{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0512,
  "eval_steps": 1000,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00064,
      "grad_norm": 1.8688431978225708,
      "learning_rate": 3.840409643695328e-08,
      "loss": 0.7168,
      "step": 10
    },
    {
      "epoch": 0.00128,
      "grad_norm": 1.835353970527649,
      "learning_rate": 8.10753147002347e-08,
      "loss": 0.7179,
      "step": 20
    },
    {
      "epoch": 0.00192,
      "grad_norm": 1.2541388273239136,
      "learning_rate": 1.2374653296351612e-07,
      "loss": 0.7177,
      "step": 30
    },
    {
      "epoch": 0.00256,
      "grad_norm": 1.1381633281707764,
      "learning_rate": 1.6641775122679754e-07,
      "loss": 0.7312,
      "step": 40
    },
    {
      "epoch": 0.0032,
      "grad_norm": 1.6313824653625488,
      "learning_rate": 2.0908896949007894e-07,
      "loss": 0.7167,
      "step": 50
    },
    {
      "epoch": 0.00384,
      "grad_norm": 1.092464566230774,
      "learning_rate": 2.517601877533604e-07,
      "loss": 0.7201,
      "step": 60
    },
    {
      "epoch": 0.00448,
      "grad_norm": 1.164099097251892,
      "learning_rate": 2.944314060166418e-07,
      "loss": 0.7195,
      "step": 70
    },
    {
      "epoch": 0.00512,
      "grad_norm": 1.9283920526504517,
      "learning_rate": 3.371026242799232e-07,
      "loss": 0.7223,
      "step": 80
    },
    {
      "epoch": 0.00576,
      "grad_norm": 1.8716129064559937,
      "learning_rate": 3.7977384254320464e-07,
      "loss": 0.7151,
      "step": 90
    },
    {
      "epoch": 0.0064,
      "grad_norm": 1.5499262809753418,
      "learning_rate": 4.22445060806486e-07,
      "loss": 0.7211,
      "step": 100
    },
    {
      "epoch": 0.00704,
      "grad_norm": 1.375114917755127,
      "learning_rate": 4.651162790697675e-07,
      "loss": 0.7247,
      "step": 110
    },
    {
      "epoch": 0.00768,
      "grad_norm": 1.384915828704834,
      "learning_rate": 5.077874973330489e-07,
      "loss": 0.7156,
      "step": 120
    },
    {
      "epoch": 0.00832,
      "grad_norm": 1.6376659870147705,
      "learning_rate": 5.504587155963304e-07,
      "loss": 0.7196,
      "step": 130
    },
    {
      "epoch": 0.00896,
      "grad_norm": 1.709489345550537,
      "learning_rate": 5.931299338596117e-07,
      "loss": 0.7215,
      "step": 140
    },
    {
      "epoch": 0.0096,
      "grad_norm": 1.350512146949768,
      "learning_rate": 6.358011521228932e-07,
      "loss": 0.71,
      "step": 150
    },
    {
      "epoch": 0.01024,
      "grad_norm": 2.33050537109375,
      "learning_rate": 6.784723703861745e-07,
      "loss": 0.7191,
      "step": 160
    },
    {
      "epoch": 0.01088,
      "grad_norm": 1.0042874813079834,
      "learning_rate": 7.21143588649456e-07,
      "loss": 0.72,
      "step": 170
    },
    {
      "epoch": 0.01152,
      "grad_norm": 1.1835744380950928,
      "learning_rate": 7.638148069127374e-07,
      "loss": 0.7122,
      "step": 180
    },
    {
      "epoch": 0.01216,
      "grad_norm": 1.949506402015686,
      "learning_rate": 8.064860251760189e-07,
      "loss": 0.7091,
      "step": 190
    },
    {
      "epoch": 0.0128,
      "grad_norm": 1.139626383781433,
      "learning_rate": 8.491572434393003e-07,
      "loss": 0.7046,
      "step": 200
    },
    {
      "epoch": 0.01344,
      "grad_norm": 1.7734779119491577,
      "learning_rate": 8.918284617025817e-07,
      "loss": 0.7135,
      "step": 210
    },
    {
      "epoch": 0.01408,
      "grad_norm": 1.3442974090576172,
      "learning_rate": 9.344996799658632e-07,
      "loss": 0.7127,
      "step": 220
    },
    {
      "epoch": 0.01472,
      "grad_norm": 1.6148335933685303,
      "learning_rate": 9.771708982291445e-07,
      "loss": 0.7168,
      "step": 230
    },
    {
      "epoch": 0.01536,
      "grad_norm": 0.9220213294029236,
      "learning_rate": 1.0198421164924258e-06,
      "loss": 0.7109,
      "step": 240
    },
    {
      "epoch": 0.016,
      "grad_norm": 1.5631815195083618,
      "learning_rate": 1.0625133347557074e-06,
      "loss": 0.7149,
      "step": 250
    },
    {
      "epoch": 0.01664,
      "grad_norm": 1.5052822828292847,
      "learning_rate": 1.1051845530189888e-06,
      "loss": 0.7112,
      "step": 260
    },
    {
      "epoch": 0.01728,
      "grad_norm": 1.6714903116226196,
      "learning_rate": 1.1478557712822702e-06,
      "loss": 0.7128,
      "step": 270
    },
    {
      "epoch": 0.01792,
      "grad_norm": 1.6667262315750122,
      "learning_rate": 1.1905269895455517e-06,
      "loss": 0.7091,
      "step": 280
    },
    {
      "epoch": 0.01856,
      "grad_norm": 1.6861907243728638,
      "learning_rate": 1.233198207808833e-06,
      "loss": 0.7078,
      "step": 290
    },
    {
      "epoch": 0.0192,
      "grad_norm": 1.6259212493896484,
      "learning_rate": 1.2758694260721145e-06,
      "loss": 0.7087,
      "step": 300
    },
    {
      "epoch": 0.01984,
      "grad_norm": 1.207320213317871,
      "learning_rate": 1.318540644335396e-06,
      "loss": 0.7087,
      "step": 310
    },
    {
      "epoch": 0.02048,
      "grad_norm": 1.087124228477478,
      "learning_rate": 1.3612118625986772e-06,
      "loss": 0.7174,
      "step": 320
    },
    {
      "epoch": 0.02112,
      "grad_norm": 1.5668721199035645,
      "learning_rate": 1.4038830808619588e-06,
      "loss": 0.7066,
      "step": 330
    },
    {
      "epoch": 0.02176,
      "grad_norm": 1.5332859754562378,
      "learning_rate": 1.4465542991252401e-06,
      "loss": 0.7115,
      "step": 340
    },
    {
      "epoch": 0.0224,
      "grad_norm": 2.092994451522827,
      "learning_rate": 1.4892255173885215e-06,
      "loss": 0.7085,
      "step": 350
    },
    {
      "epoch": 0.02304,
      "grad_norm": 1.266851544380188,
      "learning_rate": 1.531896735651803e-06,
      "loss": 0.7091,
      "step": 360
    },
    {
      "epoch": 0.02368,
      "grad_norm": 1.290616512298584,
      "learning_rate": 1.5745679539150842e-06,
      "loss": 0.7103,
      "step": 370
    },
    {
      "epoch": 0.02432,
      "grad_norm": 1.2045000791549683,
      "learning_rate": 1.6172391721783658e-06,
      "loss": 0.705,
      "step": 380
    },
    {
      "epoch": 0.02496,
      "grad_norm": 1.828832983970642,
      "learning_rate": 1.6599103904416472e-06,
      "loss": 0.7038,
      "step": 390
    },
    {
      "epoch": 0.0256,
      "grad_norm": 1.7793196439743042,
      "learning_rate": 1.7025816087049288e-06,
      "loss": 0.7085,
      "step": 400
    },
    {
      "epoch": 0.02624,
      "grad_norm": 0.8949472904205322,
      "learning_rate": 1.7452528269682101e-06,
      "loss": 0.7045,
      "step": 410
    },
    {
      "epoch": 0.02688,
      "grad_norm": 1.3071945905685425,
      "learning_rate": 1.7879240452314913e-06,
      "loss": 0.702,
      "step": 420
    },
    {
      "epoch": 0.02752,
      "grad_norm": 1.7497148513793945,
      "learning_rate": 1.8305952634947729e-06,
      "loss": 0.7073,
      "step": 430
    },
    {
      "epoch": 0.02816,
      "grad_norm": 1.0856297016143799,
      "learning_rate": 1.8732664817580542e-06,
      "loss": 0.7008,
      "step": 440
    },
    {
      "epoch": 0.0288,
      "grad_norm": 1.369019627571106,
      "learning_rate": 1.915937700021336e-06,
      "loss": 0.7059,
      "step": 450
    },
    {
      "epoch": 0.02944,
      "grad_norm": 2.0961010456085205,
      "learning_rate": 1.958608918284617e-06,
      "loss": 0.6952,
      "step": 460
    },
    {
      "epoch": 0.03008,
      "grad_norm": 1.6076347827911377,
      "learning_rate": 2.0012801365478988e-06,
      "loss": 0.7074,
      "step": 470
    },
    {
      "epoch": 0.03072,
      "grad_norm": 1.3129311800003052,
      "learning_rate": 2.04395135481118e-06,
      "loss": 0.6994,
      "step": 480
    },
    {
      "epoch": 0.03136,
      "grad_norm": 1.3621476888656616,
      "learning_rate": 2.0866225730744615e-06,
      "loss": 0.696,
      "step": 490
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.9786806106567383,
      "learning_rate": 2.129293791337743e-06,
      "loss": 0.7011,
      "step": 500
    },
    {
      "epoch": 0.03264,
      "grad_norm": 1.4611176252365112,
      "learning_rate": 2.1719650096010242e-06,
      "loss": 0.699,
      "step": 510
    },
    {
      "epoch": 0.03328,
      "grad_norm": 1.0675945281982422,
      "learning_rate": 2.214636227864306e-06,
      "loss": 0.6906,
      "step": 520
    },
    {
      "epoch": 0.03392,
      "grad_norm": 1.6564017534255981,
      "learning_rate": 2.257307446127587e-06,
      "loss": 0.6923,
      "step": 530
    },
    {
      "epoch": 0.03456,
      "grad_norm": 1.228119134902954,
      "learning_rate": 2.2999786643908685e-06,
      "loss": 0.6928,
      "step": 540
    },
    {
      "epoch": 0.0352,
      "grad_norm": 1.9868593215942383,
      "learning_rate": 2.34264988265415e-06,
      "loss": 0.6912,
      "step": 550
    },
    {
      "epoch": 0.03584,
      "grad_norm": 1.2531176805496216,
      "learning_rate": 2.3853211009174317e-06,
      "loss": 0.6923,
      "step": 560
    },
    {
      "epoch": 0.03648,
      "grad_norm": 1.413602352142334,
      "learning_rate": 2.427992319180713e-06,
      "loss": 0.6993,
      "step": 570
    },
    {
      "epoch": 0.03712,
      "grad_norm": 0.9655390977859497,
      "learning_rate": 2.470663537443994e-06,
      "loss": 0.7017,
      "step": 580
    },
    {
      "epoch": 0.03776,
      "grad_norm": 1.962438941001892,
      "learning_rate": 2.5133347557072756e-06,
      "loss": 0.6933,
      "step": 590
    },
    {
      "epoch": 0.0384,
      "grad_norm": 1.1099931001663208,
      "learning_rate": 2.556005973970557e-06,
      "loss": 0.6925,
      "step": 600
    },
    {
      "epoch": 0.03904,
      "grad_norm": 1.1766624450683594,
      "learning_rate": 2.5986771922338383e-06,
      "loss": 0.6894,
      "step": 610
    },
    {
      "epoch": 0.03968,
      "grad_norm": 1.574353814125061,
      "learning_rate": 2.64134841049712e-06,
      "loss": 0.6923,
      "step": 620
    },
    {
      "epoch": 0.04032,
      "grad_norm": 1.194074273109436,
      "learning_rate": 2.6840196287604015e-06,
      "loss": 0.6855,
      "step": 630
    },
    {
      "epoch": 0.04096,
      "grad_norm": 1.1750593185424805,
      "learning_rate": 2.7266908470236826e-06,
      "loss": 0.7002,
      "step": 640
    },
    {
      "epoch": 0.0416,
      "grad_norm": 1.3165347576141357,
      "learning_rate": 2.7693620652869642e-06,
      "loss": 0.6893,
      "step": 650
    },
    {
      "epoch": 0.04224,
      "grad_norm": 1.1079384088516235,
      "learning_rate": 2.812033283550246e-06,
      "loss": 0.6852,
      "step": 660
    },
    {
      "epoch": 0.04288,
      "grad_norm": 1.231327772140503,
      "learning_rate": 2.8547045018135274e-06,
      "loss": 0.695,
      "step": 670
    },
    {
      "epoch": 0.04352,
      "grad_norm": 1.966036319732666,
      "learning_rate": 2.897375720076808e-06,
      "loss": 0.6833,
      "step": 680
    },
    {
      "epoch": 0.04416,
      "grad_norm": 1.0460131168365479,
      "learning_rate": 2.9400469383400897e-06,
      "loss": 0.6802,
      "step": 690
    },
    {
      "epoch": 0.0448,
      "grad_norm": 1.2445200681686401,
      "learning_rate": 2.9827181566033713e-06,
      "loss": 0.6883,
      "step": 700
    },
    {
      "epoch": 0.04544,
      "grad_norm": 1.1759636402130127,
      "learning_rate": 3.025389374866653e-06,
      "loss": 0.682,
      "step": 710
    },
    {
      "epoch": 0.04608,
      "grad_norm": 1.2478561401367188,
      "learning_rate": 3.068060593129934e-06,
      "loss": 0.6802,
      "step": 720
    },
    {
      "epoch": 0.04672,
      "grad_norm": 0.8945108652114868,
      "learning_rate": 3.1107318113932156e-06,
      "loss": 0.6873,
      "step": 730
    },
    {
      "epoch": 0.04736,
      "grad_norm": 1.6810317039489746,
      "learning_rate": 3.153403029656497e-06,
      "loss": 0.6828,
      "step": 740
    },
    {
      "epoch": 0.048,
      "grad_norm": 2.882283926010132,
      "learning_rate": 3.1960742479197783e-06,
      "loss": 0.6797,
      "step": 750
    },
    {
      "epoch": 0.04864,
      "grad_norm": 1.575766921043396,
      "learning_rate": 3.23874546618306e-06,
      "loss": 0.6826,
      "step": 760
    },
    {
      "epoch": 0.04928,
      "grad_norm": 1.8044737577438354,
      "learning_rate": 3.2814166844463415e-06,
      "loss": 0.6837,
      "step": 770
    },
    {
      "epoch": 0.04992,
      "grad_norm": 1.4755513668060303,
      "learning_rate": 3.324087902709623e-06,
      "loss": 0.6815,
      "step": 780
    },
    {
      "epoch": 0.05056,
      "grad_norm": 2.0735654830932617,
      "learning_rate": 3.3667591209729038e-06,
      "loss": 0.6773,
      "step": 790
    },
    {
      "epoch": 0.0512,
      "grad_norm": 0.9823655486106873,
      "learning_rate": 3.4094303392361854e-06,
      "loss": 0.6689,
      "step": 800
    }
  ],
  "logging_steps": 10,
  "max_steps": 46875,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6731943018000000.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}