{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004239219135835179,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.478438271670358e-05,
      "grad_norm": 24.579681396484375,
      "learning_rate": 0.0001,
      "loss": 13.5065,
      "step": 1
    },
    {
      "epoch": 0.00016956876543340715,
      "grad_norm": 15.591464042663574,
      "learning_rate": 0.0002,
      "loss": 14.6243,
      "step": 2
    },
    {
      "epoch": 0.00025435314815011075,
      "grad_norm": 13.712444305419922,
      "learning_rate": 0.00019978589232386035,
      "loss": 11.6033,
      "step": 3
    },
    {
      "epoch": 0.0003391375308668143,
      "grad_norm": 25.338687896728516,
      "learning_rate": 0.00019914448613738106,
      "loss": 10.9172,
      "step": 4
    },
    {
      "epoch": 0.00042392191358351793,
      "grad_norm": 19.398792266845703,
      "learning_rate": 0.00019807852804032305,
      "loss": 6.8893,
      "step": 5
    },
    {
      "epoch": 0.0005087062963002215,
      "grad_norm": 21.508142471313477,
      "learning_rate": 0.00019659258262890683,
      "loss": 4.8226,
      "step": 6
    },
    {
      "epoch": 0.0005934906790169251,
      "grad_norm": 15.030914306640625,
      "learning_rate": 0.0001946930129495106,
      "loss": 3.7824,
      "step": 7
    },
    {
      "epoch": 0.0006782750617336286,
      "grad_norm": 15.14893627166748,
      "learning_rate": 0.0001923879532511287,
      "loss": 2.4025,
      "step": 8
    },
    {
      "epoch": 0.0007630594444503323,
      "grad_norm": 8.4822359085083,
      "learning_rate": 0.00018968727415326884,
      "loss": 2.3661,
      "step": 9
    },
    {
      "epoch": 0.0008478438271670359,
      "grad_norm": 13.65634536743164,
      "learning_rate": 0.00018660254037844388,
      "loss": 2.2553,
      "step": 10
    },
    {
      "epoch": 0.0009326282098837394,
      "grad_norm": 10.444439888000488,
      "learning_rate": 0.00018314696123025454,
      "loss": 1.9316,
      "step": 11
    },
    {
      "epoch": 0.001017412592600443,
      "grad_norm": 12.950057029724121,
      "learning_rate": 0.00017933533402912354,
      "loss": 2.0437,
      "step": 12
    },
    {
      "epoch": 0.0011021969753171467,
      "grad_norm": 8.97150707244873,
      "learning_rate": 0.00017518398074789775,
      "loss": 1.3961,
      "step": 13
    },
    {
      "epoch": 0.0011869813580338501,
      "grad_norm": 12.454018592834473,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.5085,
      "step": 14
    },
    {
      "epoch": 0.0012717657407505538,
      "grad_norm": 9.83290958404541,
      "learning_rate": 0.00016593458151000688,
      "loss": 1.9143,
      "step": 15
    },
    {
      "epoch": 0.0013565501234672572,
      "grad_norm": 13.476850509643555,
      "learning_rate": 0.00016087614290087208,
      "loss": 1.5221,
      "step": 16
    },
    {
      "epoch": 0.001441334506183961,
      "grad_norm": 10.192904472351074,
      "learning_rate": 0.00015555702330196023,
      "loss": 1.926,
      "step": 17
    },
    {
      "epoch": 0.0015261188889006646,
      "grad_norm": 9.45302963256836,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.1797,
      "step": 18
    },
    {
      "epoch": 0.001610903271617368,
      "grad_norm": 8.133692741394043,
      "learning_rate": 0.00014422886902190014,
      "loss": 1.3426,
      "step": 19
    },
    {
      "epoch": 0.0016956876543340717,
      "grad_norm": 9.124698638916016,
      "learning_rate": 0.000138268343236509,
      "loss": 1.7732,
      "step": 20
    },
    {
      "epoch": 0.0017804720370507752,
      "grad_norm": 14.199089050292969,
      "learning_rate": 0.00013214394653031616,
      "loss": 1.4573,
      "step": 21
    },
    {
      "epoch": 0.0018652564197674788,
      "grad_norm": 12.659859657287598,
      "learning_rate": 0.00012588190451025207,
      "loss": 1.4038,
      "step": 22
    },
    {
      "epoch": 0.0019500408024841825,
      "grad_norm": 11.574586868286133,
      "learning_rate": 0.00011950903220161285,
      "loss": 1.7974,
      "step": 23
    },
    {
      "epoch": 0.002034825185200886,
      "grad_norm": 7.019437313079834,
      "learning_rate": 0.00011305261922200519,
      "loss": 1.1941,
      "step": 24
    },
    {
      "epoch": 0.0021196095679175894,
      "grad_norm": 8.524972915649414,
      "learning_rate": 0.00010654031292301432,
      "loss": 1.6203,
      "step": 25
    },
    {
      "epoch": 0.0022043939506342933,
      "grad_norm": 5.318032264709473,
      "learning_rate": 0.0001,
      "loss": 1.2805,
      "step": 26
    },
    {
      "epoch": 0.0022891783333509968,
      "grad_norm": 6.56615686416626,
      "learning_rate": 9.345968707698569e-05,
      "loss": 0.7687,
      "step": 27
    },
    {
      "epoch": 0.0023739627160677002,
      "grad_norm": 6.601612091064453,
      "learning_rate": 8.694738077799488e-05,
      "loss": 0.9514,
      "step": 28
    },
    {
      "epoch": 0.002458747098784404,
      "grad_norm": 8.648096084594727,
      "learning_rate": 8.049096779838719e-05,
      "loss": 1.7966,
      "step": 29
    },
    {
      "epoch": 0.0025435314815011076,
      "grad_norm": 9.545267105102539,
      "learning_rate": 7.411809548974792e-05,
      "loss": 1.7292,
      "step": 30
    },
    {
      "epoch": 0.002628315864217811,
      "grad_norm": 7.909492015838623,
      "learning_rate": 6.785605346968386e-05,
      "loss": 1.9538,
      "step": 31
    },
    {
      "epoch": 0.0027131002469345145,
      "grad_norm": 6.8322367668151855,
      "learning_rate": 6.173165676349103e-05,
      "loss": 1.1442,
      "step": 32
    },
    {
      "epoch": 0.0027978846296512184,
      "grad_norm": 6.240336894989014,
      "learning_rate": 5.577113097809989e-05,
      "loss": 0.9339,
      "step": 33
    },
    {
      "epoch": 0.002882669012367922,
      "grad_norm": 8.01297378540039,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.525,
      "step": 34
    },
    {
      "epoch": 0.0029674533950846253,
      "grad_norm": 8.416840553283691,
      "learning_rate": 4.444297669803981e-05,
      "loss": 1.7266,
      "step": 35
    },
    {
      "epoch": 0.003052237777801329,
      "grad_norm": 6.560504913330078,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 0.9834,
      "step": 36
    },
    {
      "epoch": 0.0031370221605180326,
      "grad_norm": 6.503190994262695,
      "learning_rate": 3.406541848999312e-05,
      "loss": 1.364,
      "step": 37
    },
    {
      "epoch": 0.003221806543234736,
      "grad_norm": 8.527243614196777,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 1.5102,
      "step": 38
    },
    {
      "epoch": 0.0033065909259514395,
      "grad_norm": 8.381340026855469,
      "learning_rate": 2.4816019252102273e-05,
      "loss": 1.4996,
      "step": 39
    },
    {
      "epoch": 0.0033913753086681434,
      "grad_norm": 10.311125755310059,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 1.665,
      "step": 40
    },
    {
      "epoch": 0.003476159691384847,
      "grad_norm": 7.071728229522705,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 1.5634,
      "step": 41
    },
    {
      "epoch": 0.0035609440741015503,
      "grad_norm": 6.2012248039245605,
      "learning_rate": 1.339745962155613e-05,
      "loss": 1.1765,
      "step": 42
    },
    {
      "epoch": 0.0036457284568182542,
      "grad_norm": 6.488067150115967,
      "learning_rate": 1.0312725846731175e-05,
      "loss": 1.1878,
      "step": 43
    },
    {
      "epoch": 0.0037305128395349577,
      "grad_norm": 6.788881778717041,
      "learning_rate": 7.612046748871327e-06,
      "loss": 1.7673,
      "step": 44
    },
    {
      "epoch": 0.003815297222251661,
      "grad_norm": 8.740360260009766,
      "learning_rate": 5.306987050489442e-06,
      "loss": 1.7525,
      "step": 45
    },
    {
      "epoch": 0.003900081604968365,
      "grad_norm": 6.092394828796387,
      "learning_rate": 3.40741737109318e-06,
      "loss": 1.408,
      "step": 46
    },
    {
      "epoch": 0.003984865987685068,
      "grad_norm": 6.857183456420898,
      "learning_rate": 1.921471959676957e-06,
      "loss": 0.9187,
      "step": 47
    },
    {
      "epoch": 0.004069650370401772,
      "grad_norm": 6.588223457336426,
      "learning_rate": 8.555138626189618e-07,
      "loss": 1.0684,
      "step": 48
    },
    {
      "epoch": 0.004154434753118476,
      "grad_norm": 6.943943977355957,
      "learning_rate": 2.141076761396521e-07,
      "loss": 1.6099,
      "step": 49
    },
    {
      "epoch": 0.004239219135835179,
      "grad_norm": 8.967212677001953,
      "learning_rate": 0.0,
      "loss": 1.7563,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "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": 7.41900168462336e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}