{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 268,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018656716417910446,
      "grad_norm": 23.549664007081883,
      "learning_rate": 1.785714285714286e-05,
      "loss": 6.105,
      "step": 5
    },
    {
      "epoch": 0.03731343283582089,
      "grad_norm": 13.350189408858572,
      "learning_rate": 3.571428571428572e-05,
      "loss": 4.6199,
      "step": 10
    },
    {
      "epoch": 0.055970149253731345,
      "grad_norm": 9.366720060199096,
      "learning_rate": 4.999827900623038e-05,
      "loss": 3.3379,
      "step": 15
    },
    {
      "epoch": 0.07462686567164178,
      "grad_norm": 6.751610634894579,
      "learning_rate": 4.993807186343243e-05,
      "loss": 2.6927,
      "step": 20
    },
    {
      "epoch": 0.09328358208955224,
      "grad_norm": 6.488714411639678,
      "learning_rate": 4.979207812402531e-05,
      "loss": 2.0578,
      "step": 25
    },
    {
      "epoch": 0.11194029850746269,
      "grad_norm": 3.5421676034059377,
      "learning_rate": 4.956085596012407e-05,
      "loss": 1.5831,
      "step": 30
    },
    {
      "epoch": 0.13059701492537312,
      "grad_norm": 2.571834851270616,
      "learning_rate": 4.924528939432311e-05,
      "loss": 1.315,
      "step": 35
    },
    {
      "epoch": 0.14925373134328357,
      "grad_norm": 1.5963085542775126,
      "learning_rate": 4.884658491984735e-05,
      "loss": 1.1863,
      "step": 40
    },
    {
      "epoch": 0.16791044776119404,
      "grad_norm": 2.074329344904024,
      "learning_rate": 4.8366266887814235e-05,
      "loss": 1.1028,
      "step": 45
    },
    {
      "epoch": 0.1865671641791045,
      "grad_norm": 1.3297400462887774,
      "learning_rate": 4.780617167924209e-05,
      "loss": 1.04,
      "step": 50
    },
    {
      "epoch": 0.20522388059701493,
      "grad_norm": 1.7003158095532473,
      "learning_rate": 4.716844068408693e-05,
      "loss": 0.9969,
      "step": 55
    },
    {
      "epoch": 0.22388059701492538,
      "grad_norm": 1.3298211305507253,
      "learning_rate": 4.6455512114150546e-05,
      "loss": 0.9653,
      "step": 60
    },
    {
      "epoch": 0.24253731343283583,
      "grad_norm": 1.5188363324223721,
      "learning_rate": 4.5670111681161296e-05,
      "loss": 0.9325,
      "step": 65
    },
    {
      "epoch": 0.26119402985074625,
      "grad_norm": 1.455002995998784,
      "learning_rate": 4.481524217566783e-05,
      "loss": 0.8993,
      "step": 70
    },
    {
      "epoch": 0.2798507462686567,
      "grad_norm": 1.2015534696464851,
      "learning_rate": 4.3894171986588217e-05,
      "loss": 0.8828,
      "step": 75
    },
    {
      "epoch": 0.29850746268656714,
      "grad_norm": 2.042471802842113,
      "learning_rate": 4.29104226053073e-05,
      "loss": 0.873,
      "step": 80
    },
    {
      "epoch": 0.31716417910447764,
      "grad_norm": 1.6348429954668364,
      "learning_rate": 4.186775516209732e-05,
      "loss": 0.8589,
      "step": 85
    },
    {
      "epoch": 0.3358208955223881,
      "grad_norm": 1.2929068924137062,
      "learning_rate": 4.077015604633669e-05,
      "loss": 0.8499,
      "step": 90
    },
    {
      "epoch": 0.35447761194029853,
      "grad_norm": 1.2588102670148498,
      "learning_rate": 3.962182166550441e-05,
      "loss": 0.8296,
      "step": 95
    },
    {
      "epoch": 0.373134328358209,
      "grad_norm": 1.016824958444882,
      "learning_rate": 3.8427142401220634e-05,
      "loss": 0.8183,
      "step": 100
    },
    {
      "epoch": 0.3917910447761194,
      "grad_norm": 1.076029269402344,
      "learning_rate": 3.71906858236735e-05,
      "loss": 0.8175,
      "step": 105
    },
    {
      "epoch": 0.41044776119402987,
      "grad_norm": 0.9643240409515527,
      "learning_rate": 3.591717922860785e-05,
      "loss": 0.8024,
      "step": 110
    },
    {
      "epoch": 0.4291044776119403,
      "grad_norm": 1.0996417684236115,
      "learning_rate": 3.46114915636416e-05,
      "loss": 0.8028,
      "step": 115
    },
    {
      "epoch": 0.44776119402985076,
      "grad_norm": 0.6236520681960638,
      "learning_rate": 3.3278614813010034e-05,
      "loss": 0.7843,
      "step": 120
    },
    {
      "epoch": 0.4664179104477612,
      "grad_norm": 0.7490461585227262,
      "learning_rate": 3.1923644911909e-05,
      "loss": 0.7802,
      "step": 125
    },
    {
      "epoch": 0.48507462686567165,
      "grad_norm": 0.7753398709862848,
      "learning_rate": 3.0551762263406576e-05,
      "loss": 0.7718,
      "step": 130
    },
    {
      "epoch": 0.503731343283582,
      "grad_norm": 0.8263114166565009,
      "learning_rate": 2.9168211932412042e-05,
      "loss": 0.7694,
      "step": 135
    },
    {
      "epoch": 0.5223880597014925,
      "grad_norm": 0.5977157830288298,
      "learning_rate": 2.777828359242567e-05,
      "loss": 0.7638,
      "step": 140
    },
    {
      "epoch": 0.5410447761194029,
      "grad_norm": 0.6960446376964153,
      "learning_rate": 2.6387291301738377e-05,
      "loss": 0.7548,
      "step": 145
    },
    {
      "epoch": 0.5597014925373134,
      "grad_norm": 0.5170782529619016,
      "learning_rate": 2.50005531864019e-05,
      "loss": 0.7465,
      "step": 150
    },
    {
      "epoch": 0.5783582089552238,
      "grad_norm": 0.48159615421876123,
      "learning_rate": 2.362337110764688e-05,
      "loss": 0.7486,
      "step": 155
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 0.5432350714014745,
      "learning_rate": 2.226101039148557e-05,
      "loss": 0.741,
      "step": 160
    },
    {
      "epoch": 0.6156716417910447,
      "grad_norm": 0.4696819234168871,
      "learning_rate": 2.0918679697998252e-05,
      "loss": 0.74,
      "step": 165
    },
    {
      "epoch": 0.6343283582089553,
      "grad_norm": 0.46483548295455934,
      "learning_rate": 1.9601511107268255e-05,
      "loss": 0.7425,
      "step": 170
    },
    {
      "epoch": 0.6529850746268657,
      "grad_norm": 0.5530022968626128,
      "learning_rate": 1.8314540498102216e-05,
      "loss": 0.7338,
      "step": 175
    },
    {
      "epoch": 0.6716417910447762,
      "grad_norm": 0.4915552805413531,
      "learning_rate": 1.7062688294552992e-05,
      "loss": 0.7374,
      "step": 180
    },
    {
      "epoch": 0.6902985074626866,
      "grad_norm": 0.4452556265823543,
      "learning_rate": 1.5850740653856096e-05,
      "loss": 0.7268,
      "step": 185
    },
    {
      "epoch": 0.7089552238805971,
      "grad_norm": 0.46333067364783953,
      "learning_rate": 1.4683331167703218e-05,
      "loss": 0.7275,
      "step": 190
    },
    {
      "epoch": 0.7276119402985075,
      "grad_norm": 0.39997819847068644,
      "learning_rate": 1.356492314681356e-05,
      "loss": 0.7264,
      "step": 195
    },
    {
      "epoch": 0.746268656716418,
      "grad_norm": 0.405044297741591,
      "learning_rate": 1.2499792556533716e-05,
      "loss": 0.7238,
      "step": 200
    },
    {
      "epoch": 0.7649253731343284,
      "grad_norm": 0.42435372517376513,
      "learning_rate": 1.1492011668707753e-05,
      "loss": 0.7191,
      "step": 205
    },
    {
      "epoch": 0.7835820895522388,
      "grad_norm": 0.3991508216227003,
      "learning_rate": 1.0545433492320603e-05,
      "loss": 0.7192,
      "step": 210
    },
    {
      "epoch": 0.8022388059701493,
      "grad_norm": 0.4035129969039292,
      "learning_rate": 9.663677042440537e-06,
      "loss": 0.7175,
      "step": 215
    },
    {
      "epoch": 0.8208955223880597,
      "grad_norm": 0.3656087904784262,
      "learning_rate": 8.850113503781367e-06,
      "loss": 0.7129,
      "step": 220
    },
    {
      "epoch": 0.8395522388059702,
      "grad_norm": 0.3363321384740739,
      "learning_rate": 8.107853341784671e-06,
      "loss": 0.7197,
      "step": 225
    },
    {
      "epoch": 0.8582089552238806,
      "grad_norm": 1.564164016405774,
      "learning_rate": 7.439734410499752e-06,
      "loss": 0.716,
      "step": 230
    },
    {
      "epoch": 0.8768656716417911,
      "grad_norm": 0.38113827793929866,
      "learning_rate": 6.848311102728011e-06,
      "loss": 0.7114,
      "step": 235
    },
    {
      "epoch": 0.8955223880597015,
      "grad_norm": 0.35881991263382823,
      "learning_rate": 6.335844583913515e-06,
      "loss": 0.7117,
      "step": 240
    },
    {
      "epoch": 0.914179104477612,
      "grad_norm": 0.3389853140732799,
      "learning_rate": 5.904294147118193e-06,
      "loss": 0.7089,
      "step": 245
    },
    {
      "epoch": 0.9328358208955224,
      "grad_norm": 0.3017636686149359,
      "learning_rate": 5.555309722133842e-06,
      "loss": 0.7098,
      "step": 250
    },
    {
      "epoch": 0.9514925373134329,
      "grad_norm": 0.32612384040343395,
      "learning_rate": 5.290225567370509e-06,
      "loss": 0.7085,
      "step": 255
    },
    {
      "epoch": 0.9701492537313433,
      "grad_norm": 0.3215733932661547,
      "learning_rate": 5.110055168638854e-06,
      "loss": 0.7185,
      "step": 260
    },
    {
      "epoch": 0.9888059701492538,
      "grad_norm": 0.32235402928737444,
      "learning_rate": 5.0154873643297575e-06,
      "loss": 0.7153,
      "step": 265
    },
    {
      "epoch": 1.0,
      "step": 268,
      "total_flos": 590489283723264.0,
      "train_loss": 1.0968534403772496,
      "train_runtime": 7318.0016,
      "train_samples_per_second": 4.68,
      "train_steps_per_second": 0.037
    }
  ],
  "logging_steps": 5,
  "max_steps": 268,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 590489283723264.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}