{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.426049908703591,
  "eval_steps": 500,
  "global_step": 700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006086427267194157,
      "grad_norm": 177.1066430901351,
      "learning_rate": 8.240909090909092e-06,
      "loss": 1.4114112854003906,
      "step": 10
    },
    {
      "epoch": 0.012172854534388313,
      "grad_norm": 42.905725580588935,
      "learning_rate": 1.728636363636364e-05,
      "loss": 0.6853461265563965,
      "step": 20
    },
    {
      "epoch": 0.018259281801582473,
      "grad_norm": 315.312793062447,
      "learning_rate": 2e-05,
      "loss": 0.6460141658782959,
      "step": 30
    },
    {
      "epoch": 0.024345709068776627,
      "grad_norm": 255.46586016422472,
      "learning_rate": 2e-05,
      "loss": 0.63227858543396,
      "step": 40
    },
    {
      "epoch": 0.030432136335970784,
      "grad_norm": 35.927808362846115,
      "learning_rate": 2e-05,
      "loss": 0.6816745281219483,
      "step": 50
    },
    {
      "epoch": 0.036518563603164945,
      "grad_norm": 4.615491337413327,
      "learning_rate": 2e-05,
      "loss": 0.6420984268188477,
      "step": 60
    },
    {
      "epoch": 0.0426049908703591,
      "grad_norm": 13.617572541497282,
      "learning_rate": 2e-05,
      "loss": 0.6360928535461425,
      "step": 70
    },
    {
      "epoch": 0.048691418137553254,
      "grad_norm": 2.116438190726367,
      "learning_rate": 2e-05,
      "loss": 0.6035876274108887,
      "step": 80
    },
    {
      "epoch": 0.054777845404747415,
      "grad_norm": 4.4434587119908455,
      "learning_rate": 2e-05,
      "loss": 0.596678352355957,
      "step": 90
    },
    {
      "epoch": 0.06086427267194157,
      "grad_norm": 17.238040829980065,
      "learning_rate": 2e-05,
      "loss": 0.5986958980560303,
      "step": 100
    },
    {
      "epoch": 0.06695069993913573,
      "grad_norm": 3.2395077287839884,
      "learning_rate": 2e-05,
      "loss": 0.5872138977050781,
      "step": 110
    },
    {
      "epoch": 0.07303712720632989,
      "grad_norm": 2.6531581911101623,
      "learning_rate": 2e-05,
      "loss": 0.587078857421875,
      "step": 120
    },
    {
      "epoch": 0.07912355447352404,
      "grad_norm": 4.083616047173512,
      "learning_rate": 2e-05,
      "loss": 0.5908248424530029,
      "step": 130
    },
    {
      "epoch": 0.0852099817407182,
      "grad_norm": 5.945854930949713,
      "learning_rate": 2e-05,
      "loss": 0.572390079498291,
      "step": 140
    },
    {
      "epoch": 0.09129640900791236,
      "grad_norm": 5.969783489291381,
      "learning_rate": 2e-05,
      "loss": 0.5681081295013428,
      "step": 150
    },
    {
      "epoch": 0.09738283627510651,
      "grad_norm": 4.850183924575788,
      "learning_rate": 2e-05,
      "loss": 0.5806607723236084,
      "step": 160
    },
    {
      "epoch": 0.10346926354230067,
      "grad_norm": 3.3393494673553468,
      "learning_rate": 2e-05,
      "loss": 0.5769606590270996,
      "step": 170
    },
    {
      "epoch": 0.10955569080949483,
      "grad_norm": 1.079093866543477,
      "learning_rate": 2e-05,
      "loss": 0.5661717414855957,
      "step": 180
    },
    {
      "epoch": 0.11564211807668898,
      "grad_norm": 8.30781290035136,
      "learning_rate": 2e-05,
      "loss": 0.5638448238372803,
      "step": 190
    },
    {
      "epoch": 0.12172854534388314,
      "grad_norm": 4.44475718465134,
      "learning_rate": 2e-05,
      "loss": 0.5628957271575927,
      "step": 200
    },
    {
      "epoch": 0.1278149726110773,
      "grad_norm": 0.8106940772598021,
      "learning_rate": 2e-05,
      "loss": 0.5750382423400879,
      "step": 210
    },
    {
      "epoch": 0.13390139987827146,
      "grad_norm": 3.700074196034875,
      "learning_rate": 2e-05,
      "loss": 0.5701132774353027,
      "step": 220
    },
    {
      "epoch": 0.13998782714546562,
      "grad_norm": 27.730040112563856,
      "learning_rate": 2e-05,
      "loss": 0.5680263042449951,
      "step": 230
    },
    {
      "epoch": 0.14607425441265978,
      "grad_norm": 1.6102562760929873,
      "learning_rate": 2e-05,
      "loss": 0.5841239929199219,
      "step": 240
    },
    {
      "epoch": 0.15216068167985392,
      "grad_norm": 8.653161243969437,
      "learning_rate": 2e-05,
      "loss": 0.5821664333343506,
      "step": 250
    },
    {
      "epoch": 0.15824710894704808,
      "grad_norm": 3.0430889086449824,
      "learning_rate": 2e-05,
      "loss": 0.600792121887207,
      "step": 260
    },
    {
      "epoch": 0.16433353621424224,
      "grad_norm": 1.5049495629818932,
      "learning_rate": 2e-05,
      "loss": 0.6037143230438232,
      "step": 270
    },
    {
      "epoch": 0.1704199634814364,
      "grad_norm": 2.2158105893231204,
      "learning_rate": 2e-05,
      "loss": 0.5846007347106934,
      "step": 280
    },
    {
      "epoch": 0.17650639074863056,
      "grad_norm": 7.611907629359478,
      "learning_rate": 2e-05,
      "loss": 0.5692090034484864,
      "step": 290
    },
    {
      "epoch": 0.18259281801582472,
      "grad_norm": 20.65692765082793,
      "learning_rate": 2e-05,
      "loss": 0.5598502159118652,
      "step": 300
    },
    {
      "epoch": 0.18867924528301888,
      "grad_norm": 34.30379709347527,
      "learning_rate": 2e-05,
      "loss": 0.5550279140472412,
      "step": 310
    },
    {
      "epoch": 0.19476567255021301,
      "grad_norm": 18.392649576154003,
      "learning_rate": 2e-05,
      "loss": 0.5651645660400391,
      "step": 320
    },
    {
      "epoch": 0.20085209981740718,
      "grad_norm": 4.25640449686484,
      "learning_rate": 2e-05,
      "loss": 0.555994701385498,
      "step": 330
    },
    {
      "epoch": 0.20693852708460134,
      "grad_norm": 19.75054571302128,
      "learning_rate": 2e-05,
      "loss": 0.558559513092041,
      "step": 340
    },
    {
      "epoch": 0.2130249543517955,
      "grad_norm": 64.08737452634305,
      "learning_rate": 2e-05,
      "loss": 0.5622023582458496,
      "step": 350
    },
    {
      "epoch": 0.21911138161898966,
      "grad_norm": 16.162882872259807,
      "learning_rate": 2e-05,
      "loss": 0.5919114589691162,
      "step": 360
    },
    {
      "epoch": 0.22519780888618382,
      "grad_norm": 5.433629004414366,
      "learning_rate": 2e-05,
      "loss": 0.6137895107269287,
      "step": 370
    },
    {
      "epoch": 0.23128423615337795,
      "grad_norm": 6.10396907895517,
      "learning_rate": 2e-05,
      "loss": 0.6059017181396484,
      "step": 380
    },
    {
      "epoch": 0.23737066342057211,
      "grad_norm": 6.633493017174115,
      "learning_rate": 2e-05,
      "loss": 0.592892074584961,
      "step": 390
    },
    {
      "epoch": 0.24345709068776628,
      "grad_norm": 3.246005211480333,
      "learning_rate": 2e-05,
      "loss": 0.5881185054779052,
      "step": 400
    },
    {
      "epoch": 0.24954351795496044,
      "grad_norm": 3.481106405026975,
      "learning_rate": 2e-05,
      "loss": 0.6180205345153809,
      "step": 410
    },
    {
      "epoch": 0.2556299452221546,
      "grad_norm": 2.0233135340086754,
      "learning_rate": 2e-05,
      "loss": 0.6023763179779053,
      "step": 420
    },
    {
      "epoch": 0.26171637248934876,
      "grad_norm": 0.7324398222159224,
      "learning_rate": 2e-05,
      "loss": 0.5831488609313965,
      "step": 430
    },
    {
      "epoch": 0.2678027997565429,
      "grad_norm": 1.0450699876923712,
      "learning_rate": 2e-05,
      "loss": 0.5710578918457031,
      "step": 440
    },
    {
      "epoch": 0.2738892270237371,
      "grad_norm": 0.813279131148472,
      "learning_rate": 2e-05,
      "loss": 0.5567676544189453,
      "step": 450
    },
    {
      "epoch": 0.27997565429093124,
      "grad_norm": 0.9687180867365358,
      "learning_rate": 2e-05,
      "loss": 0.5558897972106933,
      "step": 460
    },
    {
      "epoch": 0.2860620815581254,
      "grad_norm": 1.9233731899399389,
      "learning_rate": 2e-05,
      "loss": 0.5583930969238281,
      "step": 470
    },
    {
      "epoch": 0.29214850882531956,
      "grad_norm": 2.654219178792123,
      "learning_rate": 2e-05,
      "loss": 0.5428973436355591,
      "step": 480
    },
    {
      "epoch": 0.29823493609251367,
      "grad_norm": 1.218711664368106,
      "learning_rate": 2e-05,
      "loss": 0.5464369773864746,
      "step": 490
    },
    {
      "epoch": 0.30432136335970783,
      "grad_norm": 6.411647957762936,
      "learning_rate": 2e-05,
      "loss": 0.5435049057006835,
      "step": 500
    },
    {
      "epoch": 0.310407790626902,
      "grad_norm": 2.475300856396857,
      "learning_rate": 2e-05,
      "loss": 0.540925121307373,
      "step": 510
    },
    {
      "epoch": 0.31649421789409615,
      "grad_norm": 6.237635388845118,
      "learning_rate": 2e-05,
      "loss": 0.5424368858337403,
      "step": 520
    },
    {
      "epoch": 0.3225806451612903,
      "grad_norm": 0.7519039043025744,
      "learning_rate": 2e-05,
      "loss": 0.5385677337646484,
      "step": 530
    },
    {
      "epoch": 0.3286670724284845,
      "grad_norm": 12.824391832111631,
      "learning_rate": 2e-05,
      "loss": 0.5474379539489747,
      "step": 540
    },
    {
      "epoch": 0.33475349969567864,
      "grad_norm": 1.0272008957996457,
      "learning_rate": 2e-05,
      "loss": 0.545290756225586,
      "step": 550
    },
    {
      "epoch": 0.3408399269628728,
      "grad_norm": 7.7199802014161865,
      "learning_rate": 2e-05,
      "loss": 0.538370418548584,
      "step": 560
    },
    {
      "epoch": 0.34692635423006696,
      "grad_norm": 1.2968564066603798,
      "learning_rate": 2e-05,
      "loss": 0.5329624652862549,
      "step": 570
    },
    {
      "epoch": 0.3530127814972611,
      "grad_norm": 1.2950694741050104,
      "learning_rate": 2e-05,
      "loss": 0.5377538204193115,
      "step": 580
    },
    {
      "epoch": 0.3590992087644553,
      "grad_norm": 2.0406219171716415,
      "learning_rate": 2e-05,
      "loss": 0.5325220584869385,
      "step": 590
    },
    {
      "epoch": 0.36518563603164944,
      "grad_norm": 0.673821737015998,
      "learning_rate": 2e-05,
      "loss": 0.5449214458465577,
      "step": 600
    },
    {
      "epoch": 0.3712720632988436,
      "grad_norm": 0.6718670792561827,
      "learning_rate": 2e-05,
      "loss": 0.5402190685272217,
      "step": 610
    },
    {
      "epoch": 0.37735849056603776,
      "grad_norm": 0.6003241889673046,
      "learning_rate": 2e-05,
      "loss": 0.5355330467224121,
      "step": 620
    },
    {
      "epoch": 0.38344491783323187,
      "grad_norm": 1.0179732933194914,
      "learning_rate": 2e-05,
      "loss": 0.5329505920410156,
      "step": 630
    },
    {
      "epoch": 0.38953134510042603,
      "grad_norm": 28.655532205228564,
      "learning_rate": 1.9892306274149575e-05,
      "loss": 0.521296501159668,
      "step": 640
    },
    {
      "epoch": 0.3956177723676202,
      "grad_norm": 1.4348108763494245,
      "learning_rate": 1.8041914938232418e-05,
      "loss": 0.5254436016082764,
      "step": 650
    },
    {
      "epoch": 0.40170419963481435,
      "grad_norm": 1.3546356608482832,
      "learning_rate": 1.430417317963131e-05,
      "loss": 0.5192052841186523,
      "step": 660
    },
    {
      "epoch": 0.4077906269020085,
      "grad_norm": 0.8085436388960493,
      "learning_rate": 9.561776640442192e-06,
      "loss": 0.520291519165039,
      "step": 670
    },
    {
      "epoch": 0.4138770541692027,
      "grad_norm": 1.2082854246728014,
      "learning_rate": 4.934677695277445e-06,
      "loss": 0.5259696483612061,
      "step": 680
    },
    {
      "epoch": 0.41996348143639683,
      "grad_norm": 0.8419535818251231,
      "learning_rate": 1.5156003304972938e-06,
      "loss": 0.526776647567749,
      "step": 690
    },
    {
      "epoch": 0.426049908703591,
      "grad_norm": 0.765754084422289,
      "learning_rate": 1.1198521075853458e-07,
      "loss": 0.5123984336853027,
      "step": 700
    },
    {
      "epoch": 0.426049908703591,
      "step": 700,
      "total_flos": 4821608300544000.0,
      "train_loss": 0.047694339071001325,
      "train_runtime": 2670.0791,
      "train_samples_per_second": 25.168,
      "train_steps_per_second": 0.262
    }
  ],
  "logging_steps": 10,
  "max_steps": 700,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4821608300544000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}