{
  "best_metric": 0.7389817237854004,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.017681902572716825,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017681902572716824,
      "grad_norm": 30.77566909790039,
      "learning_rate": 1e-05,
      "loss": 5.7904,
      "step": 1
    },
    {
      "epoch": 0.00017681902572716824,
      "eval_loss": 1.5057493448257446,
      "eval_runtime": 699.8238,
      "eval_samples_per_second": 13.611,
      "eval_steps_per_second": 3.404,
      "step": 1
    },
    {
      "epoch": 0.0003536380514543365,
      "grad_norm": 33.43643569946289,
      "learning_rate": 2e-05,
      "loss": 6.1229,
      "step": 2
    },
    {
      "epoch": 0.0005304570771815047,
      "grad_norm": 22.859066009521484,
      "learning_rate": 3e-05,
      "loss": 5.832,
      "step": 3
    },
    {
      "epoch": 0.000707276102908673,
      "grad_norm": 16.750789642333984,
      "learning_rate": 4e-05,
      "loss": 4.8626,
      "step": 4
    },
    {
      "epoch": 0.0008840951286358412,
      "grad_norm": 14.933880805969238,
      "learning_rate": 5e-05,
      "loss": 4.4985,
      "step": 5
    },
    {
      "epoch": 0.0010609141543630094,
      "grad_norm": 12.131953239440918,
      "learning_rate": 6e-05,
      "loss": 3.9705,
      "step": 6
    },
    {
      "epoch": 0.0012377331800901778,
      "grad_norm": 10.108991622924805,
      "learning_rate": 7e-05,
      "loss": 3.774,
      "step": 7
    },
    {
      "epoch": 0.001414552205817346,
      "grad_norm": 10.229625701904297,
      "learning_rate": 8e-05,
      "loss": 3.6096,
      "step": 8
    },
    {
      "epoch": 0.001591371231544514,
      "grad_norm": 10.535920143127441,
      "learning_rate": 9e-05,
      "loss": 3.4153,
      "step": 9
    },
    {
      "epoch": 0.0017681902572716825,
      "grad_norm": 9.722245216369629,
      "learning_rate": 0.0001,
      "loss": 3.6757,
      "step": 10
    },
    {
      "epoch": 0.0019450092829988506,
      "grad_norm": 15.117246627807617,
      "learning_rate": 9.999316524962345e-05,
      "loss": 3.6501,
      "step": 11
    },
    {
      "epoch": 0.002121828308726019,
      "grad_norm": 8.139172554016113,
      "learning_rate": 9.997266286704631e-05,
      "loss": 3.5474,
      "step": 12
    },
    {
      "epoch": 0.002298647334453187,
      "grad_norm": 9.034537315368652,
      "learning_rate": 9.993849845741524e-05,
      "loss": 3.4964,
      "step": 13
    },
    {
      "epoch": 0.0024754663601803555,
      "grad_norm": 7.310268402099609,
      "learning_rate": 9.989068136093873e-05,
      "loss": 3.3639,
      "step": 14
    },
    {
      "epoch": 0.0026522853859075237,
      "grad_norm": 6.865406513214111,
      "learning_rate": 9.98292246503335e-05,
      "loss": 3.2937,
      "step": 15
    },
    {
      "epoch": 0.002829104411634692,
      "grad_norm": 6.944815635681152,
      "learning_rate": 9.975414512725057e-05,
      "loss": 3.2835,
      "step": 16
    },
    {
      "epoch": 0.00300592343736186,
      "grad_norm": 6.507901668548584,
      "learning_rate": 9.966546331768191e-05,
      "loss": 3.1566,
      "step": 17
    },
    {
      "epoch": 0.003182742463089028,
      "grad_norm": 7.71777868270874,
      "learning_rate": 9.956320346634876e-05,
      "loss": 3.2667,
      "step": 18
    },
    {
      "epoch": 0.0033595614888161968,
      "grad_norm": 6.91279935836792,
      "learning_rate": 9.944739353007344e-05,
      "loss": 3.1104,
      "step": 19
    },
    {
      "epoch": 0.003536380514543365,
      "grad_norm": 6.425033092498779,
      "learning_rate": 9.931806517013612e-05,
      "loss": 3.1124,
      "step": 20
    },
    {
      "epoch": 0.003713199540270533,
      "grad_norm": 6.594813346862793,
      "learning_rate": 9.917525374361912e-05,
      "loss": 3.0918,
      "step": 21
    },
    {
      "epoch": 0.0038900185659977013,
      "grad_norm": 6.123743534088135,
      "learning_rate": 9.901899829374047e-05,
      "loss": 3.1857,
      "step": 22
    },
    {
      "epoch": 0.00406683759172487,
      "grad_norm": 5.8520989418029785,
      "learning_rate": 9.884934153917997e-05,
      "loss": 3.1095,
      "step": 23
    },
    {
      "epoch": 0.004243656617452038,
      "grad_norm": 5.65989351272583,
      "learning_rate": 9.86663298624003e-05,
      "loss": 3.1227,
      "step": 24
    },
    {
      "epoch": 0.004420475643179206,
      "grad_norm": 6.06626558303833,
      "learning_rate": 9.847001329696653e-05,
      "loss": 3.0941,
      "step": 25
    },
    {
      "epoch": 0.004597294668906374,
      "grad_norm": 6.0456132888793945,
      "learning_rate": 9.826044551386744e-05,
      "loss": 3.017,
      "step": 26
    },
    {
      "epoch": 0.0047741136946335425,
      "grad_norm": 5.214839935302734,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.7115,
      "step": 27
    },
    {
      "epoch": 0.004950932720360711,
      "grad_norm": 5.342077732086182,
      "learning_rate": 9.780178907671789e-05,
      "loss": 3.1084,
      "step": 28
    },
    {
      "epoch": 0.005127751746087879,
      "grad_norm": 5.682497501373291,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.8929,
      "step": 29
    },
    {
      "epoch": 0.005304570771815047,
      "grad_norm": 5.593482494354248,
      "learning_rate": 9.729086208503174e-05,
      "loss": 3.1474,
      "step": 30
    },
    {
      "epoch": 0.005481389797542215,
      "grad_norm": 5.597923278808594,
      "learning_rate": 9.701596950580806e-05,
      "loss": 2.746,
      "step": 31
    },
    {
      "epoch": 0.005658208823269384,
      "grad_norm": 6.232513427734375,
      "learning_rate": 9.672822322997305e-05,
      "loss": 2.9022,
      "step": 32
    },
    {
      "epoch": 0.005835027848996552,
      "grad_norm": 5.472952365875244,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.9239,
      "step": 33
    },
    {
      "epoch": 0.00601184687472372,
      "grad_norm": 4.986033916473389,
      "learning_rate": 9.611448774886924e-05,
      "loss": 2.8302,
      "step": 34
    },
    {
      "epoch": 0.006188665900450889,
      "grad_norm": 4.939537525177002,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.9965,
      "step": 35
    },
    {
      "epoch": 0.006365484926178056,
      "grad_norm": 4.7341628074646,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.8888,
      "step": 36
    },
    {
      "epoch": 0.006542303951905225,
      "grad_norm": 5.597661018371582,
      "learning_rate": 9.509956150664796e-05,
      "loss": 2.9968,
      "step": 37
    },
    {
      "epoch": 0.0067191229776323936,
      "grad_norm": 5.1189165115356445,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.8592,
      "step": 38
    },
    {
      "epoch": 0.006895942003359561,
      "grad_norm": 5.132823944091797,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.9616,
      "step": 39
    },
    {
      "epoch": 0.00707276102908673,
      "grad_norm": 5.72930383682251,
      "learning_rate": 9.397368756032445e-05,
      "loss": 2.7738,
      "step": 40
    },
    {
      "epoch": 0.007249580054813898,
      "grad_norm": 5.405780792236328,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.9437,
      "step": 41
    },
    {
      "epoch": 0.007426399080541066,
      "grad_norm": 5.408172607421875,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.8486,
      "step": 42
    },
    {
      "epoch": 0.007603218106268235,
      "grad_norm": 4.897181987762451,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.6534,
      "step": 43
    },
    {
      "epoch": 0.0077800371319954025,
      "grad_norm": 4.973101615905762,
      "learning_rate": 9.230476262104677e-05,
      "loss": 2.7654,
      "step": 44
    },
    {
      "epoch": 0.007956856157722571,
      "grad_norm": 4.965903282165527,
      "learning_rate": 9.185832391312644e-05,
      "loss": 2.7389,
      "step": 45
    },
    {
      "epoch": 0.00813367518344974,
      "grad_norm": 5.6687750816345215,
      "learning_rate": 9.140044155740101e-05,
      "loss": 2.6717,
      "step": 46
    },
    {
      "epoch": 0.008310494209176908,
      "grad_norm": 5.180047512054443,
      "learning_rate": 9.093124073433463e-05,
      "loss": 2.7604,
      "step": 47
    },
    {
      "epoch": 0.008487313234904075,
      "grad_norm": 4.873654842376709,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.6169,
      "step": 48
    },
    {
      "epoch": 0.008664132260631244,
      "grad_norm": 6.44728946685791,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.6376,
      "step": 49
    },
    {
      "epoch": 0.008840951286358412,
      "grad_norm": 7.412442207336426,
      "learning_rate": 8.945702546981969e-05,
      "loss": 2.8407,
      "step": 50
    },
    {
      "epoch": 0.008840951286358412,
      "eval_loss": 0.8082038164138794,
      "eval_runtime": 704.1742,
      "eval_samples_per_second": 13.526,
      "eval_steps_per_second": 3.383,
      "step": 50
    },
    {
      "epoch": 0.009017770312085581,
      "grad_norm": 10.941012382507324,
      "learning_rate": 8.894386393810563e-05,
      "loss": 3.9579,
      "step": 51
    },
    {
      "epoch": 0.009194589337812748,
      "grad_norm": 5.875502109527588,
      "learning_rate": 8.842005554284296e-05,
      "loss": 3.3415,
      "step": 52
    },
    {
      "epoch": 0.009371408363539916,
      "grad_norm": 5.685242652893066,
      "learning_rate": 8.788574348801675e-05,
      "loss": 3.1855,
      "step": 53
    },
    {
      "epoch": 0.009548227389267085,
      "grad_norm": 7.529914855957031,
      "learning_rate": 8.73410738492077e-05,
      "loss": 3.3116,
      "step": 54
    },
    {
      "epoch": 0.009725046414994254,
      "grad_norm": 4.6792707443237305,
      "learning_rate": 8.678619553365659e-05,
      "loss": 3.022,
      "step": 55
    },
    {
      "epoch": 0.009901865440721422,
      "grad_norm": 4.322147369384766,
      "learning_rate": 8.622126023955446e-05,
      "loss": 3.1485,
      "step": 56
    },
    {
      "epoch": 0.010078684466448589,
      "grad_norm": 4.370192050933838,
      "learning_rate": 8.564642241456986e-05,
      "loss": 3.0674,
      "step": 57
    },
    {
      "epoch": 0.010255503492175758,
      "grad_norm": 4.796641826629639,
      "learning_rate": 8.506183921362443e-05,
      "loss": 2.998,
      "step": 58
    },
    {
      "epoch": 0.010432322517902926,
      "grad_norm": 5.605325698852539,
      "learning_rate": 8.44676704559283e-05,
      "loss": 3.1447,
      "step": 59
    },
    {
      "epoch": 0.010609141543630095,
      "grad_norm": 4.807485103607178,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.9791,
      "step": 60
    },
    {
      "epoch": 0.010785960569357263,
      "grad_norm": 4.288360595703125,
      "learning_rate": 8.32512286056924e-05,
      "loss": 2.8238,
      "step": 61
    },
    {
      "epoch": 0.01096277959508443,
      "grad_norm": 4.529268264770508,
      "learning_rate": 8.262928807620843e-05,
      "loss": 3.0149,
      "step": 62
    },
    {
      "epoch": 0.011139598620811599,
      "grad_norm": 4.85869026184082,
      "learning_rate": 8.199842702516583e-05,
      "loss": 3.0277,
      "step": 63
    },
    {
      "epoch": 0.011316417646538767,
      "grad_norm": 4.504361152648926,
      "learning_rate": 8.135881792367686e-05,
      "loss": 2.8148,
      "step": 64
    },
    {
      "epoch": 0.011493236672265936,
      "grad_norm": 4.638814449310303,
      "learning_rate": 8.07106356344834e-05,
      "loss": 3.145,
      "step": 65
    },
    {
      "epoch": 0.011670055697993105,
      "grad_norm": 4.652398109436035,
      "learning_rate": 8.005405736415126e-05,
      "loss": 2.8357,
      "step": 66
    },
    {
      "epoch": 0.011846874723720272,
      "grad_norm": 4.040258884429932,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.7536,
      "step": 67
    },
    {
      "epoch": 0.01202369374944744,
      "grad_norm": 4.549870014190674,
      "learning_rate": 7.871643313414718e-05,
      "loss": 2.9259,
      "step": 68
    },
    {
      "epoch": 0.012200512775174609,
      "grad_norm": 3.9912383556365967,
      "learning_rate": 7.803575286758364e-05,
      "loss": 2.7272,
      "step": 69
    },
    {
      "epoch": 0.012377331800901777,
      "grad_norm": 4.487094402313232,
      "learning_rate": 7.734740790612136e-05,
      "loss": 2.8944,
      "step": 70
    },
    {
      "epoch": 0.012554150826628946,
      "grad_norm": 4.489090919494629,
      "learning_rate": 7.66515864363997e-05,
      "loss": 2.9474,
      "step": 71
    },
    {
      "epoch": 0.012730969852356113,
      "grad_norm": 4.538005828857422,
      "learning_rate": 7.594847868906076e-05,
      "loss": 2.8556,
      "step": 72
    },
    {
      "epoch": 0.012907788878083281,
      "grad_norm": 4.3861470222473145,
      "learning_rate": 7.52382768867422e-05,
      "loss": 3.0211,
      "step": 73
    },
    {
      "epoch": 0.01308460790381045,
      "grad_norm": 4.112513065338135,
      "learning_rate": 7.452117519152542e-05,
      "loss": 2.8523,
      "step": 74
    },
    {
      "epoch": 0.013261426929537619,
      "grad_norm": 4.240283489227295,
      "learning_rate": 7.379736965185368e-05,
      "loss": 2.7448,
      "step": 75
    },
    {
      "epoch": 0.013438245955264787,
      "grad_norm": 4.358696460723877,
      "learning_rate": 7.30670581489344e-05,
      "loss": 2.8285,
      "step": 76
    },
    {
      "epoch": 0.013615064980991954,
      "grad_norm": 4.034807205200195,
      "learning_rate": 7.233044034264034e-05,
      "loss": 2.7714,
      "step": 77
    },
    {
      "epoch": 0.013791884006719123,
      "grad_norm": 4.1600518226623535,
      "learning_rate": 7.158771761692464e-05,
      "loss": 2.915,
      "step": 78
    },
    {
      "epoch": 0.013968703032446291,
      "grad_norm": 4.095190525054932,
      "learning_rate": 7.083909302476453e-05,
      "loss": 2.8567,
      "step": 79
    },
    {
      "epoch": 0.01414552205817346,
      "grad_norm": 4.382471084594727,
      "learning_rate": 7.008477123264848e-05,
      "loss": 2.9988,
      "step": 80
    },
    {
      "epoch": 0.014322341083900628,
      "grad_norm": 4.3130269050598145,
      "learning_rate": 6.932495846462261e-05,
      "loss": 2.7513,
      "step": 81
    },
    {
      "epoch": 0.014499160109627795,
      "grad_norm": 4.03249454498291,
      "learning_rate": 6.855986244591104e-05,
      "loss": 2.8703,
      "step": 82
    },
    {
      "epoch": 0.014675979135354964,
      "grad_norm": 3.758502244949341,
      "learning_rate": 6.778969234612584e-05,
      "loss": 2.7361,
      "step": 83
    },
    {
      "epoch": 0.014852798161082132,
      "grad_norm": 4.064537048339844,
      "learning_rate": 6.701465872208216e-05,
      "loss": 2.697,
      "step": 84
    },
    {
      "epoch": 0.015029617186809301,
      "grad_norm": 4.2941670417785645,
      "learning_rate": 6.623497346023418e-05,
      "loss": 2.9156,
      "step": 85
    },
    {
      "epoch": 0.01520643621253647,
      "grad_norm": 4.217069625854492,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.6571,
      "step": 86
    },
    {
      "epoch": 0.015383255238263636,
      "grad_norm": 4.212507247924805,
      "learning_rate": 6.466250186922325e-05,
      "loss": 2.7511,
      "step": 87
    },
    {
      "epoch": 0.015560074263990805,
      "grad_norm": 4.505743980407715,
      "learning_rate": 6.387014543809223e-05,
      "loss": 2.6847,
      "step": 88
    },
    {
      "epoch": 0.015736893289717974,
      "grad_norm": 3.9542410373687744,
      "learning_rate": 6.307399704769099e-05,
      "loss": 2.4308,
      "step": 89
    },
    {
      "epoch": 0.015913712315445142,
      "grad_norm": 4.286926746368408,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.5392,
      "step": 90
    },
    {
      "epoch": 0.01609053134117231,
      "grad_norm": 4.219004154205322,
      "learning_rate": 6.147119600233758e-05,
      "loss": 2.5647,
      "step": 91
    },
    {
      "epoch": 0.01626735036689948,
      "grad_norm": 4.355921268463135,
      "learning_rate": 6.066498153718735e-05,
      "loss": 2.7065,
      "step": 92
    },
    {
      "epoch": 0.016444169392626648,
      "grad_norm": 3.816110610961914,
      "learning_rate": 5.985585137257401e-05,
      "loss": 2.4166,
      "step": 93
    },
    {
      "epoch": 0.016620988418353817,
      "grad_norm": 3.980553388595581,
      "learning_rate": 5.90440267166055e-05,
      "loss": 2.4319,
      "step": 94
    },
    {
      "epoch": 0.01679780744408098,
      "grad_norm": 4.162726879119873,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 2.6132,
      "step": 95
    },
    {
      "epoch": 0.01697462646980815,
      "grad_norm": 3.9977686405181885,
      "learning_rate": 5.74131823855921e-05,
      "loss": 2.5249,
      "step": 96
    },
    {
      "epoch": 0.01715144549553532,
      "grad_norm": 4.283101558685303,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 2.5313,
      "step": 97
    },
    {
      "epoch": 0.017328264521262488,
      "grad_norm": 4.2165656089782715,
      "learning_rate": 5.577423184847932e-05,
      "loss": 2.4478,
      "step": 98
    },
    {
      "epoch": 0.017505083546989656,
      "grad_norm": 4.173795223236084,
      "learning_rate": 5.495227651252315e-05,
      "loss": 2.427,
      "step": 99
    },
    {
      "epoch": 0.017681902572716825,
      "grad_norm": 4.588566780090332,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 2.4309,
      "step": 100
    },
    {
      "epoch": 0.017681902572716825,
      "eval_loss": 0.7389817237854004,
      "eval_runtime": 704.1343,
      "eval_samples_per_second": 13.527,
      "eval_steps_per_second": 3.383,
      "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": 1.430999619600384e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}