{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04134762633996937,
  "eval_steps": 9,
  "global_step": 81,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005104645227156713,
      "eval_loss": NaN,
      "eval_runtime": 8.1128,
      "eval_samples_per_second": 406.764,
      "eval_steps_per_second": 50.907,
      "step": 1
    },
    {
      "epoch": 0.0015313935681470138,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0030627871362940277,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.004594180704441042,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.004594180704441042,
      "eval_loss": NaN,
      "eval_runtime": 7.6688,
      "eval_samples_per_second": 430.315,
      "eval_steps_per_second": 53.855,
      "step": 9
    },
    {
      "epoch": 0.006125574272588055,
      "grad_norm": NaN,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.007656967840735069,
      "grad_norm": NaN,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.009188361408882083,
      "grad_norm": NaN,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.009188361408882083,
      "eval_loss": NaN,
      "eval_runtime": 7.6933,
      "eval_samples_per_second": 428.945,
      "eval_steps_per_second": 53.683,
      "step": 18
    },
    {
      "epoch": 0.010719754977029096,
      "grad_norm": NaN,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.01225114854517611,
      "grad_norm": NaN,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.013782542113323124,
      "grad_norm": NaN,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.013782542113323124,
      "eval_loss": NaN,
      "eval_runtime": 7.7058,
      "eval_samples_per_second": 428.247,
      "eval_steps_per_second": 53.596,
      "step": 27
    },
    {
      "epoch": 0.015313935681470138,
      "grad_norm": NaN,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.016845329249617153,
      "grad_norm": NaN,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.018376722817764167,
      "grad_norm": NaN,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.018376722817764167,
      "eval_loss": NaN,
      "eval_runtime": 7.7273,
      "eval_samples_per_second": 427.056,
      "eval_steps_per_second": 53.447,
      "step": 36
    },
    {
      "epoch": 0.019908116385911178,
      "grad_norm": NaN,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.021439509954058193,
      "grad_norm": NaN,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.022970903522205207,
      "grad_norm": NaN,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.022970903522205207,
      "eval_loss": NaN,
      "eval_runtime": 7.7117,
      "eval_samples_per_second": 427.919,
      "eval_steps_per_second": 53.555,
      "step": 45
    },
    {
      "epoch": 0.02450229709035222,
      "grad_norm": NaN,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.026033690658499236,
      "grad_norm": NaN,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.027565084226646247,
      "grad_norm": NaN,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.027565084226646247,
      "eval_loss": NaN,
      "eval_runtime": 7.7692,
      "eval_samples_per_second": 424.757,
      "eval_steps_per_second": 53.159,
      "step": 54
    },
    {
      "epoch": 0.02909647779479326,
      "grad_norm": NaN,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.030627871362940276,
      "grad_norm": NaN,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.03215926493108729,
      "grad_norm": NaN,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.03215926493108729,
      "eval_loss": NaN,
      "eval_runtime": 7.6876,
      "eval_samples_per_second": 429.263,
      "eval_steps_per_second": 53.723,
      "step": 63
    },
    {
      "epoch": 0.033690658499234305,
      "grad_norm": NaN,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.03522205206738132,
      "grad_norm": NaN,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.036753445635528334,
      "grad_norm": NaN,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.036753445635528334,
      "eval_loss": NaN,
      "eval_runtime": 7.7385,
      "eval_samples_per_second": 426.439,
      "eval_steps_per_second": 53.37,
      "step": 72
    },
    {
      "epoch": 0.03828483920367534,
      "grad_norm": NaN,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.039816232771822356,
      "grad_norm": NaN,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.04134762633996937,
      "grad_norm": NaN,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.04134762633996937,
      "eval_loss": NaN,
      "eval_runtime": 7.6954,
      "eval_samples_per_second": 428.825,
      "eval_steps_per_second": 53.668,
      "step": 81
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 23038284791808.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}