{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002055287226389888,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002055287226389888,
      "grad_norm": 17.887754440307617,
      "learning_rate": 2e-05,
      "loss": 20.7071,
      "step": 1
    },
    {
      "epoch": 0.0002055287226389888,
      "eval_loss": 5.155395984649658,
      "eval_runtime": 58.9663,
      "eval_samples_per_second": 34.749,
      "eval_steps_per_second": 17.383,
      "step": 1
    },
    {
      "epoch": 0.0004110574452779776,
      "grad_norm": 18.337974548339844,
      "learning_rate": 4e-05,
      "loss": 20.2608,
      "step": 2
    },
    {
      "epoch": 0.0006165861679169664,
      "grad_norm": 19.769615173339844,
      "learning_rate": 6e-05,
      "loss": 20.6774,
      "step": 3
    },
    {
      "epoch": 0.0006165861679169664,
      "eval_loss": 5.117892265319824,
      "eval_runtime": 57.4988,
      "eval_samples_per_second": 35.636,
      "eval_steps_per_second": 17.826,
      "step": 3
    },
    {
      "epoch": 0.0008221148905559552,
      "grad_norm": 19.885204315185547,
      "learning_rate": 8e-05,
      "loss": 19.5359,
      "step": 4
    },
    {
      "epoch": 0.001027643613194944,
      "grad_norm": 20.998010635375977,
      "learning_rate": 0.0001,
      "loss": 22.1287,
      "step": 5
    },
    {
      "epoch": 0.0012331723358339328,
      "grad_norm": 22.576335906982422,
      "learning_rate": 0.00012,
      "loss": 20.3478,
      "step": 6
    },
    {
      "epoch": 0.0012331723358339328,
      "eval_loss": 4.822153091430664,
      "eval_runtime": 57.6946,
      "eval_samples_per_second": 35.515,
      "eval_steps_per_second": 17.766,
      "step": 6
    },
    {
      "epoch": 0.0014387010584729215,
      "grad_norm": 20.084911346435547,
      "learning_rate": 0.00014,
      "loss": 19.1541,
      "step": 7
    },
    {
      "epoch": 0.0016442297811119105,
      "grad_norm": 18.954261779785156,
      "learning_rate": 0.00016,
      "loss": 16.6352,
      "step": 8
    },
    {
      "epoch": 0.0018497585037508992,
      "grad_norm": 24.837106704711914,
      "learning_rate": 0.00018,
      "loss": 19.5278,
      "step": 9
    },
    {
      "epoch": 0.0018497585037508992,
      "eval_loss": 3.9167871475219727,
      "eval_runtime": 57.6462,
      "eval_samples_per_second": 35.544,
      "eval_steps_per_second": 17.781,
      "step": 9
    },
    {
      "epoch": 0.002055287226389888,
      "grad_norm": 22.87350845336914,
      "learning_rate": 0.0002,
      "loss": 16.4763,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1305898647552000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}