{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9977046671767407,
  "eval_steps": 100,
  "global_step": 163,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.030604437643458302,
      "grad_norm": 2.3956207575517907,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.0865,
      "mean_token_accuracy": 0.7095605345838285,
      "step": 5
    },
    {
      "epoch": 0.061208875286916604,
      "grad_norm": 2.0418371914182054,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 0.9585,
      "mean_token_accuracy": 0.7301618747737846,
      "step": 10
    },
    {
      "epoch": 0.09181331293037491,
      "grad_norm": 1.11257855286638,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 0.8486,
      "mean_token_accuracy": 0.7503171317905428,
      "step": 15
    },
    {
      "epoch": 0.12241775057383321,
      "grad_norm": 0.8299724465639433,
      "learning_rate": 1.9979171608653926e-05,
      "loss": 0.8141,
      "mean_token_accuracy": 0.7560959624442517,
      "step": 20
    },
    {
      "epoch": 0.1530221882172915,
      "grad_norm": 0.8916010345037251,
      "learning_rate": 1.9852201067560607e-05,
      "loss": 0.7739,
      "mean_token_accuracy": 0.765613780191612,
      "step": 25
    },
    {
      "epoch": 0.18362662586074982,
      "grad_norm": 0.8550116014281596,
      "learning_rate": 1.961129783872301e-05,
      "loss": 0.7502,
      "mean_token_accuracy": 0.7706232570272338,
      "step": 30
    },
    {
      "epoch": 0.21423106350420812,
      "grad_norm": 0.7246688121931725,
      "learning_rate": 1.92592477719385e-05,
      "loss": 0.7359,
      "mean_token_accuracy": 0.7731495622693539,
      "step": 35
    },
    {
      "epoch": 0.24483550114766642,
      "grad_norm": 0.796594402129789,
      "learning_rate": 1.880012203973536e-05,
      "loss": 0.7416,
      "mean_token_accuracy": 0.7720866443990716,
      "step": 40
    },
    {
      "epoch": 0.2754399387911247,
      "grad_norm": 0.6589999071952135,
      "learning_rate": 1.8239230057575542e-05,
      "loss": 0.7229,
      "mean_token_accuracy": 0.7758317882296452,
      "step": 45
    },
    {
      "epoch": 0.306044376434583,
      "grad_norm": 0.6670732927253004,
      "learning_rate": 1.7583058084785626e-05,
      "loss": 0.7134,
      "mean_token_accuracy": 0.7779923586639284,
      "step": 50
    },
    {
      "epoch": 0.3366488140780413,
      "grad_norm": 0.6402899859627691,
      "learning_rate": 1.683919421624611e-05,
      "loss": 0.7078,
      "mean_token_accuracy": 0.7796091069874582,
      "step": 55
    },
    {
      "epoch": 0.36725325172149964,
      "grad_norm": 0.6682592985735738,
      "learning_rate": 1.6016240632249224e-05,
      "loss": 0.6944,
      "mean_token_accuracy": 0.7828741558176683,
      "step": 60
    },
    {
      "epoch": 0.3978576893649579,
      "grad_norm": 0.5747503915274951,
      "learning_rate": 1.512371412128424e-05,
      "loss": 0.6828,
      "mean_token_accuracy": 0.7866091268932821,
      "step": 65
    },
    {
      "epoch": 0.42846212700841624,
      "grad_norm": 0.6017366721008394,
      "learning_rate": 1.417193602612317e-05,
      "loss": 0.6833,
      "mean_token_accuracy": 0.7854777704763246,
      "step": 70
    },
    {
      "epoch": 0.4590665646518745,
      "grad_norm": 0.6909656637620125,
      "learning_rate": 1.3171912885891063e-05,
      "loss": 0.6867,
      "mean_token_accuracy": 0.7841435922488781,
      "step": 75
    },
    {
      "epoch": 0.48967100229533284,
      "grad_norm": 0.5680972717743182,
      "learning_rate": 1.2135209154397962e-05,
      "loss": 0.6704,
      "mean_token_accuracy": 0.7890687545099153,
      "step": 80
    },
    {
      "epoch": 0.5202754399387911,
      "grad_norm": 0.5077512809088303,
      "learning_rate": 1.1073813466641633e-05,
      "loss": 0.6871,
      "mean_token_accuracy": 0.7840379169126969,
      "step": 85
    },
    {
      "epoch": 0.5508798775822494,
      "grad_norm": 0.536075320882483,
      "learning_rate": 1e-05,
      "loss": 0.671,
      "mean_token_accuracy": 0.7886130547081162,
      "step": 90
    },
    {
      "epoch": 0.5814843152257078,
      "grad_norm": 0.4904573809215121,
      "learning_rate": 8.92618653335837e-06,
      "loss": 0.6777,
      "mean_token_accuracy": 0.7871433307114094,
      "step": 95
    },
    {
      "epoch": 0.612088752869166,
      "grad_norm": 0.55059789821494,
      "learning_rate": 7.86479084560204e-06,
      "loss": 0.6751,
      "mean_token_accuracy": 0.7871067609279663,
      "step": 100
    },
    {
      "epoch": 0.612088752869166,
      "eval_loss": 0.6865678429603577,
      "eval_mean_token_accuracy": 0.7828014183630538,
      "eval_runtime": 3.2986,
      "eval_samples_per_second": 37.895,
      "eval_steps_per_second": 1.213,
      "step": 100
    },
    {
      "epoch": 0.6426931905126243,
      "grad_norm": 0.5176104318935184,
      "learning_rate": 6.8280871141089415e-06,
      "loss": 0.673,
      "mean_token_accuracy": 0.7875675071968407,
      "step": 105
    },
    {
      "epoch": 0.6732976281560826,
      "grad_norm": 0.49658972838719107,
      "learning_rate": 5.828063973876834e-06,
      "loss": 0.669,
      "mean_token_accuracy": 0.7885898620912861,
      "step": 110
    },
    {
      "epoch": 0.703902065799541,
      "grad_norm": 0.48151170624177525,
      "learning_rate": 4.876285878715764e-06,
      "loss": 0.6591,
      "mean_token_accuracy": 0.7915397758950073,
      "step": 115
    },
    {
      "epoch": 0.7345065034429993,
      "grad_norm": 0.4786459845507803,
      "learning_rate": 3.983759367750772e-06,
      "loss": 0.6553,
      "mean_token_accuracy": 0.792250694192391,
      "step": 120
    },
    {
      "epoch": 0.7651109410864575,
      "grad_norm": 0.4512983509051795,
      "learning_rate": 3.1608057837538976e-06,
      "loss": 0.6708,
      "mean_token_accuracy": 0.7879882868675088,
      "step": 125
    },
    {
      "epoch": 0.7957153787299158,
      "grad_norm": 0.42751771255008625,
      "learning_rate": 2.416941915214377e-06,
      "loss": 0.6557,
      "mean_token_accuracy": 0.7919469636759972,
      "step": 130
    },
    {
      "epoch": 0.8263198163733741,
      "grad_norm": 0.45008874478679334,
      "learning_rate": 1.7607699424244583e-06,
      "loss": 0.6589,
      "mean_token_accuracy": 0.7912565925036045,
      "step": 135
    },
    {
      "epoch": 0.8569242540168325,
      "grad_norm": 0.43122456587499,
      "learning_rate": 1.1998779602646438e-06,
      "loss": 0.6519,
      "mean_token_accuracy": 0.7932468473712841,
      "step": 140
    },
    {
      "epoch": 0.8875286916602907,
      "grad_norm": 0.41656433519146435,
      "learning_rate": 7.40752228061502e-07,
      "loss": 0.6549,
      "mean_token_accuracy": 0.7921480402911436,
      "step": 145
    },
    {
      "epoch": 0.918133129303749,
      "grad_norm": 0.4259733563062634,
      "learning_rate": 3.887021612769937e-07,
      "loss": 0.662,
      "mean_token_accuracy": 0.7900667175944671,
      "step": 150
    },
    {
      "epoch": 0.9487375669472073,
      "grad_norm": 0.426432499566953,
      "learning_rate": 1.4779893243939358e-07,
      "loss": 0.657,
      "mean_token_accuracy": 0.7918590477702575,
      "step": 155
    },
    {
      "epoch": 0.9793420045906657,
      "grad_norm": 0.4327175151190677,
      "learning_rate": 2.082839134607828e-08,
      "loss": 0.6544,
      "mean_token_accuracy": 0.7918795329068727,
      "step": 160
    },
    {
      "epoch": 0.9977046671767407,
      "mean_token_accuracy": 0.792194867744806,
      "step": 163,
      "total_flos": 136410845675520.0,
      "train_loss": 0.7151586380472944,
      "train_runtime": 1873.0311,
      "train_samples_per_second": 11.163,
      "train_steps_per_second": 0.087
    }
  ],
  "logging_steps": 5,
  "max_steps": 163,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 136410845675520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}