| {"rows": 200, "of": 27644, "epoch": 0, "ce": 0.36085896074771884, "kl": 0.0, "lr": 2.5239457519507743e-05, "rows_per_s": 0.8489428435116587, "tokens_per_s": 5514.206366888759, "gpu_gb": 15.715003967285156} |
| {"rows": 400, "of": 27644, "epoch": 0, "ce": 0.2631891492754221, "kl": 0.0, "lr": 4.948898067637296e-05, "rows_per_s": 1.062190341226625, "tokens_per_s": 6748.328919687819, "gpu_gb": 15.993857860565186} |
| {"rows": 600, "of": 27644, "epoch": 0, "ce": 0.22552833627909422, "kl": 0.0, "lr": 7.370064985053864e-05, "rows_per_s": 1.1429982542525752, "tokens_per_s": 7415.1173545916035, "gpu_gb": 15.993857860565186} |
| {"rows": 800, "of": 27644, "epoch": 0, "ce": 0.2049107265472412, "kl": 0.0, "lr": 9.78557041525851e-05, "rows_per_s": 1.2064230405647018, "tokens_per_s": 7787.563272803598, "gpu_gb": 15.993857860565186} |
| {"rows": 1000, "of": 27644, "epoch": 0, "ce": 0.23842138186097145, "kl": 0.0, "lr": 9.96773764410274e-05, "rows_per_s": 1.249190184561534, "tokens_per_s": 7966.86030486333, "gpu_gb": 15.993857860565186} |
| {"rows": 1200, "of": 27644, "epoch": 0, "ce": 0.22905686378479004, "kl": 0.0, "lr": 9.953564214713239e-05, "rows_per_s": 1.2771554248411945, "tokens_per_s": 8107.3570937834065, "gpu_gb": 15.993857860565186} |
| {"rows": 1400, "of": 27644, "epoch": 0, "ce": 0.21381109148263933, "kl": 0.0, "lr": 9.936831122537051e-05, "rows_per_s": 1.295142654664457, "tokens_per_s": 8187.470016324035, "gpu_gb": 15.993857860565186} |
| {"rows": 1600, "of": 27644, "epoch": 0, "ce": 0.23067699164152144, "kl": 0.0, "lr": 9.917547014090404e-05, "rows_per_s": 1.311033297524685, "tokens_per_s": 8243.289014931892, "gpu_gb": 15.993857860565186} |
| {"rows": 1800, "of": 27644, "epoch": 0, "ce": 0.20589447677135467, "kl": 0.0, "lr": 9.895721854080047e-05, "rows_per_s": 1.321934010968016, "tokens_per_s": 8300.335525934108, "gpu_gb": 15.993857860565186} |
| {"rows": 2000, "of": 27644, "epoch": 0, "ce": 0.21627589035779238, "kl": 0.0, "lr": 9.871366920254174e-05, "rows_per_s": 1.326208613010953, "tokens_per_s": 8331.836648393435, "gpu_gb": 15.993857860565186} |
| {"rows": 2200, "of": 27644, "epoch": 0, "ce": 0.2108935915026814, "kl": 0.0, "lr": 9.844494797574866e-05, "rows_per_s": 1.3296080092868248, "tokens_per_s": 8361.317325411646, "gpu_gb": 15.993857860565186} |
| {"rows": 2400, "of": 27644, "epoch": 0, "ce": 0.20943921141326427, "kl": 0.0, "lr": 9.815119371715029e-05, "rows_per_s": 1.3243657112627003, "tokens_per_s": 8312.304132073848, "gpu_gb": 15.993857860565186} |
| {"rows": 2600, "of": 27644, "epoch": 0, "ce": 0.20467571575194599, "kl": 0.0, "lr": 9.783255821883243e-05, "rows_per_s": 1.330490790751763, "tokens_per_s": 8331.359344430286, "gpu_gb": 15.993857860565186} |
| {"rows": 2800, "of": 27644, "epoch": 0, "ce": 0.22089658852666616, "kl": 0.0, "lr": 9.748920612980175e-05, "rows_per_s": 1.336821439197119, "tokens_per_s": 8378.76326879226, "gpu_gb": 15.993857860565186} |
| {"rows": 3000, "of": 27644, "epoch": 0, "ce": 0.21258714515715837, "kl": 0.0, "lr": 9.712131487090656e-05, "rows_per_s": 1.3408848988054898, "tokens_per_s": 8358.13962757079, "gpu_gb": 15.993857860565186} |
| {"rows": 3200, "of": 27644, "epoch": 0, "ce": 0.2240411265939474, "kl": 0.0, "lr": 9.672907454315778e-05, "rows_per_s": 1.3441680074704951, "tokens_per_s": 8405.793279546955, "gpu_gb": 15.993857860565186} |
| {"rows": 3400, "of": 27644, "epoch": 0, "ce": 0.1996938092261553, "kl": 0.0, "lr": 9.631268782949782e-05, "rows_per_s": 1.3456492743578568, "tokens_per_s": 8434.763952960464, "gpu_gb": 16.013582706451416} |
| {"rows": 3600, "of": 27644, "epoch": 0, "ce": 0.2080060131382197, "kl": 0.0, "lr": 9.587236989006785e-05, "rows_per_s": 1.3506900085815385, "tokens_per_s": 8432.206146140248, "gpu_gb": 16.013582706451416} |
| {"rows": 3800, "of": 27644, "epoch": 0, "ce": 0.19808816716074942, "kl": 0.0, "lr": 9.540834825102782e-05, "rows_per_s": 1.3512586139565306, "tokens_per_s": 8429.909361062142, "gpu_gb": 16.013582706451416} |
| {"rows": 4000, "of": 27644, "epoch": 0, "ce": 0.19630078106187285, "kl": 0.0, "lr": 9.492086268698655e-05, "rows_per_s": 1.351504155708512, "tokens_per_s": 8454.586977311714, "gpu_gb": 16.97444248199463} |
| {"rows": 4200, "of": 27644, "epoch": 0, "ce": 0.21574503377079965, "kl": 0.0, "lr": 9.441016509710252e-05, "rows_per_s": 1.3542319030073284, "tokens_per_s": 8454.908283662391, "gpu_gb": 16.97444248199463} |
| {"rows": 4400, "of": 27644, "epoch": 0, "ce": 0.21556146416813135, "kl": 0.0, "lr": 9.387651937491975e-05, "rows_per_s": 1.3587678332678104, "tokens_per_s": 8456.888232945372, "gpu_gb": 16.97444248199463} |
| {"rows": 4600, "of": 27644, "epoch": 0, "ce": 0.19279830690473318, "kl": 0.0, "lr": 9.332020127200561e-05, "rows_per_s": 1.3585312932222424, "tokens_per_s": 8462.561950408433, "gpu_gb": 16.97444248199463} |
| {"rows": 4800, "of": 27644, "epoch": 0, "ce": 0.20191135670989752, "kl": 0.0, "lr": 9.274149825546134e-05, "rows_per_s": 1.3597932214188169, "tokens_per_s": 8477.707893884828, "gpu_gb": 16.97444248199463} |
| {"rows": 5000, "of": 27644, "epoch": 0, "ce": 0.22213074111379683, "kl": 0.0, "lr": 9.214070935937871e-05, "rows_per_s": 1.3602687364940376, "tokens_per_s": 8478.214423275718, "gpu_gb": 16.97444248199463} |
| {"rows": 5200, "of": 27644, "epoch": 0, "ce": 0.21097509548068047, "kl": 0.0, "lr": 9.151814503031972e-05, "rows_per_s": 1.3620004759472215, "tokens_per_s": 8477.15277616326, "gpu_gb": 16.97444248199463} |
| {"rows": 5400, "of": 27644, "epoch": 0, "ce": 0.22293307147920133, "kl": 0.0, "lr": 9.087412696689899e-05, "rows_per_s": 1.361504985480816, "tokens_per_s": 8479.771742593346, "gpu_gb": 16.97444248199463} |
| {"rows": 5600, "of": 27644, "epoch": 0, "ce": 0.20907054984942078, "kl": 0.0, "lr": 9.020898795355199e-05, "rows_per_s": 1.363832628852235, "tokens_per_s": 8481.185113251826, "gpu_gb": 16.97444248199463} |
| {"rows": 5800, "of": 27644, "epoch": 0, "ce": 0.19664805002510546, "kl": 0.0, "lr": 8.95230716885749e-05, "rows_per_s": 1.364152364223438, "tokens_per_s": 8491.163568724589, "gpu_gb": 16.97444248199463} |
| {"rows": 6000, "of": 27644, "epoch": 0, "ce": 0.1967082131654024, "kl": 0.0, "lr": 8.881673260652477e-05, "rows_per_s": 1.3650491455350569, "tokens_per_s": 8494.323169067728, "gpu_gb": 16.97444248199463} |
| {"rows": 6200, "of": 27644, "epoch": 0, "ce": 0.21727254492230713, "kl": 0.0, "lr": 8.809033569507202e-05, "rows_per_s": 1.368689144193678, "tokens_per_s": 8505.452895990062, "gpu_gb": 16.97444248199463} |
| {"rows": 6400, "of": 27644, "epoch": 0, "ce": 0.21077738636173307, "kl": 0.0, "lr": 8.734425630639985e-05, "rows_per_s": 1.3707163994998264, "tokens_per_s": 8516.597672308048, "gpu_gb": 16.97444248199463} |
| {"rows": 6600, "of": 27644, "epoch": 0, "ce": 0.20477758564054965, "kl": 0.0, "lr": 8.657887996324792e-05, "rows_per_s": 1.3714119390632868, "tokens_per_s": 8528.412723992877, "gpu_gb": 16.97444248199463} |
| {"rows": 6800, "of": 27644, "epoch": 0, "ce": 0.17484037813730538, "kl": 0.0, "lr": 8.579460215970059e-05, "rows_per_s": 1.3713591705164032, "tokens_per_s": 8534.653797708836, "gpu_gb": 16.97444248199463} |
| {"rows": 7000, "of": 27644, "epoch": 0, "ce": 0.1956051228940487, "kl": 0.0, "lr": 8.499182815682263e-05, "rows_per_s": 1.373425384853003, "tokens_per_s": 8538.708048693998, "gpu_gb": 16.97444248199463} |
| {"rows": 7200, "of": 27644, "epoch": 0, "ce": 0.19462666084989905, "kl": 0.0, "lr": 8.41709727732481e-05, "rows_per_s": 1.374072629079629, "tokens_per_s": 8536.931561535222, "gpu_gb": 16.97444248199463} |
| {"rows": 7400, "of": 27644, "epoch": 0, "ce": 0.20932421209290625, "kl": 0.0, "lr": 8.33324601708305e-05, "rows_per_s": 1.3759249117869576, "tokens_per_s": 8544.588157582843, "gpu_gb": 16.97444248199463} |
| {"rows": 7600, "of": 27644, "epoch": 0, "ce": 0.194134057238698, "kl": 0.0, "lr": 8.247672363546486e-05, "rows_per_s": 1.377438387691729, "tokens_per_s": 8539.878764389807, "gpu_gb": 16.97444248199463} |
| {"rows": 7800, "of": 27644, "epoch": 0, "ce": 0.20587014392018319, "kl": 0.0, "lr": 8.160420535319541e-05, "rows_per_s": 1.378449497235504, "tokens_per_s": 8536.254925606854, "gpu_gb": 16.97444248199463} |
| {"rows": 8000, "of": 27644, "epoch": 0, "ce": 0.18950007118284704, "kl": 0.0, "lr": 8.071535618172398e-05, "rows_per_s": 1.3812814879919957, "tokens_per_s": 8554.047653048166, "gpu_gb": 16.97444248199463} |
| {"rows": 8200, "of": 27644, "epoch": 0, "ce": 0.18335368227213622, "kl": 0.0, "lr": 7.981063541743774e-05, "rows_per_s": 1.3821792661806545, "tokens_per_s": 8560.614261248584, "gpu_gb": 16.97444248199463} |
| {"rows": 8400, "of": 27644, "epoch": 0, "ce": 0.19024737037718295, "kl": 0.0, "lr": 7.88905105580761e-05, "rows_per_s": 1.3817939197203468, "tokens_per_s": 8577.068586499718, "gpu_gb": 17.73898410797119} |
| {"rows": 8600, "of": 27644, "epoch": 0, "ce": 0.18951277220621704, "kl": 0.0, "lr": 7.795545706116006e-05, "rows_per_s": 1.3820581367835514, "tokens_per_s": 8568.092560428197, "gpu_gb": 17.73898410797119} |
| {"rows": 8800, "of": 27644, "epoch": 0, "ce": 0.19110010009258985, "kl": 0.0, "lr": 7.700595809830829e-05, "rows_per_s": 1.3822114940299595, "tokens_per_s": 8573.056843079254, "gpu_gb": 17.73898410797119} |
| {"rows": 9000, "of": 27644, "epoch": 0, "ce": 0.18395390592515468, "kl": 0.0, "lr": 7.604250430556701e-05, "rows_per_s": 1.3828019239884972, "tokens_per_s": 8581.750479230788, "gpu_gb": 17.73898410797119} |
| {"rows": 9200, "of": 27644, "epoch": 0, "ce": 0.17939317617565392, "kl": 0.0, "lr": 7.506559352988301e-05, "rows_per_s": 1.3849389244758508, "tokens_per_s": 8587.738315100232, "gpu_gb": 17.73898410797119} |
| {"rows": 9400, "of": 27644, "epoch": 0, "ce": 0.18097828153520823, "kl": 0.0, "lr": 7.40757305718504e-05, "rows_per_s": 1.3850563088760282, "tokens_per_s": 8584.457588966972, "gpu_gb": 17.73898410797119} |
| {"rows": 9600, "of": 27644, "epoch": 0, "ce": 0.17336546540260314, "kl": 0.0, "lr": 7.307342692486418e-05, "rows_per_s": 1.3859083109491912, "tokens_per_s": 8589.049532362978, "gpu_gb": 17.73898410797119} |
| {"rows": 9800, "of": 27644, "epoch": 0, "ce": 0.18869875993579627, "kl": 0.0, "lr": 7.20592005108155e-05, "rows_per_s": 1.384989464478349, "tokens_per_s": 8582.74240145206, "gpu_gb": 17.73898410797119} |
| {"rows": 10000, "of": 27644, "epoch": 0, "ce": 0.17679173666983844, "kl": 0.0, "lr": 7.103357541246516e-05, "rows_per_s": 1.3831154696570647, "tokens_per_s": 8571.355222414892, "gpu_gb": 17.73898410797119} |
| {"rows": 10200, "of": 27644, "epoch": 0, "ce": 0.165219550691545, "kl": 0.0, "lr": 6.999708160263342e-05, "rows_per_s": 1.3838206555499692, "tokens_per_s": 8581.440361232073, "gpu_gb": 17.73898410797119} |
| {"rows": 10400, "of": 27644, "epoch": 0, "ce": 0.1411630467325449, "kl": 0.0, "lr": 6.895025467034648e-05, "rows_per_s": 1.3843135720634494, "tokens_per_s": 8586.086731641622, "gpu_gb": 17.73898410797119} |
| {"rows": 10600, "of": 27644, "epoch": 0, "ce": 0.1758753677457571, "kl": 0.0, "lr": 6.789363554408052e-05, "rows_per_s": 1.3847466950750846, "tokens_per_s": 8583.965335790204, "gpu_gb": 17.73898410797119} |
| {"rows": 10800, "of": 27644, "epoch": 0, "ce": 0.17210819371044636, "kl": 0.0, "lr": 6.682777021224713e-05, "rows_per_s": 1.3839285684470897, "tokens_per_s": 8589.704280436476, "gpu_gb": 17.73898410797119} |
| {"rows": 11000, "of": 27644, "epoch": 0, "ce": 0.20207075713202358, "kl": 0.0, "lr": 6.575320944106378e-05, "rows_per_s": 1.3847603845265353, "tokens_per_s": 8594.501730734712, "gpu_gb": 17.73898410797119} |
| {"rows": 11200, "of": 27644, "epoch": 0, "ce": 0.17303466711193324, "kl": 0.0, "lr": 6.467050848995558e-05, "rows_per_s": 1.3845181334457055, "tokens_per_s": 8596.034989469303, "gpu_gb": 17.73898410797119} |
| {"rows": 11400, "of": 27644, "epoch": 0, "ce": 0.16000845842063427, "kl": 0.0, "lr": 6.358022682463518e-05, "rows_per_s": 1.384289650816315, "tokens_per_s": 8596.053559045422, "gpu_gb": 17.73898410797119} |
| {"rows": 11600, "of": 27644, "epoch": 0, "ce": 0.1615778366662562, "kl": 0.0, "lr": 6.248292782800926e-05, "rows_per_s": 1.3859979597833614, "tokens_per_s": 8602.154757456638, "gpu_gb": 17.73898410797119} |
| {"rows": 11800, "of": 27644, "epoch": 0, "ce": 0.18867135945707558, "kl": 0.0, "lr": 6.137917850906081e-05, "rows_per_s": 1.386882605654892, "tokens_per_s": 8604.528090564072, "gpu_gb": 17.73898410797119} |
| {"rows": 12000, "of": 27644, "epoch": 0, "ce": 0.17251531437039375, "kl": 0.0, "lr": 6.0269549209857736e-05, "rows_per_s": 1.387015366360134, "tokens_per_s": 8604.806153270623, "gpu_gb": 17.73898410797119} |
| {"rows": 12200, "of": 27644, "epoch": 0, "ce": 0.19103072963654996, "kl": 0.0, "lr": 5.9154613310839015e-05, "rows_per_s": 1.387877198423959, "tokens_per_s": 8609.05004120278, "gpu_gb": 17.73898410797119} |
| {"rows": 12400, "of": 27644, "epoch": 0, "ce": 0.1621233719959855, "kl": 0.0, "lr": 5.80349469345311e-05, "rows_per_s": 1.3874336392370512, "tokens_per_s": 8613.08688399572, "gpu_gb": 17.73898410797119} |
| {"rows": 12600, "of": 27644, "epoch": 0, "ce": 0.16437096677720547, "kl": 0.0, "lr": 5.691112864784718e-05, "rows_per_s": 1.3872882365065526, "tokens_per_s": 8605.539187722581, "gpu_gb": 17.73898410797119} |
| {"rows": 12800, "of": 27644, "epoch": 0, "ce": 0.15417302498593927, "kl": 0.0, "lr": 5.578373916312339e-05, "rows_per_s": 1.3880066329819136, "tokens_per_s": 8616.327474305606, "gpu_gb": 17.73898410797119} |
| {"rows": 13000, "of": 27644, "epoch": 0, "ce": 0.18225131146609783, "kl": 0.0, "lr": 5.465336103804653e-05, "rows_per_s": 1.3881629371489126, "tokens_per_s": 8620.444855718413, "gpu_gb": 17.73898410797119} |
| {"rows": 13200, "of": 27644, "epoch": 0, "ce": 0.17639901410788297, "kl": 0.0, "lr": 5.352057837462802e-05, "rows_per_s": 1.3881602016356724, "tokens_per_s": 8623.242759468667, "gpu_gb": 17.73898410797119} |
| {"rows": 13400, "of": 27644, "epoch": 0, "ce": 0.17552863938733934, "kl": 0.0, "lr": 5.2385976517380054e-05, "rows_per_s": 1.3874683032878061, "tokens_per_s": 8624.716684772673, "gpu_gb": 17.73898410797119} |
| {"rows": 13600, "of": 27644, "epoch": 0, "ce": 0.14498583190143108, "kl": 0.0, "lr": 5.125014175084966e-05, "rows_per_s": 1.3871155287524546, "tokens_per_s": 8619.03041445007, "gpu_gb": 17.73898410797119} |
| {"rows": 13800, "of": 27644, "epoch": 0, "ce": 0.1834407548420131, "kl": 0.0, "lr": 5.011366099666695e-05, "rows_per_s": 1.3868432671065682, "tokens_per_s": 8618.510952519093, "gpu_gb": 17.73898410797119} |
| {"rows": 14000, "of": 27644, "epoch": 0, "ce": 0.17281464175321162, "kl": 0.0, "lr": 4.897712151026418e-05, "rows_per_s": 1.386796731694343, "tokens_per_s": 8614.161993487647, "gpu_gb": 17.73898410797119} |
| {"rows": 14200, "of": 27644, "epoch": 0, "ce": 0.17652987971901893, "kl": 0.0, "lr": 4.784111057742244e-05, "rows_per_s": 1.387004261753605, "tokens_per_s": 8620.749952898752, "gpu_gb": 17.73898410797119} |
| {"rows": 14400, "of": 27644, "epoch": 0, "ce": 0.16347156874835492, "kl": 0.0, "lr": 4.670621521080252e-05, "rows_per_s": 1.3865712227531535, "tokens_per_s": 8615.184133808187, "gpu_gb": 17.73898410797119} |
| {"rows": 14600, "of": 27644, "epoch": 0, "ce": 0.1692851831763983, "kl": 0.0, "lr": 4.5573021846616976e-05, "rows_per_s": 1.3865260294195854, "tokens_per_s": 8611.38837975103, "gpu_gb": 17.73898410797119} |
| {"rows": 14800, "of": 27644, "epoch": 0, "ce": 0.18402940277010202, "kl": 0.0, "lr": 4.444211604160004e-05, "rows_per_s": 1.3857593967275548, "tokens_per_s": 8611.78828789899, "gpu_gb": 17.73898410797119} |
| {"rows": 15000, "of": 27644, "epoch": 0, "ce": 0.15683865858241916, "kl": 0.0, "lr": 4.331408217043202e-05, "rows_per_s": 1.3855295070187765, "tokens_per_s": 8610.309571748132, "gpu_gb": 17.73898410797119} |
| {"rows": 15200, "of": 27644, "epoch": 0, "ce": 0.1643610978499055, "kl": 0.0, "lr": 4.218950312377447e-05, "rows_per_s": 1.3855353426585857, "tokens_per_s": 8606.788035103547, "gpu_gb": 17.73898410797119} |
| {"rows": 15400, "of": 27644, "epoch": 0, "ce": 0.1720756763778627, "kl": 0.0, "lr": 4.1068960007072224e-05, "rows_per_s": 1.3856927047965208, "tokens_per_s": 8607.232395364686, "gpu_gb": 17.73898410797119} |
| {"rows": 15600, "of": 27644, "epoch": 0, "ce": 0.1853026487864554, "kl": 0.0, "lr": 3.995303184027782e-05, "rows_per_s": 1.3861855552335367, "tokens_per_s": 8603.907658702972, "gpu_gb": 17.73898410797119} |
| {"rows": 15800, "of": 27644, "epoch": 0, "ce": 0.1507757867872715, "kl": 0.0, "lr": 3.884229525865376e-05, "rows_per_s": 1.3871914408711918, "tokens_per_s": 8603.858949263313, "gpu_gb": 17.73898410797119} |
| {"rows": 16000, "of": 27644, "epoch": 0, "ce": 0.1430858861654997, "kl": 0.0, "lr": 3.773732421480681e-05, "rows_per_s": 1.3878025114962296, "tokens_per_s": 8605.341134873996, "gpu_gb": 17.73898410797119} |
| {"rows": 16200, "of": 27644, "epoch": 0, "ce": 0.14958408737555146, "kl": 0.0, "lr": 3.663868968210861e-05, "rows_per_s": 1.3881411665420982, "tokens_per_s": 8609.450653170083, "gpu_gb": 17.73898410797119} |
| {"rows": 16400, "of": 27644, "epoch": 0, "ce": 0.1495011910609901, "kl": 0.0, "lr": 3.554695935965571e-05, "rows_per_s": 1.3882318376807967, "tokens_per_s": 8611.437411360126, "gpu_gb": 17.73898410797119} |
| {"rows": 16600, "of": 27644, "epoch": 0, "ce": 0.1550422583054751, "kl": 0.0, "lr": 3.446269737892163e-05, "rows_per_s": 1.3884849531757826, "tokens_per_s": 8613.619642232848, "gpu_gb": 17.73898410797119} |
| {"rows": 16800, "of": 27644, "epoch": 0, "ce": 0.1474022769089788, "kl": 0.0, "lr": 3.3386464012252234e-05, "rows_per_s": 1.3885795716933338, "tokens_per_s": 8618.602954781994, "gpu_gb": 17.73898410797119} |
| {"rows": 17000, "of": 27644, "epoch": 0, "ce": 0.14810169523581862, "kl": 0.0, "lr": 3.231881538335546e-05, "rows_per_s": 1.3891911004308037, "tokens_per_s": 8620.743046381273, "gpu_gb": 17.73898410797119} |
| {"rows": 17200, "of": 27644, "epoch": 0, "ce": 0.1417401478579268, "kl": 0.0, "lr": 3.1260303179934556e-05, "rows_per_s": 1.3888488566753114, "tokens_per_s": 8615.818194912306, "gpu_gb": 17.73898410797119} |
| {"rows": 17400, "of": 27644, "epoch": 0, "ce": 0.15734178267419338, "kl": 0.0, "lr": 3.0211474368613752e-05, "rows_per_s": 1.3894888891336963, "tokens_per_s": 8613.462386217438, "gpu_gb": 17.73898410797119} |
| {"rows": 17600, "of": 27644, "epoch": 0, "ce": 0.1380095674470067, "kl": 0.0, "lr": 2.9172870912303308e-05, "rows_per_s": 1.3894239842239264, "tokens_per_s": 8612.703606000658, "gpu_gb": 17.73898410797119} |
| {"rows": 17800, "of": 27644, "epoch": 0, "ce": 0.14660378344357014, "kl": 0.0, "lr": 2.8145029490150175e-05, "rows_per_s": 1.3890173477087984, "tokens_per_s": 8612.930434412177, "gpu_gb": 17.73898410797119} |
| {"rows": 18000, "of": 27644, "epoch": 0, "ce": 0.14610900938510896, "kl": 0.0, "lr": 2.7128481220219036e-05, "rows_per_s": 1.389123803646175, "tokens_per_s": 8616.41422076567, "gpu_gb": 17.73898410797119} |
| {"rows": 18200, "of": 27644, "epoch": 0, "ce": 0.1300594929791987, "kl": 0.0, "lr": 2.612375138504679e-05, "rows_per_s": 1.388792493319898, "tokens_per_s": 8617.069780068316, "gpu_gb": 17.73898410797119} |
| {"rows": 18400, "of": 27644, "epoch": 0, "ce": 0.1290073513239622, "kl": 0.0, "lr": 2.513135916021253e-05, "rows_per_s": 1.3893520603384668, "tokens_per_s": 8618.71774632674, "gpu_gb": 17.73898410797119} |
| {"rows": 18600, "of": 27644, "epoch": 0, "ce": 0.14802748183021322, "kl": 0.0, "lr": 2.4151817346063155e-05, "rows_per_s": 1.3886449896001374, "tokens_per_s": 8619.465780780289, "gpu_gb": 17.73898410797119} |
| {"rows": 18800, "of": 27644, "epoch": 0, "ce": 0.13398919036611914, "kl": 0.0, "lr": 2.3185632102733266e-05, "rows_per_s": 1.3883950621247052, "tokens_per_s": 8617.943915514845, "gpu_gb": 17.73898410797119} |
| {"rows": 19000, "of": 27644, "epoch": 0, "ce": 0.1269960441440344, "kl": 0.0, "lr": 2.223330268859628e-05, "rows_per_s": 1.388467678952904, "tokens_per_s": 8615.201085299093, "gpu_gb": 17.73898410797119} |
| {"rows": 19200, "of": 27644, "epoch": 0, "ce": 0.12839976143091916, "kl": 0.0, "lr": 2.129532120228187e-05, "rows_per_s": 1.3880198829826724, "tokens_per_s": 8609.854947010914, "gpu_gb": 17.73898410797119} |
| {"rows": 19400, "of": 27644, "epoch": 0, "ce": 0.1504750985093415, "kl": 0.0, "lr": 2.0372172328393062e-05, "rows_per_s": 1.3879455546332673, "tokens_per_s": 8610.14171124306, "gpu_gb": 17.73898410797119} |
| {"rows": 19600, "of": 27644, "epoch": 0, "ce": 0.15901072138920427, "kl": 0.0, "lr": 1.9464333087054505e-05, "rows_per_s": 1.3881209571341546, "tokens_per_s": 8609.270370751574, "gpu_gb": 17.73898410797119} |
| {"rows": 19800, "of": 27644, "epoch": 0, "ce": 0.13902726129628717, "kl": 0.0, "lr": 1.8572272587421057e-05, "rows_per_s": 1.388038294445861, "tokens_per_s": 8610.15296280707, "gpu_gb": 17.73898410797119} |
| {"rows": 20000, "of": 27644, "epoch": 0, "ce": 0.12834056928753854, "kl": 0.0, "lr": 1.7696451785274347e-05, "rows_per_s": 1.387991368244487, "tokens_per_s": 8614.263901703216, "gpu_gb": 17.73898410797119} |
| {"rows": 20200, "of": 27644, "epoch": 0, "ce": 0.14513432241976262, "kl": 0.0, "lr": 1.6837323244832354e-05, "rows_per_s": 1.3879818708169038, "tokens_per_s": 8608.339145977621, "gpu_gb": 17.73898410797119} |
| {"rows": 20400, "of": 27644, "epoch": 0, "ce": 0.15517583202570676, "kl": 0.0, "lr": 1.5995330904895223e-05, "rows_per_s": 1.3877304057195157, "tokens_per_s": 8607.27974833881, "gpu_gb": 17.73898410797119} |
| {"rows": 20600, "of": 27644, "epoch": 0, "ce": 0.13032510291785002, "kl": 0.0, "lr": 1.5170909849448101e-05, "rows_per_s": 1.3883809086936458, "tokens_per_s": 8607.126179058654, "gpu_gb": 17.73898410797119} |
| {"rows": 20800, "of": 27644, "epoch": 0, "ce": 0.13141531277447938, "kl": 0.0, "lr": 1.4364486082839534e-05, "rows_per_s": 1.388411101679877, "tokens_per_s": 8606.403971463415, "gpu_gb": 17.73898410797119} |
| {"rows": 21000, "of": 27644, "epoch": 0, "ce": 0.12583129175007343, "kl": 0.0, "lr": 1.357647630965153e-05, "rows_per_s": 1.3887657668708695, "tokens_per_s": 8612.72108916327, "gpu_gb": 17.73898410797119} |
| {"rows": 21200, "of": 27644, "epoch": 0, "ce": 0.1305518364533782, "kl": 0.0, "lr": 1.2807287719375261e-05, "rows_per_s": 1.3884317735385276, "tokens_per_s": 8615.646163068992, "gpu_gb": 17.73898410797119} |
| {"rows": 21400, "of": 27644, "epoch": 0, "ce": 0.13091811086982488, "kl": 0.0, "lr": 1.2057317776003335e-05, "rows_per_s": 1.3885387762824761, "tokens_per_s": 8614.331057882826, "gpu_gb": 17.73898410797119} |
| {"rows": 21600, "of": 27644, "epoch": 0, "ce": 0.14964440142270177, "kl": 0.0, "lr": 1.1326954012647661e-05, "rows_per_s": 1.3882424774394952, "tokens_per_s": 8616.317691027905, "gpu_gb": 17.73898410797119} |
| {"rows": 21800, "of": 27644, "epoch": 0, "ce": 0.13317173598334192, "kl": 0.0, "lr": 1.0616573831288884e-05, "rows_per_s": 1.387940967634077, "tokens_per_s": 8612.280919425846, "gpu_gb": 17.73898410797119} |
| {"rows": 22000, "of": 27644, "epoch": 0, "ce": 0.13332346592098474, "kl": 0.0, "lr": 9.926544307760832e-06, "rows_per_s": 1.3880913256631104, "tokens_per_s": 8612.543867802104, "gpu_gb": 17.73898410797119} |
| {"rows": 22200, "of": 27644, "epoch": 0, "ce": 0.16741748777218163, "kl": 0.0, "lr": 9.257222002070925e-06, "rows_per_s": 1.3882116351045863, "tokens_per_s": 8610.521988156153, "gpu_gb": 17.73898410797119} |
| {"rows": 22400, "of": 27644, "epoch": 0, "ce": 0.12876728530973197, "kl": 0.0, "lr": 8.608952774154345e-06, "rows_per_s": 1.3879162849625273, "tokens_per_s": 8612.388841692386, "gpu_gb": 17.73898410797119} |
| {"rows": 22600, "of": 27644, "epoch": 0, "ce": 0.1317625662405044, "kl": 0.0, "lr": 7.98207160515726e-06, "rows_per_s": 1.388563497865564, "tokens_per_s": 8611.766118532125, "gpu_gb": 17.73898410797119} |
| {"rows": 22800, "of": 27644, "epoch": 0, "ce": 0.12762531377607955, "kl": 0.0, "lr": 7.376902424341625e-06, "rows_per_s": 1.3888253642786386, "tokens_per_s": 8611.489396699384, "gpu_gb": 17.73898410797119} |
| {"rows": 23000, "of": 27644, "epoch": 0, "ce": 0.12915205211378633, "kl": 0.0, "lr": 6.793757941700601e-06, "rows_per_s": 1.3892586162278142, "tokens_per_s": 8612.280899650536, "gpu_gb": 17.73898410797119} |
| {"rows": 23200, "of": 27644, "epoch": 0, "ce": 0.1360259204916656, "kl": 0.0, "lr": 6.232939486371514e-06, "rows_per_s": 1.3894697288754587, "tokens_per_s": 8614.614577019329, "gpu_gb": 17.73898410797119} |
| {"rows": 23400, "of": 27644, "epoch": 0, "ce": 0.14520388450473548, "kl": 0.0, "lr": 5.6947368509295606e-06, "rows_per_s": 1.3899298478280597, "tokens_per_s": 8616.939944494716, "gpu_gb": 17.73898410797119} |
| {"rows": 23600, "of": 27644, "epoch": 0, "ce": 0.12198533607646823, "kl": 0.0, "lr": 5.179428141642861e-06, "rows_per_s": 1.3896197981593994, "tokens_per_s": 8614.062114950066, "gpu_gb": 17.73898410797119} |
| {"rows": 23800, "of": 27644, "epoch": 0, "ce": 0.13558543171733617, "kl": 0.0, "lr": 4.687279634766173e-06, "rows_per_s": 1.3898143389765283, "tokens_per_s": 8615.418911169902, "gpu_gb": 17.73898410797119} |
| {"rows": 24000, "of": 27644, "epoch": 0, "ce": 0.14841709772124886, "kl": 0.0, "lr": 4.218545638947585e-06, "rows_per_s": 1.3893672931842282, "tokens_per_s": 8610.66979445568, "gpu_gb": 17.73898410797119} |
| {"rows": 24200, "of": 27644, "epoch": 0, "ce": 0.12530215360224248, "kl": 0.0, "lr": 3.773468363819149e-06, "rows_per_s": 1.3891257696404458, "tokens_per_s": 8606.369116738862, "gpu_gb": 17.73898410797119} |
| {"rows": 24400, "of": 27644, "epoch": 0, "ce": 0.1442721876129508, "kl": 0.0, "lr": 3.352277794839631e-06, "rows_per_s": 1.3893584685190943, "tokens_per_s": 8607.446283988622, "gpu_gb": 17.73898410797119} |
| {"rows": 24600, "of": 27644, "epoch": 0, "ce": 0.11735559469088912, "kl": 0.0, "lr": 2.9551915744536973e-06, "rows_per_s": 1.3894268472423805, "tokens_per_s": 8609.720820160683, "gpu_gb": 17.73898410797119} |
| {"rows": 24800, "of": 27644, "epoch": 0, "ce": 0.11297125708311796, "kl": 0.0, "lr": 2.5824148896292254e-06, "rows_per_s": 1.3894417139158168, "tokens_per_s": 8610.572890702346, "gpu_gb": 17.73898410797119} |
| {"rows": 25000, "of": 27644, "epoch": 0, "ce": 0.12124939039815218, "kl": 0.0, "lr": 2.2341403658307446e-06, "rows_per_s": 1.3895282687682156, "tokens_per_s": 8614.521455976137, "gpu_gb": 17.73898410797119} |
| {"rows": 25200, "of": 27644, "epoch": 0, "ce": 0.12851434271782636, "kl": 0.0, "lr": 1.9105479674837556e-06, "rows_per_s": 1.3893133146404193, "tokens_per_s": 8618.376682515656, "gpu_gb": 17.73898410797119} |
| {"rows": 25400, "of": 27644, "epoch": 0, "ce": 0.1329329369869083, "kl": 0.0, "lr": 1.6118049049814676e-06, "rows_per_s": 1.3895325725682355, "tokens_per_s": 8621.480670315243, "gpu_gb": 17.73898410797119} |
| {"rows": 25600, "of": 27644, "epoch": 0, "ce": 0.12408415727317333, "kl": 0.0, "lr": 1.3380655482818916e-06, "rows_per_s": 1.3896937485640746, "tokens_per_s": 8621.783134272055, "gpu_gb": 17.73898410797119} |
| {"rows": 25800, "of": 27644, "epoch": 0, "ce": 0.12144216819666326, "kl": 0.0, "lr": 1.0894713471400474e-06, "rows_per_s": 1.3901335760719598, "tokens_per_s": 8623.928129911359, "gpu_gb": 17.73898410797119} |
| {"rows": 26000, "of": 27644, "epoch": 0, "ce": 0.12853420542553068, "kl": 0.0, "lr": 8.661507580163819e-07, "rows_per_s": 1.3905432379055662, "tokens_per_s": 8626.490622373225, "gpu_gb": 17.73898410797119} |
| {"rows": 26200, "of": 27644, "epoch": 0, "ce": 0.1427439607679844, "kl": 0.0, "lr": 6.682191776992863e-07, "rows_per_s": 1.3908375972577987, "tokens_per_s": 8627.166439352533, "gpu_gb": 17.73898410797119} |
| {"rows": 26400, "of": 27644, "epoch": 0, "ce": 0.13167895659804343, "kl": 0.0, "lr": 4.957788836759348e-07, "rows_per_s": 1.3908509383437202, "tokens_per_s": 8627.127631890315, "gpu_gb": 17.73898410797119} |
| {"rows": 26600, "of": 27644, "epoch": 0, "ce": 0.13655862426385285, "kl": 0.0, "lr": 3.4891898128229796e-07, "rows_per_s": 1.3912108475774747, "tokens_per_s": 8629.01122347449, "gpu_gb": 17.73898410797119} |
| {"rows": 26800, "of": 27644, "epoch": 0, "ce": 0.14189616140909492, "kl": 0.0, "lr": 2.2771535765956364e-07, "rows_per_s": 1.391232673620704, "tokens_per_s": 8626.295002278292, "gpu_gb": 17.73898410797119} |
| {"rows": 27000, "of": 27644, "epoch": 0, "ce": 0.12253829274326562, "kl": 0.0, "lr": 1.3223064254090366e-07, "rows_per_s": 1.3916149015463086, "tokens_per_s": 8623.8843443762, "gpu_gb": 17.73898410797119} |
| {"rows": 27200, "of": 27644, "epoch": 0, "ce": 0.13998983905650675, "kl": 0.0, "lr": 6.251417588870046e-08, "rows_per_s": 1.3919402766863644, "tokens_per_s": 8626.37055010457, "gpu_gb": 17.73898410797119} |
| {"rows": 27400, "of": 27644, "epoch": 0, "ce": 0.13824107202701272, "kl": 0.0, "lr": 1.8601982399019114e-08, "rows_per_s": 1.392383328794809, "tokens_per_s": 8627.699012899599, "gpu_gb": 17.73898410797119} |
| {"rows": 27600, "of": 27644, "epoch": 0, "ce": 0.14036576688289643, "kl": 0.0, "lr": 5.16752886531302e-10, "rows_per_s": 1.3925534374220379, "tokens_per_s": 8624.390606988267, "gpu_gb": 17.73898410797119} |
| {"rows": 27644, "of": 27644, "epoch": 0, "ce": 0.14875189418142493, "kl": 0.0, "lr": 0.0, "rows_per_s": 1.3924991021120716, "tokens_per_s": 8623.441681654736, "gpu_gb": 17.73898410797119} |
|
|
