{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.018194223334091427,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003638844666818285,
      "grad_norm": 15.743388175964355,
      "learning_rate": 1e-05,
      "loss": 9.4147,
      "step": 1
    },
    {
      "epoch": 0.003638844666818285,
      "eval_loss": 9.673070907592773,
      "eval_runtime": 112.189,
      "eval_samples_per_second": 4.127,
      "eval_steps_per_second": 2.068,
      "step": 1
    },
    {
      "epoch": 0.00727768933363657,
      "grad_norm": 15.617484092712402,
      "learning_rate": 2e-05,
      "loss": 9.4858,
      "step": 2
    },
    {
      "epoch": 0.00727768933363657,
      "eval_loss": 9.374789237976074,
      "eval_runtime": 25.024,
      "eval_samples_per_second": 18.502,
      "eval_steps_per_second": 9.271,
      "step": 2
    },
    {
      "epoch": 0.010916534000454855,
      "grad_norm": 15.522367477416992,
      "learning_rate": 3e-05,
      "loss": 9.4558,
      "step": 3
    },
    {
      "epoch": 0.01455537866727314,
      "grad_norm": 15.092039108276367,
      "learning_rate": 4e-05,
      "loss": 9.3868,
      "step": 4
    },
    {
      "epoch": 0.01455537866727314,
      "eval_loss": 8.692112922668457,
      "eval_runtime": 25.0164,
      "eval_samples_per_second": 18.508,
      "eval_steps_per_second": 9.274,
      "step": 4
    },
    {
      "epoch": 0.018194223334091427,
      "grad_norm": 15.947641372680664,
      "learning_rate": 5e-05,
      "loss": 8.8001,
      "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": 3822182832537600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}