{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03566333808844508,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003566333808844508,
      "grad_norm": 9.774100303649902,
      "learning_rate": 1e-05,
      "loss": 4.3855,
      "step": 1
    },
    {
      "epoch": 0.0007132667617689016,
      "grad_norm": 6.548297882080078,
      "learning_rate": 2e-05,
      "loss": 3.1545,
      "step": 2
    },
    {
      "epoch": 0.0010699001426533524,
      "grad_norm": 7.257200241088867,
      "learning_rate": 3e-05,
      "loss": 3.3344,
      "step": 3
    },
    {
      "epoch": 0.0014265335235378032,
      "grad_norm": 6.974522113800049,
      "learning_rate": 4e-05,
      "loss": 3.152,
      "step": 4
    },
    {
      "epoch": 0.001783166904422254,
      "grad_norm": 8.030047416687012,
      "learning_rate": 5e-05,
      "loss": 3.5981,
      "step": 5
    },
    {
      "epoch": 0.0021398002853067048,
      "grad_norm": 8.43385124206543,
      "learning_rate": 6e-05,
      "loss": 3.3772,
      "step": 6
    },
    {
      "epoch": 0.0024964336661911554,
      "grad_norm": 6.553490161895752,
      "learning_rate": 7e-05,
      "loss": 2.7528,
      "step": 7
    },
    {
      "epoch": 0.0028530670470756064,
      "grad_norm": 5.480027675628662,
      "learning_rate": 8e-05,
      "loss": 2.5841,
      "step": 8
    },
    {
      "epoch": 0.003209700427960057,
      "grad_norm": 5.729024887084961,
      "learning_rate": 9e-05,
      "loss": 2.5566,
      "step": 9
    },
    {
      "epoch": 0.003566333808844508,
      "grad_norm": 6.299459934234619,
      "learning_rate": 0.0001,
      "loss": 2.656,
      "step": 10
    },
    {
      "epoch": 0.0039229671897289585,
      "grad_norm": 5.80184268951416,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.2856,
      "step": 11
    },
    {
      "epoch": 0.0042796005706134095,
      "grad_norm": 5.892313003540039,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.4129,
      "step": 12
    },
    {
      "epoch": 0.0046362339514978606,
      "grad_norm": 4.244318008422852,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.697,
      "step": 13
    },
    {
      "epoch": 0.004992867332382311,
      "grad_norm": 3.284872531890869,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.9739,
      "step": 14
    },
    {
      "epoch": 0.005349500713266762,
      "grad_norm": 4.807908058166504,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.6373,
      "step": 15
    },
    {
      "epoch": 0.005706134094151213,
      "grad_norm": 5.345113277435303,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.3676,
      "step": 16
    },
    {
      "epoch": 0.006062767475035664,
      "grad_norm": 3.9351136684417725,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.0759,
      "step": 17
    },
    {
      "epoch": 0.006419400855920114,
      "grad_norm": 4.3018412590026855,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.8651,
      "step": 18
    },
    {
      "epoch": 0.006776034236804565,
      "grad_norm": 3.912882089614868,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.6577,
      "step": 19
    },
    {
      "epoch": 0.007132667617689016,
      "grad_norm": 3.2970550060272217,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.7112,
      "step": 20
    },
    {
      "epoch": 0.007489300998573466,
      "grad_norm": 4.662540435791016,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.7851,
      "step": 21
    },
    {
      "epoch": 0.007845934379457917,
      "grad_norm": 4.208030700683594,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.8795,
      "step": 22
    },
    {
      "epoch": 0.008202567760342368,
      "grad_norm": 3.992008924484253,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.9006,
      "step": 23
    },
    {
      "epoch": 0.008559201141226819,
      "grad_norm": 3.2357306480407715,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.7336,
      "step": 24
    },
    {
      "epoch": 0.00891583452211127,
      "grad_norm": 4.444036483764648,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.7507,
      "step": 25
    },
    {
      "epoch": 0.009272467902995721,
      "grad_norm": 2.9058542251586914,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.5678,
      "step": 26
    },
    {
      "epoch": 0.00962910128388017,
      "grad_norm": 2.881979465484619,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.522,
      "step": 27
    },
    {
      "epoch": 0.009985734664764621,
      "grad_norm": 6.814059257507324,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7406,
      "step": 28
    },
    {
      "epoch": 0.010342368045649072,
      "grad_norm": 2.85461163520813,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.535,
      "step": 29
    },
    {
      "epoch": 0.010699001426533523,
      "grad_norm": 4.374093532562256,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.918,
      "step": 30
    },
    {
      "epoch": 0.011055634807417974,
      "grad_norm": 4.2099080085754395,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.8811,
      "step": 31
    },
    {
      "epoch": 0.011412268188302425,
      "grad_norm": 3.8226873874664307,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.6557,
      "step": 32
    },
    {
      "epoch": 0.011768901569186876,
      "grad_norm": 4.4234700202941895,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.9053,
      "step": 33
    },
    {
      "epoch": 0.012125534950071327,
      "grad_norm": 3.8180363178253174,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.7339,
      "step": 34
    },
    {
      "epoch": 0.012482168330955777,
      "grad_norm": 3.6584701538085938,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.6399,
      "step": 35
    },
    {
      "epoch": 0.012838801711840228,
      "grad_norm": 3.0617523193359375,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.6536,
      "step": 36
    },
    {
      "epoch": 0.013195435092724679,
      "grad_norm": 3.4767324924468994,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8274,
      "step": 37
    },
    {
      "epoch": 0.01355206847360913,
      "grad_norm": 3.2626168727874756,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.5745,
      "step": 38
    },
    {
      "epoch": 0.01390870185449358,
      "grad_norm": 2.738389492034912,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.6844,
      "step": 39
    },
    {
      "epoch": 0.014265335235378032,
      "grad_norm": 3.461836576461792,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.887,
      "step": 40
    },
    {
      "epoch": 0.014621968616262483,
      "grad_norm": 2.5409317016601562,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.6947,
      "step": 41
    },
    {
      "epoch": 0.014978601997146932,
      "grad_norm": 1.8447601795196533,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.3823,
      "step": 42
    },
    {
      "epoch": 0.015335235378031383,
      "grad_norm": 2.9046192169189453,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.7798,
      "step": 43
    },
    {
      "epoch": 0.015691868758915834,
      "grad_norm": 2.498103141784668,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.5778,
      "step": 44
    },
    {
      "epoch": 0.016048502139800285,
      "grad_norm": 2.751084566116333,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.4831,
      "step": 45
    },
    {
      "epoch": 0.016405135520684736,
      "grad_norm": 2.245828628540039,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.4149,
      "step": 46
    },
    {
      "epoch": 0.016761768901569187,
      "grad_norm": 3.826903820037842,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.8814,
      "step": 47
    },
    {
      "epoch": 0.017118402282453638,
      "grad_norm": 3.1380362510681152,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.5521,
      "step": 48
    },
    {
      "epoch": 0.01747503566333809,
      "grad_norm": 3.0199174880981445,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.7336,
      "step": 49
    },
    {
      "epoch": 0.01783166904422254,
      "grad_norm": 2.6297054290771484,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.6997,
      "step": 50
    },
    {
      "epoch": 0.01818830242510699,
      "grad_norm": 3.390153169631958,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.8219,
      "step": 51
    },
    {
      "epoch": 0.018544935805991442,
      "grad_norm": 3.1203787326812744,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.6488,
      "step": 52
    },
    {
      "epoch": 0.018901569186875893,
      "grad_norm": 2.848087787628174,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.6625,
      "step": 53
    },
    {
      "epoch": 0.01925820256776034,
      "grad_norm": 1.9604121446609497,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.3796,
      "step": 54
    },
    {
      "epoch": 0.019614835948644792,
      "grad_norm": 2.3012568950653076,
      "learning_rate": 5e-05,
      "loss": 0.5187,
      "step": 55
    },
    {
      "epoch": 0.019971469329529243,
      "grad_norm": 2.307490825653076,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.4771,
      "step": 56
    },
    {
      "epoch": 0.020328102710413694,
      "grad_norm": 3.150341033935547,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.8166,
      "step": 57
    },
    {
      "epoch": 0.020684736091298145,
      "grad_norm": 3.0458898544311523,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.7438,
      "step": 58
    },
    {
      "epoch": 0.021041369472182596,
      "grad_norm": 3.054081439971924,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.7589,
      "step": 59
    },
    {
      "epoch": 0.021398002853067047,
      "grad_norm": 3.3433187007904053,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.7532,
      "step": 60
    },
    {
      "epoch": 0.021754636233951498,
      "grad_norm": 1.860802412033081,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.2933,
      "step": 61
    },
    {
      "epoch": 0.02211126961483595,
      "grad_norm": 1.9675403833389282,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.4654,
      "step": 62
    },
    {
      "epoch": 0.0224679029957204,
      "grad_norm": 2.4809985160827637,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.5167,
      "step": 63
    },
    {
      "epoch": 0.02282453637660485,
      "grad_norm": 2.7916054725646973,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6389,
      "step": 64
    },
    {
      "epoch": 0.023181169757489302,
      "grad_norm": 2.9464380741119385,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.8379,
      "step": 65
    },
    {
      "epoch": 0.023537803138373753,
      "grad_norm": 2.0889384746551514,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.6764,
      "step": 66
    },
    {
      "epoch": 0.023894436519258204,
      "grad_norm": 1.9802026748657227,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.4098,
      "step": 67
    },
    {
      "epoch": 0.024251069900142655,
      "grad_norm": 2.649928331375122,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.7426,
      "step": 68
    },
    {
      "epoch": 0.024607703281027102,
      "grad_norm": 2.019575357437134,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.4589,
      "step": 69
    },
    {
      "epoch": 0.024964336661911554,
      "grad_norm": 2.0410661697387695,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.4953,
      "step": 70
    },
    {
      "epoch": 0.025320970042796005,
      "grad_norm": 3.207294464111328,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.6211,
      "step": 71
    },
    {
      "epoch": 0.025677603423680456,
      "grad_norm": 2.813213348388672,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.769,
      "step": 72
    },
    {
      "epoch": 0.026034236804564907,
      "grad_norm": 2.10286283493042,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.5105,
      "step": 73
    },
    {
      "epoch": 0.026390870185449358,
      "grad_norm": 2.057298183441162,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.4323,
      "step": 74
    },
    {
      "epoch": 0.02674750356633381,
      "grad_norm": 2.6843760013580322,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.7312,
      "step": 75
    },
    {
      "epoch": 0.02710413694721826,
      "grad_norm": 1.9968925714492798,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.508,
      "step": 76
    },
    {
      "epoch": 0.02746077032810271,
      "grad_norm": 2.609607696533203,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.542,
      "step": 77
    },
    {
      "epoch": 0.02781740370898716,
      "grad_norm": 2.267988443374634,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.413,
      "step": 78
    },
    {
      "epoch": 0.028174037089871613,
      "grad_norm": 2.5811314582824707,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.7585,
      "step": 79
    },
    {
      "epoch": 0.028530670470756064,
      "grad_norm": 2.054327964782715,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.4524,
      "step": 80
    },
    {
      "epoch": 0.028887303851640515,
      "grad_norm": 2.4103705883026123,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.6176,
      "step": 81
    },
    {
      "epoch": 0.029243937232524966,
      "grad_norm": 2.5763814449310303,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.696,
      "step": 82
    },
    {
      "epoch": 0.029600570613409417,
      "grad_norm": 2.2559149265289307,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.4984,
      "step": 83
    },
    {
      "epoch": 0.029957203994293864,
      "grad_norm": 1.892920970916748,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.4141,
      "step": 84
    },
    {
      "epoch": 0.030313837375178315,
      "grad_norm": 2.494680404663086,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.5068,
      "step": 85
    },
    {
      "epoch": 0.030670470756062766,
      "grad_norm": 3.0079333782196045,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.8526,
      "step": 86
    },
    {
      "epoch": 0.031027104136947217,
      "grad_norm": 2.6471354961395264,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.6676,
      "step": 87
    },
    {
      "epoch": 0.03138373751783167,
      "grad_norm": 2.3440585136413574,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.5147,
      "step": 88
    },
    {
      "epoch": 0.03174037089871612,
      "grad_norm": 2.2918765544891357,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.5938,
      "step": 89
    },
    {
      "epoch": 0.03209700427960057,
      "grad_norm": 2.1986241340637207,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.4577,
      "step": 90
    },
    {
      "epoch": 0.03245363766048502,
      "grad_norm": 2.8510165214538574,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.571,
      "step": 91
    },
    {
      "epoch": 0.03281027104136947,
      "grad_norm": 2.722109079360962,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.4728,
      "step": 92
    },
    {
      "epoch": 0.03316690442225392,
      "grad_norm": 1.798582911491394,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.3732,
      "step": 93
    },
    {
      "epoch": 0.033523537803138374,
      "grad_norm": 1.8506275415420532,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.536,
      "step": 94
    },
    {
      "epoch": 0.033880171184022825,
      "grad_norm": 2.3318088054656982,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.6051,
      "step": 95
    },
    {
      "epoch": 0.034236804564907276,
      "grad_norm": 2.459251642227173,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.6138,
      "step": 96
    },
    {
      "epoch": 0.03459343794579173,
      "grad_norm": 2.914124011993408,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.5388,
      "step": 97
    },
    {
      "epoch": 0.03495007132667618,
      "grad_norm": 2.980940103530884,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.7465,
      "step": 98
    },
    {
      "epoch": 0.03530670470756063,
      "grad_norm": 2.870051145553589,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.7109,
      "step": 99
    },
    {
      "epoch": 0.03566333808844508,
      "grad_norm": 1.8577947616577148,
      "learning_rate": 0.0,
      "loss": 0.341,
      "step": 100
    },
    {
      "epoch": 0.03566333808844508,
      "eval_loss": 0.5502559542655945,
      "eval_runtime": 58.5948,
      "eval_samples_per_second": 7.816,
      "eval_steps_per_second": 7.816,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5000973307084800.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}