{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1561,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016020506247997435,
      "grad_norm": 0.29081395268440247,
      "learning_rate": 1.9988337222482776e-05,
      "loss": 1.1990239715576172,
      "step": 25
    },
    {
      "epoch": 0.03204101249599487,
      "grad_norm": 0.11618245393037796,
      "learning_rate": 1.9951414786166656e-05,
      "loss": 0.9829273986816406,
      "step": 50
    },
    {
      "epoch": 0.04806151874399231,
      "grad_norm": 0.10595086961984634,
      "learning_rate": 1.988930588781978e-05,
      "loss": 0.92435546875,
      "step": 75
    },
    {
      "epoch": 0.06408202499198974,
      "grad_norm": 0.09951659291982651,
      "learning_rate": 1.9802167721513908e-05,
      "loss": 0.9162257385253906,
      "step": 100
    },
    {
      "epoch": 0.08010253123998719,
      "grad_norm": 0.08442762494087219,
      "learning_rate": 1.9690220828967406e-05,
      "loss": 0.8908739471435547,
      "step": 125
    },
    {
      "epoch": 0.09612303748798462,
      "grad_norm": 0.10172899067401886,
      "learning_rate": 1.9553748541366756e-05,
      "loss": 0.9406523895263672,
      "step": 150
    },
    {
      "epoch": 0.11214354373598205,
      "grad_norm": 0.11054546386003494,
      "learning_rate": 1.9393096262271533e-05,
      "loss": 0.9146512603759765,
      "step": 175
    },
    {
      "epoch": 0.12816404998397948,
      "grad_norm": 0.10347191989421844,
      "learning_rate": 1.9208670593417723e-05,
      "loss": 0.9219544219970703,
      "step": 200
    },
    {
      "epoch": 0.14418455623197693,
      "grad_norm": 0.10463545471429825,
      "learning_rate": 1.9000938305631975e-05,
      "loss": 0.9444712829589844,
      "step": 225
    },
    {
      "epoch": 0.16020506247997437,
      "grad_norm": 0.10991481691598892,
      "learning_rate": 1.877042515746132e-05,
      "loss": 0.9139762115478516,
      "step": 250
    },
    {
      "epoch": 0.1762255687279718,
      "grad_norm": 0.12124437093734741,
      "learning_rate": 1.8517714564508342e-05,
      "loss": 0.9185218048095704,
      "step": 275
    },
    {
      "epoch": 0.19224607497596924,
      "grad_norm": 0.10786885023117065,
      "learning_rate": 1.824344612283962e-05,
      "loss": 0.9175537872314453,
      "step": 300
    },
    {
      "epoch": 0.20826658122396668,
      "grad_norm": 0.11486810445785522,
      "learning_rate": 1.7948313990204654e-05,
      "loss": 0.8929530334472656,
      "step": 325
    },
    {
      "epoch": 0.2242870874719641,
      "grad_norm": 0.11425229907035828,
      "learning_rate": 1.7633065129162282e-05,
      "loss": 0.8928473663330078,
      "step": 350
    },
    {
      "epoch": 0.24030759371996155,
      "grad_norm": 0.11112677305936813,
      "learning_rate": 1.729849741656112e-05,
      "loss": 0.9173651123046875,
      "step": 375
    },
    {
      "epoch": 0.25632809996795897,
      "grad_norm": 0.1455482393503189,
      "learning_rate": 1.694545762415887e-05,
      "loss": 0.9193742370605469,
      "step": 400
    },
    {
      "epoch": 0.2723486062159564,
      "grad_norm": 0.14621497690677643,
      "learning_rate": 1.657483927549141e-05,
      "loss": 0.8958631134033204,
      "step": 425
    },
    {
      "epoch": 0.28836911246395386,
      "grad_norm": 0.15076446533203125,
      "learning_rate": 1.6187580384415785e-05,
      "loss": 0.9202049255371094,
      "step": 450
    },
    {
      "epoch": 0.3043896187119513,
      "grad_norm": 0.13701656460762024,
      "learning_rate": 1.5784661081050744e-05,
      "loss": 0.9259297943115234,
      "step": 475
    },
    {
      "epoch": 0.32041012495994875,
      "grad_norm": 0.14176012575626373,
      "learning_rate": 1.536710113112345e-05,
      "loss": 0.9286505126953125,
      "step": 500
    },
    {
      "epoch": 0.3364306312079462,
      "grad_norm": 0.1571187525987625,
      "learning_rate": 1.4935957355000695e-05,
      "loss": 0.9105192565917969,
      "step": 525
    },
    {
      "epoch": 0.3524511374559436,
      "grad_norm": 0.13166415691375732,
      "learning_rate": 1.4492320952936956e-05,
      "loss": 0.9180181121826172,
      "step": 550
    },
    {
      "epoch": 0.36847164370394103,
      "grad_norm": 0.1260545551776886,
      "learning_rate": 1.403731474330893e-05,
      "loss": 0.8934297943115235,
      "step": 575
    },
    {
      "epoch": 0.3844921499519385,
      "grad_norm": 0.15511398017406464,
      "learning_rate": 1.3572090320826396e-05,
      "loss": 0.9190473175048828,
      "step": 600
    },
    {
      "epoch": 0.4005126561999359,
      "grad_norm": 0.1460423320531845,
      "learning_rate": 1.3097825141911824e-05,
      "loss": 0.9066439056396485,
      "step": 625
    },
    {
      "epoch": 0.41653316244793337,
      "grad_norm": 0.17855304479599,
      "learning_rate": 1.261571954462547e-05,
      "loss": 0.899425277709961,
      "step": 650
    },
    {
      "epoch": 0.4325536686959308,
      "grad_norm": 0.16846759617328644,
      "learning_rate": 1.2126993710678361e-05,
      "loss": 0.9050975799560547,
      "step": 675
    },
    {
      "epoch": 0.4485741749439282,
      "grad_norm": 0.16906635463237762,
      "learning_rate": 1.1632884577222106e-05,
      "loss": 0.9127249145507812,
      "step": 700
    },
    {
      "epoch": 0.46459468119192565,
      "grad_norm": 0.15867382287979126,
      "learning_rate": 1.1134642706231687e-05,
      "loss": 0.9023185729980469,
      "step": 725
    },
    {
      "epoch": 0.4806151874399231,
      "grad_norm": 0.16034585237503052,
      "learning_rate": 1.0633529119404571e-05,
      "loss": 0.9134428405761719,
      "step": 750
    },
    {
      "epoch": 0.49663569368792054,
      "grad_norm": 0.16358235478401184,
      "learning_rate": 1.013081210658687e-05,
      "loss": 0.8995558166503906,
      "step": 775
    },
    {
      "epoch": 0.5126561999359179,
      "grad_norm": 0.15758606791496277,
      "learning_rate": 9.627764015804225e-06,
      "loss": 0.8870352172851562,
      "step": 800
    },
    {
      "epoch": 0.5286767061839154,
      "grad_norm": 0.16830310225486755,
      "learning_rate": 9.125658033021683e-06,
      "loss": 0.8971255493164062,
      "step": 825
    },
    {
      "epoch": 0.5446972124319128,
      "grad_norm": 0.16267818212509155,
      "learning_rate": 8.6257649597828e-06,
      "loss": 0.9000907135009766,
      "step": 850
    },
    {
      "epoch": 0.5607177186799103,
      "grad_norm": 0.15891553461551666,
      "learning_rate": 8.129349996883551e-06,
      "loss": 0.899490966796875,
      "step": 875
    },
    {
      "epoch": 0.5767382249279077,
      "grad_norm": 0.14320583641529083,
      "learning_rate": 7.637669542221446e-06,
      "loss": 0.8845912933349609,
      "step": 900
    },
    {
      "epoch": 0.5927587311759052,
      "grad_norm": 0.16313546895980835,
      "learning_rate": 7.1519680109242486e-06,
      "loss": 0.9202222442626953,
      "step": 925
    },
    {
      "epoch": 0.6087792374239026,
      "grad_norm": 0.17441782355308533,
      "learning_rate": 6.673474685806436e-06,
      "loss": 0.9076329803466797,
      "step": 950
    },
    {
      "epoch": 0.6247997436719,
      "grad_norm": 0.14890457689762115,
      "learning_rate": 6.2034006061246295e-06,
      "loss": 0.9191471862792969,
      "step": 975
    },
    {
      "epoch": 0.6408202499198975,
      "grad_norm": 0.17238198220729828,
      "learning_rate": 5.742935502506485e-06,
      "loss": 0.9056331634521484,
      "step": 1000
    },
    {
      "epoch": 0.656840756167895,
      "grad_norm": 0.1785092055797577,
      "learning_rate": 5.293244785810452e-06,
      "loss": 0.9191907501220703,
      "step": 1025
    },
    {
      "epoch": 0.6728612624158924,
      "grad_norm": 0.15417782962322235,
      "learning_rate": 4.855466597537515e-06,
      "loss": 0.9085941314697266,
      "step": 1050
    },
    {
      "epoch": 0.6888817686638897,
      "grad_norm": 0.1511709988117218,
      "learning_rate": 4.430708929260105e-06,
      "loss": 0.9095938110351562,
      "step": 1075
    },
    {
      "epoch": 0.7049022749118872,
      "grad_norm": 0.1562037169933319,
      "learning_rate": 4.0200468183587556e-06,
      "loss": 0.8718026733398437,
      "step": 1100
    },
    {
      "epoch": 0.7209227811598846,
      "grad_norm": 0.16901475191116333,
      "learning_rate": 3.624519627163946e-06,
      "loss": 0.8942552947998047,
      "step": 1125
    },
    {
      "epoch": 0.7369432874078821,
      "grad_norm": 0.15361268818378448,
      "learning_rate": 3.24512841238944e-06,
      "loss": 0.923448715209961,
      "step": 1150
    },
    {
      "epoch": 0.7529637936558795,
      "grad_norm": 0.166425421833992,
      "learning_rate": 2.8828333915149675e-06,
      "loss": 0.9021080017089844,
      "step": 1175
    },
    {
      "epoch": 0.768984299903877,
      "grad_norm": 0.17839516699314117,
      "learning_rate": 2.5385515125306683e-06,
      "loss": 0.9276787567138672,
      "step": 1200
    },
    {
      "epoch": 0.7850048061518744,
      "grad_norm": 0.17206133902072906,
      "learning_rate": 2.213154133194122e-06,
      "loss": 0.9214431762695312,
      "step": 1225
    },
    {
      "epoch": 0.8010253123998718,
      "grad_norm": 0.1896800845861435,
      "learning_rate": 1.907464815673702e-06,
      "loss": 0.9126302337646485,
      "step": 1250
    },
    {
      "epoch": 0.8170458186478693,
      "grad_norm": 0.1757972687482834,
      "learning_rate": 1.622257242159756e-06,
      "loss": 0.9005342102050782,
      "step": 1275
    },
    {
      "epoch": 0.8330663248958667,
      "grad_norm": 0.1621798872947693,
      "learning_rate": 1.3582532567192509e-06,
      "loss": 0.8823390960693359,
      "step": 1300
    },
    {
      "epoch": 0.8490868311438642,
      "grad_norm": 0.15191422402858734,
      "learning_rate": 1.1161210383496479e-06,
      "loss": 0.9226659393310547,
      "step": 1325
    },
    {
      "epoch": 0.8651073373918616,
      "grad_norm": 0.18351206183433533,
      "learning_rate": 8.964734098561001e-07,
      "loss": 0.9057015228271484,
      "step": 1350
    },
    {
      "epoch": 0.881127843639859,
      "grad_norm": 0.16578508913516998,
      "learning_rate": 6.998662868319139e-07,
      "loss": 0.8983650970458984,
      "step": 1375
    },
    {
      "epoch": 0.8971483498878564,
      "grad_norm": 0.17020930349826813,
      "learning_rate": 5.267972706679991e-07,
      "loss": 0.9050147247314453,
      "step": 1400
    },
    {
      "epoch": 0.9131688561358539,
      "grad_norm": 0.17416594922542572,
      "learning_rate": 3.777043891521559e-07,
      "loss": 0.8866185760498047,
      "step": 1425
    },
    {
      "epoch": 0.9291893623838513,
      "grad_norm": 0.16963180899620056,
      "learning_rate": 2.529649878457985e-07,
      "loss": 0.9323723602294922,
      "step": 1450
    },
    {
      "epoch": 0.9452098686318487,
      "grad_norm": 0.18463164567947388,
      "learning_rate": 1.528947750439036e-07,
      "loss": 0.9038640594482422,
      "step": 1475
    },
    {
      "epoch": 0.9612303748798462,
      "grad_norm": 0.1755848526954651,
      "learning_rate": 7.774702273535938e-08,
      "loss": 0.904787826538086,
      "step": 1500
    },
    {
      "epoch": 0.9772508811278436,
      "grad_norm": 0.1582230031490326,
      "learning_rate": 2.77119255860403e-08,
      "loss": 0.8763291168212891,
      "step": 1525
    },
    {
      "epoch": 0.9932713873758411,
      "grad_norm": 0.20413701236248016,
      "learning_rate": 2.916119566973574e-09,
      "loss": 0.920826416015625,
      "step": 1550
    }
  ],
  "logging_steps": 25,
  "max_steps": 1561,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 3.711778068942029e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}