{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02950940612320177,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005901881224640354,
      "grad_norm": 16.552900314331055,
      "learning_rate": 1e-05,
      "loss": 179.3125,
      "step": 1
    },
    {
      "epoch": 0.005901881224640354,
      "eval_loss": 11.218094825744629,
      "eval_runtime": 7.5373,
      "eval_samples_per_second": 37.945,
      "eval_steps_per_second": 18.972,
      "step": 1
    },
    {
      "epoch": 0.011803762449280709,
      "grad_norm": 16.680683135986328,
      "learning_rate": 2e-05,
      "loss": 179.75,
      "step": 2
    },
    {
      "epoch": 0.011803762449280709,
      "eval_loss": 11.217657089233398,
      "eval_runtime": 0.555,
      "eval_samples_per_second": 515.337,
      "eval_steps_per_second": 257.668,
      "step": 2
    },
    {
      "epoch": 0.01770564367392106,
      "grad_norm": 16.59784507751465,
      "learning_rate": 3e-05,
      "loss": 179.3125,
      "step": 3
    },
    {
      "epoch": 0.023607524898561418,
      "grad_norm": 16.891735076904297,
      "learning_rate": 4e-05,
      "loss": 179.4375,
      "step": 4
    },
    {
      "epoch": 0.023607524898561418,
      "eval_loss": 11.215035438537598,
      "eval_runtime": 0.5661,
      "eval_samples_per_second": 505.247,
      "eval_steps_per_second": 252.623,
      "step": 4
    },
    {
      "epoch": 0.02950940612320177,
      "grad_norm": 16.74252700805664,
      "learning_rate": 5e-05,
      "loss": 179.5625,
      "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": 385792081920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}