{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9936575052854124,
  "eval_steps": 500,
  "global_step": 354,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.042283298097251586,
      "grad_norm": 1.2008394002914429,
      "learning_rate": 4.9975392245612254e-05,
      "loss": 4.1473,
      "num_input_tokens_seen": 68384,
      "step": 5
    },
    {
      "epoch": 0.08456659619450317,
      "grad_norm": 1.1565380096435547,
      "learning_rate": 4.9901617425775067e-05,
      "loss": 4.021,
      "num_input_tokens_seen": 128224,
      "step": 10
    },
    {
      "epoch": 0.12684989429175475,
      "grad_norm": 0.972896158695221,
      "learning_rate": 4.9778820775100185e-05,
      "loss": 3.8212,
      "num_input_tokens_seen": 197760,
      "step": 15
    },
    {
      "epoch": 0.16913319238900634,
      "grad_norm": 1.0641047954559326,
      "learning_rate": 4.9607244033573156e-05,
      "loss": 3.7653,
      "num_input_tokens_seen": 262832,
      "step": 20
    },
    {
      "epoch": 0.21141649048625794,
      "grad_norm": 1.0994701385498047,
      "learning_rate": 4.93872249706591e-05,
      "loss": 3.7434,
      "num_input_tokens_seen": 333472,
      "step": 25
    },
    {
      "epoch": 0.2536997885835095,
      "grad_norm": 1.193864107131958,
      "learning_rate": 4.91191967203629e-05,
      "loss": 3.5488,
      "num_input_tokens_seen": 393616,
      "step": 30
    },
    {
      "epoch": 0.2959830866807611,
      "grad_norm": 1.0215297937393188,
      "learning_rate": 4.8803686928552736e-05,
      "loss": 3.5732,
      "num_input_tokens_seen": 458240,
      "step": 35
    },
    {
      "epoch": 0.3382663847780127,
      "grad_norm": 1.312198519706726,
      "learning_rate": 4.84413167142257e-05,
      "loss": 3.7108,
      "num_input_tokens_seen": 524576,
      "step": 40
    },
    {
      "epoch": 0.38054968287526425,
      "grad_norm": 1.3579617738723755,
      "learning_rate": 4.803279944676032e-05,
      "loss": 3.6871,
      "num_input_tokens_seen": 591856,
      "step": 45
    },
    {
      "epoch": 0.42283298097251587,
      "grad_norm": 1.4524191617965698,
      "learning_rate": 4.7578939341563095e-05,
      "loss": 3.286,
      "num_input_tokens_seen": 655648,
      "step": 50
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 1.248831033706665,
      "learning_rate": 4.70806298768736e-05,
      "loss": 3.5377,
      "num_input_tokens_seen": 721280,
      "step": 55
    },
    {
      "epoch": 0.507399577167019,
      "grad_norm": 1.2427473068237305,
      "learning_rate": 4.653885203484515e-05,
      "loss": 3.56,
      "num_input_tokens_seen": 784688,
      "step": 60
    },
    {
      "epoch": 0.5496828752642706,
      "grad_norm": 1.323653221130371,
      "learning_rate": 4.595467237036329e-05,
      "loss": 3.4937,
      "num_input_tokens_seen": 850848,
      "step": 65
    },
    {
      "epoch": 0.5919661733615222,
      "grad_norm": 1.3730229139328003,
      "learning_rate": 4.532924091140417e-05,
      "loss": 3.3823,
      "num_input_tokens_seen": 912480,
      "step": 70
    },
    {
      "epoch": 0.6342494714587738,
      "grad_norm": 1.5328903198242188,
      "learning_rate": 4.466378889506607e-05,
      "loss": 3.3798,
      "num_input_tokens_seen": 978448,
      "step": 75
    },
    {
      "epoch": 0.6765327695560254,
      "grad_norm": 1.4153543710708618,
      "learning_rate": 4.395962634373097e-05,
      "loss": 3.3044,
      "num_input_tokens_seen": 1041280,
      "step": 80
    },
    {
      "epoch": 0.718816067653277,
      "grad_norm": 1.6301600933074951,
      "learning_rate": 4.3218139486127854e-05,
      "loss": 3.3661,
      "num_input_tokens_seen": 1102224,
      "step": 85
    },
    {
      "epoch": 0.7610993657505285,
      "grad_norm": 1.6634522676467896,
      "learning_rate": 4.2440788028374624e-05,
      "loss": 3.3829,
      "num_input_tokens_seen": 1166576,
      "step": 90
    },
    {
      "epoch": 0.8033826638477801,
      "grad_norm": 1.4539167881011963,
      "learning_rate": 4.1629102280370904e-05,
      "loss": 3.2241,
      "num_input_tokens_seen": 1230096,
      "step": 95
    },
    {
      "epoch": 0.8456659619450317,
      "grad_norm": 1.453364372253418,
      "learning_rate": 4.0784680143198836e-05,
      "loss": 3.0931,
      "num_input_tokens_seen": 1297968,
      "step": 100
    },
    {
      "epoch": 0.8879492600422833,
      "grad_norm": 2.0559964179992676,
      "learning_rate": 3.990918396346254e-05,
      "loss": 3.3581,
      "num_input_tokens_seen": 1361760,
      "step": 105
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 2.0426218509674072,
      "learning_rate": 3.900433726075865e-05,
      "loss": 3.2308,
      "num_input_tokens_seen": 1422096,
      "step": 110
    },
    {
      "epoch": 0.9725158562367865,
      "grad_norm": 1.7696195840835571,
      "learning_rate": 3.8071921334720696e-05,
      "loss": 3.1427,
      "num_input_tokens_seen": 1491120,
      "step": 115
    },
    {
      "epoch": 1.014799154334038,
      "grad_norm": 2.3205981254577637,
      "learning_rate": 3.711377175831626e-05,
      "loss": 3.0988,
      "num_input_tokens_seen": 1556440,
      "step": 120
    },
    {
      "epoch": 1.0570824524312896,
      "grad_norm": 1.7631757259368896,
      "learning_rate": 3.613177476430079e-05,
      "loss": 3.0695,
      "num_input_tokens_seen": 1624200,
      "step": 125
    },
    {
      "epoch": 1.0993657505285412,
      "grad_norm": 2.32861328125,
      "learning_rate": 3.512786353194134e-05,
      "loss": 3.1109,
      "num_input_tokens_seen": 1686600,
      "step": 130
    },
    {
      "epoch": 1.1416490486257929,
      "grad_norm": 2.1291067600250244,
      "learning_rate": 3.410401438132056e-05,
      "loss": 3.116,
      "num_input_tokens_seen": 1755144,
      "step": 135
    },
    {
      "epoch": 1.1839323467230445,
      "grad_norm": 1.8158444166183472,
      "learning_rate": 3.3062242882712724e-05,
      "loss": 2.9528,
      "num_input_tokens_seen": 1819672,
      "step": 140
    },
    {
      "epoch": 1.226215644820296,
      "grad_norm": 2.161515951156616,
      "learning_rate": 3.200459988869111e-05,
      "loss": 2.8494,
      "num_input_tokens_seen": 1886136,
      "step": 145
    },
    {
      "epoch": 1.2684989429175475,
      "grad_norm": 2.321112632751465,
      "learning_rate": 3.093316749677788e-05,
      "loss": 3.1525,
      "num_input_tokens_seen": 1947656,
      "step": 150
    },
    {
      "epoch": 1.3107822410147991,
      "grad_norm": 2.4329445362091064,
      "learning_rate": 2.985005495058446e-05,
      "loss": 2.8991,
      "num_input_tokens_seen": 2013272,
      "step": 155
    },
    {
      "epoch": 1.3530655391120507,
      "grad_norm": 2.7929720878601074,
      "learning_rate": 2.875739448751176e-05,
      "loss": 3.026,
      "num_input_tokens_seen": 2079816,
      "step": 160
    },
    {
      "epoch": 1.3953488372093024,
      "grad_norm": 2.6059908866882324,
      "learning_rate": 2.7657337141184138e-05,
      "loss": 2.8813,
      "num_input_tokens_seen": 2146008,
      "step": 165
    },
    {
      "epoch": 1.437632135306554,
      "grad_norm": 2.831233501434326,
      "learning_rate": 2.655204850688085e-05,
      "loss": 2.7721,
      "num_input_tokens_seen": 2212840,
      "step": 170
    },
    {
      "epoch": 1.4799154334038054,
      "grad_norm": 2.757953643798828,
      "learning_rate": 2.5443704478301154e-05,
      "loss": 2.737,
      "num_input_tokens_seen": 2278824,
      "step": 175
    },
    {
      "epoch": 1.522198731501057,
      "grad_norm": 2.8655178546905518,
      "learning_rate": 2.433448696405563e-05,
      "loss": 2.6645,
      "num_input_tokens_seen": 2339768,
      "step": 180
    },
    {
      "epoch": 1.5644820295983086,
      "grad_norm": 2.8346216678619385,
      "learning_rate": 2.3226579592316538e-05,
      "loss": 2.7233,
      "num_input_tokens_seen": 2407976,
      "step": 185
    },
    {
      "epoch": 1.6067653276955602,
      "grad_norm": 2.432692766189575,
      "learning_rate": 2.2122163412082927e-05,
      "loss": 2.7463,
      "num_input_tokens_seen": 2469176,
      "step": 190
    },
    {
      "epoch": 1.6490486257928119,
      "grad_norm": 3.0815346240997314,
      "learning_rate": 2.1023412599523204e-05,
      "loss": 2.8348,
      "num_input_tokens_seen": 2528152,
      "step": 195
    },
    {
      "epoch": 1.6913319238900635,
      "grad_norm": 3.362581968307495,
      "learning_rate": 1.993249017784766e-05,
      "loss": 2.7732,
      "num_input_tokens_seen": 2588984,
      "step": 200
    },
    {
      "epoch": 1.733615221987315,
      "grad_norm": 3.2196719646453857,
      "learning_rate": 1.8851543759137007e-05,
      "loss": 2.7693,
      "num_input_tokens_seen": 2657016,
      "step": 205
    },
    {
      "epoch": 1.7758985200845667,
      "grad_norm": 2.6926162242889404,
      "learning_rate": 1.778270131650948e-05,
      "loss": 2.6524,
      "num_input_tokens_seen": 2719656,
      "step": 210
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 2.9597244262695312,
      "learning_rate": 1.672806699494966e-05,
      "loss": 2.7338,
      "num_input_tokens_seen": 2786168,
      "step": 215
    },
    {
      "epoch": 1.8604651162790697,
      "grad_norm": 3.4195263385772705,
      "learning_rate": 1.5689716969045848e-05,
      "loss": 2.7467,
      "num_input_tokens_seen": 2849400,
      "step": 220
    },
    {
      "epoch": 1.9027484143763214,
      "grad_norm": 2.8715097904205322,
      "learning_rate": 1.4669695355790552e-05,
      "loss": 2.5769,
      "num_input_tokens_seen": 2917000,
      "step": 225
    },
    {
      "epoch": 1.945031712473573,
      "grad_norm": 3.514866352081299,
      "learning_rate": 1.3670010190490073e-05,
      "loss": 2.784,
      "num_input_tokens_seen": 2980712,
      "step": 230
    },
    {
      "epoch": 1.9873150105708244,
      "grad_norm": 3.751493215560913,
      "learning_rate": 1.2692629473705453e-05,
      "loss": 2.7729,
      "num_input_tokens_seen": 3045848,
      "step": 235
    },
    {
      "epoch": 2.029598308668076,
      "grad_norm": 2.950978994369507,
      "learning_rate": 1.173947729700644e-05,
      "loss": 2.8171,
      "num_input_tokens_seen": 3105128,
      "step": 240
    },
    {
      "epoch": 2.0718816067653276,
      "grad_norm": 3.061615467071533,
      "learning_rate": 1.081243005516571e-05,
      "loss": 2.5436,
      "num_input_tokens_seen": 3175016,
      "step": 245
    },
    {
      "epoch": 2.1141649048625792,
      "grad_norm": 3.8741908073425293,
      "learning_rate": 9.913312752249903e-06,
      "loss": 2.4681,
      "num_input_tokens_seen": 3245608,
      "step": 250
    },
    {
      "epoch": 2.156448202959831,
      "grad_norm": 4.65464448928833,
      "learning_rate": 9.043895408879505e-06,
      "loss": 2.4036,
      "num_input_tokens_seen": 3308040,
      "step": 255
    },
    {
      "epoch": 2.1987315010570825,
      "grad_norm": 3.1693899631500244,
      "learning_rate": 8.20588957773018e-06,
      "loss": 2.4283,
      "num_input_tokens_seen": 3376152,
      "step": 260
    },
    {
      "epoch": 2.241014799154334,
      "grad_norm": 3.5537617206573486,
      "learning_rate": 7.400944974135427e-06,
      "loss": 2.6161,
      "num_input_tokens_seen": 3438504,
      "step": 265
    },
    {
      "epoch": 2.2832980972515857,
      "grad_norm": 3.5316078662872314,
      "learning_rate": 6.6306462284233234e-06,
      "loss": 2.6151,
      "num_input_tokens_seen": 3508488,
      "step": 270
    },
    {
      "epoch": 2.3255813953488373,
      "grad_norm": 3.0121572017669678,
      "learning_rate": 5.896509766381028e-06,
      "loss": 2.5051,
      "num_input_tokens_seen": 3572248,
      "step": 275
    },
    {
      "epoch": 2.367864693446089,
      "grad_norm": 3.4623148441314697,
      "learning_rate": 5.199980823988157e-06,
      "loss": 2.535,
      "num_input_tokens_seen": 3627304,
      "step": 280
    },
    {
      "epoch": 2.41014799154334,
      "grad_norm": 2.7531158924102783,
      "learning_rate": 4.542430602295774e-06,
      "loss": 2.4052,
      "num_input_tokens_seen": 3696504,
      "step": 285
    },
    {
      "epoch": 2.452431289640592,
      "grad_norm": 3.238701105117798,
      "learning_rate": 3.925153568052123e-06,
      "loss": 2.6136,
      "num_input_tokens_seen": 3757976,
      "step": 290
    },
    {
      "epoch": 2.4947145877378434,
      "grad_norm": 3.5991199016571045,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 2.2962,
      "num_input_tokens_seen": 3829192,
      "step": 295
    },
    {
      "epoch": 2.536997885835095,
      "grad_norm": 3.9785468578338623,
      "learning_rate": 2.8161981235857143e-06,
      "loss": 2.6799,
      "num_input_tokens_seen": 3900648,
      "step": 300
    },
    {
      "epoch": 2.5792811839323466,
      "grad_norm": 3.7737724781036377,
      "learning_rate": 2.3267028256193036e-06,
      "loss": 2.3375,
      "num_input_tokens_seen": 3970936,
      "step": 305
    },
    {
      "epoch": 2.6215644820295982,
      "grad_norm": 3.0493130683898926,
      "learning_rate": 1.881842641895104e-06,
      "loss": 2.5113,
      "num_input_tokens_seen": 4033192,
      "step": 310
    },
    {
      "epoch": 2.66384778012685,
      "grad_norm": 4.20770788192749,
      "learning_rate": 1.4824933332241692e-06,
      "loss": 2.5114,
      "num_input_tokens_seen": 4095144,
      "step": 315
    },
    {
      "epoch": 2.7061310782241015,
      "grad_norm": 3.411532402038574,
      "learning_rate": 1.129441066782702e-06,
      "loss": 2.5342,
      "num_input_tokens_seen": 4159320,
      "step": 320
    },
    {
      "epoch": 2.748414376321353,
      "grad_norm": 3.43635630607605,
      "learning_rate": 8.233808684473959e-07,
      "loss": 2.4773,
      "num_input_tokens_seen": 4227128,
      "step": 325
    },
    {
      "epoch": 2.7906976744186047,
      "grad_norm": 3.7875025272369385,
      "learning_rate": 5.649152545533332e-07,
      "loss": 2.4826,
      "num_input_tokens_seen": 4293848,
      "step": 330
    },
    {
      "epoch": 2.8329809725158563,
      "grad_norm": 3.2557740211486816,
      "learning_rate": 3.5455304576806347e-07,
      "loss": 2.5766,
      "num_input_tokens_seen": 4358088,
      "step": 335
    },
    {
      "epoch": 2.875264270613108,
      "grad_norm": 3.3667635917663574,
      "learning_rate": 1.927083654168854e-07,
      "loss": 2.5021,
      "num_input_tokens_seen": 4421432,
      "step": 340
    },
    {
      "epoch": 2.9175475687103596,
      "grad_norm": 3.3414418697357178,
      "learning_rate": 7.969982423124689e-08,
      "loss": 2.6718,
      "num_input_tokens_seen": 4482632,
      "step": 345
    },
    {
      "epoch": 2.9598308668076108,
      "grad_norm": 3.738370895385742,
      "learning_rate": 1.5749893125160954e-08,
      "loss": 2.3902,
      "num_input_tokens_seen": 4547096,
      "step": 350
    }
  ],
  "logging_steps": 5,
  "max_steps": 354,
  "num_input_tokens_seen": 4597544,
  "num_train_epochs": 3,
  "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": 5.475245368337203e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}