{
  "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": 0.9824252128601074,
      "eval_runtime": 136.0458,
      "eval_samples_per_second": 7.277,
      "eval_steps_per_second": 3.638,
      "step": 1
    },
    {
      "epoch": 0.002126528442317916,
      "grad_norm": 3.689708709716797,
      "learning_rate": 5e-05,
      "loss": 2.7323,
      "step": 5
    },
    {
      "epoch": 0.004253056884635832,
      "grad_norm": 3.5804293155670166,
      "learning_rate": 0.0001,
      "loss": 2.6902,
      "step": 10
    },
    {
      "epoch": 0.006379585326953748,
      "grad_norm": 4.66812801361084,
      "learning_rate": 9.98292246503335e-05,
      "loss": 3.0764,
      "step": 15
    },
    {
      "epoch": 0.008506113769271665,
      "grad_norm": 5.284685134887695,
      "learning_rate": 9.931806517013612e-05,
      "loss": 3.0659,
      "step": 20
    },
    {
      "epoch": 0.01063264221158958,
      "grad_norm": 5.655339241027832,
      "learning_rate": 9.847001329696653e-05,
      "loss": 3.0061,
      "step": 25
    },
    {
      "epoch": 0.012759170653907496,
      "grad_norm": 6.231191635131836,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.9899,
      "step": 30
    },
    {
      "epoch": 0.014885699096225412,
      "grad_norm": 8.713586807250977,
      "learning_rate": 9.578866633275288e-05,
      "loss": 3.1171,
      "step": 35
    },
    {
      "epoch": 0.01701222753854333,
      "grad_norm": 5.008473873138428,
      "learning_rate": 9.397368756032445e-05,
      "loss": 3.0791,
      "step": 40
    },
    {
      "epoch": 0.019138755980861243,
      "grad_norm": 5.398619174957275,
      "learning_rate": 9.185832391312644e-05,
      "loss": 3.2609,
      "step": 45
    },
    {
      "epoch": 0.02126528442317916,
      "grad_norm": 8.028454780578613,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.5866,
      "step": 50
    },
    {
      "epoch": 0.02126528442317916,
      "eval_loss": 0.6829224824905396,
      "eval_runtime": 137.4281,
      "eval_samples_per_second": 7.204,
      "eval_steps_per_second": 3.602,
      "step": 50
    },
    {
      "epoch": 0.023391812865497075,
      "grad_norm": 2.8156120777130127,
      "learning_rate": 8.678619553365659e-05,
      "loss": 2.3899,
      "step": 55
    },
    {
      "epoch": 0.025518341307814992,
      "grad_norm": 3.178457498550415,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.4402,
      "step": 60
    },
    {
      "epoch": 0.02764486975013291,
      "grad_norm": 33.99382781982422,
      "learning_rate": 8.07106356344834e-05,
      "loss": 2.4891,
      "step": 65
    },
    {
      "epoch": 0.029771398192450824,
      "grad_norm": 5.488627910614014,
      "learning_rate": 7.734740790612136e-05,
      "loss": 2.71,
      "step": 70
    },
    {
      "epoch": 0.03189792663476874,
      "grad_norm": 5.214168548583984,
      "learning_rate": 7.379736965185368e-05,
      "loss": 2.5916,
      "step": 75
    },
    {
      "epoch": 0.03402445507708666,
      "grad_norm": 5.504047870635986,
      "learning_rate": 7.008477123264848e-05,
      "loss": 3.3086,
      "step": 80
    },
    {
      "epoch": 0.03615098351940457,
      "grad_norm": 6.215364456176758,
      "learning_rate": 6.623497346023418e-05,
      "loss": 2.8177,
      "step": 85
    },
    {
      "epoch": 0.03827751196172249,
      "grad_norm": 4.62170934677124,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.8857,
      "step": 90
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 4.945453643798828,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 2.8055,
      "step": 95
    },
    {
      "epoch": 0.04253056884635832,
      "grad_norm": 8.435017585754395,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 2.7629,
      "step": 100
    },
    {
      "epoch": 0.04253056884635832,
      "eval_loss": 0.6609275341033936,
      "eval_runtime": 137.2892,
      "eval_samples_per_second": 7.211,
      "eval_steps_per_second": 3.606,
      "step": 100
    },
    {
      "epoch": 0.044657097288676235,
      "grad_norm": 2.559234619140625,
      "learning_rate": 5e-05,
      "loss": 2.2846,
      "step": 105
    },
    {
      "epoch": 0.04678362573099415,
      "grad_norm": 2.6849217414855957,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 2.2953,
      "step": 110
    },
    {
      "epoch": 0.04891015417331207,
      "grad_norm": 3.239586591720581,
      "learning_rate": 4.17702704859633e-05,
      "loss": 2.3252,
      "step": 115
    },
    {
      "epoch": 0.051036682615629984,
      "grad_norm": 4.120462894439697,
      "learning_rate": 3.772572564296005e-05,
      "loss": 2.8153,
      "step": 120
    },
    {
      "epoch": 0.0531632110579479,
      "grad_norm": 4.456450939178467,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 2.687,
      "step": 125
    },
    {
      "epoch": 0.05528973950026582,
      "grad_norm": 5.071579456329346,
      "learning_rate": 2.991522876735154e-05,
      "loss": 2.5384,
      "step": 130
    },
    {
      "epoch": 0.05741626794258373,
      "grad_norm": 7.56506872177124,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 3.0014,
      "step": 135
    },
    {
      "epoch": 0.05954279638490165,
      "grad_norm": 6.288489818572998,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 2.7008,
      "step": 140
    },
    {
      "epoch": 0.06166932482721956,
      "grad_norm": 5.382243633270264,
      "learning_rate": 1.928936436551661e-05,
      "loss": 2.7762,
      "step": 145
    },
    {
      "epoch": 0.06379585326953748,
      "grad_norm": 5.935976028442383,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 2.4324,
      "step": 150
    },
    {
      "epoch": 0.06379585326953748,
      "eval_loss": 0.6443139910697937,
      "eval_runtime": 137.3505,
      "eval_samples_per_second": 7.208,
      "eval_steps_per_second": 3.604,
      "step": 150
    },
    {
      "epoch": 0.0659223817118554,
      "grad_norm": 2.6514077186584473,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 2.2345,
      "step": 155
    },
    {
      "epoch": 0.06804891015417332,
      "grad_norm": 3.0705318450927734,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 2.2573,
      "step": 160
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 4.471902847290039,
      "learning_rate": 8.141676086873572e-06,
      "loss": 2.3292,
      "step": 165
    },
    {
      "epoch": 0.07230196703880915,
      "grad_norm": 34.3349723815918,
      "learning_rate": 6.026312439675552e-06,
      "loss": 2.6387,
      "step": 170
    },
    {
      "epoch": 0.07442849548112707,
      "grad_norm": 4.226323127746582,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 2.4839,
      "step": 175
    },
    {
      "epoch": 0.07655502392344497,
      "grad_norm": 4.699221611022949,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 2.7164,
      "step": 180
    },
    {
      "epoch": 0.0786815523657629,
      "grad_norm": 7.135721683502197,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 2.6103,
      "step": 185
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 25.025192260742188,
      "learning_rate": 6.819348298638839e-07,
      "loss": 3.127,
      "step": 190
    },
    {
      "epoch": 0.08293460925039872,
      "grad_norm": 5.208532810211182,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 2.8339,
      "step": 195
    },
    {
      "epoch": 0.08506113769271664,
      "grad_norm": 5.95538330078125,
      "learning_rate": 0.0,
      "loss": 2.3014,
      "step": 200
    },
    {
      "epoch": 0.08506113769271664,
      "eval_loss": 0.6416370868682861,
      "eval_runtime": 137.6919,
      "eval_samples_per_second": 7.19,
      "eval_steps_per_second": 3.595,
      "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": 1.271246088044544e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}