{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100.0,
  "global_step": 406,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0024645717806531116,
      "grad_norm": 4.4285664558410645,
      "learning_rate": 1.5384615384615387e-06,
      "loss": 0.35851195454597473,
      "step": 1,
      "token_acc": 0.9010631754678851
    },
    {
      "epoch": 0.024645717806531114,
      "grad_norm": 2.0952308177948,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.35579657554626465,
      "step": 10,
      "token_acc": 0.8943837802540097
    },
    {
      "epoch": 0.04929143561306223,
      "grad_norm": 1.162745714187622,
      "learning_rate": 1.9984348087759785e-05,
      "loss": 0.3231017589569092,
      "step": 20,
      "token_acc": 0.9000949342463621
    },
    {
      "epoch": 0.07393715341959335,
      "grad_norm": 1.0469155311584473,
      "learning_rate": 1.9907803587786273e-05,
      "loss": 0.28833014965057374,
      "step": 30,
      "token_acc": 0.9078340515688281
    },
    {
      "epoch": 0.09858287122612445,
      "grad_norm": 0.9065660834312439,
      "learning_rate": 1.976797992107587e-05,
      "loss": 0.26889336109161377,
      "step": 40,
      "token_acc": 0.9149504419788507
    },
    {
      "epoch": 0.12322858903265557,
      "grad_norm": 0.9003399014472961,
      "learning_rate": 1.9565770113518827e-05,
      "loss": 0.23356928825378417,
      "step": 50,
      "token_acc": 0.9236266795610063
    },
    {
      "epoch": 0.1478743068391867,
      "grad_norm": 0.8582137823104858,
      "learning_rate": 1.9302465638852484e-05,
      "loss": 0.24206771850585937,
      "step": 60,
      "token_acc": 0.9218463180747745
    },
    {
      "epoch": 0.1725200246457178,
      "grad_norm": 1.0135269165039062,
      "learning_rate": 1.897974817027588e-05,
      "loss": 0.23689332008361816,
      "step": 70,
      "token_acc": 0.9239593434853264
    },
    {
      "epoch": 0.1971657424522489,
      "grad_norm": 0.8614147305488586,
      "learning_rate": 1.8599678839938237e-05,
      "loss": 0.22692694664001464,
      "step": 80,
      "token_acc": 0.9264865287496846
    },
    {
      "epoch": 0.22181146025878004,
      "grad_norm": 0.9398002028465271,
      "learning_rate": 1.8164685074898737e-05,
      "loss": 0.21968631744384765,
      "step": 90,
      "token_acc": 0.9295838807428485
    },
    {
      "epoch": 0.24645717806531114,
      "grad_norm": 0.7476951479911804,
      "learning_rate": 1.7677545093633713e-05,
      "loss": 0.2011038541793823,
      "step": 100,
      "token_acc": 0.9344147595660709
    },
    {
      "epoch": 0.2711028958718423,
      "grad_norm": 0.7503615617752075,
      "learning_rate": 1.7141370162108973e-05,
      "loss": 0.2057852029800415,
      "step": 110,
      "token_acc": 0.9330569189360355
    },
    {
      "epoch": 0.2957486136783734,
      "grad_norm": 0.9481154084205627,
      "learning_rate": 1.6559584722744228e-05,
      "loss": 0.17612676620483397,
      "step": 120,
      "token_acc": 0.9414746669207006
    },
    {
      "epoch": 0.3203943314849045,
      "grad_norm": 0.7433750629425049,
      "learning_rate": 1.5935904523181872e-05,
      "loss": 0.1758814573287964,
      "step": 130,
      "token_acc": 0.9421560794951352
    },
    {
      "epoch": 0.3450400492914356,
      "grad_norm": 0.83556067943573,
      "learning_rate": 1.527431288454741e-05,
      "loss": 0.16333937644958496,
      "step": 140,
      "token_acc": 0.9466238242526768
    },
    {
      "epoch": 0.36968576709796674,
      "grad_norm": 0.7809082269668579,
      "learning_rate": 1.4579035260771374e-05,
      "loss": 0.1606190323829651,
      "step": 150,
      "token_acc": 0.9473938285655826
    },
    {
      "epoch": 0.3943314849044978,
      "grad_norm": 0.8688177466392517,
      "learning_rate": 1.3854512251457248e-05,
      "loss": 0.15198636054992676,
      "step": 160,
      "token_acc": 0.9505260762845087
    },
    {
      "epoch": 0.41897720271102895,
      "grad_norm": 0.7590353488922119,
      "learning_rate": 1.3105371240656894e-05,
      "loss": 0.14457361698150634,
      "step": 170,
      "token_acc": 0.952075147520667
    },
    {
      "epoch": 0.4436229205175601,
      "grad_norm": 0.9393133521080017,
      "learning_rate": 1.233639684269092e-05,
      "loss": 0.15146660804748535,
      "step": 180,
      "token_acc": 0.9508095578367639
    },
    {
      "epoch": 0.4682686383240912,
      "grad_norm": 0.7637022733688354,
      "learning_rate": 1.1552500343770658e-05,
      "loss": 0.15038838386535644,
      "step": 190,
      "token_acc": 0.951290851489551
    },
    {
      "epoch": 0.4929143561306223,
      "grad_norm": 0.6834350824356079,
      "learning_rate": 1.0758688334592034e-05,
      "loss": 0.12394154071807861,
      "step": 200,
      "token_acc": 0.9598665193837932
    },
    {
      "epoch": 0.5175600739371534,
      "grad_norm": 0.7546061277389526,
      "learning_rate": 9.960030734238672e-06,
      "loss": 0.12569220066070558,
      "step": 210,
      "token_acc": 0.9589528875283819
    },
    {
      "epoch": 0.5422057917436846,
      "grad_norm": 0.779545783996582,
      "learning_rate": 9.161628409619237e-06,
      "loss": 0.12487788200378418,
      "step": 220,
      "token_acc": 0.9589421215806513
    },
    {
      "epoch": 0.5668515095502157,
      "grad_norm": 0.7616660594940186,
      "learning_rate": 8.368580597247156e-06,
      "loss": 0.11189166307449341,
      "step": 230,
      "token_acc": 0.9632912747367435
    },
    {
      "epoch": 0.5914972273567468,
      "grad_norm": 0.8745431303977966,
      "learning_rate": 7.5859523354333695e-06,
      "loss": 0.09375449419021606,
      "step": 240,
      "token_acc": 0.9687846226896224
    },
    {
      "epoch": 0.6161429451632778,
      "grad_norm": 0.9441593885421753,
      "learning_rate": 6.818742114896185e-06,
      "loss": 0.10027874708175659,
      "step": 250,
      "token_acc": 0.9676357965433932
    },
    {
      "epoch": 0.640788662969809,
      "grad_norm": 0.7328006625175476,
      "learning_rate": 6.071849954397321e-06,
      "loss": 0.09634994268417359,
      "step": 260,
      "token_acc": 0.9679430186907485
    },
    {
      "epoch": 0.6654343807763401,
      "grad_norm": 0.7206295728683472,
      "learning_rate": 5.35004610529874e-06,
      "loss": 0.1047346830368042,
      "step": 270,
      "token_acc": 0.9656306522961448
    },
    {
      "epoch": 0.6900800985828712,
      "grad_norm": 0.7431440353393555,
      "learning_rate": 4.657940584917983e-06,
      "loss": 0.0888257384300232,
      "step": 280,
      "token_acc": 0.9706398288469873
    },
    {
      "epoch": 0.7147258163894024,
      "grad_norm": 0.8753840327262878,
      "learning_rate": 3.999953733266395e-06,
      "loss": 0.09608613252639771,
      "step": 290,
      "token_acc": 0.969108049311095
    },
    {
      "epoch": 0.7393715341959335,
      "grad_norm": 0.6335790753364563,
      "learning_rate": 3.380287981218536e-06,
      "loss": 0.09120213985443115,
      "step": 300,
      "token_acc": 0.9703202351742667
    },
    {
      "epoch": 0.7640172520024646,
      "grad_norm": 0.785146176815033,
      "learning_rate": 2.8029010104237786e-06,
      "loss": 0.09605880975723266,
      "step": 310,
      "token_acc": 0.9673275924451842
    },
    {
      "epoch": 0.7886629698089956,
      "grad_norm": 0.6153045296669006,
      "learning_rate": 2.2714804763824448e-06,
      "loss": 0.08603854775428772,
      "step": 320,
      "token_acc": 0.9712083643140942
    },
    {
      "epoch": 0.8133086876155268,
      "grad_norm": 0.9868772029876709,
      "learning_rate": 1.7894204561251416e-06,
      "loss": 0.08434219360351562,
      "step": 330,
      "token_acc": 0.9721527649830232
    },
    {
      "epoch": 0.8379544054220579,
      "grad_norm": 0.5985115766525269,
      "learning_rate": 1.359799770919238e-06,
      "loss": 0.07187292575836182,
      "step": 340,
      "token_acc": 0.9767571751932819
    },
    {
      "epoch": 0.862600123228589,
      "grad_norm": 0.6144799590110779,
      "learning_rate": 9.853623224511078e-07,
      "loss": 0.08109406232833863,
      "step": 350,
      "token_acc": 0.9739249053643897
    },
    {
      "epoch": 0.8872458410351202,
      "grad_norm": 0.559677243232727,
      "learning_rate": 6.684995680729489e-07,
      "loss": 0.08470932245254517,
      "step": 360,
      "token_acc": 0.9718354862416234
    },
    {
      "epoch": 0.9118915588416513,
      "grad_norm": 0.7215991616249084,
      "learning_rate": 4.1123524704133276e-07,
      "loss": 0.07193084955215454,
      "step": 370,
      "token_acc": 0.9762649270830526
    },
    {
      "epoch": 0.9365372766481824,
      "grad_norm": 0.6857699155807495,
      "learning_rate": 2.1521245529793732e-07,
      "loss": 0.08433130979537964,
      "step": 380,
      "token_acc": 0.9732891762933199
    },
    {
      "epoch": 0.9611829944547134,
      "grad_norm": 0.6883733868598938,
      "learning_rate": 8.1683151343257e-08,
      "loss": 0.07680711746215821,
      "step": 390,
      "token_acc": 0.9747542420637405
    },
    {
      "epoch": 0.9858287122612446,
      "grad_norm": 0.6657755970954895,
      "learning_rate": 1.150016022719691e-08,
      "loss": 0.0683711290359497,
      "step": 400,
      "token_acc": 0.9770520741394528
    }
  ],
  "logging_steps": 10,
  "max_steps": 406,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 325926586712064.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}