{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3714020427112349,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003714020427112349,
      "eval_loss": 10.378816604614258,
      "eval_runtime": 1.3292,
      "eval_samples_per_second": 341.551,
      "eval_steps_per_second": 42.882,
      "step": 1
    },
    {
      "epoch": 0.011142061281337047,
      "grad_norm": 0.014514707960188389,
      "learning_rate": 3e-05,
      "loss": 10.3795,
      "step": 3
    },
    {
      "epoch": 0.022284122562674095,
      "grad_norm": 0.01718750037252903,
      "learning_rate": 6e-05,
      "loss": 10.3788,
      "step": 6
    },
    {
      "epoch": 0.033426183844011144,
      "grad_norm": 0.018008925020694733,
      "learning_rate": 9e-05,
      "loss": 10.3786,
      "step": 9
    },
    {
      "epoch": 0.033426183844011144,
      "eval_loss": 10.378602981567383,
      "eval_runtime": 1.3052,
      "eval_samples_per_second": 347.852,
      "eval_steps_per_second": 43.673,
      "step": 9
    },
    {
      "epoch": 0.04456824512534819,
      "grad_norm": 0.016212427988648415,
      "learning_rate": 9.987820251299122e-05,
      "loss": 10.3789,
      "step": 12
    },
    {
      "epoch": 0.055710306406685235,
      "grad_norm": 0.016671117395162582,
      "learning_rate": 9.924038765061042e-05,
      "loss": 10.3792,
      "step": 15
    },
    {
      "epoch": 0.06685236768802229,
      "grad_norm": 0.016305958852171898,
      "learning_rate": 9.806308479691595e-05,
      "loss": 10.3783,
      "step": 18
    },
    {
      "epoch": 0.06685236768802229,
      "eval_loss": 10.378040313720703,
      "eval_runtime": 1.3173,
      "eval_samples_per_second": 344.654,
      "eval_steps_per_second": 43.272,
      "step": 18
    },
    {
      "epoch": 0.07799442896935933,
      "grad_norm": 0.018844736739993095,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.378,
      "step": 21
    },
    {
      "epoch": 0.08913649025069638,
      "grad_norm": 0.020653052255511284,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.3781,
      "step": 24
    },
    {
      "epoch": 0.10027855153203342,
      "grad_norm": 0.018101783469319344,
      "learning_rate": 9.145187862775209e-05,
      "loss": 10.3773,
      "step": 27
    },
    {
      "epoch": 0.10027855153203342,
      "eval_loss": 10.377413749694824,
      "eval_runtime": 1.3583,
      "eval_samples_per_second": 334.247,
      "eval_steps_per_second": 41.965,
      "step": 27
    },
    {
      "epoch": 0.11142061281337047,
      "grad_norm": 0.021037165075540543,
      "learning_rate": 8.83022221559489e-05,
      "loss": 10.3777,
      "step": 30
    },
    {
      "epoch": 0.12256267409470752,
      "grad_norm": 0.02159174345433712,
      "learning_rate": 8.473291852294987e-05,
      "loss": 10.3772,
      "step": 33
    },
    {
      "epoch": 0.13370473537604458,
      "grad_norm": 0.023182040080428123,
      "learning_rate": 8.07830737662829e-05,
      "loss": 10.3766,
      "step": 36
    },
    {
      "epoch": 0.13370473537604458,
      "eval_loss": 10.376729011535645,
      "eval_runtime": 1.3571,
      "eval_samples_per_second": 334.536,
      "eval_steps_per_second": 42.001,
      "step": 36
    },
    {
      "epoch": 0.14484679665738162,
      "grad_norm": 0.023219875991344452,
      "learning_rate": 7.649596321166024e-05,
      "loss": 10.3776,
      "step": 39
    },
    {
      "epoch": 0.15598885793871867,
      "grad_norm": 0.026010680943727493,
      "learning_rate": 7.191855733945387e-05,
      "loss": 10.3773,
      "step": 42
    },
    {
      "epoch": 0.1671309192200557,
      "grad_norm": 0.029791677370667458,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.3759,
      "step": 45
    },
    {
      "epoch": 0.1671309192200557,
      "eval_loss": 10.375983238220215,
      "eval_runtime": 1.3417,
      "eval_samples_per_second": 338.387,
      "eval_steps_per_second": 42.485,
      "step": 45
    },
    {
      "epoch": 0.17827298050139276,
      "grad_norm": 0.026904676109552383,
      "learning_rate": 6.209609477998338e-05,
      "loss": 10.3762,
      "step": 48
    },
    {
      "epoch": 0.1894150417827298,
      "grad_norm": 0.034599192440509796,
      "learning_rate": 5.695865504800327e-05,
      "loss": 10.375,
      "step": 51
    },
    {
      "epoch": 0.20055710306406685,
      "grad_norm": 0.034609757363796234,
      "learning_rate": 5.174497483512506e-05,
      "loss": 10.3753,
      "step": 54
    },
    {
      "epoch": 0.20055710306406685,
      "eval_loss": 10.375200271606445,
      "eval_runtime": 1.3283,
      "eval_samples_per_second": 341.798,
      "eval_steps_per_second": 42.913,
      "step": 54
    },
    {
      "epoch": 0.2116991643454039,
      "grad_norm": 0.03360167518258095,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 10.3749,
      "step": 57
    },
    {
      "epoch": 0.22284122562674094,
      "grad_norm": 0.03287893533706665,
      "learning_rate": 4.131759111665349e-05,
      "loss": 10.3746,
      "step": 60
    },
    {
      "epoch": 0.233983286908078,
      "grad_norm": 0.035624388605356216,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 10.3739,
      "step": 63
    },
    {
      "epoch": 0.233983286908078,
      "eval_loss": 10.374495506286621,
      "eval_runtime": 1.3201,
      "eval_samples_per_second": 343.917,
      "eval_steps_per_second": 43.179,
      "step": 63
    },
    {
      "epoch": 0.24512534818941503,
      "grad_norm": 0.03744365647435188,
      "learning_rate": 3.12696703292044e-05,
      "loss": 10.3745,
      "step": 66
    },
    {
      "epoch": 0.2562674094707521,
      "grad_norm": 0.03684169799089432,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 10.3749,
      "step": 69
    },
    {
      "epoch": 0.26740947075208915,
      "grad_norm": 0.041187137365341187,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 10.3751,
      "step": 72
    },
    {
      "epoch": 0.26740947075208915,
      "eval_loss": 10.373970985412598,
      "eval_runtime": 1.3239,
      "eval_samples_per_second": 342.93,
      "eval_steps_per_second": 43.055,
      "step": 72
    },
    {
      "epoch": 0.2785515320334262,
      "grad_norm": 0.04117584973573685,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 10.374,
      "step": 75
    },
    {
      "epoch": 0.28969359331476324,
      "grad_norm": 0.041653797030448914,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 10.3748,
      "step": 78
    },
    {
      "epoch": 0.3008356545961003,
      "grad_norm": 0.05219626799225807,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 10.3743,
      "step": 81
    },
    {
      "epoch": 0.3008356545961003,
      "eval_loss": 10.373651504516602,
      "eval_runtime": 1.3214,
      "eval_samples_per_second": 343.581,
      "eval_steps_per_second": 43.137,
      "step": 81
    },
    {
      "epoch": 0.31197771587743733,
      "grad_norm": 0.04116308316588402,
      "learning_rate": 7.597595192178702e-06,
      "loss": 10.374,
      "step": 84
    },
    {
      "epoch": 0.3231197771587744,
      "grad_norm": 0.04389878734946251,
      "learning_rate": 5.060297685041659e-06,
      "loss": 10.3742,
      "step": 87
    },
    {
      "epoch": 0.3342618384401114,
      "grad_norm": 0.045802537351846695,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 10.3736,
      "step": 90
    },
    {
      "epoch": 0.3342618384401114,
      "eval_loss": 10.373515129089355,
      "eval_runtime": 1.3528,
      "eval_samples_per_second": 335.605,
      "eval_steps_per_second": 42.135,
      "step": 90
    },
    {
      "epoch": 0.34540389972144847,
      "grad_norm": 0.048498645424842834,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 10.3742,
      "step": 93
    },
    {
      "epoch": 0.3565459610027855,
      "grad_norm": 0.03822680562734604,
      "learning_rate": 4.865965629214819e-07,
      "loss": 10.3734,
      "step": 96
    },
    {
      "epoch": 0.36768802228412256,
      "grad_norm": 0.05491569638252258,
      "learning_rate": 3.04586490452119e-08,
      "loss": 10.3726,
      "step": 99
    },
    {
      "epoch": 0.36768802228412256,
      "eval_loss": 10.373485565185547,
      "eval_runtime": 1.3066,
      "eval_samples_per_second": 347.471,
      "eval_steps_per_second": 43.625,
      "step": 99
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 18384309977088.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}