{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.26035359651247275,
  "eval_steps": 55,
  "global_step": 215,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001210946960523129,
      "eval_loss": NaN,
      "eval_runtime": 73.7855,
      "eval_samples_per_second": 5.895,
      "eval_steps_per_second": 2.955,
      "step": 1
    },
    {
      "epoch": 0.0036328408815693874,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.007265681763138775,
      "grad_norm": NaN,
      "learning_rate": 9.999440509051368e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.010898522644708163,
      "grad_norm": NaN,
      "learning_rate": 9.991050648838675e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.01453136352627755,
      "grad_norm": NaN,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.018164204407846937,
      "grad_norm": NaN,
      "learning_rate": 9.944154131125642e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.021797045289416325,
      "grad_norm": NaN,
      "learning_rate": 9.905741916970864e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.02542988617098571,
      "grad_norm": NaN,
      "learning_rate": 9.857450191464337e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0290627270525551,
      "grad_norm": NaN,
      "learning_rate": 9.799376207714445e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.03269556793412449,
      "grad_norm": NaN,
      "learning_rate": 9.731636918995821e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.03632840881569387,
      "grad_norm": NaN,
      "learning_rate": 9.654368743221022e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.03996124969726326,
      "grad_norm": NaN,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.04359409057883265,
      "grad_norm": NaN,
      "learning_rate": 9.471887038331685e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.047226931460402036,
      "grad_norm": NaN,
      "learning_rate": 9.367041003085649e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.05085977234197142,
      "grad_norm": NaN,
      "learning_rate": 9.253400328436699e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.054492613223540806,
      "grad_norm": NaN,
      "learning_rate": 9.131193871579975e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.0581254541051102,
      "grad_norm": NaN,
      "learning_rate": 9.000667740056032e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.061758294986679584,
      "grad_norm": NaN,
      "learning_rate": 8.862084796122998e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.06539113586824898,
      "grad_norm": NaN,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.0666020828287721,
      "eval_loss": NaN,
      "eval_runtime": 72.7094,
      "eval_samples_per_second": 5.983,
      "eval_steps_per_second": 2.998,
      "step": 55
    },
    {
      "epoch": 0.06902397674981836,
      "grad_norm": NaN,
      "learning_rate": 8.561880484756725e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.07265681763138775,
      "grad_norm": NaN,
      "learning_rate": 8.400863688854597e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.07628965851295713,
      "grad_norm": NaN,
      "learning_rate": 8.232998006078997e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.07992249939452652,
      "grad_norm": NaN,
      "learning_rate": 8.058621495575032e-05,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.0835553402760959,
      "grad_norm": NaN,
      "learning_rate": 7.878085328428369e-05,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.0871881811576653,
      "grad_norm": NaN,
      "learning_rate": 7.691753080453412e-05,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.09082102203923469,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.09445386292080407,
      "grad_norm": NaN,
      "learning_rate": 7.303212252253162e-05,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.09808670380237346,
      "grad_norm": NaN,
      "learning_rate": 7.101786141547828e-05,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.10171954468394284,
      "grad_norm": NaN,
      "learning_rate": 6.896127313264643e-05,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.10535238556551223,
      "grad_norm": NaN,
      "learning_rate": 6.686649936914152e-05,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.10898522644708161,
      "grad_norm": NaN,
      "learning_rate": 6.473775872054521e-05,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.11261806732865101,
      "grad_norm": NaN,
      "learning_rate": 6.257933818722543e-05,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 0.1162509082102204,
      "grad_norm": NaN,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.11988374909178978,
      "grad_norm": NaN,
      "learning_rate": 5.819089557075689e-05,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.12351658997335917,
      "grad_norm": NaN,
      "learning_rate": 5.596971122701221e-05,
      "loss": 0.0,
      "step": 102
    },
    {
      "epoch": 0.12714943085492855,
      "grad_norm": NaN,
      "learning_rate": 5.373650467932122e-05,
      "loss": 0.0,
      "step": 105
    },
    {
      "epoch": 0.13078227173649795,
      "grad_norm": NaN,
      "learning_rate": 5.149577330846993e-05,
      "loss": 0.0,
      "step": 108
    },
    {
      "epoch": 0.1332041656575442,
      "eval_loss": NaN,
      "eval_runtime": 75.1898,
      "eval_samples_per_second": 5.785,
      "eval_steps_per_second": 2.899,
      "step": 110
    },
    {
      "epoch": 0.13441511261806732,
      "grad_norm": NaN,
      "learning_rate": 4.925202964923683e-05,
      "loss": 0.0,
      "step": 111
    },
    {
      "epoch": 0.13804795349963672,
      "grad_norm": NaN,
      "learning_rate": 4.700979230274829e-05,
      "loss": 0.0,
      "step": 114
    },
    {
      "epoch": 0.1416807943812061,
      "grad_norm": NaN,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0,
      "step": 117
    },
    {
      "epoch": 0.1453136352627755,
      "grad_norm": NaN,
      "learning_rate": 4.254788669119127e-05,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.1489464761443449,
      "grad_norm": NaN,
      "learning_rate": 4.0337204110222346e-05,
      "loss": 0.0,
      "step": 123
    },
    {
      "epoch": 0.15257931702591426,
      "grad_norm": NaN,
      "learning_rate": 3.814598111422513e-05,
      "loss": 0.0,
      "step": 126
    },
    {
      "epoch": 0.15621215790748366,
      "grad_norm": NaN,
      "learning_rate": 3.597863053469987e-05,
      "loss": 0.0,
      "step": 129
    },
    {
      "epoch": 0.15984499878905303,
      "grad_norm": NaN,
      "learning_rate": 3.383951712727701e-05,
      "loss": 0.0,
      "step": 132
    },
    {
      "epoch": 0.16347783967062243,
      "grad_norm": NaN,
      "learning_rate": 3.173294878168025e-05,
      "loss": 0.0,
      "step": 135
    },
    {
      "epoch": 0.1671106805521918,
      "grad_norm": NaN,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0,
      "step": 138
    },
    {
      "epoch": 0.1707435214337612,
      "grad_norm": NaN,
      "learning_rate": 2.7634342584218365e-05,
      "loss": 0.0,
      "step": 141
    },
    {
      "epoch": 0.1743763623153306,
      "grad_norm": NaN,
      "learning_rate": 2.5650558779781635e-05,
      "loss": 0.0,
      "step": 144
    },
    {
      "epoch": 0.17800920319689997,
      "grad_norm": NaN,
      "learning_rate": 2.371581150947476e-05,
      "loss": 0.0,
      "step": 147
    },
    {
      "epoch": 0.18164204407846937,
      "grad_norm": NaN,
      "learning_rate": 2.1833997096818898e-05,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.18527488496003874,
      "grad_norm": NaN,
      "learning_rate": 2.0008905265604316e-05,
      "loss": 0.0,
      "step": 153
    },
    {
      "epoch": 0.18890772584160814,
      "grad_norm": NaN,
      "learning_rate": 1.8244211507891063e-05,
      "loss": 0.0,
      "step": 156
    },
    {
      "epoch": 0.19254056672317751,
      "grad_norm": NaN,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0,
      "step": 159
    },
    {
      "epoch": 0.1961734076047469,
      "grad_norm": NaN,
      "learning_rate": 1.4910104855800427e-05,
      "loss": 0.0,
      "step": 162
    },
    {
      "epoch": 0.1998062484863163,
      "grad_norm": NaN,
      "learning_rate": 1.3347406408508695e-05,
      "loss": 0.0,
      "step": 165
    },
    {
      "epoch": 0.1998062484863163,
      "eval_loss": NaN,
      "eval_runtime": 72.7309,
      "eval_samples_per_second": 5.981,
      "eval_steps_per_second": 2.997,
      "step": 165
    },
    {
      "epoch": 0.20343908936788568,
      "grad_norm": NaN,
      "learning_rate": 1.1858521406886675e-05,
      "loss": 0.0,
      "step": 168
    },
    {
      "epoch": 0.20707193024945508,
      "grad_norm": NaN,
      "learning_rate": 1.0446448267182952e-05,
      "loss": 0.0,
      "step": 171
    },
    {
      "epoch": 0.21070477113102445,
      "grad_norm": NaN,
      "learning_rate": 9.114030716778433e-06,
      "loss": 0.0,
      "step": 174
    },
    {
      "epoch": 0.21433761201259385,
      "grad_norm": NaN,
      "learning_rate": 7.863952067298042e-06,
      "loss": 0.0,
      "step": 177
    },
    {
      "epoch": 0.21797045289416322,
      "grad_norm": NaN,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0,
      "step": 180
    },
    {
      "epoch": 0.22160329377573262,
      "grad_norm": NaN,
      "learning_rate": 5.620710549772295e-06,
      "loss": 0.0,
      "step": 183
    },
    {
      "epoch": 0.22523613465730202,
      "grad_norm": NaN,
      "learning_rate": 4.632065271606756e-06,
      "loss": 0.0,
      "step": 186
    },
    {
      "epoch": 0.2288689755388714,
      "grad_norm": NaN,
      "learning_rate": 3.734784976300165e-06,
      "loss": 0.0,
      "step": 189
    },
    {
      "epoch": 0.2325018164204408,
      "grad_norm": NaN,
      "learning_rate": 2.930676666954846e-06,
      "loss": 0.0,
      "step": 192
    },
    {
      "epoch": 0.23613465730201016,
      "grad_norm": NaN,
      "learning_rate": 2.221359710692961e-06,
      "loss": 0.0,
      "step": 195
    },
    {
      "epoch": 0.23976749818357956,
      "grad_norm": NaN,
      "learning_rate": 1.6082625774666794e-06,
      "loss": 0.0,
      "step": 198
    },
    {
      "epoch": 0.24340033906514894,
      "grad_norm": NaN,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0,
      "step": 201
    },
    {
      "epoch": 0.24703317994671833,
      "grad_norm": NaN,
      "learning_rate": 6.75470303823933e-07,
      "loss": 0.0,
      "step": 204
    },
    {
      "epoch": 0.2506660208282877,
      "grad_norm": NaN,
      "learning_rate": 3.576536829081323e-07,
      "loss": 0.0,
      "step": 207
    },
    {
      "epoch": 0.2542988617098571,
      "grad_norm": NaN,
      "learning_rate": 1.3981014094099353e-07,
      "loss": 0.0,
      "step": 210
    },
    {
      "epoch": 0.2579317025914265,
      "grad_norm": NaN,
      "learning_rate": 2.237838582483387e-08,
      "loss": 0.0,
      "step": 213
    }
  ],
  "logging_steps": 3,
  "max_steps": 215,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 80,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.54324119275438e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}