{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 169,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.029585798816568046,
      "grad_norm": 2.297013532422354,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.1002,
      "mean_token_accuracy": 0.7101167571916878,
      "step": 5
    },
    {
      "epoch": 0.05917159763313609,
      "grad_norm": 1.5972245151768176,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 1.0326,
      "mean_token_accuracy": 0.7201762398077369,
      "step": 10
    },
    {
      "epoch": 0.08875739644970414,
      "grad_norm": 0.8468665415132717,
      "learning_rate": 1.7647058823529414e-05,
      "loss": 0.9517,
      "mean_token_accuracy": 0.732623946787214,
      "step": 15
    },
    {
      "epoch": 0.11834319526627218,
      "grad_norm": 0.6454308594027754,
      "learning_rate": 1.9980782984658682e-05,
      "loss": 0.8804,
      "mean_token_accuracy": 0.7473691154561544,
      "step": 20
    },
    {
      "epoch": 0.14792899408284024,
      "grad_norm": 0.5528393319325755,
      "learning_rate": 1.9863613034027224e-05,
      "loss": 0.8535,
      "mean_token_accuracy": 0.7518347609360692,
      "step": 25
    },
    {
      "epoch": 0.17751479289940827,
      "grad_norm": 0.4419547109574886,
      "learning_rate": 1.9641197940012136e-05,
      "loss": 0.8404,
      "mean_token_accuracy": 0.7545905840891362,
      "step": 30
    },
    {
      "epoch": 0.20710059171597633,
      "grad_norm": 0.3944050233585755,
      "learning_rate": 1.9315910880512792e-05,
      "loss": 0.8212,
      "mean_token_accuracy": 0.7580601690663177,
      "step": 35
    },
    {
      "epoch": 0.23668639053254437,
      "grad_norm": 0.3876590410652944,
      "learning_rate": 1.8891222681391853e-05,
      "loss": 0.8051,
      "mean_token_accuracy": 0.7621832145800718,
      "step": 40
    },
    {
      "epoch": 0.26627218934911245,
      "grad_norm": 0.4232933870541141,
      "learning_rate": 1.8371664782625287e-05,
      "loss": 0.7984,
      "mean_token_accuracy": 0.7634996989840557,
      "step": 45
    },
    {
      "epoch": 0.2958579881656805,
      "grad_norm": 0.3948617572301456,
      "learning_rate": 1.7762780887657576e-05,
      "loss": 0.7937,
      "mean_token_accuracy": 0.7643278682484194,
      "step": 50
    },
    {
      "epoch": 0.3254437869822485,
      "grad_norm": 0.37271462165657315,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 0.7894,
      "mean_token_accuracy": 0.7648770573390258,
      "step": 55
    },
    {
      "epoch": 0.35502958579881655,
      "grad_norm": 0.3686763884535947,
      "learning_rate": 1.6303906161279554e-05,
      "loss": 0.7998,
      "mean_token_accuracy": 0.7620085578688149,
      "step": 60
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.3946265365362768,
      "learning_rate": 1.5469481581224274e-05,
      "loss": 0.7867,
      "mean_token_accuracy": 0.7647475392986315,
      "step": 65
    },
    {
      "epoch": 0.41420118343195267,
      "grad_norm": 0.3741046358897725,
      "learning_rate": 1.4576697415156818e-05,
      "loss": 0.7782,
      "mean_token_accuracy": 0.7674258745201611,
      "step": 70
    },
    {
      "epoch": 0.4437869822485207,
      "grad_norm": 0.3379603958671933,
      "learning_rate": 1.3635079705638298e-05,
      "loss": 0.777,
      "mean_token_accuracy": 0.7675157666822746,
      "step": 75
    },
    {
      "epoch": 0.47337278106508873,
      "grad_norm": 0.34558064589431076,
      "learning_rate": 1.2654675551080724e-05,
      "loss": 0.7783,
      "mean_token_accuracy": 0.7666624691953885,
      "step": 80
    },
    {
      "epoch": 0.5029585798816568,
      "grad_norm": 0.33513402299160633,
      "learning_rate": 1.164594590280734e-05,
      "loss": 0.7785,
      "mean_token_accuracy": 0.7669693361801984,
      "step": 85
    },
    {
      "epoch": 0.5325443786982249,
      "grad_norm": 0.3489473677411688,
      "learning_rate": 1.0619653946285948e-05,
      "loss": 0.7723,
      "mean_token_accuracy": 0.768224282473055,
      "step": 90
    },
    {
      "epoch": 0.5621301775147929,
      "grad_norm": 0.3443175345745291,
      "learning_rate": 9.586750257511868e-06,
      "loss": 0.7668,
      "mean_token_accuracy": 0.7697911584264276,
      "step": 95
    },
    {
      "epoch": 0.591715976331361,
      "grad_norm": 0.33966464392168516,
      "learning_rate": 8.558255959926533e-06,
      "loss": 0.7582,
      "mean_token_accuracy": 0.7714483803413514,
      "step": 100
    },
    {
      "epoch": 0.591715976331361,
      "eval_loss": 0.7885444164276123,
      "eval_mean_token_accuracy": 0.7470757669252631,
      "eval_runtime": 2.2929,
      "eval_samples_per_second": 56.262,
      "eval_steps_per_second": 2.181,
      "step": 100
    },
    {
      "epoch": 0.621301775147929,
      "grad_norm": 0.3510969140805542,
      "learning_rate": 7.545145128592009e-06,
      "loss": 0.759,
      "mean_token_accuracy": 0.7715117735747477,
      "step": 105
    },
    {
      "epoch": 0.650887573964497,
      "grad_norm": 0.3164173775744966,
      "learning_rate": 6.558227696373617e-06,
      "loss": 0.7775,
      "mean_token_accuracy": 0.7664958261399522,
      "step": 110
    },
    {
      "epoch": 0.6804733727810651,
      "grad_norm": 0.30843839642426596,
      "learning_rate": 5.608034111526298e-06,
      "loss": 0.7636,
      "mean_token_accuracy": 0.7703326897538567,
      "step": 115
    },
    {
      "epoch": 0.7100591715976331,
      "grad_norm": 0.29954916181026625,
      "learning_rate": 4.704702977392914e-06,
      "loss": 0.7511,
      "mean_token_accuracy": 0.7743327496383021,
      "step": 120
    },
    {
      "epoch": 0.7396449704142012,
      "grad_norm": 0.31652606813580997,
      "learning_rate": 3.857872873103322e-06,
      "loss": 0.7594,
      "mean_token_accuracy": 0.7717091884313854,
      "step": 125
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.3199175692129167,
      "learning_rate": 3.0765795095517026e-06,
      "loss": 0.7623,
      "mean_token_accuracy": 0.7706086268052205,
      "step": 130
    },
    {
      "epoch": 0.7988165680473372,
      "grad_norm": 0.3026051669531728,
      "learning_rate": 2.369159318001937e-06,
      "loss": 0.7684,
      "mean_token_accuracy": 0.7688736914255168,
      "step": 135
    },
    {
      "epoch": 0.8284023668639053,
      "grad_norm": 0.2939363025195632,
      "learning_rate": 1.743160500034443e-06,
      "loss": 0.7596,
      "mean_token_accuracy": 0.7716677566228066,
      "step": 140
    },
    {
      "epoch": 0.8579881656804734,
      "grad_norm": 0.3119701067736413,
      "learning_rate": 1.2052624879351105e-06,
      "loss": 0.7595,
      "mean_token_accuracy": 0.7715010297619764,
      "step": 145
    },
    {
      "epoch": 0.8875739644970414,
      "grad_norm": 0.2907312732907299,
      "learning_rate": 7.612046748871327e-07,
      "loss": 0.7505,
      "mean_token_accuracy": 0.7739383589072379,
      "step": 150
    },
    {
      "epoch": 0.9171597633136095,
      "grad_norm": 0.27953217242127415,
      "learning_rate": 4.1572517541747294e-07,
      "loss": 0.741,
      "mean_token_accuracy": 0.7767892422479253,
      "step": 155
    },
    {
      "epoch": 0.9467455621301775,
      "grad_norm": 0.29613779925872324,
      "learning_rate": 1.7251026952640583e-07,
      "loss": 0.754,
      "mean_token_accuracy": 0.7731886518228532,
      "step": 160
    },
    {
      "epoch": 0.9763313609467456,
      "grad_norm": 0.27713370708518803,
      "learning_rate": 3.4155069933301535e-08,
      "loss": 0.7467,
      "mean_token_accuracy": 0.7749447315994917,
      "step": 165
    },
    {
      "epoch": 1.0,
      "mean_token_accuracy": 0.7704864777412954,
      "step": 169,
      "total_flos": 76973799899136.0,
      "train_loss": 0.802493240706314,
      "train_runtime": 753.9282,
      "train_samples_per_second": 28.68,
      "train_steps_per_second": 0.224
    }
  ],
  "logging_steps": 5,
  "max_steps": 169,
  "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": 76973799899136.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}