{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500.0,
  "global_step": 619,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016155088852988692,
      "grad_norm": 17.625,
      "learning_rate": 1.0526315789473685e-06,
      "loss": 1.1847093105316162,
      "step": 1,
      "token_acc": 0.7405614714424008
    },
    {
      "epoch": 0.01615508885298869,
      "grad_norm": 7.3125,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 0.9536339441935221,
      "step": 10,
      "token_acc": 0.7746876697447039
    },
    {
      "epoch": 0.03231017770597738,
      "grad_norm": 5.21875,
      "learning_rate": 1.999986292247427e-05,
      "loss": 0.7083949089050293,
      "step": 20,
      "token_acc": 0.817535314174379
    },
    {
      "epoch": 0.048465266558966075,
      "grad_norm": 5.09375,
      "learning_rate": 1.9983418166140286e-05,
      "loss": 0.6189894676208496,
      "step": 30,
      "token_acc": 0.8316753668866345
    },
    {
      "epoch": 0.06462035541195477,
      "grad_norm": 5.25,
      "learning_rate": 1.99396095545518e-05,
      "loss": 0.595418643951416,
      "step": 40,
      "token_acc": 0.8332687463669831
    },
    {
      "epoch": 0.08077544426494346,
      "grad_norm": 4.96875,
      "learning_rate": 1.9868557164068073e-05,
      "loss": 0.5784546852111816,
      "step": 50,
      "token_acc": 0.8330070477682068
    },
    {
      "epoch": 0.09693053311793215,
      "grad_norm": 4.78125,
      "learning_rate": 1.977045574435264e-05,
      "loss": 0.5632569313049316,
      "step": 60,
      "token_acc": 0.8422178988326848
    },
    {
      "epoch": 0.11308562197092084,
      "grad_norm": 4.53125,
      "learning_rate": 1.9645574184577982e-05,
      "loss": 0.5411516189575195,
      "step": 70,
      "token_acc": 0.8414407360281884
    },
    {
      "epoch": 0.12924071082390953,
      "grad_norm": 5.125,
      "learning_rate": 1.949425477641904e-05,
      "loss": 0.5536646366119384,
      "step": 80,
      "token_acc": 0.8417469117790098
    },
    {
      "epoch": 0.14539579967689822,
      "grad_norm": 5.375,
      "learning_rate": 1.931691227585549e-05,
      "loss": 0.552952766418457,
      "step": 90,
      "token_acc": 0.8431372549019608
    },
    {
      "epoch": 0.16155088852988692,
      "grad_norm": 4.875,
      "learning_rate": 1.9114032766354453e-05,
      "loss": 0.5462624549865722,
      "step": 100,
      "token_acc": 0.843832148768377
    },
    {
      "epoch": 0.1777059773828756,
      "grad_norm": 4.4375,
      "learning_rate": 1.888617232654949e-05,
      "loss": 0.5441291809082032,
      "step": 110,
      "token_acc": 0.8419827335338054
    },
    {
      "epoch": 0.1938610662358643,
      "grad_norm": 4.3125,
      "learning_rate": 1.8633955506067717e-05,
      "loss": 0.5480209350585937,
      "step": 120,
      "token_acc": 0.8493486139680674
    },
    {
      "epoch": 0.210016155088853,
      "grad_norm": 5.28125,
      "learning_rate": 1.8358073613682705e-05,
      "loss": 0.553197193145752,
      "step": 130,
      "token_acc": 0.8403582205782147
    },
    {
      "epoch": 0.22617124394184168,
      "grad_norm": 5.4375,
      "learning_rate": 1.805928282248516e-05,
      "loss": 0.558505630493164,
      "step": 140,
      "token_acc": 0.8416950803701899
    },
    {
      "epoch": 0.24232633279483037,
      "grad_norm": 4.5625,
      "learning_rate": 1.7738402097265063e-05,
      "loss": 0.5198162078857422,
      "step": 150,
      "token_acc": 0.8472963789923308
    },
    {
      "epoch": 0.25848142164781907,
      "grad_norm": 4.875,
      "learning_rate": 1.73963109497861e-05,
      "loss": 0.5393078804016114,
      "step": 160,
      "token_acc": 0.844424985405721
    },
    {
      "epoch": 0.27463651050080773,
      "grad_norm": 4.90625,
      "learning_rate": 1.703394702810504e-05,
      "loss": 0.5661784172058105,
      "step": 170,
      "token_acc": 0.8364490554957424
    },
    {
      "epoch": 0.29079159935379645,
      "grad_norm": 4.5625,
      "learning_rate": 1.665230354654361e-05,
      "loss": 0.5104843139648437,
      "step": 180,
      "token_acc": 0.8500578927055191
    },
    {
      "epoch": 0.3069466882067851,
      "grad_norm": 4.71875,
      "learning_rate": 1.6252426563357054e-05,
      "loss": 0.5394854545593262,
      "step": 190,
      "token_acc": 0.8471082454083626
    },
    {
      "epoch": 0.32310177705977383,
      "grad_norm": 4.46875,
      "learning_rate": 1.5835412113561176e-05,
      "loss": 0.5530763149261475,
      "step": 200,
      "token_acc": 0.8418517790446236
    },
    {
      "epoch": 0.3392568659127625,
      "grad_norm": 4.40625,
      "learning_rate": 1.5402403204776552e-05,
      "loss": 0.5297245979309082,
      "step": 210,
      "token_acc": 0.8469646691391762
    },
    {
      "epoch": 0.3554119547657512,
      "grad_norm": 4.75,
      "learning_rate": 1.4954586684324077e-05,
      "loss": 0.5240192413330078,
      "step": 220,
      "token_acc": 0.8480382588327152
    },
    {
      "epoch": 0.3715670436187399,
      "grad_norm": 4.625,
      "learning_rate": 1.4493189986158966e-05,
      "loss": 0.5166411399841309,
      "step": 230,
      "token_acc": 0.8447706065318819
    },
    {
      "epoch": 0.3877221324717286,
      "grad_norm": 4.375,
      "learning_rate": 1.4019477766559604e-05,
      "loss": 0.5292513847351075,
      "step": 240,
      "token_acc": 0.8480617127233668
    },
    {
      "epoch": 0.40387722132471726,
      "grad_norm": 5.0,
      "learning_rate": 1.3534748437792573e-05,
      "loss": 0.5284510135650635,
      "step": 250,
      "token_acc": 0.8485742379547689
    },
    {
      "epoch": 0.420032310177706,
      "grad_norm": 4.28125,
      "learning_rate": 1.3040330609254903e-05,
      "loss": 0.5196167945861816,
      "step": 260,
      "token_acc": 0.8470174753490188
    },
    {
      "epoch": 0.43618739903069464,
      "grad_norm": 4.9375,
      "learning_rate": 1.2537579445848058e-05,
      "loss": 0.5236739635467529,
      "step": 270,
      "token_acc": 0.8470025385666862
    },
    {
      "epoch": 0.45234248788368336,
      "grad_norm": 4.625,
      "learning_rate": 1.2027872953565125e-05,
      "loss": 0.5147537231445313,
      "step": 280,
      "token_acc": 0.8483849063924725
    },
    {
      "epoch": 0.46849757673667203,
      "grad_norm": 4.53125,
      "learning_rate": 1.1512608202472195e-05,
      "loss": 0.5182638168334961,
      "step": 290,
      "token_acc": 0.8484908071969325
    },
    {
      "epoch": 0.48465266558966075,
      "grad_norm": 4.5625,
      "learning_rate": 1.0993197497436392e-05,
      "loss": 0.5263832092285157,
      "step": 300,
      "token_acc": 0.848084030344291
    },
    {
      "epoch": 0.5008077544426495,
      "grad_norm": 4.28125,
      "learning_rate": 1.0471064507096427e-05,
      "loss": 0.5192934036254883,
      "step": 310,
      "token_acc": 0.8522849069472863
    },
    {
      "epoch": 0.5169628432956381,
      "grad_norm": 4.46875,
      "learning_rate": 9.947640361685805e-06,
      "loss": 0.49528074264526367,
      "step": 320,
      "token_acc": 0.853359489946052
    },
    {
      "epoch": 0.5331179321486268,
      "grad_norm": 4.625,
      "learning_rate": 9.424359730404329e-06,
      "loss": 0.5119996070861816,
      "step": 330,
      "token_acc": 0.8492686234621718
    },
    {
      "epoch": 0.5492730210016155,
      "grad_norm": 4.5625,
      "learning_rate": 8.902656889089548e-06,
      "loss": 0.5261263847351074,
      "step": 340,
      "token_acc": 0.8463559404495475
    },
    {
      "epoch": 0.5654281098546042,
      "grad_norm": 4.375,
      "learning_rate": 8.38396178896639e-06,
      "loss": 0.5155754566192627,
      "step": 350,
      "token_acc": 0.853113410111263
    },
    {
      "epoch": 0.5815831987075929,
      "grad_norm": 4.59375,
      "learning_rate": 7.869696137250235e-06,
      "loss": 0.5171246528625488,
      "step": 360,
      "token_acc": 0.8516091166976426
    },
    {
      "epoch": 0.5977382875605816,
      "grad_norm": 4.6875,
      "learning_rate": 7.361269500346274e-06,
      "loss": 0.5315141677856445,
      "step": 370,
      "token_acc": 0.8478004713275726
    },
    {
      "epoch": 0.6138933764135702,
      "grad_norm": 5.0625,
      "learning_rate": 6.860075440325951e-06,
      "loss": 0.5140278816223145,
      "step": 380,
      "token_acc": 0.8488246287006983
    },
    {
      "epoch": 0.630048465266559,
      "grad_norm": 4.78125,
      "learning_rate": 6.367487695270218e-06,
      "loss": 0.5044659614562989,
      "step": 390,
      "token_acc": 0.8520192591136877
    },
    {
      "epoch": 0.6462035541195477,
      "grad_norm": 5.0,
      "learning_rate": 5.884856413948913e-06,
      "loss": 0.5070418357849121,
      "step": 400,
      "token_acc": 0.8493284017909286
    },
    {
      "epoch": 0.6623586429725363,
      "grad_norm": 4.59375,
      "learning_rate": 5.413504455156855e-06,
      "loss": 0.5049197196960449,
      "step": 410,
      "token_acc": 0.8500828540793449
    },
    {
      "epoch": 0.678513731825525,
      "grad_norm": 4.4375,
      "learning_rate": 4.954723761849809e-06,
      "loss": 0.4989957332611084,
      "step": 420,
      "token_acc": 0.8527764127764128
    },
    {
      "epoch": 0.6946688206785138,
      "grad_norm": 5.125,
      "learning_rate": 4.509771820018682e-06,
      "loss": 0.49854435920715334,
      "step": 430,
      "token_acc": 0.8521560574948666
    },
    {
      "epoch": 0.7108239095315024,
      "grad_norm": 4.46875,
      "learning_rate": 4.0798682120078046e-06,
      "loss": 0.5228716373443604,
      "step": 440,
      "token_acc": 0.8458528951486698
    },
    {
      "epoch": 0.7269789983844911,
      "grad_norm": 5.25,
      "learning_rate": 3.6661912737244996e-06,
      "loss": 0.5174414157867432,
      "step": 450,
      "token_acc": 0.8437163814180929
    },
    {
      "epoch": 0.7431340872374798,
      "grad_norm": 5.28125,
      "learning_rate": 3.2698748649022693e-06,
      "loss": 0.4988471508026123,
      "step": 460,
      "token_acc": 0.8513395031660984
    },
    {
      "epoch": 0.7592891760904685,
      "grad_norm": 4.59375,
      "learning_rate": 2.8920052612700755e-06,
      "loss": 0.5026087760925293,
      "step": 470,
      "token_acc": 0.8537626066718387
    },
    {
      "epoch": 0.7754442649434572,
      "grad_norm": 4.40625,
      "learning_rate": 2.5336181771460877e-06,
      "loss": 0.49767255783081055,
      "step": 480,
      "token_acc": 0.8517356344381252
    },
    {
      "epoch": 0.7915993537964459,
      "grad_norm": 4.8125,
      "learning_rate": 2.195695926616702e-06,
      "loss": 0.5065960884094238,
      "step": 490,
      "token_acc": 0.8521747648902821
    },
    {
      "epoch": 0.8077544426494345,
      "grad_norm": 4.4375,
      "learning_rate": 1.8791647310819371e-06,
      "loss": 0.5075524330139161,
      "step": 500,
      "token_acc": 0.8482975174173291
    },
    {
      "epoch": 0.8239095315024233,
      "grad_norm": 5.25,
      "learning_rate": 1.5848921805469396e-06,
      "loss": 0.5103363990783691,
      "step": 510,
      "token_acc": 0.8537348455220962
    },
    {
      "epoch": 0.840064620355412,
      "grad_norm": 4.9375,
      "learning_rate": 1.3136848556180893e-06,
      "loss": 0.527727460861206,
      "step": 520,
      "token_acc": 0.8470945020543925
    },
    {
      "epoch": 0.8562197092084006,
      "grad_norm": 4.375,
      "learning_rate": 1.0662861167216243e-06,
      "loss": 0.4919741630554199,
      "step": 530,
      "token_acc": 0.8542659791808541
    },
    {
      "epoch": 0.8723747980613893,
      "grad_norm": 6.90625,
      "learning_rate": 8.433740666043899e-07,
      "loss": 0.5399604797363281,
      "step": 540,
      "token_acc": 0.8415647921760391
    },
    {
      "epoch": 0.8885298869143781,
      "grad_norm": 4.40625,
      "learning_rate": 6.455596917013274e-07,
      "loss": 0.5133064270019532,
      "step": 550,
      "token_acc": 0.8489405331510594
    },
    {
      "epoch": 0.9046849757673667,
      "grad_norm": 4.875,
      "learning_rate": 4.733851874641382e-07,
      "loss": 0.5087760925292969,
      "step": 560,
      "token_acc": 0.8505905511811024
    },
    {
      "epoch": 0.9208400646203554,
      "grad_norm": 4.625,
      "learning_rate": 3.273224722412327e-07,
      "loss": 0.4963532447814941,
      "step": 570,
      "token_acc": 0.8557692307692307
    },
    {
      "epoch": 0.9369951534733441,
      "grad_norm": 4.65625,
      "learning_rate": 2.077718937823414e-07,
      "loss": 0.5168875694274903,
      "step": 580,
      "token_acc": 0.8515441751368257
    },
    {
      "epoch": 0.9531502423263328,
      "grad_norm": 4.09375,
      "learning_rate": 1.1506113191316447e-07,
      "loss": 0.5301695823669433,
      "step": 590,
      "token_acc": 0.8447769953051644
    },
    {
      "epoch": 0.9693053311793215,
      "grad_norm": 4.53125,
      "learning_rate": 4.944430038773762e-08,
      "loss": 0.507291316986084,
      "step": 600,
      "token_acc": 0.8520109332292073
    },
    {
      "epoch": 0.9854604200323102,
      "grad_norm": 4.28125,
      "learning_rate": 1.1101250380300965e-08,
      "loss": 0.48858890533447263,
      "step": 610,
      "token_acc": 0.8529469355786176
    }
  ],
  "logging_steps": 10,
  "max_steps": 619,
  "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": 2.618575333317673e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}