{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.70873786407767,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.24271844660194175,
      "grad_norm": 2.8362834453582764,
      "learning_rate": 4.960355987055016e-05,
      "loss": 6.0742,
      "step": 50
    },
    {
      "epoch": 0.4854368932038835,
      "grad_norm": 2.9484496116638184,
      "learning_rate": 4.9199029126213595e-05,
      "loss": 5.7218,
      "step": 100
    },
    {
      "epoch": 0.7281553398058253,
      "grad_norm": 3.542572259902954,
      "learning_rate": 4.879449838187702e-05,
      "loss": 5.4227,
      "step": 150
    },
    {
      "epoch": 0.970873786407767,
      "grad_norm": 4.634098052978516,
      "learning_rate": 4.8389967637540455e-05,
      "loss": 5.1655,
      "step": 200
    },
    {
      "epoch": 1.2135922330097086,
      "grad_norm": 5.699330806732178,
      "learning_rate": 4.798543689320388e-05,
      "loss": 4.8009,
      "step": 250
    },
    {
      "epoch": 1.4563106796116505,
      "grad_norm": 5.711933135986328,
      "learning_rate": 4.7580906148867315e-05,
      "loss": 4.607,
      "step": 300
    },
    {
      "epoch": 1.6990291262135924,
      "grad_norm": 5.113691806793213,
      "learning_rate": 4.717637540453075e-05,
      "loss": 4.462,
      "step": 350
    },
    {
      "epoch": 1.941747572815534,
      "grad_norm": 5.632521152496338,
      "learning_rate": 4.6771844660194174e-05,
      "loss": 4.3695,
      "step": 400
    },
    {
      "epoch": 2.1844660194174756,
      "grad_norm": 5.428906440734863,
      "learning_rate": 4.636731391585761e-05,
      "loss": 4.1549,
      "step": 450
    },
    {
      "epoch": 2.4271844660194173,
      "grad_norm": 5.037013530731201,
      "learning_rate": 4.596278317152104e-05,
      "loss": 4.0921,
      "step": 500
    },
    {
      "epoch": 2.6699029126213594,
      "grad_norm": 5.231846809387207,
      "learning_rate": 4.555825242718447e-05,
      "loss": 4.0662,
      "step": 550
    },
    {
      "epoch": 2.912621359223301,
      "grad_norm": 5.506278038024902,
      "learning_rate": 4.51537216828479e-05,
      "loss": 4.0403,
      "step": 600
    },
    {
      "epoch": 3.1553398058252426,
      "grad_norm": 5.410216331481934,
      "learning_rate": 4.4749190938511334e-05,
      "loss": 3.8375,
      "step": 650
    },
    {
      "epoch": 3.3980582524271843,
      "grad_norm": 5.637699127197266,
      "learning_rate": 4.434466019417476e-05,
      "loss": 3.7473,
      "step": 700
    },
    {
      "epoch": 3.6407766990291264,
      "grad_norm": 5.575273513793945,
      "learning_rate": 4.3940129449838194e-05,
      "loss": 3.7835,
      "step": 750
    },
    {
      "epoch": 3.883495145631068,
      "grad_norm": 5.737198352813721,
      "learning_rate": 4.353559870550162e-05,
      "loss": 3.7919,
      "step": 800
    },
    {
      "epoch": 4.12621359223301,
      "grad_norm": 5.645532608032227,
      "learning_rate": 4.313106796116505e-05,
      "loss": 3.6425,
      "step": 850
    },
    {
      "epoch": 4.368932038834951,
      "grad_norm": 6.308927059173584,
      "learning_rate": 4.272653721682848e-05,
      "loss": 3.4785,
      "step": 900
    },
    {
      "epoch": 4.611650485436893,
      "grad_norm": 5.863094329833984,
      "learning_rate": 4.232200647249191e-05,
      "loss": 3.5268,
      "step": 950
    },
    {
      "epoch": 4.854368932038835,
      "grad_norm": 6.120258331298828,
      "learning_rate": 4.191747572815534e-05,
      "loss": 3.5296,
      "step": 1000
    },
    {
      "epoch": 5.097087378640777,
      "grad_norm": 6.231515884399414,
      "learning_rate": 4.1512944983818774e-05,
      "loss": 3.3802,
      "step": 1050
    },
    {
      "epoch": 5.339805825242719,
      "grad_norm": 6.211188316345215,
      "learning_rate": 4.11084142394822e-05,
      "loss": 3.2148,
      "step": 1100
    },
    {
      "epoch": 5.58252427184466,
      "grad_norm": 6.8676934242248535,
      "learning_rate": 4.0703883495145634e-05,
      "loss": 3.2111,
      "step": 1150
    },
    {
      "epoch": 5.825242718446602,
      "grad_norm": 6.851133346557617,
      "learning_rate": 4.029935275080906e-05,
      "loss": 3.2771,
      "step": 1200
    },
    {
      "epoch": 6.067961165048544,
      "grad_norm": 6.708765506744385,
      "learning_rate": 3.9894822006472494e-05,
      "loss": 3.1587,
      "step": 1250
    },
    {
      "epoch": 6.310679611650485,
      "grad_norm": 7.136553764343262,
      "learning_rate": 3.949029126213593e-05,
      "loss": 2.9192,
      "step": 1300
    },
    {
      "epoch": 6.553398058252427,
      "grad_norm": 7.370823383331299,
      "learning_rate": 3.9085760517799354e-05,
      "loss": 2.922,
      "step": 1350
    },
    {
      "epoch": 6.796116504854369,
      "grad_norm": 7.630361557006836,
      "learning_rate": 3.868122977346279e-05,
      "loss": 2.9417,
      "step": 1400
    },
    {
      "epoch": 7.038834951456311,
      "grad_norm": 7.765511989593506,
      "learning_rate": 3.827669902912622e-05,
      "loss": 2.8669,
      "step": 1450
    },
    {
      "epoch": 7.281553398058253,
      "grad_norm": 7.85439920425415,
      "learning_rate": 3.787216828478965e-05,
      "loss": 2.5412,
      "step": 1500
    },
    {
      "epoch": 7.524271844660194,
      "grad_norm": 8.064071655273438,
      "learning_rate": 3.746763754045307e-05,
      "loss": 2.6131,
      "step": 1550
    },
    {
      "epoch": 7.766990291262136,
      "grad_norm": 8.692522048950195,
      "learning_rate": 3.7063106796116507e-05,
      "loss": 2.6356,
      "step": 1600
    },
    {
      "epoch": 8.009708737864077,
      "grad_norm": 8.012410163879395,
      "learning_rate": 3.665857605177993e-05,
      "loss": 2.599,
      "step": 1650
    },
    {
      "epoch": 8.25242718446602,
      "grad_norm": 8.6799898147583,
      "learning_rate": 3.6254045307443366e-05,
      "loss": 2.1992,
      "step": 1700
    },
    {
      "epoch": 8.495145631067961,
      "grad_norm": 8.963507652282715,
      "learning_rate": 3.584951456310679e-05,
      "loss": 2.2701,
      "step": 1750
    },
    {
      "epoch": 8.737864077669903,
      "grad_norm": 9.833822250366211,
      "learning_rate": 3.5444983818770226e-05,
      "loss": 2.2837,
      "step": 1800
    },
    {
      "epoch": 8.980582524271846,
      "grad_norm": 9.47242259979248,
      "learning_rate": 3.504045307443366e-05,
      "loss": 2.2854,
      "step": 1850
    },
    {
      "epoch": 9.223300970873787,
      "grad_norm": 8.856402397155762,
      "learning_rate": 3.4635922330097086e-05,
      "loss": 1.8862,
      "step": 1900
    },
    {
      "epoch": 9.466019417475728,
      "grad_norm": 9.948341369628906,
      "learning_rate": 3.423139158576052e-05,
      "loss": 1.922,
      "step": 1950
    },
    {
      "epoch": 9.70873786407767,
      "grad_norm": 10.28939151763916,
      "learning_rate": 3.382686084142395e-05,
      "loss": 1.9622,
      "step": 2000
    }
  ],
  "logging_steps": 50,
  "max_steps": 6180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 928706985984000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}