{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4983012457531144,
  "eval_steps": 55,
  "global_step": 110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004530011325028313,
      "grad_norm": NaN,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.004530011325028313,
      "eval_loss": NaN,
      "eval_runtime": 17.5744,
      "eval_samples_per_second": 21.167,
      "eval_steps_per_second": 5.292,
      "step": 1
    },
    {
      "epoch": 0.009060022650056626,
      "grad_norm": NaN,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.013590033975084938,
      "grad_norm": NaN,
      "learning_rate": 6e-06,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.01812004530011325,
      "grad_norm": NaN,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.022650056625141562,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.027180067950169876,
      "grad_norm": NaN,
      "learning_rate": 1.2e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.031710079275198186,
      "grad_norm": NaN,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0362400906002265,
      "grad_norm": NaN,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.04077010192525481,
      "grad_norm": NaN,
      "learning_rate": 1.8e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.045300113250283124,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.04983012457531144,
      "grad_norm": NaN,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.05436013590033975,
      "grad_norm": NaN,
      "learning_rate": 2.4e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.05889014722536806,
      "grad_norm": NaN,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.06342015855039637,
      "grad_norm": NaN,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.06795016987542468,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.072480181200453,
      "grad_norm": NaN,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.07701019252548132,
      "grad_norm": NaN,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.08154020385050963,
      "grad_norm": NaN,
      "learning_rate": 3.6e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.08607021517553794,
      "grad_norm": NaN,
      "learning_rate": 3.8e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.09060022650056625,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.09513023782559456,
      "grad_norm": NaN,
      "learning_rate": 4.2e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.09966024915062288,
      "grad_norm": NaN,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.10419026047565119,
      "grad_norm": NaN,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.1087202718006795,
      "grad_norm": NaN,
      "learning_rate": 4.8e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.11325028312570781,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.11778029445073612,
      "grad_norm": NaN,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.12231030577576443,
      "grad_norm": NaN,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.12684031710079274,
      "grad_norm": NaN,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.13137032842582105,
      "grad_norm": NaN,
      "learning_rate": 5.8e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.13590033975084936,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.1404303510758777,
      "grad_norm": NaN,
      "learning_rate": 6.2e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.144960362400906,
      "grad_norm": NaN,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.14949037372593432,
      "grad_norm": NaN,
      "learning_rate": 6.6e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.15402038505096263,
      "grad_norm": NaN,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.15855039637599094,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.16308040770101925,
      "grad_norm": NaN,
      "learning_rate": 7.2e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.16761041902604756,
      "grad_norm": NaN,
      "learning_rate": 7.4e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.17214043035107587,
      "grad_norm": NaN,
      "learning_rate": 7.6e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.17667044167610418,
      "grad_norm": NaN,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.1812004530011325,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.1857304643261608,
      "grad_norm": NaN,
      "learning_rate": 8.2e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.19026047565118911,
      "grad_norm": NaN,
      "learning_rate": 8.4e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.19479048697621745,
      "grad_norm": NaN,
      "learning_rate": 8.6e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.19932049830124576,
      "grad_norm": NaN,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.20385050962627407,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.20838052095130238,
      "grad_norm": NaN,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.2129105322763307,
      "grad_norm": NaN,
      "learning_rate": 9.4e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.217440543601359,
      "grad_norm": NaN,
      "learning_rate": 9.6e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.22197055492638731,
      "grad_norm": NaN,
      "learning_rate": 9.8e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.22650056625141562,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.23103057757644394,
      "grad_norm": NaN,
      "learning_rate": 9.999146252290264e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.23556058890147225,
      "grad_norm": NaN,
      "learning_rate": 9.996585300715116e-05,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.24009060022650056,
      "grad_norm": NaN,
      "learning_rate": 9.99231801983717e-05,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.24462061155152887,
      "grad_norm": NaN,
      "learning_rate": 9.986345866928941e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.2491506228765572,
      "grad_norm": NaN,
      "learning_rate": 9.978670881475172e-05,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.2491506228765572,
      "eval_loss": NaN,
      "eval_runtime": 16.9373,
      "eval_samples_per_second": 21.963,
      "eval_steps_per_second": 5.491,
      "step": 55
    },
    {
      "epoch": 0.2536806342015855,
      "grad_norm": NaN,
      "learning_rate": 9.96929568447637e-05,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.2582106455266138,
      "grad_norm": NaN,
      "learning_rate": 9.958223477553714e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.2627406568516421,
      "grad_norm": NaN,
      "learning_rate": 9.94545804185573e-05,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.26727066817667045,
      "grad_norm": NaN,
      "learning_rate": 9.931003736767013e-05,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.2718006795016987,
      "grad_norm": NaN,
      "learning_rate": 9.91486549841951e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.27633069082672707,
      "grad_norm": NaN,
      "learning_rate": 9.89704883800683e-05,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.2808607021517554,
      "grad_norm": NaN,
      "learning_rate": 9.877559839902184e-05,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.2853907134767837,
      "grad_norm": NaN,
      "learning_rate": 9.85640515958057e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.289920724801812,
      "grad_norm": NaN,
      "learning_rate": 9.833592021345937e-05,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.2944507361268403,
      "grad_norm": NaN,
      "learning_rate": 9.809128215864097e-05,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.29898074745186864,
      "grad_norm": NaN,
      "learning_rate": 9.783022097502204e-05,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.3035107587768969,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.30804077010192527,
      "grad_norm": NaN,
      "learning_rate": 9.725919140804099e-05,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.31257078142695355,
      "grad_norm": NaN,
      "learning_rate": 9.694941803075283e-05,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.3171007927519819,
      "grad_norm": NaN,
      "learning_rate": 9.662361147021779e-05,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.32163080407701017,
      "grad_norm": NaN,
      "learning_rate": 9.628188298907782e-05,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.3261608154020385,
      "grad_norm": NaN,
      "learning_rate": 9.592434928729616e-05,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.33069082672706684,
      "grad_norm": NaN,
      "learning_rate": 9.555113246230442e-05,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.3352208380520951,
      "grad_norm": NaN,
      "learning_rate": 9.516235996730645e-05,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.33975084937712347,
      "grad_norm": NaN,
      "learning_rate": 9.475816456775313e-05,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.34428086070215175,
      "grad_norm": NaN,
      "learning_rate": 9.43386842960031e-05,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 0.3488108720271801,
      "grad_norm": NaN,
      "learning_rate": 9.39040624041849e-05,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 0.35334088335220837,
      "grad_norm": NaN,
      "learning_rate": 9.345444731527642e-05,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.3578708946772367,
      "grad_norm": NaN,
      "learning_rate": 9.298999257241863e-05,
      "loss": 0.0,
      "step": 79
    },
    {
      "epoch": 0.362400906002265,
      "grad_norm": NaN,
      "learning_rate": 9.251085678648072e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.3669309173272933,
      "grad_norm": NaN,
      "learning_rate": 9.201720358189464e-05,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.3714609286523216,
      "grad_norm": NaN,
      "learning_rate": 9.150920154077754e-05,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 0.37599093997734995,
      "grad_norm": NaN,
      "learning_rate": 9.098702414536107e-05,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 0.38052095130237823,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.38505096262740657,
      "grad_norm": NaN,
      "learning_rate": 8.9900861364012e-05,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.3895809739524349,
      "grad_norm": NaN,
      "learning_rate": 8.933724690167417e-05,
      "loss": 0.0,
      "step": 86
    },
    {
      "epoch": 0.3941109852774632,
      "grad_norm": NaN,
      "learning_rate": 8.876019880555649e-05,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.3986409966024915,
      "grad_norm": NaN,
      "learning_rate": 8.816991413705516e-05,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 0.4031710079275198,
      "grad_norm": NaN,
      "learning_rate": 8.756659447784368e-05,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 0.40770101925254815,
      "grad_norm": NaN,
      "learning_rate": 8.695044586103296e-05,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.41223103057757643,
      "grad_norm": NaN,
      "learning_rate": 8.632167870081121e-05,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 0.41676104190260477,
      "grad_norm": NaN,
      "learning_rate": 8.568050772058762e-05,
      "loss": 0.0,
      "step": 92
    },
    {
      "epoch": 0.42129105322763305,
      "grad_norm": NaN,
      "learning_rate": 8.502715187966455e-05,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 0.4258210645526614,
      "grad_norm": NaN,
      "learning_rate": 8.436183429846313e-05,
      "loss": 0.0,
      "step": 94
    },
    {
      "epoch": 0.43035107587768967,
      "grad_norm": NaN,
      "learning_rate": 8.368478218232787e-05,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.434881087202718,
      "grad_norm": NaN,
      "learning_rate": 8.299622674393614e-05,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.43941109852774635,
      "grad_norm": NaN,
      "learning_rate": 8.229640312433937e-05,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 0.44394110985277463,
      "grad_norm": NaN,
      "learning_rate": 8.158555031266254e-05,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 0.44847112117780297,
      "grad_norm": NaN,
      "learning_rate": 8.086391106448965e-05,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.45300113250283125,
      "grad_norm": NaN,
      "learning_rate": 8.013173181896283e-05,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.4575311438278596,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 101
    },
    {
      "epoch": 0.46206115515288787,
      "grad_norm": NaN,
      "learning_rate": 7.863675700402526e-05,
      "loss": 0.0,
      "step": 102
    },
    {
      "epoch": 0.4665911664779162,
      "grad_norm": NaN,
      "learning_rate": 7.787447196714427e-05,
      "loss": 0.0,
      "step": 103
    },
    {
      "epoch": 0.4711211778029445,
      "grad_norm": NaN,
      "learning_rate": 7.710266782362247e-05,
      "loss": 0.0,
      "step": 104
    },
    {
      "epoch": 0.47565118912797283,
      "grad_norm": NaN,
      "learning_rate": 7.63216081438678e-05,
      "loss": 0.0,
      "step": 105
    },
    {
      "epoch": 0.4801812004530011,
      "grad_norm": NaN,
      "learning_rate": 7.553155965904535e-05,
      "loss": 0.0,
      "step": 106
    },
    {
      "epoch": 0.48471121177802945,
      "grad_norm": NaN,
      "learning_rate": 7.473279216998895e-05,
      "loss": 0.0,
      "step": 107
    },
    {
      "epoch": 0.48924122310305773,
      "grad_norm": NaN,
      "learning_rate": 7.392557845506432e-05,
      "loss": 0.0,
      "step": 108
    },
    {
      "epoch": 0.49377123442808607,
      "grad_norm": NaN,
      "learning_rate": 7.311019417701566e-05,
      "loss": 0.0,
      "step": 109
    },
    {
      "epoch": 0.4983012457531144,
      "grad_norm": NaN,
      "learning_rate": 7.228691778882693e-05,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.4983012457531144,
      "eval_loss": NaN,
      "eval_runtime": 16.8907,
      "eval_samples_per_second": 22.024,
      "eval_steps_per_second": 5.506,
      "step": 110
    }
  ],
  "logging_steps": 1,
  "max_steps": 220,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 55,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.58609946181632e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}