{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03544057059318655,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017720285296593275,
      "eval_loss": 4.797103404998779,
      "eval_runtime": 202.2883,
      "eval_samples_per_second": 11.751,
      "eval_steps_per_second": 5.878,
      "step": 1
    },
    {
      "epoch": 0.0008860142648296638,
      "grad_norm": 4.123016834259033,
      "learning_rate": 5e-05,
      "loss": 19.8119,
      "step": 5
    },
    {
      "epoch": 0.0017720285296593276,
      "grad_norm": 5.777862548828125,
      "learning_rate": 0.0001,
      "loss": 19.0328,
      "step": 10
    },
    {
      "epoch": 0.0026580427944889913,
      "grad_norm": 7.132779598236084,
      "learning_rate": 9.98292246503335e-05,
      "loss": 17.2132,
      "step": 15
    },
    {
      "epoch": 0.0035440570593186552,
      "grad_norm": 8.808661460876465,
      "learning_rate": 9.931806517013612e-05,
      "loss": 15.4076,
      "step": 20
    },
    {
      "epoch": 0.004430071324148319,
      "grad_norm": 10.981788635253906,
      "learning_rate": 9.847001329696653e-05,
      "loss": 13.8381,
      "step": 25
    },
    {
      "epoch": 0.005316085588977983,
      "grad_norm": 9.182146072387695,
      "learning_rate": 9.729086208503174e-05,
      "loss": 13.1008,
      "step": 30
    },
    {
      "epoch": 0.006202099853807646,
      "grad_norm": 9.88818073272705,
      "learning_rate": 9.578866633275288e-05,
      "loss": 12.0098,
      "step": 35
    },
    {
      "epoch": 0.0070881141186373104,
      "grad_norm": 11.1784086227417,
      "learning_rate": 9.397368756032445e-05,
      "loss": 13.0421,
      "step": 40
    },
    {
      "epoch": 0.007974128383466974,
      "grad_norm": 12.804244995117188,
      "learning_rate": 9.185832391312644e-05,
      "loss": 11.3405,
      "step": 45
    },
    {
      "epoch": 0.008860142648296638,
      "grad_norm": 12.981225967407227,
      "learning_rate": 8.945702546981969e-05,
      "loss": 10.5342,
      "step": 50
    },
    {
      "epoch": 0.008860142648296638,
      "eval_loss": 2.9552793502807617,
      "eval_runtime": 203.6535,
      "eval_samples_per_second": 11.672,
      "eval_steps_per_second": 5.838,
      "step": 50
    },
    {
      "epoch": 0.009746156913126301,
      "grad_norm": 10.348260879516602,
      "learning_rate": 8.678619553365659e-05,
      "loss": 12.8096,
      "step": 55
    },
    {
      "epoch": 0.010632171177955965,
      "grad_norm": 10.762813568115234,
      "learning_rate": 8.386407858128706e-05,
      "loss": 11.6477,
      "step": 60
    },
    {
      "epoch": 0.01151818544278563,
      "grad_norm": 10.93557357788086,
      "learning_rate": 8.07106356344834e-05,
      "loss": 11.2053,
      "step": 65
    },
    {
      "epoch": 0.012404199707615292,
      "grad_norm": 10.613462448120117,
      "learning_rate": 7.734740790612136e-05,
      "loss": 10.8535,
      "step": 70
    },
    {
      "epoch": 0.013290213972444957,
      "grad_norm": 9.136550903320312,
      "learning_rate": 7.379736965185368e-05,
      "loss": 11.4889,
      "step": 75
    },
    {
      "epoch": 0.014176228237274621,
      "grad_norm": 12.011136054992676,
      "learning_rate": 7.008477123264848e-05,
      "loss": 11.381,
      "step": 80
    },
    {
      "epoch": 0.015062242502104283,
      "grad_norm": 12.142571449279785,
      "learning_rate": 6.623497346023418e-05,
      "loss": 11.4218,
      "step": 85
    },
    {
      "epoch": 0.015948256766933948,
      "grad_norm": 11.393709182739258,
      "learning_rate": 6.227427435703997e-05,
      "loss": 10.5837,
      "step": 90
    },
    {
      "epoch": 0.01683427103176361,
      "grad_norm": 12.14599609375,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 10.3925,
      "step": 95
    },
    {
      "epoch": 0.017720285296593277,
      "grad_norm": 15.305344581604004,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 9.9706,
      "step": 100
    },
    {
      "epoch": 0.017720285296593277,
      "eval_loss": 2.7050416469573975,
      "eval_runtime": 203.9687,
      "eval_samples_per_second": 11.654,
      "eval_steps_per_second": 5.829,
      "step": 100
    },
    {
      "epoch": 0.01860629956142294,
      "grad_norm": 11.99126148223877,
      "learning_rate": 5e-05,
      "loss": 10.8777,
      "step": 105
    },
    {
      "epoch": 0.019492313826252602,
      "grad_norm": 11.454866409301758,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 10.4074,
      "step": 110
    },
    {
      "epoch": 0.020378328091082268,
      "grad_norm": 13.158794403076172,
      "learning_rate": 4.17702704859633e-05,
      "loss": 11.0133,
      "step": 115
    },
    {
      "epoch": 0.02126434235591193,
      "grad_norm": 12.096662521362305,
      "learning_rate": 3.772572564296005e-05,
      "loss": 10.6467,
      "step": 120
    },
    {
      "epoch": 0.022150356620741593,
      "grad_norm": 10.214104652404785,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 10.8093,
      "step": 125
    },
    {
      "epoch": 0.02303637088557126,
      "grad_norm": 11.612906455993652,
      "learning_rate": 2.991522876735154e-05,
      "loss": 10.643,
      "step": 130
    },
    {
      "epoch": 0.023922385150400922,
      "grad_norm": 12.742725372314453,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 10.2774,
      "step": 135
    },
    {
      "epoch": 0.024808399415230584,
      "grad_norm": 12.095250129699707,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 9.669,
      "step": 140
    },
    {
      "epoch": 0.02569441368006025,
      "grad_norm": 14.42609691619873,
      "learning_rate": 1.928936436551661e-05,
      "loss": 10.3575,
      "step": 145
    },
    {
      "epoch": 0.026580427944889913,
      "grad_norm": 18.136564254760742,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 10.1422,
      "step": 150
    },
    {
      "epoch": 0.026580427944889913,
      "eval_loss": 2.63204288482666,
      "eval_runtime": 203.804,
      "eval_samples_per_second": 11.663,
      "eval_steps_per_second": 5.834,
      "step": 150
    },
    {
      "epoch": 0.027466442209719576,
      "grad_norm": 10.153324127197266,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 11.3695,
      "step": 155
    },
    {
      "epoch": 0.028352456474549242,
      "grad_norm": 11.483891487121582,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 10.4618,
      "step": 160
    },
    {
      "epoch": 0.029238470739378904,
      "grad_norm": 10.634285926818848,
      "learning_rate": 8.141676086873572e-06,
      "loss": 10.6649,
      "step": 165
    },
    {
      "epoch": 0.030124485004208567,
      "grad_norm": 11.71572494506836,
      "learning_rate": 6.026312439675552e-06,
      "loss": 11.1251,
      "step": 170
    },
    {
      "epoch": 0.031010499269038233,
      "grad_norm": 12.61253547668457,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 10.1915,
      "step": 175
    },
    {
      "epoch": 0.031896513533867896,
      "grad_norm": 13.30790901184082,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 10.6393,
      "step": 180
    },
    {
      "epoch": 0.03278252779869756,
      "grad_norm": 12.893260955810547,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 10.5345,
      "step": 185
    },
    {
      "epoch": 0.03366854206352722,
      "grad_norm": 11.798104286193848,
      "learning_rate": 6.819348298638839e-07,
      "loss": 9.7845,
      "step": 190
    },
    {
      "epoch": 0.034554556328356884,
      "grad_norm": 13.706073760986328,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 10.8492,
      "step": 195
    },
    {
      "epoch": 0.03544057059318655,
      "grad_norm": 15.757190704345703,
      "learning_rate": 0.0,
      "loss": 9.9755,
      "step": 200
    },
    {
      "epoch": 0.03544057059318655,
      "eval_loss": 2.6143457889556885,
      "eval_runtime": 203.7021,
      "eval_samples_per_second": 11.669,
      "eval_steps_per_second": 5.837,
      "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": 5.898398699405722e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}