{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13588110403397027,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006794055201698514,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.6168,
      "step": 1
    },
    {
      "epoch": 0.006794055201698514,
      "eval_loss": NaN,
      "eval_runtime": 79.0556,
      "eval_samples_per_second": 3.137,
      "eval_steps_per_second": 1.569,
      "step": 1
    },
    {
      "epoch": 0.013588110403397028,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.02038216560509554,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.027176220806794056,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.03397027600849257,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.03397027600849257,
      "eval_loss": NaN,
      "eval_runtime": 2.3502,
      "eval_samples_per_second": 105.521,
      "eval_steps_per_second": 52.761,
      "step": 5
    },
    {
      "epoch": 0.04076433121019108,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0475583864118896,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.05435244161358811,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.061146496815286625,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.06794055201698514,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.06794055201698514,
      "eval_loss": NaN,
      "eval_runtime": 2.3633,
      "eval_samples_per_second": 104.937,
      "eval_steps_per_second": 52.469,
      "step": 10
    },
    {
      "epoch": 0.07473460721868365,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.08152866242038216,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.08832271762208067,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.0951167728237792,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.10191082802547771,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.10191082802547771,
      "eval_loss": NaN,
      "eval_runtime": 2.3469,
      "eval_samples_per_second": 105.673,
      "eval_steps_per_second": 52.836,
      "step": 15
    },
    {
      "epoch": 0.10870488322717622,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.11549893842887474,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.12229299363057325,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.12908704883227176,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.13588110403397027,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.13588110403397027,
      "eval_loss": NaN,
      "eval_runtime": 2.3136,
      "eval_samples_per_second": 107.19,
      "eval_steps_per_second": 53.595,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "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": 290370832957440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}