{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05879710914213385,
  "eval_steps": 9,
  "global_step": 45,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013066024253807521,
      "eval_loss": NaN,
      "eval_runtime": 439.2747,
      "eval_samples_per_second": 5.869,
      "eval_steps_per_second": 2.934,
      "step": 1
    },
    {
      "epoch": 0.003919807276142257,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.007839614552284513,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.011759421828426769,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.011759421828426769,
      "eval_loss": NaN,
      "eval_runtime": 439.3706,
      "eval_samples_per_second": 5.867,
      "eval_steps_per_second": 2.934,
      "step": 9
    },
    {
      "epoch": 0.015679229104569026,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.019599036380711282,
      "grad_norm": NaN,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.023518843656853538,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.023518843656853538,
      "eval_loss": NaN,
      "eval_runtime": 439.3537,
      "eval_samples_per_second": 5.868,
      "eval_steps_per_second": 2.934,
      "step": 18
    },
    {
      "epoch": 0.027438650932995794,
      "grad_norm": NaN,
      "learning_rate": 0.0001999229036240723,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.03135845820913805,
      "grad_norm": NaN,
      "learning_rate": 0.00019876883405951377,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.035278265485280305,
      "grad_norm": NaN,
      "learning_rate": 0.00019624552364536473,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.035278265485280305,
      "eval_loss": NaN,
      "eval_runtime": 439.4105,
      "eval_samples_per_second": 5.867,
      "eval_steps_per_second": 2.933,
      "step": 27
    },
    {
      "epoch": 0.039198072761422564,
      "grad_norm": NaN,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.04311788003756482,
      "grad_norm": NaN,
      "learning_rate": 0.00018724960070727972,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.047037687313707076,
      "grad_norm": NaN,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.047037687313707076,
      "eval_loss": NaN,
      "eval_runtime": 439.315,
      "eval_samples_per_second": 5.868,
      "eval_steps_per_second": 2.934,
      "step": 36
    },
    {
      "epoch": 0.050957494589849335,
      "grad_norm": NaN,
      "learning_rate": 0.00017343225094356855,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.05487730186599159,
      "grad_norm": NaN,
      "learning_rate": 0.00016494480483301836,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.05879710914213385,
      "grad_norm": NaN,
      "learning_rate": 0.00015555702330196023,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.05879710914213385,
      "eval_loss": NaN,
      "eval_runtime": 439.436,
      "eval_samples_per_second": 5.867,
      "eval_steps_per_second": 2.933,
      "step": 45
    }
  ],
  "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": 4.602762570498048e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}