{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08035355564483729,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008035355564483728,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0008035355564483728,
      "eval_loss": NaN,
      "eval_runtime": 64.7903,
      "eval_samples_per_second": 16.175,
      "eval_steps_per_second": 2.022,
      "step": 1
    },
    {
      "epoch": 0.0016070711128967456,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0024106066693451184,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0032141422257934912,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.004017677782241864,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.004821213338690237,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00562474889513861,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0064282844515869825,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.007231820008035355,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.007231820008035355,
      "eval_loss": NaN,
      "eval_runtime": 64.4073,
      "eval_samples_per_second": 16.271,
      "eval_steps_per_second": 2.034,
      "step": 9
    },
    {
      "epoch": 0.008035355564483728,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.008838891120932101,
      "grad_norm": NaN,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.009642426677380474,
      "grad_norm": NaN,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.010445962233828847,
      "grad_norm": NaN,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.01124949779027722,
      "grad_norm": NaN,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.012053033346725592,
      "grad_norm": NaN,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.012856568903173965,
      "grad_norm": NaN,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.013660104459622338,
      "grad_norm": NaN,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.01446364001607071,
      "grad_norm": NaN,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.01446364001607071,
      "eval_loss": NaN,
      "eval_runtime": 64.4931,
      "eval_samples_per_second": 16.25,
      "eval_steps_per_second": 2.031,
      "step": 18
    },
    {
      "epoch": 0.015267175572519083,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.016070711128967456,
      "grad_norm": NaN,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.01687424668541583,
      "grad_norm": NaN,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.017677782241864202,
      "grad_norm": NaN,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.018481317798312576,
      "grad_norm": NaN,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.019284853354760947,
      "grad_norm": NaN,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.020088388911209322,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.020891924467657693,
      "grad_norm": NaN,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.021695460024106068,
      "grad_norm": NaN,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.021695460024106068,
      "eval_loss": NaN,
      "eval_runtime": 64.886,
      "eval_samples_per_second": 16.151,
      "eval_steps_per_second": 2.019,
      "step": 27
    },
    {
      "epoch": 0.02249899558055444,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.023302531137002813,
      "grad_norm": NaN,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.024106066693451184,
      "grad_norm": NaN,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.02490960224989956,
      "grad_norm": NaN,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.02571313780634793,
      "grad_norm": NaN,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.026516673362796304,
      "grad_norm": NaN,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.027320208919244676,
      "grad_norm": NaN,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.02812374447569305,
      "grad_norm": NaN,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.02892728003214142,
      "grad_norm": NaN,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.02892728003214142,
      "eval_loss": NaN,
      "eval_runtime": 64.4883,
      "eval_samples_per_second": 16.251,
      "eval_steps_per_second": 2.031,
      "step": 36
    },
    {
      "epoch": 0.029730815588589796,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.030534351145038167,
      "grad_norm": NaN,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.03133788670148654,
      "grad_norm": NaN,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.03214142225793491,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.03294495781438329,
      "grad_norm": NaN,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.03374849337083166,
      "grad_norm": NaN,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.03455202892728003,
      "grad_norm": NaN,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.035355564483728404,
      "grad_norm": NaN,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.03615910004017678,
      "grad_norm": NaN,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.03615910004017678,
      "eval_loss": NaN,
      "eval_runtime": 64.3413,
      "eval_samples_per_second": 16.288,
      "eval_steps_per_second": 2.036,
      "step": 45
    },
    {
      "epoch": 0.03696263559662515,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.03776617115307352,
      "grad_norm": NaN,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.038569706709521895,
      "grad_norm": NaN,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.03937324226597027,
      "grad_norm": NaN,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.040176777822418644,
      "grad_norm": NaN,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.04098031337886701,
      "grad_norm": NaN,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.041783848935315386,
      "grad_norm": NaN,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.04258738449176376,
      "grad_norm": NaN,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.043390920048212135,
      "grad_norm": NaN,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.043390920048212135,
      "eval_loss": NaN,
      "eval_runtime": 64.3224,
      "eval_samples_per_second": 16.293,
      "eval_steps_per_second": 2.037,
      "step": 54
    },
    {
      "epoch": 0.0441944556046605,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.04499799116110888,
      "grad_norm": NaN,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.04580152671755725,
      "grad_norm": NaN,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.046605062274005626,
      "grad_norm": NaN,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.047408597830454,
      "grad_norm": NaN,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.04821213338690237,
      "grad_norm": NaN,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.04901566894335074,
      "grad_norm": NaN,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.04981920449979912,
      "grad_norm": NaN,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.05062274005624749,
      "grad_norm": NaN,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.05062274005624749,
      "eval_loss": NaN,
      "eval_runtime": 64.3796,
      "eval_samples_per_second": 16.278,
      "eval_steps_per_second": 2.035,
      "step": 63
    },
    {
      "epoch": 0.05142627561269586,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.052229811169144234,
      "grad_norm": NaN,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.05303334672559261,
      "grad_norm": NaN,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.05383688228204098,
      "grad_norm": NaN,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.05464041783848935,
      "grad_norm": NaN,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.055443953394937726,
      "grad_norm": NaN,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.0562474889513861,
      "grad_norm": NaN,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.057051024507834475,
      "grad_norm": NaN,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.05785456006428284,
      "grad_norm": NaN,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.05785456006428284,
      "eval_loss": NaN,
      "eval_runtime": 64.3731,
      "eval_samples_per_second": 16.28,
      "eval_steps_per_second": 2.035,
      "step": 72
    },
    {
      "epoch": 0.05865809562073122,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.05946163117717959,
      "grad_norm": NaN,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.060265166733627966,
      "grad_norm": NaN,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.061068702290076333,
      "grad_norm": NaN,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 0.06187223784652471,
      "grad_norm": NaN,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 0.06267577340297308,
      "grad_norm": NaN,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.06347930895942146,
      "grad_norm": NaN,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0,
      "step": 79
    },
    {
      "epoch": 0.06428284451586982,
      "grad_norm": NaN,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.0650863800723182,
      "grad_norm": NaN,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.0650863800723182,
      "eval_loss": NaN,
      "eval_runtime": 64.4251,
      "eval_samples_per_second": 16.267,
      "eval_steps_per_second": 2.033,
      "step": 81
    },
    {
      "epoch": 0.06588991562876657,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 0.06669345118521494,
      "grad_norm": NaN,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 0.06749698674166332,
      "grad_norm": NaN,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.06830052229811169,
      "grad_norm": NaN,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.06910405785456006,
      "grad_norm": NaN,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0,
      "step": 86
    },
    {
      "epoch": 0.06990759341100844,
      "grad_norm": NaN,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.07071112896745681,
      "grad_norm": NaN,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 0.07151466452390519,
      "grad_norm": NaN,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 0.07231820008035356,
      "grad_norm": NaN,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.07231820008035356,
      "eval_loss": NaN,
      "eval_runtime": 64.4276,
      "eval_samples_per_second": 16.266,
      "eval_steps_per_second": 2.033,
      "step": 90
    },
    {
      "epoch": 0.07312173563680192,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 0.0739252711932503,
      "grad_norm": NaN,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.0,
      "step": 92
    },
    {
      "epoch": 0.07472880674969867,
      "grad_norm": NaN,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 0.07553234230614704,
      "grad_norm": NaN,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0,
      "step": 94
    },
    {
      "epoch": 0.07633587786259542,
      "grad_norm": NaN,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.07713941341904379,
      "grad_norm": NaN,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.07794294897549217,
      "grad_norm": NaN,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 0.07874648453194054,
      "grad_norm": NaN,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 0.0795500200883889,
      "grad_norm": NaN,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.0795500200883889,
      "eval_loss": NaN,
      "eval_runtime": 64.3523,
      "eval_samples_per_second": 16.285,
      "eval_steps_per_second": 2.036,
      "step": 99
    },
    {
      "epoch": 0.08035355564483729,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.8088171438800896e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}