{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0011959433601224645,
  "eval_steps": 7,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.7837734404898585e-05,
      "eval_loss": NaN,
      "eval_runtime": 1288.4559,
      "eval_samples_per_second": 6.831,
      "eval_steps_per_second": 3.416,
      "step": 1
    },
    {
      "epoch": 0.00014351320321469576,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0002870264064293915,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00033486414083429007,
      "eval_loss": NaN,
      "eval_runtime": 1289.5727,
      "eval_samples_per_second": 6.826,
      "eval_steps_per_second": 3.413,
      "step": 7
    },
    {
      "epoch": 0.00043053960964408724,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.000574052812858783,
      "grad_norm": NaN,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0006697282816685801,
      "eval_loss": NaN,
      "eval_runtime": 1288.7737,
      "eval_samples_per_second": 6.83,
      "eval_steps_per_second": 3.415,
      "step": 14
    },
    {
      "epoch": 0.0007175660160734788,
      "grad_norm": NaN,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0008610792192881745,
      "grad_norm": NaN,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0010045924225028703,
      "grad_norm": NaN,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0010045924225028703,
      "eval_loss": NaN,
      "eval_runtime": 1288.2551,
      "eval_samples_per_second": 6.832,
      "eval_steps_per_second": 3.416,
      "step": 21
    },
    {
      "epoch": 0.001148105625717566,
      "grad_norm": NaN,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.0,
      "step": 24
    }
  ],
  "logging_steps": 3,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 30,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1499252895186944e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}