models/newsroom-P75/val_rewards.jsonl

{"step": 50, "score": 0.8283134324539405}
{"step": 100, "score": 0.8283134324539405}
{"step": 150, "score": 0.8382784316335946}
{"step": 200, "score": 0.87565528870887}
{"step": 250, "score": 0.8759554493011963}
{"step": 300, "score": 0.88018633985922}
{"step": 350, "score": 0.8801283947632017}
{"step": 400, "score": 0.8849458603530654}
{"step": 450, "score": 0.8850584373101716}
{"step": 500, "score": 0.8831870640322887}
{"step": 550, "score": 0.8862657924181598}
{"step": 600, "score": 0.8879287907716551}
{"step": 650, "score": 0.888359617718917}
{"step": 700, "score": 0.8888664424223289}
{"step": 750, "score": 0.8898338725541177}
{"step": 800, "score": 0.8875200184893313}
{"step": 850, "score": 0.8896366378368942}
{"step": 900, "score": 0.8911240469264998}
{"step": 950, "score": 0.8897653950733934}
{"step": 1000, "score": 0.8863400219783426}
{"step": 1050, "score": 0.8913232799567093}
{"step": 1100, "score": 0.8923818159475123}
{"step": 1150, "score": 0.8911988577013392}
{"step": 1200, "score": 0.8922601409809152}
{"step": 1250, "score": 0.892835918992339}
{"step": 1300, "score": 0.8928710553981657}
{"step": 1350, "score": 0.8910834246494406}
{"step": 1400, "score": 0.8928367154294015}
{"step": 1450, "score": 0.8936643612112523}
{"step": 1500, "score": 0.8925538295382446}
{"step": 1550, "score": 0.8907871126612066}
{"step": 1600, "score": 0.8938084681401481}
{"step": 1650, "score": 0.8938513909465773}
{"step": 1700, "score": 0.8926017538868303}
{"step": 1750, "score": 0.8938495854727357}
{"step": 1800, "score": 0.8936504092039284}
{"step": 1850, "score": 0.8932358544643292}
{"step": 1900, "score": 0.8938076935134851}
{"step": 1950, "score": 0.8901996262616141}
{"step": 2000, "score": 0.8950877945863592}
{"step": 2050, "score": 0.894534826740838}
{"step": 2100, "score": 0.8949094300290359}
{"step": 2150, "score": 0.8944349145563493}
{"step": 2200, "score": 0.8948373851163405}
{"step": 2250, "score": 0.8954467021087977}
{"step": 2300, "score": 0.8952429024051445}
{"step": 2350, "score": 0.8931451204246652}
{"step": 2400, "score": 0.8952362254950417}
{"step": 2450, "score": 0.8919960072030028}
{"step": 2500, "score": 0.894505425929091}
{"step": 2550, "score": 0.8948650206828472}
{"step": 2600, "score": 0.8953750970790608}
{"step": 2650, "score": 0.8946082905967303}
{"step": 2700, "score": 0.8955443243294067}
{"step": 2750, "score": 0.8961763527651689}
{"step": 2800, "score": 0.8956847622256784}
{"step": 2850, "score": 0.8958943976218279}
{"step": 2900, "score": 0.8960151713907711}
{"step": 2950, "score": 0.896133034880698}
{"step": 3000, "score": 0.8962539427705911}
{"step": 3050, "score": 0.895851308167702}
{"step": 3100, "score": 0.8960345383116355}
{"step": 3150, "score": 0.8968774318696944}
{"step": 3200, "score": 0.8971616206951337}
{"step": 3250, "score": 0.8974804857179277}
{"step": 3300, "score": 0.8972902975478643}
{"step": 3350, "score": 0.8971664476204642}
{"step": 3400, "score": 0.897489686569066}
{"step": 3450, "score": 0.8960264305033274}
{"step": 3500, "score": 0.8970305506286921}
{"step": 3550, "score": 0.8968956637246226}
{"step": 3600, "score": 0.8962759053985496}
{"step": 3650, "score": 0.8976534584058967}
{"step": 3700, "score": 0.8970741065524064}
{"step": 3750, "score": 0.8954944722463356}
{"step": 3800, "score": 0.8976818367803219}
{"step": 3850, "score": 0.8975088559557588}
{"step": 3900, "score": 0.8966912642204689}
{"step": 3950, "score": 0.8979084637940122}
{"step": 4000, "score": 0.8979621588838167}
{"step": 4050, "score": 0.8957953469741269}
{"step": 4100, "score": 0.8940948778368808}
{"step": 4150, "score": 0.8974883052754306}
{"step": 4200, "score": 0.896608589014672}
{"step": 4250, "score": 0.8963754076338519}
{"step": 4300, "score": 0.8967461528919356}
{"step": 4350, "score": 0.8978175126648518}
{"step": 4400, "score": 0.8977756157157618}
{"step": 4450, "score": 0.8978930224660769}
{"step": 4500, "score": 0.8964841876501137}
{"step": 4550, "score": 0.8976494571207743}
{"step": 4600, "score": 0.8982386452742688}
{"step": 4650, "score": 0.8981621592469147}
{"step": 4700, "score": 0.8966905938454153}
{"step": 4750, "score": 0.8961805424777232}
{"step": 4800, "score": 0.8982413707414741}
{"step": 4850, "score": 0.8983790050211959}
{"step": 4900, "score": 0.898052147088658}
{"step": 4950, "score": 0.8980331288774696}
{"step": 5000, "score": 0.8967874651565023}
{"step": 5050, "score": 0.8984159952700528}
{"step": 5100, "score": 0.8979917226167837}
{"step": 5150, "score": 0.8982434393787484}
{"step": 5200, "score": 0.8985472362112594}
{"step": 5250, "score": 0.898036697399726}
{"step": 5300, "score": 0.8986771759530059}
{"step": 5350, "score": 0.8980967657657172}
{"step": 5400, "score": 0.8982609719925583}
{"step": 5450, "score": 0.8980990810313884}
{"step": 5500, "score": 0.8980024331059993}
{"step": 5550, "score": 0.8975074574668149}
{"step": 5600, "score": 0.8976278724530207}
{"step": 5650, "score": 0.8979552165116895}
{"step": 5700, "score": 0.8965482058435477}
{"step": 5750, "score": 0.8983041914599181}
{"step": 5800, "score": 0.898411338221507}
{"step": 5850, "score": 0.8985099769727312}
{"step": 5900, "score": 0.8978187419020109}
{"step": 5950, "score": 0.8980615953149944}
{"step": 6000, "score": 0.8987791453396228}
{"step": 6050, "score": 0.898578445514008}
{"step": 6100, "score": 0.8986196522787988}
{"step": 6150, "score": 0.8983606707590559}
{"step": 6200, "score": 0.898674242146978}
{"step": 6250, "score": 0.8989544126980072}
{"step": 6300, "score": 0.8987810995181524}
{"step": 6350, "score": 0.8985866001937183}
{"step": 6400, "score": 0.89921446637899}
{"step": 6450, "score": 0.8985906831968252}
{"step": 6500, "score": 0.8991285505750218}
{"step": 6550, "score": 0.8992190566260381}
{"step": 6600, "score": 0.8992933196710317}
{"step": 6650, "score": 0.8981656772773653}
{"step": 6700, "score": 0.8987353576250796}
{"step": 6750, "score": 0.8987747222313643}
{"step": 6800, "score": 0.8976966089556089}
{"step": 6850, "score": 0.8994401895882187}
{"step": 6900, "score": 0.8988709432922406}
{"step": 6950, "score": 0.8990617975317781}
{"step": 7000, "score": 0.8994705661693214}
{"step": 7050, "score": 0.8985027944636594}
{"step": 7100, "score": 0.8985308724798717}
{"step": 7150, "score": 0.8988259772729532}
{"step": 7200, "score": 0.8990128182747672}
{"step": 7250, "score": 0.8996996334384681}
{"step": 7300, "score": 0.8953986639970155}
{"step": 7350, "score": 0.8989464273452953}
{"step": 7400, "score": 0.8993826387674158}
{"step": 7450, "score": 0.899516620460908}
{"step": 7500, "score": 0.8992197274592562}
{"step": 7550, "score": 0.90029356483029}
{"step": 7600, "score": 0.8990811506279714}
{"step": 7650, "score": 0.8998325021738898}
{"step": 7700, "score": 0.8990694710615815}
{"step": 7750, "score": 0.9002195224517118}
{"step": 7800, "score": 0.9003446103221169}
{"step": 7850, "score": 0.8998171883385083}
{"step": 7900, "score": 0.8996666834835512}
{"step": 7950, "score": 0.9005801318704207}