{
  "best_global_step": 250,
  "best_metric": 0.4610269367694855,
  "best_model_checkpoint": "/root/autodl-tmp/model/lora-textui/stage1_cap_func/checkpoint-250",
  "epoch": 2.4482338611449452,
  "eval_steps": 25,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0097442143727162,
      "grad_norm": 1.4819260835647583,
      "learning_rate": 0.0,
      "loss": 0.9971,
      "step": 1
    },
    {
      "epoch": 0.0194884287454324,
      "grad_norm": 1.1177597045898438,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.8357,
      "step": 2
    },
    {
      "epoch": 0.029232643118148598,
      "grad_norm": 1.5783437490463257,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.0968,
      "step": 3
    },
    {
      "epoch": 0.0389768574908648,
      "grad_norm": 1.3322019577026367,
      "learning_rate": 1.2e-05,
      "loss": 0.9436,
      "step": 4
    },
    {
      "epoch": 0.048721071863580996,
      "grad_norm": 1.1600998640060425,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.8405,
      "step": 5
    },
    {
      "epoch": 0.058465286236297195,
      "grad_norm": 3.9179673194885254,
      "learning_rate": 2e-05,
      "loss": 0.8719,
      "step": 6
    },
    {
      "epoch": 0.0682095006090134,
      "grad_norm": 0.7671970725059509,
      "learning_rate": 2.4e-05,
      "loss": 0.7487,
      "step": 7
    },
    {
      "epoch": 0.0779537149817296,
      "grad_norm": 0.6959292888641357,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.8104,
      "step": 8
    },
    {
      "epoch": 0.0876979293544458,
      "grad_norm": 0.4416683316230774,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.7356,
      "step": 9
    },
    {
      "epoch": 0.09744214372716199,
      "grad_norm": 0.48265624046325684,
      "learning_rate": 3.6e-05,
      "loss": 0.7642,
      "step": 10
    },
    {
      "epoch": 0.1071863580998782,
      "grad_norm": 0.45329996943473816,
      "learning_rate": 4e-05,
      "loss": 0.734,
      "step": 11
    },
    {
      "epoch": 0.11693057247259439,
      "grad_norm": 0.506803572177887,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.7155,
      "step": 12
    },
    {
      "epoch": 0.12667478684531058,
      "grad_norm": 0.5821135640144348,
      "learning_rate": 4.8e-05,
      "loss": 0.7207,
      "step": 13
    },
    {
      "epoch": 0.1364190012180268,
      "grad_norm": 0.6181040406227112,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.7882,
      "step": 14
    },
    {
      "epoch": 0.146163215590743,
      "grad_norm": 0.47155848145484924,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.7188,
      "step": 15
    },
    {
      "epoch": 0.1559074299634592,
      "grad_norm": 0.3960055112838745,
      "learning_rate": 6e-05,
      "loss": 0.7002,
      "step": 16
    },
    {
      "epoch": 0.1656516443361754,
      "grad_norm": 0.4034963846206665,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.7174,
      "step": 17
    },
    {
      "epoch": 0.1753958587088916,
      "grad_norm": 0.408160924911499,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.7085,
      "step": 18
    },
    {
      "epoch": 0.1851400730816078,
      "grad_norm": 0.4035159647464752,
      "learning_rate": 7.2e-05,
      "loss": 0.788,
      "step": 19
    },
    {
      "epoch": 0.19488428745432398,
      "grad_norm": 0.38708168268203735,
      "learning_rate": 7.6e-05,
      "loss": 0.6491,
      "step": 20
    },
    {
      "epoch": 0.2046285018270402,
      "grad_norm": 0.42144861817359924,
      "learning_rate": 8e-05,
      "loss": 0.6749,
      "step": 21
    },
    {
      "epoch": 0.2143727161997564,
      "grad_norm": 0.3642968237400055,
      "learning_rate": 8.4e-05,
      "loss": 0.6431,
      "step": 22
    },
    {
      "epoch": 0.2241169305724726,
      "grad_norm": 0.4132453203201294,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.6089,
      "step": 23
    },
    {
      "epoch": 0.23386114494518878,
      "grad_norm": 0.4148790240287781,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.605,
      "step": 24
    },
    {
      "epoch": 0.243605359317905,
      "grad_norm": 0.46465402841567993,
      "learning_rate": 9.6e-05,
      "loss": 0.6383,
      "step": 25
    },
    {
      "epoch": 0.243605359317905,
      "eval_loss": 0.6978875398635864,
      "eval_runtime": 116.3355,
      "eval_samples_per_second": 7.367,
      "eval_steps_per_second": 0.464,
      "step": 25
    },
    {
      "epoch": 0.25334957369062117,
      "grad_norm": 0.38448578119277954,
      "learning_rate": 0.0001,
      "loss": 0.6573,
      "step": 26
    },
    {
      "epoch": 0.2630937880633374,
      "grad_norm": 0.386096715927124,
      "learning_rate": 9.999512620046522e-05,
      "loss": 0.6503,
      "step": 27
    },
    {
      "epoch": 0.2728380024360536,
      "grad_norm": 0.4173428416252136,
      "learning_rate": 9.998050575201771e-05,
      "loss": 0.6056,
      "step": 28
    },
    {
      "epoch": 0.28258221680876977,
      "grad_norm": 0.3838996887207031,
      "learning_rate": 9.995614150494293e-05,
      "loss": 0.6291,
      "step": 29
    },
    {
      "epoch": 0.292326431181486,
      "grad_norm": 0.37374845147132874,
      "learning_rate": 9.992203820909906e-05,
      "loss": 0.5929,
      "step": 30
    },
    {
      "epoch": 0.3020706455542022,
      "grad_norm": 0.38990911841392517,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.6166,
      "step": 31
    },
    {
      "epoch": 0.3118148599269184,
      "grad_norm": 0.3717946410179138,
      "learning_rate": 9.982464296247522e-05,
      "loss": 0.631,
      "step": 32
    },
    {
      "epoch": 0.3215590742996346,
      "grad_norm": 0.38515135645866394,
      "learning_rate": 9.976136999909156e-05,
      "loss": 0.6309,
      "step": 33
    },
    {
      "epoch": 0.3313032886723508,
      "grad_norm": 0.4617915749549866,
      "learning_rate": 9.968839595802982e-05,
      "loss": 0.6514,
      "step": 34
    },
    {
      "epoch": 0.341047503045067,
      "grad_norm": 0.36573508381843567,
      "learning_rate": 9.96057350657239e-05,
      "loss": 0.5839,
      "step": 35
    },
    {
      "epoch": 0.3507917174177832,
      "grad_norm": 0.38394173979759216,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.5927,
      "step": 36
    },
    {
      "epoch": 0.36053593179049936,
      "grad_norm": 0.41442376375198364,
      "learning_rate": 9.941141907232765e-05,
      "loss": 0.6388,
      "step": 37
    },
    {
      "epoch": 0.3702801461632156,
      "grad_norm": 0.3883739709854126,
      "learning_rate": 9.929980185352526e-05,
      "loss": 0.6241,
      "step": 38
    },
    {
      "epoch": 0.3800243605359318,
      "grad_norm": 0.3784323036670685,
      "learning_rate": 9.917857354066931e-05,
      "loss": 0.5968,
      "step": 39
    },
    {
      "epoch": 0.38976857490864797,
      "grad_norm": 0.38477954268455505,
      "learning_rate": 9.904775776745958e-05,
      "loss": 0.6051,
      "step": 40
    },
    {
      "epoch": 0.3995127892813642,
      "grad_norm": 0.42043524980545044,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.6269,
      "step": 41
    },
    {
      "epoch": 0.4092570036540804,
      "grad_norm": 0.4155956208705902,
      "learning_rate": 9.875746771527816e-05,
      "loss": 0.6137,
      "step": 42
    },
    {
      "epoch": 0.4190012180267966,
      "grad_norm": 0.39818403124809265,
      "learning_rate": 9.859805002892732e-05,
      "loss": 0.5831,
      "step": 43
    },
    {
      "epoch": 0.4287454323995128,
      "grad_norm": 0.4027486741542816,
      "learning_rate": 9.842915805643155e-05,
      "loss": 0.5671,
      "step": 44
    },
    {
      "epoch": 0.438489646772229,
      "grad_norm": 0.3745126724243164,
      "learning_rate": 9.825082472361557e-05,
      "loss": 0.5605,
      "step": 45
    },
    {
      "epoch": 0.4482338611449452,
      "grad_norm": 0.4132031798362732,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.6192,
      "step": 46
    },
    {
      "epoch": 0.4579780755176614,
      "grad_norm": 0.42464327812194824,
      "learning_rate": 9.786597487660337e-05,
      "loss": 0.5856,
      "step": 47
    },
    {
      "epoch": 0.46772228989037756,
      "grad_norm": 0.42480695247650146,
      "learning_rate": 9.765953338964735e-05,
      "loss": 0.6433,
      "step": 48
    },
    {
      "epoch": 0.4774665042630938,
      "grad_norm": 0.4505927562713623,
      "learning_rate": 9.744380058222483e-05,
      "loss": 0.6637,
      "step": 49
    },
    {
      "epoch": 0.48721071863581,
      "grad_norm": 0.40766066312789917,
      "learning_rate": 9.721881851187406e-05,
      "loss": 0.5722,
      "step": 50
    },
    {
      "epoch": 0.48721071863581,
      "eval_loss": 0.6059486865997314,
      "eval_runtime": 116.3481,
      "eval_samples_per_second": 7.366,
      "eval_steps_per_second": 0.464,
      "step": 50
    },
    {
      "epoch": 0.49695493300852617,
      "grad_norm": 0.45385217666625977,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.6223,
      "step": 51
    },
    {
      "epoch": 0.5066991473812423,
      "grad_norm": 0.4196796417236328,
      "learning_rate": 9.674128381980072e-05,
      "loss": 0.572,
      "step": 52
    },
    {
      "epoch": 0.5164433617539586,
      "grad_norm": 0.4284449517726898,
      "learning_rate": 9.648882429441257e-05,
      "loss": 0.5225,
      "step": 53
    },
    {
      "epoch": 0.5261875761266748,
      "grad_norm": 0.45584678649902344,
      "learning_rate": 9.622730168061567e-05,
      "loss": 0.5592,
      "step": 54
    },
    {
      "epoch": 0.535931790499391,
      "grad_norm": 0.4218933582305908,
      "learning_rate": 9.595676696276172e-05,
      "loss": 0.5857,
      "step": 55
    },
    {
      "epoch": 0.5456760048721072,
      "grad_norm": 0.45864835381507874,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.5908,
      "step": 56
    },
    {
      "epoch": 0.5554202192448234,
      "grad_norm": 0.4483995735645294,
      "learning_rate": 9.538887392664544e-05,
      "loss": 0.5695,
      "step": 57
    },
    {
      "epoch": 0.5651644336175395,
      "grad_norm": 0.48954787850379944,
      "learning_rate": 9.50916263202557e-05,
      "loss": 0.5314,
      "step": 58
    },
    {
      "epoch": 0.5749086479902558,
      "grad_norm": 0.515805184841156,
      "learning_rate": 9.478558801197065e-05,
      "loss": 0.6366,
      "step": 59
    },
    {
      "epoch": 0.584652862362972,
      "grad_norm": 0.4741595387458801,
      "learning_rate": 9.447081866456489e-05,
      "loss": 0.4933,
      "step": 60
    },
    {
      "epoch": 0.5943970767356882,
      "grad_norm": 0.4829859137535095,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.6337,
      "step": 61
    },
    {
      "epoch": 0.6041412911084044,
      "grad_norm": 0.45033347606658936,
      "learning_rate": 9.381533400219318e-05,
      "loss": 0.5714,
      "step": 62
    },
    {
      "epoch": 0.6138855054811205,
      "grad_norm": 0.4400843381881714,
      "learning_rate": 9.347474647526095e-05,
      "loss": 0.5756,
      "step": 63
    },
    {
      "epoch": 0.6236297198538368,
      "grad_norm": 0.45498228073120117,
      "learning_rate": 9.312568346036288e-05,
      "loss": 0.5635,
      "step": 64
    },
    {
      "epoch": 0.633373934226553,
      "grad_norm": 0.4397442936897278,
      "learning_rate": 9.276821300802534e-05,
      "loss": 0.5508,
      "step": 65
    },
    {
      "epoch": 0.6431181485992692,
      "grad_norm": 0.465465247631073,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.5118,
      "step": 66
    },
    {
      "epoch": 0.6528623629719854,
      "grad_norm": 0.4904666244983673,
      "learning_rate": 9.202833017478422e-05,
      "loss": 0.5555,
      "step": 67
    },
    {
      "epoch": 0.6626065773447016,
      "grad_norm": 0.4522901177406311,
      "learning_rate": 9.164606203550497e-05,
      "loss": 0.5712,
      "step": 68
    },
    {
      "epoch": 0.6723507917174177,
      "grad_norm": 0.46516191959381104,
      "learning_rate": 9.125567491391476e-05,
      "loss": 0.54,
      "step": 69
    },
    {
      "epoch": 0.682095006090134,
      "grad_norm": 0.563292384147644,
      "learning_rate": 9.085724491675642e-05,
      "loss": 0.5334,
      "step": 70
    },
    {
      "epoch": 0.6918392204628502,
      "grad_norm": 0.4758321940898895,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.558,
      "step": 71
    },
    {
      "epoch": 0.7015834348355664,
      "grad_norm": 0.4505232870578766,
      "learning_rate": 9.003656854743667e-05,
      "loss": 0.5592,
      "step": 72
    },
    {
      "epoch": 0.7113276492082826,
      "grad_norm": 0.49200811982154846,
      "learning_rate": 8.961448216775954e-05,
      "loss": 0.562,
      "step": 73
    },
    {
      "epoch": 0.7210718635809987,
      "grad_norm": 0.49411916732788086,
      "learning_rate": 8.9184672866292e-05,
      "loss": 0.5502,
      "step": 74
    },
    {
      "epoch": 0.730816077953715,
      "grad_norm": 0.49506062269210815,
      "learning_rate": 8.874722443520899e-05,
      "loss": 0.5268,
      "step": 75
    },
    {
      "epoch": 0.730816077953715,
      "eval_loss": 0.5484524369239807,
      "eval_runtime": 116.2855,
      "eval_samples_per_second": 7.37,
      "eval_steps_per_second": 0.464,
      "step": 75
    },
    {
      "epoch": 0.7405602923264312,
      "grad_norm": 0.4459410607814789,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.5651,
      "step": 76
    },
    {
      "epoch": 0.7503045066991474,
      "grad_norm": 0.4649423360824585,
      "learning_rate": 8.784975278258783e-05,
      "loss": 0.507,
      "step": 77
    },
    {
      "epoch": 0.7600487210718636,
      "grad_norm": 0.5267335176467896,
      "learning_rate": 8.73899045249266e-05,
      "loss": 0.5846,
      "step": 78
    },
    {
      "epoch": 0.7697929354445798,
      "grad_norm": 0.48191651701927185,
      "learning_rate": 8.692276703129421e-05,
      "loss": 0.4785,
      "step": 79
    },
    {
      "epoch": 0.7795371498172959,
      "grad_norm": 0.4713154137134552,
      "learning_rate": 8.644843137107059e-05,
      "loss": 0.5115,
      "step": 80
    },
    {
      "epoch": 0.7892813641900122,
      "grad_norm": 0.48336002230644226,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.4972,
      "step": 81
    },
    {
      "epoch": 0.7990255785627284,
      "grad_norm": 0.5115373730659485,
      "learning_rate": 8.547853682682604e-05,
      "loss": 0.5548,
      "step": 82
    },
    {
      "epoch": 0.8087697929354446,
      "grad_norm": 0.4678809344768524,
      "learning_rate": 8.498316702566828e-05,
      "loss": 0.5017,
      "step": 83
    },
    {
      "epoch": 0.8185140073081608,
      "grad_norm": 0.46973857283592224,
      "learning_rate": 8.44809771867835e-05,
      "loss": 0.5304,
      "step": 84
    },
    {
      "epoch": 0.8282582216808769,
      "grad_norm": 0.5022630095481873,
      "learning_rate": 8.397206521307584e-05,
      "loss": 0.4957,
      "step": 85
    },
    {
      "epoch": 0.8380024360535931,
      "grad_norm": 0.47750282287597656,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.4853,
      "step": 86
    },
    {
      "epoch": 0.8477466504263094,
      "grad_norm": 0.48647361993789673,
      "learning_rate": 8.293447300593402e-05,
      "loss": 0.499,
      "step": 87
    },
    {
      "epoch": 0.8574908647990256,
      "grad_norm": 0.5240001082420349,
      "learning_rate": 8.240599505315655e-05,
      "loss": 0.5061,
      "step": 88
    },
    {
      "epoch": 0.8672350791717418,
      "grad_norm": 0.4904966354370117,
      "learning_rate": 8.18711994874345e-05,
      "loss": 0.5139,
      "step": 89
    },
    {
      "epoch": 0.876979293544458,
      "grad_norm": 0.5042212605476379,
      "learning_rate": 8.133019056822304e-05,
      "loss": 0.5355,
      "step": 90
    },
    {
      "epoch": 0.8867235079171741,
      "grad_norm": 0.4775819778442383,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.4889,
      "step": 91
    },
    {
      "epoch": 0.8964677222898904,
      "grad_norm": 0.5047743320465088,
      "learning_rate": 8.022995574311876e-05,
      "loss": 0.4788,
      "step": 92
    },
    {
      "epoch": 0.9062119366626066,
      "grad_norm": 0.4905475676059723,
      "learning_rate": 7.967094433018508e-05,
      "loss": 0.5104,
      "step": 93
    },
    {
      "epoch": 0.9159561510353228,
      "grad_norm": 0.49578583240509033,
      "learning_rate": 7.910614850786448e-05,
      "loss": 0.4903,
      "step": 94
    },
    {
      "epoch": 0.925700365408039,
      "grad_norm": 0.5329849123954773,
      "learning_rate": 7.85356783842216e-05,
      "loss": 0.4926,
      "step": 95
    },
    {
      "epoch": 0.9354445797807551,
      "grad_norm": 0.5267957448959351,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.5514,
      "step": 96
    },
    {
      "epoch": 0.9451887941534713,
      "grad_norm": 0.5095996856689453,
      "learning_rate": 7.737816117462752e-05,
      "loss": 0.4886,
      "step": 97
    },
    {
      "epoch": 0.9549330085261876,
      "grad_norm": 0.46476784348487854,
      "learning_rate": 7.679133974894983e-05,
      "loss": 0.4776,
      "step": 98
    },
    {
      "epoch": 0.9646772228989038,
      "grad_norm": 0.516237735748291,
      "learning_rate": 7.619929529850397e-05,
      "loss": 0.5343,
      "step": 99
    },
    {
      "epoch": 0.97442143727162,
      "grad_norm": 0.5128530859947205,
      "learning_rate": 7.560214324352858e-05,
      "loss": 0.492,
      "step": 100
    },
    {
      "epoch": 0.97442143727162,
      "eval_loss": 0.5159465074539185,
      "eval_runtime": 116.1788,
      "eval_samples_per_second": 7.377,
      "eval_steps_per_second": 0.465,
      "step": 100
    },
    {
      "epoch": 0.9841656516443362,
      "grad_norm": 0.525909960269928,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.5276,
      "step": 101
    },
    {
      "epoch": 0.9939098660170523,
      "grad_norm": 0.4755876958370209,
      "learning_rate": 7.439298295693665e-05,
      "loss": 0.4887,
      "step": 102
    },
    {
      "epoch": 1.0097442143727162,
      "grad_norm": 0.898318350315094,
      "learning_rate": 7.378121045351378e-05,
      "loss": 0.896,
      "step": 103
    },
    {
      "epoch": 1.0194884287454324,
      "grad_norm": 0.5060648918151855,
      "learning_rate": 7.316480175599309e-05,
      "loss": 0.4999,
      "step": 104
    },
    {
      "epoch": 1.0292326431181487,
      "grad_norm": 0.46954262256622314,
      "learning_rate": 7.254387703447154e-05,
      "loss": 0.4633,
      "step": 105
    },
    {
      "epoch": 1.0389768574908649,
      "grad_norm": 0.4725915193557739,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.4491,
      "step": 106
    },
    {
      "epoch": 1.048721071863581,
      "grad_norm": 0.4837670624256134,
      "learning_rate": 7.128896457825364e-05,
      "loss": 0.4508,
      "step": 107
    },
    {
      "epoch": 1.058465286236297,
      "grad_norm": 0.5884471535682678,
      "learning_rate": 7.06552214912271e-05,
      "loss": 0.4297,
      "step": 108
    },
    {
      "epoch": 1.0682095006090133,
      "grad_norm": 0.5307117104530334,
      "learning_rate": 7.001745162784477e-05,
      "loss": 0.4592,
      "step": 109
    },
    {
      "epoch": 1.0779537149817295,
      "grad_norm": 0.5245863795280457,
      "learning_rate": 6.937577932260515e-05,
      "loss": 0.4819,
      "step": 110
    },
    {
      "epoch": 1.0876979293544458,
      "grad_norm": 0.5525639653205872,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.4678,
      "step": 111
    },
    {
      "epoch": 1.097442143727162,
      "grad_norm": 0.5659409761428833,
      "learning_rate": 6.808122850410461e-05,
      "loss": 0.4635,
      "step": 112
    },
    {
      "epoch": 1.1071863580998782,
      "grad_norm": 0.5493988394737244,
      "learning_rate": 6.742860236609077e-05,
      "loss": 0.4307,
      "step": 113
    },
    {
      "epoch": 1.1169305724725944,
      "grad_norm": 0.5591247081756592,
      "learning_rate": 6.677257848751277e-05,
      "loss": 0.416,
      "step": 114
    },
    {
      "epoch": 1.1266747868453106,
      "grad_norm": 0.4955357611179352,
      "learning_rate": 6.611328476152557e-05,
      "loss": 0.4662,
      "step": 115
    },
    {
      "epoch": 1.1364190012180269,
      "grad_norm": 0.5241750478744507,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.4301,
      "step": 116
    },
    {
      "epoch": 1.146163215590743,
      "grad_norm": 0.4876319468021393,
      "learning_rate": 6.478540250220234e-05,
      "loss": 0.4564,
      "step": 117
    },
    {
      "epoch": 1.155907429963459,
      "grad_norm": 0.5395438075065613,
      "learning_rate": 6.411707284214384e-05,
      "loss": 0.502,
      "step": 118
    },
    {
      "epoch": 1.1656516443361755,
      "grad_norm": 0.5435388684272766,
      "learning_rate": 6.344599103076329e-05,
      "loss": 0.4536,
      "step": 119
    },
    {
      "epoch": 1.1753958587088915,
      "grad_norm": 0.526055097579956,
      "learning_rate": 6.277228789678953e-05,
      "loss": 0.4576,
      "step": 120
    },
    {
      "epoch": 1.1851400730816077,
      "grad_norm": 0.5060620903968811,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.4814,
      "step": 121
    },
    {
      "epoch": 1.194884287454324,
      "grad_norm": 0.4862349033355713,
      "learning_rate": 6.141754350553279e-05,
      "loss": 0.4277,
      "step": 122
    },
    {
      "epoch": 1.2046285018270402,
      "grad_norm": 0.5572500824928284,
      "learning_rate": 6.073676635835317e-05,
      "loss": 0.5118,
      "step": 123
    },
    {
      "epoch": 1.2143727161997564,
      "grad_norm": 0.5726194381713867,
      "learning_rate": 6.005389605729824e-05,
      "loss": 0.4725,
      "step": 124
    },
    {
      "epoch": 1.2241169305724726,
      "grad_norm": 0.5314717888832092,
      "learning_rate": 5.9369065729286245e-05,
      "loss": 0.4719,
      "step": 125
    },
    {
      "epoch": 1.2241169305724726,
      "eval_loss": 0.4989548325538635,
      "eval_runtime": 116.3548,
      "eval_samples_per_second": 7.365,
      "eval_steps_per_second": 0.464,
      "step": 125
    },
    {
      "epoch": 1.2338611449451888,
      "grad_norm": 0.5402824878692627,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.4735,
      "step": 126
    },
    {
      "epoch": 1.243605359317905,
      "grad_norm": 0.5422326922416687,
      "learning_rate": 5.799405938459175e-05,
      "loss": 0.4729,
      "step": 127
    },
    {
      "epoch": 1.2533495736906213,
      "grad_norm": 0.5375432968139648,
      "learning_rate": 5.730415142812059e-05,
      "loss": 0.4589,
      "step": 128
    },
    {
      "epoch": 1.2630937880633373,
      "grad_norm": 0.5534482002258301,
      "learning_rate": 5.661281951285613e-05,
      "loss": 0.4464,
      "step": 129
    },
    {
      "epoch": 1.2728380024360537,
      "grad_norm": 0.5432469844818115,
      "learning_rate": 5.5920198415325064e-05,
      "loss": 0.4537,
      "step": 130
    },
    {
      "epoch": 1.2825822168087697,
      "grad_norm": 0.5186154246330261,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.4158,
      "step": 131
    },
    {
      "epoch": 1.292326431181486,
      "grad_norm": 0.5382589101791382,
      "learning_rate": 5.453162900988902e-05,
      "loss": 0.4176,
      "step": 132
    },
    {
      "epoch": 1.3020706455542022,
      "grad_norm": 0.5565094351768494,
      "learning_rate": 5.383595140634093e-05,
      "loss": 0.4287,
      "step": 133
    },
    {
      "epoch": 1.3118148599269184,
      "grad_norm": 0.5403843522071838,
      "learning_rate": 5.313952597646568e-05,
      "loss": 0.4118,
      "step": 134
    },
    {
      "epoch": 1.3215590742996346,
      "grad_norm": 0.5338913798332214,
      "learning_rate": 5.244248848978067e-05,
      "loss": 0.3948,
      "step": 135
    },
    {
      "epoch": 1.3313032886723508,
      "grad_norm": 0.5245387554168701,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.4579,
      "step": 136
    },
    {
      "epoch": 1.341047503045067,
      "grad_norm": 0.51710045337677,
      "learning_rate": 5.104712099416785e-05,
      "loss": 0.4025,
      "step": 137
    },
    {
      "epoch": 1.3507917174177833,
      "grad_norm": 0.56063312292099,
      "learning_rate": 5.034906301489808e-05,
      "loss": 0.4956,
      "step": 138
    },
    {
      "epoch": 1.3605359317904995,
      "grad_norm": 0.6041215658187866,
      "learning_rate": 4.965093698510193e-05,
      "loss": 0.4336,
      "step": 139
    },
    {
      "epoch": 1.3702801461632155,
      "grad_norm": 0.5541957020759583,
      "learning_rate": 4.895287900583216e-05,
      "loss": 0.4456,
      "step": 140
    },
    {
      "epoch": 1.380024360535932,
      "grad_norm": 0.5618797540664673,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.3996,
      "step": 141
    },
    {
      "epoch": 1.389768574908648,
      "grad_norm": 0.533968448638916,
      "learning_rate": 4.755751151021934e-05,
      "loss": 0.4155,
      "step": 142
    },
    {
      "epoch": 1.3995127892813641,
      "grad_norm": 0.5411080121994019,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 0.4325,
      "step": 143
    },
    {
      "epoch": 1.4092570036540804,
      "grad_norm": 0.5761292576789856,
      "learning_rate": 4.616404859365907e-05,
      "loss": 0.4166,
      "step": 144
    },
    {
      "epoch": 1.4190012180267966,
      "grad_norm": 0.5804659128189087,
      "learning_rate": 4.5468370990111006e-05,
      "loss": 0.4436,
      "step": 145
    },
    {
      "epoch": 1.4287454323995128,
      "grad_norm": 0.5537294745445251,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.3795,
      "step": 146
    },
    {
      "epoch": 1.438489646772229,
      "grad_norm": 0.5477214455604553,
      "learning_rate": 4.407980158467495e-05,
      "loss": 0.3896,
      "step": 147
    },
    {
      "epoch": 1.4482338611449452,
      "grad_norm": 0.5110722780227661,
      "learning_rate": 4.3387180487143876e-05,
      "loss": 0.4036,
      "step": 148
    },
    {
      "epoch": 1.4579780755176615,
      "grad_norm": 0.5480209589004517,
      "learning_rate": 4.269584857187943e-05,
      "loss": 0.4451,
      "step": 149
    },
    {
      "epoch": 1.4677222898903777,
      "grad_norm": 0.5255818367004395,
      "learning_rate": 4.2005940615408264e-05,
      "loss": 0.4031,
      "step": 150
    },
    {
      "epoch": 1.4677222898903777,
      "eval_loss": 0.4808570146560669,
      "eval_runtime": 116.3103,
      "eval_samples_per_second": 7.368,
      "eval_steps_per_second": 0.464,
      "step": 150
    },
    {
      "epoch": 1.4774665042630937,
      "grad_norm": 0.5485397577285767,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.462,
      "step": 151
    },
    {
      "epoch": 1.4872107186358101,
      "grad_norm": 0.5463838577270508,
      "learning_rate": 4.063093427071376e-05,
      "loss": 0.4265,
      "step": 152
    },
    {
      "epoch": 1.4969549330085261,
      "grad_norm": 0.5511963367462158,
      "learning_rate": 3.9946103942701777e-05,
      "loss": 0.3964,
      "step": 153
    },
    {
      "epoch": 1.5066991473812423,
      "grad_norm": 0.5571511387825012,
      "learning_rate": 3.926323364164684e-05,
      "loss": 0.4642,
      "step": 154
    },
    {
      "epoch": 1.5164433617539586,
      "grad_norm": 0.5894230604171753,
      "learning_rate": 3.858245649446721e-05,
      "loss": 0.4511,
      "step": 155
    },
    {
      "epoch": 1.5261875761266748,
      "grad_norm": 0.5373761653900146,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.388,
      "step": 156
    },
    {
      "epoch": 1.535931790499391,
      "grad_norm": 0.5737512707710266,
      "learning_rate": 3.7227712103210486e-05,
      "loss": 0.375,
      "step": 157
    },
    {
      "epoch": 1.5456760048721072,
      "grad_norm": 0.5502772331237793,
      "learning_rate": 3.655400896923672e-05,
      "loss": 0.4433,
      "step": 158
    },
    {
      "epoch": 1.5554202192448234,
      "grad_norm": 0.5434299111366272,
      "learning_rate": 3.588292715785617e-05,
      "loss": 0.4002,
      "step": 159
    },
    {
      "epoch": 1.5651644336175394,
      "grad_norm": 0.5924922227859497,
      "learning_rate": 3.5214597497797684e-05,
      "loss": 0.4141,
      "step": 160
    },
    {
      "epoch": 1.5749086479902559,
      "grad_norm": 0.6273884177207947,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.4277,
      "step": 161
    },
    {
      "epoch": 1.5846528623629719,
      "grad_norm": 0.578081488609314,
      "learning_rate": 3.388671523847445e-05,
      "loss": 0.3956,
      "step": 162
    },
    {
      "epoch": 1.5943970767356883,
      "grad_norm": 0.5401508212089539,
      "learning_rate": 3.322742151248725e-05,
      "loss": 0.4305,
      "step": 163
    },
    {
      "epoch": 1.6041412911084043,
      "grad_norm": 0.6144226789474487,
      "learning_rate": 3.257139763390925e-05,
      "loss": 0.4126,
      "step": 164
    },
    {
      "epoch": 1.6138855054811205,
      "grad_norm": 0.5739960670471191,
      "learning_rate": 3.1918771495895396e-05,
      "loss": 0.404,
      "step": 165
    },
    {
      "epoch": 1.6236297198538368,
      "grad_norm": 0.5783050060272217,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.4209,
      "step": 166
    },
    {
      "epoch": 1.633373934226553,
      "grad_norm": 0.5928875207901001,
      "learning_rate": 3.062422067739485e-05,
      "loss": 0.4317,
      "step": 167
    },
    {
      "epoch": 1.6431181485992692,
      "grad_norm": 0.5249680876731873,
      "learning_rate": 2.9982548372155263e-05,
      "loss": 0.3964,
      "step": 168
    },
    {
      "epoch": 1.6528623629719854,
      "grad_norm": 0.5612180233001709,
      "learning_rate": 2.934477850877292e-05,
      "loss": 0.3919,
      "step": 169
    },
    {
      "epoch": 1.6626065773447016,
      "grad_norm": 0.5700953006744385,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 0.4403,
      "step": 170
    },
    {
      "epoch": 1.6723507917174176,
      "grad_norm": 0.5822266936302185,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.4265,
      "step": 171
    },
    {
      "epoch": 1.682095006090134,
      "grad_norm": 0.5738089680671692,
      "learning_rate": 2.7456122965528475e-05,
      "loss": 0.4612,
      "step": 172
    },
    {
      "epoch": 1.69183922046285,
      "grad_norm": 0.5751779079437256,
      "learning_rate": 2.6835198244006927e-05,
      "loss": 0.3983,
      "step": 173
    },
    {
      "epoch": 1.7015834348355665,
      "grad_norm": 0.5598529577255249,
      "learning_rate": 2.6218789546486234e-05,
      "loss": 0.4338,
      "step": 174
    },
    {
      "epoch": 1.7113276492082825,
      "grad_norm": 0.5587442517280579,
      "learning_rate": 2.560701704306336e-05,
      "loss": 0.3825,
      "step": 175
    },
    {
      "epoch": 1.7113276492082825,
      "eval_loss": 0.47023555636405945,
      "eval_runtime": 116.2392,
      "eval_samples_per_second": 7.373,
      "eval_steps_per_second": 0.465,
      "step": 175
    },
    {
      "epoch": 1.7210718635809987,
      "grad_norm": 0.5803806185722351,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.4265,
      "step": 176
    },
    {
      "epoch": 1.730816077953715,
      "grad_norm": 0.5986764430999756,
      "learning_rate": 2.4397856756471432e-05,
      "loss": 0.4299,
      "step": 177
    },
    {
      "epoch": 1.7405602923264312,
      "grad_norm": 0.6137004494667053,
      "learning_rate": 2.3800704701496053e-05,
      "loss": 0.4355,
      "step": 178
    },
    {
      "epoch": 1.7503045066991474,
      "grad_norm": 0.5777759552001953,
      "learning_rate": 2.3208660251050158e-05,
      "loss": 0.4235,
      "step": 179
    },
    {
      "epoch": 1.7600487210718636,
      "grad_norm": 0.599251389503479,
      "learning_rate": 2.2621838825372493e-05,
      "loss": 0.4078,
      "step": 180
    },
    {
      "epoch": 1.7697929354445798,
      "grad_norm": 0.5639720559120178,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.4046,
      "step": 181
    },
    {
      "epoch": 1.7795371498172958,
      "grad_norm": 0.5639522075653076,
      "learning_rate": 2.1464321615778422e-05,
      "loss": 0.433,
      "step": 182
    },
    {
      "epoch": 1.7892813641900123,
      "grad_norm": 0.5366583466529846,
      "learning_rate": 2.0893851492135537e-05,
      "loss": 0.4318,
      "step": 183
    },
    {
      "epoch": 1.7990255785627283,
      "grad_norm": 0.5910248160362244,
      "learning_rate": 2.0329055669814934e-05,
      "loss": 0.4184,
      "step": 184
    },
    {
      "epoch": 1.8087697929354447,
      "grad_norm": 0.5742807388305664,
      "learning_rate": 1.977004425688126e-05,
      "loss": 0.4346,
      "step": 185
    },
    {
      "epoch": 1.8185140073081607,
      "grad_norm": 0.5683897137641907,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.4007,
      "step": 186
    },
    {
      "epoch": 1.828258221680877,
      "grad_norm": 0.5249460339546204,
      "learning_rate": 1.866980943177699e-05,
      "loss": 0.4165,
      "step": 187
    },
    {
      "epoch": 1.8380024360535931,
      "grad_norm": 0.5429449677467346,
      "learning_rate": 1.8128800512565513e-05,
      "loss": 0.378,
      "step": 188
    },
    {
      "epoch": 1.8477466504263094,
      "grad_norm": 0.5251733660697937,
      "learning_rate": 1.7594004946843456e-05,
      "loss": 0.3824,
      "step": 189
    },
    {
      "epoch": 1.8574908647990256,
      "grad_norm": 0.5763549208641052,
      "learning_rate": 1.7065526994065973e-05,
      "loss": 0.3788,
      "step": 190
    },
    {
      "epoch": 1.8672350791717418,
      "grad_norm": 0.5946308970451355,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.448,
      "step": 191
    },
    {
      "epoch": 1.876979293544458,
      "grad_norm": 0.5707454085350037,
      "learning_rate": 1.602793478692419e-05,
      "loss": 0.3816,
      "step": 192
    },
    {
      "epoch": 1.886723507917174,
      "grad_norm": 0.5635607838630676,
      "learning_rate": 1.551902281321651e-05,
      "loss": 0.3979,
      "step": 193
    },
    {
      "epoch": 1.8964677222898905,
      "grad_norm": 1.6317293643951416,
      "learning_rate": 1.5016832974331724e-05,
      "loss": 0.3654,
      "step": 194
    },
    {
      "epoch": 1.9062119366626065,
      "grad_norm": 0.5927464365959167,
      "learning_rate": 1.4521463173173965e-05,
      "loss": 0.4432,
      "step": 195
    },
    {
      "epoch": 1.915956151035323,
      "grad_norm": 0.5671654343605042,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.364,
      "step": 196
    },
    {
      "epoch": 1.925700365408039,
      "grad_norm": 0.5950899124145508,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 0.4442,
      "step": 197
    },
    {
      "epoch": 1.9354445797807551,
      "grad_norm": 0.5787199139595032,
      "learning_rate": 1.3077232968705805e-05,
      "loss": 0.4042,
      "step": 198
    },
    {
      "epoch": 1.9451887941534713,
      "grad_norm": 0.5602390766143799,
      "learning_rate": 1.2610095475073414e-05,
      "loss": 0.4252,
      "step": 199
    },
    {
      "epoch": 1.9549330085261876,
      "grad_norm": 0.5912858843803406,
      "learning_rate": 1.2150247217412186e-05,
      "loss": 0.3944,
      "step": 200
    },
    {
      "epoch": 1.9549330085261876,
      "eval_loss": 0.4625219404697418,
      "eval_runtime": 116.3528,
      "eval_samples_per_second": 7.366,
      "eval_steps_per_second": 0.464,
      "step": 200
    },
    {
      "epoch": 1.9646772228989038,
      "grad_norm": 0.5247693657875061,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.397,
      "step": 201
    },
    {
      "epoch": 1.97442143727162,
      "grad_norm": 0.5671912431716919,
      "learning_rate": 1.1252775564791024e-05,
      "loss": 0.4191,
      "step": 202
    },
    {
      "epoch": 1.9841656516443362,
      "grad_norm": 0.5699170827865601,
      "learning_rate": 1.0815327133708015e-05,
      "loss": 0.4126,
      "step": 203
    },
    {
      "epoch": 1.9939098660170522,
      "grad_norm": 0.5686872005462646,
      "learning_rate": 1.0385517832240471e-05,
      "loss": 0.3936,
      "step": 204
    },
    {
      "epoch": 2.009744214372716,
      "grad_norm": 0.9932243824005127,
      "learning_rate": 9.963431452563332e-06,
      "loss": 0.8769,
      "step": 205
    },
    {
      "epoch": 2.0194884287454324,
      "grad_norm": 0.5336227416992188,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.3756,
      "step": 206
    },
    {
      "epoch": 2.0292326431181484,
      "grad_norm": 0.5651218891143799,
      "learning_rate": 9.142755083243576e-06,
      "loss": 0.4197,
      "step": 207
    },
    {
      "epoch": 2.038976857490865,
      "grad_norm": 0.5759946703910828,
      "learning_rate": 8.744325086085248e-06,
      "loss": 0.4043,
      "step": 208
    },
    {
      "epoch": 2.048721071863581,
      "grad_norm": 0.529643177986145,
      "learning_rate": 8.353937964495029e-06,
      "loss": 0.3806,
      "step": 209
    },
    {
      "epoch": 2.0584652862362973,
      "grad_norm": 0.563081681728363,
      "learning_rate": 7.971669825215788e-06,
      "loss": 0.3838,
      "step": 210
    },
    {
      "epoch": 2.0682095006090133,
      "grad_norm": 0.5327872037887573,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.3778,
      "step": 211
    },
    {
      "epoch": 2.0779537149817298,
      "grad_norm": 0.5525795817375183,
      "learning_rate": 7.2317869919746705e-06,
      "loss": 0.4119,
      "step": 212
    },
    {
      "epoch": 2.0876979293544458,
      "grad_norm": 0.5779188871383667,
      "learning_rate": 6.874316539637127e-06,
      "loss": 0.3804,
      "step": 213
    },
    {
      "epoch": 2.097442143727162,
      "grad_norm": 0.5842592716217041,
      "learning_rate": 6.52525352473905e-06,
      "loss": 0.3932,
      "step": 214
    },
    {
      "epoch": 2.107186358099878,
      "grad_norm": 0.5471872091293335,
      "learning_rate": 6.184665997806832e-06,
      "loss": 0.3658,
      "step": 215
    },
    {
      "epoch": 2.116930572472594,
      "grad_norm": 0.5467835664749146,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.3683,
      "step": 216
    },
    {
      "epoch": 2.1266747868453106,
      "grad_norm": 0.5607587099075317,
      "learning_rate": 5.529181335435124e-06,
      "loss": 0.3635,
      "step": 217
    },
    {
      "epoch": 2.1364190012180266,
      "grad_norm": 0.5682641267776489,
      "learning_rate": 5.214411988029355e-06,
      "loss": 0.3929,
      "step": 218
    },
    {
      "epoch": 2.146163215590743,
      "grad_norm": 0.5493900775909424,
      "learning_rate": 4.908373679744316e-06,
      "loss": 0.3579,
      "step": 219
    },
    {
      "epoch": 2.155907429963459,
      "grad_norm": 0.5399561524391174,
      "learning_rate": 4.611126073354571e-06,
      "loss": 0.397,
      "step": 220
    },
    {
      "epoch": 2.1656516443361755,
      "grad_norm": 0.566953182220459,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.3996,
      "step": 221
    },
    {
      "epoch": 2.1753958587088915,
      "grad_norm": 0.5458848476409912,
      "learning_rate": 4.043233037238281e-06,
      "loss": 0.3797,
      "step": 222
    },
    {
      "epoch": 2.185140073081608,
      "grad_norm": 0.5842291116714478,
      "learning_rate": 3.772698319384349e-06,
      "loss": 0.4177,
      "step": 223
    },
    {
      "epoch": 2.194884287454324,
      "grad_norm": 0.5811557769775391,
      "learning_rate": 3.511175705587433e-06,
      "loss": 0.4057,
      "step": 224
    },
    {
      "epoch": 2.2046285018270404,
      "grad_norm": 0.5538292527198792,
      "learning_rate": 3.258716180199278e-06,
      "loss": 0.3411,
      "step": 225
    },
    {
      "epoch": 2.2046285018270404,
      "eval_loss": 0.461640328168869,
      "eval_runtime": 116.2914,
      "eval_samples_per_second": 7.369,
      "eval_steps_per_second": 0.464,
      "step": 225
    },
    {
      "epoch": 2.2143727161997564,
      "grad_norm": 0.5587625503540039,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.3767,
      "step": 226
    },
    {
      "epoch": 2.2241169305724724,
      "grad_norm": 0.6179119348526001,
      "learning_rate": 2.7811814881259503e-06,
      "loss": 0.3909,
      "step": 227
    },
    {
      "epoch": 2.233861144945189,
      "grad_norm": 0.5846551060676575,
      "learning_rate": 2.5561994177751737e-06,
      "loss": 0.377,
      "step": 228
    },
    {
      "epoch": 2.243605359317905,
      "grad_norm": 0.5826045274734497,
      "learning_rate": 2.340466610352654e-06,
      "loss": 0.3621,
      "step": 229
    },
    {
      "epoch": 2.2533495736906213,
      "grad_norm": 0.5827783942222595,
      "learning_rate": 2.134025123396638e-06,
      "loss": 0.4011,
      "step": 230
    },
    {
      "epoch": 2.2630937880633373,
      "grad_norm": 0.5747119188308716,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.3517,
      "step": 231
    },
    {
      "epoch": 2.2728380024360537,
      "grad_norm": 0.5735805630683899,
      "learning_rate": 1.7491752763844293e-06,
      "loss": 0.3749,
      "step": 232
    },
    {
      "epoch": 2.2825822168087697,
      "grad_norm": 0.5682513117790222,
      "learning_rate": 1.5708419435684462e-06,
      "loss": 0.3629,
      "step": 233
    },
    {
      "epoch": 2.292326431181486,
      "grad_norm": 0.587968111038208,
      "learning_rate": 1.4019499710726913e-06,
      "loss": 0.3971,
      "step": 234
    },
    {
      "epoch": 2.302070645554202,
      "grad_norm": 0.5531240105628967,
      "learning_rate": 1.2425322847218368e-06,
      "loss": 0.3643,
      "step": 235
    },
    {
      "epoch": 2.311814859926918,
      "grad_norm": 0.5963295698165894,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.3678,
      "step": 236
    },
    {
      "epoch": 2.3215590742996346,
      "grad_norm": 0.593429684638977,
      "learning_rate": 9.522422325404235e-07,
      "loss": 0.4407,
      "step": 237
    },
    {
      "epoch": 2.331303288672351,
      "grad_norm": 0.5391296148300171,
      "learning_rate": 8.214264593307098e-07,
      "loss": 0.3228,
      "step": 238
    },
    {
      "epoch": 2.341047503045067,
      "grad_norm": 0.5678541660308838,
      "learning_rate": 7.001981464747565e-07,
      "loss": 0.3825,
      "step": 239
    },
    {
      "epoch": 2.350791717417783,
      "grad_norm": 0.5584573149681091,
      "learning_rate": 5.885809276723608e-07,
      "loss": 0.3306,
      "step": 240
    },
    {
      "epoch": 2.3605359317904995,
      "grad_norm": 0.5642800331115723,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.368,
      "step": 241
    },
    {
      "epoch": 2.3702801461632155,
      "grad_norm": 0.5758326053619385,
      "learning_rate": 3.9426493427611177e-07,
      "loss": 0.3755,
      "step": 242
    },
    {
      "epoch": 2.380024360535932,
      "grad_norm": 0.5884226560592651,
      "learning_rate": 3.1160404197018154e-07,
      "loss": 0.389,
      "step": 243
    },
    {
      "epoch": 2.389768574908648,
      "grad_norm": 0.5593277812004089,
      "learning_rate": 2.386300009084408e-07,
      "loss": 0.3565,
      "step": 244
    },
    {
      "epoch": 2.3995127892813644,
      "grad_norm": 0.5782268643379211,
      "learning_rate": 1.753570375247815e-07,
      "loss": 0.3858,
      "step": 245
    },
    {
      "epoch": 2.4092570036540804,
      "grad_norm": 0.5798349380493164,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.3403,
      "step": 246
    },
    {
      "epoch": 2.4190012180267964,
      "grad_norm": 0.596785843372345,
      "learning_rate": 7.796179090094891e-08,
      "loss": 0.3451,
      "step": 247
    },
    {
      "epoch": 2.428745432399513,
      "grad_norm": 0.5822293162345886,
      "learning_rate": 4.385849505708084e-08,
      "loss": 0.3843,
      "step": 248
    },
    {
      "epoch": 2.4384896467722292,
      "grad_norm": 0.5595471262931824,
      "learning_rate": 1.949424798228239e-08,
      "loss": 0.409,
      "step": 249
    },
    {
      "epoch": 2.4482338611449452,
      "grad_norm": 0.5454703569412231,
      "learning_rate": 4.873799534788059e-09,
      "loss": 0.3588,
      "step": 250
    },
    {
      "epoch": 2.4482338611449452,
      "eval_loss": 0.4610269367694855,
      "eval_runtime": 116.2672,
      "eval_samples_per_second": 7.371,
      "eval_steps_per_second": 0.464,
      "step": 250
    },
    {
      "epoch": 2.4482338611449452,
      "step": 250,
      "total_flos": 2.3792355349217935e+18,
      "train_loss": 0.49713707935810086,
      "train_runtime": 9531.3935,
      "train_samples_per_second": 2.518,
      "train_steps_per_second": 0.026
    }
  ],
  "logging_steps": 1,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.3792355349217935e+18,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}