{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.12746972594008923,
  "eval_steps": 5,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025493945188017845,
      "eval_loss": 9.921944618225098,
      "eval_runtime": 44.9872,
      "eval_samples_per_second": 14.693,
      "eval_steps_per_second": 1.845,
      "step": 1
    },
    {
      "epoch": 0.0076481835564053535,
      "grad_norm": 91.03157806396484,
      "learning_rate": 3e-05,
      "loss": 41.0818,
      "step": 3
    },
    {
      "epoch": 0.012746972594008922,
      "eval_loss": 7.452924728393555,
      "eval_runtime": 45.6149,
      "eval_samples_per_second": 14.491,
      "eval_steps_per_second": 1.82,
      "step": 5
    },
    {
      "epoch": 0.015296367112810707,
      "grad_norm": 57.06651306152344,
      "learning_rate": 6e-05,
      "loss": 33.9118,
      "step": 6
    },
    {
      "epoch": 0.022944550669216062,
      "grad_norm": 33.99550247192383,
      "learning_rate": 9e-05,
      "loss": 18.7413,
      "step": 9
    },
    {
      "epoch": 0.025493945188017845,
      "eval_loss": 1.7238086462020874,
      "eval_runtime": 45.6025,
      "eval_samples_per_second": 14.495,
      "eval_steps_per_second": 1.82,
      "step": 10
    },
    {
      "epoch": 0.030592734225621414,
      "grad_norm": 16.043848037719727,
      "learning_rate": 9.938441702975689e-05,
      "loss": 7.497,
      "step": 12
    },
    {
      "epoch": 0.03824091778202677,
      "grad_norm": 6.3374714851379395,
      "learning_rate": 9.619397662556435e-05,
      "loss": 4.8002,
      "step": 15
    },
    {
      "epoch": 0.03824091778202677,
      "eval_loss": 1.1935869455337524,
      "eval_runtime": 45.6398,
      "eval_samples_per_second": 14.483,
      "eval_steps_per_second": 1.819,
      "step": 15
    },
    {
      "epoch": 0.045889101338432124,
      "grad_norm": 7.580458641052246,
      "learning_rate": 9.045084971874738e-05,
      "loss": 4.7468,
      "step": 18
    },
    {
      "epoch": 0.05098789037603569,
      "eval_loss": 1.1845386028289795,
      "eval_runtime": 45.6734,
      "eval_samples_per_second": 14.472,
      "eval_steps_per_second": 1.817,
      "step": 20
    },
    {
      "epoch": 0.05353728489483748,
      "grad_norm": 5.485244274139404,
      "learning_rate": 8.247240241650918e-05,
      "loss": 4.8632,
      "step": 21
    },
    {
      "epoch": 0.06118546845124283,
      "grad_norm": 4.333637237548828,
      "learning_rate": 7.269952498697734e-05,
      "loss": 4.6469,
      "step": 24
    },
    {
      "epoch": 0.06373486297004462,
      "eval_loss": 1.155869960784912,
      "eval_runtime": 45.6691,
      "eval_samples_per_second": 14.474,
      "eval_steps_per_second": 1.817,
      "step": 25
    },
    {
      "epoch": 0.06883365200764818,
      "grad_norm": 6.469546318054199,
      "learning_rate": 6.167226819279528e-05,
      "loss": 4.9472,
      "step": 27
    },
    {
      "epoch": 0.07648183556405354,
      "grad_norm": 4.241927623748779,
      "learning_rate": 5e-05,
      "loss": 4.5811,
      "step": 30
    },
    {
      "epoch": 0.07648183556405354,
      "eval_loss": 1.1859575510025024,
      "eval_runtime": 45.6587,
      "eval_samples_per_second": 14.477,
      "eval_steps_per_second": 1.818,
      "step": 30
    },
    {
      "epoch": 0.0841300191204589,
      "grad_norm": 4.258800983428955,
      "learning_rate": 3.832773180720475e-05,
      "loss": 4.7365,
      "step": 33
    },
    {
      "epoch": 0.08922880815806246,
      "eval_loss": 1.1394585371017456,
      "eval_runtime": 45.5765,
      "eval_samples_per_second": 14.503,
      "eval_steps_per_second": 1.821,
      "step": 35
    },
    {
      "epoch": 0.09177820267686425,
      "grad_norm": 20.26199722290039,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 4.4689,
      "step": 36
    },
    {
      "epoch": 0.0994263862332696,
      "grad_norm": 7.42047643661499,
      "learning_rate": 1.7527597583490822e-05,
      "loss": 4.5736,
      "step": 39
    },
    {
      "epoch": 0.10197578075207138,
      "eval_loss": 1.158954381942749,
      "eval_runtime": 45.6266,
      "eval_samples_per_second": 14.487,
      "eval_steps_per_second": 1.819,
      "step": 40
    },
    {
      "epoch": 0.10707456978967496,
      "grad_norm": 7.441665172576904,
      "learning_rate": 9.549150281252633e-06,
      "loss": 4.8598,
      "step": 42
    },
    {
      "epoch": 0.1147227533460803,
      "grad_norm": 8.042488098144531,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 4.4286,
      "step": 45
    },
    {
      "epoch": 0.1147227533460803,
      "eval_loss": 1.1251012086868286,
      "eval_runtime": 45.6063,
      "eval_samples_per_second": 14.494,
      "eval_steps_per_second": 1.82,
      "step": 45
    },
    {
      "epoch": 0.12237093690248566,
      "grad_norm": 5.9597859382629395,
      "learning_rate": 6.15582970243117e-07,
      "loss": 4.3533,
      "step": 48
    },
    {
      "epoch": 0.12746972594008923,
      "eval_loss": 1.1204696893692017,
      "eval_runtime": 45.6772,
      "eval_samples_per_second": 14.471,
      "eval_steps_per_second": 1.817,
      "step": 50
    }
  ],
  "logging_steps": 3,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.795984052125696e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}