{
  "best_metric": 1.00209379196167,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 2.0202020202020203,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.020202020202020204,
      "grad_norm": 5.289388179779053,
      "learning_rate": 5e-06,
      "loss": 3.9043,
      "step": 1
    },
    {
      "epoch": 0.020202020202020204,
      "eval_loss": 5.048096656799316,
      "eval_runtime": 4.2841,
      "eval_samples_per_second": 19.607,
      "eval_steps_per_second": 9.804,
      "step": 1
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 6.221162796020508,
      "learning_rate": 1e-05,
      "loss": 4.4545,
      "step": 2
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 6.830175876617432,
      "learning_rate": 1.5e-05,
      "loss": 4.4955,
      "step": 3
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 7.195596694946289,
      "learning_rate": 2e-05,
      "loss": 4.5755,
      "step": 4
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 6.808708667755127,
      "learning_rate": 2.5e-05,
      "loss": 4.6561,
      "step": 5
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 7.063287258148193,
      "learning_rate": 3e-05,
      "loss": 4.7259,
      "step": 6
    },
    {
      "epoch": 0.1414141414141414,
      "grad_norm": 7.591980934143066,
      "learning_rate": 3.5e-05,
      "loss": 4.7279,
      "step": 7
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 6.363076686859131,
      "learning_rate": 4e-05,
      "loss": 4.4684,
      "step": 8
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 4.987633228302002,
      "learning_rate": 4.5e-05,
      "loss": 4.4504,
      "step": 9
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 4.296280860900879,
      "learning_rate": 5e-05,
      "loss": 4.0533,
      "step": 10
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 3.862339735031128,
      "learning_rate": 5.500000000000001e-05,
      "loss": 4.0011,
      "step": 11
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 3.470243453979492,
      "learning_rate": 6e-05,
      "loss": 4.0229,
      "step": 12
    },
    {
      "epoch": 0.26262626262626265,
      "grad_norm": 2.2312989234924316,
      "learning_rate": 6.500000000000001e-05,
      "loss": 2.9522,
      "step": 13
    },
    {
      "epoch": 0.2828282828282828,
      "grad_norm": 2.9605283737182617,
      "learning_rate": 7e-05,
      "loss": 3.0682,
      "step": 14
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 2.9798710346221924,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.2887,
      "step": 15
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 2.613205671310425,
      "learning_rate": 8e-05,
      "loss": 3.043,
      "step": 16
    },
    {
      "epoch": 0.3434343434343434,
      "grad_norm": 2.627354860305786,
      "learning_rate": 8.5e-05,
      "loss": 3.0214,
      "step": 17
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 2.2543275356292725,
      "learning_rate": 9e-05,
      "loss": 2.7168,
      "step": 18
    },
    {
      "epoch": 0.3838383838383838,
      "grad_norm": 1.868975281715393,
      "learning_rate": 9.5e-05,
      "loss": 2.8404,
      "step": 19
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 1.8961381912231445,
      "learning_rate": 0.0001,
      "loss": 2.6021,
      "step": 20
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 1.7066221237182617,
      "learning_rate": 9.998517349225698e-05,
      "loss": 2.5649,
      "step": 21
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 1.9032788276672363,
      "learning_rate": 9.994070276204116e-05,
      "loss": 2.3567,
      "step": 22
    },
    {
      "epoch": 0.46464646464646464,
      "grad_norm": 1.6003658771514893,
      "learning_rate": 9.986661418317759e-05,
      "loss": 2.2917,
      "step": 23
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 1.7048600912094116,
      "learning_rate": 9.976295169466178e-05,
      "loss": 2.5865,
      "step": 24
    },
    {
      "epoch": 0.5050505050505051,
      "grad_norm": 1.562213659286499,
      "learning_rate": 9.962977677460132e-05,
      "loss": 2.0904,
      "step": 25
    },
    {
      "epoch": 0.5252525252525253,
      "grad_norm": 1.4012371301651,
      "learning_rate": 9.946716840375551e-05,
      "loss": 1.9331,
      "step": 26
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 1.4172520637512207,
      "learning_rate": 9.927522301869515e-05,
      "loss": 2.04,
      "step": 27
    },
    {
      "epoch": 0.5656565656565656,
      "grad_norm": 1.2087681293487549,
      "learning_rate": 9.905405445460972e-05,
      "loss": 2.0439,
      "step": 28
    },
    {
      "epoch": 0.5858585858585859,
      "grad_norm": 1.3168634176254272,
      "learning_rate": 9.880379387779637e-05,
      "loss": 2.0186,
      "step": 29
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 1.3884882926940918,
      "learning_rate": 9.852458970787026e-05,
      "loss": 1.7423,
      "step": 30
    },
    {
      "epoch": 0.6262626262626263,
      "grad_norm": 1.2662495374679565,
      "learning_rate": 9.821660752974293e-05,
      "loss": 1.8134,
      "step": 31
    },
    {
      "epoch": 0.6464646464646465,
      "grad_norm": 1.2647764682769775,
      "learning_rate": 9.78800299954203e-05,
      "loss": 1.9441,
      "step": 32
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.4162395000457764,
      "learning_rate": 9.751505671567913e-05,
      "loss": 1.7532,
      "step": 33
    },
    {
      "epoch": 0.6868686868686869,
      "grad_norm": 1.3138062953948975,
      "learning_rate": 9.712190414168572e-05,
      "loss": 1.8705,
      "step": 34
    },
    {
      "epoch": 0.7070707070707071,
      "grad_norm": 1.2262977361679077,
      "learning_rate": 9.67008054366274e-05,
      "loss": 1.7738,
      "step": 35
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 1.5342642068862915,
      "learning_rate": 9.625201033743261e-05,
      "loss": 1.9003,
      "step": 36
    },
    {
      "epoch": 0.7474747474747475,
      "grad_norm": 1.0173803567886353,
      "learning_rate": 9.577578500666187e-05,
      "loss": 1.4541,
      "step": 37
    },
    {
      "epoch": 0.7676767676767676,
      "grad_norm": 0.9901583194732666,
      "learning_rate": 9.527241187465734e-05,
      "loss": 1.577,
      "step": 38
    },
    {
      "epoch": 0.7878787878787878,
      "grad_norm": 0.9777953028678894,
      "learning_rate": 9.474218947204459e-05,
      "loss": 1.396,
      "step": 39
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 1.240479588508606,
      "learning_rate": 9.418543225268596e-05,
      "loss": 1.6402,
      "step": 40
    },
    {
      "epoch": 0.8282828282828283,
      "grad_norm": 1.1354819536209106,
      "learning_rate": 9.360247040719039e-05,
      "loss": 1.5014,
      "step": 41
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 1.0067344903945923,
      "learning_rate": 9.29936496670905e-05,
      "loss": 1.4353,
      "step": 42
    },
    {
      "epoch": 0.8686868686868687,
      "grad_norm": 1.0829236507415771,
      "learning_rate": 9.235933109980301e-05,
      "loss": 1.4657,
      "step": 43
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 1.0891422033309937,
      "learning_rate": 9.16998908944939e-05,
      "loss": 1.5081,
      "step": 44
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 1.0870673656463623,
      "learning_rate": 9.101572013897555e-05,
      "loss": 1.4492,
      "step": 45
    },
    {
      "epoch": 0.9292929292929293,
      "grad_norm": 1.154875636100769,
      "learning_rate": 9.030722458776814e-05,
      "loss": 1.4784,
      "step": 46
    },
    {
      "epoch": 0.9494949494949495,
      "grad_norm": 1.2022784948349,
      "learning_rate": 8.957482442146272e-05,
      "loss": 1.4172,
      "step": 47
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 1.1286842823028564,
      "learning_rate": 8.881895399752874e-05,
      "loss": 1.3976,
      "step": 48
    },
    {
      "epoch": 0.98989898989899,
      "grad_norm": 1.2492576837539673,
      "learning_rate": 8.80400615927139e-05,
      "loss": 1.3521,
      "step": 49
    },
    {
      "epoch": 1.0101010101010102,
      "grad_norm": 1.5818628072738647,
      "learning_rate": 8.72386091371891e-05,
      "loss": 1.8895,
      "step": 50
    },
    {
      "epoch": 1.0101010101010102,
      "eval_loss": 1.3664671182632446,
      "eval_runtime": 4.2876,
      "eval_samples_per_second": 19.591,
      "eval_steps_per_second": 9.796,
      "step": 50
    },
    {
      "epoch": 1.0303030303030303,
      "grad_norm": 0.9870416522026062,
      "learning_rate": 8.641507194059579e-05,
      "loss": 1.1644,
      "step": 51
    },
    {
      "epoch": 1.0505050505050506,
      "grad_norm": 0.9368259906768799,
      "learning_rate": 8.55699384101589e-05,
      "loss": 1.2176,
      "step": 52
    },
    {
      "epoch": 1.0707070707070707,
      "grad_norm": 0.9914711117744446,
      "learning_rate": 8.47037097610317e-05,
      "loss": 1.2754,
      "step": 53
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.9624159336090088,
      "learning_rate": 8.381689971904514e-05,
      "loss": 1.2237,
      "step": 54
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.8989251852035522,
      "learning_rate": 8.29100342160374e-05,
      "loss": 1.1661,
      "step": 55
    },
    {
      "epoch": 1.1313131313131313,
      "grad_norm": 0.8935759663581848,
      "learning_rate": 8.198365107794457e-05,
      "loss": 1.1071,
      "step": 56
    },
    {
      "epoch": 1.1515151515151516,
      "grad_norm": 0.8914757370948792,
      "learning_rate": 8.103829970583742e-05,
      "loss": 1.1958,
      "step": 57
    },
    {
      "epoch": 1.1717171717171717,
      "grad_norm": 0.9382041692733765,
      "learning_rate": 8.007454075009351e-05,
      "loss": 1.0885,
      "step": 58
    },
    {
      "epoch": 1.1919191919191918,
      "grad_norm": 1.026020884513855,
      "learning_rate": 7.909294577789766e-05,
      "loss": 1.196,
      "step": 59
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 1.0326781272888184,
      "learning_rate": 7.809409693426803e-05,
      "loss": 1.2008,
      "step": 60
    },
    {
      "epoch": 1.2323232323232323,
      "grad_norm": 1.0171078443527222,
      "learning_rate": 7.707858659680924e-05,
      "loss": 1.0956,
      "step": 61
    },
    {
      "epoch": 1.2525252525252526,
      "grad_norm": 1.1952531337738037,
      "learning_rate": 7.604701702439651e-05,
      "loss": 1.2509,
      "step": 62
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.9705902338027954,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.1169,
      "step": 63
    },
    {
      "epoch": 1.2929292929292928,
      "grad_norm": 0.8539131879806519,
      "learning_rate": 7.393815646786046e-05,
      "loss": 0.9659,
      "step": 64
    },
    {
      "epoch": 1.3131313131313131,
      "grad_norm": 1.0443497896194458,
      "learning_rate": 7.286211616523193e-05,
      "loss": 1.1447,
      "step": 65
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.9528786540031433,
      "learning_rate": 7.177251724890956e-05,
      "loss": 1.0219,
      "step": 66
    },
    {
      "epoch": 1.3535353535353536,
      "grad_norm": 1.04220449924469,
      "learning_rate": 7.067000591676416e-05,
      "loss": 0.997,
      "step": 67
    },
    {
      "epoch": 1.3737373737373737,
      "grad_norm": 0.7969975471496582,
      "learning_rate": 6.95552360245078e-05,
      "loss": 0.8762,
      "step": 68
    },
    {
      "epoch": 1.393939393939394,
      "grad_norm": 1.0815095901489258,
      "learning_rate": 6.842886869791809e-05,
      "loss": 1.0771,
      "step": 69
    },
    {
      "epoch": 1.4141414141414141,
      "grad_norm": 1.0188919305801392,
      "learning_rate": 6.729157194075057e-05,
      "loss": 1.0527,
      "step": 70
    },
    {
      "epoch": 1.4343434343434343,
      "grad_norm": 1.126763939857483,
      "learning_rate": 6.614402023857232e-05,
      "loss": 1.0613,
      "step": 71
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.9159054160118103,
      "learning_rate": 6.498689415875121e-05,
      "loss": 0.9561,
      "step": 72
    },
    {
      "epoch": 1.4747474747474747,
      "grad_norm": 1.2112116813659668,
      "learning_rate": 6.382087994683859e-05,
      "loss": 1.1898,
      "step": 73
    },
    {
      "epoch": 1.494949494949495,
      "grad_norm": 1.1874535083770752,
      "learning_rate": 6.264666911958404e-05,
      "loss": 1.2197,
      "step": 74
    },
    {
      "epoch": 1.5151515151515151,
      "grad_norm": 0.8190261721611023,
      "learning_rate": 6.146495805482451e-05,
      "loss": 0.8199,
      "step": 75
    },
    {
      "epoch": 1.5353535353535355,
      "grad_norm": 0.9896472096443176,
      "learning_rate": 6.0276447578490035e-05,
      "loss": 1.0456,
      "step": 76
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 0.9824926257133484,
      "learning_rate": 5.908184254897182e-05,
      "loss": 1.0388,
      "step": 77
    },
    {
      "epoch": 1.5757575757575757,
      "grad_norm": 0.9661423563957214,
      "learning_rate": 5.788185143909868e-05,
      "loss": 0.9587,
      "step": 78
    },
    {
      "epoch": 1.595959595959596,
      "grad_norm": 0.9323811531066895,
      "learning_rate": 5.66771859159699e-05,
      "loss": 0.9407,
      "step": 79
    },
    {
      "epoch": 1.6161616161616161,
      "grad_norm": 0.9910972714424133,
      "learning_rate": 5.546856041889373e-05,
      "loss": 1.0198,
      "step": 80
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 1.2142277956008911,
      "learning_rate": 5.4256691735681786e-05,
      "loss": 1.112,
      "step": 81
    },
    {
      "epoch": 1.6565656565656566,
      "grad_norm": 1.0950809717178345,
      "learning_rate": 5.3042298577550696e-05,
      "loss": 0.9386,
      "step": 82
    },
    {
      "epoch": 1.676767676767677,
      "grad_norm": 1.1096038818359375,
      "learning_rate": 5.182610115288295e-05,
      "loss": 0.9791,
      "step": 83
    },
    {
      "epoch": 1.696969696969697,
      "grad_norm": 1.2279932498931885,
      "learning_rate": 5.060882074009988e-05,
      "loss": 1.167,
      "step": 84
    },
    {
      "epoch": 1.7171717171717171,
      "grad_norm": 1.151942491531372,
      "learning_rate": 4.9391179259900125e-05,
      "loss": 0.9379,
      "step": 85
    },
    {
      "epoch": 1.7373737373737375,
      "grad_norm": 1.0891432762145996,
      "learning_rate": 4.817389884711705e-05,
      "loss": 1.0535,
      "step": 86
    },
    {
      "epoch": 1.7575757575757576,
      "grad_norm": 0.877910315990448,
      "learning_rate": 4.695770142244931e-05,
      "loss": 0.9166,
      "step": 87
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.822179913520813,
      "learning_rate": 4.574330826431821e-05,
      "loss": 0.8026,
      "step": 88
    },
    {
      "epoch": 1.797979797979798,
      "grad_norm": 0.8958245515823364,
      "learning_rate": 4.4531439581106295e-05,
      "loss": 0.8582,
      "step": 89
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 1.048801302909851,
      "learning_rate": 4.332281408403011e-05,
      "loss": 0.9083,
      "step": 90
    },
    {
      "epoch": 1.8383838383838382,
      "grad_norm": 1.161761999130249,
      "learning_rate": 4.2118148560901325e-05,
      "loss": 0.8411,
      "step": 91
    },
    {
      "epoch": 1.8585858585858586,
      "grad_norm": 0.9891107678413391,
      "learning_rate": 4.0918157451028185e-05,
      "loss": 0.8344,
      "step": 92
    },
    {
      "epoch": 1.878787878787879,
      "grad_norm": 0.9550774693489075,
      "learning_rate": 3.972355242150998e-05,
      "loss": 0.914,
      "step": 93
    },
    {
      "epoch": 1.898989898989899,
      "grad_norm": 1.0667641162872314,
      "learning_rate": 3.8535041945175506e-05,
      "loss": 0.9441,
      "step": 94
    },
    {
      "epoch": 1.9191919191919191,
      "grad_norm": 1.065216302871704,
      "learning_rate": 3.735333088041596e-05,
      "loss": 0.9306,
      "step": 95
    },
    {
      "epoch": 1.9393939393939394,
      "grad_norm": 0.9413928985595703,
      "learning_rate": 3.6179120053161416e-05,
      "loss": 0.8101,
      "step": 96
    },
    {
      "epoch": 1.9595959595959596,
      "grad_norm": 1.1866222620010376,
      "learning_rate": 3.5013105841248795e-05,
      "loss": 0.8617,
      "step": 97
    },
    {
      "epoch": 1.9797979797979797,
      "grad_norm": 1.1086472272872925,
      "learning_rate": 3.38559797614277e-05,
      "loss": 1.0243,
      "step": 98
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.5880515575408936,
      "learning_rate": 3.2708428059249436e-05,
      "loss": 1.2843,
      "step": 99
    },
    {
      "epoch": 2.0202020202020203,
      "grad_norm": 0.8188629746437073,
      "learning_rate": 3.157113130208191e-05,
      "loss": 0.7934,
      "step": 100
    },
    {
      "epoch": 2.0202020202020203,
      "eval_loss": 1.00209379196167,
      "eval_runtime": 4.3279,
      "eval_samples_per_second": 19.409,
      "eval_steps_per_second": 9.704,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 149,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.719746402287616e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}