{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 742,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013490725126475547,
      "grad_norm": 65.45332336425781,
      "learning_rate": 0.00019964061096136568,
      "loss": 22.1843,
      "step": 10
    },
    {
      "epoch": 0.026981450252951095,
      "grad_norm": 6.102770805358887,
      "learning_rate": 0.00019874213836477988,
      "loss": 7.6527,
      "step": 20
    },
    {
      "epoch": 0.04047217537942664,
      "grad_norm": 2.982379913330078,
      "learning_rate": 0.00019784366576819408,
      "loss": 3.4532,
      "step": 30
    },
    {
      "epoch": 0.05396290050590219,
      "grad_norm": 3.4628562927246094,
      "learning_rate": 0.00019694519317160826,
      "loss": 2.4467,
      "step": 40
    },
    {
      "epoch": 0.06745362563237774,
      "grad_norm": 3.0008349418640137,
      "learning_rate": 0.00019604672057502246,
      "loss": 1.6481,
      "step": 50
    },
    {
      "epoch": 0.08094435075885328,
      "grad_norm": 1.767865777015686,
      "learning_rate": 0.00019514824797843666,
      "loss": 1.2119,
      "step": 60
    },
    {
      "epoch": 0.09443507588532883,
      "grad_norm": 3.416968584060669,
      "learning_rate": 0.00019424977538185087,
      "loss": 0.967,
      "step": 70
    },
    {
      "epoch": 0.10792580101180438,
      "grad_norm": 3.718262195587158,
      "learning_rate": 0.00019335130278526507,
      "loss": 0.8783,
      "step": 80
    },
    {
      "epoch": 0.12141652613827993,
      "grad_norm": 3.689655065536499,
      "learning_rate": 0.00019245283018867927,
      "loss": 0.7619,
      "step": 90
    },
    {
      "epoch": 0.13490725126475547,
      "grad_norm": 6.728384017944336,
      "learning_rate": 0.00019155435759209347,
      "loss": 0.7244,
      "step": 100
    },
    {
      "epoch": 0.14839797639123103,
      "grad_norm": 4.880130290985107,
      "learning_rate": 0.00019065588499550765,
      "loss": 0.6931,
      "step": 110
    },
    {
      "epoch": 0.16188870151770657,
      "grad_norm": 10.14767074584961,
      "learning_rate": 0.00018975741239892185,
      "loss": 0.6995,
      "step": 120
    },
    {
      "epoch": 0.17537942664418213,
      "grad_norm": 10.897403717041016,
      "learning_rate": 0.00018885893980233605,
      "loss": 0.69,
      "step": 130
    },
    {
      "epoch": 0.18887015177065766,
      "grad_norm": 7.759915351867676,
      "learning_rate": 0.00018796046720575023,
      "loss": 0.6899,
      "step": 140
    },
    {
      "epoch": 0.20236087689713322,
      "grad_norm": 7.006256580352783,
      "learning_rate": 0.00018706199460916443,
      "loss": 0.6739,
      "step": 150
    },
    {
      "epoch": 0.21585160202360876,
      "grad_norm": 5.777213096618652,
      "learning_rate": 0.00018616352201257863,
      "loss": 0.6731,
      "step": 160
    },
    {
      "epoch": 0.22934232715008432,
      "grad_norm": 10.224111557006836,
      "learning_rate": 0.00018526504941599283,
      "loss": 0.6417,
      "step": 170
    },
    {
      "epoch": 0.24283305227655985,
      "grad_norm": 6.332294464111328,
      "learning_rate": 0.000184366576819407,
      "loss": 0.6452,
      "step": 180
    },
    {
      "epoch": 0.2563237774030354,
      "grad_norm": 3.9472005367279053,
      "learning_rate": 0.0001834681042228212,
      "loss": 0.6271,
      "step": 190
    },
    {
      "epoch": 0.26981450252951095,
      "grad_norm": 6.640835762023926,
      "learning_rate": 0.0001825696316262354,
      "loss": 0.6161,
      "step": 200
    },
    {
      "epoch": 0.28330522765598654,
      "grad_norm": 5.6504316329956055,
      "learning_rate": 0.00018167115902964959,
      "loss": 0.6452,
      "step": 210
    },
    {
      "epoch": 0.29679595278246207,
      "grad_norm": 3.4219472408294678,
      "learning_rate": 0.0001807726864330638,
      "loss": 0.6228,
      "step": 220
    },
    {
      "epoch": 0.3102866779089376,
      "grad_norm": 7.479050636291504,
      "learning_rate": 0.000179874213836478,
      "loss": 0.6035,
      "step": 230
    },
    {
      "epoch": 0.32377740303541314,
      "grad_norm": 6.84128475189209,
      "learning_rate": 0.0001789757412398922,
      "loss": 0.5763,
      "step": 240
    },
    {
      "epoch": 0.3372681281618887,
      "grad_norm": 3.407183885574341,
      "learning_rate": 0.0001780772686433064,
      "loss": 0.5981,
      "step": 250
    },
    {
      "epoch": 0.35075885328836426,
      "grad_norm": 6.634527683258057,
      "learning_rate": 0.0001771787960467206,
      "loss": 0.6313,
      "step": 260
    },
    {
      "epoch": 0.3642495784148398,
      "grad_norm": 6.274175643920898,
      "learning_rate": 0.0001762803234501348,
      "loss": 0.5971,
      "step": 270
    },
    {
      "epoch": 0.3777403035413153,
      "grad_norm": 5.464880466461182,
      "learning_rate": 0.00017538185085354897,
      "loss": 0.629,
      "step": 280
    },
    {
      "epoch": 0.3912310286677909,
      "grad_norm": 7.9421234130859375,
      "learning_rate": 0.00017448337825696318,
      "loss": 0.5604,
      "step": 290
    },
    {
      "epoch": 0.40472175379426645,
      "grad_norm": 6.513714790344238,
      "learning_rate": 0.00017358490566037738,
      "loss": 0.5442,
      "step": 300
    },
    {
      "epoch": 0.418212478920742,
      "grad_norm": 4.856393337249756,
      "learning_rate": 0.00017268643306379155,
      "loss": 0.5444,
      "step": 310
    },
    {
      "epoch": 0.4317032040472175,
      "grad_norm": 7.252712249755859,
      "learning_rate": 0.00017178796046720576,
      "loss": 0.6071,
      "step": 320
    },
    {
      "epoch": 0.4451939291736931,
      "grad_norm": 6.8953328132629395,
      "learning_rate": 0.00017088948787061996,
      "loss": 0.5622,
      "step": 330
    },
    {
      "epoch": 0.45868465430016864,
      "grad_norm": 6.220505237579346,
      "learning_rate": 0.00016999101527403416,
      "loss": 0.6213,
      "step": 340
    },
    {
      "epoch": 0.47217537942664417,
      "grad_norm": 1.9960452318191528,
      "learning_rate": 0.00016909254267744833,
      "loss": 0.5752,
      "step": 350
    },
    {
      "epoch": 0.4856661045531197,
      "grad_norm": 4.8189778327941895,
      "learning_rate": 0.00016819407008086254,
      "loss": 0.5695,
      "step": 360
    },
    {
      "epoch": 0.4991568296795953,
      "grad_norm": 2.157482624053955,
      "learning_rate": 0.00016729559748427674,
      "loss": 0.5818,
      "step": 370
    },
    {
      "epoch": 0.5126475548060708,
      "grad_norm": 6.034278392791748,
      "learning_rate": 0.00016639712488769091,
      "loss": 0.5632,
      "step": 380
    },
    {
      "epoch": 0.5261382799325464,
      "grad_norm": 3.6643030643463135,
      "learning_rate": 0.00016549865229110512,
      "loss": 0.5149,
      "step": 390
    },
    {
      "epoch": 0.5396290050590219,
      "grad_norm": 3.4874682426452637,
      "learning_rate": 0.00016460017969451932,
      "loss": 0.5712,
      "step": 400
    },
    {
      "epoch": 0.5531197301854974,
      "grad_norm": 5.94505500793457,
      "learning_rate": 0.00016370170709793352,
      "loss": 0.5579,
      "step": 410
    },
    {
      "epoch": 0.5666104553119731,
      "grad_norm": 2.6858978271484375,
      "learning_rate": 0.00016280323450134772,
      "loss": 0.5601,
      "step": 420
    },
    {
      "epoch": 0.5801011804384486,
      "grad_norm": 0.5919632315635681,
      "learning_rate": 0.00016190476190476192,
      "loss": 0.5122,
      "step": 430
    },
    {
      "epoch": 0.5935919055649241,
      "grad_norm": 9.723355293273926,
      "learning_rate": 0.00016100628930817613,
      "loss": 0.5408,
      "step": 440
    },
    {
      "epoch": 0.6070826306913997,
      "grad_norm": 3.421534776687622,
      "learning_rate": 0.0001601078167115903,
      "loss": 0.5125,
      "step": 450
    },
    {
      "epoch": 0.6205733558178752,
      "grad_norm": 1.350819706916809,
      "learning_rate": 0.0001592093441150045,
      "loss": 0.5443,
      "step": 460
    },
    {
      "epoch": 0.6340640809443507,
      "grad_norm": 2.9618473052978516,
      "learning_rate": 0.0001583108715184187,
      "loss": 0.5792,
      "step": 470
    },
    {
      "epoch": 0.6475548060708263,
      "grad_norm": 11.16501522064209,
      "learning_rate": 0.00015741239892183288,
      "loss": 0.5499,
      "step": 480
    },
    {
      "epoch": 0.6610455311973018,
      "grad_norm": 2.7122786045074463,
      "learning_rate": 0.00015651392632524708,
      "loss": 0.589,
      "step": 490
    },
    {
      "epoch": 0.6745362563237775,
      "grad_norm": 6.2460408210754395,
      "learning_rate": 0.00015561545372866128,
      "loss": 0.5422,
      "step": 500
    },
    {
      "epoch": 0.688026981450253,
      "grad_norm": 12.943184852600098,
      "learning_rate": 0.0001547169811320755,
      "loss": 0.5431,
      "step": 510
    },
    {
      "epoch": 0.7015177065767285,
      "grad_norm": 2.4169883728027344,
      "learning_rate": 0.00015381850853548966,
      "loss": 0.4984,
      "step": 520
    },
    {
      "epoch": 0.715008431703204,
      "grad_norm": 5.108154773712158,
      "learning_rate": 0.00015292003593890386,
      "loss": 0.4795,
      "step": 530
    },
    {
      "epoch": 0.7284991568296796,
      "grad_norm": 3.268669605255127,
      "learning_rate": 0.00015202156334231807,
      "loss": 0.4961,
      "step": 540
    },
    {
      "epoch": 0.7419898819561551,
      "grad_norm": 1.7926982641220093,
      "learning_rate": 0.00015112309074573224,
      "loss": 0.5339,
      "step": 550
    },
    {
      "epoch": 0.7554806070826307,
      "grad_norm": 3.6382663249969482,
      "learning_rate": 0.00015022461814914644,
      "loss": 0.4855,
      "step": 560
    },
    {
      "epoch": 0.7689713322091062,
      "grad_norm": 8.025957107543945,
      "learning_rate": 0.00014932614555256067,
      "loss": 0.4901,
      "step": 570
    },
    {
      "epoch": 0.7824620573355818,
      "grad_norm": 4.220882892608643,
      "learning_rate": 0.00014842767295597485,
      "loss": 0.5448,
      "step": 580
    },
    {
      "epoch": 0.7959527824620574,
      "grad_norm": 6.42817497253418,
      "learning_rate": 0.00014752920035938905,
      "loss": 0.4969,
      "step": 590
    },
    {
      "epoch": 0.8094435075885329,
      "grad_norm": 4.182610988616943,
      "learning_rate": 0.00014663072776280325,
      "loss": 0.4863,
      "step": 600
    },
    {
      "epoch": 0.8229342327150084,
      "grad_norm": 3.687934637069702,
      "learning_rate": 0.00014573225516621745,
      "loss": 0.5162,
      "step": 610
    },
    {
      "epoch": 0.836424957841484,
      "grad_norm": 3.8240537643432617,
      "learning_rate": 0.00014483378256963163,
      "loss": 0.5089,
      "step": 620
    },
    {
      "epoch": 0.8499156829679595,
      "grad_norm": 3.3823423385620117,
      "learning_rate": 0.00014393530997304583,
      "loss": 0.5447,
      "step": 630
    },
    {
      "epoch": 0.863406408094435,
      "grad_norm": 4.591256618499756,
      "learning_rate": 0.00014303683737646003,
      "loss": 0.5067,
      "step": 640
    },
    {
      "epoch": 0.8768971332209107,
      "grad_norm": 4.414494514465332,
      "learning_rate": 0.0001421383647798742,
      "loss": 0.4858,
      "step": 650
    },
    {
      "epoch": 0.8903878583473862,
      "grad_norm": 3.4649970531463623,
      "learning_rate": 0.0001412398921832884,
      "loss": 0.5243,
      "step": 660
    },
    {
      "epoch": 0.9038785834738617,
      "grad_norm": 4.813696384429932,
      "learning_rate": 0.0001403414195867026,
      "loss": 0.51,
      "step": 670
    },
    {
      "epoch": 0.9173693086003373,
      "grad_norm": 4.597005844116211,
      "learning_rate": 0.00013944294699011681,
      "loss": 0.5079,
      "step": 680
    },
    {
      "epoch": 0.9308600337268128,
      "grad_norm": 4.291003704071045,
      "learning_rate": 0.000138544474393531,
      "loss": 0.4966,
      "step": 690
    },
    {
      "epoch": 0.9443507588532883,
      "grad_norm": 3.8949058055877686,
      "learning_rate": 0.0001376460017969452,
      "loss": 0.5086,
      "step": 700
    },
    {
      "epoch": 0.9578414839797639,
      "grad_norm": 4.685634613037109,
      "learning_rate": 0.0001367475292003594,
      "loss": 0.5005,
      "step": 710
    },
    {
      "epoch": 0.9713322091062394,
      "grad_norm": 3.9277801513671875,
      "learning_rate": 0.0001358490566037736,
      "loss": 0.4759,
      "step": 720
    },
    {
      "epoch": 0.984822934232715,
      "grad_norm": 4.3011345863342285,
      "learning_rate": 0.0001349505840071878,
      "loss": 0.4371,
      "step": 730
    },
    {
      "epoch": 0.9983136593591906,
      "grad_norm": 3.370706796646118,
      "learning_rate": 0.000134052111410602,
      "loss": 0.4811,
      "step": 740
    }
  ],
  "logging_steps": 10,
  "max_steps": 2226,
  "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": 3.690343765927526e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}