{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1137009664582149,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011370096645821489,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0011370096645821489,
      "eval_loss": NaN,
      "eval_runtime": 269.8696,
      "eval_samples_per_second": 2.746,
      "eval_steps_per_second": 0.345,
      "step": 1
    },
    {
      "epoch": 0.0022740193291642978,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0034110289937464467,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0045480386583285955,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.005685048322910745,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.006822057987492893,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.007959067652075043,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.009096077316657191,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.01023308698123934,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.01023308698123934,
      "eval_loss": NaN,
      "eval_runtime": 268.2775,
      "eval_samples_per_second": 2.762,
      "eval_steps_per_second": 0.347,
      "step": 9
    },
    {
      "epoch": 0.01137009664582149,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.012507106310403639,
      "grad_norm": NaN,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.013644115974985787,
      "grad_norm": NaN,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.014781125639567936,
      "grad_norm": NaN,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.015918135304150087,
      "grad_norm": NaN,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.017055144968732235,
      "grad_norm": NaN,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.018192154633314382,
      "grad_norm": NaN,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.019329164297896533,
      "grad_norm": NaN,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.02046617396247868,
      "grad_norm": NaN,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.02046617396247868,
      "eval_loss": NaN,
      "eval_runtime": 268.2715,
      "eval_samples_per_second": 2.762,
      "eval_steps_per_second": 0.347,
      "step": 18
    },
    {
      "epoch": 0.02160318362706083,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.02274019329164298,
      "grad_norm": NaN,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.023877202956225127,
      "grad_norm": NaN,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.025014212620807278,
      "grad_norm": NaN,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.026151222285389426,
      "grad_norm": NaN,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.027288231949971573,
      "grad_norm": NaN,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.028425241614553724,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.029562251279135872,
      "grad_norm": NaN,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0,
      "step": 26
    },
    {
      "epoch": 0.030699260943718023,
      "grad_norm": NaN,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.030699260943718023,
      "eval_loss": NaN,
      "eval_runtime": 268.3109,
      "eval_samples_per_second": 2.762,
      "eval_steps_per_second": 0.347,
      "step": 27
    },
    {
      "epoch": 0.031836270608300174,
      "grad_norm": NaN,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0,
      "step": 28
    },
    {
      "epoch": 0.03297328027288232,
      "grad_norm": NaN,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.0,
      "step": 29
    },
    {
      "epoch": 0.03411028993746447,
      "grad_norm": NaN,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.03524729960204662,
      "grad_norm": NaN,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.0,
      "step": 31
    },
    {
      "epoch": 0.036384309266628764,
      "grad_norm": NaN,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.0,
      "step": 32
    },
    {
      "epoch": 0.03752131893121091,
      "grad_norm": NaN,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.038658328595793066,
      "grad_norm": NaN,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.039795338260375214,
      "grad_norm": NaN,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.04093234792495736,
      "grad_norm": NaN,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.04093234792495736,
      "eval_loss": NaN,
      "eval_runtime": 268.2847,
      "eval_samples_per_second": 2.762,
      "eval_steps_per_second": 0.347,
      "step": 36
    },
    {
      "epoch": 0.04206935758953951,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.04320636725412166,
      "grad_norm": NaN,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.04434337691870381,
      "grad_norm": NaN,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.04548038658328596,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.046617396247868106,
      "grad_norm": NaN,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.047754405912450254,
      "grad_norm": NaN,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.0488914155770324,
      "grad_norm": NaN,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0,
      "step": 43
    },
    {
      "epoch": 0.050028425241614556,
      "grad_norm": NaN,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.0,
      "step": 44
    },
    {
      "epoch": 0.051165434906196704,
      "grad_norm": NaN,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.051165434906196704,
      "eval_loss": NaN,
      "eval_runtime": 268.3394,
      "eval_samples_per_second": 2.761,
      "eval_steps_per_second": 0.347,
      "step": 45
    },
    {
      "epoch": 0.05230244457077885,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 46
    },
    {
      "epoch": 0.053439454235361,
      "grad_norm": NaN,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.0,
      "step": 47
    },
    {
      "epoch": 0.054576463899943146,
      "grad_norm": NaN,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.0557134735645253,
      "grad_norm": NaN,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0,
      "step": 49
    },
    {
      "epoch": 0.05685048322910745,
      "grad_norm": NaN,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.057987492893689596,
      "grad_norm": NaN,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.059124502558271744,
      "grad_norm": NaN,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0,
      "step": 52
    },
    {
      "epoch": 0.06026151222285389,
      "grad_norm": NaN,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.0,
      "step": 53
    },
    {
      "epoch": 0.061398521887436046,
      "grad_norm": NaN,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.061398521887436046,
      "eval_loss": NaN,
      "eval_runtime": 268.3246,
      "eval_samples_per_second": 2.762,
      "eval_steps_per_second": 0.347,
      "step": 54
    },
    {
      "epoch": 0.06253553155201819,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 55
    },
    {
      "epoch": 0.06367254121660035,
      "grad_norm": NaN,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0,
      "step": 56
    },
    {
      "epoch": 0.0648095508811825,
      "grad_norm": NaN,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.06594656054576464,
      "grad_norm": NaN,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0,
      "step": 58
    },
    {
      "epoch": 0.06708357021034679,
      "grad_norm": NaN,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.06822057987492894,
      "grad_norm": NaN,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.06935758953951109,
      "grad_norm": NaN,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.07049459920409323,
      "grad_norm": NaN,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.07163160886867538,
      "grad_norm": NaN,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.07163160886867538,
      "eval_loss": NaN,
      "eval_runtime": 268.5027,
      "eval_samples_per_second": 2.76,
      "eval_steps_per_second": 0.346,
      "step": 63
    },
    {
      "epoch": 0.07276861853325753,
      "grad_norm": NaN,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.07390562819783968,
      "grad_norm": NaN,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.07504263786242182,
      "grad_norm": NaN,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.07617964752700399,
      "grad_norm": NaN,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.07731665719158613,
      "grad_norm": NaN,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.07845366685616828,
      "grad_norm": NaN,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.07959067652075043,
      "grad_norm": NaN,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 70
    },
    {
      "epoch": 0.08072768618533258,
      "grad_norm": NaN,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.08186469584991472,
      "grad_norm": NaN,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.08186469584991472,
      "eval_loss": NaN,
      "eval_runtime": 268.3062,
      "eval_samples_per_second": 2.762,
      "eval_steps_per_second": 0.347,
      "step": 72
    },
    {
      "epoch": 0.08300170551449687,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.08413871517907902,
      "grad_norm": NaN,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.08527572484366117,
      "grad_norm": NaN,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.08641273450824331,
      "grad_norm": NaN,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 0.08754974417282547,
      "grad_norm": NaN,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 0.08868675383740762,
      "grad_norm": NaN,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.08982376350198977,
      "grad_norm": NaN,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0,
      "step": 79
    },
    {
      "epoch": 0.09096077316657192,
      "grad_norm": NaN,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.09209778283115407,
      "grad_norm": NaN,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.09209778283115407,
      "eval_loss": NaN,
      "eval_runtime": 268.2648,
      "eval_samples_per_second": 2.762,
      "eval_steps_per_second": 0.347,
      "step": 81
    },
    {
      "epoch": 0.09323479249573621,
      "grad_norm": NaN,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 0.09437180216031836,
      "grad_norm": NaN,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 0.09550881182490051,
      "grad_norm": NaN,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.09664582148948266,
      "grad_norm": NaN,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.0977828311540648,
      "grad_norm": NaN,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0,
      "step": 86
    },
    {
      "epoch": 0.09891984081864696,
      "grad_norm": NaN,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.10005685048322911,
      "grad_norm": NaN,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 0.10119386014781126,
      "grad_norm": NaN,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 0.10233086981239341,
      "grad_norm": NaN,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.10233086981239341,
      "eval_loss": NaN,
      "eval_runtime": 268.2325,
      "eval_samples_per_second": 2.763,
      "eval_steps_per_second": 0.347,
      "step": 90
    },
    {
      "epoch": 0.10346787947697555,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 0.1046048891415577,
      "grad_norm": NaN,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.0,
      "step": 92
    },
    {
      "epoch": 0.10574189880613985,
      "grad_norm": NaN,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 0.106878908470722,
      "grad_norm": NaN,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0,
      "step": 94
    },
    {
      "epoch": 0.10801591813530415,
      "grad_norm": NaN,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.10915292779988629,
      "grad_norm": NaN,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.11028993746446845,
      "grad_norm": NaN,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 0.1114269471290506,
      "grad_norm": NaN,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 0.11256395679363275,
      "grad_norm": NaN,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.11256395679363275,
      "eval_loss": NaN,
      "eval_runtime": 268.243,
      "eval_samples_per_second": 2.762,
      "eval_steps_per_second": 0.347,
      "step": 99
    },
    {
      "epoch": 0.1137009664582149,
      "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": 2.5786267786543104e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}