{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06754474839581223,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00033772374197906115,
      "eval_loss": 11.5,
      "eval_runtime": 10.9061,
      "eval_samples_per_second": 457.267,
      "eval_steps_per_second": 57.216,
      "step": 1
    },
    {
      "epoch": 0.0016886187098953055,
      "grad_norm": 3.728782758116722e-05,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.003377237419790611,
      "grad_norm": 4.0675662603462115e-05,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.005065856129685917,
      "grad_norm": 3.8669018977088854e-05,
      "learning_rate": 9.98292246503335e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.006754474839581222,
      "grad_norm": 2.2602793251280673e-05,
      "learning_rate": 9.931806517013612e-05,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.008443093549476529,
      "grad_norm": 2.7893383958144113e-05,
      "learning_rate": 9.847001329696653e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.010131712259371834,
      "grad_norm": 3.99921991629526e-05,
      "learning_rate": 9.729086208503174e-05,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.01182033096926714,
      "grad_norm": 2.4645582016091794e-05,
      "learning_rate": 9.578866633275288e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.013508949679162444,
      "grad_norm": 4.132384492550045e-05,
      "learning_rate": 9.397368756032445e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.015197568389057751,
      "grad_norm": 4.581116809276864e-05,
      "learning_rate": 9.185832391312644e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.016886187098953058,
      "grad_norm": 3.232359449611977e-05,
      "learning_rate": 8.945702546981969e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.016886187098953058,
      "eval_loss": 11.5,
      "eval_runtime": 10.8922,
      "eval_samples_per_second": 457.848,
      "eval_steps_per_second": 57.288,
      "step": 50
    },
    {
      "epoch": 0.018574805808848363,
      "grad_norm": 5.087464160169475e-05,
      "learning_rate": 8.678619553365659e-05,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 0.020263424518743668,
      "grad_norm": 5.1521910791052505e-05,
      "learning_rate": 8.386407858128706e-05,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 0.021952043228638973,
      "grad_norm": 2.9947657822049223e-05,
      "learning_rate": 8.07106356344834e-05,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 0.02364066193853428,
      "grad_norm": 7.605524297105148e-05,
      "learning_rate": 7.734740790612136e-05,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 0.025329280648429583,
      "grad_norm": 3.3280884963460267e-05,
      "learning_rate": 7.379736965185368e-05,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 0.02701789935832489,
      "grad_norm": 6.204171950230375e-05,
      "learning_rate": 7.008477123264848e-05,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 0.028706518068220197,
      "grad_norm": 4.314877514843829e-05,
      "learning_rate": 6.623497346023418e-05,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 0.030395136778115502,
      "grad_norm": 4.03290796384681e-05,
      "learning_rate": 6.227427435703997e-05,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 0.032083755488010804,
      "grad_norm": 6.041528467903845e-05,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 0.033772374197906116,
      "grad_norm": 4.744988473248668e-05,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 0.033772374197906116,
      "eval_loss": 11.5,
      "eval_runtime": 10.9179,
      "eval_samples_per_second": 456.774,
      "eval_steps_per_second": 57.154,
      "step": 100
    },
    {
      "epoch": 0.03546099290780142,
      "grad_norm": 7.060080679366365e-05,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 105
    },
    {
      "epoch": 0.037149611617696726,
      "grad_norm": 6.990566180320457e-05,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 46.0,
      "step": 110
    },
    {
      "epoch": 0.03883823032759203,
      "grad_norm": 8.377931953873485e-05,
      "learning_rate": 4.17702704859633e-05,
      "loss": 46.0,
      "step": 115
    },
    {
      "epoch": 0.040526849037487336,
      "grad_norm": 7.871050911489874e-05,
      "learning_rate": 3.772572564296005e-05,
      "loss": 46.0,
      "step": 120
    },
    {
      "epoch": 0.04221546774738264,
      "grad_norm": 4.501568400883116e-05,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 46.0,
      "step": 125
    },
    {
      "epoch": 0.04390408645727795,
      "grad_norm": 5.9967882407363504e-05,
      "learning_rate": 2.991522876735154e-05,
      "loss": 46.0,
      "step": 130
    },
    {
      "epoch": 0.04559270516717325,
      "grad_norm": 7.424813520628959e-05,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 46.0,
      "step": 135
    },
    {
      "epoch": 0.04728132387706856,
      "grad_norm": 5.756051541538909e-05,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 46.0,
      "step": 140
    },
    {
      "epoch": 0.04896994258696386,
      "grad_norm": 8.542805153410882e-05,
      "learning_rate": 1.928936436551661e-05,
      "loss": 46.0,
      "step": 145
    },
    {
      "epoch": 0.05065856129685917,
      "grad_norm": 5.660971874021925e-05,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 46.0,
      "step": 150
    },
    {
      "epoch": 0.05065856129685917,
      "eval_loss": 11.5,
      "eval_runtime": 10.8808,
      "eval_samples_per_second": 458.329,
      "eval_steps_per_second": 57.349,
      "step": 150
    },
    {
      "epoch": 0.05234718000675447,
      "grad_norm": 7.042593642836437e-05,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 46.0,
      "step": 155
    },
    {
      "epoch": 0.05403579871664978,
      "grad_norm": 7.274065137607977e-05,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 46.0,
      "step": 160
    },
    {
      "epoch": 0.05572441742654509,
      "grad_norm": 7.54787542973645e-05,
      "learning_rate": 8.141676086873572e-06,
      "loss": 46.0,
      "step": 165
    },
    {
      "epoch": 0.057413036136440394,
      "grad_norm": 5.682763730874285e-05,
      "learning_rate": 6.026312439675552e-06,
      "loss": 46.0,
      "step": 170
    },
    {
      "epoch": 0.0591016548463357,
      "grad_norm": 5.760012936661951e-05,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 46.0,
      "step": 175
    },
    {
      "epoch": 0.060790273556231005,
      "grad_norm": 9.038842108566314e-05,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 46.0,
      "step": 180
    },
    {
      "epoch": 0.06247889226612631,
      "grad_norm": 7.682358409510925e-05,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 46.0,
      "step": 185
    },
    {
      "epoch": 0.06416751097602161,
      "grad_norm": 7.236807869048789e-05,
      "learning_rate": 6.819348298638839e-07,
      "loss": 46.0,
      "step": 190
    },
    {
      "epoch": 0.06585612968591692,
      "grad_norm": 8.365535904886201e-05,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 46.0,
      "step": 195
    },
    {
      "epoch": 0.06754474839581223,
      "grad_norm": 6.14263117313385e-05,
      "learning_rate": 0.0,
      "loss": 46.0,
      "step": 200
    },
    {
      "epoch": 0.06754474839581223,
      "eval_loss": 11.5,
      "eval_runtime": 15.3054,
      "eval_samples_per_second": 325.832,
      "eval_steps_per_second": 40.77,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 200,
  "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": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 45583545532416.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}