{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00881057268722467,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000881057268722467,
      "grad_norm": 0.9495444893836975,
      "learning_rate": 2e-05,
      "loss": 7.3361,
      "step": 1
    },
    {
      "epoch": 0.000881057268722467,
      "eval_loss": 1.7044769525527954,
      "eval_runtime": 26.1095,
      "eval_samples_per_second": 18.308,
      "eval_steps_per_second": 9.154,
      "step": 1
    },
    {
      "epoch": 0.001762114537444934,
      "grad_norm": 0.9346479773521423,
      "learning_rate": 4e-05,
      "loss": 7.4161,
      "step": 2
    },
    {
      "epoch": 0.0026431718061674008,
      "grad_norm": 0.7981148362159729,
      "learning_rate": 6e-05,
      "loss": 6.6434,
      "step": 3
    },
    {
      "epoch": 0.0026431718061674008,
      "eval_loss": 1.7027397155761719,
      "eval_runtime": 25.9222,
      "eval_samples_per_second": 18.44,
      "eval_steps_per_second": 9.22,
      "step": 3
    },
    {
      "epoch": 0.003524229074889868,
      "grad_norm": 0.9818300008773804,
      "learning_rate": 8e-05,
      "loss": 6.9665,
      "step": 4
    },
    {
      "epoch": 0.004405286343612335,
      "grad_norm": 1.1542925834655762,
      "learning_rate": 0.0001,
      "loss": 7.614,
      "step": 5
    },
    {
      "epoch": 0.0052863436123348016,
      "grad_norm": 1.1080232858657837,
      "learning_rate": 0.00012,
      "loss": 6.5453,
      "step": 6
    },
    {
      "epoch": 0.0052863436123348016,
      "eval_loss": 1.676714301109314,
      "eval_runtime": 25.8459,
      "eval_samples_per_second": 18.494,
      "eval_steps_per_second": 9.247,
      "step": 6
    },
    {
      "epoch": 0.006167400881057269,
      "grad_norm": 1.2612648010253906,
      "learning_rate": 0.00014,
      "loss": 6.9101,
      "step": 7
    },
    {
      "epoch": 0.007048458149779736,
      "grad_norm": 1.3245511054992676,
      "learning_rate": 0.00016,
      "loss": 6.7708,
      "step": 8
    },
    {
      "epoch": 0.007929515418502203,
      "grad_norm": 1.502492904663086,
      "learning_rate": 0.00018,
      "loss": 6.5086,
      "step": 9
    },
    {
      "epoch": 0.007929515418502203,
      "eval_loss": 1.5617804527282715,
      "eval_runtime": 26.0349,
      "eval_samples_per_second": 18.36,
      "eval_steps_per_second": 9.18,
      "step": 9
    },
    {
      "epoch": 0.00881057268722467,
      "grad_norm": 1.1788829565048218,
      "learning_rate": 0.0002,
      "loss": 6.1462,
      "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": 3166224305356800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}