{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010084033613445379,
  "eval_steps": 3,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016806722689075631,
      "grad_norm": 9.418672561645508,
      "learning_rate": 2e-05,
      "loss": 44.5542,
      "step": 1
    },
    {
      "epoch": 0.0016806722689075631,
      "eval_loss": 11.104904174804688,
      "eval_runtime": 2.8126,
      "eval_samples_per_second": 89.242,
      "eval_steps_per_second": 44.799,
      "step": 1
    },
    {
      "epoch": 0.0033613445378151263,
      "grad_norm": 9.15264892578125,
      "learning_rate": 4e-05,
      "loss": 44.4688,
      "step": 2
    },
    {
      "epoch": 0.005042016806722689,
      "grad_norm": 10.31497573852539,
      "learning_rate": 6e-05,
      "loss": 44.3937,
      "step": 3
    },
    {
      "epoch": 0.005042016806722689,
      "eval_loss": 11.091708183288574,
      "eval_runtime": 2.2441,
      "eval_samples_per_second": 111.846,
      "eval_steps_per_second": 56.146,
      "step": 3
    },
    {
      "epoch": 0.0067226890756302525,
      "grad_norm": 9.29781723022461,
      "learning_rate": 8e-05,
      "loss": 44.8208,
      "step": 4
    },
    {
      "epoch": 0.008403361344537815,
      "grad_norm": 10.151296615600586,
      "learning_rate": 0.0001,
      "loss": 44.3333,
      "step": 5
    },
    {
      "epoch": 0.010084033613445379,
      "grad_norm": 9.226962089538574,
      "learning_rate": 0.00012,
      "loss": 44.2604,
      "step": 6
    },
    {
      "epoch": 0.010084033613445379,
      "eval_loss": 11.047111511230469,
      "eval_runtime": 2.2793,
      "eval_samples_per_second": 110.122,
      "eval_steps_per_second": 55.28,
      "step": 6
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 499189284864.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}