| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 98, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "completion_length": 160.0, |
| "epoch": 0.01020408163265306, |
| "grad_norm": 0.16015149652957916, |
| "kl": 0.0, |
| "learning_rate": 1.0000000000000002e-06, |
| "loss": 0.0, |
| "reward": 0.13549137115478516, |
| "reward_std": 0.122966468334198, |
| "rewards/<lambda>": 0.13549137115478516, |
| "step": 1 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.02040816326530612, |
| "grad_norm": 0.1122620478272438, |
| "kl": 0.0, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 0.0, |
| "reward": 0.1350748986005783, |
| "reward_std": 0.13239088654518127, |
| "rewards/<lambda>": 0.1350748986005783, |
| "step": 2 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.030612244897959183, |
| "grad_norm": 0.10055773705244064, |
| "kl": 0.0009823411237448454, |
| "learning_rate": 3e-06, |
| "loss": 0.0, |
| "reward": 0.11044053733348846, |
| "reward_std": 0.09149592369794846, |
| "rewards/<lambda>": 0.11044053733348846, |
| "step": 3 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.04081632653061224, |
| "grad_norm": 0.1106867864727974, |
| "kl": 0.0011138569097965956, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.0, |
| "reward": 0.14424282312393188, |
| "reward_std": 0.08860041201114655, |
| "rewards/<lambda>": 0.14424282312393188, |
| "step": 4 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.05102040816326531, |
| "grad_norm": 0.10906749963760376, |
| "kl": 0.0009323786944150925, |
| "learning_rate": 5e-06, |
| "loss": 0.0, |
| "reward": 0.15370804071426392, |
| "reward_std": 0.12023884057998657, |
| "rewards/<lambda>": 0.15370804071426392, |
| "step": 5 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.061224489795918366, |
| "grad_norm": 0.0973278358578682, |
| "kl": 0.000986273866146803, |
| "learning_rate": 6e-06, |
| "loss": 0.0, |
| "reward": 0.16775861382484436, |
| "reward_std": 0.11324145644903183, |
| "rewards/<lambda>": 0.16775861382484436, |
| "step": 6 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.07142857142857142, |
| "grad_norm": 0.11650331318378448, |
| "kl": 0.0009559993632137775, |
| "learning_rate": 7.000000000000001e-06, |
| "loss": 0.0, |
| "reward": 0.12161540985107422, |
| "reward_std": 0.09721754491329193, |
| "rewards/<lambda>": 0.12161540985107422, |
| "step": 7 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.08163265306122448, |
| "grad_norm": 0.14426998794078827, |
| "kl": 0.001172696123830974, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.0, |
| "reward": 0.10382680594921112, |
| "reward_std": 0.08653440326452255, |
| "rewards/<lambda>": 0.10382680594921112, |
| "step": 8 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.09183673469387756, |
| "grad_norm": 0.09224210679531097, |
| "kl": 0.0009267181158065796, |
| "learning_rate": 9e-06, |
| "loss": 0.0, |
| "reward": 0.15248040854930878, |
| "reward_std": 0.10083242505788803, |
| "rewards/<lambda>": 0.15248040854930878, |
| "step": 9 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.10204081632653061, |
| "grad_norm": 0.10662151873111725, |
| "kl": 0.001049146056175232, |
| "learning_rate": 1e-05, |
| "loss": 0.0, |
| "reward": 0.10904872417449951, |
| "reward_std": 0.07905881851911545, |
| "rewards/<lambda>": 0.10904872417449951, |
| "step": 10 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.11224489795918367, |
| "grad_norm": 0.08880773186683655, |
| "kl": 0.0009575427393428981, |
| "learning_rate": 1.1000000000000001e-05, |
| "loss": 0.0, |
| "reward": 0.1023264229297638, |
| "reward_std": 0.09154930710792542, |
| "rewards/<lambda>": 0.1023264229297638, |
| "step": 11 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.12244897959183673, |
| "grad_norm": 0.1399761289358139, |
| "kl": 0.0010016188025474548, |
| "learning_rate": 1.2e-05, |
| "loss": 0.0, |
| "reward": 0.12774227559566498, |
| "reward_std": 0.10531343519687653, |
| "rewards/<lambda>": 0.12774227559566498, |
| "step": 12 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.1326530612244898, |
| "grad_norm": 0.10604196786880493, |
| "kl": 0.0010334912221878767, |
| "learning_rate": 1.3000000000000001e-05, |
| "loss": 0.0, |
| "reward": 0.13598087430000305, |
| "reward_std": 0.12228463590145111, |
| "rewards/<lambda>": 0.13598087430000305, |
| "step": 13 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.14285714285714285, |
| "grad_norm": 0.1302865892648697, |
| "kl": 0.0010531357256695628, |
| "learning_rate": 1.4000000000000001e-05, |
| "loss": 0.0, |
| "reward": 0.09349755942821503, |
| "reward_std": 0.07072040438652039, |
| "rewards/<lambda>": 0.09349755942821503, |
| "step": 14 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.15306122448979592, |
| "grad_norm": 0.12415535002946854, |
| "kl": 0.0009964585769921541, |
| "learning_rate": 1.5e-05, |
| "loss": 0.0, |
| "reward": 0.11064597219228745, |
| "reward_std": 0.08005572855472565, |
| "rewards/<lambda>": 0.11064597219228745, |
| "step": 15 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.16326530612244897, |
| "grad_norm": 0.11816220730543137, |
| "kl": 0.0009764357237145305, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 0.0, |
| "reward": 0.1383560299873352, |
| "reward_std": 0.09371937811374664, |
| "rewards/<lambda>": 0.1383560299873352, |
| "step": 16 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.17346938775510204, |
| "grad_norm": 0.10982600599527359, |
| "kl": 0.0009334891801699996, |
| "learning_rate": 1.7000000000000003e-05, |
| "loss": 0.0, |
| "reward": 0.12855608761310577, |
| "reward_std": 0.11154236644506454, |
| "rewards/<lambda>": 0.12855608761310577, |
| "step": 17 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.1836734693877551, |
| "grad_norm": 0.09776873886585236, |
| "kl": 0.0008928977185860276, |
| "learning_rate": 1.8e-05, |
| "loss": 0.0, |
| "reward": 0.15613257884979248, |
| "reward_std": 0.13504436612129211, |
| "rewards/<lambda>": 0.15613257884979248, |
| "step": 18 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.19387755102040816, |
| "grad_norm": 0.12221962213516235, |
| "kl": 0.0010021468624472618, |
| "learning_rate": 1.9e-05, |
| "loss": 0.0, |
| "reward": 0.15936216711997986, |
| "reward_std": 0.09952296316623688, |
| "rewards/<lambda>": 0.15936216711997986, |
| "step": 19 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.20408163265306123, |
| "grad_norm": 0.09339983761310577, |
| "kl": 0.0011222452158108354, |
| "learning_rate": 2e-05, |
| "loss": 0.0, |
| "reward": 0.09720780700445175, |
| "reward_std": 0.08142109215259552, |
| "rewards/<lambda>": 0.09720780700445175, |
| "step": 20 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.21428571428571427, |
| "grad_norm": 0.11736761033535004, |
| "kl": 0.0011920102406293154, |
| "learning_rate": 2.1e-05, |
| "loss": 0.0, |
| "reward": 0.15125760436058044, |
| "reward_std": 0.10276186466217041, |
| "rewards/<lambda>": 0.15125760436058044, |
| "step": 21 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.22448979591836735, |
| "grad_norm": 0.13611504435539246, |
| "kl": 0.00114919594489038, |
| "learning_rate": 2.2000000000000003e-05, |
| "loss": 0.0, |
| "reward": 0.1826939433813095, |
| "reward_std": 0.12737450003623962, |
| "rewards/<lambda>": 0.1826939433813095, |
| "step": 22 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.23469387755102042, |
| "grad_norm": 0.12078937888145447, |
| "kl": 0.001010789768770337, |
| "learning_rate": 2.3000000000000003e-05, |
| "loss": 0.0, |
| "reward": 0.15208037197589874, |
| "reward_std": 0.13148412108421326, |
| "rewards/<lambda>": 0.15208037197589874, |
| "step": 23 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.24489795918367346, |
| "grad_norm": 0.14114625751972198, |
| "kl": 0.0011141165159642696, |
| "learning_rate": 2.4e-05, |
| "loss": 0.0, |
| "reward": 0.13319575786590576, |
| "reward_std": 0.10379491746425629, |
| "rewards/<lambda>": 0.13319575786590576, |
| "step": 24 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.25510204081632654, |
| "grad_norm": 0.08827733993530273, |
| "kl": 0.0010151572059839964, |
| "learning_rate": 2.5e-05, |
| "loss": 0.0, |
| "reward": 0.1206921935081482, |
| "reward_std": 0.11820320785045624, |
| "rewards/<lambda>": 0.1206921935081482, |
| "step": 25 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.2653061224489796, |
| "grad_norm": 0.10461141169071198, |
| "kl": 0.0010629891185089946, |
| "learning_rate": 2.6000000000000002e-05, |
| "loss": 0.0, |
| "reward": 0.12660565972328186, |
| "reward_std": 0.09369075298309326, |
| "rewards/<lambda>": 0.12660565972328186, |
| "step": 26 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.2755102040816326, |
| "grad_norm": 0.12817198038101196, |
| "kl": 0.0014134375378489494, |
| "learning_rate": 2.7000000000000002e-05, |
| "loss": 0.0001, |
| "reward": 0.15190695226192474, |
| "reward_std": 0.1361895054578781, |
| "rewards/<lambda>": 0.15190695226192474, |
| "step": 27 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.2857142857142857, |
| "grad_norm": 0.14398054778575897, |
| "kl": 0.0014005769044160843, |
| "learning_rate": 2.8000000000000003e-05, |
| "loss": 0.0001, |
| "reward": 0.11002078652381897, |
| "reward_std": 0.08406772464513779, |
| "rewards/<lambda>": 0.11002078652381897, |
| "step": 28 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.29591836734693877, |
| "grad_norm": 0.12125135213136673, |
| "kl": 0.001406812109053135, |
| "learning_rate": 2.9e-05, |
| "loss": 0.0001, |
| "reward": 0.1488090455532074, |
| "reward_std": 0.09648909419775009, |
| "rewards/<lambda>": 0.1488090455532074, |
| "step": 29 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.30612244897959184, |
| "grad_norm": 0.1116093099117279, |
| "kl": 0.001532193971797824, |
| "learning_rate": 3e-05, |
| "loss": 0.0001, |
| "reward": 0.1401943415403366, |
| "reward_std": 0.10262932628393173, |
| "rewards/<lambda>": 0.1401943415403366, |
| "step": 30 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.3163265306122449, |
| "grad_norm": 0.11590556800365448, |
| "kl": 0.0013668447500094771, |
| "learning_rate": 3.1e-05, |
| "loss": 0.0001, |
| "reward": 0.15992209315299988, |
| "reward_std": 0.13228771090507507, |
| "rewards/<lambda>": 0.15992209315299988, |
| "step": 31 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.32653061224489793, |
| "grad_norm": 0.22361916303634644, |
| "kl": 0.0015757133951410651, |
| "learning_rate": 3.2000000000000005e-05, |
| "loss": 0.0001, |
| "reward": 0.14634232223033905, |
| "reward_std": 0.0937654972076416, |
| "rewards/<lambda>": 0.14634232223033905, |
| "step": 32 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.336734693877551, |
| "grad_norm": 0.11585766822099686, |
| "kl": 0.0013871926348656416, |
| "learning_rate": 3.3e-05, |
| "loss": 0.0001, |
| "reward": 0.1371658891439438, |
| "reward_std": 0.0987061858177185, |
| "rewards/<lambda>": 0.1371658891439438, |
| "step": 33 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.3469387755102041, |
| "grad_norm": 0.12178175151348114, |
| "kl": 0.00142570654861629, |
| "learning_rate": 3.4000000000000007e-05, |
| "loss": 0.0001, |
| "reward": 0.12351685017347336, |
| "reward_std": 0.11602398008108139, |
| "rewards/<lambda>": 0.12351685017347336, |
| "step": 34 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.35714285714285715, |
| "grad_norm": 0.0959494486451149, |
| "kl": 0.0016183136031031609, |
| "learning_rate": 3.5e-05, |
| "loss": 0.0001, |
| "reward": 0.08838998526334763, |
| "reward_std": 0.08110953867435455, |
| "rewards/<lambda>": 0.08838998526334763, |
| "step": 35 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.3673469387755102, |
| "grad_norm": 0.10338612645864487, |
| "kl": 0.0017382192891091108, |
| "learning_rate": 3.6e-05, |
| "loss": 0.0001, |
| "reward": 0.16435359418392181, |
| "reward_std": 0.13644874095916748, |
| "rewards/<lambda>": 0.16435359418392181, |
| "step": 36 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.37755102040816324, |
| "grad_norm": 0.08886157721281052, |
| "kl": 0.00104477908462286, |
| "learning_rate": 3.7e-05, |
| "loss": 0.0, |
| "reward": 0.12062600255012512, |
| "reward_std": 0.10176925361156464, |
| "rewards/<lambda>": 0.12062600255012512, |
| "step": 37 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.3877551020408163, |
| "grad_norm": 0.16644084453582764, |
| "kl": 0.001502887113019824, |
| "learning_rate": 3.8e-05, |
| "loss": 0.0001, |
| "reward": 0.12538418173789978, |
| "reward_std": 0.11342241615056992, |
| "rewards/<lambda>": 0.12538418173789978, |
| "step": 38 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.3979591836734694, |
| "grad_norm": 0.10507523268461227, |
| "kl": 0.0016810973174870014, |
| "learning_rate": 3.9000000000000006e-05, |
| "loss": 0.0001, |
| "reward": 0.1384812593460083, |
| "reward_std": 0.10060354322195053, |
| "rewards/<lambda>": 0.1384812593460083, |
| "step": 39 |
| }, |
| { |
| "completion_length": 156.89584350585938, |
| "epoch": 0.40816326530612246, |
| "grad_norm": 0.13816726207733154, |
| "kl": 0.002180024515837431, |
| "learning_rate": 4e-05, |
| "loss": 0.0001, |
| "reward": 0.1627415418624878, |
| "reward_std": 0.09559802711009979, |
| "rewards/<lambda>": 0.1627415418624878, |
| "step": 40 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.41836734693877553, |
| "grad_norm": 0.09595762193202972, |
| "kl": 0.001595992362126708, |
| "learning_rate": 4.1e-05, |
| "loss": 0.0001, |
| "reward": 0.1617720127105713, |
| "reward_std": 0.09887909144163132, |
| "rewards/<lambda>": 0.1617720127105713, |
| "step": 41 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.42857142857142855, |
| "grad_norm": 0.19110041856765747, |
| "kl": 0.002547662705183029, |
| "learning_rate": 4.2e-05, |
| "loss": 0.0001, |
| "reward": 0.19862735271453857, |
| "reward_std": 0.11392591893672943, |
| "rewards/<lambda>": 0.19862735271453857, |
| "step": 42 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.4387755102040816, |
| "grad_norm": 0.09072164446115494, |
| "kl": 0.0016248103929683566, |
| "learning_rate": 4.3e-05, |
| "loss": 0.0001, |
| "reward": 0.13210207223892212, |
| "reward_std": 0.09667991101741791, |
| "rewards/<lambda>": 0.13210207223892212, |
| "step": 43 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.4489795918367347, |
| "grad_norm": 0.10356740653514862, |
| "kl": 0.002113830065354705, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.0001, |
| "reward": 0.14277184009552002, |
| "reward_std": 0.09977956861257553, |
| "rewards/<lambda>": 0.14277184009552002, |
| "step": 44 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.45918367346938777, |
| "grad_norm": 0.1663713902235031, |
| "kl": 0.0063522434793412685, |
| "learning_rate": 4.5e-05, |
| "loss": 0.0003, |
| "reward": 0.16242042183876038, |
| "reward_std": 0.12298040091991425, |
| "rewards/<lambda>": 0.16242042183876038, |
| "step": 45 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.46938775510204084, |
| "grad_norm": 0.11778972297906876, |
| "kl": 0.0025551035068929195, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.0001, |
| "reward": 0.12898343801498413, |
| "reward_std": 0.09911265969276428, |
| "rewards/<lambda>": 0.12898343801498413, |
| "step": 46 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.47959183673469385, |
| "grad_norm": 0.13733811676502228, |
| "kl": 0.004000469576567411, |
| "learning_rate": 4.7e-05, |
| "loss": 0.0002, |
| "reward": 0.18428276479244232, |
| "reward_std": 0.1296135038137436, |
| "rewards/<lambda>": 0.18428276479244232, |
| "step": 47 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.4897959183673469, |
| "grad_norm": 0.10343091934919357, |
| "kl": 0.0036480827257037163, |
| "learning_rate": 4.8e-05, |
| "loss": 0.0001, |
| "reward": 0.1390620619058609, |
| "reward_std": 0.10592266172170639, |
| "rewards/<lambda>": 0.1390620619058609, |
| "step": 48 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.5, |
| "grad_norm": 0.1648188680410385, |
| "kl": 0.003458770690485835, |
| "learning_rate": 4.9e-05, |
| "loss": 0.0001, |
| "reward": 0.16380682587623596, |
| "reward_std": 0.10548572242259979, |
| "rewards/<lambda>": 0.16380682587623596, |
| "step": 49 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.5102040816326531, |
| "grad_norm": 0.0953877791762352, |
| "kl": 0.002513691782951355, |
| "learning_rate": 5e-05, |
| "loss": 0.0001, |
| "reward": 0.14581327140331268, |
| "reward_std": 0.12193475663661957, |
| "rewards/<lambda>": 0.14581327140331268, |
| "step": 50 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.5204081632653061, |
| "grad_norm": 0.14063876867294312, |
| "kl": 0.004633021075278521, |
| "learning_rate": 5.1000000000000006e-05, |
| "loss": 0.0002, |
| "reward": 0.20702508091926575, |
| "reward_std": 0.13710586726665497, |
| "rewards/<lambda>": 0.20702508091926575, |
| "step": 51 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.5306122448979592, |
| "grad_norm": 0.1019497662782669, |
| "kl": 0.0037124312948435545, |
| "learning_rate": 5.2000000000000004e-05, |
| "loss": 0.0001, |
| "reward": 0.13214847445487976, |
| "reward_std": 0.09029597043991089, |
| "rewards/<lambda>": 0.13214847445487976, |
| "step": 52 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.5408163265306123, |
| "grad_norm": 0.12852047383785248, |
| "kl": 0.004707551561295986, |
| "learning_rate": 5.300000000000001e-05, |
| "loss": 0.0002, |
| "reward": 0.1572979986667633, |
| "reward_std": 0.11500580608844757, |
| "rewards/<lambda>": 0.1572979986667633, |
| "step": 53 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.5510204081632653, |
| "grad_norm": 0.1126970499753952, |
| "kl": 0.0029443646781146526, |
| "learning_rate": 5.4000000000000005e-05, |
| "loss": 0.0001, |
| "reward": 0.11422993242740631, |
| "reward_std": 0.1095927357673645, |
| "rewards/<lambda>": 0.11422993242740631, |
| "step": 54 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.5612244897959183, |
| "grad_norm": 0.1265789270401001, |
| "kl": 0.004524104297161102, |
| "learning_rate": 5.500000000000001e-05, |
| "loss": 0.0002, |
| "reward": 0.1222875714302063, |
| "reward_std": 0.0923609733581543, |
| "rewards/<lambda>": 0.1222875714302063, |
| "step": 55 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.5714285714285714, |
| "grad_norm": 0.12009646743535995, |
| "kl": 0.0038815774023532867, |
| "learning_rate": 5.6000000000000006e-05, |
| "loss": 0.0002, |
| "reward": 0.1649770438671112, |
| "reward_std": 0.10861348360776901, |
| "rewards/<lambda>": 0.1649770438671112, |
| "step": 56 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.5816326530612245, |
| "grad_norm": 0.1011093482375145, |
| "kl": 0.0032921030651777983, |
| "learning_rate": 5.6999999999999996e-05, |
| "loss": 0.0001, |
| "reward": 0.17336896061897278, |
| "reward_std": 0.12328130006790161, |
| "rewards/<lambda>": 0.17336896061897278, |
| "step": 57 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.5918367346938775, |
| "grad_norm": 0.10525462031364441, |
| "kl": 0.004167443141341209, |
| "learning_rate": 5.8e-05, |
| "loss": 0.0002, |
| "reward": 0.1390347182750702, |
| "reward_std": 0.11740852892398834, |
| "rewards/<lambda>": 0.1390347182750702, |
| "step": 58 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.6020408163265306, |
| "grad_norm": 0.3547665774822235, |
| "kl": 0.00994147639721632, |
| "learning_rate": 5.9e-05, |
| "loss": 0.0004, |
| "reward": 0.1372447907924652, |
| "reward_std": 0.08885445445775986, |
| "rewards/<lambda>": 0.1372447907924652, |
| "step": 59 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.6122448979591837, |
| "grad_norm": 0.14041198790073395, |
| "kl": 0.005412312224507332, |
| "learning_rate": 6e-05, |
| "loss": 0.0002, |
| "reward": 0.14578765630722046, |
| "reward_std": 0.095134437084198, |
| "rewards/<lambda>": 0.14578765630722046, |
| "step": 60 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.6224489795918368, |
| "grad_norm": 0.13052710890769958, |
| "kl": 0.004689443856477737, |
| "learning_rate": 6.1e-05, |
| "loss": 0.0002, |
| "reward": 0.09727954864501953, |
| "reward_std": 0.06896870583295822, |
| "rewards/<lambda>": 0.09727954864501953, |
| "step": 61 |
| }, |
| { |
| "completion_length": 157.1875, |
| "epoch": 0.6326530612244898, |
| "grad_norm": 0.1129918321967125, |
| "kl": 0.004512472078204155, |
| "learning_rate": 6.2e-05, |
| "loss": 0.0002, |
| "reward": 0.17984223365783691, |
| "reward_std": 0.09912577271461487, |
| "rewards/<lambda>": 0.17984223365783691, |
| "step": 62 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.6428571428571429, |
| "grad_norm": 0.11350245773792267, |
| "kl": 0.005884611513465643, |
| "learning_rate": 6.3e-05, |
| "loss": 0.0002, |
| "reward": 0.13487395644187927, |
| "reward_std": 0.09702014178037643, |
| "rewards/<lambda>": 0.13487395644187927, |
| "step": 63 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.6530612244897959, |
| "grad_norm": 0.1478883922100067, |
| "kl": 0.0060376739129424095, |
| "learning_rate": 6.400000000000001e-05, |
| "loss": 0.0002, |
| "reward": 0.13012471795082092, |
| "reward_std": 0.09517987817525864, |
| "rewards/<lambda>": 0.13012471795082092, |
| "step": 64 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.6632653061224489, |
| "grad_norm": 0.09250291436910629, |
| "kl": 0.005326719488948584, |
| "learning_rate": 6.500000000000001e-05, |
| "loss": 0.0002, |
| "reward": 0.17718777060508728, |
| "reward_std": 0.11379577964544296, |
| "rewards/<lambda>": 0.17718777060508728, |
| "step": 65 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.673469387755102, |
| "grad_norm": 0.18939143419265747, |
| "kl": 0.0049583157524466515, |
| "learning_rate": 6.6e-05, |
| "loss": 0.0002, |
| "reward": 0.14007148146629333, |
| "reward_std": 0.09873458743095398, |
| "rewards/<lambda>": 0.14007148146629333, |
| "step": 66 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.6836734693877551, |
| "grad_norm": 0.09305741637945175, |
| "kl": 0.00586826354265213, |
| "learning_rate": 6.7e-05, |
| "loss": 0.0002, |
| "reward": 0.10462306439876556, |
| "reward_std": 0.09117605537176132, |
| "rewards/<lambda>": 0.10462306439876556, |
| "step": 67 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.6938775510204082, |
| "grad_norm": 0.14123046398162842, |
| "kl": 0.006275478284806013, |
| "learning_rate": 6.800000000000001e-05, |
| "loss": 0.0003, |
| "reward": 0.16492299735546112, |
| "reward_std": 0.1278476119041443, |
| "rewards/<lambda>": 0.16492299735546112, |
| "step": 68 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.7040816326530612, |
| "grad_norm": 0.10926412045955658, |
| "kl": 0.005929266568273306, |
| "learning_rate": 6.9e-05, |
| "loss": 0.0002, |
| "reward": 0.1173870787024498, |
| "reward_std": 0.09027393907308578, |
| "rewards/<lambda>": 0.1173870787024498, |
| "step": 69 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.7142857142857143, |
| "grad_norm": 0.11727511882781982, |
| "kl": 0.007982933893799782, |
| "learning_rate": 7e-05, |
| "loss": 0.0003, |
| "reward": 0.1433873325586319, |
| "reward_std": 0.09991258382797241, |
| "rewards/<lambda>": 0.1433873325586319, |
| "step": 70 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.7244897959183674, |
| "grad_norm": 0.09994583576917648, |
| "kl": 0.008151376619935036, |
| "learning_rate": 7.1e-05, |
| "loss": 0.0003, |
| "reward": 0.17650912702083588, |
| "reward_std": 0.1265939176082611, |
| "rewards/<lambda>": 0.17650912702083588, |
| "step": 71 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.7346938775510204, |
| "grad_norm": 0.11233754456043243, |
| "kl": 0.008668525144457817, |
| "learning_rate": 7.2e-05, |
| "loss": 0.0003, |
| "reward": 0.1490788459777832, |
| "reward_std": 0.10998384654521942, |
| "rewards/<lambda>": 0.1490788459777832, |
| "step": 72 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.7448979591836735, |
| "grad_norm": 0.15177902579307556, |
| "kl": 0.008991223759949207, |
| "learning_rate": 7.3e-05, |
| "loss": 0.0004, |
| "reward": 0.1158258318901062, |
| "reward_std": 0.09271200001239777, |
| "rewards/<lambda>": 0.1158258318901062, |
| "step": 73 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.7551020408163265, |
| "grad_norm": 0.12361659109592438, |
| "kl": 0.009935474023222923, |
| "learning_rate": 7.4e-05, |
| "loss": 0.0004, |
| "reward": 0.16675977408885956, |
| "reward_std": 0.11429008096456528, |
| "rewards/<lambda>": 0.16675977408885956, |
| "step": 74 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.7653061224489796, |
| "grad_norm": 0.10791321843862534, |
| "kl": 0.01029084250330925, |
| "learning_rate": 7.500000000000001e-05, |
| "loss": 0.0004, |
| "reward": 0.1560361236333847, |
| "reward_std": 0.12631307542324066, |
| "rewards/<lambda>": 0.1560361236333847, |
| "step": 75 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.7755102040816326, |
| "grad_norm": 0.11729063093662262, |
| "kl": 0.013020636513829231, |
| "learning_rate": 7.6e-05, |
| "loss": 0.0005, |
| "reward": 0.13625627756118774, |
| "reward_std": 0.09627413749694824, |
| "rewards/<lambda>": 0.13625627756118774, |
| "step": 76 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.7857142857142857, |
| "grad_norm": 0.14529183506965637, |
| "kl": 0.016384603455662727, |
| "learning_rate": 7.7e-05, |
| "loss": 0.0007, |
| "reward": 0.1917780488729477, |
| "reward_std": 0.10966574400663376, |
| "rewards/<lambda>": 0.1917780488729477, |
| "step": 77 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.7959183673469388, |
| "grad_norm": 0.11583904176950455, |
| "kl": 0.016116080805659294, |
| "learning_rate": 7.800000000000001e-05, |
| "loss": 0.0006, |
| "reward": 0.1915496587753296, |
| "reward_std": 0.12190195918083191, |
| "rewards/<lambda>": 0.1915496587753296, |
| "step": 78 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.8061224489795918, |
| "grad_norm": 0.10830377042293549, |
| "kl": 0.015441562049090862, |
| "learning_rate": 7.900000000000001e-05, |
| "loss": 0.0006, |
| "reward": 0.15522490441799164, |
| "reward_std": 0.08264317363500595, |
| "rewards/<lambda>": 0.15522490441799164, |
| "step": 79 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.8163265306122449, |
| "grad_norm": 0.11148685216903687, |
| "kl": 0.01857638917863369, |
| "learning_rate": 8e-05, |
| "loss": 0.0007, |
| "reward": 0.21693138778209686, |
| "reward_std": 0.132161483168602, |
| "rewards/<lambda>": 0.21693138778209686, |
| "step": 80 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.826530612244898, |
| "grad_norm": 0.1557169258594513, |
| "kl": 0.01583457738161087, |
| "learning_rate": 8.1e-05, |
| "loss": 0.0006, |
| "reward": 0.1813575029373169, |
| "reward_std": 0.12332402914762497, |
| "rewards/<lambda>": 0.1813575029373169, |
| "step": 81 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.8367346938775511, |
| "grad_norm": 0.11910691857337952, |
| "kl": 0.025130536407232285, |
| "learning_rate": 8.2e-05, |
| "loss": 0.001, |
| "reward": 0.1874808669090271, |
| "reward_std": 0.13184116780757904, |
| "rewards/<lambda>": 0.1874808669090271, |
| "step": 82 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.8469387755102041, |
| "grad_norm": 0.09641101211309433, |
| "kl": 0.020103760063648224, |
| "learning_rate": 8.3e-05, |
| "loss": 0.0008, |
| "reward": 0.16875742375850677, |
| "reward_std": 0.12786784768104553, |
| "rewards/<lambda>": 0.16875742375850677, |
| "step": 83 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.8571428571428571, |
| "grad_norm": 0.11505434662103653, |
| "kl": 0.03201855719089508, |
| "learning_rate": 8.4e-05, |
| "loss": 0.0013, |
| "reward": 0.1941194385290146, |
| "reward_std": 0.1352878361940384, |
| "rewards/<lambda>": 0.1941194385290146, |
| "step": 84 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.8673469387755102, |
| "grad_norm": 0.20420552790164948, |
| "kl": 0.025220511481165886, |
| "learning_rate": 8.5e-05, |
| "loss": 0.001, |
| "reward": 0.1499064564704895, |
| "reward_std": 0.10931651294231415, |
| "rewards/<lambda>": 0.1499064564704895, |
| "step": 85 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.8775510204081632, |
| "grad_norm": 0.1504613608121872, |
| "kl": 0.030149614438414574, |
| "learning_rate": 8.6e-05, |
| "loss": 0.0012, |
| "reward": 0.2021590918302536, |
| "reward_std": 0.11808289587497711, |
| "rewards/<lambda>": 0.2021590918302536, |
| "step": 86 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.8877551020408163, |
| "grad_norm": 0.12947432696819305, |
| "kl": 0.03943827003240585, |
| "learning_rate": 8.7e-05, |
| "loss": 0.0016, |
| "reward": 0.16302035748958588, |
| "reward_std": 0.12248598039150238, |
| "rewards/<lambda>": 0.16302035748958588, |
| "step": 87 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.8979591836734694, |
| "grad_norm": 0.10003241151571274, |
| "kl": 0.031025437638163567, |
| "learning_rate": 8.800000000000001e-05, |
| "loss": 0.0012, |
| "reward": 0.17104387283325195, |
| "reward_std": 0.11305706948041916, |
| "rewards/<lambda>": 0.17104387283325195, |
| "step": 88 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.9081632653061225, |
| "grad_norm": 0.178684264421463, |
| "kl": 0.0443422794342041, |
| "learning_rate": 8.900000000000001e-05, |
| "loss": 0.0018, |
| "reward": 0.21491599082946777, |
| "reward_std": 0.11920367181301117, |
| "rewards/<lambda>": 0.21491599082946777, |
| "step": 89 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.9183673469387755, |
| "grad_norm": 0.4619559347629547, |
| "kl": 0.14378872513771057, |
| "learning_rate": 9e-05, |
| "loss": 0.0058, |
| "reward": 0.170355886220932, |
| "reward_std": 0.11420422047376633, |
| "rewards/<lambda>": 0.170355886220932, |
| "step": 90 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.9285714285714286, |
| "grad_norm": 0.18158575892448425, |
| "kl": 0.05551178380846977, |
| "learning_rate": 9.1e-05, |
| "loss": 0.0022, |
| "reward": 0.17519733309745789, |
| "reward_std": 0.1182706207036972, |
| "rewards/<lambda>": 0.17519733309745789, |
| "step": 91 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.9387755102040817, |
| "grad_norm": 0.1649360954761505, |
| "kl": 0.0335373729467392, |
| "learning_rate": 9.200000000000001e-05, |
| "loss": 0.0013, |
| "reward": 0.19423919916152954, |
| "reward_std": 0.13439567387104034, |
| "rewards/<lambda>": 0.19423919916152954, |
| "step": 92 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.9489795918367347, |
| "grad_norm": 0.10932810604572296, |
| "kl": 0.035153284668922424, |
| "learning_rate": 9.300000000000001e-05, |
| "loss": 0.0014, |
| "reward": 0.15611481666564941, |
| "reward_std": 0.09644447267055511, |
| "rewards/<lambda>": 0.15611481666564941, |
| "step": 93 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.9591836734693877, |
| "grad_norm": 0.099422886967659, |
| "kl": 0.03238137811422348, |
| "learning_rate": 9.4e-05, |
| "loss": 0.0013, |
| "reward": 0.1927059292793274, |
| "reward_std": 0.11067558825016022, |
| "rewards/<lambda>": 0.1927059292793274, |
| "step": 94 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.9693877551020408, |
| "grad_norm": 0.1119072213768959, |
| "kl": 0.027582138776779175, |
| "learning_rate": 9.5e-05, |
| "loss": 0.0011, |
| "reward": 0.2055554836988449, |
| "reward_std": 0.14050546288490295, |
| "rewards/<lambda>": 0.2055554836988449, |
| "step": 95 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.9795918367346939, |
| "grad_norm": 0.119843028485775, |
| "kl": 0.029401419684290886, |
| "learning_rate": 9.6e-05, |
| "loss": 0.0012, |
| "reward": 0.19861146807670593, |
| "reward_std": 0.12701785564422607, |
| "rewards/<lambda>": 0.19861146807670593, |
| "step": 96 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 0.9897959183673469, |
| "grad_norm": 0.10992871224880219, |
| "kl": 0.03312207758426666, |
| "learning_rate": 9.7e-05, |
| "loss": 0.0013, |
| "reward": 0.15577931702136993, |
| "reward_std": 0.10662981122732162, |
| "rewards/<lambda>": 0.15577931702136993, |
| "step": 97 |
| }, |
| { |
| "completion_length": 160.0, |
| "epoch": 1.0, |
| "grad_norm": 0.13580623269081116, |
| "kl": 0.0318591445684433, |
| "learning_rate": 9.8e-05, |
| "loss": 0.0013, |
| "reward": 0.256815642118454, |
| "reward_std": 0.17193631827831268, |
| "rewards/<lambda>": 0.256815642118454, |
| "step": 98 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 98, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
