{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 37500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "grad_norm": 7.915888786315918,
      "learning_rate": 4.947192513368984e-05,
      "loss": 4.0126,
      "step": 500
    },
    {
      "epoch": 0.08,
      "grad_norm": 3.184572219848633,
      "learning_rate": 4.880347593582888e-05,
      "loss": 0.6684,
      "step": 1000
    },
    {
      "epoch": 0.12,
      "grad_norm": 5.76563835144043,
      "learning_rate": 4.813502673796791e-05,
      "loss": 0.5942,
      "step": 1500
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.7340965270996094,
      "learning_rate": 4.7466577540106955e-05,
      "loss": 0.5723,
      "step": 2000
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.790732502937317,
      "learning_rate": 4.679812834224599e-05,
      "loss": 0.5391,
      "step": 2500
    },
    {
      "epoch": 0.24,
      "grad_norm": 2.157850742340088,
      "learning_rate": 4.612967914438503e-05,
      "loss": 0.5188,
      "step": 3000
    },
    {
      "epoch": 0.28,
      "grad_norm": 1.461838960647583,
      "learning_rate": 4.5461229946524065e-05,
      "loss": 0.5113,
      "step": 3500
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.106745719909668,
      "learning_rate": 4.47927807486631e-05,
      "loss": 0.4956,
      "step": 4000
    },
    {
      "epoch": 0.36,
      "grad_norm": 1.2794815301895142,
      "learning_rate": 4.412433155080214e-05,
      "loss": 0.4906,
      "step": 4500
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.2381389141082764,
      "learning_rate": 4.345588235294118e-05,
      "loss": 0.4717,
      "step": 5000
    },
    {
      "epoch": 0.44,
      "grad_norm": 2.9455885887145996,
      "learning_rate": 4.278743315508021e-05,
      "loss": 0.4721,
      "step": 5500
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.1448231935501099,
      "learning_rate": 4.2118983957219257e-05,
      "loss": 0.4745,
      "step": 6000
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.9075339436531067,
      "learning_rate": 4.145053475935829e-05,
      "loss": 0.4597,
      "step": 6500
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.962452232837677,
      "learning_rate": 4.078208556149733e-05,
      "loss": 0.4583,
      "step": 7000
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.7801158428192139,
      "learning_rate": 4.011363636363637e-05,
      "loss": 0.4594,
      "step": 7500
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.1708343029022217,
      "learning_rate": 3.9445187165775404e-05,
      "loss": 0.45,
      "step": 8000
    },
    {
      "epoch": 0.68,
      "grad_norm": 1.1591224670410156,
      "learning_rate": 3.877807486631016e-05,
      "loss": 0.45,
      "step": 8500
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.8542613387107849,
      "learning_rate": 3.81096256684492e-05,
      "loss": 0.4433,
      "step": 9000
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.8478009700775146,
      "learning_rate": 3.744117647058823e-05,
      "loss": 0.4437,
      "step": 9500
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.9733747839927673,
      "learning_rate": 3.677272727272728e-05,
      "loss": 0.4362,
      "step": 10000
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.7879180312156677,
      "learning_rate": 3.610427807486631e-05,
      "loss": 0.4324,
      "step": 10500
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.3161998987197876,
      "learning_rate": 3.543582887700535e-05,
      "loss": 0.4354,
      "step": 11000
    },
    {
      "epoch": 0.92,
      "grad_norm": 1.153984785079956,
      "learning_rate": 3.476737967914439e-05,
      "loss": 0.4215,
      "step": 11500
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.7850612998008728,
      "learning_rate": 3.4098930481283425e-05,
      "loss": 0.4298,
      "step": 12000
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.3549928665161133,
      "learning_rate": 3.343181818181818e-05,
      "loss": 0.4245,
      "step": 12500
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.8405876755714417,
      "learning_rate": 3.2763368983957224e-05,
      "loss": 0.4204,
      "step": 13000
    },
    {
      "epoch": 1.08,
      "grad_norm": 1.5088772773742676,
      "learning_rate": 3.2094919786096254e-05,
      "loss": 0.4218,
      "step": 13500
    },
    {
      "epoch": 1.12,
      "grad_norm": 1.469650149345398,
      "learning_rate": 3.14264705882353e-05,
      "loss": 0.4074,
      "step": 14000
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.8406803607940674,
      "learning_rate": 3.075802139037433e-05,
      "loss": 0.4173,
      "step": 14500
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.754941999912262,
      "learning_rate": 3.0090909090909093e-05,
      "loss": 0.4095,
      "step": 15000
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.7950364947319031,
      "learning_rate": 2.9422459893048134e-05,
      "loss": 0.4053,
      "step": 15500
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.8804301023483276,
      "learning_rate": 2.8754010695187167e-05,
      "loss": 0.4117,
      "step": 16000
    },
    {
      "epoch": 1.32,
      "grad_norm": 1.4785621166229248,
      "learning_rate": 2.8085561497326207e-05,
      "loss": 0.4068,
      "step": 16500
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 1.0254385471343994,
      "learning_rate": 2.7419786096256685e-05,
      "loss": 0.4032,
      "step": 17000
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.9251853823661804,
      "learning_rate": 2.6751336898395725e-05,
      "loss": 0.4023,
      "step": 17500
    },
    {
      "epoch": 1.44,
      "grad_norm": 2.7361536026000977,
      "learning_rate": 2.608288770053476e-05,
      "loss": 0.3997,
      "step": 18000
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.9054092764854431,
      "learning_rate": 2.54144385026738e-05,
      "loss": 0.3981,
      "step": 18500
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.8799841403961182,
      "learning_rate": 2.4745989304812836e-05,
      "loss": 0.3943,
      "step": 19000
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.7638904452323914,
      "learning_rate": 2.4077540106951873e-05,
      "loss": 0.3962,
      "step": 19500
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.0725598335266113,
      "learning_rate": 2.341042780748663e-05,
      "loss": 0.3918,
      "step": 20000
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.7163866758346558,
      "learning_rate": 2.274197860962567e-05,
      "loss": 0.3987,
      "step": 20500
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 1.1992738246917725,
      "learning_rate": 2.2073529411764705e-05,
      "loss": 0.3983,
      "step": 21000
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.9536983966827393,
      "learning_rate": 2.1405080213903746e-05,
      "loss": 0.3961,
      "step": 21500
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.8780732154846191,
      "learning_rate": 2.0736631016042782e-05,
      "loss": 0.3926,
      "step": 22000
    },
    {
      "epoch": 1.8,
      "grad_norm": 1.201428771018982,
      "learning_rate": 2.006818181818182e-05,
      "loss": 0.3903,
      "step": 22500
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.9713455438613892,
      "learning_rate": 1.9399732620320856e-05,
      "loss": 0.3977,
      "step": 23000
    },
    {
      "epoch": 1.88,
      "grad_norm": 1.4893653392791748,
      "learning_rate": 1.8731283422459893e-05,
      "loss": 0.3923,
      "step": 23500
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.8749503493309021,
      "learning_rate": 1.8062834224598933e-05,
      "loss": 0.3868,
      "step": 24000
    },
    {
      "epoch": 1.96,
      "grad_norm": 1.0122476816177368,
      "learning_rate": 1.739438502673797e-05,
      "loss": 0.3879,
      "step": 24500
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.9151819944381714,
      "learning_rate": 1.6725935828877007e-05,
      "loss": 0.3878,
      "step": 25000
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.9272295832633972,
      "learning_rate": 1.6057486631016044e-05,
      "loss": 0.3826,
      "step": 25500
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.9182801842689514,
      "learning_rate": 1.5391711229946525e-05,
      "loss": 0.382,
      "step": 26000
    },
    {
      "epoch": 2.12,
      "grad_norm": 1.7542533874511719,
      "learning_rate": 1.4723262032085564e-05,
      "loss": 0.3786,
      "step": 26500
    },
    {
      "epoch": 2.16,
      "grad_norm": 1.5916212797164917,
      "learning_rate": 1.4054812834224599e-05,
      "loss": 0.3812,
      "step": 27000
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.9425985813140869,
      "learning_rate": 1.3386363636363636e-05,
      "loss": 0.3828,
      "step": 27500
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.9243144989013672,
      "learning_rate": 1.2717914438502672e-05,
      "loss": 0.3807,
      "step": 28000
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 1.0092005729675293,
      "learning_rate": 1.2049465240641713e-05,
      "loss": 0.3714,
      "step": 28500
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.8653339743614197,
      "learning_rate": 1.138101604278075e-05,
      "loss": 0.3792,
      "step": 29000
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.9960777163505554,
      "learning_rate": 1.0712566844919786e-05,
      "loss": 0.369,
      "step": 29500
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.3958770036697388,
      "learning_rate": 1.0045454545454545e-05,
      "loss": 0.3742,
      "step": 30000
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.6805775761604309,
      "learning_rate": 9.377005347593582e-06,
      "loss": 0.3766,
      "step": 30500
    },
    {
      "epoch": 2.48,
      "grad_norm": 2.525830030441284,
      "learning_rate": 8.70855614973262e-06,
      "loss": 0.3781,
      "step": 31000
    },
    {
      "epoch": 2.52,
      "grad_norm": 1.4676679372787476,
      "learning_rate": 8.040106951871658e-06,
      "loss": 0.3758,
      "step": 31500
    },
    {
      "epoch": 2.56,
      "grad_norm": 1.1790502071380615,
      "learning_rate": 7.371657754010695e-06,
      "loss": 0.3756,
      "step": 32000
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.7830659747123718,
      "learning_rate": 6.704545454545455e-06,
      "loss": 0.3786,
      "step": 32500
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.960568904876709,
      "learning_rate": 6.038770053475936e-06,
      "loss": 0.3778,
      "step": 33000
    },
    {
      "epoch": 2.68,
      "grad_norm": 1.0638457536697388,
      "learning_rate": 5.370320855614974e-06,
      "loss": 0.3826,
      "step": 33500
    },
    {
      "epoch": 2.7199999999999998,
      "grad_norm": 1.3440908193588257,
      "learning_rate": 4.701871657754011e-06,
      "loss": 0.3697,
      "step": 34000
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.6467347145080566,
      "learning_rate": 4.0334224598930485e-06,
      "loss": 0.38,
      "step": 34500
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.818299412727356,
      "learning_rate": 3.364973262032086e-06,
      "loss": 0.3677,
      "step": 35000
    },
    {
      "epoch": 2.84,
      "grad_norm": 1.8121366500854492,
      "learning_rate": 2.696524064171123e-06,
      "loss": 0.3777,
      "step": 35500
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.7342619895935059,
      "learning_rate": 2.0280748663101604e-06,
      "loss": 0.3709,
      "step": 36000
    },
    {
      "epoch": 2.92,
      "grad_norm": 0.925221860408783,
      "learning_rate": 1.3596256684491979e-06,
      "loss": 0.3709,
      "step": 36500
    },
    {
      "epoch": 2.96,
      "grad_norm": 0.8312897682189941,
      "learning_rate": 6.911764705882354e-07,
      "loss": 0.3725,
      "step": 37000
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.9641203880310059,
      "learning_rate": 2.272727272727273e-08,
      "loss": 0.3679,
      "step": 37500
    }
  ],
  "logging_steps": 500,
  "max_steps": 37500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 30000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.083549155328e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}