{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0009670478446921161,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.223492815640387e-05,
      "eval_loss": 4.91297721862793,
      "eval_runtime": 586.0104,
      "eval_samples_per_second": 22.29,
      "eval_steps_per_second": 11.145,
      "step": 1
    },
    {
      "epoch": 9.670478446921161e-05,
      "grad_norm": 0.5574466586112976,
      "learning_rate": 3e-05,
      "loss": 4.9944,
      "step": 3
    },
    {
      "epoch": 0.00019340956893842322,
      "grad_norm": 0.9119413495063782,
      "learning_rate": 6e-05,
      "loss": 4.8276,
      "step": 6
    },
    {
      "epoch": 0.00025787942525123096,
      "eval_loss": 4.782009124755859,
      "eval_runtime": 588.4106,
      "eval_samples_per_second": 22.199,
      "eval_steps_per_second": 11.099,
      "step": 8
    },
    {
      "epoch": 0.0002901143534076348,
      "grad_norm": 0.629593014717102,
      "learning_rate": 9e-05,
      "loss": 4.8815,
      "step": 9
    },
    {
      "epoch": 0.00038681913787684644,
      "grad_norm": 0.7127167582511902,
      "learning_rate": 9.755282581475769e-05,
      "loss": 4.7568,
      "step": 12
    },
    {
      "epoch": 0.00048352392234605806,
      "grad_norm": 0.5076147317886353,
      "learning_rate": 8.535533905932738e-05,
      "loss": 4.6065,
      "step": 15
    },
    {
      "epoch": 0.0005157588505024619,
      "eval_loss": 4.587831497192383,
      "eval_runtime": 584.8082,
      "eval_samples_per_second": 22.336,
      "eval_steps_per_second": 11.168,
      "step": 16
    },
    {
      "epoch": 0.0005802287068152696,
      "grad_norm": 0.4356367886066437,
      "learning_rate": 6.545084971874738e-05,
      "loss": 4.7105,
      "step": 18
    },
    {
      "epoch": 0.0006769334912844813,
      "grad_norm": 0.4588887095451355,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 4.6608,
      "step": 21
    },
    {
      "epoch": 0.0007736382757536929,
      "grad_norm": 0.5872651934623718,
      "learning_rate": 2.061073738537635e-05,
      "loss": 4.588,
      "step": 24
    },
    {
      "epoch": 0.0007736382757536929,
      "eval_loss": 4.554722309112549,
      "eval_runtime": 586.3558,
      "eval_samples_per_second": 22.277,
      "eval_steps_per_second": 11.138,
      "step": 24
    },
    {
      "epoch": 0.0008703430602229046,
      "grad_norm": 0.5140621066093445,
      "learning_rate": 5.449673790581611e-06,
      "loss": 4.4738,
      "step": 27
    },
    {
      "epoch": 0.0009670478446921161,
      "grad_norm": 0.5304310917854309,
      "learning_rate": 0.0,
      "loss": 4.6474,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2008388336615424.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}