{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.235469448584203,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.029806259314456036,
      "grad_norm": 0.22671940922737122,
      "learning_rate": 8e-05,
      "loss": 1.3506,
      "step": 20
    },
    {
      "epoch": 0.05961251862891207,
      "grad_norm": 0.05189573019742966,
      "learning_rate": 0.00016,
      "loss": 0.8372,
      "step": 40
    },
    {
      "epoch": 0.08941877794336811,
      "grad_norm": 0.049646440893411636,
      "learning_rate": 0.0001999871938117722,
      "loss": 0.7053,
      "step": 60
    },
    {
      "epoch": 0.11922503725782414,
      "grad_norm": 0.04605806618928909,
      "learning_rate": 0.0001998847639849245,
      "loss": 0.5957,
      "step": 80
    },
    {
      "epoch": 0.14903129657228018,
      "grad_norm": 0.04606040194630623,
      "learning_rate": 0.0001996800092633612,
      "loss": 0.5457,
      "step": 100
    },
    {
      "epoch": 0.17883755588673622,
      "grad_norm": 0.03791499882936478,
      "learning_rate": 0.0001993731394038509,
      "loss": 0.5301,
      "step": 120
    },
    {
      "epoch": 0.20864381520119224,
      "grad_norm": 0.047940950840711594,
      "learning_rate": 0.0001989644687729177,
      "loss": 0.5223,
      "step": 140
    },
    {
      "epoch": 0.23845007451564829,
      "grad_norm": 0.0519738644361496,
      "learning_rate": 0.0001984544160247949,
      "loss": 0.5117,
      "step": 160
    },
    {
      "epoch": 0.26825633383010433,
      "grad_norm": 0.04569224268198013,
      "learning_rate": 0.00019784350367254322,
      "loss": 0.5181,
      "step": 180
    },
    {
      "epoch": 0.29806259314456035,
      "grad_norm": 0.045780543237924576,
      "learning_rate": 0.0001971323575527731,
      "loss": 0.5168,
      "step": 200
    },
    {
      "epoch": 0.32786885245901637,
      "grad_norm": 0.046496499329805374,
      "learning_rate": 0.0001963217061845192,
      "loss": 0.5051,
      "step": 220
    },
    {
      "epoch": 0.35767511177347244,
      "grad_norm": 0.04850991442799568,
      "learning_rate": 0.00019541238002292394,
      "loss": 0.5083,
      "step": 240
    },
    {
      "epoch": 0.38748137108792846,
      "grad_norm": 0.046593230217695236,
      "learning_rate": 0.00019440531060849504,
      "loss": 0.5066,
      "step": 260
    },
    {
      "epoch": 0.4172876304023845,
      "grad_norm": 0.050816215574741364,
      "learning_rate": 0.00019330152961280765,
      "loss": 0.5021,
      "step": 280
    },
    {
      "epoch": 0.44709388971684055,
      "grad_norm": 0.0533340722322464,
      "learning_rate": 0.00019210216778162994,
      "loss": 0.5017,
      "step": 300
    },
    {
      "epoch": 0.47690014903129657,
      "grad_norm": 0.10607749223709106,
      "learning_rate": 0.00019080845377655352,
      "loss": 0.4996,
      "step": 320
    },
    {
      "epoch": 0.5067064083457526,
      "grad_norm": 0.054169464856386185,
      "learning_rate": 0.00018942171291631653,
      "loss": 0.5014,
      "step": 340
    },
    {
      "epoch": 0.5365126676602087,
      "grad_norm": 0.047340892255306244,
      "learning_rate": 0.000187943365819108,
      "loss": 0.4988,
      "step": 360
    },
    {
      "epoch": 0.5663189269746647,
      "grad_norm": 0.04948943480849266,
      "learning_rate": 0.00018637492694724466,
      "loss": 0.4975,
      "step": 380
    },
    {
      "epoch": 0.5961251862891207,
      "grad_norm": 0.04684118553996086,
      "learning_rate": 0.00018471800305571129,
      "loss": 0.4961,
      "step": 400
    },
    {
      "epoch": 0.6259314456035767,
      "grad_norm": 0.04512176662683487,
      "learning_rate": 0.00018297429154615338,
      "loss": 0.4956,
      "step": 420
    },
    {
      "epoch": 0.6557377049180327,
      "grad_norm": 0.05711393430829048,
      "learning_rate": 0.00018114557872800905,
      "loss": 0.4944,
      "step": 440
    },
    {
      "epoch": 0.6855439642324889,
      "grad_norm": 0.05339927598834038,
      "learning_rate": 0.000179233737988561,
      "loss": 0.4922,
      "step": 460
    },
    {
      "epoch": 0.7153502235469449,
      "grad_norm": 0.04622140899300575,
      "learning_rate": 0.00017724072787378333,
      "loss": 0.4846,
      "step": 480
    },
    {
      "epoch": 0.7451564828614009,
      "grad_norm": 0.0447109080851078,
      "learning_rate": 0.00017516859008194938,
      "loss": 0.4855,
      "step": 500
    },
    {
      "epoch": 0.7749627421758569,
      "grad_norm": 0.0435018390417099,
      "learning_rate": 0.00017301944737205588,
      "loss": 0.486,
      "step": 520
    },
    {
      "epoch": 0.8047690014903129,
      "grad_norm": 0.04844864085316658,
      "learning_rate": 0.0001707955013892061,
      "loss": 0.4911,
      "step": 540
    },
    {
      "epoch": 0.834575260804769,
      "grad_norm": 0.05155207961797714,
      "learning_rate": 0.00016849903040917975,
      "loss": 0.4861,
      "step": 560
    },
    {
      "epoch": 0.8643815201192251,
      "grad_norm": 0.04522501304745674,
      "learning_rate": 0.00016613238700450013,
      "loss": 0.4852,
      "step": 580
    },
    {
      "epoch": 0.8941877794336811,
      "grad_norm": 0.047208670526742935,
      "learning_rate": 0.00016369799563438958,
      "loss": 0.4844,
      "step": 600
    },
    {
      "epoch": 0.9239940387481371,
      "grad_norm": 0.054809391498565674,
      "learning_rate": 0.00016119835016108197,
      "loss": 0.4815,
      "step": 620
    },
    {
      "epoch": 0.9538002980625931,
      "grad_norm": 0.04929815232753754,
      "learning_rate": 0.00015863601129503688,
      "loss": 0.4823,
      "step": 640
    },
    {
      "epoch": 0.9836065573770492,
      "grad_norm": 0.05650775134563446,
      "learning_rate": 0.00015601360397167214,
      "loss": 0.481,
      "step": 660
    },
    {
      "epoch": 1.0134128166915053,
      "grad_norm": 0.04741150885820389,
      "learning_rate": 0.00015333381466230294,
      "loss": 0.488,
      "step": 680
    },
    {
      "epoch": 1.0432190760059612,
      "grad_norm": 0.057174187153577805,
      "learning_rate": 0.00015059938862204127,
      "loss": 0.4821,
      "step": 700
    },
    {
      "epoch": 1.0730253353204173,
      "grad_norm": 0.054773855954408646,
      "learning_rate": 0.0001478131270774758,
      "loss": 0.4776,
      "step": 720
    },
    {
      "epoch": 1.1028315946348732,
      "grad_norm": 0.05249800160527229,
      "learning_rate": 0.0001449778843570128,
      "loss": 0.4782,
      "step": 740
    },
    {
      "epoch": 1.1326378539493294,
      "grad_norm": 0.049587223678827286,
      "learning_rate": 0.00014209656496681812,
      "loss": 0.4819,
      "step": 760
    },
    {
      "epoch": 1.1624441132637853,
      "grad_norm": 0.048591841012239456,
      "learning_rate": 0.0001391721206153554,
      "loss": 0.4796,
      "step": 780
    },
    {
      "epoch": 1.1922503725782414,
      "grad_norm": 0.05344521254301071,
      "learning_rate": 0.000136207547189569,
      "loss": 0.472,
      "step": 800
    },
    {
      "epoch": 1.2220566318926975,
      "grad_norm": 0.052742790430784225,
      "learning_rate": 0.0001332058816858092,
      "loss": 0.476,
      "step": 820
    },
    {
      "epoch": 1.2518628912071534,
      "grad_norm": 0.05483981594443321,
      "learning_rate": 0.00013017019909864364,
      "loss": 0.4755,
      "step": 840
    },
    {
      "epoch": 1.2816691505216096,
      "grad_norm": 0.050890855491161346,
      "learning_rate": 0.00012710360927074233,
      "loss": 0.4719,
      "step": 860
    },
    {
      "epoch": 1.3114754098360657,
      "grad_norm": 0.05531829223036766,
      "learning_rate": 0.0001240092537070631,
      "loss": 0.4745,
      "step": 880
    },
    {
      "epoch": 1.3412816691505216,
      "grad_norm": 0.05655696988105774,
      "learning_rate": 0.00012089030235660155,
      "loss": 0.475,
      "step": 900
    },
    {
      "epoch": 1.3710879284649775,
      "grad_norm": 0.059185780584812164,
      "learning_rate": 0.00011774995036500181,
      "loss": 0.4714,
      "step": 920
    },
    {
      "epoch": 1.4008941877794336,
      "grad_norm": 0.05000292509794235,
      "learning_rate": 0.00011459141480135518,
      "loss": 0.4774,
      "step": 940
    },
    {
      "epoch": 1.4307004470938898,
      "grad_norm": 0.05054055526852608,
      "learning_rate": 0.00011141793136253986,
      "loss": 0.4666,
      "step": 960
    },
    {
      "epoch": 1.4605067064083457,
      "grad_norm": 0.04777640849351883,
      "learning_rate": 0.00010823275105847772,
      "loss": 0.4711,
      "step": 980
    },
    {
      "epoch": 1.4903129657228018,
      "grad_norm": 0.05582300201058388,
      "learning_rate": 0.00010503913688170396,
      "loss": 0.4668,
      "step": 1000
    },
    {
      "epoch": 1.520119225037258,
      "grad_norm": 0.059767983853816986,
      "learning_rate": 0.00010184036046466143,
      "loss": 0.4683,
      "step": 1020
    },
    {
      "epoch": 1.5499254843517138,
      "grad_norm": 0.0632881224155426,
      "learning_rate": 9.863969872814403e-05,
      "loss": 0.4695,
      "step": 1040
    },
    {
      "epoch": 1.5797317436661698,
      "grad_norm": 0.05366360396146774,
      "learning_rate": 9.544043052432244e-05,
      "loss": 0.4672,
      "step": 1060
    },
    {
      "epoch": 1.6095380029806259,
      "grad_norm": 0.049754392355680466,
      "learning_rate": 9.224583327779134e-05,
      "loss": 0.4655,
      "step": 1080
    },
    {
      "epoch": 1.639344262295082,
      "grad_norm": 0.055744487792253494,
      "learning_rate": 8.905917962807927e-05,
      "loss": 0.4714,
      "step": 1100
    },
    {
      "epoch": 1.669150521609538,
      "grad_norm": 0.05113043636083603,
      "learning_rate": 8.588373407706007e-05,
      "loss": 0.4626,
      "step": 1120
    },
    {
      "epoch": 1.698956780923994,
      "grad_norm": 0.05468016862869263,
      "learning_rate": 8.272274964470118e-05,
      "loss": 0.4681,
      "step": 1140
    },
    {
      "epoch": 1.7287630402384502,
      "grad_norm": 0.05420814827084541,
      "learning_rate": 7.957946453657403e-05,
      "loss": 0.4684,
      "step": 1160
    },
    {
      "epoch": 1.758569299552906,
      "grad_norm": 0.06343657523393631,
      "learning_rate": 7.645709882654093e-05,
      "loss": 0.4659,
      "step": 1180
    },
    {
      "epoch": 1.788375558867362,
      "grad_norm": 0.05385758727788925,
      "learning_rate": 7.335885115801656e-05,
      "loss": 0.4659,
      "step": 1200
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.05174577608704567,
      "learning_rate": 7.028789546718326e-05,
      "loss": 0.4646,
      "step": 1220
    },
    {
      "epoch": 1.8479880774962743,
      "grad_norm": 0.05492328852415085,
      "learning_rate": 6.72473777315176e-05,
      "loss": 0.4657,
      "step": 1240
    },
    {
      "epoch": 1.8777943368107302,
      "grad_norm": 0.060056205838918686,
      "learning_rate": 6.424041274695804e-05,
      "loss": 0.4677,
      "step": 1260
    },
    {
      "epoch": 1.9076005961251863,
      "grad_norm": 0.061595309525728226,
      "learning_rate": 6.127008093701658e-05,
      "loss": 0.4661,
      "step": 1280
    },
    {
      "epoch": 1.9374068554396424,
      "grad_norm": 0.05786813423037529,
      "learning_rate": 5.833942519710177e-05,
      "loss": 0.4641,
      "step": 1300
    },
    {
      "epoch": 1.9672131147540983,
      "grad_norm": 0.05672052502632141,
      "learning_rate": 5.5451447777287324e-05,
      "loss": 0.4653,
      "step": 1320
    },
    {
      "epoch": 1.9970193740685542,
      "grad_norm": 0.06217477470636368,
      "learning_rate": 5.260910720671858e-05,
      "loss": 0.4658,
      "step": 1340
    },
    {
      "epoch": 2.0268256333830106,
      "grad_norm": 0.05346861109137535,
      "learning_rate": 4.981531526280807e-05,
      "loss": 0.4665,
      "step": 1360
    },
    {
      "epoch": 2.0566318926974665,
      "grad_norm": 0.05857508257031441,
      "learning_rate": 4.707293398832504e-05,
      "loss": 0.4676,
      "step": 1380
    },
    {
      "epoch": 2.0864381520119224,
      "grad_norm": 0.05544683709740639,
      "learning_rate": 4.4384772759434425e-05,
      "loss": 0.4678,
      "step": 1400
    },
    {
      "epoch": 2.1162444113263787,
      "grad_norm": 0.05981365218758583,
      "learning_rate": 4.175358540768922e-05,
      "loss": 0.4684,
      "step": 1420
    },
    {
      "epoch": 2.1460506706408347,
      "grad_norm": 0.05496670678257942,
      "learning_rate": 3.9182067398924324e-05,
      "loss": 0.4646,
      "step": 1440
    },
    {
      "epoch": 2.1758569299552906,
      "grad_norm": 0.05577287822961807,
      "learning_rate": 3.667285307194176e-05,
      "loss": 0.4696,
      "step": 1460
    },
    {
      "epoch": 2.2056631892697465,
      "grad_norm": 0.054632559418678284,
      "learning_rate": 3.422851293981676e-05,
      "loss": 0.4686,
      "step": 1480
    },
    {
      "epoch": 2.235469448584203,
      "grad_norm": 0.05347989872097969,
      "learning_rate": 3.185155105658798e-05,
      "loss": 0.4593,
      "step": 1500
    }
  ],
  "logging_steps": 20,
  "max_steps": 2013,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.5407796188453274e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}