{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0007838526357044876,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001567705271408975,
      "grad_norm": 16.795921325683594,
      "learning_rate": 1e-05,
      "loss": 104.0213,
      "step": 1
    },
    {
      "epoch": 0.0001567705271408975,
      "eval_loss": 7.0129475593566895,
      "eval_runtime": 1787.1811,
      "eval_samples_per_second": 6.012,
      "eval_steps_per_second": 3.006,
      "step": 1
    },
    {
      "epoch": 0.000313541054281795,
      "grad_norm": 19.216100692749023,
      "learning_rate": 2e-05,
      "loss": 112.8802,
      "step": 2
    },
    {
      "epoch": 0.000313541054281795,
      "eval_loss": 6.941263198852539,
      "eval_runtime": 1650.1215,
      "eval_samples_per_second": 6.511,
      "eval_steps_per_second": 3.256,
      "step": 2
    },
    {
      "epoch": 0.00047031158142269255,
      "grad_norm": 16.65349769592285,
      "learning_rate": 3e-05,
      "loss": 108.6886,
      "step": 3
    },
    {
      "epoch": 0.00062708210856359,
      "grad_norm": 18.71934700012207,
      "learning_rate": 4e-05,
      "loss": 99.0921,
      "step": 4
    },
    {
      "epoch": 0.00062708210856359,
      "eval_loss": 6.895726680755615,
      "eval_runtime": 1652.4436,
      "eval_samples_per_second": 6.502,
      "eval_steps_per_second": 3.251,
      "step": 4
    },
    {
      "epoch": 0.0007838526357044876,
      "grad_norm": 21.542518615722656,
      "learning_rate": 5e-05,
      "loss": 106.4952,
      "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": 6794734731264000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}