{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 399,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012531328320802004,
      "grad_norm": 4.616424560546875,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.934977722167969,
      "step": 5
    },
    {
      "epoch": 0.02506265664160401,
      "grad_norm": 0.9663957357406616,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.6157804489135743,
      "step": 10
    },
    {
      "epoch": 0.03759398496240601,
      "grad_norm": 0.8866068124771118,
      "learning_rate": 9.999341026006419e-05,
      "loss": 2.3903940200805662,
      "step": 15
    },
    {
      "epoch": 0.05012531328320802,
      "grad_norm": 0.592215895652771,
      "learning_rate": 9.991929563254914e-05,
      "loss": 2.2077911376953123,
      "step": 20
    },
    {
      "epoch": 0.06265664160401002,
      "grad_norm": 0.7318651676177979,
      "learning_rate": 9.976295169466178e-05,
      "loss": 2.1383132934570312,
      "step": 25
    },
    {
      "epoch": 0.07518796992481203,
      "grad_norm": 0.487021803855896,
      "learning_rate": 9.952463598317285e-05,
      "loss": 2.086687469482422,
      "step": 30
    },
    {
      "epoch": 0.08771929824561403,
      "grad_norm": 0.42140164971351624,
      "learning_rate": 9.920474106244763e-05,
      "loss": 1.91082763671875,
      "step": 35
    },
    {
      "epoch": 0.10025062656641603,
      "grad_norm": 0.3986339569091797,
      "learning_rate": 9.880379387779637e-05,
      "loss": 1.8581930160522462,
      "step": 40
    },
    {
      "epoch": 0.11278195488721804,
      "grad_norm": 0.3607427477836609,
      "learning_rate": 9.832245488746611e-05,
      "loss": 1.8432674407958984,
      "step": 45
    },
    {
      "epoch": 0.12531328320802004,
      "grad_norm": 0.36158058047294617,
      "learning_rate": 9.77615169747043e-05,
      "loss": 1.7825313568115235,
      "step": 50
    },
    {
      "epoch": 0.13784461152882205,
      "grad_norm": 0.48840442299842834,
      "learning_rate": 9.712190414168572e-05,
      "loss": 1.7588272094726562,
      "step": 55
    },
    {
      "epoch": 0.15037593984962405,
      "grad_norm": 0.4558253288269043,
      "learning_rate": 9.640466998745456e-05,
      "loss": 1.7384506225585938,
      "step": 60
    },
    {
      "epoch": 0.16290726817042606,
      "grad_norm": 0.4790010154247284,
      "learning_rate": 9.56109959723886e-05,
      "loss": 1.773073959350586,
      "step": 65
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 0.43606677651405334,
      "learning_rate": 9.474218947204459e-05,
      "loss": 1.701727294921875,
      "step": 70
    },
    {
      "epoch": 0.18796992481203006,
      "grad_norm": 0.41107335686683655,
      "learning_rate": 9.379968162359034e-05,
      "loss": 1.6692758560180665,
      "step": 75
    },
    {
      "epoch": 0.20050125313283207,
      "grad_norm": 0.49184519052505493,
      "learning_rate": 9.278502496837116e-05,
      "loss": 1.65777530670166,
      "step": 80
    },
    {
      "epoch": 0.21303258145363407,
      "grad_norm": 0.4494943618774414,
      "learning_rate": 9.16998908944939e-05,
      "loss": 1.642690658569336,
      "step": 85
    },
    {
      "epoch": 0.22556390977443608,
      "grad_norm": 0.4311301112174988,
      "learning_rate": 9.05460668836413e-05,
      "loss": 1.644818115234375,
      "step": 90
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 0.4352401793003082,
      "learning_rate": 8.932545356665157e-05,
      "loss": 1.6862640380859375,
      "step": 95
    },
    {
      "epoch": 0.2506265664160401,
      "grad_norm": 0.5165485739707947,
      "learning_rate": 8.80400615927139e-05,
      "loss": 1.6043413162231446,
      "step": 100
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 0.5238773226737976,
      "learning_rate": 8.669200831733655e-05,
      "loss": 1.6020179748535157,
      "step": 105
    },
    {
      "epoch": 0.2756892230576441,
      "grad_norm": 0.48641711473464966,
      "learning_rate": 8.528351431454351e-05,
      "loss": 1.667029571533203,
      "step": 110
    },
    {
      "epoch": 0.2882205513784461,
      "grad_norm": 0.4841844141483307,
      "learning_rate": 8.381689971904514e-05,
      "loss": 1.581167984008789,
      "step": 115
    },
    {
      "epoch": 0.3007518796992481,
      "grad_norm": 0.5289077162742615,
      "learning_rate": 8.229458040440783e-05,
      "loss": 1.5388771057128907,
      "step": 120
    },
    {
      "epoch": 0.3132832080200501,
      "grad_norm": 0.5193697810173035,
      "learning_rate": 8.071906400351822e-05,
      "loss": 1.6895849227905273,
      "step": 125
    },
    {
      "epoch": 0.3258145363408521,
      "grad_norm": 0.5744988918304443,
      "learning_rate": 7.909294577789766e-05,
      "loss": 1.588879680633545,
      "step": 130
    },
    {
      "epoch": 0.3383458646616541,
      "grad_norm": 0.5400910973548889,
      "learning_rate": 7.741890434267043e-05,
      "loss": 1.5413589477539062,
      "step": 135
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 0.5330870747566223,
      "learning_rate": 7.56996972542285e-05,
      "loss": 1.5666592597961426,
      "step": 140
    },
    {
      "epoch": 0.3634085213032581,
      "grad_norm": 0.48990681767463684,
      "learning_rate": 7.393815646786046e-05,
      "loss": 1.5437944412231446,
      "step": 145
    },
    {
      "epoch": 0.37593984962406013,
      "grad_norm": 0.5819255709648132,
      "learning_rate": 7.213718367282737e-05,
      "loss": 1.5589888572692872,
      "step": 150
    },
    {
      "epoch": 0.38847117794486213,
      "grad_norm": 0.543954074382782,
      "learning_rate": 7.029974551256956e-05,
      "loss": 1.549081516265869,
      "step": 155
    },
    {
      "epoch": 0.40100250626566414,
      "grad_norm": 0.49433743953704834,
      "learning_rate": 6.842886869791809e-05,
      "loss": 1.647486114501953,
      "step": 160
    },
    {
      "epoch": 0.41353383458646614,
      "grad_norm": 0.7563313841819763,
      "learning_rate": 6.652763502136043e-05,
      "loss": 1.5014152526855469,
      "step": 165
    },
    {
      "epoch": 0.42606516290726815,
      "grad_norm": 0.5794914364814758,
      "learning_rate": 6.45991762805732e-05,
      "loss": 1.5561296463012695,
      "step": 170
    },
    {
      "epoch": 0.43859649122807015,
      "grad_norm": 0.5829029083251953,
      "learning_rate": 6.264666911958404e-05,
      "loss": 1.489358139038086,
      "step": 175
    },
    {
      "epoch": 0.45112781954887216,
      "grad_norm": 0.6162887215614319,
      "learning_rate": 6.0673329796060686e-05,
      "loss": 1.657431411743164,
      "step": 180
    },
    {
      "epoch": 0.46365914786967416,
      "grad_norm": 0.5041324496269226,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.5830360412597657,
      "step": 185
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.44108399748802185,
      "learning_rate": 5.66771859159699e-05,
      "loss": 1.5609025001525878,
      "step": 190
    },
    {
      "epoch": 0.48872180451127817,
      "grad_norm": 0.6012187004089355,
      "learning_rate": 5.46609639874473e-05,
      "loss": 1.5093048095703125,
      "step": 195
    },
    {
      "epoch": 0.5012531328320802,
      "grad_norm": 0.5483066439628601,
      "learning_rate": 5.263706430927895e-05,
      "loss": 1.509588623046875,
      "step": 200
    },
    {
      "epoch": 0.5137844611528822,
      "grad_norm": 0.5817646980285645,
      "learning_rate": 5.060882074009988e-05,
      "loss": 1.4990989685058593,
      "step": 205
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.5909322500228882,
      "learning_rate": 4.857957429399788e-05,
      "loss": 1.4792702674865723,
      "step": 210
    },
    {
      "epoch": 0.5388471177944862,
      "grad_norm": 0.4901309907436371,
      "learning_rate": 4.655266763704476e-05,
      "loss": 1.5089725494384765,
      "step": 215
    },
    {
      "epoch": 0.5513784461152882,
      "grad_norm": 0.5499526858329773,
      "learning_rate": 4.4531439581106295e-05,
      "loss": 1.4816458702087403,
      "step": 220
    },
    {
      "epoch": 0.5639097744360902,
      "grad_norm": 0.5426397919654846,
      "learning_rate": 4.25192195840011e-05,
      "loss": 1.4949656486511231,
      "step": 225
    },
    {
      "epoch": 0.5764411027568922,
      "grad_norm": 0.6726823449134827,
      "learning_rate": 4.051932226506797e-05,
      "loss": 1.473857307434082,
      "step": 230
    },
    {
      "epoch": 0.5889724310776943,
      "grad_norm": 0.4919537901878357,
      "learning_rate": 3.8535041945175506e-05,
      "loss": 1.476518726348877,
      "step": 235
    },
    {
      "epoch": 0.6015037593984962,
      "grad_norm": 0.6418251991271973,
      "learning_rate": 3.656964722016875e-05,
      "loss": 1.5176348686218262,
      "step": 240
    },
    {
      "epoch": 0.6140350877192983,
      "grad_norm": 0.7057491540908813,
      "learning_rate": 3.462637557669084e-05,
      "loss": 1.4741716384887695,
      "step": 245
    },
    {
      "epoch": 0.6265664160401002,
      "grad_norm": 0.5438081622123718,
      "learning_rate": 3.2708428059249436e-05,
      "loss": 1.4777631759643555,
      "step": 250
    },
    {
      "epoch": 0.6390977443609023,
      "grad_norm": 0.6389463543891907,
      "learning_rate": 3.081896399731202e-05,
      "loss": 1.4393177032470703,
      "step": 255
    },
    {
      "epoch": 0.6516290726817042,
      "grad_norm": 0.5171266198158264,
      "learning_rate": 2.896109580111634e-05,
      "loss": 1.4910090446472168,
      "step": 260
    },
    {
      "epoch": 0.6641604010025063,
      "grad_norm": 0.503493070602417,
      "learning_rate": 2.7137883834768073e-05,
      "loss": 1.5207834243774414,
      "step": 265
    },
    {
      "epoch": 0.6766917293233082,
      "grad_norm": 0.5760393738746643,
      "learning_rate": 2.5352331375071437e-05,
      "loss": 1.4389854431152345,
      "step": 270
    },
    {
      "epoch": 0.6892230576441103,
      "grad_norm": 0.5519845485687256,
      "learning_rate": 2.360737966439641e-05,
      "loss": 1.5199569702148437,
      "step": 275
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 0.47045156359672546,
      "learning_rate": 2.1905903065731974e-05,
      "loss": 1.5139789581298828,
      "step": 280
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.5225965976715088,
      "learning_rate": 2.0250704327906024e-05,
      "loss": 1.4618739128112792,
      "step": 285
    },
    {
      "epoch": 0.7268170426065163,
      "grad_norm": 0.6951541900634766,
      "learning_rate": 1.86445099687713e-05,
      "loss": 1.4188865661621093,
      "step": 290
    },
    {
      "epoch": 0.7393483709273183,
      "grad_norm": 0.5570498108863831,
      "learning_rate": 1.7089965783962608e-05,
      "loss": 1.4332854270935058,
      "step": 295
    },
    {
      "epoch": 0.7518796992481203,
      "grad_norm": 0.6068281531333923,
      "learning_rate": 1.5589632488623053e-05,
      "loss": 1.4512317657470704,
      "step": 300
    },
    {
      "epoch": 0.7644110275689223,
      "grad_norm": 0.6222130656242371,
      "learning_rate": 1.4145981499278876e-05,
      "loss": 1.426743507385254,
      "step": 305
    },
    {
      "epoch": 0.7769423558897243,
      "grad_norm": 0.5513938069343567,
      "learning_rate": 1.2761390862810907e-05,
      "loss": 1.4764443397521974,
      "step": 310
    },
    {
      "epoch": 0.7894736842105263,
      "grad_norm": 0.4660240709781647,
      "learning_rate": 1.143814133922872e-05,
      "loss": 1.4647582054138184,
      "step": 315
    },
    {
      "epoch": 0.8020050125313283,
      "grad_norm": 0.5222885012626648,
      "learning_rate": 1.0178412644700092e-05,
      "loss": 1.540810489654541,
      "step": 320
    },
    {
      "epoch": 0.8145363408521303,
      "grad_norm": 0.5397015810012817,
      "learning_rate": 8.984279861024453e-06,
      "loss": 1.5305503845214843,
      "step": 325
    },
    {
      "epoch": 0.8270676691729323,
      "grad_norm": 0.6163002848625183,
      "learning_rate": 7.857710017464737e-06,
      "loss": 1.5169111251831056,
      "step": 330
    },
    {
      "epoch": 0.8395989974937343,
      "grad_norm": 0.5306107997894287,
      "learning_rate": 6.800558850568295e-06,
      "loss": 1.5120708465576171,
      "step": 335
    },
    {
      "epoch": 0.8521303258145363,
      "grad_norm": 0.6487607359886169,
      "learning_rate": 5.814567747314048e-06,
      "loss": 1.4791044235229491,
      "step": 340
    },
    {
      "epoch": 0.8646616541353384,
      "grad_norm": 0.49410057067871094,
      "learning_rate": 4.901360876621597e-06,
      "loss": 1.5121532440185548,
      "step": 345
    },
    {
      "epoch": 0.8771929824561403,
      "grad_norm": 0.7189502716064453,
      "learning_rate": 4.062442513947007e-06,
      "loss": 1.4464287757873535,
      "step": 350
    },
    {
      "epoch": 0.8897243107769424,
      "grad_norm": 0.5118407607078552,
      "learning_rate": 3.299194563372604e-06,
      "loss": 1.4606318473815918,
      "step": 355
    },
    {
      "epoch": 0.9022556390977443,
      "grad_norm": 0.7187556624412537,
      "learning_rate": 2.6128742812723704e-06,
      "loss": 1.4171567916870118,
      "step": 360
    },
    {
      "epoch": 0.9147869674185464,
      "grad_norm": 0.5013515949249268,
      "learning_rate": 2.0046122053026694e-06,
      "loss": 1.4973943710327149,
      "step": 365
    },
    {
      "epoch": 0.9273182957393483,
      "grad_norm": 0.5586349368095398,
      "learning_rate": 1.4754102921297364e-06,
      "loss": 1.441578483581543,
      "step": 370
    },
    {
      "epoch": 0.9398496240601504,
      "grad_norm": 0.538459300994873,
      "learning_rate": 1.0261402669615505e-06,
      "loss": 1.4135071754455566,
      "step": 375
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.5685633420944214,
      "learning_rate": 6.57542187602872e-07,
      "loss": 1.547743797302246,
      "step": 380
    },
    {
      "epoch": 0.9649122807017544,
      "grad_norm": 0.4842998683452606,
      "learning_rate": 3.702232253986804e-07,
      "loss": 1.4555327415466308,
      "step": 385
    },
    {
      "epoch": 0.9774436090225563,
      "grad_norm": 0.4818095266819,
      "learning_rate": 1.6465666507425315e-07,
      "loss": 1.4351191520690918,
      "step": 390
    },
    {
      "epoch": 0.9899749373433584,
      "grad_norm": 0.5525173544883728,
      "learning_rate": 4.1181125119221787e-08,
      "loss": 1.523050022125244,
      "step": 395
    }
  ],
  "logging_steps": 5,
  "max_steps": 399,
  "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": 1.94892544964821e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}