{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.014551407393933883,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014551407393933883,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.00014551407393933883,
      "eval_loss": NaN,
      "eval_runtime": 683.2128,
      "eval_samples_per_second": 16.942,
      "eval_steps_per_second": 8.472,
      "step": 1
    },
    {
      "epoch": 0.00029102814787867765,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.4033,
      "step": 2
    },
    {
      "epoch": 0.0004365422218180165,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0005820562957573553,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0007275703696966941,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 1.055,
      "step": 5
    },
    {
      "epoch": 0.000873084443636033,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0010185985175753718,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 79.0395,
      "step": 7
    },
    {
      "epoch": 0.0011641125915147106,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0013096266654540494,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 614.4304,
      "step": 9
    },
    {
      "epoch": 0.0014551407393933883,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.001600654813332727,
      "grad_norm": NaN,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.001746168887272066,
      "grad_norm": NaN,
      "learning_rate": 9.987820251299122e-05,
      "loss": 27.9699,
      "step": 12
    },
    {
      "epoch": 0.0018916829612114047,
      "grad_norm": NaN,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.1398,
      "step": 13
    },
    {
      "epoch": 0.0020371970351507436,
      "grad_norm": NaN,
      "learning_rate": 9.951340343707852e-05,
      "loss": 322.9458,
      "step": 14
    },
    {
      "epoch": 0.0021827111090900824,
      "grad_norm": NaN,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0023282251830294212,
      "grad_norm": NaN,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.00247373925696876,
      "grad_norm": NaN,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1829.8519,
      "step": 17
    },
    {
      "epoch": 0.002619253330908099,
      "grad_norm": NaN,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0027647674048474377,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.5466,
      "step": 19
    },
    {
      "epoch": 0.0029102814787867765,
      "grad_norm": NaN,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.5196,
      "step": 20
    },
    {
      "epoch": 0.0030557955527261154,
      "grad_norm": NaN,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.003201309626665454,
      "grad_norm": NaN,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.7301,
      "step": 22
    },
    {
      "epoch": 0.003346823700604793,
      "grad_norm": NaN,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.0033,
      "step": 23
    },
    {
      "epoch": 0.003492337774544132,
      "grad_norm": NaN,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0036378518484834707,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.9755,
      "step": 25
    },
    {
      "epoch": 0.0036378518484834707,
      "eval_loss": NaN,
      "eval_runtime": 671.1088,
      "eval_samples_per_second": 17.248,
      "eval_steps_per_second": 8.625,
      "step": 25
    },
    {
      "epoch": 0.0037833659224228095,
      "grad_norm": NaN,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.003928879996362148,
      "grad_norm": NaN,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1030.2118,
      "step": 27
    },
    {
      "epoch": 0.004074394070301487,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 26.7243,
      "step": 28
    },
    {
      "epoch": 0.0042199081442408255,
      "grad_norm": NaN,
      "learning_rate": 8.940053768033609e-05,
      "loss": 166.2636,
      "step": 29
    },
    {
      "epoch": 0.004365422218180165,
      "grad_norm": NaN,
      "learning_rate": 8.83022221559489e-05,
      "loss": 12.1136,
      "step": 30
    },
    {
      "epoch": 0.004510936292119503,
      "grad_norm": NaN,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.0046564503660588424,
      "grad_norm": NaN,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.9216,
      "step": 32
    },
    {
      "epoch": 0.004801964439998181,
      "grad_norm": NaN,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.8871,
      "step": 33
    },
    {
      "epoch": 0.00494747851393752,
      "grad_norm": NaN,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.0050929925878768585,
      "grad_norm": NaN,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0417,
      "step": 35
    },
    {
      "epoch": 0.005238506661816198,
      "grad_norm": NaN,
      "learning_rate": 8.07830737662829e-05,
      "loss": 285.9546,
      "step": 36
    },
    {
      "epoch": 0.005384020735755536,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 5.9744,
      "step": 37
    },
    {
      "epoch": 0.005529534809694875,
      "grad_norm": NaN,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.005675048883634214,
      "grad_norm": NaN,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.005820562957573553,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1151.3813,
      "step": 40
    },
    {
      "epoch": 0.0059660770315128914,
      "grad_norm": NaN,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.006111591105452231,
      "grad_norm": NaN,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.006257105179391569,
      "grad_norm": NaN,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.006402619253330908,
      "grad_norm": NaN,
      "learning_rate": 6.873032967079561e-05,
      "loss": 284.621,
      "step": 44
    },
    {
      "epoch": 0.006548133327270247,
      "grad_norm": NaN,
      "learning_rate": 6.710100716628344e-05,
      "loss": 919.1181,
      "step": 45
    },
    {
      "epoch": 0.006693647401209586,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.006839161475148924,
      "grad_norm": NaN,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.006984675549088264,
      "grad_norm": NaN,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.2871,
      "step": 48
    },
    {
      "epoch": 0.007130189623027602,
      "grad_norm": NaN,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 207.4022,
      "step": 49
    },
    {
      "epoch": 0.007275703696966941,
      "grad_norm": NaN,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.007275703696966941,
      "eval_loss": NaN,
      "eval_runtime": 486.4771,
      "eval_samples_per_second": 23.794,
      "eval_steps_per_second": 11.898,
      "step": 50
    },
    {
      "epoch": 0.00742121777090628,
      "grad_norm": NaN,
      "learning_rate": 5.695865504800327e-05,
      "loss": 695.8876,
      "step": 51
    },
    {
      "epoch": 0.007566731844845619,
      "grad_norm": NaN,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0448,
      "step": 52
    },
    {
      "epoch": 0.007712245918784957,
      "grad_norm": NaN,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.007857759992724296,
      "grad_norm": NaN,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1894.3701,
      "step": 54
    },
    {
      "epoch": 0.008003274066663636,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.008148788140602974,
      "grad_norm": NaN,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.008294302214542313,
      "grad_norm": NaN,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.008439816288481651,
      "grad_norm": NaN,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.008585330362420991,
      "grad_norm": NaN,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.00873084443636033,
      "grad_norm": NaN,
      "learning_rate": 4.131759111665349e-05,
      "loss": 4.4834,
      "step": 60
    },
    {
      "epoch": 0.008876358510299668,
      "grad_norm": NaN,
      "learning_rate": 3.960441545911204e-05,
      "loss": 3.3222,
      "step": 61
    },
    {
      "epoch": 0.009021872584239006,
      "grad_norm": NaN,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.6483,
      "step": 62
    },
    {
      "epoch": 0.009167386658178346,
      "grad_norm": NaN,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.5401,
      "step": 63
    },
    {
      "epoch": 0.009312900732117685,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.009458414806057023,
      "grad_norm": NaN,
      "learning_rate": 3.289899283371657e-05,
      "loss": 246.4682,
      "step": 65
    },
    {
      "epoch": 0.009603928879996362,
      "grad_norm": NaN,
      "learning_rate": 3.12696703292044e-05,
      "loss": 6.8512,
      "step": 66
    },
    {
      "epoch": 0.009749442953935702,
      "grad_norm": NaN,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.00989495702787504,
      "grad_norm": NaN,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.010040471101814379,
      "grad_norm": NaN,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.1364,
      "step": 69
    },
    {
      "epoch": 0.010185985175753717,
      "grad_norm": NaN,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.010331499249693057,
      "grad_norm": NaN,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.010477013323632395,
      "grad_norm": NaN,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0832,
      "step": 72
    },
    {
      "epoch": 0.010622527397571734,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 564.688,
      "step": 73
    },
    {
      "epoch": 0.010768041471511072,
      "grad_norm": NaN,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.010913555545450412,
      "grad_norm": NaN,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.010913555545450412,
      "eval_loss": NaN,
      "eval_runtime": 490.0061,
      "eval_samples_per_second": 23.622,
      "eval_steps_per_second": 11.812,
      "step": 75
    },
    {
      "epoch": 0.01105906961938975,
      "grad_norm": NaN,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 0.01120458369332909,
      "grad_norm": NaN,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.8149,
      "step": 77
    },
    {
      "epoch": 0.011350097767268428,
      "grad_norm": NaN,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.011495611841207766,
      "grad_norm": NaN,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 27.1689,
      "step": 79
    },
    {
      "epoch": 0.011641125915147106,
      "grad_norm": NaN,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.011786639989086444,
      "grad_norm": NaN,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.011932154063025783,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 0.012077668136965121,
      "grad_norm": NaN,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.0737,
      "step": 83
    },
    {
      "epoch": 0.012223182210904461,
      "grad_norm": NaN,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.4136,
      "step": 84
    },
    {
      "epoch": 0.0123686962848438,
      "grad_norm": NaN,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.7889,
      "step": 85
    },
    {
      "epoch": 0.012514210358783138,
      "grad_norm": NaN,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0,
      "step": 86
    },
    {
      "epoch": 0.012659724432722477,
      "grad_norm": NaN,
      "learning_rate": 5.060297685041659e-06,
      "loss": 3.8622,
      "step": 87
    },
    {
      "epoch": 0.012805238506661817,
      "grad_norm": NaN,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 0.012950752580601155,
      "grad_norm": NaN,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.5282,
      "step": 89
    },
    {
      "epoch": 0.013096266654540493,
      "grad_norm": NaN,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.013241780728479832,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 0.013387294802419172,
      "grad_norm": NaN,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.046,
      "step": 92
    },
    {
      "epoch": 0.01353280887635851,
      "grad_norm": NaN,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 0.013678322950297849,
      "grad_norm": NaN,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0549,
      "step": 94
    },
    {
      "epoch": 0.013823837024237187,
      "grad_norm": NaN,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.047,
      "step": 95
    },
    {
      "epoch": 0.013969351098176527,
      "grad_norm": NaN,
      "learning_rate": 4.865965629214819e-07,
      "loss": 2397.8171,
      "step": 96
    },
    {
      "epoch": 0.014114865172115866,
      "grad_norm": NaN,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 0.014260379246055204,
      "grad_norm": NaN,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 112.5829,
      "step": 98
    },
    {
      "epoch": 0.014405893319994542,
      "grad_norm": NaN,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.014551407393933883,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 19.1941,
      "step": 100
    },
    {
      "epoch": 0.014551407393933883,
      "eval_loss": NaN,
      "eval_runtime": 819.6423,
      "eval_samples_per_second": 14.122,
      "eval_steps_per_second": 7.062,
      "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": 1.523972939710464e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}