{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.11366865586814436,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011366865586814436,
      "eval_loss": NaN,
      "eval_runtime": 10.2124,
      "eval_samples_per_second": 72.559,
      "eval_steps_per_second": 18.213,
      "step": 1
    },
    {
      "epoch": 0.0034100596760443308,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0068201193520886615,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.010230179028132993,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.010230179028132993,
      "eval_loss": NaN,
      "eval_runtime": 9.506,
      "eval_samples_per_second": 77.951,
      "eval_steps_per_second": 19.567,
      "step": 9
    },
    {
      "epoch": 0.013640238704177323,
      "grad_norm": NaN,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.017050298380221655,
      "grad_norm": NaN,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.020460358056265986,
      "grad_norm": NaN,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.020460358056265986,
      "eval_loss": NaN,
      "eval_runtime": 9.4086,
      "eval_samples_per_second": 78.758,
      "eval_steps_per_second": 19.769,
      "step": 18
    },
    {
      "epoch": 0.023870417732310314,
      "grad_norm": NaN,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.027280477408354646,
      "grad_norm": NaN,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.030690537084398978,
      "grad_norm": NaN,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.030690537084398978,
      "eval_loss": NaN,
      "eval_runtime": 9.4899,
      "eval_samples_per_second": 78.083,
      "eval_steps_per_second": 19.6,
      "step": 27
    },
    {
      "epoch": 0.03410059676044331,
      "grad_norm": NaN,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.03751065643648764,
      "grad_norm": NaN,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.04092071611253197,
      "grad_norm": NaN,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.04092071611253197,
      "eval_loss": NaN,
      "eval_runtime": 9.4694,
      "eval_samples_per_second": 78.252,
      "eval_steps_per_second": 19.642,
      "step": 36
    },
    {
      "epoch": 0.0443307757885763,
      "grad_norm": NaN,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.04774083546462063,
      "grad_norm": NaN,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.05115089514066496,
      "grad_norm": NaN,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.05115089514066496,
      "eval_loss": NaN,
      "eval_runtime": 9.4456,
      "eval_samples_per_second": 78.449,
      "eval_steps_per_second": 19.692,
      "step": 45
    },
    {
      "epoch": 0.05456095481670929,
      "grad_norm": NaN,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.057971014492753624,
      "grad_norm": NaN,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.061381074168797956,
      "grad_norm": NaN,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.061381074168797956,
      "eval_loss": NaN,
      "eval_runtime": 9.1147,
      "eval_samples_per_second": 81.298,
      "eval_steps_per_second": 20.407,
      "step": 54
    },
    {
      "epoch": 0.06479113384484228,
      "grad_norm": NaN,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.06820119352088662,
      "grad_norm": NaN,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.07161125319693094,
      "grad_norm": NaN,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.07161125319693094,
      "eval_loss": NaN,
      "eval_runtime": 9.0811,
      "eval_samples_per_second": 81.598,
      "eval_steps_per_second": 20.482,
      "step": 63
    },
    {
      "epoch": 0.07502131287297528,
      "grad_norm": NaN,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.0784313725490196,
      "grad_norm": NaN,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.08184143222506395,
      "grad_norm": NaN,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.08184143222506395,
      "eval_loss": NaN,
      "eval_runtime": 9.1793,
      "eval_samples_per_second": 80.725,
      "eval_steps_per_second": 20.263,
      "step": 72
    },
    {
      "epoch": 0.08525149190110827,
      "grad_norm": NaN,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.0886615515771526,
      "grad_norm": NaN,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.09207161125319693,
      "grad_norm": NaN,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.09207161125319693,
      "eval_loss": NaN,
      "eval_runtime": 9.1688,
      "eval_samples_per_second": 80.817,
      "eval_steps_per_second": 20.286,
      "step": 81
    },
    {
      "epoch": 0.09548167092924126,
      "grad_norm": NaN,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.0988917306052856,
      "grad_norm": NaN,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.10230179028132992,
      "grad_norm": NaN,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.10230179028132992,
      "eval_loss": NaN,
      "eval_runtime": 9.4343,
      "eval_samples_per_second": 78.544,
      "eval_steps_per_second": 19.715,
      "step": 90
    },
    {
      "epoch": 0.10571184995737426,
      "grad_norm": NaN,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 0.10912190963341858,
      "grad_norm": NaN,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.11253196930946291,
      "grad_norm": NaN,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.11253196930946291,
      "eval_loss": NaN,
      "eval_runtime": 9.1912,
      "eval_samples_per_second": 80.621,
      "eval_steps_per_second": 20.237,
      "step": 99
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1322614184214528.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}