{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.014343858139243004,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.171929069621502e-05,
      "eval_loss": 3.896871328353882,
      "eval_runtime": 150.5228,
      "eval_samples_per_second": 39.004,
      "eval_steps_per_second": 19.505,
      "step": 1
    },
    {
      "epoch": 0.00035859645348107505,
      "grad_norm": 7.537045955657959,
      "learning_rate": 5e-05,
      "loss": 15.7433,
      "step": 5
    },
    {
      "epoch": 0.0007171929069621501,
      "grad_norm": 3.0281822681427,
      "learning_rate": 0.0001,
      "loss": 14.7594,
      "step": 10
    },
    {
      "epoch": 0.0010757893604432251,
      "grad_norm": 2.9730570316314697,
      "learning_rate": 9.98292246503335e-05,
      "loss": 14.5921,
      "step": 15
    },
    {
      "epoch": 0.0014343858139243002,
      "grad_norm": 4.12907075881958,
      "learning_rate": 9.931806517013612e-05,
      "loss": 14.3322,
      "step": 20
    },
    {
      "epoch": 0.0017929822674053754,
      "grad_norm": 4.960537433624268,
      "learning_rate": 9.847001329696653e-05,
      "loss": 13.7462,
      "step": 25
    },
    {
      "epoch": 0.0021515787208864503,
      "grad_norm": 5.624700546264648,
      "learning_rate": 9.729086208503174e-05,
      "loss": 13.634,
      "step": 30
    },
    {
      "epoch": 0.0025101751743675255,
      "grad_norm": 5.187963008880615,
      "learning_rate": 9.578866633275288e-05,
      "loss": 13.6907,
      "step": 35
    },
    {
      "epoch": 0.0028687716278486004,
      "grad_norm": 5.658892631530762,
      "learning_rate": 9.397368756032445e-05,
      "loss": 13.4865,
      "step": 40
    },
    {
      "epoch": 0.0032273680813296756,
      "grad_norm": 6.080160140991211,
      "learning_rate": 9.185832391312644e-05,
      "loss": 13.8621,
      "step": 45
    },
    {
      "epoch": 0.003585964534810751,
      "grad_norm": 16.94916534423828,
      "learning_rate": 8.945702546981969e-05,
      "loss": 11.9914,
      "step": 50
    },
    {
      "epoch": 0.003585964534810751,
      "eval_loss": 3.3596150875091553,
      "eval_runtime": 150.4881,
      "eval_samples_per_second": 39.013,
      "eval_steps_per_second": 19.51,
      "step": 50
    },
    {
      "epoch": 0.003944560988291826,
      "grad_norm": 4.447661399841309,
      "learning_rate": 8.678619553365659e-05,
      "loss": 13.6562,
      "step": 55
    },
    {
      "epoch": 0.0043031574417729005,
      "grad_norm": 3.9606738090515137,
      "learning_rate": 8.386407858128706e-05,
      "loss": 13.3884,
      "step": 60
    },
    {
      "epoch": 0.004661753895253976,
      "grad_norm": 4.225571155548096,
      "learning_rate": 8.07106356344834e-05,
      "loss": 13.3974,
      "step": 65
    },
    {
      "epoch": 0.005020350348735051,
      "grad_norm": 4.775456428527832,
      "learning_rate": 7.734740790612136e-05,
      "loss": 13.501,
      "step": 70
    },
    {
      "epoch": 0.005378946802216126,
      "grad_norm": 4.323382377624512,
      "learning_rate": 7.379736965185368e-05,
      "loss": 12.5206,
      "step": 75
    },
    {
      "epoch": 0.005737543255697201,
      "grad_norm": 5.417544841766357,
      "learning_rate": 7.008477123264848e-05,
      "loss": 12.731,
      "step": 80
    },
    {
      "epoch": 0.006096139709178276,
      "grad_norm": 6.104112148284912,
      "learning_rate": 6.623497346023418e-05,
      "loss": 13.2522,
      "step": 85
    },
    {
      "epoch": 0.006454736162659351,
      "grad_norm": 6.44561767578125,
      "learning_rate": 6.227427435703997e-05,
      "loss": 13.1932,
      "step": 90
    },
    {
      "epoch": 0.006813332616140426,
      "grad_norm": 8.966840744018555,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 12.8247,
      "step": 95
    },
    {
      "epoch": 0.007171929069621502,
      "grad_norm": 21.272382736206055,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 12.1808,
      "step": 100
    },
    {
      "epoch": 0.007171929069621502,
      "eval_loss": 3.2473652362823486,
      "eval_runtime": 150.4778,
      "eval_samples_per_second": 39.016,
      "eval_steps_per_second": 19.511,
      "step": 100
    },
    {
      "epoch": 0.007530525523102577,
      "grad_norm": 4.7019782066345215,
      "learning_rate": 5e-05,
      "loss": 13.3399,
      "step": 105
    },
    {
      "epoch": 0.007889121976583651,
      "grad_norm": 4.884238243103027,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 13.4529,
      "step": 110
    },
    {
      "epoch": 0.008247718430064726,
      "grad_norm": 5.408816337585449,
      "learning_rate": 4.17702704859633e-05,
      "loss": 12.8787,
      "step": 115
    },
    {
      "epoch": 0.008606314883545801,
      "grad_norm": 5.3005266189575195,
      "learning_rate": 3.772572564296005e-05,
      "loss": 12.6546,
      "step": 120
    },
    {
      "epoch": 0.008964911337026878,
      "grad_norm": 5.632955074310303,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 12.6845,
      "step": 125
    },
    {
      "epoch": 0.009323507790507952,
      "grad_norm": 5.560728549957275,
      "learning_rate": 2.991522876735154e-05,
      "loss": 13.0643,
      "step": 130
    },
    {
      "epoch": 0.009682104243989027,
      "grad_norm": 5.892542839050293,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 12.5008,
      "step": 135
    },
    {
      "epoch": 0.010040700697470102,
      "grad_norm": 6.764001846313477,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 13.3643,
      "step": 140
    },
    {
      "epoch": 0.010399297150951177,
      "grad_norm": 7.127413749694824,
      "learning_rate": 1.928936436551661e-05,
      "loss": 12.4191,
      "step": 145
    },
    {
      "epoch": 0.010757893604432252,
      "grad_norm": 21.99660301208496,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 12.0512,
      "step": 150
    },
    {
      "epoch": 0.010757893604432252,
      "eval_loss": 3.210005283355713,
      "eval_runtime": 150.4651,
      "eval_samples_per_second": 39.019,
      "eval_steps_per_second": 19.513,
      "step": 150
    },
    {
      "epoch": 0.011116490057913327,
      "grad_norm": 4.79033899307251,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 13.248,
      "step": 155
    },
    {
      "epoch": 0.011475086511394401,
      "grad_norm": 5.844348430633545,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 13.2126,
      "step": 160
    },
    {
      "epoch": 0.011833682964875478,
      "grad_norm": 5.08646821975708,
      "learning_rate": 8.141676086873572e-06,
      "loss": 12.5782,
      "step": 165
    },
    {
      "epoch": 0.012192279418356553,
      "grad_norm": 6.094292640686035,
      "learning_rate": 6.026312439675552e-06,
      "loss": 12.7998,
      "step": 170
    },
    {
      "epoch": 0.012550875871837628,
      "grad_norm": 7.0739970207214355,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 12.7072,
      "step": 175
    },
    {
      "epoch": 0.012909472325318702,
      "grad_norm": 6.14113712310791,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 12.8715,
      "step": 180
    },
    {
      "epoch": 0.013268068778799777,
      "grad_norm": 6.727238655090332,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 12.4374,
      "step": 185
    },
    {
      "epoch": 0.013626665232280852,
      "grad_norm": 7.21618127822876,
      "learning_rate": 6.819348298638839e-07,
      "loss": 12.9327,
      "step": 190
    },
    {
      "epoch": 0.013985261685761927,
      "grad_norm": 6.706393718719482,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 13.4929,
      "step": 195
    },
    {
      "epoch": 0.014343858139243004,
      "grad_norm": 22.996488571166992,
      "learning_rate": 0.0,
      "loss": 11.883,
      "step": 200
    },
    {
      "epoch": 0.014343858139243004,
      "eval_loss": 3.2014191150665283,
      "eval_runtime": 150.4957,
      "eval_samples_per_second": 39.011,
      "eval_steps_per_second": 19.509,
      "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": 3010293084979200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}