{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1485,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 0.4179236888885498,
      "learning_rate": 3.3670033670033673e-07,
      "loss": 1.6395,
      "step": 20
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 0.41700685024261475,
      "learning_rate": 6.734006734006735e-07,
      "loss": 1.6704,
      "step": 40
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 0.41969290375709534,
      "learning_rate": 1.01010101010101e-06,
      "loss": 1.6681,
      "step": 60
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 0.43269139528274536,
      "learning_rate": 1.346801346801347e-06,
      "loss": 1.5497,
      "step": 80
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 0.4519573450088501,
      "learning_rate": 1.6835016835016838e-06,
      "loss": 1.6648,
      "step": 100
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 0.4950277507305145,
      "learning_rate": 2.02020202020202e-06,
      "loss": 1.5099,
      "step": 120
    },
    {
      "epoch": 0.2828282828282828,
      "grad_norm": 0.39855948090553284,
      "learning_rate": 2.3569023569023572e-06,
      "loss": 1.5483,
      "step": 140
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 0.422542542219162,
      "learning_rate": 2.693602693602694e-06,
      "loss": 1.6411,
      "step": 160
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.393912672996521,
      "learning_rate": 3.0303030303030305e-06,
      "loss": 1.5534,
      "step": 180
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 0.3975161910057068,
      "learning_rate": 3.3670033670033675e-06,
      "loss": 1.5223,
      "step": 200
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.40105801820755005,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 1.4514,
      "step": 220
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 0.4912654459476471,
      "learning_rate": 4.04040404040404e-06,
      "loss": 1.346,
      "step": 240
    },
    {
      "epoch": 0.5252525252525253,
      "grad_norm": 0.739983081817627,
      "learning_rate": 4.377104377104377e-06,
      "loss": 1.2296,
      "step": 260
    },
    {
      "epoch": 0.5656565656565656,
      "grad_norm": 0.48706138134002686,
      "learning_rate": 4.7138047138047145e-06,
      "loss": 0.9912,
      "step": 280
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.5479212999343872,
      "learning_rate": 4.999921328558333e-06,
      "loss": 0.9724,
      "step": 300
    },
    {
      "epoch": 0.6464646464646465,
      "grad_norm": 0.5364205241203308,
      "learning_rate": 4.995377268577495e-06,
      "loss": 0.8591,
      "step": 320
    },
    {
      "epoch": 0.6868686868686869,
      "grad_norm": 0.465681791305542,
      "learning_rate": 4.983854712613647e-06,
      "loss": 0.8323,
      "step": 340
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.4937388300895691,
      "learning_rate": 4.965385884295467e-06,
      "loss": 0.8475,
      "step": 360
    },
    {
      "epoch": 0.7676767676767676,
      "grad_norm": 0.49361351132392883,
      "learning_rate": 4.940022432985096e-06,
      "loss": 0.8435,
      "step": 380
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 0.5452327728271484,
      "learning_rate": 4.907835289337116e-06,
      "loss": 0.7949,
      "step": 400
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 0.6474315524101257,
      "learning_rate": 4.868914466936038e-06,
      "loss": 0.8125,
      "step": 420
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.6446932554244995,
      "learning_rate": 4.823368810567056e-06,
      "loss": 0.8134,
      "step": 440
    },
    {
      "epoch": 0.9292929292929293,
      "grad_norm": 0.5589977502822876,
      "learning_rate": 4.771325691824046e-06,
      "loss": 0.7894,
      "step": 460
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.9970992803573608,
      "learning_rate": 4.7129306529060415e-06,
      "loss": 0.713,
      "step": 480
    },
    {
      "epoch": 1.0101010101010102,
      "grad_norm": 0.6452479958534241,
      "learning_rate": 4.651720442612076e-06,
      "loss": 0.7647,
      "step": 500
    },
    {
      "epoch": 1.0505050505050506,
      "grad_norm": 0.6939157247543335,
      "learning_rate": 4.5814246365869285e-06,
      "loss": 0.7049,
      "step": 520
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.47475144267082214,
      "learning_rate": 4.50530798188761e-06,
      "loss": 0.753,
      "step": 540
    },
    {
      "epoch": 1.1313131313131313,
      "grad_norm": 0.837317943572998,
      "learning_rate": 4.423583344029786e-06,
      "loss": 0.7873,
      "step": 560
    },
    {
      "epoch": 1.1717171717171717,
      "grad_norm": 0.6641133427619934,
      "learning_rate": 4.336479271643833e-06,
      "loss": 0.7261,
      "step": 580
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 0.5319123864173889,
      "learning_rate": 4.244239357322705e-06,
      "loss": 0.7751,
      "step": 600
    },
    {
      "epoch": 1.2525252525252526,
      "grad_norm": 0.5603788495063782,
      "learning_rate": 4.1471215563983125e-06,
      "loss": 0.6936,
      "step": 620
    },
    {
      "epoch": 1.2929292929292928,
      "grad_norm": 0.613637387752533,
      "learning_rate": 4.045397465551513e-06,
      "loss": 0.74,
      "step": 640
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.4830845296382904,
      "learning_rate": 3.93935156327311e-06,
      "loss": 0.7406,
      "step": 660
    },
    {
      "epoch": 1.3737373737373737,
      "grad_norm": 0.6951391696929932,
      "learning_rate": 3.82928041429998e-06,
      "loss": 0.7329,
      "step": 680
    },
    {
      "epoch": 1.4141414141414141,
      "grad_norm": 0.46375522017478943,
      "learning_rate": 3.715491840251172e-06,
      "loss": 0.7398,
      "step": 700
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.5353007912635803,
      "learning_rate": 3.598304058783357e-06,
      "loss": 0.7807,
      "step": 720
    },
    {
      "epoch": 1.494949494949495,
      "grad_norm": 0.4662165939807892,
      "learning_rate": 3.478044793673025e-06,
      "loss": 0.7504,
      "step": 740
    },
    {
      "epoch": 1.5353535353535355,
      "grad_norm": 0.5738622546195984,
      "learning_rate": 3.3550503583141726e-06,
      "loss": 0.7317,
      "step": 760
    },
    {
      "epoch": 1.5757575757575757,
      "grad_norm": 0.6228781342506409,
      "learning_rate": 3.2296647151945116e-06,
      "loss": 0.7184,
      "step": 780
    },
    {
      "epoch": 1.6161616161616161,
      "grad_norm": 0.5194560289382935,
      "learning_rate": 3.102238513980471e-06,
      "loss": 0.7674,
      "step": 800
    },
    {
      "epoch": 1.6565656565656566,
      "grad_norm": 0.5566609501838684,
      "learning_rate": 2.973128110901026e-06,
      "loss": 0.7514,
      "step": 820
    },
    {
      "epoch": 1.696969696969697,
      "grad_norm": 0.6666210293769836,
      "learning_rate": 2.842694572172737e-06,
      "loss": 0.7387,
      "step": 840
    },
    {
      "epoch": 1.7373737373737375,
      "grad_norm": 0.5752224326133728,
      "learning_rate": 2.7113026642529733e-06,
      "loss": 0.706,
      "step": 860
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.5893978476524353,
      "learning_rate": 2.57931983374517e-06,
      "loss": 0.726,
      "step": 880
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.5704651474952698,
      "learning_rate": 2.4471151798088465e-06,
      "loss": 0.7362,
      "step": 900
    },
    {
      "epoch": 1.8585858585858586,
      "grad_norm": 0.5845484733581543,
      "learning_rate": 2.3150584219481644e-06,
      "loss": 0.7105,
      "step": 920
    },
    {
      "epoch": 1.898989898989899,
      "grad_norm": 0.4336787760257721,
      "learning_rate": 2.183518866065627e-06,
      "loss": 0.6878,
      "step": 940
    },
    {
      "epoch": 1.9393939393939394,
      "grad_norm": 0.6674192547798157,
      "learning_rate": 2.0528643716724572e-06,
      "loss": 0.6198,
      "step": 960
    },
    {
      "epoch": 1.9797979797979797,
      "grad_norm": 0.4571789503097534,
      "learning_rate": 1.9234603231439e-06,
      "loss": 0.7451,
      "step": 980
    },
    {
      "epoch": 2.0202020202020203,
      "grad_norm": 0.5650418996810913,
      "learning_rate": 1.7956686078964257e-06,
      "loss": 0.6723,
      "step": 1000
    },
    {
      "epoch": 2.0606060606060606,
      "grad_norm": 0.6139554381370544,
      "learning_rate": 1.6698466043444122e-06,
      "loss": 0.731,
      "step": 1020
    },
    {
      "epoch": 2.101010101010101,
      "grad_norm": 0.5360502600669861,
      "learning_rate": 1.546346182466566e-06,
      "loss": 0.7429,
      "step": 1040
    },
    {
      "epoch": 2.1414141414141414,
      "grad_norm": 0.5541247725486755,
      "learning_rate": 1.425512719777071e-06,
      "loss": 0.7364,
      "step": 1060
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 0.5136921405792236,
      "learning_rate": 1.3076841354533658e-06,
      "loss": 0.7516,
      "step": 1080
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.4408280551433563,
      "learning_rate": 1.1931899453216698e-06,
      "loss": 0.6962,
      "step": 1100
    },
    {
      "epoch": 2.2626262626262625,
      "grad_norm": 0.581975519657135,
      "learning_rate": 1.0823503403430736e-06,
      "loss": 0.6866,
      "step": 1120
    },
    {
      "epoch": 2.303030303030303,
      "grad_norm": 0.5768681764602661,
      "learning_rate": 9.754752911772616e-07,
      "loss": 0.6871,
      "step": 1140
    },
    {
      "epoch": 2.3434343434343434,
      "grad_norm": 0.4733218848705292,
      "learning_rate": 8.728636813280164e-07,
      "loss": 0.6909,
      "step": 1160
    },
    {
      "epoch": 2.3838383838383836,
      "grad_norm": 0.7906825542449951,
      "learning_rate": 7.748024712947205e-07,
      "loss": 0.7064,
      "step": 1180
    },
    {
      "epoch": 2.4242424242424243,
      "grad_norm": 0.5581986904144287,
      "learning_rate": 6.815658960673782e-07,
      "loss": 0.7708,
      "step": 1200
    },
    {
      "epoch": 2.4646464646464645,
      "grad_norm": 0.49159321188926697,
      "learning_rate": 5.934146982094049e-07,
      "loss": 0.7367,
      "step": 1220
    },
    {
      "epoch": 2.505050505050505,
      "grad_norm": 0.6523622274398804,
      "learning_rate": 5.105953986729196e-07,
      "loss": 0.7043,
      "step": 1240
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 0.48596930503845215,
      "learning_rate": 4.3333960738577236e-07,
      "loss": 0.6872,
      "step": 1260
    },
    {
      "epoch": 2.5858585858585856,
      "grad_norm": 0.6256952285766602,
      "learning_rate": 3.6186337553827747e-07,
      "loss": 0.7094,
      "step": 1280
    },
    {
      "epoch": 2.6262626262626263,
      "grad_norm": 0.5648958683013916,
      "learning_rate": 2.963665913810451e-07,
      "loss": 0.6617,
      "step": 1300
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.5555101037025452,
      "learning_rate": 2.370324212235936e-07,
      "loss": 0.7337,
      "step": 1320
    },
    {
      "epoch": 2.707070707070707,
      "grad_norm": 0.6085281372070312,
      "learning_rate": 1.840267971970344e-07,
      "loss": 0.7236,
      "step": 1340
    },
    {
      "epoch": 2.7474747474747474,
      "grad_norm": 0.6137179136276245,
      "learning_rate": 1.3749795321332887e-07,
      "loss": 0.7372,
      "step": 1360
    },
    {
      "epoch": 2.787878787878788,
      "grad_norm": 0.4088153839111328,
      "learning_rate": 9.757601041885694e-08,
      "loss": 0.7663,
      "step": 1380
    },
    {
      "epoch": 2.8282828282828283,
      "grad_norm": 0.5769473314285278,
      "learning_rate": 6.437261330158206e-08,
      "loss": 0.7463,
      "step": 1400
    },
    {
      "epoch": 2.8686868686868685,
      "grad_norm": 0.47392240166664124,
      "learning_rate": 3.798061746947995e-08,
      "loss": 0.6858,
      "step": 1420
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 0.48467594385147095,
      "learning_rate": 1.847382997337943e-08,
      "loss": 0.6589,
      "step": 1440
    },
    {
      "epoch": 2.9494949494949494,
      "grad_norm": 0.5985103249549866,
      "learning_rate": 5.906802900412789e-09,
      "loss": 0.6969,
      "step": 1460
    },
    {
      "epoch": 2.98989898989899,
      "grad_norm": 0.534121036529541,
      "learning_rate": 3.146808153123293e-10,
      "loss": 0.6605,
      "step": 1480
    },
    {
      "epoch": 3.0,
      "step": 1485,
      "total_flos": 6.836552056302797e+16,
      "train_loss": 0.8824553647025266,
      "train_runtime": 1815.9955,
      "train_samples_per_second": 3.271,
      "train_steps_per_second": 0.818
    }
  ],
  "logging_steps": 20,
  "max_steps": 1485,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 6.836552056302797e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}