{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004590314436538903,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004590314436538903,
      "grad_norm": 1.3668051958084106,
      "learning_rate": 2e-05,
      "loss": 44.313,
      "step": 1
    },
    {
      "epoch": 0.0004590314436538903,
      "eval_loss": 11.08893871307373,
      "eval_runtime": 2.5034,
      "eval_samples_per_second": 366.699,
      "eval_steps_per_second": 183.349,
      "step": 1
    },
    {
      "epoch": 0.0009180628873077806,
      "grad_norm": 1.162681221961975,
      "learning_rate": 4e-05,
      "loss": 44.3196,
      "step": 2
    },
    {
      "epoch": 0.001377094330961671,
      "grad_norm": 1.092293620109558,
      "learning_rate": 6e-05,
      "loss": 44.422,
      "step": 3
    },
    {
      "epoch": 0.001377094330961671,
      "eval_loss": 11.088753700256348,
      "eval_runtime": 2.0372,
      "eval_samples_per_second": 450.612,
      "eval_steps_per_second": 225.306,
      "step": 3
    },
    {
      "epoch": 0.0018361257746155612,
      "grad_norm": 1.034910798072815,
      "learning_rate": 8e-05,
      "loss": 44.3525,
      "step": 4
    },
    {
      "epoch": 0.0022951572182694515,
      "grad_norm": 1.1993321180343628,
      "learning_rate": 0.0001,
      "loss": 44.3262,
      "step": 5
    },
    {
      "epoch": 0.002754188661923342,
      "grad_norm": 1.2331390380859375,
      "learning_rate": 0.00012,
      "loss": 44.3666,
      "step": 6
    },
    {
      "epoch": 0.002754188661923342,
      "eval_loss": 11.087939262390137,
      "eval_runtime": 2.0726,
      "eval_samples_per_second": 442.924,
      "eval_steps_per_second": 221.462,
      "step": 6
    },
    {
      "epoch": 0.003213220105577232,
      "grad_norm": 1.1357131004333496,
      "learning_rate": 0.00014,
      "loss": 44.3384,
      "step": 7
    },
    {
      "epoch": 0.0036722515492311225,
      "grad_norm": 0.9281848073005676,
      "learning_rate": 0.00016,
      "loss": 44.3828,
      "step": 8
    },
    {
      "epoch": 0.004131282992885013,
      "grad_norm": 1.3926825523376465,
      "learning_rate": 0.00018,
      "loss": 44.3876,
      "step": 9
    },
    {
      "epoch": 0.004131282992885013,
      "eval_loss": 11.086424827575684,
      "eval_runtime": 2.0742,
      "eval_samples_per_second": 442.582,
      "eval_steps_per_second": 221.291,
      "step": 9
    },
    {
      "epoch": 0.004590314436538903,
      "grad_norm": 1.4349191188812256,
      "learning_rate": 0.0002,
      "loss": 44.3378,
      "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": 7471104000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}