{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.7278617710583153,
  "eval_steps": 17,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008639308855291577,
      "eval_loss": 0.0871872752904892,
      "eval_runtime": 27.2621,
      "eval_samples_per_second": 7.153,
      "eval_steps_per_second": 0.917,
      "step": 1
    },
    {
      "epoch": 0.02591792656587473,
      "grad_norm": 0.4171031415462494,
      "learning_rate": 3e-05,
      "loss": 0.097,
      "step": 3
    },
    {
      "epoch": 0.05183585313174946,
      "grad_norm": 0.2446499764919281,
      "learning_rate": 6e-05,
      "loss": 0.0725,
      "step": 6
    },
    {
      "epoch": 0.07775377969762419,
      "grad_norm": 0.18422715365886688,
      "learning_rate": 9e-05,
      "loss": 0.0455,
      "step": 9
    },
    {
      "epoch": 0.10367170626349892,
      "grad_norm": 0.1500893086194992,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.0206,
      "step": 12
    },
    {
      "epoch": 0.12958963282937366,
      "grad_norm": 0.09739550203084946,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.0159,
      "step": 15
    },
    {
      "epoch": 0.1468682505399568,
      "eval_loss": 0.009772061370313168,
      "eval_runtime": 27.6846,
      "eval_samples_per_second": 7.044,
      "eval_steps_per_second": 0.903,
      "step": 17
    },
    {
      "epoch": 0.15550755939524838,
      "grad_norm": 0.06743879616260529,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.0099,
      "step": 18
    },
    {
      "epoch": 0.18142548596112312,
      "grad_norm": 0.06798849254846573,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.0086,
      "step": 21
    },
    {
      "epoch": 0.20734341252699784,
      "grad_norm": 0.05319894850254059,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.0072,
      "step": 24
    },
    {
      "epoch": 0.23326133909287258,
      "grad_norm": 0.06538129597902298,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.0055,
      "step": 27
    },
    {
      "epoch": 0.2591792656587473,
      "grad_norm": 0.060455236583948135,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.0051,
      "step": 30
    },
    {
      "epoch": 0.28509719222462204,
      "grad_norm": 0.06194108724594116,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.0042,
      "step": 33
    },
    {
      "epoch": 0.2937365010799136,
      "eval_loss": 0.0031290610786527395,
      "eval_runtime": 27.6858,
      "eval_samples_per_second": 7.043,
      "eval_steps_per_second": 0.903,
      "step": 34
    },
    {
      "epoch": 0.31101511879049676,
      "grad_norm": 0.04522060602903366,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.0033,
      "step": 36
    },
    {
      "epoch": 0.3369330453563715,
      "grad_norm": 0.021508673205971718,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.0018,
      "step": 39
    },
    {
      "epoch": 0.36285097192224625,
      "grad_norm": 0.047018762677907944,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.0024,
      "step": 42
    },
    {
      "epoch": 0.38876889848812096,
      "grad_norm": 0.023386940360069275,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.0015,
      "step": 45
    },
    {
      "epoch": 0.4146868250539957,
      "grad_norm": 0.03639828786253929,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0016,
      "step": 48
    },
    {
      "epoch": 0.4406047516198704,
      "grad_norm": 0.05475722253322601,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.0008,
      "step": 51
    },
    {
      "epoch": 0.4406047516198704,
      "eval_loss": 0.000927323882933706,
      "eval_runtime": 27.706,
      "eval_samples_per_second": 7.038,
      "eval_steps_per_second": 0.902,
      "step": 51
    },
    {
      "epoch": 0.46652267818574517,
      "grad_norm": 0.016481637954711914,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.0012,
      "step": 54
    },
    {
      "epoch": 0.4924406047516199,
      "grad_norm": 0.024859052151441574,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.0017,
      "step": 57
    },
    {
      "epoch": 0.5183585313174947,
      "grad_norm": 0.059106212109327316,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.0011,
      "step": 60
    },
    {
      "epoch": 0.5442764578833693,
      "grad_norm": 0.02869432047009468,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.0014,
      "step": 63
    },
    {
      "epoch": 0.5701943844492441,
      "grad_norm": 0.009494743309915066,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.001,
      "step": 66
    },
    {
      "epoch": 0.5874730021598272,
      "eval_loss": 0.0004647255700547248,
      "eval_runtime": 27.6692,
      "eval_samples_per_second": 7.048,
      "eval_steps_per_second": 0.904,
      "step": 68
    },
    {
      "epoch": 0.5961123110151187,
      "grad_norm": 0.02036004327237606,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.0008,
      "step": 69
    },
    {
      "epoch": 0.6220302375809935,
      "grad_norm": 0.009525030851364136,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.0007,
      "step": 72
    },
    {
      "epoch": 0.6479481641468683,
      "grad_norm": 0.010703514330089092,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.0008,
      "step": 75
    },
    {
      "epoch": 0.673866090712743,
      "grad_norm": 0.025075966492295265,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.0004,
      "step": 78
    },
    {
      "epoch": 0.6997840172786177,
      "grad_norm": 0.007703394629061222,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.0004,
      "step": 81
    },
    {
      "epoch": 0.7257019438444925,
      "grad_norm": 0.04455381631851196,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.0008,
      "step": 84
    },
    {
      "epoch": 0.734341252699784,
      "eval_loss": 0.00040637567872181535,
      "eval_runtime": 27.7097,
      "eval_samples_per_second": 7.037,
      "eval_steps_per_second": 0.902,
      "step": 85
    },
    {
      "epoch": 0.7516198704103672,
      "grad_norm": 0.03314139321446419,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.0014,
      "step": 87
    },
    {
      "epoch": 0.7775377969762419,
      "grad_norm": 0.0045311711728572845,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.0003,
      "step": 90
    },
    {
      "epoch": 0.8034557235421166,
      "grad_norm": 0.004199441522359848,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.0003,
      "step": 93
    },
    {
      "epoch": 0.8293736501079914,
      "grad_norm": 0.006650756578892469,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.0005,
      "step": 96
    },
    {
      "epoch": 0.8552915766738661,
      "grad_norm": 0.01657930016517639,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.0005,
      "step": 99
    },
    {
      "epoch": 0.8812095032397408,
      "grad_norm": 0.017045479267835617,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.0003,
      "step": 102
    },
    {
      "epoch": 0.8812095032397408,
      "eval_loss": 0.00029769778484478593,
      "eval_runtime": 27.6925,
      "eval_samples_per_second": 7.042,
      "eval_steps_per_second": 0.903,
      "step": 102
    },
    {
      "epoch": 0.9071274298056156,
      "grad_norm": 0.0062201423570513725,
      "learning_rate": 5e-05,
      "loss": 0.0004,
      "step": 105
    },
    {
      "epoch": 0.9330453563714903,
      "grad_norm": 0.002783352741971612,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.0003,
      "step": 108
    },
    {
      "epoch": 0.958963282937365,
      "grad_norm": 0.015172963961958885,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.0004,
      "step": 111
    },
    {
      "epoch": 0.9848812095032398,
      "grad_norm": 0.012813996523618698,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.0003,
      "step": 114
    },
    {
      "epoch": 1.0107991360691144,
      "grad_norm": 0.0013970539439469576,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.0004,
      "step": 117
    },
    {
      "epoch": 1.0280777537796977,
      "eval_loss": 0.00030021622660569847,
      "eval_runtime": 27.7142,
      "eval_samples_per_second": 7.036,
      "eval_steps_per_second": 0.902,
      "step": 119
    },
    {
      "epoch": 1.0367170626349893,
      "grad_norm": 0.0011866734130308032,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.0003,
      "step": 120
    },
    {
      "epoch": 1.062634989200864,
      "grad_norm": 0.02045155130326748,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.0003,
      "step": 123
    },
    {
      "epoch": 1.0885529157667386,
      "grad_norm": 0.0018892658408731222,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.0003,
      "step": 126
    },
    {
      "epoch": 1.1144708423326133,
      "grad_norm": 0.0013002033811062574,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.0002,
      "step": 129
    },
    {
      "epoch": 1.1403887688984882,
      "grad_norm": 0.0019219208043068647,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.0005,
      "step": 132
    },
    {
      "epoch": 1.1663066954643628,
      "grad_norm": 0.010504819452762604,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.0003,
      "step": 135
    },
    {
      "epoch": 1.1749460043196545,
      "eval_loss": 0.00026334126596339047,
      "eval_runtime": 27.7071,
      "eval_samples_per_second": 7.038,
      "eval_steps_per_second": 0.902,
      "step": 136
    },
    {
      "epoch": 1.1922246220302375,
      "grad_norm": 0.003067749785259366,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.0002,
      "step": 138
    },
    {
      "epoch": 1.2181425485961124,
      "grad_norm": 0.003538350109010935,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.0003,
      "step": 141
    },
    {
      "epoch": 1.244060475161987,
      "grad_norm": 0.0014513281639665365,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.0002,
      "step": 144
    },
    {
      "epoch": 1.2699784017278617,
      "grad_norm": 0.003303627949208021,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.0002,
      "step": 147
    },
    {
      "epoch": 1.2958963282937366,
      "grad_norm": 0.001433212892152369,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0002,
      "step": 150
    },
    {
      "epoch": 1.3218142548596112,
      "grad_norm": 0.001963813090696931,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.0003,
      "step": 153
    },
    {
      "epoch": 1.3218142548596112,
      "eval_loss": 0.00025074489531107247,
      "eval_runtime": 27.728,
      "eval_samples_per_second": 7.033,
      "eval_steps_per_second": 0.902,
      "step": 153
    },
    {
      "epoch": 1.347732181425486,
      "grad_norm": 0.0024869884364306927,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.0002,
      "step": 156
    },
    {
      "epoch": 1.3736501079913608,
      "grad_norm": 0.0010916889877989888,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.0002,
      "step": 159
    },
    {
      "epoch": 1.3995680345572354,
      "grad_norm": 0.0038498463109135628,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0004,
      "step": 162
    },
    {
      "epoch": 1.42548596112311,
      "grad_norm": 0.001822186284698546,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.0004,
      "step": 165
    },
    {
      "epoch": 1.451403887688985,
      "grad_norm": 0.0019195277709513903,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.0002,
      "step": 168
    },
    {
      "epoch": 1.468682505399568,
      "eval_loss": 0.00026034220354631543,
      "eval_runtime": 27.6782,
      "eval_samples_per_second": 7.045,
      "eval_steps_per_second": 0.903,
      "step": 170
    },
    {
      "epoch": 1.4773218142548596,
      "grad_norm": 0.003331635845825076,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.0002,
      "step": 171
    },
    {
      "epoch": 1.5032397408207343,
      "grad_norm": 0.004186209756880999,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.0001,
      "step": 174
    },
    {
      "epoch": 1.5291576673866092,
      "grad_norm": 0.0025692307390272617,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.0002,
      "step": 177
    },
    {
      "epoch": 1.5550755939524838,
      "grad_norm": 0.020796336233615875,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.0005,
      "step": 180
    },
    {
      "epoch": 1.5809935205183585,
      "grad_norm": 0.002934974618256092,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.0002,
      "step": 183
    },
    {
      "epoch": 1.6069114470842334,
      "grad_norm": 0.0028173394966870546,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.0003,
      "step": 186
    },
    {
      "epoch": 1.6155507559395248,
      "eval_loss": 0.0002737921313382685,
      "eval_runtime": 27.6746,
      "eval_samples_per_second": 7.046,
      "eval_steps_per_second": 0.903,
      "step": 187
    },
    {
      "epoch": 1.6328293736501078,
      "grad_norm": 0.013227006420493126,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.0002,
      "step": 189
    },
    {
      "epoch": 1.6587473002159827,
      "grad_norm": 0.000987304258160293,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.0003,
      "step": 192
    },
    {
      "epoch": 1.6846652267818576,
      "grad_norm": 0.0019625353161245584,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.0002,
      "step": 195
    },
    {
      "epoch": 1.710583153347732,
      "grad_norm": 0.003295398550108075,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.0002,
      "step": 198
    }
  ],
  "logging_steps": 3,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 17,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.837725562516275e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}