{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9980657640232108,
  "eval_steps": 100,
  "global_step": 258,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0038684719535783366,
      "grad_norm": 6.09610478125056e+18,
      "learning_rate": 0.0,
      "loss": 3.1242,
      "step": 1
    },
    {
      "epoch": 0.019342359767891684,
      "grad_norm": 2697.71337890625,
      "learning_rate": 3.0769230769230774e-06,
      "loss": 3.1772,
      "step": 5
    },
    {
      "epoch": 0.03868471953578337,
      "grad_norm": 25.10409927368164,
      "learning_rate": 6.923076923076923e-06,
      "loss": 2.8881,
      "step": 10
    },
    {
      "epoch": 0.058027079303675046,
      "grad_norm": 12.363713264465332,
      "learning_rate": 1.076923076923077e-05,
      "loss": 2.4609,
      "step": 15
    },
    {
      "epoch": 0.07736943907156674,
      "grad_norm": 22.165477752685547,
      "learning_rate": 1.4615384615384615e-05,
      "loss": 2.2508,
      "step": 20
    },
    {
      "epoch": 0.09671179883945841,
      "grad_norm": 14.86285400390625,
      "learning_rate": 1.8461538461538465e-05,
      "loss": 2.0898,
      "step": 25
    },
    {
      "epoch": 0.11605415860735009,
      "grad_norm": 7.5494914054870605,
      "learning_rate": 1.9991749570421146e-05,
      "loss": 1.9877,
      "step": 30
    },
    {
      "epoch": 0.13539651837524178,
      "grad_norm": 4.193073272705078,
      "learning_rate": 1.9941379571543597e-05,
      "loss": 1.8119,
      "step": 35
    },
    {
      "epoch": 0.15473887814313347,
      "grad_norm": 5.1745171546936035,
      "learning_rate": 1.984545368367337e-05,
      "loss": 1.7714,
      "step": 40
    },
    {
      "epoch": 0.17408123791102514,
      "grad_norm": 6.300442695617676,
      "learning_rate": 1.9704411482532116e-05,
      "loss": 1.7391,
      "step": 45
    },
    {
      "epoch": 0.19342359767891681,
      "grad_norm": 5.5538201332092285,
      "learning_rate": 1.9518899287155558e-05,
      "loss": 1.7088,
      "step": 50
    },
    {
      "epoch": 0.2127659574468085,
      "grad_norm": 4.729171276092529,
      "learning_rate": 1.9289767198167918e-05,
      "loss": 1.6553,
      "step": 55
    },
    {
      "epoch": 0.23210831721470018,
      "grad_norm": 2.736438512802124,
      "learning_rate": 1.9018065202237083e-05,
      "loss": 1.6234,
      "step": 60
    },
    {
      "epoch": 0.2514506769825919,
      "grad_norm": 2.781848192214966,
      "learning_rate": 1.8705038360561724e-05,
      "loss": 1.6005,
      "step": 65
    },
    {
      "epoch": 0.27079303675048355,
      "grad_norm": 30.041719436645508,
      "learning_rate": 1.8352121103438804e-05,
      "loss": 1.6161,
      "step": 70
    },
    {
      "epoch": 0.2901353965183752,
      "grad_norm": 2.318030595779419,
      "learning_rate": 1.796093065705644e-05,
      "loss": 1.5743,
      "step": 75
    },
    {
      "epoch": 0.30947775628626695,
      "grad_norm": 2.369173526763916,
      "learning_rate": 1.7533259632633443e-05,
      "loss": 1.537,
      "step": 80
    },
    {
      "epoch": 0.3288201160541586,
      "grad_norm": 8.767570495605469,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 1.5716,
      "step": 85
    },
    {
      "epoch": 0.3481624758220503,
      "grad_norm": 2.4866902828216553,
      "learning_rate": 1.6576473166320644e-05,
      "loss": 1.5327,
      "step": 90
    },
    {
      "epoch": 0.36750483558994196,
      "grad_norm": 2.8688602447509766,
      "learning_rate": 1.6051742151937655e-05,
      "loss": 1.5223,
      "step": 95
    },
    {
      "epoch": 0.38684719535783363,
      "grad_norm": 9.360047340393066,
      "learning_rate": 1.549927932310155e-05,
      "loss": 1.5069,
      "step": 100
    },
    {
      "epoch": 0.38684719535783363,
      "eval_loss": 1.489111065864563,
      "eval_runtime": 4.7946,
      "eval_samples_per_second": 186.667,
      "eval_steps_per_second": 5.84,
      "step": 100
    },
    {
      "epoch": 0.40618955512572535,
      "grad_norm": 2.7148385047912598,
      "learning_rate": 1.4921616313890073e-05,
      "loss": 1.4631,
      "step": 105
    },
    {
      "epoch": 0.425531914893617,
      "grad_norm": 2.1432764530181885,
      "learning_rate": 1.4321400236983459e-05,
      "loss": 1.4502,
      "step": 110
    },
    {
      "epoch": 0.4448742746615087,
      "grad_norm": 2.373682975769043,
      "learning_rate": 1.3701381553399147e-05,
      "loss": 1.411,
      "step": 115
    },
    {
      "epoch": 0.46421663442940037,
      "grad_norm": 2.2317380905151367,
      "learning_rate": 1.3064401468637793e-05,
      "loss": 1.4031,
      "step": 120
    },
    {
      "epoch": 0.4835589941972921,
      "grad_norm": 1.9476709365844727,
      "learning_rate": 1.2413378912997058e-05,
      "loss": 1.3929,
      "step": 125
    },
    {
      "epoch": 0.5029013539651838,
      "grad_norm": 1.9585973024368286,
      "learning_rate": 1.175129716571531e-05,
      "loss": 1.3855,
      "step": 130
    },
    {
      "epoch": 0.5222437137330754,
      "grad_norm": 2.38059401512146,
      "learning_rate": 1.1081190184239418e-05,
      "loss": 1.3818,
      "step": 135
    },
    {
      "epoch": 0.5415860735009671,
      "grad_norm": 2.2399237155914307,
      "learning_rate": 1.0406128701262128e-05,
      "loss": 1.334,
      "step": 140
    },
    {
      "epoch": 0.5609284332688588,
      "grad_norm": 2.42098069190979,
      "learning_rate": 9.729206153238658e-06,
      "loss": 1.3365,
      "step": 145
    },
    {
      "epoch": 0.5802707930367504,
      "grad_norm": 2.278903007507324,
      "learning_rate": 9.053524504864391e-06,
      "loss": 1.3288,
      "step": 150
    },
    {
      "epoch": 0.5996131528046421,
      "grad_norm": 1.902079701423645,
      "learning_rate": 8.382180034472353e-06,
      "loss": 1.309,
      "step": 155
    },
    {
      "epoch": 0.6189555125725339,
      "grad_norm": 1.8283921480178833,
      "learning_rate": 7.718249145488143e-06,
      "loss": 1.3069,
      "step": 160
    },
    {
      "epoch": 0.6382978723404256,
      "grad_norm": 1.9884213209152222,
      "learning_rate": 7.064774268960654e-06,
      "loss": 1.2787,
      "step": 165
    },
    {
      "epoch": 0.6576402321083172,
      "grad_norm": 2.0930237770080566,
      "learning_rate": 6.4247499217695995e-06,
      "loss": 1.2678,
      "step": 170
    },
    {
      "epoch": 0.6769825918762089,
      "grad_norm": 2.522498369216919,
      "learning_rate": 5.801108984397355e-06,
      "loss": 1.2107,
      "step": 175
    },
    {
      "epoch": 0.6963249516441006,
      "grad_norm": 2.825383424758911,
      "learning_rate": 5.196709261146606e-06,
      "loss": 1.2417,
      "step": 180
    },
    {
      "epoch": 0.7156673114119922,
      "grad_norm": 2.353144645690918,
      "learning_rate": 4.614320384390959e-06,
      "loss": 1.2198,
      "step": 185
    },
    {
      "epoch": 0.7350096711798839,
      "grad_norm": 2.3441641330718994,
      "learning_rate": 4.056611122869106e-06,
      "loss": 1.2026,
      "step": 190
    },
    {
      "epoch": 0.7543520309477756,
      "grad_norm": 2.090709924697876,
      "learning_rate": 3.5261371521817247e-06,
      "loss": 1.1828,
      "step": 195
    },
    {
      "epoch": 0.7736943907156673,
      "grad_norm": 1.8887003660202026,
      "learning_rate": 3.0253293435321797e-06,
      "loss": 1.2171,
      "step": 200
    },
    {
      "epoch": 0.7736943907156673,
      "eval_loss": 1.193406581878662,
      "eval_runtime": 4.7625,
      "eval_samples_per_second": 187.926,
      "eval_steps_per_second": 5.879,
      "step": 200
    },
    {
      "epoch": 0.793036750483559,
      "grad_norm": 2.0174171924591064,
      "learning_rate": 2.5564826243772965e-06,
      "loss": 1.1818,
      "step": 205
    },
    {
      "epoch": 0.8123791102514507,
      "grad_norm": 2.1461687088012695,
      "learning_rate": 2.1217454620337842e-06,
      "loss": 1.1851,
      "step": 210
    },
    {
      "epoch": 0.8317214700193424,
      "grad_norm": 1.9792951345443726,
      "learning_rate": 1.7231100184310955e-06,
      "loss": 1.1799,
      "step": 215
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 2.1498570442199707,
      "learning_rate": 1.3624030211261684e-06,
      "loss": 1.1748,
      "step": 220
    },
    {
      "epoch": 0.8704061895551257,
      "grad_norm": 2.3734147548675537,
      "learning_rate": 1.0412773924131202e-06,
      "loss": 1.1529,
      "step": 225
    },
    {
      "epoch": 0.8897485493230174,
      "grad_norm": 21.268768310546875,
      "learning_rate": 7.612046748871327e-07,
      "loss": 1.1486,
      "step": 230
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 2.0091605186462402,
      "learning_rate": 5.234682881719766e-07,
      "loss": 1.1451,
      "step": 235
    },
    {
      "epoch": 0.9284332688588007,
      "grad_norm": 1.8940573930740356,
      "learning_rate": 3.2915764771193294e-07,
      "loss": 1.1681,
      "step": 240
    },
    {
      "epoch": 0.9477756286266924,
      "grad_norm": 2.0212926864624023,
      "learning_rate": 1.791631725784404e-07,
      "loss": 1.1391,
      "step": 245
    },
    {
      "epoch": 0.9671179883945842,
      "grad_norm": 2.1692233085632324,
      "learning_rate": 7.4172205167945e-08,
      "loss": 1.1662,
      "step": 250
    },
    {
      "epoch": 0.9864603481624759,
      "grad_norm": 1.9714499711990356,
      "learning_rate": 1.4665861488761813e-08,
      "loss": 1.163,
      "step": 255
    },
    {
      "epoch": 0.9980657640232108,
      "step": 258,
      "total_flos": 9.517157411769549e+16,
      "train_loss": 1.5008004404777704,
      "train_runtime": 885.0234,
      "train_samples_per_second": 18.662,
      "train_steps_per_second": 0.292
    }
  ],
  "logging_steps": 5,
  "max_steps": 258,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.517157411769549e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}