{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.015787811809283233,
  "eval_steps": 4,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006315124723713293,
      "grad_norm": 1.6231694221496582,
      "learning_rate": 1e-05,
      "loss": 1.4639,
      "step": 1
    },
    {
      "epoch": 0.0006315124723713293,
      "eval_loss": 1.4297218322753906,
      "eval_runtime": 147.347,
      "eval_samples_per_second": 9.053,
      "eval_steps_per_second": 1.133,
      "step": 1
    },
    {
      "epoch": 0.0012630249447426586,
      "grad_norm": 1.371222972869873,
      "learning_rate": 2e-05,
      "loss": 1.2465,
      "step": 2
    },
    {
      "epoch": 0.001894537417113988,
      "grad_norm": 1.57561457157135,
      "learning_rate": 3e-05,
      "loss": 1.306,
      "step": 3
    },
    {
      "epoch": 0.0025260498894853173,
      "grad_norm": 1.6284863948822021,
      "learning_rate": 4e-05,
      "loss": 1.4806,
      "step": 4
    },
    {
      "epoch": 0.0025260498894853173,
      "eval_loss": 1.4122623205184937,
      "eval_runtime": 146.9317,
      "eval_samples_per_second": 9.079,
      "eval_steps_per_second": 1.137,
      "step": 4
    },
    {
      "epoch": 0.0031575623618566467,
      "grad_norm": 1.6506390571594238,
      "learning_rate": 5e-05,
      "loss": 1.3763,
      "step": 5
    },
    {
      "epoch": 0.003789074834227976,
      "grad_norm": 1.495873212814331,
      "learning_rate": 6e-05,
      "loss": 1.3849,
      "step": 6
    },
    {
      "epoch": 0.004420587306599305,
      "grad_norm": 1.7928879261016846,
      "learning_rate": 7e-05,
      "loss": 1.5544,
      "step": 7
    },
    {
      "epoch": 0.0050520997789706345,
      "grad_norm": 1.6524287462234497,
      "learning_rate": 8e-05,
      "loss": 1.3508,
      "step": 8
    },
    {
      "epoch": 0.0050520997789706345,
      "eval_loss": 1.2305155992507935,
      "eval_runtime": 146.9104,
      "eval_samples_per_second": 9.08,
      "eval_steps_per_second": 1.137,
      "step": 8
    },
    {
      "epoch": 0.005683612251341964,
      "grad_norm": 1.367221713066101,
      "learning_rate": 9e-05,
      "loss": 1.2594,
      "step": 9
    },
    {
      "epoch": 0.006315124723713293,
      "grad_norm": 1.0462695360183716,
      "learning_rate": 0.0001,
      "loss": 1.1139,
      "step": 10
    },
    {
      "epoch": 0.006946637196084623,
      "grad_norm": 1.2705315351486206,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.0496,
      "step": 11
    },
    {
      "epoch": 0.007578149668455952,
      "grad_norm": 0.9749987721443176,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.1736,
      "step": 12
    },
    {
      "epoch": 0.007578149668455952,
      "eval_loss": 1.096311330795288,
      "eval_runtime": 146.9674,
      "eval_samples_per_second": 9.077,
      "eval_steps_per_second": 1.136,
      "step": 12
    },
    {
      "epoch": 0.008209662140827282,
      "grad_norm": 1.246494174003601,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.0207,
      "step": 13
    },
    {
      "epoch": 0.00884117461319861,
      "grad_norm": 1.047814965248108,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.012,
      "step": 14
    },
    {
      "epoch": 0.00947268708556994,
      "grad_norm": 1.0972003936767578,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.0798,
      "step": 15
    },
    {
      "epoch": 0.010104199557941269,
      "grad_norm": 0.9175119400024414,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.9433,
      "step": 16
    },
    {
      "epoch": 0.010104199557941269,
      "eval_loss": 1.0177850723266602,
      "eval_runtime": 146.953,
      "eval_samples_per_second": 9.078,
      "eval_steps_per_second": 1.136,
      "step": 16
    },
    {
      "epoch": 0.0107357120303126,
      "grad_norm": 0.9215424060821533,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.0286,
      "step": 17
    },
    {
      "epoch": 0.011367224502683928,
      "grad_norm": 1.0609725713729858,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.1007,
      "step": 18
    },
    {
      "epoch": 0.011998736975055258,
      "grad_norm": 0.855086088180542,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.0273,
      "step": 19
    },
    {
      "epoch": 0.012630249447426587,
      "grad_norm": 0.9077870845794678,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.0521,
      "step": 20
    },
    {
      "epoch": 0.012630249447426587,
      "eval_loss": 1.0034620761871338,
      "eval_runtime": 146.9695,
      "eval_samples_per_second": 9.077,
      "eval_steps_per_second": 1.136,
      "step": 20
    },
    {
      "epoch": 0.013261761919797915,
      "grad_norm": 0.8460921049118042,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.134,
      "step": 21
    },
    {
      "epoch": 0.013893274392169246,
      "grad_norm": 0.8915419578552246,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.8705,
      "step": 22
    },
    {
      "epoch": 0.014524786864540574,
      "grad_norm": 0.9171346426010132,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.0633,
      "step": 23
    },
    {
      "epoch": 0.015156299336911904,
      "grad_norm": 0.992637038230896,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.0297,
      "step": 24
    },
    {
      "epoch": 0.015156299336911904,
      "eval_loss": 0.9986490607261658,
      "eval_runtime": 146.9673,
      "eval_samples_per_second": 9.077,
      "eval_steps_per_second": 1.136,
      "step": 24
    },
    {
      "epoch": 0.015787811809283233,
      "grad_norm": 0.954824686050415,
      "learning_rate": 0.0,
      "loss": 0.9646,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.85475042115584e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}