{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0011567881776248247,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00023135763552496494,
      "grad_norm": 0.9703558683395386,
      "learning_rate": 1e-05,
      "loss": 1.6578,
      "step": 1
    },
    {
      "epoch": 0.00023135763552496494,
      "eval_loss": 2.1697514057159424,
      "eval_runtime": 369.8016,
      "eval_samples_per_second": 19.686,
      "eval_steps_per_second": 9.843,
      "step": 1
    },
    {
      "epoch": 0.0004627152710499299,
      "grad_norm": 2.0454063415527344,
      "learning_rate": 2e-05,
      "loss": 2.078,
      "step": 2
    },
    {
      "epoch": 0.0004627152710499299,
      "eval_loss": 2.127061128616333,
      "eval_runtime": 193.7546,
      "eval_samples_per_second": 37.573,
      "eval_steps_per_second": 18.787,
      "step": 2
    },
    {
      "epoch": 0.0006940729065748948,
      "grad_norm": 1.6047369241714478,
      "learning_rate": 3e-05,
      "loss": 2.1175,
      "step": 3
    },
    {
      "epoch": 0.0009254305420998598,
      "grad_norm": 1.6281163692474365,
      "learning_rate": 4e-05,
      "loss": 2.1508,
      "step": 4
    },
    {
      "epoch": 0.0009254305420998598,
      "eval_loss": 2.0870847702026367,
      "eval_runtime": 176.1345,
      "eval_samples_per_second": 41.332,
      "eval_steps_per_second": 20.666,
      "step": 4
    },
    {
      "epoch": 0.0011567881776248247,
      "grad_norm": 1.1154183149337769,
      "learning_rate": 5e-05,
      "loss": 1.6447,
      "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": 3295645846732800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}