{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0030950170225936243,
  "eval_steps": 4,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00012380068090374498,
      "grad_norm": NaN,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.00012380068090374498,
      "eval_loss": NaN,
      "eval_runtime": 357.1677,
      "eval_samples_per_second": 9.525,
      "eval_steps_per_second": 2.383,
      "step": 1
    },
    {
      "epoch": 0.00024760136180748996,
      "grad_norm": NaN,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0003714020427112349,
      "grad_norm": NaN,
      "learning_rate": 3e-06,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0004952027236149799,
      "grad_norm": NaN,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0004952027236149799,
      "eval_loss": NaN,
      "eval_runtime": 356.5355,
      "eval_samples_per_second": 9.542,
      "eval_steps_per_second": 2.387,
      "step": 4
    },
    {
      "epoch": 0.0006190034045187249,
      "grad_norm": NaN,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0007428040854224698,
      "grad_norm": NaN,
      "learning_rate": 6e-06,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0008666047663262148,
      "grad_norm": NaN,
      "learning_rate": 7e-06,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0009904054472299599,
      "grad_norm": NaN,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0009904054472299599,
      "eval_loss": NaN,
      "eval_runtime": 356.7245,
      "eval_samples_per_second": 9.537,
      "eval_steps_per_second": 2.386,
      "step": 8
    },
    {
      "epoch": 0.0011142061281337048,
      "grad_norm": NaN,
      "learning_rate": 9e-06,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0012380068090374497,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.0013618074899411946,
      "grad_norm": NaN,
      "learning_rate": 9.890738003669029e-06,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.0014856081708449396,
      "grad_norm": NaN,
      "learning_rate": 9.567727288213005e-06,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0014856081708449396,
      "eval_loss": NaN,
      "eval_runtime": 356.7468,
      "eval_samples_per_second": 9.536,
      "eval_steps_per_second": 2.385,
      "step": 12
    },
    {
      "epoch": 0.0016094088517486847,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.0017332095326524296,
      "grad_norm": NaN,
      "learning_rate": 8.345653031794292e-06,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.0018570102135561746,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0019808108944599197,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.0019808108944599197,
      "eval_loss": NaN,
      "eval_runtime": 356.7515,
      "eval_samples_per_second": 9.536,
      "eval_steps_per_second": 2.385,
      "step": 16
    },
    {
      "epoch": 0.0021046115753636644,
      "grad_norm": NaN,
      "learning_rate": 5.522642316338268e-06,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.0022284122562674096,
      "grad_norm": NaN,
      "learning_rate": 4.477357683661734e-06,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0023522129371711543,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.0024760136180748994,
      "grad_norm": NaN,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0024760136180748994,
      "eval_loss": NaN,
      "eval_runtime": 356.6354,
      "eval_samples_per_second": 9.539,
      "eval_steps_per_second": 2.386,
      "step": 20
    },
    {
      "epoch": 0.0025998142989786446,
      "grad_norm": NaN,
      "learning_rate": 1.6543469682057105e-06,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0027236149798823893,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.0028474156607861344,
      "grad_norm": NaN,
      "learning_rate": 4.322727117869951e-07,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.002971216341689879,
      "grad_norm": NaN,
      "learning_rate": 1.0926199633097156e-07,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.002971216341689879,
      "eval_loss": NaN,
      "eval_runtime": 356.486,
      "eval_samples_per_second": 9.543,
      "eval_steps_per_second": 2.387,
      "step": 24
    },
    {
      "epoch": 0.0030950170225936243,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8168308054425600.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}