{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000421474105684632,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.21474105684632e-05,
      "grad_norm": 0.541431188583374,
      "learning_rate": 2e-05,
      "loss": 1.7169,
      "step": 1
    },
    {
      "epoch": 4.21474105684632e-05,
      "eval_loss": 1.6580084562301636,
      "eval_runtime": 553.6364,
      "eval_samples_per_second": 18.044,
      "eval_steps_per_second": 9.022,
      "step": 1
    },
    {
      "epoch": 8.42948211369264e-05,
      "grad_norm": 0.48165619373321533,
      "learning_rate": 4e-05,
      "loss": 1.4538,
      "step": 2
    },
    {
      "epoch": 0.0001264422317053896,
      "grad_norm": 0.5114144086837769,
      "learning_rate": 6e-05,
      "loss": 1.7415,
      "step": 3
    },
    {
      "epoch": 0.0001264422317053896,
      "eval_loss": 1.6541515588760376,
      "eval_runtime": 553.1847,
      "eval_samples_per_second": 18.059,
      "eval_steps_per_second": 9.03,
      "step": 3
    },
    {
      "epoch": 0.0001685896422738528,
      "grad_norm": 0.5347130298614502,
      "learning_rate": 8e-05,
      "loss": 1.7013,
      "step": 4
    },
    {
      "epoch": 0.000210737052842316,
      "grad_norm": 0.7098687291145325,
      "learning_rate": 0.0001,
      "loss": 1.7653,
      "step": 5
    },
    {
      "epoch": 0.0002528844634107792,
      "grad_norm": 0.6764225959777832,
      "learning_rate": 0.00012,
      "loss": 1.6061,
      "step": 6
    },
    {
      "epoch": 0.0002528844634107792,
      "eval_loss": 1.6010996103286743,
      "eval_runtime": 553.2531,
      "eval_samples_per_second": 18.057,
      "eval_steps_per_second": 9.028,
      "step": 6
    },
    {
      "epoch": 0.0002950318739792424,
      "grad_norm": 0.7717322707176208,
      "learning_rate": 0.00014,
      "loss": 1.6238,
      "step": 7
    },
    {
      "epoch": 0.0003371792845477056,
      "grad_norm": 0.7759086489677429,
      "learning_rate": 0.00016,
      "loss": 1.6759,
      "step": 8
    },
    {
      "epoch": 0.0003793266951161688,
      "grad_norm": 0.6566513776779175,
      "learning_rate": 0.00018,
      "loss": 1.6666,
      "step": 9
    },
    {
      "epoch": 0.0003793266951161688,
      "eval_loss": 1.5033568143844604,
      "eval_runtime": 553.3876,
      "eval_samples_per_second": 18.052,
      "eval_steps_per_second": 9.026,
      "step": 9
    },
    {
      "epoch": 0.000421474105684632,
      "grad_norm": 0.6918085813522339,
      "learning_rate": 0.0002,
      "loss": 1.5941,
      "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": 3560411177680896.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}