{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09813542688910697,
  "eval_steps": 5,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001962708537782139,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.001962708537782139,
      "eval_loss": NaN,
      "eval_runtime": 113.1751,
      "eval_samples_per_second": 3.799,
      "eval_steps_per_second": 1.9,
      "step": 1
    },
    {
      "epoch": 0.003925417075564278,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.005888125613346418,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.007850834151128557,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.009813542688910697,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.009813542688910697,
      "eval_loss": NaN,
      "eval_runtime": 113.6953,
      "eval_samples_per_second": 3.782,
      "eval_steps_per_second": 1.891,
      "step": 5
    },
    {
      "epoch": 0.011776251226692836,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.013738959764474975,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.015701668302257114,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.017664376840039256,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.019627085377821395,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.019627085377821395,
      "eval_loss": NaN,
      "eval_runtime": 113.7342,
      "eval_samples_per_second": 3.781,
      "eval_steps_per_second": 1.89,
      "step": 10
    },
    {
      "epoch": 0.021589793915603533,
      "grad_norm": NaN,
      "learning_rate": 0.0001996917333733128,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.023552502453385672,
      "grad_norm": NaN,
      "learning_rate": 0.00019876883405951377,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.02551521099116781,
      "grad_norm": NaN,
      "learning_rate": 0.00019723699203976766,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.02747791952894995,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.029440628066732092,
      "grad_norm": NaN,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.029440628066732092,
      "eval_loss": NaN,
      "eval_runtime": 113.7827,
      "eval_samples_per_second": 3.779,
      "eval_steps_per_second": 1.89,
      "step": 15
    },
    {
      "epoch": 0.03140333660451423,
      "grad_norm": NaN,
      "learning_rate": 0.0001891006524188368,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.033366045142296366,
      "grad_norm": NaN,
      "learning_rate": 0.00018526401643540922,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.03532875368007851,
      "grad_norm": NaN,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.03729146221786065,
      "grad_norm": NaN,
      "learning_rate": 0.0001760405965600031,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.03925417075564279,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.03925417075564279,
      "eval_loss": NaN,
      "eval_runtime": 113.618,
      "eval_samples_per_second": 3.785,
      "eval_steps_per_second": 1.892,
      "step": 20
    },
    {
      "epoch": 0.04121687929342493,
      "grad_norm": NaN,
      "learning_rate": 0.00016494480483301836,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.04317958783120707,
      "grad_norm": NaN,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.045142296368989206,
      "grad_norm": NaN,
      "learning_rate": 0.0001522498564715949,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.047105004906771344,
      "grad_norm": NaN,
      "learning_rate": 0.00014539904997395468,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.04906771344455348,
      "grad_norm": NaN,
      "learning_rate": 0.000138268343236509,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.04906771344455348,
      "eval_loss": NaN,
      "eval_runtime": 113.5259,
      "eval_samples_per_second": 3.788,
      "eval_steps_per_second": 1.894,
      "step": 25
    },
    {
      "epoch": 0.05103042198233562,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.05299313052011776,
      "grad_norm": NaN,
      "learning_rate": 0.00012334453638559057,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0549558390578999,
      "grad_norm": NaN,
      "learning_rate": 0.0001156434465040231,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.05691854759568204,
      "grad_norm": NaN,
      "learning_rate": 0.0001078459095727845,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.058881256133464184,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.058881256133464184,
      "eval_loss": NaN,
      "eval_runtime": 113.6298,
      "eval_samples_per_second": 3.784,
      "eval_steps_per_second": 1.892,
      "step": 30
    },
    {
      "epoch": 0.06084396467124632,
      "grad_norm": NaN,
      "learning_rate": 9.215409042721552e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.06280667320902845,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.0647693817468106,
      "grad_norm": NaN,
      "learning_rate": 7.66554636144095e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.06673209028459273,
      "grad_norm": NaN,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.06869479882237488,
      "grad_norm": NaN,
      "learning_rate": 6.173165676349103e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.06869479882237488,
      "eval_loss": NaN,
      "eval_runtime": 113.8894,
      "eval_samples_per_second": 3.776,
      "eval_steps_per_second": 1.888,
      "step": 35
    },
    {
      "epoch": 0.07065750736015702,
      "grad_norm": NaN,
      "learning_rate": 5.4600950026045326e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.07262021589793916,
      "grad_norm": NaN,
      "learning_rate": 4.7750143528405126e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.0745829244357213,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.07654563297350343,
      "grad_norm": NaN,
      "learning_rate": 3.5055195166981645e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.07850834151128558,
      "grad_norm": NaN,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.07850834151128558,
      "eval_loss": NaN,
      "eval_runtime": 114.0229,
      "eval_samples_per_second": 3.771,
      "eval_steps_per_second": 1.886,
      "step": 40
    },
    {
      "epoch": 0.08047105004906771,
      "grad_norm": NaN,
      "learning_rate": 2.3959403439996907e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.08243375858684986,
      "grad_norm": NaN,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.08439646712463199,
      "grad_norm": NaN,
      "learning_rate": 1.4735983564590783e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.08635917566241413,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.08832188420019627,
      "grad_norm": NaN,
      "learning_rate": 7.612046748871327e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.08832188420019627,
      "eval_loss": NaN,
      "eval_runtime": 113.8643,
      "eval_samples_per_second": 3.776,
      "eval_steps_per_second": 1.888,
      "step": 45
    },
    {
      "epoch": 0.09028459273797841,
      "grad_norm": NaN,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.09224730127576054,
      "grad_norm": NaN,
      "learning_rate": 2.7630079602323442e-06,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.09421000981354269,
      "grad_norm": NaN,
      "learning_rate": 1.231165940486234e-06,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.09617271835132483,
      "grad_norm": NaN,
      "learning_rate": 3.0826662668720364e-07,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.09813542688910697,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.09813542688910697,
      "eval_loss": NaN,
      "eval_runtime": 113.6436,
      "eval_samples_per_second": 3.784,
      "eval_steps_per_second": 1.892,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "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": 8.068420238258995e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}