{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006808510638297872,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006808510638297873,
      "grad_norm": 9.413938522338867,
      "learning_rate": 2e-05,
      "loss": 6.1076,
      "step": 1
    },
    {
      "epoch": 0.0006808510638297873,
      "eval_loss": 9.31494426727295,
      "eval_runtime": 40.3532,
      "eval_samples_per_second": 7.682,
      "eval_steps_per_second": 7.682,
      "step": 1
    },
    {
      "epoch": 0.0013617021276595745,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 9.0477,
      "step": 2
    },
    {
      "epoch": 0.0020425531914893616,
      "grad_norm": 13.506296157836914,
      "learning_rate": 4e-05,
      "loss": 7.9634,
      "step": 3
    },
    {
      "epoch": 0.0020425531914893616,
      "eval_loss": 9.232772827148438,
      "eval_runtime": 40.3184,
      "eval_samples_per_second": 7.689,
      "eval_steps_per_second": 7.689,
      "step": 3
    },
    {
      "epoch": 0.002723404255319149,
      "grad_norm": 14.115647315979004,
      "learning_rate": 6e-05,
      "loss": 9.5016,
      "step": 4
    },
    {
      "epoch": 0.003404255319148936,
      "grad_norm": 11.721460342407227,
      "learning_rate": 8e-05,
      "loss": 8.0658,
      "step": 5
    },
    {
      "epoch": 0.004085106382978723,
      "grad_norm": 15.277981758117676,
      "learning_rate": 0.0001,
      "loss": 7.7441,
      "step": 6
    },
    {
      "epoch": 0.004085106382978723,
      "eval_loss": 8.222854614257812,
      "eval_runtime": 40.3279,
      "eval_samples_per_second": 7.687,
      "eval_steps_per_second": 7.687,
      "step": 6
    },
    {
      "epoch": 0.004765957446808511,
      "grad_norm": 11.895439147949219,
      "learning_rate": 0.00012,
      "loss": 7.4861,
      "step": 7
    },
    {
      "epoch": 0.005446808510638298,
      "grad_norm": 13.066421508789062,
      "learning_rate": 0.00014,
      "loss": 7.6098,
      "step": 8
    },
    {
      "epoch": 0.006127659574468085,
      "grad_norm": 11.546978950500488,
      "learning_rate": 0.00016,
      "loss": 6.4677,
      "step": 9
    },
    {
      "epoch": 0.006127659574468085,
      "eval_loss": 6.334994792938232,
      "eval_runtime": 40.3134,
      "eval_samples_per_second": 7.69,
      "eval_steps_per_second": 7.69,
      "step": 9
    },
    {
      "epoch": 0.006808510638297872,
      "grad_norm": 9.970052719116211,
      "learning_rate": 0.00018,
      "loss": 7.4085,
      "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": 2010596581048320.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}