{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05494128150539111,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005494128150539112,
      "grad_norm": 0.09600650519132614,
      "learning_rate": 1e-05,
      "loss": 10.8347,
      "step": 1
    },
    {
      "epoch": 0.0005494128150539112,
      "eval_loss": 10.83652400970459,
      "eval_runtime": 25.3592,
      "eval_samples_per_second": 120.903,
      "eval_steps_per_second": 60.451,
      "step": 1
    },
    {
      "epoch": 0.0010988256301078224,
      "grad_norm": 0.11173133552074432,
      "learning_rate": 2e-05,
      "loss": 10.8339,
      "step": 2
    },
    {
      "epoch": 0.0016482384451617334,
      "grad_norm": 0.1001177430152893,
      "learning_rate": 3e-05,
      "loss": 10.8356,
      "step": 3
    },
    {
      "epoch": 0.0021976512602156447,
      "grad_norm": 0.1040872111916542,
      "learning_rate": 4e-05,
      "loss": 10.8343,
      "step": 4
    },
    {
      "epoch": 0.002747064075269556,
      "grad_norm": 0.09792021661996841,
      "learning_rate": 5e-05,
      "loss": 10.8357,
      "step": 5
    },
    {
      "epoch": 0.003296476890323467,
      "grad_norm": 0.09441577643156052,
      "learning_rate": 6e-05,
      "loss": 10.835,
      "step": 6
    },
    {
      "epoch": 0.003845889705377378,
      "grad_norm": 0.11089451611042023,
      "learning_rate": 7e-05,
      "loss": 10.8338,
      "step": 7
    },
    {
      "epoch": 0.0043953025204312894,
      "grad_norm": 0.09310828894376755,
      "learning_rate": 8e-05,
      "loss": 10.8346,
      "step": 8
    },
    {
      "epoch": 0.0049447153354852,
      "grad_norm": 0.09884480386972427,
      "learning_rate": 9e-05,
      "loss": 10.835,
      "step": 9
    },
    {
      "epoch": 0.005494128150539112,
      "grad_norm": 0.12582162022590637,
      "learning_rate": 0.0001,
      "loss": 10.8333,
      "step": 10
    },
    {
      "epoch": 0.006043540965593022,
      "grad_norm": 0.11061394959688187,
      "learning_rate": 9.99695413509548e-05,
      "loss": 10.8362,
      "step": 11
    },
    {
      "epoch": 0.006592953780646934,
      "grad_norm": 0.09800900518894196,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.8297,
      "step": 12
    },
    {
      "epoch": 0.007142366595700844,
      "grad_norm": 0.11028425395488739,
      "learning_rate": 9.972609476841367e-05,
      "loss": 10.8357,
      "step": 13
    },
    {
      "epoch": 0.007691779410754756,
      "grad_norm": 0.11087824404239655,
      "learning_rate": 9.951340343707852e-05,
      "loss": 10.8324,
      "step": 14
    },
    {
      "epoch": 0.008241192225808667,
      "grad_norm": 0.1042320504784584,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.8347,
      "step": 15
    },
    {
      "epoch": 0.008790605040862579,
      "grad_norm": 0.10207958519458771,
      "learning_rate": 9.890738003669029e-05,
      "loss": 10.8362,
      "step": 16
    },
    {
      "epoch": 0.00934001785591649,
      "grad_norm": 0.10438362509012222,
      "learning_rate": 9.851478631379982e-05,
      "loss": 10.8327,
      "step": 17
    },
    {
      "epoch": 0.0098894306709704,
      "grad_norm": 0.1137293353676796,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.832,
      "step": 18
    },
    {
      "epoch": 0.01043884348602431,
      "grad_norm": 0.10011179000139236,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.8308,
      "step": 19
    },
    {
      "epoch": 0.010988256301078223,
      "grad_norm": 0.11841128021478653,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.8312,
      "step": 20
    },
    {
      "epoch": 0.011537669116132134,
      "grad_norm": 0.12272407114505768,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.8299,
      "step": 21
    },
    {
      "epoch": 0.012087081931186044,
      "grad_norm": 0.12626005709171295,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.8311,
      "step": 22
    },
    {
      "epoch": 0.012636494746239957,
      "grad_norm": 0.11208302527666092,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.8293,
      "step": 23
    },
    {
      "epoch": 0.013185907561293867,
      "grad_norm": 0.11252301931381226,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.8326,
      "step": 24
    },
    {
      "epoch": 0.013735320376347778,
      "grad_norm": 0.12755857408046722,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.828,
      "step": 25
    },
    {
      "epoch": 0.013735320376347778,
      "eval_loss": 10.828333854675293,
      "eval_runtime": 14.0013,
      "eval_samples_per_second": 218.98,
      "eval_steps_per_second": 109.49,
      "step": 25
    },
    {
      "epoch": 0.014284733191401689,
      "grad_norm": 0.10949414223432541,
      "learning_rate": 9.24024048078213e-05,
      "loss": 10.8323,
      "step": 26
    },
    {
      "epoch": 0.014834146006455601,
      "grad_norm": 0.12477957457304001,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.826,
      "step": 27
    },
    {
      "epoch": 0.015383558821509512,
      "grad_norm": 0.1223072037100792,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.8298,
      "step": 28
    },
    {
      "epoch": 0.015932971636563424,
      "grad_norm": 0.11999625712633133,
      "learning_rate": 8.940053768033609e-05,
      "loss": 10.824,
      "step": 29
    },
    {
      "epoch": 0.016482384451617333,
      "grad_norm": 0.12540574371814728,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.8277,
      "step": 30
    },
    {
      "epoch": 0.017031797266671245,
      "grad_norm": 0.13100536167621613,
      "learning_rate": 8.715724127386972e-05,
      "loss": 10.8219,
      "step": 31
    },
    {
      "epoch": 0.017581210081725158,
      "grad_norm": 0.128668412566185,
      "learning_rate": 8.596699001693255e-05,
      "loss": 10.8246,
      "step": 32
    },
    {
      "epoch": 0.018130622896779067,
      "grad_norm": 0.11359424144029617,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.8271,
      "step": 33
    },
    {
      "epoch": 0.01868003571183298,
      "grad_norm": 0.12260546535253525,
      "learning_rate": 8.345653031794292e-05,
      "loss": 10.8207,
      "step": 34
    },
    {
      "epoch": 0.019229448526886888,
      "grad_norm": 0.13337105512619019,
      "learning_rate": 8.213938048432697e-05,
      "loss": 10.8189,
      "step": 35
    },
    {
      "epoch": 0.0197788613419408,
      "grad_norm": 0.1408015340566635,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.8277,
      "step": 36
    },
    {
      "epoch": 0.020328274156994713,
      "grad_norm": 0.12261249870061874,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.8242,
      "step": 37
    },
    {
      "epoch": 0.02087768697204862,
      "grad_norm": 0.12526747584342957,
      "learning_rate": 7.795964517353735e-05,
      "loss": 10.8273,
      "step": 38
    },
    {
      "epoch": 0.021427099787102534,
      "grad_norm": 0.12910766899585724,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.824,
      "step": 39
    },
    {
      "epoch": 0.021976512602156446,
      "grad_norm": 0.1519177109003067,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.8164,
      "step": 40
    },
    {
      "epoch": 0.022525925417210355,
      "grad_norm": 0.14746390283107758,
      "learning_rate": 7.347357813929454e-05,
      "loss": 10.8221,
      "step": 41
    },
    {
      "epoch": 0.023075338232264268,
      "grad_norm": 0.12614132463932037,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.8211,
      "step": 42
    },
    {
      "epoch": 0.02362475104731818,
      "grad_norm": 0.1671351045370102,
      "learning_rate": 7.033683215379002e-05,
      "loss": 10.8163,
      "step": 43
    },
    {
      "epoch": 0.02417416386237209,
      "grad_norm": 0.12974338233470917,
      "learning_rate": 6.873032967079561e-05,
      "loss": 10.8187,
      "step": 44
    },
    {
      "epoch": 0.024723576677426,
      "grad_norm": 0.1563933938741684,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.8121,
      "step": 45
    },
    {
      "epoch": 0.025272989492479914,
      "grad_norm": 0.15365718305110931,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.8147,
      "step": 46
    },
    {
      "epoch": 0.025822402307533823,
      "grad_norm": 0.17594094574451447,
      "learning_rate": 6.378186779084995e-05,
      "loss": 10.8136,
      "step": 47
    },
    {
      "epoch": 0.026371815122587735,
      "grad_norm": 0.15102382004261017,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.8187,
      "step": 48
    },
    {
      "epoch": 0.026921227937641644,
      "grad_norm": 0.15570496022701263,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 10.8184,
      "step": 49
    },
    {
      "epoch": 0.027470640752695556,
      "grad_norm": 0.17091411352157593,
      "learning_rate": 5.868240888334653e-05,
      "loss": 10.8095,
      "step": 50
    },
    {
      "epoch": 0.027470640752695556,
      "eval_loss": 10.815298080444336,
      "eval_runtime": 13.8507,
      "eval_samples_per_second": 221.361,
      "eval_steps_per_second": 110.681,
      "step": 50
    },
    {
      "epoch": 0.02802005356774947,
      "grad_norm": 0.16749072074890137,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.8153,
      "step": 51
    },
    {
      "epoch": 0.028569466382803377,
      "grad_norm": 0.20695950090885162,
      "learning_rate": 5.522642316338268e-05,
      "loss": 10.8049,
      "step": 52
    },
    {
      "epoch": 0.02911887919785729,
      "grad_norm": 0.17667506635189056,
      "learning_rate": 5.348782368720626e-05,
      "loss": 10.8138,
      "step": 53
    },
    {
      "epoch": 0.029668292012911202,
      "grad_norm": 0.1662524938583374,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.8134,
      "step": 54
    },
    {
      "epoch": 0.03021770482796511,
      "grad_norm": 0.17990642786026,
      "learning_rate": 5e-05,
      "loss": 10.8107,
      "step": 55
    },
    {
      "epoch": 0.030767117643019024,
      "grad_norm": 0.1645970642566681,
      "learning_rate": 4.825502516487497e-05,
      "loss": 10.8116,
      "step": 56
    },
    {
      "epoch": 0.031316530458072936,
      "grad_norm": 0.16238118708133698,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.8175,
      "step": 57
    },
    {
      "epoch": 0.03186594327312685,
      "grad_norm": 0.17180070281028748,
      "learning_rate": 4.477357683661734e-05,
      "loss": 10.8095,
      "step": 58
    },
    {
      "epoch": 0.032415356088180754,
      "grad_norm": 0.19333012402057648,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 10.8041,
      "step": 59
    },
    {
      "epoch": 0.032964768903234666,
      "grad_norm": 0.1807578206062317,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.81,
      "step": 60
    },
    {
      "epoch": 0.03351418171828858,
      "grad_norm": 0.1692892611026764,
      "learning_rate": 3.960441545911204e-05,
      "loss": 10.8077,
      "step": 61
    },
    {
      "epoch": 0.03406359453334249,
      "grad_norm": 0.17745496332645416,
      "learning_rate": 3.790390522001662e-05,
      "loss": 10.8102,
      "step": 62
    },
    {
      "epoch": 0.0346130073483964,
      "grad_norm": 0.1852971315383911,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.8103,
      "step": 63
    },
    {
      "epoch": 0.035162420163450316,
      "grad_norm": 0.19535671174526215,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.8071,
      "step": 64
    },
    {
      "epoch": 0.03571183297850422,
      "grad_norm": 0.19186407327651978,
      "learning_rate": 3.289899283371657e-05,
      "loss": 10.8055,
      "step": 65
    },
    {
      "epoch": 0.03626124579355813,
      "grad_norm": 0.18476377427577972,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.8102,
      "step": 66
    },
    {
      "epoch": 0.036810658608612046,
      "grad_norm": 0.19189932942390442,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 10.8072,
      "step": 67
    },
    {
      "epoch": 0.03736007142366596,
      "grad_norm": 0.20658567547798157,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 10.8069,
      "step": 68
    },
    {
      "epoch": 0.03790948423871987,
      "grad_norm": 0.17630618810653687,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.8047,
      "step": 69
    },
    {
      "epoch": 0.038458897053773776,
      "grad_norm": 0.18739624321460724,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.8088,
      "step": 70
    },
    {
      "epoch": 0.03900830986882769,
      "grad_norm": 0.20612762868404388,
      "learning_rate": 2.350403678833976e-05,
      "loss": 10.804,
      "step": 71
    },
    {
      "epoch": 0.0395577226838816,
      "grad_norm": 0.17694811522960663,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.8049,
      "step": 72
    },
    {
      "epoch": 0.04010713549893551,
      "grad_norm": 0.2062751203775406,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.8003,
      "step": 73
    },
    {
      "epoch": 0.040656548313989425,
      "grad_norm": 0.2096233367919922,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 10.7996,
      "step": 74
    },
    {
      "epoch": 0.04120596112904334,
      "grad_norm": 0.1980363428592682,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.8074,
      "step": 75
    },
    {
      "epoch": 0.04120596112904334,
      "eval_loss": 10.805519104003906,
      "eval_runtime": 13.9152,
      "eval_samples_per_second": 220.335,
      "eval_steps_per_second": 110.168,
      "step": 75
    },
    {
      "epoch": 0.04175537394409724,
      "grad_norm": 0.18881097435951233,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 10.805,
      "step": 76
    },
    {
      "epoch": 0.042304786759151156,
      "grad_norm": 0.208832249045372,
      "learning_rate": 1.526708147705013e-05,
      "loss": 10.8029,
      "step": 77
    },
    {
      "epoch": 0.04285419957420507,
      "grad_norm": 0.19329778850078583,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.802,
      "step": 78
    },
    {
      "epoch": 0.04340361238925898,
      "grad_norm": 0.20163513720035553,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 10.8032,
      "step": 79
    },
    {
      "epoch": 0.04395302520431289,
      "grad_norm": 0.19688774645328522,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 10.8037,
      "step": 80
    },
    {
      "epoch": 0.044502438019366805,
      "grad_norm": 0.19582399725914001,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.8032,
      "step": 81
    },
    {
      "epoch": 0.04505185083442071,
      "grad_norm": 0.16219070553779602,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.8132,
      "step": 82
    },
    {
      "epoch": 0.04560126364947462,
      "grad_norm": 0.21864815056324005,
      "learning_rate": 8.548121372247918e-06,
      "loss": 10.8021,
      "step": 83
    },
    {
      "epoch": 0.046150676464528535,
      "grad_norm": 0.1872103065252304,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.8065,
      "step": 84
    },
    {
      "epoch": 0.04670008927958245,
      "grad_norm": 0.21468770503997803,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.8071,
      "step": 85
    },
    {
      "epoch": 0.04724950209463636,
      "grad_norm": 0.2009747177362442,
      "learning_rate": 5.852620357053651e-06,
      "loss": 10.8053,
      "step": 86
    },
    {
      "epoch": 0.047798914909690265,
      "grad_norm": 0.20177090167999268,
      "learning_rate": 5.060297685041659e-06,
      "loss": 10.8031,
      "step": 87
    },
    {
      "epoch": 0.04834832772474418,
      "grad_norm": 0.18578961491584778,
      "learning_rate": 4.322727117869951e-06,
      "loss": 10.8091,
      "step": 88
    },
    {
      "epoch": 0.04889774053979809,
      "grad_norm": 0.20493243634700775,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 10.7979,
      "step": 89
    },
    {
      "epoch": 0.049447153354852,
      "grad_norm": 0.19400815665721893,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.8031,
      "step": 90
    },
    {
      "epoch": 0.049996566169905915,
      "grad_norm": 0.20439405739307404,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.8008,
      "step": 91
    },
    {
      "epoch": 0.05054597898495983,
      "grad_norm": 0.21862730383872986,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 10.8059,
      "step": 92
    },
    {
      "epoch": 0.05109539180001373,
      "grad_norm": 0.1954014152288437,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 10.8072,
      "step": 93
    },
    {
      "epoch": 0.051644804615067645,
      "grad_norm": 0.19296152889728546,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 10.8057,
      "step": 94
    },
    {
      "epoch": 0.05219421743012156,
      "grad_norm": 0.20052501559257507,
      "learning_rate": 7.596123493895991e-07,
      "loss": 10.7977,
      "step": 95
    },
    {
      "epoch": 0.05274363024517547,
      "grad_norm": 0.20131036639213562,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.8016,
      "step": 96
    },
    {
      "epoch": 0.05329304306022938,
      "grad_norm": 0.20154723525047302,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 10.802,
      "step": 97
    },
    {
      "epoch": 0.05384245587528329,
      "grad_norm": 0.171908438205719,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 10.8097,
      "step": 98
    },
    {
      "epoch": 0.0543918686903372,
      "grad_norm": 0.18649089336395264,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.8051,
      "step": 99
    },
    {
      "epoch": 0.05494128150539111,
      "grad_norm": 0.21302233636379242,
      "learning_rate": 0.0,
      "loss": 10.8014,
      "step": 100
    },
    {
      "epoch": 0.05494128150539111,
      "eval_loss": 10.80360221862793,
      "eval_runtime": 13.7784,
      "eval_samples_per_second": 222.522,
      "eval_steps_per_second": 111.261,
      "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": 57297658970112.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}