{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.99695843190267,
  "eval_steps": 500,
  "global_step": 1107,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.027036160865157147,
      "grad_norm": 3.3627634794530086,
      "learning_rate": 5e-06,
      "loss": 0.8839,
      "step": 10
    },
    {
      "epoch": 0.054072321730314295,
      "grad_norm": 1.9703511972746102,
      "learning_rate": 5e-06,
      "loss": 0.6886,
      "step": 20
    },
    {
      "epoch": 0.08110848259547145,
      "grad_norm": 1.895618934030067,
      "learning_rate": 5e-06,
      "loss": 0.649,
      "step": 30
    },
    {
      "epoch": 0.10814464346062859,
      "grad_norm": 3.018653004689794,
      "learning_rate": 5e-06,
      "loss": 0.6375,
      "step": 40
    },
    {
      "epoch": 0.13518080432578575,
      "grad_norm": 2.253174703767421,
      "learning_rate": 5e-06,
      "loss": 0.6233,
      "step": 50
    },
    {
      "epoch": 0.1622169651909429,
      "grad_norm": 2.5770804247981793,
      "learning_rate": 5e-06,
      "loss": 0.6164,
      "step": 60
    },
    {
      "epoch": 0.18925312605610004,
      "grad_norm": 1.9685443465813035,
      "learning_rate": 5e-06,
      "loss": 0.6127,
      "step": 70
    },
    {
      "epoch": 0.21628928692125718,
      "grad_norm": 2.1325268775254034,
      "learning_rate": 5e-06,
      "loss": 0.6039,
      "step": 80
    },
    {
      "epoch": 0.24332544778641432,
      "grad_norm": 1.4745840951249662,
      "learning_rate": 5e-06,
      "loss": 0.601,
      "step": 90
    },
    {
      "epoch": 0.2703616086515715,
      "grad_norm": 1.971048371029162,
      "learning_rate": 5e-06,
      "loss": 0.6032,
      "step": 100
    },
    {
      "epoch": 0.29739776951672864,
      "grad_norm": 1.6569004063408272,
      "learning_rate": 5e-06,
      "loss": 0.6012,
      "step": 110
    },
    {
      "epoch": 0.3244339303818858,
      "grad_norm": 2.057401724353791,
      "learning_rate": 5e-06,
      "loss": 0.5971,
      "step": 120
    },
    {
      "epoch": 0.3514700912470429,
      "grad_norm": 1.525579699451329,
      "learning_rate": 5e-06,
      "loss": 0.5993,
      "step": 130
    },
    {
      "epoch": 0.37850625211220007,
      "grad_norm": 1.60308792852181,
      "learning_rate": 5e-06,
      "loss": 0.5985,
      "step": 140
    },
    {
      "epoch": 0.4055424129773572,
      "grad_norm": 1.6398129211146073,
      "learning_rate": 5e-06,
      "loss": 0.5895,
      "step": 150
    },
    {
      "epoch": 0.43257857384251436,
      "grad_norm": 1.9310976828981994,
      "learning_rate": 5e-06,
      "loss": 0.5918,
      "step": 160
    },
    {
      "epoch": 0.4596147347076715,
      "grad_norm": 1.385584059931609,
      "learning_rate": 5e-06,
      "loss": 0.593,
      "step": 170
    },
    {
      "epoch": 0.48665089557282865,
      "grad_norm": 1.2861159852159507,
      "learning_rate": 5e-06,
      "loss": 0.5918,
      "step": 180
    },
    {
      "epoch": 0.5136870564379858,
      "grad_norm": 1.444176832285908,
      "learning_rate": 5e-06,
      "loss": 0.5885,
      "step": 190
    },
    {
      "epoch": 0.540723217303143,
      "grad_norm": 1.4862672671337698,
      "learning_rate": 5e-06,
      "loss": 0.5867,
      "step": 200
    },
    {
      "epoch": 0.5677593781683001,
      "grad_norm": 1.5075706410261351,
      "learning_rate": 5e-06,
      "loss": 0.5885,
      "step": 210
    },
    {
      "epoch": 0.5947955390334573,
      "grad_norm": 1.2766576640698686,
      "learning_rate": 5e-06,
      "loss": 0.5831,
      "step": 220
    },
    {
      "epoch": 0.6218316998986144,
      "grad_norm": 1.3449220128756942,
      "learning_rate": 5e-06,
      "loss": 0.5853,
      "step": 230
    },
    {
      "epoch": 0.6488678607637716,
      "grad_norm": 1.2820825044433828,
      "learning_rate": 5e-06,
      "loss": 0.5816,
      "step": 240
    },
    {
      "epoch": 0.6759040216289287,
      "grad_norm": 2.0436410705486927,
      "learning_rate": 5e-06,
      "loss": 0.575,
      "step": 250
    },
    {
      "epoch": 0.7029401824940859,
      "grad_norm": 1.5111257680075043,
      "learning_rate": 5e-06,
      "loss": 0.5781,
      "step": 260
    },
    {
      "epoch": 0.729976343359243,
      "grad_norm": 1.4284810364538454,
      "learning_rate": 5e-06,
      "loss": 0.5805,
      "step": 270
    },
    {
      "epoch": 0.7570125042244001,
      "grad_norm": 1.2912410275065467,
      "learning_rate": 5e-06,
      "loss": 0.5753,
      "step": 280
    },
    {
      "epoch": 0.7840486650895573,
      "grad_norm": 1.3589332122580937,
      "learning_rate": 5e-06,
      "loss": 0.5757,
      "step": 290
    },
    {
      "epoch": 0.8110848259547144,
      "grad_norm": 1.4270507706028406,
      "learning_rate": 5e-06,
      "loss": 0.5759,
      "step": 300
    },
    {
      "epoch": 0.8381209868198716,
      "grad_norm": 1.4167431698605149,
      "learning_rate": 5e-06,
      "loss": 0.5728,
      "step": 310
    },
    {
      "epoch": 0.8651571476850287,
      "grad_norm": 1.476127949628171,
      "learning_rate": 5e-06,
      "loss": 0.5711,
      "step": 320
    },
    {
      "epoch": 0.8921933085501859,
      "grad_norm": 1.3615337414773585,
      "learning_rate": 5e-06,
      "loss": 0.5729,
      "step": 330
    },
    {
      "epoch": 0.919229469415343,
      "grad_norm": 1.3530496841079478,
      "learning_rate": 5e-06,
      "loss": 0.5797,
      "step": 340
    },
    {
      "epoch": 0.9462656302805001,
      "grad_norm": 1.6939163932161898,
      "learning_rate": 5e-06,
      "loss": 0.5713,
      "step": 350
    },
    {
      "epoch": 0.9733017911456573,
      "grad_norm": 1.2503611827765622,
      "learning_rate": 5e-06,
      "loss": 0.5711,
      "step": 360
    },
    {
      "epoch": 0.9976343359242987,
      "eval_loss": 0.07110526412725449,
      "eval_runtime": 379.7453,
      "eval_samples_per_second": 26.241,
      "eval_steps_per_second": 0.411,
      "step": 369
    },
    {
      "epoch": 1.0023656640757013,
      "grad_norm": 2.951009083063046,
      "learning_rate": 5e-06,
      "loss": 0.5659,
      "step": 370
    },
    {
      "epoch": 1.0294018249408583,
      "grad_norm": 2.275911553065513,
      "learning_rate": 5e-06,
      "loss": 0.4791,
      "step": 380
    },
    {
      "epoch": 1.0564379858060156,
      "grad_norm": 1.9146887520712665,
      "learning_rate": 5e-06,
      "loss": 0.4742,
      "step": 390
    },
    {
      "epoch": 1.0834741466711728,
      "grad_norm": 1.7060151561064856,
      "learning_rate": 5e-06,
      "loss": 0.4754,
      "step": 400
    },
    {
      "epoch": 1.1105103075363298,
      "grad_norm": 1.4307333510541713,
      "learning_rate": 5e-06,
      "loss": 0.4723,
      "step": 410
    },
    {
      "epoch": 1.1375464684014869,
      "grad_norm": 1.3914100165165024,
      "learning_rate": 5e-06,
      "loss": 0.4744,
      "step": 420
    },
    {
      "epoch": 1.1645826292666441,
      "grad_norm": 1.7655561621577454,
      "learning_rate": 5e-06,
      "loss": 0.4823,
      "step": 430
    },
    {
      "epoch": 1.1916187901318014,
      "grad_norm": 1.750541560120252,
      "learning_rate": 5e-06,
      "loss": 0.4746,
      "step": 440
    },
    {
      "epoch": 1.2186549509969584,
      "grad_norm": 1.3542180298546558,
      "learning_rate": 5e-06,
      "loss": 0.4795,
      "step": 450
    },
    {
      "epoch": 1.2456911118621157,
      "grad_norm": 1.3487709786995525,
      "learning_rate": 5e-06,
      "loss": 0.4811,
      "step": 460
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 1.4890081594482487,
      "learning_rate": 5e-06,
      "loss": 0.4838,
      "step": 470
    },
    {
      "epoch": 1.29976343359243,
      "grad_norm": 1.6710110403178111,
      "learning_rate": 5e-06,
      "loss": 0.4803,
      "step": 480
    },
    {
      "epoch": 1.326799594457587,
      "grad_norm": 1.3946918887630642,
      "learning_rate": 5e-06,
      "loss": 0.4814,
      "step": 490
    },
    {
      "epoch": 1.3538357553227442,
      "grad_norm": 1.349529389304425,
      "learning_rate": 5e-06,
      "loss": 0.4838,
      "step": 500
    },
    {
      "epoch": 1.3808719161879013,
      "grad_norm": 1.7196111346917198,
      "learning_rate": 5e-06,
      "loss": 0.4834,
      "step": 510
    },
    {
      "epoch": 1.4079080770530585,
      "grad_norm": 1.3671419685233817,
      "learning_rate": 5e-06,
      "loss": 0.4868,
      "step": 520
    },
    {
      "epoch": 1.4349442379182156,
      "grad_norm": 1.6390806735333066,
      "learning_rate": 5e-06,
      "loss": 0.4797,
      "step": 530
    },
    {
      "epoch": 1.4619803987833728,
      "grad_norm": 2.033732375443223,
      "learning_rate": 5e-06,
      "loss": 0.4838,
      "step": 540
    },
    {
      "epoch": 1.4890165596485299,
      "grad_norm": 1.6780750098228978,
      "learning_rate": 5e-06,
      "loss": 0.4828,
      "step": 550
    },
    {
      "epoch": 1.5160527205136871,
      "grad_norm": 1.4650147086655332,
      "learning_rate": 5e-06,
      "loss": 0.4833,
      "step": 560
    },
    {
      "epoch": 1.5430888813788441,
      "grad_norm": 1.6474963909234748,
      "learning_rate": 5e-06,
      "loss": 0.4801,
      "step": 570
    },
    {
      "epoch": 1.5701250422440014,
      "grad_norm": 1.2672048074445312,
      "learning_rate": 5e-06,
      "loss": 0.4821,
      "step": 580
    },
    {
      "epoch": 1.5971612031091587,
      "grad_norm": 1.2455105330473952,
      "learning_rate": 5e-06,
      "loss": 0.4858,
      "step": 590
    },
    {
      "epoch": 1.6241973639743157,
      "grad_norm": 1.3365218119955355,
      "learning_rate": 5e-06,
      "loss": 0.4826,
      "step": 600
    },
    {
      "epoch": 1.6512335248394727,
      "grad_norm": 1.453771936609652,
      "learning_rate": 5e-06,
      "loss": 0.4824,
      "step": 610
    },
    {
      "epoch": 1.67826968570463,
      "grad_norm": 1.3826705153584662,
      "learning_rate": 5e-06,
      "loss": 0.4872,
      "step": 620
    },
    {
      "epoch": 1.7053058465697872,
      "grad_norm": 1.3948399069255963,
      "learning_rate": 5e-06,
      "loss": 0.4923,
      "step": 630
    },
    {
      "epoch": 1.7323420074349443,
      "grad_norm": 1.3015399889788772,
      "learning_rate": 5e-06,
      "loss": 0.4897,
      "step": 640
    },
    {
      "epoch": 1.7593781683001013,
      "grad_norm": 1.5649098361174691,
      "learning_rate": 5e-06,
      "loss": 0.4882,
      "step": 650
    },
    {
      "epoch": 1.7864143291652586,
      "grad_norm": 1.4369334673977943,
      "learning_rate": 5e-06,
      "loss": 0.4856,
      "step": 660
    },
    {
      "epoch": 1.8134504900304158,
      "grad_norm": 1.3582444869164498,
      "learning_rate": 5e-06,
      "loss": 0.4872,
      "step": 670
    },
    {
      "epoch": 1.8404866508955728,
      "grad_norm": 1.4410245166819187,
      "learning_rate": 5e-06,
      "loss": 0.4902,
      "step": 680
    },
    {
      "epoch": 1.8675228117607299,
      "grad_norm": 1.2401548016118424,
      "learning_rate": 5e-06,
      "loss": 0.4876,
      "step": 690
    },
    {
      "epoch": 1.8945589726258871,
      "grad_norm": 1.3435104700539477,
      "learning_rate": 5e-06,
      "loss": 0.4906,
      "step": 700
    },
    {
      "epoch": 1.9215951334910444,
      "grad_norm": 1.4535634930233825,
      "learning_rate": 5e-06,
      "loss": 0.4955,
      "step": 710
    },
    {
      "epoch": 1.9486312943562014,
      "grad_norm": 1.267760090624259,
      "learning_rate": 5e-06,
      "loss": 0.4887,
      "step": 720
    },
    {
      "epoch": 1.9756674552213584,
      "grad_norm": 1.2488776839475728,
      "learning_rate": 5e-06,
      "loss": 0.4845,
      "step": 730
    },
    {
      "epoch": 1.9972963839134843,
      "eval_loss": 0.07172359526157379,
      "eval_runtime": 380.951,
      "eval_samples_per_second": 26.158,
      "eval_steps_per_second": 0.41,
      "step": 738
    },
    {
      "epoch": 2.0047313281514025,
      "grad_norm": 3.0892791498740326,
      "learning_rate": 5e-06,
      "loss": 0.4728,
      "step": 740
    },
    {
      "epoch": 2.0317674890165596,
      "grad_norm": 2.0695271423861037,
      "learning_rate": 5e-06,
      "loss": 0.3816,
      "step": 750
    },
    {
      "epoch": 2.0588036498817166,
      "grad_norm": 1.694338271769957,
      "learning_rate": 5e-06,
      "loss": 0.3823,
      "step": 760
    },
    {
      "epoch": 2.085839810746874,
      "grad_norm": 1.492703018660841,
      "learning_rate": 5e-06,
      "loss": 0.3768,
      "step": 770
    },
    {
      "epoch": 2.112875971612031,
      "grad_norm": 1.6552377461262013,
      "learning_rate": 5e-06,
      "loss": 0.3769,
      "step": 780
    },
    {
      "epoch": 2.139912132477188,
      "grad_norm": 1.9420361419361558,
      "learning_rate": 5e-06,
      "loss": 0.3761,
      "step": 790
    },
    {
      "epoch": 2.1669482933423456,
      "grad_norm": 1.5563624108859666,
      "learning_rate": 5e-06,
      "loss": 0.3826,
      "step": 800
    },
    {
      "epoch": 2.1939844542075027,
      "grad_norm": 1.7915429380933352,
      "learning_rate": 5e-06,
      "loss": 0.3804,
      "step": 810
    },
    {
      "epoch": 2.2210206150726597,
      "grad_norm": 1.5584683923881884,
      "learning_rate": 5e-06,
      "loss": 0.3816,
      "step": 820
    },
    {
      "epoch": 2.2480567759378167,
      "grad_norm": 1.60097536516568,
      "learning_rate": 5e-06,
      "loss": 0.3844,
      "step": 830
    },
    {
      "epoch": 2.2750929368029738,
      "grad_norm": 1.6548064908062865,
      "learning_rate": 5e-06,
      "loss": 0.3865,
      "step": 840
    },
    {
      "epoch": 2.3021290976681312,
      "grad_norm": 1.7027619140998314,
      "learning_rate": 5e-06,
      "loss": 0.3818,
      "step": 850
    },
    {
      "epoch": 2.3291652585332883,
      "grad_norm": 1.6016849568444829,
      "learning_rate": 5e-06,
      "loss": 0.3847,
      "step": 860
    },
    {
      "epoch": 2.3562014193984453,
      "grad_norm": 1.8796231385046944,
      "learning_rate": 5e-06,
      "loss": 0.39,
      "step": 870
    },
    {
      "epoch": 2.3832375802636028,
      "grad_norm": 1.5319470307978418,
      "learning_rate": 5e-06,
      "loss": 0.3892,
      "step": 880
    },
    {
      "epoch": 2.41027374112876,
      "grad_norm": 1.7017719120193255,
      "learning_rate": 5e-06,
      "loss": 0.3881,
      "step": 890
    },
    {
      "epoch": 2.437309901993917,
      "grad_norm": 1.5344718368107968,
      "learning_rate": 5e-06,
      "loss": 0.3873,
      "step": 900
    },
    {
      "epoch": 2.464346062859074,
      "grad_norm": 1.6102507634771308,
      "learning_rate": 5e-06,
      "loss": 0.3854,
      "step": 910
    },
    {
      "epoch": 2.4913822237242313,
      "grad_norm": 1.6690069949519504,
      "learning_rate": 5e-06,
      "loss": 0.3872,
      "step": 920
    },
    {
      "epoch": 2.5184183845893884,
      "grad_norm": 1.5743935677314018,
      "learning_rate": 5e-06,
      "loss": 0.3867,
      "step": 930
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 1.5720807503966818,
      "learning_rate": 5e-06,
      "loss": 0.394,
      "step": 940
    },
    {
      "epoch": 2.5724907063197024,
      "grad_norm": 1.4596744684339498,
      "learning_rate": 5e-06,
      "loss": 0.3896,
      "step": 950
    },
    {
      "epoch": 2.59952686718486,
      "grad_norm": 1.4774112887538513,
      "learning_rate": 5e-06,
      "loss": 0.3959,
      "step": 960
    },
    {
      "epoch": 2.626563028050017,
      "grad_norm": 1.6927054304904465,
      "learning_rate": 5e-06,
      "loss": 0.3946,
      "step": 970
    },
    {
      "epoch": 2.653599188915174,
      "grad_norm": 1.6990634986226298,
      "learning_rate": 5e-06,
      "loss": 0.399,
      "step": 980
    },
    {
      "epoch": 2.6806353497803315,
      "grad_norm": 1.5811069605653503,
      "learning_rate": 5e-06,
      "loss": 0.3968,
      "step": 990
    },
    {
      "epoch": 2.7076715106454885,
      "grad_norm": 1.929742002611046,
      "learning_rate": 5e-06,
      "loss": 0.3906,
      "step": 1000
    },
    {
      "epoch": 2.7347076715106455,
      "grad_norm": 1.4332871535309044,
      "learning_rate": 5e-06,
      "loss": 0.3984,
      "step": 1010
    },
    {
      "epoch": 2.7617438323758026,
      "grad_norm": 1.6711055842838813,
      "learning_rate": 5e-06,
      "loss": 0.4002,
      "step": 1020
    },
    {
      "epoch": 2.7887799932409596,
      "grad_norm": 1.6261611517040526,
      "learning_rate": 5e-06,
      "loss": 0.3984,
      "step": 1030
    },
    {
      "epoch": 2.815816154106117,
      "grad_norm": 1.4326621075330992,
      "learning_rate": 5e-06,
      "loss": 0.3972,
      "step": 1040
    },
    {
      "epoch": 2.842852314971274,
      "grad_norm": 1.4683518261050355,
      "learning_rate": 5e-06,
      "loss": 0.399,
      "step": 1050
    },
    {
      "epoch": 2.869888475836431,
      "grad_norm": 1.4432147424830148,
      "learning_rate": 5e-06,
      "loss": 0.3953,
      "step": 1060
    },
    {
      "epoch": 2.8969246367015886,
      "grad_norm": 1.4795447507798194,
      "learning_rate": 5e-06,
      "loss": 0.4029,
      "step": 1070
    },
    {
      "epoch": 2.9239607975667457,
      "grad_norm": 1.54599126728265,
      "learning_rate": 5e-06,
      "loss": 0.3982,
      "step": 1080
    },
    {
      "epoch": 2.9509969584319027,
      "grad_norm": 1.4383101466258315,
      "learning_rate": 5e-06,
      "loss": 0.4018,
      "step": 1090
    },
    {
      "epoch": 2.9780331192970597,
      "grad_norm": 1.3572001471611468,
      "learning_rate": 5e-06,
      "loss": 0.401,
      "step": 1100
    },
    {
      "epoch": 2.99695843190267,
      "eval_loss": 0.07649821043014526,
      "eval_runtime": 382.4679,
      "eval_samples_per_second": 26.054,
      "eval_steps_per_second": 0.408,
      "step": 1107
    },
    {
      "epoch": 2.99695843190267,
      "step": 1107,
      "total_flos": 1854056851046400.0,
      "train_loss": 0.49201587243670264,
      "train_runtime": 63342.9422,
      "train_samples_per_second": 8.967,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 10,
  "max_steps": 1107,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1854056851046400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}