{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.30864197530864196,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006172839506172839,
      "eval_loss": 11.103055000305176,
      "eval_runtime": 1.1491,
      "eval_samples_per_second": 60.046,
      "eval_steps_per_second": 30.458,
      "step": 1
    },
    {
      "epoch": 0.030864197530864196,
      "grad_norm": 1.2091351747512817,
      "learning_rate": 5e-05,
      "loss": 44.4063,
      "step": 5
    },
    {
      "epoch": 0.06172839506172839,
      "grad_norm": 0.92451012134552,
      "learning_rate": 0.0001,
      "loss": 44.3968,
      "step": 10
    },
    {
      "epoch": 0.06172839506172839,
      "eval_loss": 11.0997953414917,
      "eval_runtime": 0.3699,
      "eval_samples_per_second": 186.524,
      "eval_steps_per_second": 94.614,
      "step": 10
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 1.2541087865829468,
      "learning_rate": 9.619397662556435e-05,
      "loss": 44.3926,
      "step": 15
    },
    {
      "epoch": 0.12345679012345678,
      "grad_norm": 1.094192385673523,
      "learning_rate": 8.535533905932738e-05,
      "loss": 44.3622,
      "step": 20
    },
    {
      "epoch": 0.12345679012345678,
      "eval_loss": 11.090730667114258,
      "eval_runtime": 0.3616,
      "eval_samples_per_second": 190.829,
      "eval_steps_per_second": 96.797,
      "step": 20
    },
    {
      "epoch": 0.15432098765432098,
      "grad_norm": 1.0229359865188599,
      "learning_rate": 6.91341716182545e-05,
      "loss": 44.3424,
      "step": 25
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 1.2451244592666626,
      "learning_rate": 5e-05,
      "loss": 44.3362,
      "step": 30
    },
    {
      "epoch": 0.18518518518518517,
      "eval_loss": 11.081714630126953,
      "eval_runtime": 0.3782,
      "eval_samples_per_second": 182.461,
      "eval_steps_per_second": 92.553,
      "step": 30
    },
    {
      "epoch": 0.21604938271604937,
      "grad_norm": 1.223387598991394,
      "learning_rate": 3.086582838174551e-05,
      "loss": 44.2939,
      "step": 35
    },
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 1.3323183059692383,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 44.2949,
      "step": 40
    },
    {
      "epoch": 0.24691358024691357,
      "eval_loss": 11.077107429504395,
      "eval_runtime": 0.388,
      "eval_samples_per_second": 177.824,
      "eval_steps_per_second": 90.2,
      "step": 40
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 1.403401255607605,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 44.2959,
      "step": 45
    },
    {
      "epoch": 0.30864197530864196,
      "grad_norm": 1.1209239959716797,
      "learning_rate": 0.0,
      "loss": 44.3291,
      "step": 50
    },
    {
      "epoch": 0.30864197530864196,
      "eval_loss": 11.076295852661133,
      "eval_runtime": 0.3649,
      "eval_samples_per_second": 189.081,
      "eval_steps_per_second": 95.91,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 482240102400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}