{
  "best_metric": 2.4205310344696045,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.3009781790820166,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0030097817908201654,
      "grad_norm": 6.573893070220947,
      "learning_rate": 1e-05,
      "loss": 9.4986,
      "step": 1
    },
    {
      "epoch": 0.0030097817908201654,
      "eval_loss": 2.8468708992004395,
      "eval_runtime": 54.2783,
      "eval_samples_per_second": 10.317,
      "eval_steps_per_second": 2.579,
      "step": 1
    },
    {
      "epoch": 0.006019563581640331,
      "grad_norm": 7.830665111541748,
      "learning_rate": 2e-05,
      "loss": 9.5231,
      "step": 2
    },
    {
      "epoch": 0.009029345372460496,
      "grad_norm": 7.3165059089660645,
      "learning_rate": 3e-05,
      "loss": 8.9478,
      "step": 3
    },
    {
      "epoch": 0.012039127163280662,
      "grad_norm": 8.22419261932373,
      "learning_rate": 4e-05,
      "loss": 9.1723,
      "step": 4
    },
    {
      "epoch": 0.015048908954100828,
      "grad_norm": 7.707956314086914,
      "learning_rate": 5e-05,
      "loss": 9.4721,
      "step": 5
    },
    {
      "epoch": 0.01805869074492099,
      "grad_norm": 7.3733649253845215,
      "learning_rate": 6e-05,
      "loss": 9.1231,
      "step": 6
    },
    {
      "epoch": 0.021068472535741158,
      "grad_norm": 9.522957801818848,
      "learning_rate": 7e-05,
      "loss": 10.3674,
      "step": 7
    },
    {
      "epoch": 0.024078254326561323,
      "grad_norm": 7.464807987213135,
      "learning_rate": 8e-05,
      "loss": 8.7806,
      "step": 8
    },
    {
      "epoch": 0.02708803611738149,
      "grad_norm": 8.447348594665527,
      "learning_rate": 9e-05,
      "loss": 9.8534,
      "step": 9
    },
    {
      "epoch": 0.030097817908201655,
      "grad_norm": 9.508760452270508,
      "learning_rate": 0.0001,
      "loss": 10.1334,
      "step": 10
    },
    {
      "epoch": 0.03310759969902182,
      "grad_norm": 11.263378143310547,
      "learning_rate": 9.999316524962345e-05,
      "loss": 10.433,
      "step": 11
    },
    {
      "epoch": 0.03611738148984198,
      "grad_norm": 9.284879684448242,
      "learning_rate": 9.997266286704631e-05,
      "loss": 10.0197,
      "step": 12
    },
    {
      "epoch": 0.03912716328066215,
      "grad_norm": 8.84637451171875,
      "learning_rate": 9.993849845741524e-05,
      "loss": 9.5473,
      "step": 13
    },
    {
      "epoch": 0.042136945071482315,
      "grad_norm": 9.146723747253418,
      "learning_rate": 9.989068136093873e-05,
      "loss": 9.3743,
      "step": 14
    },
    {
      "epoch": 0.045146726862302484,
      "grad_norm": 8.942791938781738,
      "learning_rate": 9.98292246503335e-05,
      "loss": 9.7516,
      "step": 15
    },
    {
      "epoch": 0.04815650865312265,
      "grad_norm": 10.329294204711914,
      "learning_rate": 9.975414512725057e-05,
      "loss": 9.7756,
      "step": 16
    },
    {
      "epoch": 0.051166290443942816,
      "grad_norm": 8.851433753967285,
      "learning_rate": 9.966546331768191e-05,
      "loss": 9.7867,
      "step": 17
    },
    {
      "epoch": 0.05417607223476298,
      "grad_norm": 8.984696388244629,
      "learning_rate": 9.956320346634876e-05,
      "loss": 9.5581,
      "step": 18
    },
    {
      "epoch": 0.05718585402558315,
      "grad_norm": 9.131317138671875,
      "learning_rate": 9.944739353007344e-05,
      "loss": 9.5847,
      "step": 19
    },
    {
      "epoch": 0.06019563581640331,
      "grad_norm": 10.204080581665039,
      "learning_rate": 9.931806517013612e-05,
      "loss": 10.3269,
      "step": 20
    },
    {
      "epoch": 0.06320541760722348,
      "grad_norm": 8.885244369506836,
      "learning_rate": 9.917525374361912e-05,
      "loss": 9.7441,
      "step": 21
    },
    {
      "epoch": 0.06621519939804364,
      "grad_norm": 9.042747497558594,
      "learning_rate": 9.901899829374047e-05,
      "loss": 10.0208,
      "step": 22
    },
    {
      "epoch": 0.0692249811888638,
      "grad_norm": 9.553254127502441,
      "learning_rate": 9.884934153917997e-05,
      "loss": 10.0202,
      "step": 23
    },
    {
      "epoch": 0.07223476297968397,
      "grad_norm": 8.767007827758789,
      "learning_rate": 9.86663298624003e-05,
      "loss": 8.8363,
      "step": 24
    },
    {
      "epoch": 0.07524454477050414,
      "grad_norm": 9.454209327697754,
      "learning_rate": 9.847001329696653e-05,
      "loss": 9.7709,
      "step": 25
    },
    {
      "epoch": 0.0782543265613243,
      "grad_norm": 9.191224098205566,
      "learning_rate": 9.826044551386744e-05,
      "loss": 9.5502,
      "step": 26
    },
    {
      "epoch": 0.08126410835214447,
      "grad_norm": 9.49747085571289,
      "learning_rate": 9.803768380684242e-05,
      "loss": 9.6738,
      "step": 27
    },
    {
      "epoch": 0.08427389014296463,
      "grad_norm": 10.24111270904541,
      "learning_rate": 9.780178907671789e-05,
      "loss": 10.03,
      "step": 28
    },
    {
      "epoch": 0.0872836719337848,
      "grad_norm": 9.009526252746582,
      "learning_rate": 9.755282581475769e-05,
      "loss": 8.6197,
      "step": 29
    },
    {
      "epoch": 0.09029345372460497,
      "grad_norm": 11.295206069946289,
      "learning_rate": 9.729086208503174e-05,
      "loss": 10.0076,
      "step": 30
    },
    {
      "epoch": 0.09330323551542513,
      "grad_norm": 11.421455383300781,
      "learning_rate": 9.701596950580806e-05,
      "loss": 9.5754,
      "step": 31
    },
    {
      "epoch": 0.0963130173062453,
      "grad_norm": 10.831648826599121,
      "learning_rate": 9.672822322997305e-05,
      "loss": 9.439,
      "step": 32
    },
    {
      "epoch": 0.09932279909706546,
      "grad_norm": 12.72357177734375,
      "learning_rate": 9.642770192448536e-05,
      "loss": 10.3717,
      "step": 33
    },
    {
      "epoch": 0.10233258088788563,
      "grad_norm": 11.876553535461426,
      "learning_rate": 9.611448774886924e-05,
      "loss": 9.5917,
      "step": 34
    },
    {
      "epoch": 0.1053423626787058,
      "grad_norm": 11.42211627960205,
      "learning_rate": 9.578866633275288e-05,
      "loss": 10.0323,
      "step": 35
    },
    {
      "epoch": 0.10835214446952596,
      "grad_norm": 11.210999488830566,
      "learning_rate": 9.545032675245813e-05,
      "loss": 9.6294,
      "step": 36
    },
    {
      "epoch": 0.11136192626034612,
      "grad_norm": 10.617776870727539,
      "learning_rate": 9.509956150664796e-05,
      "loss": 10.1042,
      "step": 37
    },
    {
      "epoch": 0.1143717080511663,
      "grad_norm": 12.666061401367188,
      "learning_rate": 9.473646649103818e-05,
      "loss": 10.3523,
      "step": 38
    },
    {
      "epoch": 0.11738148984198646,
      "grad_norm": 11.441605567932129,
      "learning_rate": 9.43611409721806e-05,
      "loss": 9.6864,
      "step": 39
    },
    {
      "epoch": 0.12039127163280662,
      "grad_norm": 14.956219673156738,
      "learning_rate": 9.397368756032445e-05,
      "loss": 10.7549,
      "step": 40
    },
    {
      "epoch": 0.12340105342362678,
      "grad_norm": 13.108258247375488,
      "learning_rate": 9.357421218136386e-05,
      "loss": 10.5067,
      "step": 41
    },
    {
      "epoch": 0.12641083521444696,
      "grad_norm": 12.229085922241211,
      "learning_rate": 9.316282404787871e-05,
      "loss": 10.5228,
      "step": 42
    },
    {
      "epoch": 0.1294206170052671,
      "grad_norm": 13.60671615600586,
      "learning_rate": 9.273963562927695e-05,
      "loss": 11.0104,
      "step": 43
    },
    {
      "epoch": 0.13243039879608728,
      "grad_norm": 13.636900901794434,
      "learning_rate": 9.230476262104677e-05,
      "loss": 10.4467,
      "step": 44
    },
    {
      "epoch": 0.13544018058690746,
      "grad_norm": 11.208077430725098,
      "learning_rate": 9.185832391312644e-05,
      "loss": 9.3656,
      "step": 45
    },
    {
      "epoch": 0.1384499623777276,
      "grad_norm": 13.557292938232422,
      "learning_rate": 9.140044155740101e-05,
      "loss": 10.3251,
      "step": 46
    },
    {
      "epoch": 0.14145974416854779,
      "grad_norm": 13.766647338867188,
      "learning_rate": 9.093124073433463e-05,
      "loss": 9.9424,
      "step": 47
    },
    {
      "epoch": 0.14446952595936793,
      "grad_norm": 14.213854789733887,
      "learning_rate": 9.045084971874738e-05,
      "loss": 11.234,
      "step": 48
    },
    {
      "epoch": 0.1474793077501881,
      "grad_norm": 19.774276733398438,
      "learning_rate": 8.995939984474624e-05,
      "loss": 12.4225,
      "step": 49
    },
    {
      "epoch": 0.1504890895410083,
      "grad_norm": 20.662708282470703,
      "learning_rate": 8.945702546981969e-05,
      "loss": 12.5272,
      "step": 50
    },
    {
      "epoch": 0.1504890895410083,
      "eval_loss": 2.5100247859954834,
      "eval_runtime": 54.9415,
      "eval_samples_per_second": 10.193,
      "eval_steps_per_second": 2.548,
      "step": 50
    },
    {
      "epoch": 0.15349887133182843,
      "grad_norm": 6.058256149291992,
      "learning_rate": 8.894386393810563e-05,
      "loss": 8.2189,
      "step": 51
    },
    {
      "epoch": 0.1565086531226486,
      "grad_norm": 6.569075107574463,
      "learning_rate": 8.842005554284296e-05,
      "loss": 9.1637,
      "step": 52
    },
    {
      "epoch": 0.1595184349134688,
      "grad_norm": 5.583766937255859,
      "learning_rate": 8.788574348801675e-05,
      "loss": 8.7535,
      "step": 53
    },
    {
      "epoch": 0.16252821670428894,
      "grad_norm": 5.88881778717041,
      "learning_rate": 8.73410738492077e-05,
      "loss": 9.8206,
      "step": 54
    },
    {
      "epoch": 0.1655379984951091,
      "grad_norm": 5.4886651039123535,
      "learning_rate": 8.678619553365659e-05,
      "loss": 8.7837,
      "step": 55
    },
    {
      "epoch": 0.16854778028592926,
      "grad_norm": 5.4740705490112305,
      "learning_rate": 8.622126023955446e-05,
      "loss": 9.2256,
      "step": 56
    },
    {
      "epoch": 0.17155756207674944,
      "grad_norm": 5.433065891265869,
      "learning_rate": 8.564642241456986e-05,
      "loss": 9.2593,
      "step": 57
    },
    {
      "epoch": 0.1745673438675696,
      "grad_norm": 5.914703845977783,
      "learning_rate": 8.506183921362443e-05,
      "loss": 9.1884,
      "step": 58
    },
    {
      "epoch": 0.17757712565838976,
      "grad_norm": 6.139044284820557,
      "learning_rate": 8.44676704559283e-05,
      "loss": 9.8026,
      "step": 59
    },
    {
      "epoch": 0.18058690744920994,
      "grad_norm": 6.379807472229004,
      "learning_rate": 8.386407858128706e-05,
      "loss": 9.324,
      "step": 60
    },
    {
      "epoch": 0.1835966892400301,
      "grad_norm": 7.047702312469482,
      "learning_rate": 8.32512286056924e-05,
      "loss": 9.2618,
      "step": 61
    },
    {
      "epoch": 0.18660647103085026,
      "grad_norm": 6.448022365570068,
      "learning_rate": 8.262928807620843e-05,
      "loss": 9.5976,
      "step": 62
    },
    {
      "epoch": 0.18961625282167044,
      "grad_norm": 8.178146362304688,
      "learning_rate": 8.199842702516583e-05,
      "loss": 10.021,
      "step": 63
    },
    {
      "epoch": 0.1926260346124906,
      "grad_norm": 6.976129055023193,
      "learning_rate": 8.135881792367686e-05,
      "loss": 9.7405,
      "step": 64
    },
    {
      "epoch": 0.19563581640331076,
      "grad_norm": 7.0136308670043945,
      "learning_rate": 8.07106356344834e-05,
      "loss": 9.4789,
      "step": 65
    },
    {
      "epoch": 0.1986455981941309,
      "grad_norm": 7.680490970611572,
      "learning_rate": 8.005405736415126e-05,
      "loss": 9.5718,
      "step": 66
    },
    {
      "epoch": 0.2016553799849511,
      "grad_norm": 8.17990493774414,
      "learning_rate": 7.938926261462366e-05,
      "loss": 9.8405,
      "step": 67
    },
    {
      "epoch": 0.20466516177577126,
      "grad_norm": 8.38397216796875,
      "learning_rate": 7.871643313414718e-05,
      "loss": 10.1608,
      "step": 68
    },
    {
      "epoch": 0.2076749435665914,
      "grad_norm": 8.197789192199707,
      "learning_rate": 7.803575286758364e-05,
      "loss": 8.672,
      "step": 69
    },
    {
      "epoch": 0.2106847253574116,
      "grad_norm": 6.918241024017334,
      "learning_rate": 7.734740790612136e-05,
      "loss": 9.5279,
      "step": 70
    },
    {
      "epoch": 0.21369450714823177,
      "grad_norm": 6.7393035888671875,
      "learning_rate": 7.66515864363997e-05,
      "loss": 9.1222,
      "step": 71
    },
    {
      "epoch": 0.21670428893905191,
      "grad_norm": 8.266468048095703,
      "learning_rate": 7.594847868906076e-05,
      "loss": 9.943,
      "step": 72
    },
    {
      "epoch": 0.2197140707298721,
      "grad_norm": 7.681157112121582,
      "learning_rate": 7.52382768867422e-05,
      "loss": 9.2706,
      "step": 73
    },
    {
      "epoch": 0.22272385252069224,
      "grad_norm": 9.782959938049316,
      "learning_rate": 7.452117519152542e-05,
      "loss": 10.0855,
      "step": 74
    },
    {
      "epoch": 0.22573363431151242,
      "grad_norm": 8.54826545715332,
      "learning_rate": 7.379736965185368e-05,
      "loss": 9.7183,
      "step": 75
    },
    {
      "epoch": 0.2287434161023326,
      "grad_norm": 7.834469318389893,
      "learning_rate": 7.30670581489344e-05,
      "loss": 9.5791,
      "step": 76
    },
    {
      "epoch": 0.23175319789315274,
      "grad_norm": 8.019440650939941,
      "learning_rate": 7.233044034264034e-05,
      "loss": 9.8348,
      "step": 77
    },
    {
      "epoch": 0.23476297968397292,
      "grad_norm": 9.625268936157227,
      "learning_rate": 7.158771761692464e-05,
      "loss": 10.2138,
      "step": 78
    },
    {
      "epoch": 0.23777276147479307,
      "grad_norm": 8.725410461425781,
      "learning_rate": 7.083909302476453e-05,
      "loss": 9.9408,
      "step": 79
    },
    {
      "epoch": 0.24078254326561324,
      "grad_norm": 8.686917304992676,
      "learning_rate": 7.008477123264848e-05,
      "loss": 9.4381,
      "step": 80
    },
    {
      "epoch": 0.24379232505643342,
      "grad_norm": 9.45250415802002,
      "learning_rate": 6.932495846462261e-05,
      "loss": 9.5831,
      "step": 81
    },
    {
      "epoch": 0.24680210684725357,
      "grad_norm": 8.683648109436035,
      "learning_rate": 6.855986244591104e-05,
      "loss": 9.2012,
      "step": 82
    },
    {
      "epoch": 0.24981188863807374,
      "grad_norm": 10.793254852294922,
      "learning_rate": 6.778969234612584e-05,
      "loss": 10.2356,
      "step": 83
    },
    {
      "epoch": 0.2528216704288939,
      "grad_norm": 9.123403549194336,
      "learning_rate": 6.701465872208216e-05,
      "loss": 9.7882,
      "step": 84
    },
    {
      "epoch": 0.2558314522197141,
      "grad_norm": 10.348355293273926,
      "learning_rate": 6.623497346023418e-05,
      "loss": 9.885,
      "step": 85
    },
    {
      "epoch": 0.2588412340105342,
      "grad_norm": 10.56598949432373,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.1376,
      "step": 86
    },
    {
      "epoch": 0.2618510158013544,
      "grad_norm": 9.426460266113281,
      "learning_rate": 6.466250186922325e-05,
      "loss": 9.368,
      "step": 87
    },
    {
      "epoch": 0.26486079759217457,
      "grad_norm": 10.77817153930664,
      "learning_rate": 6.387014543809223e-05,
      "loss": 9.7117,
      "step": 88
    },
    {
      "epoch": 0.26787057938299474,
      "grad_norm": 11.538412094116211,
      "learning_rate": 6.307399704769099e-05,
      "loss": 10.1616,
      "step": 89
    },
    {
      "epoch": 0.2708803611738149,
      "grad_norm": 10.98781681060791,
      "learning_rate": 6.227427435703997e-05,
      "loss": 9.7931,
      "step": 90
    },
    {
      "epoch": 0.27389014296463504,
      "grad_norm": 10.231600761413574,
      "learning_rate": 6.147119600233758e-05,
      "loss": 9.1857,
      "step": 91
    },
    {
      "epoch": 0.2768999247554552,
      "grad_norm": 11.264632225036621,
      "learning_rate": 6.066498153718735e-05,
      "loss": 9.0738,
      "step": 92
    },
    {
      "epoch": 0.2799097065462754,
      "grad_norm": 12.202892303466797,
      "learning_rate": 5.985585137257401e-05,
      "loss": 9.6755,
      "step": 93
    },
    {
      "epoch": 0.28291948833709557,
      "grad_norm": 13.844965934753418,
      "learning_rate": 5.90440267166055e-05,
      "loss": 11.1556,
      "step": 94
    },
    {
      "epoch": 0.28592927012791575,
      "grad_norm": 12.187628746032715,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 9.2201,
      "step": 95
    },
    {
      "epoch": 0.28893905191873587,
      "grad_norm": 13.739523887634277,
      "learning_rate": 5.74131823855921e-05,
      "loss": 10.5167,
      "step": 96
    },
    {
      "epoch": 0.29194883370955604,
      "grad_norm": 12.928597450256348,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 9.7247,
      "step": 97
    },
    {
      "epoch": 0.2949586155003762,
      "grad_norm": 16.119169235229492,
      "learning_rate": 5.577423184847932e-05,
      "loss": 10.4071,
      "step": 98
    },
    {
      "epoch": 0.2979683972911964,
      "grad_norm": 15.795464515686035,
      "learning_rate": 5.495227651252315e-05,
      "loss": 10.2401,
      "step": 99
    },
    {
      "epoch": 0.3009781790820166,
      "grad_norm": 22.210914611816406,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 11.3174,
      "step": 100
    },
    {
      "epoch": 0.3009781790820166,
      "eval_loss": 2.4205310344696045,
      "eval_runtime": 54.9516,
      "eval_samples_per_second": 10.191,
      "eval_steps_per_second": 2.548,
      "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": 1.4453079890775245e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}