{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005519715734639666,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005519715734639666,
      "grad_norm": 0.028218459337949753,
      "learning_rate": 1e-05,
      "loss": 11.9268,
      "step": 1
    },
    {
      "epoch": 0.0005519715734639666,
      "eval_loss": 11.924099922180176,
      "eval_runtime": 11.6004,
      "eval_samples_per_second": 263.095,
      "eval_steps_per_second": 131.548,
      "step": 1
    },
    {
      "epoch": 0.0011039431469279332,
      "grad_norm": 0.037630319595336914,
      "learning_rate": 2e-05,
      "loss": 11.9218,
      "step": 2
    },
    {
      "epoch": 0.0016559147203918999,
      "grad_norm": 0.03941420838236809,
      "learning_rate": 3e-05,
      "loss": 11.9268,
      "step": 3
    },
    {
      "epoch": 0.0016559147203918999,
      "eval_loss": 11.924081802368164,
      "eval_runtime": 4.1944,
      "eval_samples_per_second": 727.642,
      "eval_steps_per_second": 363.821,
      "step": 3
    },
    {
      "epoch": 0.0022078862938558663,
      "grad_norm": 0.050059083849191666,
      "learning_rate": 4e-05,
      "loss": 11.9234,
      "step": 4
    },
    {
      "epoch": 0.002759857867319833,
      "grad_norm": 0.038522422313690186,
      "learning_rate": 5e-05,
      "loss": 11.9252,
      "step": 5
    },
    {
      "epoch": 0.0033118294407837997,
      "grad_norm": 0.03802747279405594,
      "learning_rate": 6e-05,
      "loss": 11.9218,
      "step": 6
    },
    {
      "epoch": 0.0033118294407837997,
      "eval_loss": 11.924002647399902,
      "eval_runtime": 4.2591,
      "eval_samples_per_second": 716.59,
      "eval_steps_per_second": 358.295,
      "step": 6
    },
    {
      "epoch": 0.003863801014247766,
      "grad_norm": 0.04355938360095024,
      "learning_rate": 7e-05,
      "loss": 11.9278,
      "step": 7
    },
    {
      "epoch": 0.004415772587711733,
      "grad_norm": 0.04228552058339119,
      "learning_rate": 8e-05,
      "loss": 11.9289,
      "step": 8
    },
    {
      "epoch": 0.004967744161175699,
      "grad_norm": 0.04489218071103096,
      "learning_rate": 9e-05,
      "loss": 11.9273,
      "step": 9
    },
    {
      "epoch": 0.004967744161175699,
      "eval_loss": 11.923870086669922,
      "eval_runtime": 4.3152,
      "eval_samples_per_second": 707.26,
      "eval_steps_per_second": 353.63,
      "step": 9
    },
    {
      "epoch": 0.005519715734639666,
      "grad_norm": 0.0435008704662323,
      "learning_rate": 0.0001,
      "loss": 11.9317,
      "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": 4726456320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}