{
  "best_metric": 0.7275850176811218,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.3436426116838488,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003436426116838488,
      "grad_norm": 6.999215602874756,
      "learning_rate": 1e-05,
      "loss": 4.5691,
      "step": 1
    },
    {
      "epoch": 0.003436426116838488,
      "eval_loss": 1.1649625301361084,
      "eval_runtime": 56.8491,
      "eval_samples_per_second": 8.619,
      "eval_steps_per_second": 2.164,
      "step": 1
    },
    {
      "epoch": 0.006872852233676976,
      "grad_norm": 10.226408004760742,
      "learning_rate": 2e-05,
      "loss": 4.7735,
      "step": 2
    },
    {
      "epoch": 0.010309278350515464,
      "grad_norm": 7.403202056884766,
      "learning_rate": 3e-05,
      "loss": 5.4566,
      "step": 3
    },
    {
      "epoch": 0.013745704467353952,
      "grad_norm": 7.148951053619385,
      "learning_rate": 4e-05,
      "loss": 4.5726,
      "step": 4
    },
    {
      "epoch": 0.01718213058419244,
      "grad_norm": 5.320497512817383,
      "learning_rate": 5e-05,
      "loss": 3.4752,
      "step": 5
    },
    {
      "epoch": 0.020618556701030927,
      "grad_norm": 4.6576151847839355,
      "learning_rate": 6e-05,
      "loss": 3.3295,
      "step": 6
    },
    {
      "epoch": 0.024054982817869417,
      "grad_norm": 3.996817111968994,
      "learning_rate": 7e-05,
      "loss": 3.2337,
      "step": 7
    },
    {
      "epoch": 0.027491408934707903,
      "grad_norm": 3.309384822845459,
      "learning_rate": 8e-05,
      "loss": 3.0622,
      "step": 8
    },
    {
      "epoch": 0.030927835051546393,
      "grad_norm": 3.21154522895813,
      "learning_rate": 9e-05,
      "loss": 3.2033,
      "step": 9
    },
    {
      "epoch": 0.03436426116838488,
      "grad_norm": 2.495940685272217,
      "learning_rate": 0.0001,
      "loss": 2.7851,
      "step": 10
    },
    {
      "epoch": 0.037800687285223365,
      "grad_norm": 2.862969160079956,
      "learning_rate": 9.999316524962345e-05,
      "loss": 3.0626,
      "step": 11
    },
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 2.983869791030884,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.7385,
      "step": 12
    },
    {
      "epoch": 0.044673539518900345,
      "grad_norm": 2.9540152549743652,
      "learning_rate": 9.993849845741524e-05,
      "loss": 2.9303,
      "step": 13
    },
    {
      "epoch": 0.048109965635738834,
      "grad_norm": 2.927572727203369,
      "learning_rate": 9.989068136093873e-05,
      "loss": 2.8194,
      "step": 14
    },
    {
      "epoch": 0.05154639175257732,
      "grad_norm": 2.69342303276062,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.6651,
      "step": 15
    },
    {
      "epoch": 0.054982817869415807,
      "grad_norm": 2.8283026218414307,
      "learning_rate": 9.975414512725057e-05,
      "loss": 2.7093,
      "step": 16
    },
    {
      "epoch": 0.058419243986254296,
      "grad_norm": 2.476212978363037,
      "learning_rate": 9.966546331768191e-05,
      "loss": 2.7536,
      "step": 17
    },
    {
      "epoch": 0.061855670103092786,
      "grad_norm": 2.6046454906463623,
      "learning_rate": 9.956320346634876e-05,
      "loss": 2.7008,
      "step": 18
    },
    {
      "epoch": 0.06529209621993128,
      "grad_norm": 2.432948350906372,
      "learning_rate": 9.944739353007344e-05,
      "loss": 2.6092,
      "step": 19
    },
    {
      "epoch": 0.06872852233676977,
      "grad_norm": 2.418318271636963,
      "learning_rate": 9.931806517013612e-05,
      "loss": 2.6675,
      "step": 20
    },
    {
      "epoch": 0.07216494845360824,
      "grad_norm": 2.530046224594116,
      "learning_rate": 9.917525374361912e-05,
      "loss": 2.5549,
      "step": 21
    },
    {
      "epoch": 0.07560137457044673,
      "grad_norm": 2.896991729736328,
      "learning_rate": 9.901899829374047e-05,
      "loss": 2.6267,
      "step": 22
    },
    {
      "epoch": 0.07903780068728522,
      "grad_norm": 2.8084323406219482,
      "learning_rate": 9.884934153917997e-05,
      "loss": 2.5245,
      "step": 23
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": 2.604916572570801,
      "learning_rate": 9.86663298624003e-05,
      "loss": 2.6195,
      "step": 24
    },
    {
      "epoch": 0.0859106529209622,
      "grad_norm": 2.957746744155884,
      "learning_rate": 9.847001329696653e-05,
      "loss": 2.87,
      "step": 25
    },
    {
      "epoch": 0.08934707903780069,
      "grad_norm": 3.0972800254821777,
      "learning_rate": 9.826044551386744e-05,
      "loss": 2.8663,
      "step": 26
    },
    {
      "epoch": 0.09278350515463918,
      "grad_norm": 2.5497095584869385,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.6693,
      "step": 27
    },
    {
      "epoch": 0.09621993127147767,
      "grad_norm": 2.661566972732544,
      "learning_rate": 9.780178907671789e-05,
      "loss": 2.6146,
      "step": 28
    },
    {
      "epoch": 0.09965635738831616,
      "grad_norm": 3.422123670578003,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.6913,
      "step": 29
    },
    {
      "epoch": 0.10309278350515463,
      "grad_norm": 3.245452880859375,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.842,
      "step": 30
    },
    {
      "epoch": 0.10652920962199312,
      "grad_norm": 2.8833205699920654,
      "learning_rate": 9.701596950580806e-05,
      "loss": 2.9433,
      "step": 31
    },
    {
      "epoch": 0.10996563573883161,
      "grad_norm": 3.3487491607666016,
      "learning_rate": 9.672822322997305e-05,
      "loss": 3.1002,
      "step": 32
    },
    {
      "epoch": 0.1134020618556701,
      "grad_norm": 3.0698416233062744,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.6802,
      "step": 33
    },
    {
      "epoch": 0.11683848797250859,
      "grad_norm": 3.376664400100708,
      "learning_rate": 9.611448774886924e-05,
      "loss": 2.9653,
      "step": 34
    },
    {
      "epoch": 0.12027491408934708,
      "grad_norm": 2.8750152587890625,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.9137,
      "step": 35
    },
    {
      "epoch": 0.12371134020618557,
      "grad_norm": 3.473970651626587,
      "learning_rate": 9.545032675245813e-05,
      "loss": 3.1216,
      "step": 36
    },
    {
      "epoch": 0.12714776632302405,
      "grad_norm": 2.9692599773406982,
      "learning_rate": 9.509956150664796e-05,
      "loss": 3.2168,
      "step": 37
    },
    {
      "epoch": 0.13058419243986255,
      "grad_norm": 3.3146817684173584,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.6558,
      "step": 38
    },
    {
      "epoch": 0.13402061855670103,
      "grad_norm": 4.520171642303467,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.963,
      "step": 39
    },
    {
      "epoch": 0.13745704467353953,
      "grad_norm": 3.6921310424804688,
      "learning_rate": 9.397368756032445e-05,
      "loss": 3.1284,
      "step": 40
    },
    {
      "epoch": 0.140893470790378,
      "grad_norm": 3.9622802734375,
      "learning_rate": 9.357421218136386e-05,
      "loss": 3.6196,
      "step": 41
    },
    {
      "epoch": 0.14432989690721648,
      "grad_norm": 3.812455177307129,
      "learning_rate": 9.316282404787871e-05,
      "loss": 3.7704,
      "step": 42
    },
    {
      "epoch": 0.14776632302405499,
      "grad_norm": 5.3475728034973145,
      "learning_rate": 9.273963562927695e-05,
      "loss": 3.2741,
      "step": 43
    },
    {
      "epoch": 0.15120274914089346,
      "grad_norm": 5.504002571105957,
      "learning_rate": 9.230476262104677e-05,
      "loss": 3.0969,
      "step": 44
    },
    {
      "epoch": 0.15463917525773196,
      "grad_norm": 4.543576240539551,
      "learning_rate": 9.185832391312644e-05,
      "loss": 3.1458,
      "step": 45
    },
    {
      "epoch": 0.15807560137457044,
      "grad_norm": 4.998715400695801,
      "learning_rate": 9.140044155740101e-05,
      "loss": 3.4173,
      "step": 46
    },
    {
      "epoch": 0.16151202749140894,
      "grad_norm": 5.311492919921875,
      "learning_rate": 9.093124073433463e-05,
      "loss": 3.1931,
      "step": 47
    },
    {
      "epoch": 0.16494845360824742,
      "grad_norm": 5.836362361907959,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.9172,
      "step": 48
    },
    {
      "epoch": 0.16838487972508592,
      "grad_norm": 9.274666786193848,
      "learning_rate": 8.995939984474624e-05,
      "loss": 3.9358,
      "step": 49
    },
    {
      "epoch": 0.1718213058419244,
      "grad_norm": 12.288378715515137,
      "learning_rate": 8.945702546981969e-05,
      "loss": 5.0356,
      "step": 50
    },
    {
      "epoch": 0.1718213058419244,
      "eval_loss": 0.7464320659637451,
      "eval_runtime": 57.9439,
      "eval_samples_per_second": 8.456,
      "eval_steps_per_second": 2.123,
      "step": 50
    },
    {
      "epoch": 0.17525773195876287,
      "grad_norm": 3.77553129196167,
      "learning_rate": 8.894386393810563e-05,
      "loss": 4.0078,
      "step": 51
    },
    {
      "epoch": 0.17869415807560138,
      "grad_norm": 3.6236894130706787,
      "learning_rate": 8.842005554284296e-05,
      "loss": 4.8044,
      "step": 52
    },
    {
      "epoch": 0.18213058419243985,
      "grad_norm": 2.9243147373199463,
      "learning_rate": 8.788574348801675e-05,
      "loss": 4.12,
      "step": 53
    },
    {
      "epoch": 0.18556701030927836,
      "grad_norm": 2.872667074203491,
      "learning_rate": 8.73410738492077e-05,
      "loss": 3.8321,
      "step": 54
    },
    {
      "epoch": 0.18900343642611683,
      "grad_norm": 2.234645128250122,
      "learning_rate": 8.678619553365659e-05,
      "loss": 2.9262,
      "step": 55
    },
    {
      "epoch": 0.19243986254295534,
      "grad_norm": 2.077925682067871,
      "learning_rate": 8.622126023955446e-05,
      "loss": 2.7141,
      "step": 56
    },
    {
      "epoch": 0.1958762886597938,
      "grad_norm": 1.9878581762313843,
      "learning_rate": 8.564642241456986e-05,
      "loss": 2.3659,
      "step": 57
    },
    {
      "epoch": 0.19931271477663232,
      "grad_norm": 2.166398525238037,
      "learning_rate": 8.506183921362443e-05,
      "loss": 2.4228,
      "step": 58
    },
    {
      "epoch": 0.2027491408934708,
      "grad_norm": 2.4756956100463867,
      "learning_rate": 8.44676704559283e-05,
      "loss": 2.6523,
      "step": 59
    },
    {
      "epoch": 0.20618556701030927,
      "grad_norm": 2.474353075027466,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.5776,
      "step": 60
    },
    {
      "epoch": 0.20962199312714777,
      "grad_norm": 2.264328956604004,
      "learning_rate": 8.32512286056924e-05,
      "loss": 2.5572,
      "step": 61
    },
    {
      "epoch": 0.21305841924398625,
      "grad_norm": 2.2260265350341797,
      "learning_rate": 8.262928807620843e-05,
      "loss": 2.6668,
      "step": 62
    },
    {
      "epoch": 0.21649484536082475,
      "grad_norm": 2.046036720275879,
      "learning_rate": 8.199842702516583e-05,
      "loss": 2.4594,
      "step": 63
    },
    {
      "epoch": 0.21993127147766323,
      "grad_norm": 1.9594258069992065,
      "learning_rate": 8.135881792367686e-05,
      "loss": 2.8038,
      "step": 64
    },
    {
      "epoch": 0.22336769759450173,
      "grad_norm": 2.100553274154663,
      "learning_rate": 8.07106356344834e-05,
      "loss": 2.6334,
      "step": 65
    },
    {
      "epoch": 0.2268041237113402,
      "grad_norm": 1.7995946407318115,
      "learning_rate": 8.005405736415126e-05,
      "loss": 2.8142,
      "step": 66
    },
    {
      "epoch": 0.23024054982817868,
      "grad_norm": 1.8127626180648804,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.5587,
      "step": 67
    },
    {
      "epoch": 0.23367697594501718,
      "grad_norm": 2.1307082176208496,
      "learning_rate": 7.871643313414718e-05,
      "loss": 2.2027,
      "step": 68
    },
    {
      "epoch": 0.23711340206185566,
      "grad_norm": 1.9283121824264526,
      "learning_rate": 7.803575286758364e-05,
      "loss": 2.6447,
      "step": 69
    },
    {
      "epoch": 0.24054982817869416,
      "grad_norm": 2.103541851043701,
      "learning_rate": 7.734740790612136e-05,
      "loss": 2.454,
      "step": 70
    },
    {
      "epoch": 0.24398625429553264,
      "grad_norm": 2.1929001808166504,
      "learning_rate": 7.66515864363997e-05,
      "loss": 2.6667,
      "step": 71
    },
    {
      "epoch": 0.24742268041237114,
      "grad_norm": 2.1750361919403076,
      "learning_rate": 7.594847868906076e-05,
      "loss": 2.4168,
      "step": 72
    },
    {
      "epoch": 0.2508591065292096,
      "grad_norm": 2.0648245811462402,
      "learning_rate": 7.52382768867422e-05,
      "loss": 2.53,
      "step": 73
    },
    {
      "epoch": 0.2542955326460481,
      "grad_norm": 2.0837292671203613,
      "learning_rate": 7.452117519152542e-05,
      "loss": 2.4515,
      "step": 74
    },
    {
      "epoch": 0.25773195876288657,
      "grad_norm": 1.9967957735061646,
      "learning_rate": 7.379736965185368e-05,
      "loss": 2.5799,
      "step": 75
    },
    {
      "epoch": 0.2611683848797251,
      "grad_norm": 2.303253412246704,
      "learning_rate": 7.30670581489344e-05,
      "loss": 2.6162,
      "step": 76
    },
    {
      "epoch": 0.2646048109965636,
      "grad_norm": 2.3726534843444824,
      "learning_rate": 7.233044034264034e-05,
      "loss": 2.7798,
      "step": 77
    },
    {
      "epoch": 0.26804123711340205,
      "grad_norm": 2.3450615406036377,
      "learning_rate": 7.158771761692464e-05,
      "loss": 2.5697,
      "step": 78
    },
    {
      "epoch": 0.27147766323024053,
      "grad_norm": 2.02581787109375,
      "learning_rate": 7.083909302476453e-05,
      "loss": 2.4828,
      "step": 79
    },
    {
      "epoch": 0.27491408934707906,
      "grad_norm": 2.140730381011963,
      "learning_rate": 7.008477123264848e-05,
      "loss": 2.4736,
      "step": 80
    },
    {
      "epoch": 0.27835051546391754,
      "grad_norm": 2.4021403789520264,
      "learning_rate": 6.932495846462261e-05,
      "loss": 2.6348,
      "step": 81
    },
    {
      "epoch": 0.281786941580756,
      "grad_norm": 2.3539841175079346,
      "learning_rate": 6.855986244591104e-05,
      "loss": 2.6499,
      "step": 82
    },
    {
      "epoch": 0.2852233676975945,
      "grad_norm": 2.6271588802337646,
      "learning_rate": 6.778969234612584e-05,
      "loss": 2.6928,
      "step": 83
    },
    {
      "epoch": 0.28865979381443296,
      "grad_norm": 2.907905340194702,
      "learning_rate": 6.701465872208216e-05,
      "loss": 3.0853,
      "step": 84
    },
    {
      "epoch": 0.2920962199312715,
      "grad_norm": 2.975721836090088,
      "learning_rate": 6.623497346023418e-05,
      "loss": 3.2194,
      "step": 85
    },
    {
      "epoch": 0.29553264604810997,
      "grad_norm": 3.38991117477417,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.0417,
      "step": 86
    },
    {
      "epoch": 0.29896907216494845,
      "grad_norm": 2.8174936771392822,
      "learning_rate": 6.466250186922325e-05,
      "loss": 2.738,
      "step": 87
    },
    {
      "epoch": 0.3024054982817869,
      "grad_norm": 2.843874216079712,
      "learning_rate": 6.387014543809223e-05,
      "loss": 3.462,
      "step": 88
    },
    {
      "epoch": 0.30584192439862545,
      "grad_norm": 2.7298972606658936,
      "learning_rate": 6.307399704769099e-05,
      "loss": 3.2924,
      "step": 89
    },
    {
      "epoch": 0.30927835051546393,
      "grad_norm": 3.1683461666107178,
      "learning_rate": 6.227427435703997e-05,
      "loss": 3.3211,
      "step": 90
    },
    {
      "epoch": 0.3127147766323024,
      "grad_norm": 3.1999478340148926,
      "learning_rate": 6.147119600233758e-05,
      "loss": 3.6313,
      "step": 91
    },
    {
      "epoch": 0.3161512027491409,
      "grad_norm": 3.4098615646362305,
      "learning_rate": 6.066498153718735e-05,
      "loss": 3.3579,
      "step": 92
    },
    {
      "epoch": 0.31958762886597936,
      "grad_norm": 3.4101476669311523,
      "learning_rate": 5.985585137257401e-05,
      "loss": 3.2301,
      "step": 93
    },
    {
      "epoch": 0.3230240549828179,
      "grad_norm": 3.569462776184082,
      "learning_rate": 5.90440267166055e-05,
      "loss": 3.1225,
      "step": 94
    },
    {
      "epoch": 0.32646048109965636,
      "grad_norm": 3.819608688354492,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 3.3291,
      "step": 95
    },
    {
      "epoch": 0.32989690721649484,
      "grad_norm": 4.344887733459473,
      "learning_rate": 5.74131823855921e-05,
      "loss": 3.2619,
      "step": 96
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 5.571539402008057,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 3.4909,
      "step": 97
    },
    {
      "epoch": 0.33676975945017185,
      "grad_norm": 4.887326717376709,
      "learning_rate": 5.577423184847932e-05,
      "loss": 3.3086,
      "step": 98
    },
    {
      "epoch": 0.3402061855670103,
      "grad_norm": 5.068550109863281,
      "learning_rate": 5.495227651252315e-05,
      "loss": 3.2474,
      "step": 99
    },
    {
      "epoch": 0.3436426116838488,
      "grad_norm": 7.036664962768555,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 4.2552,
      "step": 100
    },
    {
      "epoch": 0.3436426116838488,
      "eval_loss": 0.7275850176811218,
      "eval_runtime": 57.9445,
      "eval_samples_per_second": 8.456,
      "eval_steps_per_second": 2.123,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 2.5413965215432704e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}