{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002479082739386427,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.479082739386427e-05,
      "grad_norm": 7.148635387420654,
      "learning_rate": 1e-05,
      "loss": 8.347,
      "step": 1
    },
    {
      "epoch": 2.479082739386427e-05,
      "eval_loss": 8.011682510375977,
      "eval_runtime": 3460.4868,
      "eval_samples_per_second": 9.816,
      "eval_steps_per_second": 1.227,
      "step": 1
    },
    {
      "epoch": 4.958165478772854e-05,
      "grad_norm": 9.141607284545898,
      "learning_rate": 2e-05,
      "loss": 8.3711,
      "step": 2
    },
    {
      "epoch": 7.437248218159282e-05,
      "grad_norm": 8.014404296875,
      "learning_rate": 3e-05,
      "loss": 7.8997,
      "step": 3
    },
    {
      "epoch": 9.916330957545708e-05,
      "grad_norm": 8.278745651245117,
      "learning_rate": 4e-05,
      "loss": 7.9701,
      "step": 4
    },
    {
      "epoch": 0.00012395413696932134,
      "grad_norm": 9.53559398651123,
      "learning_rate": 5e-05,
      "loss": 7.8895,
      "step": 5
    },
    {
      "epoch": 0.00014874496436318563,
      "grad_norm": 9.13082218170166,
      "learning_rate": 6e-05,
      "loss": 7.7234,
      "step": 6
    },
    {
      "epoch": 0.0001735357917570499,
      "grad_norm": 10.035101890563965,
      "learning_rate": 7e-05,
      "loss": 7.0331,
      "step": 7
    },
    {
      "epoch": 0.00019832661915091416,
      "grad_norm": 9.153826713562012,
      "learning_rate": 8e-05,
      "loss": 6.3258,
      "step": 8
    },
    {
      "epoch": 0.00022311744654477842,
      "grad_norm": 8.993047714233398,
      "learning_rate": 9e-05,
      "loss": 5.4439,
      "step": 9
    },
    {
      "epoch": 0.00022311744654477842,
      "eval_loss": 4.42119836807251,
      "eval_runtime": 3459.9507,
      "eval_samples_per_second": 9.818,
      "eval_steps_per_second": 1.227,
      "step": 9
    },
    {
      "epoch": 0.0002479082739386427,
      "grad_norm": 8.447330474853516,
      "learning_rate": 0.0001,
      "loss": 4.5064,
      "step": 10
    },
    {
      "epoch": 0.00027269910133250695,
      "grad_norm": 6.945399761199951,
      "learning_rate": 9.99695413509548e-05,
      "loss": 3.6772,
      "step": 11
    },
    {
      "epoch": 0.00029748992872637126,
      "grad_norm": 7.0555195808410645,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.8837,
      "step": 12
    },
    {
      "epoch": 0.0003222807561202355,
      "grad_norm": 5.693431377410889,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.0602,
      "step": 13
    },
    {
      "epoch": 0.0003470715835140998,
      "grad_norm": 4.972978591918945,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.6747,
      "step": 14
    },
    {
      "epoch": 0.00037186241090796405,
      "grad_norm": 4.800112247467041,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.2383,
      "step": 15
    },
    {
      "epoch": 0.0003966532383018283,
      "grad_norm": 3.8513824939727783,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.0105,
      "step": 16
    },
    {
      "epoch": 0.0004214440656956926,
      "grad_norm": 3.1367251873016357,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.6486,
      "step": 17
    },
    {
      "epoch": 0.00044623489308955684,
      "grad_norm": 3.300088405609131,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.4758,
      "step": 18
    },
    {
      "epoch": 0.00044623489308955684,
      "eval_loss": 0.3575020134449005,
      "eval_runtime": 3460.448,
      "eval_samples_per_second": 9.816,
      "eval_steps_per_second": 1.227,
      "step": 18
    },
    {
      "epoch": 0.00047102572048342116,
      "grad_norm": 2.4475772380828857,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.3181,
      "step": 19
    },
    {
      "epoch": 0.0004958165478772854,
      "grad_norm": 1.2668708562850952,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2255,
      "step": 20
    },
    {
      "epoch": 0.0005206073752711496,
      "grad_norm": 2.5756964683532715,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.1964,
      "step": 21
    },
    {
      "epoch": 0.0005453982026650139,
      "grad_norm": 4.635815143585205,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.225,
      "step": 22
    },
    {
      "epoch": 0.0005701890300588783,
      "grad_norm": 1.6424202919006348,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.1076,
      "step": 23
    },
    {
      "epoch": 0.0005949798574527425,
      "grad_norm": 2.1951308250427246,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0633,
      "step": 24
    },
    {
      "epoch": 0.0006197706848466068,
      "grad_norm": 1.9961215257644653,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0552,
      "step": 25
    },
    {
      "epoch": 0.000644561512240471,
      "grad_norm": 0.26518455147743225,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0045,
      "step": 26
    },
    {
      "epoch": 0.0006693523396343353,
      "grad_norm": 0.3753717541694641,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.003,
      "step": 27
    },
    {
      "epoch": 0.0006693523396343353,
      "eval_loss": 0.06290628761053085,
      "eval_runtime": 3459.9356,
      "eval_samples_per_second": 9.818,
      "eval_steps_per_second": 1.227,
      "step": 27
    },
    {
      "epoch": 0.0006941431670281996,
      "grad_norm": 0.20908643305301666,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0015,
      "step": 28
    },
    {
      "epoch": 0.0007189339944220638,
      "grad_norm": 0.05302276089787483,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.0005,
      "step": 29
    },
    {
      "epoch": 0.0007437248218159281,
      "grad_norm": 0.017372814938426018,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0002,
      "step": 30
    },
    {
      "epoch": 0.0007685156492097924,
      "grad_norm": 6.220452308654785,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.4412,
      "step": 31
    },
    {
      "epoch": 0.0007933064766036566,
      "grad_norm": 3.6316118240356445,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.2788,
      "step": 32
    },
    {
      "epoch": 0.0008180973039975209,
      "grad_norm": 3.141017436981201,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.2178,
      "step": 33
    },
    {
      "epoch": 0.0008428881313913852,
      "grad_norm": 0.36752939224243164,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0052,
      "step": 34
    },
    {
      "epoch": 0.0008676789587852494,
      "grad_norm": 0.10909147560596466,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0014,
      "step": 35
    },
    {
      "epoch": 0.0008924697861791137,
      "grad_norm": 0.14188747107982635,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0018,
      "step": 36
    },
    {
      "epoch": 0.0008924697861791137,
      "eval_loss": 0.01222518365830183,
      "eval_runtime": 3459.2234,
      "eval_samples_per_second": 9.82,
      "eval_steps_per_second": 1.228,
      "step": 36
    },
    {
      "epoch": 0.0009172606135729779,
      "grad_norm": 0.01495317555963993,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0002,
      "step": 37
    },
    {
      "epoch": 0.0009420514409668423,
      "grad_norm": 0.06873802840709686,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0011,
      "step": 38
    },
    {
      "epoch": 0.0009668422683607066,
      "grad_norm": 0.04712967574596405,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.0004,
      "step": 39
    },
    {
      "epoch": 0.0009916330957545707,
      "grad_norm": 0.018527941778302193,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0002,
      "step": 40
    },
    {
      "epoch": 0.001016423923148435,
      "grad_norm": 0.004091004375368357,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.0001,
      "step": 41
    },
    {
      "epoch": 0.0010412147505422993,
      "grad_norm": 0.0373254232108593,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0002,
      "step": 42
    },
    {
      "epoch": 0.0010660055779361636,
      "grad_norm": 0.0022029399406164885,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.0010907964053300278,
      "grad_norm": 0.10897021740674973,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.0005,
      "step": 44
    },
    {
      "epoch": 0.0011155872327238922,
      "grad_norm": 0.0015826758462935686,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.0011155872327238922,
      "eval_loss": 0.011905557475984097,
      "eval_runtime": 3460.4198,
      "eval_samples_per_second": 9.816,
      "eval_steps_per_second": 1.227,
      "step": 45
    },
    {
      "epoch": 0.0011403780601177565,
      "grad_norm": 0.004921503830701113,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0001,
      "step": 46
    },
    {
      "epoch": 0.0011651688875116207,
      "grad_norm": 0.0008932303753681481,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.001189959714905485,
      "grad_norm": 0.009026121348142624,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0002,
      "step": 48
    },
    {
      "epoch": 0.0012147505422993492,
      "grad_norm": 0.001327559701167047,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.0012395413696932136,
      "grad_norm": 0.0029878842178732157,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0001,
      "step": 50
    },
    {
      "epoch": 0.0012643321970870777,
      "grad_norm": 0.0016621012473478913,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.001289123024480942,
      "grad_norm": 0.0011065489379689097,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.0013139138518748063,
      "grad_norm": 0.0038463855162262917,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.0001,
      "step": 53
    },
    {
      "epoch": 0.0013387046792686706,
      "grad_norm": 0.002665896201506257,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.0013387046792686706,
      "eval_loss": 0.01291303988546133,
      "eval_runtime": 3460.672,
      "eval_samples_per_second": 9.816,
      "eval_steps_per_second": 1.227,
      "step": 54
    },
    {
      "epoch": 0.0013634955066625348,
      "grad_norm": 0.001753911841660738,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.0013882863340563992,
      "grad_norm": 0.0013742155861109495,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.0014130771614502633,
      "grad_norm": 0.0016975795151665807,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.0014378679888441277,
      "grad_norm": 0.004371886607259512,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0001,
      "step": 58
    },
    {
      "epoch": 0.0014626588162379918,
      "grad_norm": 0.002545311814174056,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.0014874496436318562,
      "grad_norm": 0.0012721183011308312,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.0015122404710257206,
      "grad_norm": 1.5859683752059937,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0221,
      "step": 61
    },
    {
      "epoch": 0.0015370312984195847,
      "grad_norm": 0.001025455305352807,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.001561822125813449,
      "grad_norm": 0.0023683272302150726,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.0001,
      "step": 63
    },
    {
      "epoch": 0.001561822125813449,
      "eval_loss": 0.00975963193923235,
      "eval_runtime": 3462.2141,
      "eval_samples_per_second": 9.811,
      "eval_steps_per_second": 1.227,
      "step": 63
    },
    {
      "epoch": 0.0015866129532073133,
      "grad_norm": 0.002758202375844121,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.0016114037806011776,
      "grad_norm": 0.001786602195352316,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.0016361946079950418,
      "grad_norm": 0.0019201320828869939,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.0016609854353889062,
      "grad_norm": 0.0011184336617588997,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.0016857762627827703,
      "grad_norm": 0.0006105133797973394,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.0017105670901766347,
      "grad_norm": 0.000507171789649874,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.0017353579175704988,
      "grad_norm": 0.002627558307722211,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0001,
      "step": 70
    },
    {
      "epoch": 0.0017601487449643632,
      "grad_norm": 0.0008504163706675172,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.0017849395723582274,
      "grad_norm": 0.001379123074002564,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.0017849395723582274,
      "eval_loss": 0.009472197853028774,
      "eval_runtime": 3463.5975,
      "eval_samples_per_second": 9.807,
      "eval_steps_per_second": 1.226,
      "step": 72
    },
    {
      "epoch": 0.0018097303997520917,
      "grad_norm": 0.0017566120950505137,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.0018345212271459559,
      "grad_norm": 0.0016617800574749708,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.0018593120545398203,
      "grad_norm": 0.0014876762870699167,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.0018841028819336846,
      "grad_norm": 4.014698028564453,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.3185,
      "step": 76
    },
    {
      "epoch": 0.0019088937093275488,
      "grad_norm": 0.015278141014277935,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.0002,
      "step": 77
    },
    {
      "epoch": 0.0019336845367214132,
      "grad_norm": 0.001542494399473071,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.0019584753641152773,
      "grad_norm": 0.009143107570707798,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0002,
      "step": 79
    },
    {
      "epoch": 0.0019832661915091415,
      "grad_norm": 0.020335160195827484,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0003,
      "step": 80
    },
    {
      "epoch": 0.002008057018903006,
      "grad_norm": 0.0007250762428157032,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.002008057018903006,
      "eval_loss": 0.006126614287495613,
      "eval_runtime": 3463.0899,
      "eval_samples_per_second": 9.809,
      "eval_steps_per_second": 1.226,
      "step": 81
    },
    {
      "epoch": 0.00203284784629687,
      "grad_norm": 0.006182220298796892,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0001,
      "step": 82
    },
    {
      "epoch": 0.0020576386736907344,
      "grad_norm": 0.0013380810851231217,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 0.0020824295010845985,
      "grad_norm": 0.010265359655022621,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0001,
      "step": 84
    },
    {
      "epoch": 0.002107220328478463,
      "grad_norm": 0.0020443315152078867,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.0021320111558723273,
      "grad_norm": 0.04433085024356842,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0005,
      "step": 86
    },
    {
      "epoch": 0.0021568019832661914,
      "grad_norm": 0.006436903961002827,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.0021815928106600556,
      "grad_norm": 0.0021947952918708324,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 0.00220638363805392,
      "grad_norm": 0.0019828679505735636,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 0.0022311744654477843,
      "grad_norm": 0.008004413917660713,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0001,
      "step": 90
    },
    {
      "epoch": 0.0022311744654477843,
      "eval_loss": 0.004822232760488987,
      "eval_runtime": 3464.2169,
      "eval_samples_per_second": 9.806,
      "eval_steps_per_second": 1.226,
      "step": 90
    },
    {
      "epoch": 0.0022559652928416485,
      "grad_norm": 0.001327146659605205,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 0.002280756120235513,
      "grad_norm": 0.0026161230634897947,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.0,
      "step": 92
    },
    {
      "epoch": 0.002305546947629377,
      "grad_norm": 0.006191144231706858,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.0001,
      "step": 93
    },
    {
      "epoch": 0.0023303377750232414,
      "grad_norm": 0.0058226496912539005,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0001,
      "step": 94
    },
    {
      "epoch": 0.0023551286024171055,
      "grad_norm": 0.002520521404221654,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0001,
      "step": 95
    },
    {
      "epoch": 0.00237991942981097,
      "grad_norm": 0.002172236330807209,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.0024047102572048343,
      "grad_norm": 0.002350907539948821,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 0.0024295010845986984,
      "grad_norm": 0.0026973439380526543,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0001,
      "step": 98
    },
    {
      "epoch": 0.0024542919119925626,
      "grad_norm": 0.07727763801813126,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0013,
      "step": 99
    },
    {
      "epoch": 0.0024542919119925626,
      "eval_loss": 0.0047203367576003075,
      "eval_runtime": 3466.2129,
      "eval_samples_per_second": 9.8,
      "eval_steps_per_second": 1.225,
      "step": 99
    },
    {
      "epoch": 0.002479082739386427,
      "grad_norm": 0.003464354667812586,
      "learning_rate": 0.0,
      "loss": 0.0001,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.6109411688448e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}