{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08506113769271664,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004253056884635832,
      "eval_loss": 10.378556251525879,
      "eval_runtime": 3.2562,
      "eval_samples_per_second": 304.033,
      "eval_steps_per_second": 152.017,
      "step": 1
    },
    {
      "epoch": 0.002126528442317916,
      "grad_norm": 0.015116095542907715,
      "learning_rate": 5e-05,
      "loss": 10.3789,
      "step": 5
    },
    {
      "epoch": 0.004253056884635832,
      "grad_norm": 0.01645716466009617,
      "learning_rate": 0.0001,
      "loss": 10.3781,
      "step": 10
    },
    {
      "epoch": 0.006379585326953748,
      "grad_norm": 0.01671130210161209,
      "learning_rate": 9.98292246503335e-05,
      "loss": 10.3789,
      "step": 15
    },
    {
      "epoch": 0.008506113769271665,
      "grad_norm": 0.013499540276825428,
      "learning_rate": 9.931806517013612e-05,
      "loss": 10.3803,
      "step": 20
    },
    {
      "epoch": 0.01063264221158958,
      "grad_norm": 0.01616002433001995,
      "learning_rate": 9.847001329696653e-05,
      "loss": 10.3796,
      "step": 25
    },
    {
      "epoch": 0.012759170653907496,
      "grad_norm": 0.025751912966370583,
      "learning_rate": 9.729086208503174e-05,
      "loss": 10.3792,
      "step": 30
    },
    {
      "epoch": 0.014885699096225412,
      "grad_norm": 0.018546029925346375,
      "learning_rate": 9.578866633275288e-05,
      "loss": 10.3803,
      "step": 35
    },
    {
      "epoch": 0.01701222753854333,
      "grad_norm": 0.022502359002828598,
      "learning_rate": 9.397368756032445e-05,
      "loss": 10.3781,
      "step": 40
    },
    {
      "epoch": 0.019138755980861243,
      "grad_norm": 0.018336759880185127,
      "learning_rate": 9.185832391312644e-05,
      "loss": 10.3781,
      "step": 45
    },
    {
      "epoch": 0.02126528442317916,
      "grad_norm": 0.01745198853313923,
      "learning_rate": 8.945702546981969e-05,
      "loss": 10.378,
      "step": 50
    },
    {
      "epoch": 0.02126528442317916,
      "eval_loss": 10.377801895141602,
      "eval_runtime": 3.3118,
      "eval_samples_per_second": 298.931,
      "eval_steps_per_second": 149.465,
      "step": 50
    },
    {
      "epoch": 0.023391812865497075,
      "grad_norm": 0.01711806282401085,
      "learning_rate": 8.678619553365659e-05,
      "loss": 10.38,
      "step": 55
    },
    {
      "epoch": 0.025518341307814992,
      "grad_norm": 0.02074848860502243,
      "learning_rate": 8.386407858128706e-05,
      "loss": 10.3752,
      "step": 60
    },
    {
      "epoch": 0.02764486975013291,
      "grad_norm": 0.019658250734210014,
      "learning_rate": 8.07106356344834e-05,
      "loss": 10.3791,
      "step": 65
    },
    {
      "epoch": 0.029771398192450824,
      "grad_norm": 0.018285149708390236,
      "learning_rate": 7.734740790612136e-05,
      "loss": 10.3758,
      "step": 70
    },
    {
      "epoch": 0.03189792663476874,
      "grad_norm": 0.01787448488175869,
      "learning_rate": 7.379736965185368e-05,
      "loss": 10.3775,
      "step": 75
    },
    {
      "epoch": 0.03402445507708666,
      "grad_norm": 0.018909407779574394,
      "learning_rate": 7.008477123264848e-05,
      "loss": 10.3771,
      "step": 80
    },
    {
      "epoch": 0.03615098351940457,
      "grad_norm": 0.016881730407476425,
      "learning_rate": 6.623497346023418e-05,
      "loss": 10.3786,
      "step": 85
    },
    {
      "epoch": 0.03827751196172249,
      "grad_norm": 0.01865757815539837,
      "learning_rate": 6.227427435703997e-05,
      "loss": 10.379,
      "step": 90
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 0.022227605804800987,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 10.3765,
      "step": 95
    },
    {
      "epoch": 0.04253056884635832,
      "grad_norm": 0.04912203922867775,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 10.3773,
      "step": 100
    },
    {
      "epoch": 0.04253056884635832,
      "eval_loss": 10.37693977355957,
      "eval_runtime": 3.1865,
      "eval_samples_per_second": 310.685,
      "eval_steps_per_second": 155.342,
      "step": 100
    },
    {
      "epoch": 0.044657097288676235,
      "grad_norm": 0.018772883340716362,
      "learning_rate": 5e-05,
      "loss": 10.3782,
      "step": 105
    },
    {
      "epoch": 0.04678362573099415,
      "grad_norm": 0.028032859787344933,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 10.3769,
      "step": 110
    },
    {
      "epoch": 0.04891015417331207,
      "grad_norm": 0.014557150192558765,
      "learning_rate": 4.17702704859633e-05,
      "loss": 10.3784,
      "step": 115
    },
    {
      "epoch": 0.051036682615629984,
      "grad_norm": 0.03546245023608208,
      "learning_rate": 3.772572564296005e-05,
      "loss": 10.3749,
      "step": 120
    },
    {
      "epoch": 0.0531632110579479,
      "grad_norm": 0.01906292513012886,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 10.3765,
      "step": 125
    },
    {
      "epoch": 0.05528973950026582,
      "grad_norm": 0.02249256521463394,
      "learning_rate": 2.991522876735154e-05,
      "loss": 10.3759,
      "step": 130
    },
    {
      "epoch": 0.05741626794258373,
      "grad_norm": 0.022847173735499382,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 10.3769,
      "step": 135
    },
    {
      "epoch": 0.05954279638490165,
      "grad_norm": 0.022361597046256065,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 10.3763,
      "step": 140
    },
    {
      "epoch": 0.06166932482721956,
      "grad_norm": 0.021767321974039078,
      "learning_rate": 1.928936436551661e-05,
      "loss": 10.3786,
      "step": 145
    },
    {
      "epoch": 0.06379585326953748,
      "grad_norm": 0.023146463558077812,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 10.3771,
      "step": 150
    },
    {
      "epoch": 0.06379585326953748,
      "eval_loss": 10.376352310180664,
      "eval_runtime": 3.1976,
      "eval_samples_per_second": 309.608,
      "eval_steps_per_second": 154.804,
      "step": 150
    },
    {
      "epoch": 0.0659223817118554,
      "grad_norm": 0.03459914028644562,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 10.3752,
      "step": 155
    },
    {
      "epoch": 0.06804891015417332,
      "grad_norm": 0.026126541197299957,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 10.3767,
      "step": 160
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 0.02168152667582035,
      "learning_rate": 8.141676086873572e-06,
      "loss": 10.3748,
      "step": 165
    },
    {
      "epoch": 0.07230196703880915,
      "grad_norm": 0.030395662412047386,
      "learning_rate": 6.026312439675552e-06,
      "loss": 10.3775,
      "step": 170
    },
    {
      "epoch": 0.07442849548112707,
      "grad_norm": 0.02148647978901863,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 10.3768,
      "step": 175
    },
    {
      "epoch": 0.07655502392344497,
      "grad_norm": 0.027581162750720978,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 10.3745,
      "step": 180
    },
    {
      "epoch": 0.0786815523657629,
      "grad_norm": 0.019557451829314232,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 10.3774,
      "step": 185
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 0.0335659459233284,
      "learning_rate": 6.819348298638839e-07,
      "loss": 10.3748,
      "step": 190
    },
    {
      "epoch": 0.08293460925039872,
      "grad_norm": 0.018269188702106476,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 10.3759,
      "step": 195
    },
    {
      "epoch": 0.08506113769271664,
      "grad_norm": 0.025745518505573273,
      "learning_rate": 0.0,
      "loss": 10.3751,
      "step": 200
    },
    {
      "epoch": 0.08506113769271664,
      "eval_loss": 10.376242637634277,
      "eval_runtime": 3.2404,
      "eval_samples_per_second": 305.514,
      "eval_steps_per_second": 152.757,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5437446881280.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}