{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002083007863354684,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002083007863354684,
      "grad_norm": 0.020760023966431618,
      "learning_rate": 2e-05,
      "loss": 10.3758,
      "step": 1
    },
    {
      "epoch": 0.0002083007863354684,
      "eval_loss": 10.377957344055176,
      "eval_runtime": 5.393,
      "eval_samples_per_second": 374.933,
      "eval_steps_per_second": 187.466,
      "step": 1
    },
    {
      "epoch": 0.0004166015726709368,
      "grad_norm": 0.018370022997260094,
      "learning_rate": 4e-05,
      "loss": 10.3782,
      "step": 2
    },
    {
      "epoch": 0.0006249023590064052,
      "grad_norm": 0.017808234319090843,
      "learning_rate": 6e-05,
      "loss": 10.376,
      "step": 3
    },
    {
      "epoch": 0.0006249023590064052,
      "eval_loss": 10.377946853637695,
      "eval_runtime": 5.42,
      "eval_samples_per_second": 373.059,
      "eval_steps_per_second": 186.53,
      "step": 3
    },
    {
      "epoch": 0.0008332031453418737,
      "grad_norm": 0.014559566974639893,
      "learning_rate": 8e-05,
      "loss": 10.3766,
      "step": 4
    },
    {
      "epoch": 0.001041503931677342,
      "grad_norm": 0.014331599697470665,
      "learning_rate": 0.0001,
      "loss": 10.3777,
      "step": 5
    },
    {
      "epoch": 0.0012498047180128104,
      "grad_norm": 0.01702534221112728,
      "learning_rate": 0.00012,
      "loss": 10.3773,
      "step": 6
    },
    {
      "epoch": 0.0012498047180128104,
      "eval_loss": 10.377894401550293,
      "eval_runtime": 5.4941,
      "eval_samples_per_second": 368.034,
      "eval_steps_per_second": 184.017,
      "step": 6
    },
    {
      "epoch": 0.001458105504348279,
      "grad_norm": 0.01738913357257843,
      "learning_rate": 0.00014,
      "loss": 10.3765,
      "step": 7
    },
    {
      "epoch": 0.0016664062906837473,
      "grad_norm": 0.02019212394952774,
      "learning_rate": 0.00016,
      "loss": 10.3767,
      "step": 8
    },
    {
      "epoch": 0.0018747070770192159,
      "grad_norm": 0.016985896974802017,
      "learning_rate": 0.00018,
      "loss": 10.377,
      "step": 9
    },
    {
      "epoch": 0.0018747070770192159,
      "eval_loss": 10.377796173095703,
      "eval_runtime": 5.4923,
      "eval_samples_per_second": 368.152,
      "eval_steps_per_second": 184.076,
      "step": 9
    },
    {
      "epoch": 0.002083007863354684,
      "grad_norm": 0.015802349895238876,
      "learning_rate": 0.0002,
      "loss": 10.377,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 174567260160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}