{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13065490772497143,
  "eval_steps": 17,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006532745386248571,
      "eval_loss": 2.095608949661255,
      "eval_runtime": 57.0442,
      "eval_samples_per_second": 45.193,
      "eval_steps_per_second": 5.662,
      "step": 1
    },
    {
      "epoch": 0.0032663726931242854,
      "grad_norm": 0.21221201121807098,
      "learning_rate": 5e-05,
      "loss": 1.6508,
      "step": 5
    },
    {
      "epoch": 0.006532745386248571,
      "grad_norm": 0.22674362361431122,
      "learning_rate": 0.0001,
      "loss": 1.7102,
      "step": 10
    },
    {
      "epoch": 0.009799118079372856,
      "grad_norm": 0.269519180059433,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.7246,
      "step": 15
    },
    {
      "epoch": 0.01110566715662257,
      "eval_loss": 2.028172254562378,
      "eval_runtime": 57.359,
      "eval_samples_per_second": 44.945,
      "eval_steps_per_second": 5.631,
      "step": 17
    },
    {
      "epoch": 0.013065490772497142,
      "grad_norm": 0.31122979521751404,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.7273,
      "step": 20
    },
    {
      "epoch": 0.01633186346562143,
      "grad_norm": 0.41586434841156006,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.7933,
      "step": 25
    },
    {
      "epoch": 0.019598236158745713,
      "grad_norm": 0.5983772277832031,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.7516,
      "step": 30
    },
    {
      "epoch": 0.02221133431324514,
      "eval_loss": 1.929399013519287,
      "eval_runtime": 57.6067,
      "eval_samples_per_second": 44.752,
      "eval_steps_per_second": 5.607,
      "step": 34
    },
    {
      "epoch": 0.02286460885187,
      "grad_norm": 0.943932831287384,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.9982,
      "step": 35
    },
    {
      "epoch": 0.026130981544994283,
      "grad_norm": 1.333251953125,
      "learning_rate": 9.397368756032445e-05,
      "loss": 2.1041,
      "step": 40
    },
    {
      "epoch": 0.02939735423811857,
      "grad_norm": 1.7958847284317017,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.15,
      "step": 45
    },
    {
      "epoch": 0.03266372693124286,
      "grad_norm": 4.410415172576904,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.5185,
      "step": 50
    },
    {
      "epoch": 0.03331700146986771,
      "eval_loss": 1.9736422300338745,
      "eval_runtime": 57.487,
      "eval_samples_per_second": 44.845,
      "eval_steps_per_second": 5.619,
      "step": 51
    },
    {
      "epoch": 0.03593009962436714,
      "grad_norm": 0.5272660255432129,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.6951,
      "step": 55
    },
    {
      "epoch": 0.039196472317491425,
      "grad_norm": 0.2936265170574188,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.6946,
      "step": 60
    },
    {
      "epoch": 0.04246284501061571,
      "grad_norm": 0.2740556299686432,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.6546,
      "step": 65
    },
    {
      "epoch": 0.04442266862649028,
      "eval_loss": 1.8947619199752808,
      "eval_runtime": 57.6624,
      "eval_samples_per_second": 44.709,
      "eval_steps_per_second": 5.602,
      "step": 68
    },
    {
      "epoch": 0.04572921770374,
      "grad_norm": 0.3228052258491516,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.6589,
      "step": 70
    },
    {
      "epoch": 0.04899559039686428,
      "grad_norm": 0.42957571148872375,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.7451,
      "step": 75
    },
    {
      "epoch": 0.05226196308998857,
      "grad_norm": 0.5609195232391357,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.7741,
      "step": 80
    },
    {
      "epoch": 0.05552833578311285,
      "grad_norm": 0.8654677271842957,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.8785,
      "step": 85
    },
    {
      "epoch": 0.05552833578311285,
      "eval_loss": 1.8576701879501343,
      "eval_runtime": 57.2998,
      "eval_samples_per_second": 44.991,
      "eval_steps_per_second": 5.637,
      "step": 85
    },
    {
      "epoch": 0.05879470847623714,
      "grad_norm": 1.3158453702926636,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.0237,
      "step": 90
    },
    {
      "epoch": 0.062061081169361425,
      "grad_norm": 1.6945480108261108,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 2.0945,
      "step": 95
    },
    {
      "epoch": 0.06532745386248572,
      "grad_norm": 3.3736517429351807,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 2.3271,
      "step": 100
    },
    {
      "epoch": 0.06663400293973543,
      "eval_loss": 1.8315001726150513,
      "eval_runtime": 57.6522,
      "eval_samples_per_second": 44.716,
      "eval_steps_per_second": 5.603,
      "step": 102
    },
    {
      "epoch": 0.06859382655561,
      "grad_norm": 0.35630449652671814,
      "learning_rate": 5e-05,
      "loss": 1.5742,
      "step": 105
    },
    {
      "epoch": 0.07186019924873428,
      "grad_norm": 0.3723335266113281,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.6171,
      "step": 110
    },
    {
      "epoch": 0.07512657194185857,
      "grad_norm": 0.39353442192077637,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.6489,
      "step": 115
    },
    {
      "epoch": 0.07773967009635799,
      "eval_loss": 1.8114745616912842,
      "eval_runtime": 57.6514,
      "eval_samples_per_second": 44.717,
      "eval_steps_per_second": 5.603,
      "step": 119
    },
    {
      "epoch": 0.07839294463498285,
      "grad_norm": 0.37837105989456177,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.6021,
      "step": 120
    },
    {
      "epoch": 0.08165931732810713,
      "grad_norm": 0.4824821949005127,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.7757,
      "step": 125
    },
    {
      "epoch": 0.08492569002123142,
      "grad_norm": 0.612577497959137,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.7622,
      "step": 130
    },
    {
      "epoch": 0.0881920627143557,
      "grad_norm": 0.9872429370880127,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.9061,
      "step": 135
    },
    {
      "epoch": 0.08884533725298056,
      "eval_loss": 1.812151551246643,
      "eval_runtime": 57.6472,
      "eval_samples_per_second": 44.72,
      "eval_steps_per_second": 5.603,
      "step": 136
    },
    {
      "epoch": 0.09145843540748,
      "grad_norm": 1.347030758857727,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.9406,
      "step": 140
    },
    {
      "epoch": 0.09472480810060428,
      "grad_norm": 2.084744453430176,
      "learning_rate": 1.928936436551661e-05,
      "loss": 2.0861,
      "step": 145
    },
    {
      "epoch": 0.09799118079372857,
      "grad_norm": 3.422002077102661,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 2.375,
      "step": 150
    },
    {
      "epoch": 0.09995100440960314,
      "eval_loss": 1.7937358617782593,
      "eval_runtime": 57.499,
      "eval_samples_per_second": 44.836,
      "eval_steps_per_second": 5.617,
      "step": 153
    },
    {
      "epoch": 0.10125755348685285,
      "grad_norm": 0.30897772312164307,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.5451,
      "step": 155
    },
    {
      "epoch": 0.10452392617997713,
      "grad_norm": 0.3643786609172821,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.6042,
      "step": 160
    },
    {
      "epoch": 0.10779029887310142,
      "grad_norm": 0.42373302578926086,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.6688,
      "step": 165
    },
    {
      "epoch": 0.1110566715662257,
      "grad_norm": 0.5218139886856079,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.7141,
      "step": 170
    },
    {
      "epoch": 0.1110566715662257,
      "eval_loss": 1.794013500213623,
      "eval_runtime": 57.8137,
      "eval_samples_per_second": 44.592,
      "eval_steps_per_second": 5.587,
      "step": 170
    },
    {
      "epoch": 0.11432304425935,
      "grad_norm": 0.6702213883399963,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.7233,
      "step": 175
    },
    {
      "epoch": 0.11758941695247428,
      "grad_norm": 0.9712100028991699,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.7565,
      "step": 180
    },
    {
      "epoch": 0.12085578964559857,
      "grad_norm": 1.1032600402832031,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.8817,
      "step": 185
    },
    {
      "epoch": 0.12216233872284828,
      "eval_loss": 1.784209966659546,
      "eval_runtime": 57.6323,
      "eval_samples_per_second": 44.732,
      "eval_steps_per_second": 5.605,
      "step": 187
    },
    {
      "epoch": 0.12412216233872285,
      "grad_norm": 1.3396888971328735,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.8765,
      "step": 190
    },
    {
      "epoch": 0.12738853503184713,
      "grad_norm": 1.7500126361846924,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.9182,
      "step": 195
    },
    {
      "epoch": 0.13065490772497143,
      "grad_norm": 3.3364036083221436,
      "learning_rate": 0.0,
      "loss": 2.1906,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.12349324705792e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}