{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0020127811603683388,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004025562320736678,
      "grad_norm": 7.847188472747803,
      "learning_rate": 1e-05,
      "loss": 7.0975,
      "step": 1
    },
    {
      "epoch": 0.0004025562320736678,
      "eval_loss": 7.144729137420654,
      "eval_runtime": 261.2987,
      "eval_samples_per_second": 16.012,
      "eval_steps_per_second": 8.006,
      "step": 1
    },
    {
      "epoch": 0.0008051124641473356,
      "grad_norm": 7.879615306854248,
      "learning_rate": 2e-05,
      "loss": 6.7961,
      "step": 2
    },
    {
      "epoch": 0.0008051124641473356,
      "eval_loss": 6.924757480621338,
      "eval_runtime": 176.0128,
      "eval_samples_per_second": 23.771,
      "eval_steps_per_second": 11.885,
      "step": 2
    },
    {
      "epoch": 0.0012076686962210034,
      "grad_norm": 7.642736911773682,
      "learning_rate": 3e-05,
      "loss": 6.9927,
      "step": 3
    },
    {
      "epoch": 0.0016102249282946711,
      "grad_norm": 7.4557414054870605,
      "learning_rate": 4e-05,
      "loss": 6.9774,
      "step": 4
    },
    {
      "epoch": 0.0016102249282946711,
      "eval_loss": 6.5781683921813965,
      "eval_runtime": 176.6219,
      "eval_samples_per_second": 23.689,
      "eval_steps_per_second": 11.845,
      "step": 4
    },
    {
      "epoch": 0.0020127811603683388,
      "grad_norm": 7.715116500854492,
      "learning_rate": 5e-05,
      "loss": 6.2666,
      "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": 4808867045179392.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}