{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9974145360528583,
  "eval_steps": 100,
  "global_step": 870,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02298190175237001,
      "grad_norm": 17.473215136625974,
      "learning_rate": 3.703703703703703e-07,
      "loss": 1.4133,
      "step": 10
    },
    {
      "epoch": 0.04596380350474002,
      "grad_norm": 14.901168774762104,
      "learning_rate": 7.407407407407406e-07,
      "loss": 1.3532,
      "step": 20
    },
    {
      "epoch": 0.06894570525711002,
      "grad_norm": 20.27126148400169,
      "learning_rate": 9.999687519737637e-07,
      "loss": 1.0492,
      "step": 30
    },
    {
      "epoch": 0.09192760700948004,
      "grad_norm": 4.636768648212712,
      "learning_rate": 9.994133401546208e-07,
      "loss": 0.4967,
      "step": 40
    },
    {
      "epoch": 0.11490950876185005,
      "grad_norm": 0.9099176924012666,
      "learning_rate": 9.981644155508344e-07,
      "loss": 0.3076,
      "step": 50
    },
    {
      "epoch": 0.13789141051422005,
      "grad_norm": 0.9678246586532336,
      "learning_rate": 9.962237124876827e-07,
      "loss": 0.2864,
      "step": 60
    },
    {
      "epoch": 0.16087331226659007,
      "grad_norm": 0.9659318174214611,
      "learning_rate": 9.935939259319937e-07,
      "loss": 0.2787,
      "step": 70
    },
    {
      "epoch": 0.18385521401896007,
      "grad_norm": 0.805167386524419,
      "learning_rate": 9.902787077497684e-07,
      "loss": 0.2702,
      "step": 80
    },
    {
      "epoch": 0.20683711577133007,
      "grad_norm": 0.9470260811178999,
      "learning_rate": 9.86282661634998e-07,
      "loss": 0.2655,
      "step": 90
    },
    {
      "epoch": 0.2298190175237001,
      "grad_norm": 0.8090766933333231,
      "learning_rate": 9.816113367167225e-07,
      "loss": 0.2676,
      "step": 100
    },
    {
      "epoch": 0.25280091927607007,
      "grad_norm": 0.7368007334104237,
      "learning_rate": 9.76271219853204e-07,
      "loss": 0.2576,
      "step": 110
    },
    {
      "epoch": 0.2757828210284401,
      "grad_norm": 0.8981477534949046,
      "learning_rate": 9.70269726623921e-07,
      "loss": 0.2575,
      "step": 120
    },
    {
      "epoch": 0.2987647227808101,
      "grad_norm": 0.8279384079792477,
      "learning_rate": 9.636151910318863e-07,
      "loss": 0.2567,
      "step": 130
    },
    {
      "epoch": 0.32174662453318015,
      "grad_norm": 0.7524359854054471,
      "learning_rate": 9.563168539305926e-07,
      "loss": 0.2522,
      "step": 140
    },
    {
      "epoch": 0.3447285262855501,
      "grad_norm": 0.9062422906574367,
      "learning_rate": 9.483848501916577e-07,
      "loss": 0.2532,
      "step": 150
    },
    {
      "epoch": 0.36771042803792015,
      "grad_norm": 0.8033233708041935,
      "learning_rate": 9.398301946309833e-07,
      "loss": 0.2493,
      "step": 160
    },
    {
      "epoch": 0.39069232979029017,
      "grad_norm": 0.7450917369382344,
      "learning_rate": 9.306647667129779e-07,
      "loss": 0.2538,
      "step": 170
    },
    {
      "epoch": 0.41367423154266014,
      "grad_norm": 0.9250714135548187,
      "learning_rate": 9.209012940540805e-07,
      "loss": 0.2561,
      "step": 180
    },
    {
      "epoch": 0.43665613329503017,
      "grad_norm": 0.9058620445402442,
      "learning_rate": 9.105533347484926e-07,
      "loss": 0.2504,
      "step": 190
    },
    {
      "epoch": 0.4596380350474002,
      "grad_norm": 0.8785859807305939,
      "learning_rate": 8.996352585406653e-07,
      "loss": 0.2584,
      "step": 200
    },
    {
      "epoch": 0.48261993679977017,
      "grad_norm": 0.7116360370849345,
      "learning_rate": 8.881622268706824e-07,
      "loss": 0.2493,
      "step": 210
    },
    {
      "epoch": 0.5056018385521401,
      "grad_norm": 1.0284687042792997,
      "learning_rate": 8.761501718202527e-07,
      "loss": 0.2536,
      "step": 220
    },
    {
      "epoch": 0.5285837403045102,
      "grad_norm": 0.8893106047180209,
      "learning_rate": 8.636157739885461e-07,
      "loss": 0.247,
      "step": 230
    },
    {
      "epoch": 0.5515656420568802,
      "grad_norm": 0.8004232352394812,
      "learning_rate": 8.505764393285983e-07,
      "loss": 0.2553,
      "step": 240
    },
    {
      "epoch": 0.5745475438092502,
      "grad_norm": 0.759365345423453,
      "learning_rate": 8.370502749764485e-07,
      "loss": 0.2429,
      "step": 250
    },
    {
      "epoch": 0.5975294455616202,
      "grad_norm": 0.7308397489232427,
      "learning_rate": 8.230560641065758e-07,
      "loss": 0.2527,
      "step": 260
    },
    {
      "epoch": 0.6205113473139903,
      "grad_norm": 0.8096275403043853,
      "learning_rate": 8.086132398485523e-07,
      "loss": 0.246,
      "step": 270
    },
    {
      "epoch": 0.6434932490663603,
      "grad_norm": 0.6917369274707355,
      "learning_rate": 7.937418583011324e-07,
      "loss": 0.2475,
      "step": 280
    },
    {
      "epoch": 0.6664751508187302,
      "grad_norm": 0.7690495541865903,
      "learning_rate": 7.784625706812521e-07,
      "loss": 0.2435,
      "step": 290
    },
    {
      "epoch": 0.6894570525711002,
      "grad_norm": 0.8546741074565729,
      "learning_rate": 7.627965946466166e-07,
      "loss": 0.2359,
      "step": 300
    },
    {
      "epoch": 0.7124389543234703,
      "grad_norm": 0.6943293008079208,
      "learning_rate": 7.467656848316945e-07,
      "loss": 0.2411,
      "step": 310
    },
    {
      "epoch": 0.7354208560758403,
      "grad_norm": 0.6740313335607717,
      "learning_rate": 7.303921026380388e-07,
      "loss": 0.2421,
      "step": 320
    },
    {
      "epoch": 0.7584027578282103,
      "grad_norm": 0.7401309143105904,
      "learning_rate": 7.136985853208823e-07,
      "loss": 0.2403,
      "step": 330
    },
    {
      "epoch": 0.7813846595805803,
      "grad_norm": 0.8972697133537101,
      "learning_rate": 6.967083144149364e-07,
      "loss": 0.2427,
      "step": 340
    },
    {
      "epoch": 0.8043665613329503,
      "grad_norm": 0.8034283234751667,
      "learning_rate": 6.794448835432393e-07,
      "loss": 0.2462,
      "step": 350
    },
    {
      "epoch": 0.8273484630853203,
      "grad_norm": 0.8789698751068616,
      "learning_rate": 6.619322656537552e-07,
      "loss": 0.251,
      "step": 360
    },
    {
      "epoch": 0.8503303648376903,
      "grad_norm": 0.9764465079161455,
      "learning_rate": 6.441947797292236e-07,
      "loss": 0.2453,
      "step": 370
    },
    {
      "epoch": 0.8733122665900603,
      "grad_norm": 1.1399876406432237,
      "learning_rate": 6.262570570164836e-07,
      "loss": 0.2527,
      "step": 380
    },
    {
      "epoch": 0.8962941683424304,
      "grad_norm": 0.68445267974101,
      "learning_rate": 6.081440068221722e-07,
      "loss": 0.247,
      "step": 390
    },
    {
      "epoch": 0.9192760700948004,
      "grad_norm": 0.8957092040404943,
      "learning_rate": 5.898807819222944e-07,
      "loss": 0.2585,
      "step": 400
    },
    {
      "epoch": 0.9422579718471703,
      "grad_norm": 0.8770324868068373,
      "learning_rate": 5.714927436336963e-07,
      "loss": 0.2463,
      "step": 410
    },
    {
      "epoch": 0.9652398735995403,
      "grad_norm": 0.9677676134901866,
      "learning_rate": 5.530054265959485e-07,
      "loss": 0.2389,
      "step": 420
    },
    {
      "epoch": 0.9882217753519104,
      "grad_norm": 0.8462887454752388,
      "learning_rate": 5.344445033125437e-07,
      "loss": 0.2454,
      "step": 430
    },
    {
      "epoch": 1.009192760700948,
      "grad_norm": 0.945055581666683,
      "learning_rate": 5.15835748500649e-07,
      "loss": 0.2213,
      "step": 440
    },
    {
      "epoch": 1.032174662453318,
      "grad_norm": 0.8021937472797979,
      "learning_rate": 4.972050032989174e-07,
      "loss": 0.2397,
      "step": 450
    },
    {
      "epoch": 1.055156564205688,
      "grad_norm": 0.752181939596644,
      "learning_rate": 4.785781393830657e-07,
      "loss": 0.2424,
      "step": 460
    },
    {
      "epoch": 1.078138465958058,
      "grad_norm": 0.8486783739435911,
      "learning_rate": 4.5998102303904327e-07,
      "loss": 0.247,
      "step": 470
    },
    {
      "epoch": 1.101120367710428,
      "grad_norm": 0.8362567515559186,
      "learning_rate": 4.4143947924368765e-07,
      "loss": 0.244,
      "step": 480
    },
    {
      "epoch": 1.124102269462798,
      "grad_norm": 0.811906457503492,
      "learning_rate": 4.2297925580274513e-07,
      "loss": 0.2399,
      "step": 490
    },
    {
      "epoch": 1.147084171215168,
      "grad_norm": 0.777970615999953,
      "learning_rate": 4.0462598759605194e-07,
      "loss": 0.2426,
      "step": 500
    },
    {
      "epoch": 1.170066072967538,
      "grad_norm": 0.8530171512659619,
      "learning_rate": 3.8640516097953404e-07,
      "loss": 0.2472,
      "step": 510
    },
    {
      "epoch": 1.193047974719908,
      "grad_norm": 0.8981370161868097,
      "learning_rate": 3.683420783934537e-07,
      "loss": 0.2442,
      "step": 520
    },
    {
      "epoch": 1.2160298764722781,
      "grad_norm": 0.9690978990653164,
      "learning_rate": 3.50461823226051e-07,
      "loss": 0.2391,
      "step": 530
    },
    {
      "epoch": 1.2390117782246481,
      "grad_norm": 0.6701870042781312,
      "learning_rate": 3.3278922498137454e-07,
      "loss": 0.2433,
      "step": 540
    },
    {
      "epoch": 1.2619936799770182,
      "grad_norm": 0.9229238547578185,
      "learning_rate": 3.153488247996686e-07,
      "loss": 0.2445,
      "step": 550
    },
    {
      "epoch": 1.284975581729388,
      "grad_norm": 0.9247475568229516,
      "learning_rate": 2.981648413781984e-07,
      "loss": 0.2374,
      "step": 560
    },
    {
      "epoch": 1.3079574834817582,
      "grad_norm": 0.9627262851467593,
      "learning_rate": 2.8126113733983646e-07,
      "loss": 0.2448,
      "step": 570
    },
    {
      "epoch": 1.330939385234128,
      "grad_norm": 0.9120263302438554,
      "learning_rate": 2.6466118609611595e-07,
      "loss": 0.2404,
      "step": 580
    },
    {
      "epoch": 1.353921286986498,
      "grad_norm": 0.8397564783689743,
      "learning_rate": 2.4838803925076145e-07,
      "loss": 0.243,
      "step": 590
    },
    {
      "epoch": 1.376903188738868,
      "grad_norm": 0.9304678269053254,
      "learning_rate": 2.3246429458896632e-07,
      "loss": 0.2452,
      "step": 600
    },
    {
      "epoch": 1.399885090491238,
      "grad_norm": 1.0020243730326204,
      "learning_rate": 2.1691206469686806e-07,
      "loss": 0.2422,
      "step": 610
    },
    {
      "epoch": 1.4228669922436081,
      "grad_norm": 0.9391802799011835,
      "learning_rate": 2.0175294625479694e-07,
      "loss": 0.2456,
      "step": 620
    },
    {
      "epoch": 1.4458488939959782,
      "grad_norm": 0.8231683928715978,
      "learning_rate": 1.8700799004693917e-07,
      "loss": 0.2397,
      "step": 630
    },
    {
      "epoch": 1.4688307957483482,
      "grad_norm": 0.8520636087166905,
      "learning_rate": 1.7269767172906352e-07,
      "loss": 0.2441,
      "step": 640
    },
    {
      "epoch": 1.4918126975007182,
      "grad_norm": 0.9752243817047155,
      "learning_rate": 1.5884186339490007e-07,
      "loss": 0.2401,
      "step": 650
    },
    {
      "epoch": 1.5147945992530882,
      "grad_norm": 0.7665318624135639,
      "learning_rate": 1.4545980598066088e-07,
      "loss": 0.2439,
      "step": 660
    },
    {
      "epoch": 1.537776501005458,
      "grad_norm": 0.7876208993507292,
      "learning_rate": 1.325700825460192e-07,
      "loss": 0.241,
      "step": 670
    },
    {
      "epoch": 1.5607584027578283,
      "grad_norm": 0.793689651615786,
      "learning_rate": 1.201905924686518e-07,
      "loss": 0.2439,
      "step": 680
    },
    {
      "epoch": 1.583740304510198,
      "grad_norm": 0.8116081679288228,
      "learning_rate": 1.0833852658818165e-07,
      "loss": 0.2453,
      "step": 690
    },
    {
      "epoch": 1.6067222062625683,
      "grad_norm": 0.7757866512002836,
      "learning_rate": 9.703034333403315e-08,
      "loss": 0.2401,
      "step": 700
    },
    {
      "epoch": 1.6297041080149381,
      "grad_norm": 0.722479725366503,
      "learning_rate": 8.628174587035341e-08,
      "loss": 0.2337,
      "step": 710
    },
    {
      "epoch": 1.6526860097673084,
      "grad_norm": 0.8093501442802761,
      "learning_rate": 7.610766028973709e-08,
      "loss": 0.2359,
      "step": 720
    },
    {
      "epoch": 1.6756679115196782,
      "grad_norm": 0.7148511605688279,
      "learning_rate": 6.65222148860341e-08,
      "loss": 0.2372,
      "step": 730
    },
    {
      "epoch": 1.6986498132720482,
      "grad_norm": 0.7422092393121354,
      "learning_rate": 5.7538720535024675e-08,
      "loss": 0.2449,
      "step": 740
    },
    {
      "epoch": 1.7216317150244183,
      "grad_norm": 0.7434466170466291,
      "learning_rate": 4.916965221020752e-08,
      "loss": 0.2395,
      "step": 750
    },
    {
      "epoch": 1.7446136167767883,
      "grad_norm": 0.7850559068635626,
      "learning_rate": 4.142663165936577e-08,
      "loss": 0.2436,
      "step": 760
    },
    {
      "epoch": 1.7675955185291583,
      "grad_norm": 0.7936937510399781,
      "learning_rate": 3.4320411265970126e-08,
      "loss": 0.2449,
      "step": 770
    },
    {
      "epoch": 1.7905774202815283,
      "grad_norm": 0.8234052802867052,
      "learning_rate": 2.7860859117828982e-08,
      "loss": 0.2367,
      "step": 780
    },
    {
      "epoch": 1.8135593220338984,
      "grad_norm": 0.7210582583571304,
      "learning_rate": 2.2056945303719654e-08,
      "loss": 0.241,
      "step": 790
    },
    {
      "epoch": 1.8365412237862682,
      "grad_norm": 0.7831307857864389,
      "learning_rate": 1.6916729457030876e-08,
      "loss": 0.2493,
      "step": 800
    },
    {
      "epoch": 1.8595231255386384,
      "grad_norm": 0.6495236499007406,
      "learning_rate": 1.2447349563713182e-08,
      "loss": 0.2364,
      "step": 810
    },
    {
      "epoch": 1.8825050272910082,
      "grad_norm": 0.8108447079621942,
      "learning_rate": 8.655012050079568e-09,
      "loss": 0.2418,
      "step": 820
    },
    {
      "epoch": 1.9054869290433785,
      "grad_norm": 0.8061530065813931,
      "learning_rate": 5.5449831642214174e-09,
      "loss": 0.2466,
      "step": 830
    },
    {
      "epoch": 1.9284688307957483,
      "grad_norm": 0.6679927143166136,
      "learning_rate": 3.1215816630071335e-09,
      "loss": 0.2349,
      "step": 840
    },
    {
      "epoch": 1.9514507325481185,
      "grad_norm": 0.8406010249602488,
      "learning_rate": 1.3881728148191773e-09,
      "loss": 0.2448,
      "step": 850
    },
    {
      "epoch": 1.9744326343004883,
      "grad_norm": 0.7452328846254022,
      "learning_rate": 3.471637263576799e-10,
      "loss": 0.2369,
      "step": 860
    },
    {
      "epoch": 1.9974145360528583,
      "grad_norm": 0.9360407578833112,
      "learning_rate": 0.0,
      "loss": 0.243,
      "step": 870
    }
  ],
  "logging_steps": 10,
  "max_steps": 870,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 264326257573888.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}