{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06897740989825832,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003448870494912916,
      "eval_loss": 1.6494632959365845,
      "eval_runtime": 34.9623,
      "eval_samples_per_second": 34.923,
      "eval_steps_per_second": 17.476,
      "step": 1
    },
    {
      "epoch": 0.001724435247456458,
      "grad_norm": 0.19907526671886444,
      "learning_rate": 5e-05,
      "loss": 0.4441,
      "step": 5
    },
    {
      "epoch": 0.003448870494912916,
      "grad_norm": 0.31890785694122314,
      "learning_rate": 0.0001,
      "loss": 0.5543,
      "step": 10
    },
    {
      "epoch": 0.005173305742369374,
      "grad_norm": 0.5191323757171631,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.8524,
      "step": 15
    },
    {
      "epoch": 0.006897740989825832,
      "grad_norm": 0.8150956630706787,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.8316,
      "step": 20
    },
    {
      "epoch": 0.00862217623728229,
      "grad_norm": 0.657228410243988,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.9428,
      "step": 25
    },
    {
      "epoch": 0.010346611484738748,
      "grad_norm": 0.7401005029678345,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.893,
      "step": 30
    },
    {
      "epoch": 0.012071046732195206,
      "grad_norm": 0.9956038594245911,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.8458,
      "step": 35
    },
    {
      "epoch": 0.013795481979651664,
      "grad_norm": 1.206120252609253,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.8457,
      "step": 40
    },
    {
      "epoch": 0.015519917227108122,
      "grad_norm": 1.13577139377594,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.9052,
      "step": 45
    },
    {
      "epoch": 0.01724435247456458,
      "grad_norm": 1.588378667831421,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.938,
      "step": 50
    },
    {
      "epoch": 0.01724435247456458,
      "eval_loss": 0.4283510148525238,
      "eval_runtime": 34.9319,
      "eval_samples_per_second": 34.954,
      "eval_steps_per_second": 17.491,
      "step": 50
    },
    {
      "epoch": 0.018968787722021038,
      "grad_norm": 0.2711787819862366,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.1996,
      "step": 55
    },
    {
      "epoch": 0.020693222969477496,
      "grad_norm": 0.32828548550605774,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.1949,
      "step": 60
    },
    {
      "epoch": 0.022417658216933953,
      "grad_norm": 0.33665451407432556,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.2292,
      "step": 65
    },
    {
      "epoch": 0.02414209346439041,
      "grad_norm": 0.4061940908432007,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.1893,
      "step": 70
    },
    {
      "epoch": 0.02586652871184687,
      "grad_norm": 0.33809414505958557,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.1598,
      "step": 75
    },
    {
      "epoch": 0.027590963959303327,
      "grad_norm": 0.4947359263896942,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.1491,
      "step": 80
    },
    {
      "epoch": 0.029315399206759785,
      "grad_norm": 0.6811371445655823,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.1912,
      "step": 85
    },
    {
      "epoch": 0.031039834454216243,
      "grad_norm": 0.7676391005516052,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.1897,
      "step": 90
    },
    {
      "epoch": 0.032764269701672705,
      "grad_norm": 0.6365978717803955,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.2189,
      "step": 95
    },
    {
      "epoch": 0.03448870494912916,
      "grad_norm": 1.828718662261963,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.1891,
      "step": 100
    },
    {
      "epoch": 0.03448870494912916,
      "eval_loss": 0.1450214385986328,
      "eval_runtime": 34.9196,
      "eval_samples_per_second": 34.966,
      "eval_steps_per_second": 17.497,
      "step": 100
    },
    {
      "epoch": 0.03621314019658562,
      "grad_norm": 0.3101787567138672,
      "learning_rate": 5e-05,
      "loss": 0.1246,
      "step": 105
    },
    {
      "epoch": 0.037937575444042075,
      "grad_norm": 0.3164457678794861,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.1236,
      "step": 110
    },
    {
      "epoch": 0.039662010691498537,
      "grad_norm": 0.15494108200073242,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.1161,
      "step": 115
    },
    {
      "epoch": 0.04138644593895499,
      "grad_norm": 0.443514347076416,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.1247,
      "step": 120
    },
    {
      "epoch": 0.04311088118641145,
      "grad_norm": 0.4595088064670563,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.1405,
      "step": 125
    },
    {
      "epoch": 0.04483531643386791,
      "grad_norm": 0.41964155435562134,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.0973,
      "step": 130
    },
    {
      "epoch": 0.04655975168132437,
      "grad_norm": 0.5859366059303284,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.1341,
      "step": 135
    },
    {
      "epoch": 0.04828418692878082,
      "grad_norm": 0.5248180627822876,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.1571,
      "step": 140
    },
    {
      "epoch": 0.050008622176237284,
      "grad_norm": 0.5005312561988831,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.0833,
      "step": 145
    },
    {
      "epoch": 0.05173305742369374,
      "grad_norm": 0.4643927812576294,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0745,
      "step": 150
    },
    {
      "epoch": 0.05173305742369374,
      "eval_loss": 0.12103913724422455,
      "eval_runtime": 34.8214,
      "eval_samples_per_second": 35.065,
      "eval_steps_per_second": 17.547,
      "step": 150
    },
    {
      "epoch": 0.0534574926711502,
      "grad_norm": 0.12251858413219452,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.1379,
      "step": 155
    },
    {
      "epoch": 0.055181927918606655,
      "grad_norm": 0.1927584558725357,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.0771,
      "step": 160
    },
    {
      "epoch": 0.056906363166063116,
      "grad_norm": 0.14378532767295837,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.0829,
      "step": 165
    },
    {
      "epoch": 0.05863079841351957,
      "grad_norm": 0.15649206936359406,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.1004,
      "step": 170
    },
    {
      "epoch": 0.06035523366097603,
      "grad_norm": 0.30328625440597534,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.1024,
      "step": 175
    },
    {
      "epoch": 0.062079668908432487,
      "grad_norm": 0.7782003283500671,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.1006,
      "step": 180
    },
    {
      "epoch": 0.06380410415588894,
      "grad_norm": 0.27843937277793884,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.1131,
      "step": 185
    },
    {
      "epoch": 0.06552853940334541,
      "grad_norm": 0.4829224944114685,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.1107,
      "step": 190
    },
    {
      "epoch": 0.06725297465080186,
      "grad_norm": 0.6723254323005676,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.0773,
      "step": 195
    },
    {
      "epoch": 0.06897740989825832,
      "grad_norm": 1.1532963514328003,
      "learning_rate": 0.0,
      "loss": 0.1007,
      "step": 200
    },
    {
      "epoch": 0.06897740989825832,
      "eval_loss": 0.10738521069288254,
      "eval_runtime": 35.0011,
      "eval_samples_per_second": 34.885,
      "eval_steps_per_second": 17.457,
      "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": 3312052607385600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}