{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04607789358200768,
  "eval_steps": 9,
  "global_step": 63,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007313951362223441,
      "eval_loss": 10.364601135253906,
      "eval_runtime": 5.9218,
      "eval_samples_per_second": 388.903,
      "eval_steps_per_second": 48.634,
      "step": 1
    },
    {
      "epoch": 0.0021941854086670325,
      "grad_norm": 0.03942021355032921,
      "learning_rate": 3e-05,
      "loss": 10.3614,
      "step": 3
    },
    {
      "epoch": 0.004388370817334065,
      "grad_norm": 0.043478213250637054,
      "learning_rate": 6e-05,
      "loss": 10.3643,
      "step": 6
    },
    {
      "epoch": 0.006582556226001097,
      "grad_norm": 0.04088541120290756,
      "learning_rate": 9e-05,
      "loss": 10.3649,
      "step": 9
    },
    {
      "epoch": 0.006582556226001097,
      "eval_loss": 10.3641357421875,
      "eval_runtime": 5.933,
      "eval_samples_per_second": 388.168,
      "eval_steps_per_second": 48.542,
      "step": 9
    },
    {
      "epoch": 0.00877674163466813,
      "grad_norm": 0.043213389813899994,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3636,
      "step": 12
    },
    {
      "epoch": 0.010970927043335162,
      "grad_norm": 0.040926627814769745,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.3624,
      "step": 15
    },
    {
      "epoch": 0.013165112452002194,
      "grad_norm": 0.04403068125247955,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.3638,
      "step": 18
    },
    {
      "epoch": 0.013165112452002194,
      "eval_loss": 10.362990379333496,
      "eval_runtime": 5.9511,
      "eval_samples_per_second": 386.987,
      "eval_steps_per_second": 48.394,
      "step": 18
    },
    {
      "epoch": 0.015359297860669226,
      "grad_norm": 0.03578553721308708,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.3645,
      "step": 21
    },
    {
      "epoch": 0.01755348326933626,
      "grad_norm": 0.03931654617190361,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.3648,
      "step": 24
    },
    {
      "epoch": 0.019747668678003292,
      "grad_norm": 0.045229654759168625,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.3649,
      "step": 27
    },
    {
      "epoch": 0.019747668678003292,
      "eval_loss": 10.361788749694824,
      "eval_runtime": 5.9151,
      "eval_samples_per_second": 389.344,
      "eval_steps_per_second": 48.689,
      "step": 27
    },
    {
      "epoch": 0.021941854086670324,
      "grad_norm": 0.04005541652441025,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3633,
      "step": 30
    },
    {
      "epoch": 0.024136039495337356,
      "grad_norm": 0.046545449644327164,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.3606,
      "step": 33
    },
    {
      "epoch": 0.026330224904004388,
      "grad_norm": 0.051434703171253204,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.3625,
      "step": 36
    },
    {
      "epoch": 0.026330224904004388,
      "eval_loss": 10.360490798950195,
      "eval_runtime": 5.9512,
      "eval_samples_per_second": 386.98,
      "eval_steps_per_second": 48.393,
      "step": 36
    },
    {
      "epoch": 0.02852441031267142,
      "grad_norm": 0.052758339792490005,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.3602,
      "step": 39
    },
    {
      "epoch": 0.030718595721338452,
      "grad_norm": 0.049764346331357956,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.3591,
      "step": 42
    },
    {
      "epoch": 0.03291278113000549,
      "grad_norm": 0.044394351541996,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.3574,
      "step": 45
    },
    {
      "epoch": 0.03291278113000549,
      "eval_loss": 10.359164237976074,
      "eval_runtime": 5.9037,
      "eval_samples_per_second": 390.095,
      "eval_steps_per_second": 48.783,
      "step": 45
    },
    {
      "epoch": 0.03510696653867252,
      "grad_norm": 0.04386267438530922,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.3583,
      "step": 48
    },
    {
      "epoch": 0.03730115194733955,
      "grad_norm": 0.055752791464328766,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.3627,
      "step": 51
    },
    {
      "epoch": 0.039495337356006584,
      "grad_norm": 0.05771073326468468,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.358,
      "step": 54
    },
    {
      "epoch": 0.039495337356006584,
      "eval_loss": 10.357931137084961,
      "eval_runtime": 5.8745,
      "eval_samples_per_second": 392.035,
      "eval_steps_per_second": 49.026,
      "step": 54
    },
    {
      "epoch": 0.041689522764673616,
      "grad_norm": 0.04935748130083084,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.3587,
      "step": 57
    },
    {
      "epoch": 0.04388370817334065,
      "grad_norm": 0.05488388612866402,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.3586,
      "step": 60
    },
    {
      "epoch": 0.04607789358200768,
      "grad_norm": 0.06005234271287918,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.3566,
      "step": 63
    },
    {
      "epoch": 0.04607789358200768,
      "eval_loss": 10.356916427612305,
      "eval_runtime": 5.9411,
      "eval_samples_per_second": 387.638,
      "eval_steps_per_second": 48.476,
      "step": 63
    }
  ],
  "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": 9283684270080.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}