{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00013361793954456326,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.3361793954456326e-05,
      "grad_norm": 12.711153984069824,
      "learning_rate": 2e-05,
      "loss": 2.1096,
      "step": 1
    },
    {
      "epoch": 1.3361793954456326e-05,
      "eval_loss": 2.254793405532837,
      "eval_runtime": 551.6423,
      "eval_samples_per_second": 57.124,
      "eval_steps_per_second": 28.562,
      "step": 1
    },
    {
      "epoch": 2.6723587908912652e-05,
      "grad_norm": 15.669854164123535,
      "learning_rate": 4e-05,
      "loss": 1.9175,
      "step": 2
    },
    {
      "epoch": 4.0085381863368976e-05,
      "grad_norm": 13.797361373901367,
      "learning_rate": 6e-05,
      "loss": 2.0773,
      "step": 3
    },
    {
      "epoch": 4.0085381863368976e-05,
      "eval_loss": 2.1823835372924805,
      "eval_runtime": 549.2666,
      "eval_samples_per_second": 57.371,
      "eval_steps_per_second": 28.686,
      "step": 3
    },
    {
      "epoch": 5.3447175817825303e-05,
      "grad_norm": 9.476820945739746,
      "learning_rate": 8e-05,
      "loss": 1.7693,
      "step": 4
    },
    {
      "epoch": 6.680896977228163e-05,
      "grad_norm": 10.984297752380371,
      "learning_rate": 0.0001,
      "loss": 2.3105,
      "step": 5
    },
    {
      "epoch": 8.017076372673795e-05,
      "grad_norm": 7.2995734214782715,
      "learning_rate": 0.00012,
      "loss": 1.5486,
      "step": 6
    },
    {
      "epoch": 8.017076372673795e-05,
      "eval_loss": 1.6521787643432617,
      "eval_runtime": 547.3221,
      "eval_samples_per_second": 57.575,
      "eval_steps_per_second": 28.787,
      "step": 6
    },
    {
      "epoch": 9.353255768119427e-05,
      "grad_norm": 18.50226593017578,
      "learning_rate": 0.00014,
      "loss": 1.8519,
      "step": 7
    },
    {
      "epoch": 0.00010689435163565061,
      "grad_norm": 20.47998046875,
      "learning_rate": 0.00016,
      "loss": 1.3752,
      "step": 8
    },
    {
      "epoch": 0.00012025614559010693,
      "grad_norm": 32.270774841308594,
      "learning_rate": 0.00018,
      "loss": 1.3206,
      "step": 9
    },
    {
      "epoch": 0.00012025614559010693,
      "eval_loss": 1.212482213973999,
      "eval_runtime": 546.306,
      "eval_samples_per_second": 57.682,
      "eval_steps_per_second": 28.841,
      "step": 9
    },
    {
      "epoch": 0.00013361793954456326,
      "grad_norm": 14.155308723449707,
      "learning_rate": 0.0002,
      "loss": 1.3488,
      "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": 255791978250240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}