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "166166": {"text": "<ref>chair</ref><box><0><318><225><764></box><|im_end|>", "sec": 5.17, "stats": {"steps": 5, "total_s": 2.5, "npu_llm_s": 2.38, "ar_switches": 1, "tokens": 10}}, "24919": {"text": "<ref>elephant</ref><box><161><344><511><716></box><box><483><348><812><717></box><|im_end|>", "sec": 5.09, "stats": {"steps": 4, "total_s": 2.41, "npu_llm_s": 2.27, "ar_switches": 0, "tokens": 17}}, "325347": {"text": "<ref>chair</ref><box>None</box><|im_end|>", "sec": 4.86, "stats": {"steps": 3, "total_s": 2.18, "npu_llm_s": 2.08, "ar_switches": 0, "tokens": 7}}, "108026": {"text": "<ref>person</ref><box><161><0><1000><1000></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "14007": {"text": "<ref>cat</ref><box>None</box><|im_end|>", "sec": 4.85, "stats": {"steps": 3, "total_s": 2.18, "npu_llm_s": 2.08, "ar_switches": 0, "tokens": 7}}, "328683": {"text": "<ref>parking meter</ref><box><358><58><594><932></box><|im_end|>", "sec": 4.9, "stats": {"steps": 3, "total_s": 2.22, "npu_llm_s": 2.11, "ar_switches": 0, "tokens": 12}}, "427077": {"text": "<ref>person</ref><box><358><148><800><818></box><|im_end|>", "sec": 4.87, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "73702": {"text": "<ref>handbag</ref><box>None</box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.2, "npu_llm_s": 2.1, "ar_switches": 0, "tokens": 8}}, "357567": {"text": "<ref>toilet</ref><box><577><720><998><998></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 11}}, "190756": {"text": "<ref>motorcycle</ref><box><148><198><780><910></box><|im_end|>", "sec": 5.46, "stats": {"steps": 7, "total_s": 2.79, "npu_llm_s": 2.64, "ar_switches": 1, "tokens": 11}}, "311909": {"text": "<ref>bus</ref><box><0><99><999><905></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.1, "ar_switches": 0, "tokens": 10}}, "19221": {"text": "<ref>person</ref><box><128><0><901><1000></box><|im_end|>", "sec": 5.58, "stats": {"steps": 8, "total_s": 2.91, "npu_llm_s": 2.76, "ar_switches": 1, "tokens": 10}}, "112626": {"text": "<ref>couch</ref><box><612><267><998><733></box><|im_end|>", "sec": 4.9, "stats": {"steps": 3, "total_s": 2.22, "npu_llm_s": 2.1, "ar_switches": 0, "tokens": 11}}, "187249": {"text": "<ref>person</ref><box><200><262><588><668></box><|im_end|>", "sec": 4.89, "stats": {"steps": 3, "total_s": 2.22, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "267434": {"text": "<ref>cow</ref><box><78><426><239><906></box><box><188><412><379><1000></box><box><438><402><567><751></box><box><542><418><644><743></box><box><633><413><752><734></box><box><728><415><827><705></box><box><821><416><935><681></box><box><897><417><1000><698></box><|im_end|>", "sec": 7.23, "stats": {"steps": 16, "total_s": 4.55, "npu_llm_s": 4.18, "ar_switches": 2, "tokens": 52}}, "422670": {"text": "<ref>person</ref><box><340><146><998><998></box><|im_end|>", "sec": 4.87, "stats": {"steps": 3, "total_s": 2.2, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "130566": {"text": "<ref>train</ref><box><0><272><911><733></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.2, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "365098": {"text": "<ref>boat</ref><box><74><144><1000><945></box><|im_end|>", "sec": 5.45, "stats": {"steps": 7, "total_s": 2.78, "npu_llm_s": 2.65, "ar_switches": 1, "tokens": 10}}, "253386": {"text": "<ref>person</ref><box><0><0><998><998></box><|im_end|>", "sec": 4.87, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "470779": {"text": "<ref>person</ref><box><88><200><275><812></box><box><231><188><439><815></box><box><359><155><576><778></box><box><510><115><684><770></box><box><611><92><842><755></box><|im_end|>", "sec": 5.71, "stats": {"steps": 7, "total_s": 3.04, "npu_llm_s": 2.8, "ar_switches": 0, "tokens": 34}}, "335328": {"text": "<ref>person</ref><box><108><515><418><667></box><box><664><326><958><511></box><|im_end|>", "sec": 5.08, "stats": {"steps": 4, "total_s": 2.41, "npu_llm_s": 2.26, "ar_switches": 0, "tokens": 16}}, "161397": {"text": "<ref>vase</ref><box><130><552><362><760></box><|im_end|>", "sec": 5.56, "stats": {"steps": 8, "total_s": 2.89, "npu_llm_s": 2.76, "ar_switches": 1, "tokens": 11}}, "433980": {"text": "<ref>cell phone</ref><box><205><562><380><998></box><|im_end|>", "sec": 5.58, "stats": {"steps": 8, "total_s": 2.91, "npu_llm_s": 2.77, "ar_switches": 1, "tokens": 11}}, "80057": {"text": "<ref>teddy bear</ref><box><0><0><881><655></box><|im_end|>", "sec": 4.9, "stats": {"steps": 3, "total_s": 2.23, "npu_llm_s": 2.11, "ar_switches": 0, "tokens": 12}}, "336265": {"text": "<ref>person</ref><box><515><477><569><564></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "133567": {"text": "<ref>train</ref><box><0><201><900><694></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "231549": {"text": "<ref>bed</ref><box><163><0><839><998></box><|im_end|>", "sec": 5.58, "stats": {"steps": 8, "total_s": 2.91, "npu_llm_s": 2.76, "ar_switches": 1, "tokens": 10}}, "502336": {"text": "<ref>person</ref><box><261><684><594><998></box><box><947><617><1000><888></box><|im_end|>", "sec": 5.77, "stats": {"steps": 9, "total_s": 3.1, "npu_llm_s": 2.94, "ar_switches": 1, "tokens": 16}}, "468632": {"text": "<ref>person</ref><box><108><362><250><856></box><box><112><293><612><866></box><box><456><291><637><749></box><box><770><376><912><888></box><|im_end|>", "sec": 5.95, "stats": {"steps": 9, "total_s": 3.28, "npu_llm_s": 3.05, "ar_switches": 1, "tokens": 28}}, "156292": {"text": "<ref>clock</ref><box>None</box><|im_end|>", "sec": 4.86, "stats": {"steps": 3, "total_s": 2.19, "npu_llm_s": 2.08, "ar_switches": 0, "tokens": 7}}, "115885": {"text": "<ref>cat</ref><box><448><405><998><995></box><|im_end|>", "sec": 5.44, "stats": {"steps": 7, "total_s": 2.76, "npu_llm_s": 2.64, "ar_switches": 1, "tokens": 10}}, "581615": {"text": "<ref>toilet</ref><box><304><597><673><998></box><|im_end|>", "sec": 4.89, "stats": {"steps": 3, "total_s": 2.22, "npu_llm_s": 2.1, "ar_switches": 0, "tokens": 11}}, "556873": {"text": "<ref>cake</ref><box><204><497><577><828></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.1, "ar_switches": 0, "tokens": 10}}, "575372": {"text": "<ref>traffic light</ref><box><417><766><480><999></box><box><422><364><471><569></box><box><495><144><700><380></box><box><922><765><1000><999></box><|im_end|>", "sec": 6.53, "stats": {"steps": 13, "total_s": 3.86, "npu_llm_s": 3.61, "ar_switches": 2, "tokens": 29}}, "394328": {"text": "<ref>toilet</ref><box><336><569><748><998></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 11}}, "360943": {"text": "<ref>cat</ref><box><403><359><556><456></box><|im_end|>", "sec": 4.87, "stats": {"steps": 3, "total_s": 2.2, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "287545": {"text": "<ref>giraffe</ref><box><95><234><603><748></box><box><353><479><495><735></box><|im_end|>", "sec": 5.79, "stats": {"steps": 9, "total_s": 3.12, "npu_llm_s": 2.95, "ar_switches": 1, "tokens": 18}}, "194506": {"text": "<ref>bear</ref><box><133><218><471><574></box><box><454><295><627><508></box><|im_end|>", "sec": 5.77, "stats": {"steps": 9, "total_s": 3.1, "npu_llm_s": 2.93, "ar_switches": 1, "tokens": 16}}, "107087": {"text": "<ref>cat</ref><box>None</box><|im_end|>", "sec": 4.85, "stats": {"steps": 3, "total_s": 2.18, "npu_llm_s": 2.08, "ar_switches": 0, "tokens": 7}}, "263474": {"text": "<ref>toilet</ref><box><47><312><806><998></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 11}}, "407518": {"text": "<ref>bird</ref><box><573><197><866><826></box><|im_end|>", "sec": 5.18, "stats": {"steps": 5, "total_s": 2.51, "npu_llm_s": 2.39, "ar_switches": 1, "tokens": 10}}, "31620": {"text": "<ref>person</ref><box><406><357><511><630></box><|im_end|>", "sec": 5.56, "stats": {"steps": 8, "total_s": 2.89, "npu_llm_s": 2.76, "ar_switches": 1, "tokens": 10}}, "398237": {"text": "<ref>kite</ref><box><131><491><408><718></box><box><138><77><366><235></box><box><475><106><612><267></box><box><769><70><842><207></box><|im_end|>", "sec": 6.67, "stats": {"steps": 14, "total_s": 3.99, "npu_llm_s": 3.75, "ar_switches": 2, "tokens": 29}}, "509403": {"text": "<ref>person</ref><box><71><362><135><697></box><box><260><300><339><519></box><box><562><143><757><888></box><|im_end|>", "sec": 5.31, "stats": {"steps": 5, "total_s": 2.63, "npu_llm_s": 2.45, "ar_switches": 0, "tokens": 22}}, "292456": {"text": "<ref>person</ref><box><241><94><375><730></box><box><405><126><598><944></box><box><625><176><892><946></box><|im_end|>", "sec": 5.3, "stats": {"steps": 5, "total_s": 2.63, "npu_llm_s": 2.45, "ar_switches": 0, "tokens": 22}}, "359833": {"text": "<ref>apple</ref><box><0><158><42><201></box><box><0><212><67><266></box><box><0><262><71><315></box><box><0><312><73><375></box><box><0><372><78><435></box><box><0><432><83><505></box><box><0><502><89><562></box><box><0><625><91><708></box><box><0><702><92><818></box><box><0><810><94><909></box><box><2><107><53><153></box><box><5><148><97><207></box><box><7><215><98><267></box><box><8><265><101><318></box><box><10><316><103><370></box><box><12><88><109><150></box><box><15><558><114><638></box><box><19><807><122><909></box><box><23><557><112><639></box><box><25><417><125><481></box><box><29><477><102><532></box><box><31><90><105><148></box><box><33><145><128><203></box><box><35><204><127><262></box><box><37><258><132><317></box><box><38><310><135><373></box><box><40><367><137><422></box><box><44><425><142><478></box><box><47><168><131><216></box><box><50><770><123><839></box><box><52><898><113><969></box><box><57><70><136><124></box><box><59><909><130><982></box><box><62><697><143><152></box><box><65><492><140><561></box><box><69><652><141><715></box><box><72><147><160><205></box><box><77><254><164><319></box><box><79><206><167><263></box><box><81><315><165><368></box><box><85><420><169><420></box><box><87><68><173><119></box><box><89><419><175><482></box><box><93><674><163><743></box><box><95><916><174><974></box><box><96><908><177><972></box><box><99><718><188><791></box><box><100><788><185><863></box><box><104><782><192><853></box><box><106><536><179><621></box><box><108><893><191><959></box><box><110><628><194><694></box><box><111><230><189><286></box><box><115><288><198><322></box><box><117><320><199><369></box><box><120><366><208><423></box><box><126><418><211><480></box><box><129><197><213><250></box><box><133><479><223><540></box><box><134><121><226><172></box><box><138><843><223><915></box><box><139><64><227><118></box><box><144><912><228><966></box><box><146><769><233><836></box><box><151><232><225><290></box><box><154><282><235><325></box><box><156><321><237><365></box>", "sec": 64.61, "stats": {"steps": 222, "total_s": 61.94, "npu_llm_s": 56.79, "ar_switches": 43, "tokens": 405}}, "261982": {"text": "<ref>car</ref><box><0><0><574><358></box><|im_end|>", "sec": 5.31, "stats": {"steps": 6, "total_s": 2.64, "npu_llm_s": 2.51, "ar_switches": 1, "tokens": 10}}, "429761": {"text": "<ref>person</ref><box><304><188><500><924></box><box><452><133><612><856></box><|im_end|>", "sec": 5.09, "stats": {"steps": 4, "total_s": 2.41, "npu_llm_s": 2.26, "ar_switches": 0, "tokens": 16}}, "482719": {"text": "<ref>chair</ref><box>None</box><|im_end|>", "sec": 4.86, "stats": {"steps": 3, "total_s": 2.18, "npu_llm_s": 2.08, "ar_switches": 0, "tokens": 7}}, "506178": {"text": "<ref>person</ref><box><197><188><760><998></box><|im_end|>", "sec": 5.3, "stats": {"steps": 6, "total_s": 2.63, "npu_llm_s": 2.5, "ar_switches": 1, "tokens": 10}}, "131131": {"text": "<ref>tv</ref><box><104><202><887><999></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.1, "ar_switches": 0, "tokens": 10}}, "68286": {"text": "<ref>bed</ref><box><0><149><856><998></box><|im_end|>", "sec": 4.87, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "67896": {"text": "<ref>clock</ref><box><271><140><729><755></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "297830": {"text": "<ref>dog</ref><box><336><88><908><1000></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "398810": {"text": "<ref>cat</ref><box><452><302><998><903></box><|im_end|>", "sec": 5.17, "stats": {"steps": 5, "total_s": 2.5, "npu_llm_s": 2.38, "ar_switches": 1, "tokens": 10}}, "569565": {"text": "<ref>truck</ref><box><188><431><998><732></box><|im_end|>", "sec": 4.89, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.1, "ar_switches": 0, "tokens": 10}}, "161879": {"text": "<ref>person</ref><box><102><0><362><604></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.2, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "333069": {"text": "<ref>giraffe</ref><box><222><304><600><915></box><box><538><300><908><908></box><|im_end|>", "sec": 5.1, "stats": {"steps": 4, "total_s": 2.43, "npu_llm_s": 2.28, "ar_switches": 0, "tokens": 18}}, "544306": {"text": "<ref>clock</ref><box><541><660><616><810></box><box><716><662><819><808></box><|im_end|>", "sec": 5.08, "stats": {"steps": 4, "total_s": 2.41, "npu_llm_s": 2.26, "ar_switches": 0, "tokens": 16}}, "455555": {"text": "<ref>person</ref><box><222><200><673><902></box><box><728><98><960><425></box><|im_end|>", "sec": 5.77, "stats": {"steps": 9, "total_s": 3.1, "npu_llm_s": 2.93, "ar_switches": 1, "tokens": 16}}, "377575": {"text": "<ref>dog</ref><box><128><302><622><958></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.2, "npu_llm_s": 2.09, "ar_switches": 0, "tokens": 10}}, "157213": {"text": "<ref>elephant</ref><box><438><208><607><630></box><|im_end|>", "sec": 4.88, "stats": {"steps": 3, "total_s": 2.21, "npu_llm_s": 2.1, "ar_switches": 0, "tokens": 11}}}