{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05784526391901663,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011569052783803326,
      "grad_norm": 5.558375358581543,
      "learning_rate": 1e-05,
      "loss": 20.5273,
      "step": 1
    },
    {
      "epoch": 0.011569052783803326,
      "eval_loss": NaN,
      "eval_runtime": 54.2677,
      "eval_samples_per_second": 2.69,
      "eval_steps_per_second": 1.345,
      "step": 1
    },
    {
      "epoch": 0.023138105567606652,
      "grad_norm": 7.110665321350098,
      "learning_rate": 2e-05,
      "loss": 21.1713,
      "step": 2
    },
    {
      "epoch": 0.023138105567606652,
      "eval_loss": NaN,
      "eval_runtime": 3.5368,
      "eval_samples_per_second": 41.28,
      "eval_steps_per_second": 20.64,
      "step": 2
    },
    {
      "epoch": 0.03470715835140998,
      "grad_norm": 5.456160068511963,
      "learning_rate": 3e-05,
      "loss": 20.8095,
      "step": 3
    },
    {
      "epoch": 0.046276211135213303,
      "grad_norm": 5.923030376434326,
      "learning_rate": 4e-05,
      "loss": 20.7911,
      "step": 4
    },
    {
      "epoch": 0.046276211135213303,
      "eval_loss": NaN,
      "eval_runtime": 3.5704,
      "eval_samples_per_second": 40.892,
      "eval_steps_per_second": 20.446,
      "step": 4
    },
    {
      "epoch": 0.05784526391901663,
      "grad_norm": 6.397828578948975,
      "learning_rate": 5e-05,
      "loss": 20.5015,
      "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": 3699128496291840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}