{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.016185594820609658,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005395198273536552,
      "eval_loss": 10.37635612487793,
      "eval_runtime": 2.3593,
      "eval_samples_per_second": 331.032,
      "eval_steps_per_second": 165.728,
      "step": 1
    },
    {
      "epoch": 0.0016185594820609657,
      "grad_norm": 0.03989125043153763,
      "learning_rate": 6e-05,
      "loss": 10.379,
      "step": 3
    },
    {
      "epoch": 0.0032371189641219314,
      "grad_norm": 0.03422015532851219,
      "learning_rate": 0.00012,
      "loss": 10.375,
      "step": 6
    },
    {
      "epoch": 0.004316158618829242,
      "eval_loss": 10.376011848449707,
      "eval_runtime": 2.3813,
      "eval_samples_per_second": 327.966,
      "eval_steps_per_second": 164.193,
      "step": 8
    },
    {
      "epoch": 0.0048556784461828975,
      "grad_norm": 0.033457089215517044,
      "learning_rate": 0.00018,
      "loss": 10.3781,
      "step": 9
    },
    {
      "epoch": 0.006474237928243863,
      "grad_norm": 0.03284232318401337,
      "learning_rate": 0.00019510565162951537,
      "loss": 10.3776,
      "step": 12
    },
    {
      "epoch": 0.008092797410304829,
      "grad_norm": 0.04211742803454399,
      "learning_rate": 0.00017071067811865476,
      "loss": 10.3778,
      "step": 15
    },
    {
      "epoch": 0.008632317237658484,
      "eval_loss": 10.375029563903809,
      "eval_runtime": 2.4423,
      "eval_samples_per_second": 319.782,
      "eval_steps_per_second": 160.096,
      "step": 16
    },
    {
      "epoch": 0.009711356892365795,
      "grad_norm": 0.0264265239238739,
      "learning_rate": 0.00013090169943749476,
      "loss": 10.3724,
      "step": 18
    },
    {
      "epoch": 0.01132991637442676,
      "grad_norm": 0.03241078555583954,
      "learning_rate": 8.435655349597689e-05,
      "loss": 10.3745,
      "step": 21
    },
    {
      "epoch": 0.012948475856487725,
      "grad_norm": 0.05751446634531021,
      "learning_rate": 4.12214747707527e-05,
      "loss": 10.3767,
      "step": 24
    },
    {
      "epoch": 0.012948475856487725,
      "eval_loss": 10.374396324157715,
      "eval_runtime": 2.3962,
      "eval_samples_per_second": 325.934,
      "eval_steps_per_second": 163.176,
      "step": 24
    },
    {
      "epoch": 0.014567035338548692,
      "grad_norm": 0.03685376048088074,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 10.38,
      "step": 27
    },
    {
      "epoch": 0.016185594820609658,
      "grad_norm": 0.034746699035167694,
      "learning_rate": 0.0,
      "loss": 10.3767,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 784536698880.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}