models/newsroom-L11/val_rewards.jsonl

{"step": 50, "score": 0.5600825537247436}
{"step": 100, "score": 0.7160333037645308}
{"step": 150, "score": 0.7415132375583778}
{"step": 200, "score": 0.7646486601158993}
{"step": 250, "score": 0.753900180541996}
{"step": 300, "score": 0.7791755375446883}
{"step": 350, "score": 0.7879296430895751}
{"step": 400, "score": 0.7936365759202212}
{"step": 450, "score": 0.8003163527432773}
{"step": 500, "score": 0.804375982907132}
{"step": 550, "score": 0.8025337746540109}
{"step": 600, "score": 0.8066804929458806}
{"step": 650, "score": 0.805683673270486}
{"step": 700, "score": 0.807707975981405}
{"step": 750, "score": 0.8103491635548241}
{"step": 800, "score": 0.7982157335075735}
{"step": 850, "score": 0.8097115077852215}
{"step": 900, "score": 0.808007365388258}
{"step": 950, "score": 0.8026434635530465}
{"step": 1000, "score": 0.8029641750761232}
{"step": 1050, "score": 0.8118594590094432}
{"step": 1100, "score": 0.8138242778808067}
{"step": 1150, "score": 0.8148499201079165}
{"step": 1200, "score": 0.8142244010907924}
{"step": 1250, "score": 0.8079136209212462}
{"step": 1300, "score": 0.8081123889662722}
{"step": 1350, "score": 0.8097404240715987}
{"step": 1400, "score": 0.8145890024949975}
{"step": 1450, "score": 0.8102011363933808}
{"step": 1500, "score": 0.8173217910710835}
{"step": 1550, "score": 0.8091349723793799}
{"step": 1600, "score": 0.8167768314718523}
{"step": 1650, "score": 0.8147662013418006}
{"step": 1700, "score": 0.8064179274670655}
{"step": 1750, "score": 0.804794661384035}
{"step": 1800, "score": 0.8191092348095996}
{"step": 1850, "score": 0.8152777185397143}
{"step": 1900, "score": 0.8183795887279695}
{"step": 1950, "score": 0.8131329272210601}
{"step": 2000, "score": 0.8196157372010608}
{"step": 2050, "score": 0.8130854941887788}
{"step": 2100, "score": 0.8165477217247152}
{"step": 2150, "score": 0.817675173599929}
{"step": 2200, "score": 0.8190740988866444}
{"step": 2250, "score": 0.816429895715111}
{"step": 2300, "score": 0.8196442254729276}
{"step": 2350, "score": 0.8193104055929125}
{"step": 2400, "score": 0.8177349523508064}
{"step": 2450, "score": 0.8151212270862905}
{"step": 2500, "score": 0.817476535215153}
{"step": 2550, "score": 0.8193416028759755}
{"step": 2600, "score": 0.8173432518336962}
{"step": 2650, "score": 0.8036066617135473}
{"step": 2700, "score": 0.8225247464997466}
{"step": 2750, "score": 0.8222590379149861}
{"step": 2800, "score": 0.8184771214188691}
{"step": 2850, "score": 0.8161350837426327}
{"step": 2900, "score": 0.8216721552741456}
{"step": 2950, "score": 0.8151865013636144}
{"step": 3000, "score": 0.8207507259285893}
{"step": 3050, "score": 0.815293519407251}
{"step": 3100, "score": 0.8232930542338762}
{"step": 3150, "score": 0.8194217432080888}
{"step": 3200, "score": 0.8153201703444041}
{"step": 3250, "score": 0.8238689107745046}
{"step": 3300, "score": 0.8224847957480224}
{"step": 3350, "score": 0.8244100896435445}
{"step": 3400, "score": 0.8209398247303468}
{"step": 3450, "score": 0.8181315146503356}
{"step": 3500, "score": 0.8228899565505313}
{"step": 3550, "score": 0.8252197302277502}
{"step": 3600, "score": 0.8209153141605355}
{"step": 3650, "score": 0.8225599482141284}
{"step": 3700, "score": 0.813239540073101}
{"step": 3750, "score": 0.8248502084879364}
{"step": 3800, "score": 0.8252416425026308}
{"step": 3850, "score": 0.8232330066864841}
{"step": 3900, "score": 0.8212150780658433}
{"step": 3950, "score": 0.8154009622474487}
{"step": 4000, "score": 0.8222541059225692}
{"step": 4050, "score": 0.8191898886215535}
{"step": 4100, "score": 0.8272256504887692}
{"step": 4150, "score": 0.821779135287197}
{"step": 4200, "score": 0.8191734289266257}
{"step": 4250, "score": 0.8264217390918509}
{"step": 4300, "score": 0.8253068540299224}
{"step": 4350, "score": 0.8258056905799496}
{"step": 4400, "score": 0.8267062702226036}
{"step": 4450, "score": 0.8221718422953366}
{"step": 4500, "score": 0.8199994246451825}
{"step": 4550, "score": 0.8252450230587468}
{"step": 4600, "score": 0.822553507120066}
{"step": 4650, "score": 0.8249520931079006}
{"step": 4700, "score": 0.825128961893334}
{"step": 4750, "score": 0.8256260303864421}
{"step": 4800, "score": 0.8261325005092448}
{"step": 4850, "score": 0.8158265058489559}
{"step": 4900, "score": 0.8171151723445829}
{"step": 4950, "score": 0.8258768473629783}
{"step": 5000, "score": 0.824699477859566}
{"step": 5050, "score": 0.8253544677904988}
{"step": 5100, "score": 0.820042407440226}
{"step": 5150, "score": 0.8081891943156574}
{"step": 5200, "score": 0.8234324940840629}
{"step": 5250, "score": 0.8118778653620797}
{"step": 5300, "score": 0.8272362747701436}
{"step": 5350, "score": 0.8251873152553797}
{"step": 5400, "score": 0.8253175497819278}
{"step": 5450, "score": 0.82605107306342}
{"step": 5500, "score": 0.8259306959064308}
{"step": 5550, "score": 0.819401486265195}
{"step": 5600, "score": 0.8251817120269181}
{"step": 5650, "score": 0.8208030616651669}
{"step": 5700, "score": 0.8273435408557301}
{"step": 5750, "score": 0.8265721831217137}
{"step": 5800, "score": 0.8273738417262451}
{"step": 5850, "score": 0.8262777195742375}
{"step": 5900, "score": 0.8275267812896142}
{"step": 5950, "score": 0.8250092958780442}
{"step": 6000, "score": 0.8236398771619894}
{"step": 6050, "score": 0.8189616796490211}
{"step": 6100, "score": 0.8291110371211359}
{"step": 6150, "score": 0.8246026362668826}
{"step": 6200, "score": 0.8282749709853853}
{"step": 6250, "score": 0.8221707238114202}
{"step": 6300, "score": 0.8284406104377899}
{"step": 6350, "score": 0.8257812249898718}
{"step": 6400, "score": 0.8244889615047732}
{"step": 6450, "score": 0.8304522660275484}
{"step": 6500, "score": 0.8248220896663072}
{"step": 6550, "score": 0.8258681035105279}
{"step": 6600, "score": 0.8302872372845407}
{"step": 6650, "score": 0.8309077843341448}
{"step": 6700, "score": 0.8235504436952438}
{"step": 6750, "score": 0.8275492194486169}
{"step": 6800, "score": 0.8278539035689911}
{"step": 6850, "score": 0.8259349880581295}
{"step": 6900, "score": 0.8303410865353742}
{"step": 6950, "score": 0.8250796277894957}
{"step": 7000, "score": 0.8241616628070323}
{"step": 7050, "score": 0.8295237556149039}
{"step": 7100, "score": 0.8289991435732607}
{"step": 7150, "score": 0.8303492325152942}
{"step": 7200, "score": 0.8311947318957487}
{"step": 7250, "score": 0.83039924315249}
{"step": 7300, "score": 0.823568445961413}
{"step": 7350, "score": 0.818761908686793}
{"step": 7400, "score": 0.8175686957742276}
{"step": 7450, "score": 0.8289748945181594}
{"step": 7500, "score": 0.8300976503382151}
{"step": 7550, "score": 0.8306490058416762}
{"step": 7600, "score": 0.8303127238271015}
{"step": 7650, "score": 0.8282718031405167}
{"step": 7700, "score": 0.8313761266283056}
{"step": 7750, "score": 0.8279773508497827}
{"step": 7800, "score": 0.8129895598051526}
{"step": 7850, "score": 0.823979547657415}
{"step": 7900, "score": 0.828088323472961}
{"step": 7950, "score": 0.8322161999199741}