{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013029315960912053,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0026058631921824105,
      "grad_norm": 83.162109375,
      "learning_rate": 1e-05,
      "loss": 172.9864,
      "step": 1
    },
    {
      "epoch": 0.0026058631921824105,
      "eval_loss": 10.98365306854248,
      "eval_runtime": 63.2057,
      "eval_samples_per_second": 10.236,
      "eval_steps_per_second": 5.126,
      "step": 1
    },
    {
      "epoch": 0.005211726384364821,
      "grad_norm": 86.73918151855469,
      "learning_rate": 2e-05,
      "loss": 180.1079,
      "step": 2
    },
    {
      "epoch": 0.005211726384364821,
      "eval_loss": 10.806900024414062,
      "eval_runtime": 34.0248,
      "eval_samples_per_second": 19.016,
      "eval_steps_per_second": 9.522,
      "step": 2
    },
    {
      "epoch": 0.007817589576547232,
      "grad_norm": 103.43224334716797,
      "learning_rate": 3e-05,
      "loss": 174.1901,
      "step": 3
    },
    {
      "epoch": 0.010423452768729642,
      "grad_norm": 88.40193176269531,
      "learning_rate": 4e-05,
      "loss": 176.9486,
      "step": 4
    },
    {
      "epoch": 0.010423452768729642,
      "eval_loss": 10.61976146697998,
      "eval_runtime": 34.2698,
      "eval_samples_per_second": 18.88,
      "eval_steps_per_second": 9.454,
      "step": 4
    },
    {
      "epoch": 0.013029315960912053,
      "grad_norm": 97.77085876464844,
      "learning_rate": 5e-05,
      "loss": 174.9047,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6332408345395200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}