{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9962406015037594,
  "eval_steps": 500,
  "global_step": 265,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018796992481203006,
      "grad_norm": 0.8913070559501648,
      "learning_rate": 2.162496240601504e-06,
      "loss": 0.1157,
      "mean_token_accuracy": 0.9578125059604645,
      "num_tokens": 1094126.0,
      "step": 5
    },
    {
      "epoch": 0.03759398496240601,
      "grad_norm": 0.539890706539154,
      "learning_rate": 4.865616541353383e-06,
      "loss": 0.1052,
      "mean_token_accuracy": 0.9611979275941849,
      "num_tokens": 2180906.0,
      "step": 10
    },
    {
      "epoch": 0.05639097744360902,
      "grad_norm": 0.6225920915603638,
      "learning_rate": 7.568736842105265e-06,
      "loss": 0.0973,
      "mean_token_accuracy": 0.9657118082046509,
      "num_tokens": 3277544.0,
      "step": 15
    },
    {
      "epoch": 0.07518796992481203,
      "grad_norm": 0.5330905318260193,
      "learning_rate": 1.0271857142857143e-05,
      "loss": 0.0899,
      "mean_token_accuracy": 0.966232642531395,
      "num_tokens": 4357967.0,
      "step": 20
    },
    {
      "epoch": 0.09398496240601503,
      "grad_norm": 0.6511453986167908,
      "learning_rate": 1.2974977443609024e-05,
      "loss": 0.0884,
      "mean_token_accuracy": 0.9683159798383713,
      "num_tokens": 5440817.0,
      "step": 25
    },
    {
      "epoch": 0.11278195488721804,
      "grad_norm": 0.5497301816940308,
      "learning_rate": 1.5678097744360906e-05,
      "loss": 0.0801,
      "mean_token_accuracy": 0.9699652880430222,
      "num_tokens": 6519852.0,
      "step": 30
    },
    {
      "epoch": 0.13157894736842105,
      "grad_norm": 0.45359334349632263,
      "learning_rate": 1.8381218045112784e-05,
      "loss": 0.0823,
      "mean_token_accuracy": 0.9693576544523239,
      "num_tokens": 7608898.0,
      "step": 35
    },
    {
      "epoch": 0.15037593984962405,
      "grad_norm": 0.6279494762420654,
      "learning_rate": 1.8911253940180176e-05,
      "loss": 0.0772,
      "mean_token_accuracy": 0.972482654452324,
      "num_tokens": 8705080.0,
      "step": 40
    },
    {
      "epoch": 0.16917293233082706,
      "grad_norm": 0.5761957764625549,
      "learning_rate": 1.88682936707162e-05,
      "loss": 0.0718,
      "mean_token_accuracy": 0.9738715320825577,
      "num_tokens": 9799167.0,
      "step": 45
    },
    {
      "epoch": 0.18796992481203006,
      "grad_norm": 0.5918647050857544,
      "learning_rate": 1.8792499682807395e-05,
      "loss": 0.0744,
      "mean_token_accuracy": 0.9723958432674408,
      "num_tokens": 10884528.0,
      "step": 50
    },
    {
      "epoch": 0.20676691729323307,
      "grad_norm": 0.4599367082118988,
      "learning_rate": 1.868422536301333e-05,
      "loss": 0.0714,
      "mean_token_accuracy": 0.9723090320825577,
      "num_tokens": 11979898.0,
      "step": 55
    },
    {
      "epoch": 0.22556390977443608,
      "grad_norm": 0.3332800567150116,
      "learning_rate": 1.854397553619436e-05,
      "loss": 0.0706,
      "mean_token_accuracy": 0.97421875,
      "num_tokens": 13068980.0,
      "step": 60
    },
    {
      "epoch": 0.24436090225563908,
      "grad_norm": 0.3522525131702423,
      "learning_rate": 1.837240411178509e-05,
      "loss": 0.0735,
      "mean_token_accuracy": 0.9730034738779068,
      "num_tokens": 14160224.0,
      "step": 65
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 0.4098234474658966,
      "learning_rate": 1.8170311034966734e-05,
      "loss": 0.072,
      "mean_token_accuracy": 0.9725694507360458,
      "num_tokens": 15252034.0,
      "step": 70
    },
    {
      "epoch": 0.2819548872180451,
      "grad_norm": 0.4282197058200836,
      "learning_rate": 1.7938638556953408e-05,
      "loss": 0.0714,
      "mean_token_accuracy": 0.9732638895511627,
      "num_tokens": 16344130.0,
      "step": 75
    },
    {
      "epoch": 0.3007518796992481,
      "grad_norm": 0.4061741828918457,
      "learning_rate": 1.7678466841782004e-05,
      "loss": 0.0679,
      "mean_token_accuracy": 0.9733507066965104,
      "num_tokens": 17428357.0,
      "step": 80
    },
    {
      "epoch": 0.31954887218045114,
      "grad_norm": 0.5221928358078003,
      "learning_rate": 1.7391008930088843e-05,
      "loss": 0.0709,
      "mean_token_accuracy": 0.9722222268581391,
      "num_tokens": 18517758.0,
      "step": 85
    },
    {
      "epoch": 0.3383458646616541,
      "grad_norm": 0.3468131124973297,
      "learning_rate": 1.7077605083354247e-05,
      "loss": 0.069,
      "mean_token_accuracy": 0.9737847357988357,
      "num_tokens": 19600212.0,
      "step": 90
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.3492281436920166,
      "learning_rate": 1.6739716534984836e-05,
      "loss": 0.0681,
      "mean_token_accuracy": 0.9741319507360459,
      "num_tokens": 20687674.0,
      "step": 95
    },
    {
      "epoch": 0.37593984962406013,
      "grad_norm": 0.32158297300338745,
      "learning_rate": 1.637891867736886e-05,
      "loss": 0.0698,
      "mean_token_accuracy": 0.9731770902872086,
      "num_tokens": 21761517.0,
      "step": 100
    },
    {
      "epoch": 0.39473684210526316,
      "grad_norm": 0.3257518708705902,
      "learning_rate": 1.5996893716669644e-05,
      "loss": 0.0691,
      "mean_token_accuracy": 0.9726562470197677,
      "num_tokens": 22839370.0,
      "step": 105
    },
    {
      "epoch": 0.41353383458646614,
      "grad_norm": 0.43623876571655273,
      "learning_rate": 1.5595422829603913e-05,
      "loss": 0.0674,
      "mean_token_accuracy": 0.9750000089406967,
      "num_tokens": 23929717.0,
      "step": 110
    },
    {
      "epoch": 0.4323308270676692,
      "grad_norm": 0.47612956166267395,
      "learning_rate": 1.5176377858773726e-05,
      "loss": 0.0662,
      "mean_token_accuracy": 0.9756076484918594,
      "num_tokens": 25030158.0,
      "step": 115
    },
    {
      "epoch": 0.45112781954887216,
      "grad_norm": 0.3309917747974396,
      "learning_rate": 1.4741712585272186e-05,
      "loss": 0.0669,
      "mean_token_accuracy": 0.9744791835546494,
      "num_tokens": 26097086.0,
      "step": 120
    },
    {
      "epoch": 0.4699248120300752,
      "grad_norm": 0.2843182682991028,
      "learning_rate": 1.429345361925407e-05,
      "loss": 0.0664,
      "mean_token_accuracy": 0.9760416746139526,
      "num_tokens": 27200174.0,
      "step": 125
    },
    {
      "epoch": 0.48872180451127817,
      "grad_norm": 0.39493700861930847,
      "learning_rate": 1.3833690950943765e-05,
      "loss": 0.0665,
      "mean_token_accuracy": 0.9750868201255798,
      "num_tokens": 28294110.0,
      "step": 130
    },
    {
      "epoch": 0.5075187969924813,
      "grad_norm": 0.30301254987716675,
      "learning_rate": 1.3364568206136098e-05,
      "loss": 0.0649,
      "mean_token_accuracy": 0.9734375149011611,
      "num_tokens": 29380607.0,
      "step": 135
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.22746075689792633,
      "learning_rate": 1.2888272651623283e-05,
      "loss": 0.0652,
      "mean_token_accuracy": 0.9748263955116272,
      "num_tokens": 30469885.0,
      "step": 140
    },
    {
      "epoch": 0.5451127819548872,
      "grad_norm": 0.2289746105670929,
      "learning_rate": 1.2407024997147512e-05,
      "loss": 0.0676,
      "mean_token_accuracy": 0.9730034828186035,
      "num_tokens": 31552370.0,
      "step": 145
    },
    {
      "epoch": 0.5639097744360902,
      "grad_norm": 0.264146625995636,
      "learning_rate": 1.192306904142696e-05,
      "loss": 0.0649,
      "mean_token_accuracy": 0.9747395932674408,
      "num_tokens": 32632929.0,
      "step": 150
    },
    {
      "epoch": 0.5827067669172933,
      "grad_norm": 0.3296896815299988,
      "learning_rate": 1.1438661210530435e-05,
      "loss": 0.066,
      "mean_token_accuracy": 0.9733507096767425,
      "num_tokens": 33722959.0,
      "step": 155
    },
    {
      "epoch": 0.6015037593984962,
      "grad_norm": 0.28742000460624695,
      "learning_rate": 1.0956060037377391e-05,
      "loss": 0.0635,
      "mean_token_accuracy": 0.9750868171453476,
      "num_tokens": 34807784.0,
      "step": 160
    },
    {
      "epoch": 0.6203007518796992,
      "grad_norm": 0.2558082938194275,
      "learning_rate": 1.0477515631414902e-05,
      "loss": 0.0645,
      "mean_token_accuracy": 0.9738715440034866,
      "num_tokens": 35906877.0,
      "step": 165
    },
    {
      "epoch": 0.6390977443609023,
      "grad_norm": 0.3014199435710907,
      "learning_rate": 1.0005259187568716e-05,
      "loss": 0.067,
      "mean_token_accuracy": 0.9740451484918594,
      "num_tokens": 36996802.0,
      "step": 170
    },
    {
      "epoch": 0.6578947368421053,
      "grad_norm": 0.32616809010505676,
      "learning_rate": 9.541492583382556e-06,
      "loss": 0.07,
      "mean_token_accuracy": 0.9730034738779068,
      "num_tokens": 38080245.0,
      "step": 175
    },
    {
      "epoch": 0.6766917293233082,
      "grad_norm": 0.24906273186206818,
      "learning_rate": 9.088378112848576e-06,
      "loss": 0.0638,
      "mean_token_accuracy": 0.9751736253499985,
      "num_tokens": 39167397.0,
      "step": 180
    },
    {
      "epoch": 0.6954887218045113,
      "grad_norm": 0.3311786949634552,
      "learning_rate": 8.648028404794624e-06,
      "loss": 0.0593,
      "mean_token_accuracy": 0.9757812678813934,
      "num_tokens": 40252792.0,
      "step": 185
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.24213548004627228,
      "learning_rate": 8.222496572833397e-06,
      "loss": 0.062,
      "mean_token_accuracy": 0.9757812649011612,
      "num_tokens": 41329232.0,
      "step": 190
    },
    {
      "epoch": 0.7330827067669173,
      "grad_norm": 0.2773512601852417,
      "learning_rate": 7.813766642799051e-06,
      "loss": 0.0614,
      "mean_token_accuracy": 0.9768229246139526,
      "num_tokens": 42421662.0,
      "step": 195
    },
    {
      "epoch": 0.7518796992481203,
      "grad_norm": 0.3418289124965668,
      "learning_rate": 7.42374430230287e-06,
      "loss": 0.062,
      "mean_token_accuracy": 0.9759548664093017,
      "num_tokens": 43505109.0,
      "step": 200
    },
    {
      "epoch": 0.7706766917293233,
      "grad_norm": 0.4662540555000305,
      "learning_rate": 7.0542480155379425e-06,
      "loss": 0.0631,
      "mean_token_accuracy": 0.975347226858139,
      "num_tokens": 44594339.0,
      "step": 205
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 0.2698640823364258,
      "learning_rate": 6.707000544759643e-06,
      "loss": 0.0603,
      "mean_token_accuracy": 0.9757812738418579,
      "num_tokens": 45682459.0,
      "step": 210
    },
    {
      "epoch": 0.8082706766917294,
      "grad_norm": 0.3404809236526489,
      "learning_rate": 6.383620917972744e-06,
      "loss": 0.062,
      "mean_token_accuracy": 0.9758680582046508,
      "num_tokens": 46778973.0,
      "step": 215
    },
    {
      "epoch": 0.8270676691729323,
      "grad_norm": 0.4449962377548218,
      "learning_rate": 6.085616880275477e-06,
      "loss": 0.0606,
      "mean_token_accuracy": 0.9747395992279053,
      "num_tokens": 47875425.0,
      "step": 220
    },
    {
      "epoch": 0.8458646616541353,
      "grad_norm": 0.38036465644836426,
      "learning_rate": 5.814377864055892e-06,
      "loss": 0.0651,
      "mean_token_accuracy": 0.9736111253499985,
      "num_tokens": 48960695.0,
      "step": 225
    },
    {
      "epoch": 0.8646616541353384,
      "grad_norm": 0.36274492740631104,
      "learning_rate": 5.571168510816669e-06,
      "loss": 0.0633,
      "mean_token_accuracy": 0.9746527761220932,
      "num_tokens": 50052087.0,
      "step": 230
    },
    {
      "epoch": 0.8834586466165414,
      "grad_norm": 0.26603877544403076,
      "learning_rate": 5.357122774832645e-06,
      "loss": 0.0631,
      "mean_token_accuracy": 0.9753472328186035,
      "num_tokens": 51130056.0,
      "step": 235
    },
    {
      "epoch": 0.9022556390977443,
      "grad_norm": 0.2719307541847229,
      "learning_rate": 5.173238636132541e-06,
      "loss": 0.0578,
      "mean_token_accuracy": 0.977170142531395,
      "num_tokens": 52221506.0,
      "step": 240
    },
    {
      "epoch": 0.9210526315789473,
      "grad_norm": 0.47163859009742737,
      "learning_rate": 5.0203734474553736e-06,
      "loss": 0.0617,
      "mean_token_accuracy": 0.9761284768581391,
      "num_tokens": 53311285.0,
      "step": 245
    },
    {
      "epoch": 0.9398496240601504,
      "grad_norm": 0.3558019697666168,
      "learning_rate": 4.899239936876221e-06,
      "loss": 0.0619,
      "mean_token_accuracy": 0.9756076365709305,
      "num_tokens": 54395430.0,
      "step": 250
    },
    {
      "epoch": 0.9586466165413534,
      "grad_norm": 0.2686137557029724,
      "learning_rate": 4.810402884738922e-06,
      "loss": 0.0652,
      "mean_token_accuracy": 0.9745659828186035,
      "num_tokens": 55478594.0,
      "step": 255
    },
    {
      "epoch": 0.9774436090225563,
      "grad_norm": 0.2539461851119995,
      "learning_rate": 4.754276490389406e-06,
      "loss": 0.0616,
      "mean_token_accuracy": 0.9756944477558136,
      "num_tokens": 56563588.0,
      "step": 260
    },
    {
      "epoch": 0.9962406015037594,
      "grad_norm": 0.32729315757751465,
      "learning_rate": 4.731122440987136e-06,
      "loss": 0.0588,
      "mean_token_accuracy": 0.9761284828186035,
      "num_tokens": 57656747.0,
      "step": 265
    }
  ],
  "logging_steps": 5,
  "max_steps": 265,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.499800954943832e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}