{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9883268482490273,
  "eval_steps": 32,
  "global_step": 256,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007782101167315175,
      "grad_norm": 13.2358487482735,
      "learning_rate": 4e-08,
      "loss": 1.3028,
      "step": 1
    },
    {
      "epoch": 0.007782101167315175,
      "eval_loss": 1.1581796407699585,
      "eval_runtime": 193.4094,
      "eval_samples_per_second": 13.939,
      "eval_steps_per_second": 0.222,
      "step": 1
    },
    {
      "epoch": 0.01556420233463035,
      "grad_norm": 13.517130491540176,
      "learning_rate": 8e-08,
      "loss": 1.2437,
      "step": 2
    },
    {
      "epoch": 0.023346303501945526,
      "grad_norm": 13.028970161750262,
      "learning_rate": 1.2000000000000002e-07,
      "loss": 1.3071,
      "step": 3
    },
    {
      "epoch": 0.0311284046692607,
      "grad_norm": 13.538257754320586,
      "learning_rate": 1.6e-07,
      "loss": 1.3013,
      "step": 4
    },
    {
      "epoch": 0.038910505836575876,
      "grad_norm": 13.666771312447045,
      "learning_rate": 2e-07,
      "loss": 1.2823,
      "step": 5
    },
    {
      "epoch": 0.04669260700389105,
      "grad_norm": 12.758203259942219,
      "learning_rate": 2.4000000000000003e-07,
      "loss": 1.2447,
      "step": 6
    },
    {
      "epoch": 0.054474708171206226,
      "grad_norm": 12.521308995567729,
      "learning_rate": 2.8e-07,
      "loss": 1.261,
      "step": 7
    },
    {
      "epoch": 0.0622568093385214,
      "grad_norm": 11.561801223157566,
      "learning_rate": 3.2e-07,
      "loss": 1.2665,
      "step": 8
    },
    {
      "epoch": 0.07003891050583658,
      "grad_norm": 11.156739432208562,
      "learning_rate": 3.6e-07,
      "loss": 1.2488,
      "step": 9
    },
    {
      "epoch": 0.07782101167315175,
      "grad_norm": 10.490731019339595,
      "learning_rate": 4e-07,
      "loss": 1.2695,
      "step": 10
    },
    {
      "epoch": 0.08560311284046693,
      "grad_norm": 8.664509193480505,
      "learning_rate": 4.3999999999999997e-07,
      "loss": 1.2306,
      "step": 11
    },
    {
      "epoch": 0.0933852140077821,
      "grad_norm": 7.187121902510894,
      "learning_rate": 4.800000000000001e-07,
      "loss": 1.2614,
      "step": 12
    },
    {
      "epoch": 0.10116731517509728,
      "grad_norm": 6.109576574934582,
      "learning_rate": 5.2e-07,
      "loss": 1.227,
      "step": 13
    },
    {
      "epoch": 0.10894941634241245,
      "grad_norm": 5.033716100027243,
      "learning_rate": 5.6e-07,
      "loss": 1.2676,
      "step": 14
    },
    {
      "epoch": 0.11673151750972763,
      "grad_norm": 3.4452961961682815,
      "learning_rate": 6e-07,
      "loss": 1.177,
      "step": 15
    },
    {
      "epoch": 0.1245136186770428,
      "grad_norm": 3.1164741035862455,
      "learning_rate": 6.4e-07,
      "loss": 1.229,
      "step": 16
    },
    {
      "epoch": 0.13229571984435798,
      "grad_norm": 3.1002564736005267,
      "learning_rate": 6.8e-07,
      "loss": 1.2488,
      "step": 17
    },
    {
      "epoch": 0.14007782101167315,
      "grad_norm": 3.1257169665944833,
      "learning_rate": 7.2e-07,
      "loss": 1.2324,
      "step": 18
    },
    {
      "epoch": 0.14785992217898833,
      "grad_norm": 3.0581482597501832,
      "learning_rate": 7.599999999999999e-07,
      "loss": 1.1873,
      "step": 19
    },
    {
      "epoch": 0.1556420233463035,
      "grad_norm": 3.043731725003644,
      "learning_rate": 8e-07,
      "loss": 1.1759,
      "step": 20
    },
    {
      "epoch": 0.16342412451361868,
      "grad_norm": 2.734793910693522,
      "learning_rate": 8.4e-07,
      "loss": 1.165,
      "step": 21
    },
    {
      "epoch": 0.17120622568093385,
      "grad_norm": 2.5471637005098233,
      "learning_rate": 8.799999999999999e-07,
      "loss": 1.2258,
      "step": 22
    },
    {
      "epoch": 0.17898832684824903,
      "grad_norm": 2.133879636511503,
      "learning_rate": 9.2e-07,
      "loss": 1.1924,
      "step": 23
    },
    {
      "epoch": 0.1867704280155642,
      "grad_norm": 1.809481995522435,
      "learning_rate": 9.600000000000001e-07,
      "loss": 1.1285,
      "step": 24
    },
    {
      "epoch": 0.19455252918287938,
      "grad_norm": 1.5258999116809353,
      "learning_rate": 1e-06,
      "loss": 1.1613,
      "step": 25
    },
    {
      "epoch": 0.20233463035019456,
      "grad_norm": 1.363595982806325,
      "learning_rate": 9.995654063450673e-07,
      "loss": 1.1791,
      "step": 26
    },
    {
      "epoch": 0.21011673151750973,
      "grad_norm": 1.4125313988908728,
      "learning_rate": 9.9912739965096e-07,
      "loss": 1.2031,
      "step": 27
    },
    {
      "epoch": 0.2178988326848249,
      "grad_norm": 1.446135093305486,
      "learning_rate": 9.986859395532194e-07,
      "loss": 1.1514,
      "step": 28
    },
    {
      "epoch": 0.22568093385214008,
      "grad_norm": 1.342713959761476,
      "learning_rate": 9.98240985048373e-07,
      "loss": 1.1741,
      "step": 29
    },
    {
      "epoch": 0.23346303501945526,
      "grad_norm": 1.2716097075011323,
      "learning_rate": 9.977924944812361e-07,
      "loss": 1.1696,
      "step": 30
    },
    {
      "epoch": 0.24124513618677043,
      "grad_norm": 1.1283654885451528,
      "learning_rate": 9.973404255319148e-07,
      "loss": 1.1564,
      "step": 31
    },
    {
      "epoch": 0.2490272373540856,
      "grad_norm": 1.0833672902427003,
      "learning_rate": 9.968847352024923e-07,
      "loss": 1.1924,
      "step": 32
    },
    {
      "epoch": 0.2490272373540856,
      "eval_loss": 1.017075777053833,
      "eval_runtime": 192.9829,
      "eval_samples_per_second": 13.97,
      "eval_steps_per_second": 0.223,
      "step": 32
    },
    {
      "epoch": 0.25680933852140075,
      "grad_norm": 1.1221714895781139,
      "learning_rate": 9.964253798033959e-07,
      "loss": 1.1953,
      "step": 33
    },
    {
      "epoch": 0.26459143968871596,
      "grad_norm": 1.1667935320099643,
      "learning_rate": 9.959623149394347e-07,
      "loss": 1.1631,
      "step": 34
    },
    {
      "epoch": 0.2723735408560311,
      "grad_norm": 1.1728769110368067,
      "learning_rate": 9.954954954954955e-07,
      "loss": 1.1979,
      "step": 35
    },
    {
      "epoch": 0.2801556420233463,
      "grad_norm": 1.1879928099076524,
      "learning_rate": 9.950248756218905e-07,
      "loss": 1.2109,
      "step": 36
    },
    {
      "epoch": 0.28793774319066145,
      "grad_norm": 1.0793090685595952,
      "learning_rate": 9.94550408719346e-07,
      "loss": 1.1517,
      "step": 37
    },
    {
      "epoch": 0.29571984435797666,
      "grad_norm": 1.2162353553544407,
      "learning_rate": 9.940720474236205e-07,
      "loss": 1.1667,
      "step": 38
    },
    {
      "epoch": 0.3035019455252918,
      "grad_norm": 1.1553136659353096,
      "learning_rate": 9.935897435897434e-07,
      "loss": 1.1564,
      "step": 39
    },
    {
      "epoch": 0.311284046692607,
      "grad_norm": 0.8975925277420491,
      "learning_rate": 9.931034482758622e-07,
      "loss": 1.1409,
      "step": 40
    },
    {
      "epoch": 0.31906614785992216,
      "grad_norm": 0.848010373104077,
      "learning_rate": 9.92613111726685e-07,
      "loss": 1.1489,
      "step": 41
    },
    {
      "epoch": 0.32684824902723736,
      "grad_norm": 0.8445987480588121,
      "learning_rate": 9.921186833565135e-07,
      "loss": 1.1518,
      "step": 42
    },
    {
      "epoch": 0.3346303501945525,
      "grad_norm": 0.8910485581415633,
      "learning_rate": 9.916201117318436e-07,
      "loss": 1.1663,
      "step": 43
    },
    {
      "epoch": 0.3424124513618677,
      "grad_norm": 0.8226662462385251,
      "learning_rate": 9.911173445535296e-07,
      "loss": 1.1975,
      "step": 44
    },
    {
      "epoch": 0.35019455252918286,
      "grad_norm": 1.266452159867259,
      "learning_rate": 9.906103286384975e-07,
      "loss": 1.19,
      "step": 45
    },
    {
      "epoch": 0.35797665369649806,
      "grad_norm": 0.8228834741800612,
      "learning_rate": 9.900990099009902e-07,
      "loss": 1.1672,
      "step": 46
    },
    {
      "epoch": 0.3657587548638132,
      "grad_norm": 0.7967316496651314,
      "learning_rate": 9.895833333333333e-07,
      "loss": 1.1653,
      "step": 47
    },
    {
      "epoch": 0.3735408560311284,
      "grad_norm": 0.8385685679438281,
      "learning_rate": 9.8906324298621e-07,
      "loss": 1.2161,
      "step": 48
    },
    {
      "epoch": 0.38132295719844356,
      "grad_norm": 0.7832731689890803,
      "learning_rate": 9.88538681948424e-07,
      "loss": 1.1493,
      "step": 49
    },
    {
      "epoch": 0.38910505836575876,
      "grad_norm": 0.7470950974115376,
      "learning_rate": 9.88009592326139e-07,
      "loss": 1.1444,
      "step": 50
    },
    {
      "epoch": 0.3968871595330739,
      "grad_norm": 0.9407081004608256,
      "learning_rate": 9.874759152215799e-07,
      "loss": 1.2262,
      "step": 51
    },
    {
      "epoch": 0.4046692607003891,
      "grad_norm": 0.7807613751449256,
      "learning_rate": 9.869375907111757e-07,
      "loss": 1.1761,
      "step": 52
    },
    {
      "epoch": 0.41245136186770426,
      "grad_norm": 0.7814091677207984,
      "learning_rate": 9.86394557823129e-07,
      "loss": 1.1684,
      "step": 53
    },
    {
      "epoch": 0.42023346303501946,
      "grad_norm": 0.7209307303105739,
      "learning_rate": 9.858467545143973e-07,
      "loss": 1.1429,
      "step": 54
    },
    {
      "epoch": 0.4280155642023346,
      "grad_norm": 0.6839759799403674,
      "learning_rate": 9.852941176470587e-07,
      "loss": 1.1591,
      "step": 55
    },
    {
      "epoch": 0.4357976653696498,
      "grad_norm": 0.7399500476567901,
      "learning_rate": 9.847365829640571e-07,
      "loss": 1.1264,
      "step": 56
    },
    {
      "epoch": 0.44357976653696496,
      "grad_norm": 0.7250794425256079,
      "learning_rate": 9.841740850642927e-07,
      "loss": 1.1764,
      "step": 57
    },
    {
      "epoch": 0.45136186770428016,
      "grad_norm": 0.6729705016341,
      "learning_rate": 9.836065573770493e-07,
      "loss": 1.1557,
      "step": 58
    },
    {
      "epoch": 0.4591439688715953,
      "grad_norm": 0.6814295448695143,
      "learning_rate": 9.830339321357286e-07,
      "loss": 1.1674,
      "step": 59
    },
    {
      "epoch": 0.4669260700389105,
      "grad_norm": 0.6657154699765654,
      "learning_rate": 9.824561403508773e-07,
      "loss": 1.1441,
      "step": 60
    },
    {
      "epoch": 0.47470817120622566,
      "grad_norm": 0.6256174713114324,
      "learning_rate": 9.818731117824774e-07,
      "loss": 1.1797,
      "step": 61
    },
    {
      "epoch": 0.48249027237354086,
      "grad_norm": 0.6194904383458136,
      "learning_rate": 9.81284774911482e-07,
      "loss": 1.1476,
      "step": 62
    },
    {
      "epoch": 0.490272373540856,
      "grad_norm": 0.7409013991341397,
      "learning_rate": 9.80691056910569e-07,
      "loss": 1.1563,
      "step": 63
    },
    {
      "epoch": 0.4980544747081712,
      "grad_norm": 0.6529431777087924,
      "learning_rate": 9.800918836140888e-07,
      "loss": 1.13,
      "step": 64
    },
    {
      "epoch": 0.4980544747081712,
      "eval_loss": 0.993022084236145,
      "eval_runtime": 193.0792,
      "eval_samples_per_second": 13.963,
      "eval_steps_per_second": 0.223,
      "step": 64
    },
    {
      "epoch": 0.5058365758754864,
      "grad_norm": 0.6249987093009363,
      "learning_rate": 9.794871794871796e-07,
      "loss": 1.1365,
      "step": 65
    },
    {
      "epoch": 0.5136186770428015,
      "grad_norm": 0.5714052179303046,
      "learning_rate": 9.788768675940237e-07,
      "loss": 1.1486,
      "step": 66
    },
    {
      "epoch": 0.5214007782101168,
      "grad_norm": 0.6266253830635832,
      "learning_rate": 9.782608695652173e-07,
      "loss": 1.1297,
      "step": 67
    },
    {
      "epoch": 0.5291828793774319,
      "grad_norm": 0.6413361931814175,
      "learning_rate": 9.776391055642225e-07,
      "loss": 1.1346,
      "step": 68
    },
    {
      "epoch": 0.5369649805447471,
      "grad_norm": 0.6401174657840715,
      "learning_rate": 9.770114942528735e-07,
      "loss": 1.1443,
      "step": 69
    },
    {
      "epoch": 0.5447470817120622,
      "grad_norm": 0.6160976711769636,
      "learning_rate": 9.763779527559055e-07,
      "loss": 1.138,
      "step": 70
    },
    {
      "epoch": 0.5525291828793775,
      "grad_norm": 0.6234000690415658,
      "learning_rate": 9.757383966244725e-07,
      "loss": 1.1018,
      "step": 71
    },
    {
      "epoch": 0.5603112840466926,
      "grad_norm": 0.6528376037799454,
      "learning_rate": 9.75092739798622e-07,
      "loss": 1.1059,
      "step": 72
    },
    {
      "epoch": 0.5680933852140078,
      "grad_norm": 0.5652314830088928,
      "learning_rate": 9.744408945686901e-07,
      "loss": 1.1222,
      "step": 73
    },
    {
      "epoch": 0.5758754863813229,
      "grad_norm": 0.585673991341348,
      "learning_rate": 9.737827715355804e-07,
      "loss": 1.1067,
      "step": 74
    },
    {
      "epoch": 0.5836575875486382,
      "grad_norm": 0.5888031772006102,
      "learning_rate": 9.731182795698924e-07,
      "loss": 1.1495,
      "step": 75
    },
    {
      "epoch": 0.5914396887159533,
      "grad_norm": 0.6220423369607407,
      "learning_rate": 9.72447325769854e-07,
      "loss": 1.1197,
      "step": 76
    },
    {
      "epoch": 0.5992217898832685,
      "grad_norm": 0.6112403683619732,
      "learning_rate": 9.71769815418024e-07,
      "loss": 1.1382,
      "step": 77
    },
    {
      "epoch": 0.6070038910505836,
      "grad_norm": 0.6459405223806135,
      "learning_rate": 9.710856519367158e-07,
      "loss": 1.1518,
      "step": 78
    },
    {
      "epoch": 0.6147859922178989,
      "grad_norm": 0.6209769863467987,
      "learning_rate": 9.703947368421054e-07,
      "loss": 1.1239,
      "step": 79
    },
    {
      "epoch": 0.622568093385214,
      "grad_norm": 0.5843668163519747,
      "learning_rate": 9.696969696969695e-07,
      "loss": 1.1433,
      "step": 80
    },
    {
      "epoch": 0.6303501945525292,
      "grad_norm": 0.5969841579813842,
      "learning_rate": 9.689922480620153e-07,
      "loss": 1.1312,
      "step": 81
    },
    {
      "epoch": 0.6381322957198443,
      "grad_norm": 0.5567475366696957,
      "learning_rate": 9.68280467445743e-07,
      "loss": 1.0717,
      "step": 82
    },
    {
      "epoch": 0.6459143968871596,
      "grad_norm": 0.8841164939701298,
      "learning_rate": 9.675615212527965e-07,
      "loss": 1.1229,
      "step": 83
    },
    {
      "epoch": 0.6536964980544747,
      "grad_norm": 0.6021627871478876,
      "learning_rate": 9.668353007307475e-07,
      "loss": 1.119,
      "step": 84
    },
    {
      "epoch": 0.6614785992217899,
      "grad_norm": 0.561817882301385,
      "learning_rate": 9.661016949152542e-07,
      "loss": 1.1298,
      "step": 85
    },
    {
      "epoch": 0.669260700389105,
      "grad_norm": 0.6382338925455957,
      "learning_rate": 9.653605905735377e-07,
      "loss": 1.1168,
      "step": 86
    },
    {
      "epoch": 0.6770428015564203,
      "grad_norm": 0.602322633909128,
      "learning_rate": 9.646118721461186e-07,
      "loss": 1.1291,
      "step": 87
    },
    {
      "epoch": 0.6848249027237354,
      "grad_norm": 0.5990302538351283,
      "learning_rate": 9.63855421686747e-07,
      "loss": 1.1332,
      "step": 88
    },
    {
      "epoch": 0.6926070038910506,
      "grad_norm": 0.5869777798515858,
      "learning_rate": 9.630911188004613e-07,
      "loss": 1.1404,
      "step": 89
    },
    {
      "epoch": 0.7003891050583657,
      "grad_norm": 0.5933684142522954,
      "learning_rate": 9.623188405797102e-07,
      "loss": 1.1528,
      "step": 90
    },
    {
      "epoch": 0.708171206225681,
      "grad_norm": 0.6118209958752469,
      "learning_rate": 9.615384615384615e-07,
      "loss": 1.1486,
      "step": 91
    },
    {
      "epoch": 0.7159533073929961,
      "grad_norm": 0.626189163793506,
      "learning_rate": 9.607498535442295e-07,
      "loss": 1.1079,
      "step": 92
    },
    {
      "epoch": 0.7237354085603113,
      "grad_norm": 0.5824843670586056,
      "learning_rate": 9.599528857479386e-07,
      "loss": 1.1471,
      "step": 93
    },
    {
      "epoch": 0.7315175097276264,
      "grad_norm": 0.6045894845802466,
      "learning_rate": 9.591474245115454e-07,
      "loss": 1.0899,
      "step": 94
    },
    {
      "epoch": 0.7392996108949417,
      "grad_norm": 0.5453528811988809,
      "learning_rate": 9.583333333333334e-07,
      "loss": 1.1232,
      "step": 95
    },
    {
      "epoch": 0.7470817120622568,
      "grad_norm": 0.6430932607963977,
      "learning_rate": 9.57510472770796e-07,
      "loss": 1.0917,
      "step": 96
    },
    {
      "epoch": 0.7470817120622568,
      "eval_loss": 0.9749420881271362,
      "eval_runtime": 194.1545,
      "eval_samples_per_second": 13.886,
      "eval_steps_per_second": 0.221,
      "step": 96
    },
    {
      "epoch": 0.754863813229572,
      "grad_norm": 0.5852779384368416,
      "learning_rate": 9.566787003610106e-07,
      "loss": 1.1517,
      "step": 97
    },
    {
      "epoch": 0.7626459143968871,
      "grad_norm": 0.6409842274490922,
      "learning_rate": 9.55837870538415e-07,
      "loss": 1.1254,
      "step": 98
    },
    {
      "epoch": 0.7704280155642024,
      "grad_norm": 0.5639528294869124,
      "learning_rate": 9.549878345498782e-07,
      "loss": 1.1121,
      "step": 99
    },
    {
      "epoch": 0.7782101167315175,
      "grad_norm": 0.6213244609041039,
      "learning_rate": 9.541284403669725e-07,
      "loss": 1.0915,
      "step": 100
    },
    {
      "epoch": 0.7859922178988327,
      "grad_norm": 0.6551114483360119,
      "learning_rate": 9.53259532595326e-07,
      "loss": 1.1534,
      "step": 101
    },
    {
      "epoch": 0.7937743190661478,
      "grad_norm": 0.6413194021766461,
      "learning_rate": 9.523809523809523e-07,
      "loss": 1.1432,
      "step": 102
    },
    {
      "epoch": 0.8015564202334631,
      "grad_norm": 0.5912246112879433,
      "learning_rate": 9.514925373134328e-07,
      "loss": 1.1856,
      "step": 103
    },
    {
      "epoch": 0.8093385214007782,
      "grad_norm": 0.5929209222521526,
      "learning_rate": 9.505941213258286e-07,
      "loss": 1.1097,
      "step": 104
    },
    {
      "epoch": 0.8171206225680934,
      "grad_norm": 0.5781185505602303,
      "learning_rate": 9.496855345911948e-07,
      "loss": 1.093,
      "step": 105
    },
    {
      "epoch": 0.8249027237354085,
      "grad_norm": 0.5850063235452896,
      "learning_rate": 9.487666034155598e-07,
      "loss": 1.1053,
      "step": 106
    },
    {
      "epoch": 0.8326848249027238,
      "grad_norm": 0.5557542208140502,
      "learning_rate": 9.478371501272264e-07,
      "loss": 1.1072,
      "step": 107
    },
    {
      "epoch": 0.8404669260700389,
      "grad_norm": 0.6939378070209432,
      "learning_rate": 9.46896992962252e-07,
      "loss": 1.1557,
      "step": 108
    },
    {
      "epoch": 0.8482490272373541,
      "grad_norm": 0.5821602482631876,
      "learning_rate": 9.459459459459459e-07,
      "loss": 1.1008,
      "step": 109
    },
    {
      "epoch": 0.8560311284046692,
      "grad_norm": 0.5641222765431608,
      "learning_rate": 9.449838187702264e-07,
      "loss": 1.1066,
      "step": 110
    },
    {
      "epoch": 0.8638132295719845,
      "grad_norm": 0.6073853509255491,
      "learning_rate": 9.440104166666666e-07,
      "loss": 1.1347,
      "step": 111
    },
    {
      "epoch": 0.8715953307392996,
      "grad_norm": 0.6652073708936578,
      "learning_rate": 9.430255402750491e-07,
      "loss": 1.1539,
      "step": 112
    },
    {
      "epoch": 0.8793774319066148,
      "grad_norm": 0.5779065641712691,
      "learning_rate": 9.420289855072464e-07,
      "loss": 1.1286,
      "step": 113
    },
    {
      "epoch": 0.8871595330739299,
      "grad_norm": 1.0893325101395284,
      "learning_rate": 9.410205434062292e-07,
      "loss": 1.1327,
      "step": 114
    },
    {
      "epoch": 0.8949416342412452,
      "grad_norm": 0.5897769203979899,
      "learning_rate": 9.399999999999999e-07,
      "loss": 1.1083,
      "step": 115
    },
    {
      "epoch": 0.9027237354085603,
      "grad_norm": 0.5962317172776513,
      "learning_rate": 9.389671361502347e-07,
      "loss": 1.0842,
      "step": 116
    },
    {
      "epoch": 0.9105058365758755,
      "grad_norm": 0.5955932544091112,
      "learning_rate": 9.379217273954116e-07,
      "loss": 1.1366,
      "step": 117
    },
    {
      "epoch": 0.9182879377431906,
      "grad_norm": 0.5949693376391756,
      "learning_rate": 9.368635437881874e-07,
      "loss": 1.1094,
      "step": 118
    },
    {
      "epoch": 0.9260700389105059,
      "grad_norm": 0.6044514449577904,
      "learning_rate": 9.357923497267759e-07,
      "loss": 1.1639,
      "step": 119
    },
    {
      "epoch": 0.933852140077821,
      "grad_norm": 0.625428671903296,
      "learning_rate": 9.347079037800687e-07,
      "loss": 1.1054,
      "step": 120
    },
    {
      "epoch": 0.9416342412451362,
      "grad_norm": 0.5297520430435139,
      "learning_rate": 9.33609958506224e-07,
      "loss": 1.1396,
      "step": 121
    },
    {
      "epoch": 0.9494163424124513,
      "grad_norm": 0.604395748227856,
      "learning_rate": 9.324982602644397e-07,
      "loss": 1.1297,
      "step": 122
    },
    {
      "epoch": 0.9571984435797666,
      "grad_norm": 0.5935060150814615,
      "learning_rate": 9.313725490196079e-07,
      "loss": 1.1327,
      "step": 123
    },
    {
      "epoch": 0.9649805447470817,
      "grad_norm": 0.6213246371577336,
      "learning_rate": 9.30232558139535e-07,
      "loss": 1.1655,
      "step": 124
    },
    {
      "epoch": 0.9727626459143969,
      "grad_norm": 0.5459987203799985,
      "learning_rate": 9.290780141843972e-07,
      "loss": 1.1119,
      "step": 125
    },
    {
      "epoch": 0.980544747081712,
      "grad_norm": 0.5862633284111678,
      "learning_rate": 9.279086366880799e-07,
      "loss": 1.1102,
      "step": 126
    },
    {
      "epoch": 0.9883268482490273,
      "grad_norm": 0.5749701605073742,
      "learning_rate": 9.267241379310344e-07,
      "loss": 1.1215,
      "step": 127
    },
    {
      "epoch": 0.9961089494163424,
      "grad_norm": 0.5608948491944076,
      "learning_rate": 9.25524222704266e-07,
      "loss": 1.1171,
      "step": 128
    },
    {
      "epoch": 0.9961089494163424,
      "eval_loss": 0.9638092517852783,
      "eval_runtime": 193.8483,
      "eval_samples_per_second": 13.908,
      "eval_steps_per_second": 0.222,
      "step": 128
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5608948491944076,
      "learning_rate": 9.243085880640464e-07,
      "loss": 1.1281,
      "step": 129
    },
    {
      "epoch": 1.0077821011673151,
      "grad_norm": 0.8826714731817153,
      "learning_rate": 9.230769230769229e-07,
      "loss": 1.1385,
      "step": 130
    },
    {
      "epoch": 1.0155642023346303,
      "grad_norm": 0.585537303127348,
      "learning_rate": 9.218289085545723e-07,
      "loss": 1.0753,
      "step": 131
    },
    {
      "epoch": 1.0233463035019454,
      "grad_norm": 0.574845853397158,
      "learning_rate": 9.205642167780252e-07,
      "loss": 1.1466,
      "step": 132
    },
    {
      "epoch": 1.0311284046692606,
      "grad_norm": 0.573244467973897,
      "learning_rate": 9.192825112107622e-07,
      "loss": 1.1359,
      "step": 133
    },
    {
      "epoch": 1.038910505836576,
      "grad_norm": 0.6964714993014424,
      "learning_rate": 9.179834462001504e-07,
      "loss": 1.1122,
      "step": 134
    },
    {
      "epoch": 1.046692607003891,
      "grad_norm": 0.641322046313728,
      "learning_rate": 9.166666666666665e-07,
      "loss": 1.0825,
      "step": 135
    },
    {
      "epoch": 1.0544747081712063,
      "grad_norm": 0.5360716115631284,
      "learning_rate": 9.153318077803201e-07,
      "loss": 1.1006,
      "step": 136
    },
    {
      "epoch": 1.0622568093385214,
      "grad_norm": 0.5816374932590664,
      "learning_rate": 9.139784946236559e-07,
      "loss": 1.1116,
      "step": 137
    },
    {
      "epoch": 1.0700389105058365,
      "grad_norm": 0.6372126076146449,
      "learning_rate": 9.126063418406805e-07,
      "loss": 1.0979,
      "step": 138
    },
    {
      "epoch": 1.0778210116731517,
      "grad_norm": 0.5578000693621826,
      "learning_rate": 9.11214953271028e-07,
      "loss": 1.1263,
      "step": 139
    },
    {
      "epoch": 1.0856031128404668,
      "grad_norm": 0.5923651609485125,
      "learning_rate": 9.098039215686274e-07,
      "loss": 1.0966,
      "step": 140
    },
    {
      "epoch": 1.0933852140077822,
      "grad_norm": 0.533195556847129,
      "learning_rate": 9.083728278041073e-07,
      "loss": 1.1349,
      "step": 141
    },
    {
      "epoch": 1.1011673151750974,
      "grad_norm": 0.6329974401580136,
      "learning_rate": 9.069212410501193e-07,
      "loss": 1.1072,
      "step": 142
    },
    {
      "epoch": 1.1089494163424125,
      "grad_norm": 0.5546033043372056,
      "learning_rate": 9.054487179487179e-07,
      "loss": 1.1565,
      "step": 143
    },
    {
      "epoch": 1.1167315175097277,
      "grad_norm": 0.5975088088440533,
      "learning_rate": 9.03954802259887e-07,
      "loss": 1.0724,
      "step": 144
    },
    {
      "epoch": 1.1245136186770428,
      "grad_norm": 0.57801276427658,
      "learning_rate": 9.024390243902439e-07,
      "loss": 1.1346,
      "step": 145
    },
    {
      "epoch": 1.132295719844358,
      "grad_norm": 0.5879398504293435,
      "learning_rate": 9.009009009009008e-07,
      "loss": 1.159,
      "step": 146
    },
    {
      "epoch": 1.140077821011673,
      "grad_norm": 0.593628488224272,
      "learning_rate": 8.993399339933992e-07,
      "loss": 1.1464,
      "step": 147
    },
    {
      "epoch": 1.1478599221789882,
      "grad_norm": 0.5593315767964653,
      "learning_rate": 8.977556109725684e-07,
      "loss": 1.1054,
      "step": 148
    },
    {
      "epoch": 1.1556420233463034,
      "grad_norm": 0.5787699146029086,
      "learning_rate": 8.96147403685092e-07,
      "loss": 1.096,
      "step": 149
    },
    {
      "epoch": 1.1634241245136188,
      "grad_norm": 0.5877657497768165,
      "learning_rate": 8.945147679324893e-07,
      "loss": 1.0887,
      "step": 150
    },
    {
      "epoch": 1.171206225680934,
      "grad_norm": 0.6197879903738175,
      "learning_rate": 8.928571428571428e-07,
      "loss": 1.1514,
      "step": 151
    },
    {
      "epoch": 1.178988326848249,
      "grad_norm": 0.5393516857845513,
      "learning_rate": 8.911739502999142e-07,
      "loss": 1.1215,
      "step": 152
    },
    {
      "epoch": 1.1867704280155642,
      "grad_norm": 0.5758698948439026,
      "learning_rate": 8.894645941278064e-07,
      "loss": 1.0557,
      "step": 153
    },
    {
      "epoch": 1.1945525291828794,
      "grad_norm": 0.5870780530298951,
      "learning_rate": 8.877284595300261e-07,
      "loss": 1.0892,
      "step": 154
    },
    {
      "epoch": 1.2023346303501945,
      "grad_norm": 0.5933780513917563,
      "learning_rate": 8.859649122807017e-07,
      "loss": 1.1125,
      "step": 155
    },
    {
      "epoch": 1.2101167315175096,
      "grad_norm": 0.5615488624761017,
      "learning_rate": 8.841732979664014e-07,
      "loss": 1.1394,
      "step": 156
    },
    {
      "epoch": 1.217898832684825,
      "grad_norm": 0.5960612312151845,
      "learning_rate": 8.823529411764706e-07,
      "loss": 1.0859,
      "step": 157
    },
    {
      "epoch": 1.2256809338521402,
      "grad_norm": 0.6325808125841859,
      "learning_rate": 8.80503144654088e-07,
      "loss": 1.1128,
      "step": 158
    },
    {
      "epoch": 1.2334630350194553,
      "grad_norm": 0.6076576722454798,
      "learning_rate": 8.78623188405797e-07,
      "loss": 1.1092,
      "step": 159
    },
    {
      "epoch": 1.2412451361867705,
      "grad_norm": 0.5821560609671981,
      "learning_rate": 8.767123287671233e-07,
      "loss": 1.0963,
      "step": 160
    },
    {
      "epoch": 1.2412451361867705,
      "eval_loss": 0.9557842016220093,
      "eval_runtime": 193.7527,
      "eval_samples_per_second": 13.915,
      "eval_steps_per_second": 0.222,
      "step": 160
    },
    {
      "epoch": 1.2490272373540856,
      "grad_norm": 0.5621223931485095,
      "learning_rate": 8.747697974217309e-07,
      "loss": 1.1338,
      "step": 161
    },
    {
      "epoch": 1.2568093385214008,
      "grad_norm": 0.5962800493628467,
      "learning_rate": 8.727948003714019e-07,
      "loss": 1.1388,
      "step": 162
    },
    {
      "epoch": 1.264591439688716,
      "grad_norm": 0.5814349430158473,
      "learning_rate": 8.707865168539326e-07,
      "loss": 1.1038,
      "step": 163
    },
    {
      "epoch": 1.272373540856031,
      "grad_norm": 0.6004347939909851,
      "learning_rate": 8.687440982058545e-07,
      "loss": 1.143,
      "step": 164
    },
    {
      "epoch": 1.2801556420233462,
      "grad_norm": 0.5948532065914537,
      "learning_rate": 8.666666666666666e-07,
      "loss": 1.155,
      "step": 165
    },
    {
      "epoch": 1.2879377431906613,
      "grad_norm": 0.5570114843646816,
      "learning_rate": 8.645533141210375e-07,
      "loss": 1.095,
      "step": 166
    },
    {
      "epoch": 1.2957198443579767,
      "grad_norm": 0.6592254796476543,
      "learning_rate": 8.624031007751938e-07,
      "loss": 1.1114,
      "step": 167
    },
    {
      "epoch": 1.3035019455252919,
      "grad_norm": 0.5375793451912569,
      "learning_rate": 8.602150537634409e-07,
      "loss": 1.1018,
      "step": 168
    },
    {
      "epoch": 1.311284046692607,
      "grad_norm": 0.5774524273066066,
      "learning_rate": 8.579881656804733e-07,
      "loss": 1.0866,
      "step": 169
    },
    {
      "epoch": 1.3190661478599222,
      "grad_norm": 0.5767675794480738,
      "learning_rate": 8.557213930348258e-07,
      "loss": 1.0919,
      "step": 170
    },
    {
      "epoch": 1.3268482490272373,
      "grad_norm": 0.5424563326577124,
      "learning_rate": 8.534136546184737e-07,
      "loss": 1.097,
      "step": 171
    },
    {
      "epoch": 1.3346303501945525,
      "grad_norm": 0.5504324773913235,
      "learning_rate": 8.510638297872341e-07,
      "loss": 1.1088,
      "step": 172
    },
    {
      "epoch": 1.3424124513618678,
      "grad_norm": 0.5631592132878254,
      "learning_rate": 8.486707566462167e-07,
      "loss": 1.141,
      "step": 173
    },
    {
      "epoch": 1.350194552529183,
      "grad_norm": 0.5987091201900138,
      "learning_rate": 8.462332301341588e-07,
      "loss": 1.1352,
      "step": 174
    },
    {
      "epoch": 1.3579766536964981,
      "grad_norm": 0.5644686177164949,
      "learning_rate": 8.4375e-07,
      "loss": 1.1086,
      "step": 175
    },
    {
      "epoch": 1.3657587548638133,
      "grad_norm": 0.5603933667416149,
      "learning_rate": 8.412197686645635e-07,
      "loss": 1.1066,
      "step": 176
    },
    {
      "epoch": 1.3735408560311284,
      "grad_norm": 1.1467757879130558,
      "learning_rate": 8.386411889596603e-07,
      "loss": 1.1587,
      "step": 177
    },
    {
      "epoch": 1.3813229571984436,
      "grad_norm": 0.7887321457214312,
      "learning_rate": 8.360128617363344e-07,
      "loss": 1.088,
      "step": 178
    },
    {
      "epoch": 1.3891050583657587,
      "grad_norm": 1.3469817773930703,
      "learning_rate": 8.333333333333332e-07,
      "loss": 1.0843,
      "step": 179
    },
    {
      "epoch": 1.3968871595330739,
      "grad_norm": 0.5467899896948426,
      "learning_rate": 8.306010928961747e-07,
      "loss": 1.1669,
      "step": 180
    },
    {
      "epoch": 1.404669260700389,
      "grad_norm": 0.5788709158633432,
      "learning_rate": 8.278145695364237e-07,
      "loss": 1.1163,
      "step": 181
    },
    {
      "epoch": 1.4124513618677041,
      "grad_norm": 0.5711519564174999,
      "learning_rate": 8.249721293199554e-07,
      "loss": 1.1085,
      "step": 182
    },
    {
      "epoch": 1.4202334630350195,
      "grad_norm": 0.5648595416368181,
      "learning_rate": 8.220720720720721e-07,
      "loss": 1.0845,
      "step": 183
    },
    {
      "epoch": 1.4280155642023347,
      "grad_norm": 0.525420807610935,
      "learning_rate": 8.191126279863481e-07,
      "loss": 1.1037,
      "step": 184
    },
    {
      "epoch": 1.4357976653696498,
      "grad_norm": 0.6990978764976382,
      "learning_rate": 8.160919540229884e-07,
      "loss": 1.0672,
      "step": 185
    },
    {
      "epoch": 1.443579766536965,
      "grad_norm": 0.565722083537725,
      "learning_rate": 8.130081300813006e-07,
      "loss": 1.1214,
      "step": 186
    },
    {
      "epoch": 1.45136186770428,
      "grad_norm": 0.6283006226852244,
      "learning_rate": 8.098591549295774e-07,
      "loss": 1.0992,
      "step": 187
    },
    {
      "epoch": 1.4591439688715953,
      "grad_norm": 0.5550197869791744,
      "learning_rate": 8.066429418742585e-07,
      "loss": 1.1136,
      "step": 188
    },
    {
      "epoch": 1.4669260700389106,
      "grad_norm": 0.5659938483591545,
      "learning_rate": 8.03357314148681e-07,
      "loss": 1.0884,
      "step": 189
    },
    {
      "epoch": 1.4747081712062258,
      "grad_norm": 0.5872567653519262,
      "learning_rate": 8e-07,
      "loss": 1.1283,
      "step": 190
    },
    {
      "epoch": 1.482490272373541,
      "grad_norm": 0.6010641188429918,
      "learning_rate": 7.965686274509804e-07,
      "loss": 1.0959,
      "step": 191
    },
    {
      "epoch": 1.490272373540856,
      "grad_norm": 0.559777631958916,
      "learning_rate": 7.930607187112763e-07,
      "loss": 1.1047,
      "step": 192
    },
    {
      "epoch": 1.490272373540856,
      "eval_loss": 0.949611485004425,
      "eval_runtime": 193.3019,
      "eval_samples_per_second": 13.947,
      "eval_steps_per_second": 0.222,
      "step": 192
    },
    {
      "epoch": 1.4980544747081712,
      "grad_norm": 0.5608029800864122,
      "learning_rate": 7.894736842105262e-07,
      "loss": 1.0798,
      "step": 193
    },
    {
      "epoch": 1.5058365758754864,
      "grad_norm": 0.5765576143527928,
      "learning_rate": 7.85804816223067e-07,
      "loss": 1.0887,
      "step": 194
    },
    {
      "epoch": 1.5136186770428015,
      "grad_norm": 0.5783903086304087,
      "learning_rate": 7.82051282051282e-07,
      "loss": 1.1015,
      "step": 195
    },
    {
      "epoch": 1.5214007782101167,
      "grad_norm": 0.5252594928277367,
      "learning_rate": 7.782101167315173e-07,
      "loss": 1.0802,
      "step": 196
    },
    {
      "epoch": 1.5291828793774318,
      "grad_norm": 0.5435740719293682,
      "learning_rate": 7.742782152230972e-07,
      "loss": 1.0874,
      "step": 197
    },
    {
      "epoch": 1.536964980544747,
      "grad_norm": 0.5369255828107669,
      "learning_rate": 7.702523240371846e-07,
      "loss": 1.095,
      "step": 198
    },
    {
      "epoch": 1.544747081712062,
      "grad_norm": 0.6850191931654889,
      "learning_rate": 7.661290322580645e-07,
      "loss": 1.0912,
      "step": 199
    },
    {
      "epoch": 1.5525291828793775,
      "grad_norm": 0.5688231956299873,
      "learning_rate": 7.619047619047617e-07,
      "loss": 1.0552,
      "step": 200
    },
    {
      "epoch": 1.5603112840466926,
      "grad_norm": 0.5928997625619618,
      "learning_rate": 7.575757575757575e-07,
      "loss": 1.0621,
      "step": 201
    },
    {
      "epoch": 1.5680933852140078,
      "grad_norm": 0.7716125599428396,
      "learning_rate": 7.531380753138075e-07,
      "loss": 1.0758,
      "step": 202
    },
    {
      "epoch": 1.575875486381323,
      "grad_norm": 0.5629855625488145,
      "learning_rate": 7.48587570621469e-07,
      "loss": 1.0606,
      "step": 203
    },
    {
      "epoch": 1.5836575875486383,
      "grad_norm": 0.5635371246521241,
      "learning_rate": 7.439198855507868e-07,
      "loss": 1.1029,
      "step": 204
    },
    {
      "epoch": 1.5914396887159534,
      "grad_norm": 0.6498217881509594,
      "learning_rate": 7.391304347826086e-07,
      "loss": 1.0737,
      "step": 205
    },
    {
      "epoch": 1.5992217898832686,
      "grad_norm": 0.5578772825539674,
      "learning_rate": 7.342143906020557e-07,
      "loss": 1.0938,
      "step": 206
    },
    {
      "epoch": 1.6070038910505837,
      "grad_norm": 0.6895801155757268,
      "learning_rate": 7.291666666666667e-07,
      "loss": 1.108,
      "step": 207
    },
    {
      "epoch": 1.6147859922178989,
      "grad_norm": 0.5472071760512172,
      "learning_rate": 7.239819004524887e-07,
      "loss": 1.0799,
      "step": 208
    },
    {
      "epoch": 1.622568093385214,
      "grad_norm": 0.5551855311336273,
      "learning_rate": 7.186544342507645e-07,
      "loss": 1.1011,
      "step": 209
    },
    {
      "epoch": 1.6303501945525292,
      "grad_norm": 0.5922020624280246,
      "learning_rate": 7.131782945736434e-07,
      "loss": 1.0883,
      "step": 210
    },
    {
      "epoch": 1.6381322957198443,
      "grad_norm": 0.5855500909084618,
      "learning_rate": 7.075471698113208e-07,
      "loss": 1.0277,
      "step": 211
    },
    {
      "epoch": 1.6459143968871595,
      "grad_norm": 0.5436280978302126,
      "learning_rate": 7.017543859649121e-07,
      "loss": 1.0829,
      "step": 212
    },
    {
      "epoch": 1.6536964980544746,
      "grad_norm": 0.568803772556928,
      "learning_rate": 6.957928802588997e-07,
      "loss": 1.0778,
      "step": 213
    },
    {
      "epoch": 1.6614785992217898,
      "grad_norm": 0.5954446162983249,
      "learning_rate": 6.89655172413793e-07,
      "loss": 1.0885,
      "step": 214
    },
    {
      "epoch": 1.669260700389105,
      "grad_norm": 0.6318388963180205,
      "learning_rate": 6.833333333333333e-07,
      "loss": 1.0761,
      "step": 215
    },
    {
      "epoch": 1.6770428015564203,
      "grad_norm": 1.0424216403770146,
      "learning_rate": 6.768189509306259e-07,
      "loss": 1.0882,
      "step": 216
    },
    {
      "epoch": 1.6848249027237354,
      "grad_norm": 0.5848369566451875,
      "learning_rate": 6.701030927835052e-07,
      "loss": 1.0933,
      "step": 217
    },
    {
      "epoch": 1.6926070038910506,
      "grad_norm": 0.6540113258331898,
      "learning_rate": 6.63176265270506e-07,
      "loss": 1.0997,
      "step": 218
    },
    {
      "epoch": 1.7003891050583657,
      "grad_norm": 0.5945247307598128,
      "learning_rate": 6.560283687943263e-07,
      "loss": 1.1121,
      "step": 219
    },
    {
      "epoch": 1.708171206225681,
      "grad_norm": 0.5812576783107466,
      "learning_rate": 6.486486486486486e-07,
      "loss": 1.1089,
      "step": 220
    },
    {
      "epoch": 1.7159533073929962,
      "grad_norm": 0.5422687962188623,
      "learning_rate": 6.41025641025641e-07,
      "loss": 1.0689,
      "step": 221
    },
    {
      "epoch": 1.7237354085603114,
      "grad_norm": 0.5655113478395188,
      "learning_rate": 6.33147113594041e-07,
      "loss": 1.1083,
      "step": 222
    },
    {
      "epoch": 1.7315175097276265,
      "grad_norm": 0.5479997273898842,
      "learning_rate": 6.249999999999999e-07,
      "loss": 1.0495,
      "step": 223
    },
    {
      "epoch": 1.7392996108949417,
      "grad_norm": 0.6082276343842562,
      "learning_rate": 6.165703275529864e-07,
      "loss": 1.0847,
      "step": 224
    },
    {
      "epoch": 1.7392996108949417,
      "eval_loss": 0.9448344707489014,
      "eval_runtime": 193.8348,
      "eval_samples_per_second": 13.909,
      "eval_steps_per_second": 0.222,
      "step": 224
    },
    {
      "epoch": 1.7470817120622568,
      "grad_norm": 0.5456728126246078,
      "learning_rate": 6.078431372549019e-07,
      "loss": 1.0543,
      "step": 225
    },
    {
      "epoch": 1.754863813229572,
      "grad_norm": 0.8395615938618125,
      "learning_rate": 5.988023952095807e-07,
      "loss": 1.1133,
      "step": 226
    },
    {
      "epoch": 1.7626459143968871,
      "grad_norm": 0.5699433030581755,
      "learning_rate": 5.89430894308943e-07,
      "loss": 1.0878,
      "step": 227
    },
    {
      "epoch": 1.7704280155642023,
      "grad_norm": 0.5372956205386954,
      "learning_rate": 5.797101449275362e-07,
      "loss": 1.0749,
      "step": 228
    },
    {
      "epoch": 1.7782101167315174,
      "grad_norm": 0.5485335276065648,
      "learning_rate": 5.696202531645569e-07,
      "loss": 1.056,
      "step": 229
    },
    {
      "epoch": 1.7859922178988326,
      "grad_norm": 0.5739239028380502,
      "learning_rate": 5.591397849462365e-07,
      "loss": 1.1175,
      "step": 230
    },
    {
      "epoch": 1.7937743190661477,
      "grad_norm": 0.5674136555108149,
      "learning_rate": 5.482456140350876e-07,
      "loss": 1.1061,
      "step": 231
    },
    {
      "epoch": 1.801556420233463,
      "grad_norm": 0.6414824329123738,
      "learning_rate": 5.369127516778523e-07,
      "loss": 1.1502,
      "step": 232
    },
    {
      "epoch": 1.8093385214007782,
      "grad_norm": 0.5567692960590215,
      "learning_rate": 5.251141552511415e-07,
      "loss": 1.074,
      "step": 233
    },
    {
      "epoch": 1.8171206225680934,
      "grad_norm": 0.5203307823955872,
      "learning_rate": 5.128205128205127e-07,
      "loss": 1.0576,
      "step": 234
    },
    {
      "epoch": 1.8249027237354085,
      "grad_norm": 0.5480039922419879,
      "learning_rate": 5e-07,
      "loss": 1.0692,
      "step": 235
    },
    {
      "epoch": 1.8326848249027239,
      "grad_norm": 0.6602968949965664,
      "learning_rate": 4.8661800486618e-07,
      "loss": 1.0716,
      "step": 236
    },
    {
      "epoch": 1.840466926070039,
      "grad_norm": 0.5621257570421472,
      "learning_rate": 4.72636815920398e-07,
      "loss": 1.1222,
      "step": 237
    },
    {
      "epoch": 1.8482490272373542,
      "grad_norm": 0.5778853314353605,
      "learning_rate": 4.5801526717557246e-07,
      "loss": 1.0651,
      "step": 238
    },
    {
      "epoch": 1.8560311284046693,
      "grad_norm": 0.5284341924121511,
      "learning_rate": 4.4270833333333337e-07,
      "loss": 1.0708,
      "step": 239
    },
    {
      "epoch": 1.8638132295719845,
      "grad_norm": 0.5965113916130589,
      "learning_rate": 4.266666666666667e-07,
      "loss": 1.0981,
      "step": 240
    },
    {
      "epoch": 1.8715953307392996,
      "grad_norm": 0.5597034969209712,
      "learning_rate": 4.098360655737704e-07,
      "loss": 1.1179,
      "step": 241
    },
    {
      "epoch": 1.8793774319066148,
      "grad_norm": 0.5536241929831267,
      "learning_rate": 3.92156862745098e-07,
      "loss": 1.0935,
      "step": 242
    },
    {
      "epoch": 1.88715953307393,
      "grad_norm": 0.5584595178829068,
      "learning_rate": 3.7356321839080463e-07,
      "loss": 1.1041,
      "step": 243
    },
    {
      "epoch": 1.894941634241245,
      "grad_norm": 0.5427158370327506,
      "learning_rate": 3.539823008849558e-07,
      "loss": 1.0756,
      "step": 244
    },
    {
      "epoch": 1.9027237354085602,
      "grad_norm": 0.5336572931407305,
      "learning_rate": 3.333333333333333e-07,
      "loss": 1.0514,
      "step": 245
    },
    {
      "epoch": 1.9105058365758754,
      "grad_norm": 0.5369948018962315,
      "learning_rate": 3.1152647975077885e-07,
      "loss": 1.1033,
      "step": 246
    },
    {
      "epoch": 1.9182879377431905,
      "grad_norm": 0.5717043508183633,
      "learning_rate": 2.8846153846153846e-07,
      "loss": 1.0766,
      "step": 247
    },
    {
      "epoch": 1.9260700389105059,
      "grad_norm": 0.5722908601877614,
      "learning_rate": 2.64026402640264e-07,
      "loss": 1.13,
      "step": 248
    },
    {
      "epoch": 1.933852140077821,
      "grad_norm": 0.5419564077709611,
      "learning_rate": 2.3809523809523806e-07,
      "loss": 1.0729,
      "step": 249
    },
    {
      "epoch": 1.9416342412451362,
      "grad_norm": 0.5886685089221407,
      "learning_rate": 2.1052631578947366e-07,
      "loss": 1.1071,
      "step": 250
    },
    {
      "epoch": 1.9494163424124513,
      "grad_norm": 0.5403936814687964,
      "learning_rate": 1.8115942028985505e-07,
      "loss": 1.0983,
      "step": 251
    },
    {
      "epoch": 1.9571984435797667,
      "grad_norm": 0.528388946685679,
      "learning_rate": 1.4981273408239696e-07,
      "loss": 1.1008,
      "step": 252
    },
    {
      "epoch": 1.9649805447470818,
      "grad_norm": 0.5354770235277335,
      "learning_rate": 1.1627906976744186e-07,
      "loss": 1.1341,
      "step": 253
    },
    {
      "epoch": 1.972762645914397,
      "grad_norm": 0.5252514289927873,
      "learning_rate": 8.032128514056224e-08,
      "loss": 1.0818,
      "step": 254
    },
    {
      "epoch": 1.9805447470817121,
      "grad_norm": 0.5858247065123809,
      "learning_rate": 4.166666666666666e-08,
      "loss": 1.0804,
      "step": 255
    },
    {
      "epoch": 1.9883268482490273,
      "grad_norm": 0.5257477128880242,
      "learning_rate": 0,
      "loss": 1.0901,
      "step": 256
    },
    {
      "epoch": 1.9883268482490273,
      "eval_loss": 0.9421924352645874,
      "eval_runtime": 193.7536,
      "eval_samples_per_second": 13.915,
      "eval_steps_per_second": 0.222,
      "step": 256
    }
  ],
  "logging_steps": 1,
  "max_steps": 256,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 64,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.554618867587219e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}