{
  "best_metric": 0.6673134565353394,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.333889816360601,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00333889816360601,
      "grad_norm": 0.6808415651321411,
      "learning_rate": 1.6666666666666668e-07,
      "loss": 0.6329,
      "step": 1
    },
    {
      "epoch": 0.00333889816360601,
      "eval_loss": 1.3715972900390625,
      "eval_runtime": 14.6478,
      "eval_samples_per_second": 34.476,
      "eval_steps_per_second": 4.369,
      "step": 1
    },
    {
      "epoch": 0.00667779632721202,
      "grad_norm": 0.9426732659339905,
      "learning_rate": 3.3333333333333335e-07,
      "loss": 0.8749,
      "step": 2
    },
    {
      "epoch": 0.01001669449081803,
      "grad_norm": 1.0648221969604492,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.8861,
      "step": 3
    },
    {
      "epoch": 0.01335559265442404,
      "grad_norm": 1.0404049158096313,
      "learning_rate": 6.666666666666667e-07,
      "loss": 0.9215,
      "step": 4
    },
    {
      "epoch": 0.01669449081803005,
      "grad_norm": 1.0711796283721924,
      "learning_rate": 8.333333333333333e-07,
      "loss": 0.9232,
      "step": 5
    },
    {
      "epoch": 0.02003338898163606,
      "grad_norm": 1.204472541809082,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.9701,
      "step": 6
    },
    {
      "epoch": 0.02337228714524207,
      "grad_norm": 1.364141583442688,
      "learning_rate": 1.1666666666666668e-06,
      "loss": 1.1403,
      "step": 7
    },
    {
      "epoch": 0.02671118530884808,
      "grad_norm": 1.2284804582595825,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 0.9842,
      "step": 8
    },
    {
      "epoch": 0.03005008347245409,
      "grad_norm": 1.3882466554641724,
      "learning_rate": 1.5e-06,
      "loss": 1.0306,
      "step": 9
    },
    {
      "epoch": 0.0333889816360601,
      "grad_norm": 1.3619149923324585,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 1.1067,
      "step": 10
    },
    {
      "epoch": 0.03672787979966611,
      "grad_norm": 1.3187345266342163,
      "learning_rate": 1.8333333333333333e-06,
      "loss": 1.0109,
      "step": 11
    },
    {
      "epoch": 0.04006677796327212,
      "grad_norm": 1.3394725322723389,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.0854,
      "step": 12
    },
    {
      "epoch": 0.04340567612687813,
      "grad_norm": 1.3412361145019531,
      "learning_rate": 2.166666666666667e-06,
      "loss": 1.0576,
      "step": 13
    },
    {
      "epoch": 0.04674457429048414,
      "grad_norm": 1.3448151350021362,
      "learning_rate": 2.3333333333333336e-06,
      "loss": 1.0436,
      "step": 14
    },
    {
      "epoch": 0.05008347245409015,
      "grad_norm": 1.5222915410995483,
      "learning_rate": 2.5e-06,
      "loss": 1.234,
      "step": 15
    },
    {
      "epoch": 0.05342237061769616,
      "grad_norm": 1.5176973342895508,
      "learning_rate": 2.666666666666667e-06,
      "loss": 1.0968,
      "step": 16
    },
    {
      "epoch": 0.05676126878130217,
      "grad_norm": 1.4612019062042236,
      "learning_rate": 2.8333333333333335e-06,
      "loss": 1.1438,
      "step": 17
    },
    {
      "epoch": 0.06010016694490818,
      "grad_norm": 1.4692972898483276,
      "learning_rate": 3e-06,
      "loss": 1.0425,
      "step": 18
    },
    {
      "epoch": 0.06343906510851419,
      "grad_norm": 1.5923115015029907,
      "learning_rate": 3.1666666666666667e-06,
      "loss": 1.0416,
      "step": 19
    },
    {
      "epoch": 0.0667779632721202,
      "grad_norm": 1.6494970321655273,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.1061,
      "step": 20
    },
    {
      "epoch": 0.07011686143572621,
      "grad_norm": 1.588154673576355,
      "learning_rate": 3.5e-06,
      "loss": 0.9903,
      "step": 21
    },
    {
      "epoch": 0.07345575959933222,
      "grad_norm": 1.5404223203659058,
      "learning_rate": 3.6666666666666666e-06,
      "loss": 1.093,
      "step": 22
    },
    {
      "epoch": 0.07679465776293823,
      "grad_norm": 1.5791702270507812,
      "learning_rate": 3.833333333333334e-06,
      "loss": 1.053,
      "step": 23
    },
    {
      "epoch": 0.08013355592654424,
      "grad_norm": 1.8075627088546753,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.0991,
      "step": 24
    },
    {
      "epoch": 0.08347245409015025,
      "grad_norm": 1.8390108346939087,
      "learning_rate": 4.166666666666667e-06,
      "loss": 0.9902,
      "step": 25
    },
    {
      "epoch": 0.08681135225375626,
      "grad_norm": 1.7681668996810913,
      "learning_rate": 4.333333333333334e-06,
      "loss": 1.0757,
      "step": 26
    },
    {
      "epoch": 0.09015025041736227,
      "grad_norm": 1.6858803033828735,
      "learning_rate": 4.5e-06,
      "loss": 0.9493,
      "step": 27
    },
    {
      "epoch": 0.09348914858096828,
      "grad_norm": 1.818709135055542,
      "learning_rate": 4.666666666666667e-06,
      "loss": 0.9834,
      "step": 28
    },
    {
      "epoch": 0.09682804674457429,
      "grad_norm": 1.8249784708023071,
      "learning_rate": 4.833333333333333e-06,
      "loss": 1.0134,
      "step": 29
    },
    {
      "epoch": 0.1001669449081803,
      "grad_norm": 1.7814394235610962,
      "learning_rate": 5e-06,
      "loss": 0.8181,
      "step": 30
    },
    {
      "epoch": 0.10350584307178631,
      "grad_norm": 2.066978931427002,
      "learning_rate": 4.997482666353287e-06,
      "loss": 0.9081,
      "step": 31
    },
    {
      "epoch": 0.10684474123539232,
      "grad_norm": 1.8057966232299805,
      "learning_rate": 4.989935734988098e-06,
      "loss": 0.8483,
      "step": 32
    },
    {
      "epoch": 0.11018363939899833,
      "grad_norm": 1.9546151161193848,
      "learning_rate": 4.977374404419838e-06,
      "loss": 0.8044,
      "step": 33
    },
    {
      "epoch": 0.11352253756260434,
      "grad_norm": 1.980887770652771,
      "learning_rate": 4.959823971496575e-06,
      "loss": 1.038,
      "step": 34
    },
    {
      "epoch": 0.11686143572621036,
      "grad_norm": 1.793314814567566,
      "learning_rate": 4.937319780454559e-06,
      "loss": 0.8432,
      "step": 35
    },
    {
      "epoch": 0.12020033388981637,
      "grad_norm": 1.9506480693817139,
      "learning_rate": 4.909907151739634e-06,
      "loss": 0.9311,
      "step": 36
    },
    {
      "epoch": 0.12353923205342238,
      "grad_norm": 2.0865514278411865,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 0.8967,
      "step": 37
    },
    {
      "epoch": 0.12687813021702837,
      "grad_norm": 2.0743038654327393,
      "learning_rate": 4.8405871765993435e-06,
      "loss": 0.9611,
      "step": 38
    },
    {
      "epoch": 0.1302170283806344,
      "grad_norm": 1.8424172401428223,
      "learning_rate": 4.7988194313786275e-06,
      "loss": 0.7384,
      "step": 39
    },
    {
      "epoch": 0.1335559265442404,
      "grad_norm": 1.9602130651474,
      "learning_rate": 4.752422169756048e-06,
      "loss": 0.771,
      "step": 40
    },
    {
      "epoch": 0.13689482470784642,
      "grad_norm": 2.0811424255371094,
      "learning_rate": 4.701488829641845e-06,
      "loss": 0.8183,
      "step": 41
    },
    {
      "epoch": 0.14023372287145242,
      "grad_norm": 2.1757004261016846,
      "learning_rate": 4.646121984004666e-06,
      "loss": 0.9766,
      "step": 42
    },
    {
      "epoch": 0.14357262103505844,
      "grad_norm": 2.3917033672332764,
      "learning_rate": 4.586433134303257e-06,
      "loss": 0.7409,
      "step": 43
    },
    {
      "epoch": 0.14691151919866444,
      "grad_norm": 2.366704225540161,
      "learning_rate": 4.522542485937369e-06,
      "loss": 0.9042,
      "step": 44
    },
    {
      "epoch": 0.15025041736227046,
      "grad_norm": 2.359403133392334,
      "learning_rate": 4.454578706170075e-06,
      "loss": 0.898,
      "step": 45
    },
    {
      "epoch": 0.15358931552587646,
      "grad_norm": 3.6760094165802,
      "learning_rate": 4.382678665009028e-06,
      "loss": 0.9776,
      "step": 46
    },
    {
      "epoch": 0.15692821368948248,
      "grad_norm": 5.558593273162842,
      "learning_rate": 4.3069871595684795e-06,
      "loss": 1.5063,
      "step": 47
    },
    {
      "epoch": 0.16026711185308848,
      "grad_norm": 8.863731384277344,
      "learning_rate": 4.227656622467162e-06,
      "loss": 2.3487,
      "step": 48
    },
    {
      "epoch": 0.1636060100166945,
      "grad_norm": 14.891101837158203,
      "learning_rate": 4.144846814849282e-06,
      "loss": 3.9516,
      "step": 49
    },
    {
      "epoch": 0.1669449081803005,
      "grad_norm": 52.261959075927734,
      "learning_rate": 4.058724504646834e-06,
      "loss": 8.3347,
      "step": 50
    },
    {
      "epoch": 0.1669449081803005,
      "eval_loss": 0.8487523794174194,
      "eval_runtime": 14.2649,
      "eval_samples_per_second": 35.402,
      "eval_steps_per_second": 4.487,
      "step": 50
    },
    {
      "epoch": 0.17028380634390652,
      "grad_norm": 2.774435043334961,
      "learning_rate": 3.969463130731183e-06,
      "loss": 0.5446,
      "step": 51
    },
    {
      "epoch": 0.17362270450751252,
      "grad_norm": 3.7148523330688477,
      "learning_rate": 3.8772424536302565e-06,
      "loss": 0.5936,
      "step": 52
    },
    {
      "epoch": 0.17696160267111852,
      "grad_norm": 3.6507351398468018,
      "learning_rate": 3.782248193514766e-06,
      "loss": 0.7174,
      "step": 53
    },
    {
      "epoch": 0.18030050083472454,
      "grad_norm": 3.6278743743896484,
      "learning_rate": 3.684671656182497e-06,
      "loss": 0.6394,
      "step": 54
    },
    {
      "epoch": 0.18363939899833054,
      "grad_norm": 3.270397186279297,
      "learning_rate": 3.5847093477938955e-06,
      "loss": 0.6554,
      "step": 55
    },
    {
      "epoch": 0.18697829716193656,
      "grad_norm": 2.640061140060425,
      "learning_rate": 3.4825625791348093e-06,
      "loss": 0.6313,
      "step": 56
    },
    {
      "epoch": 0.19031719532554256,
      "grad_norm": 2.5344226360321045,
      "learning_rate": 3.3784370602033572e-06,
      "loss": 0.6616,
      "step": 57
    },
    {
      "epoch": 0.19365609348914858,
      "grad_norm": 1.8079237937927246,
      "learning_rate": 3.272542485937369e-06,
      "loss": 0.6266,
      "step": 58
    },
    {
      "epoch": 0.19699499165275458,
      "grad_norm": 1.5996860265731812,
      "learning_rate": 3.165092113916688e-06,
      "loss": 0.6096,
      "step": 59
    },
    {
      "epoch": 0.2003338898163606,
      "grad_norm": 1.3042566776275635,
      "learning_rate": 3.056302334890786e-06,
      "loss": 0.6548,
      "step": 60
    },
    {
      "epoch": 0.2036727879799666,
      "grad_norm": 1.1529649496078491,
      "learning_rate": 2.946392236996592e-06,
      "loss": 0.6394,
      "step": 61
    },
    {
      "epoch": 0.20701168614357263,
      "grad_norm": 1.0117923021316528,
      "learning_rate": 2.835583164544139e-06,
      "loss": 0.6212,
      "step": 62
    },
    {
      "epoch": 0.21035058430717862,
      "grad_norm": 0.8776710033416748,
      "learning_rate": 2.724098272258584e-06,
      "loss": 0.5597,
      "step": 63
    },
    {
      "epoch": 0.21368948247078465,
      "grad_norm": 0.9580402970314026,
      "learning_rate": 2.6121620758762877e-06,
      "loss": 0.6268,
      "step": 64
    },
    {
      "epoch": 0.21702838063439064,
      "grad_norm": 0.9075307250022888,
      "learning_rate": 2.5e-06,
      "loss": 0.5357,
      "step": 65
    },
    {
      "epoch": 0.22036727879799667,
      "grad_norm": 0.9319755434989929,
      "learning_rate": 2.3878379241237136e-06,
      "loss": 0.5899,
      "step": 66
    },
    {
      "epoch": 0.22370617696160267,
      "grad_norm": 0.9590993523597717,
      "learning_rate": 2.2759017277414165e-06,
      "loss": 0.618,
      "step": 67
    },
    {
      "epoch": 0.2270450751252087,
      "grad_norm": 1.0425666570663452,
      "learning_rate": 2.1644168354558623e-06,
      "loss": 0.5349,
      "step": 68
    },
    {
      "epoch": 0.2303839732888147,
      "grad_norm": 0.9576693177223206,
      "learning_rate": 2.053607763003409e-06,
      "loss": 0.5221,
      "step": 69
    },
    {
      "epoch": 0.2337228714524207,
      "grad_norm": 0.8880669474601746,
      "learning_rate": 1.9436976651092143e-06,
      "loss": 0.493,
      "step": 70
    },
    {
      "epoch": 0.2370617696160267,
      "grad_norm": 1.1609593629837036,
      "learning_rate": 1.8349078860833125e-06,
      "loss": 0.62,
      "step": 71
    },
    {
      "epoch": 0.24040066777963273,
      "grad_norm": 1.0580207109451294,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 0.5414,
      "step": 72
    },
    {
      "epoch": 0.24373956594323873,
      "grad_norm": 0.9047161340713501,
      "learning_rate": 1.6215629397966432e-06,
      "loss": 0.4679,
      "step": 73
    },
    {
      "epoch": 0.24707846410684475,
      "grad_norm": 1.0645842552185059,
      "learning_rate": 1.5174374208651913e-06,
      "loss": 0.5592,
      "step": 74
    },
    {
      "epoch": 0.25041736227045075,
      "grad_norm": 1.0351444482803345,
      "learning_rate": 1.415290652206105e-06,
      "loss": 0.4938,
      "step": 75
    },
    {
      "epoch": 0.25375626043405675,
      "grad_norm": 1.0303648710250854,
      "learning_rate": 1.3153283438175036e-06,
      "loss": 0.5191,
      "step": 76
    },
    {
      "epoch": 0.2570951585976628,
      "grad_norm": 1.0689729452133179,
      "learning_rate": 1.217751806485235e-06,
      "loss": 0.5241,
      "step": 77
    },
    {
      "epoch": 0.2604340567612688,
      "grad_norm": 1.0949710607528687,
      "learning_rate": 1.122757546369744e-06,
      "loss": 0.5091,
      "step": 78
    },
    {
      "epoch": 0.2637729549248748,
      "grad_norm": 1.066139578819275,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 0.5245,
      "step": 79
    },
    {
      "epoch": 0.2671118530884808,
      "grad_norm": 1.0166308879852295,
      "learning_rate": 9.412754953531664e-07,
      "loss": 0.4759,
      "step": 80
    },
    {
      "epoch": 0.2704507512520868,
      "grad_norm": 1.113553524017334,
      "learning_rate": 8.551531851507186e-07,
      "loss": 0.4975,
      "step": 81
    },
    {
      "epoch": 0.27378964941569284,
      "grad_norm": 1.1330246925354004,
      "learning_rate": 7.723433775328385e-07,
      "loss": 0.5459,
      "step": 82
    },
    {
      "epoch": 0.27712854757929883,
      "grad_norm": 1.0714497566223145,
      "learning_rate": 6.930128404315214e-07,
      "loss": 0.4841,
      "step": 83
    },
    {
      "epoch": 0.28046744574290483,
      "grad_norm": 1.0576684474945068,
      "learning_rate": 6.17321334990973e-07,
      "loss": 0.4325,
      "step": 84
    },
    {
      "epoch": 0.2838063439065108,
      "grad_norm": 1.2464218139648438,
      "learning_rate": 5.454212938299256e-07,
      "loss": 0.5759,
      "step": 85
    },
    {
      "epoch": 0.2871452420701169,
      "grad_norm": 1.2016359567642212,
      "learning_rate": 4.774575140626317e-07,
      "loss": 0.4957,
      "step": 86
    },
    {
      "epoch": 0.2904841402337229,
      "grad_norm": 1.2413355112075806,
      "learning_rate": 4.1356686569674344e-07,
      "loss": 0.5146,
      "step": 87
    },
    {
      "epoch": 0.2938230383973289,
      "grad_norm": 1.3268682956695557,
      "learning_rate": 3.538780159953348e-07,
      "loss": 0.6438,
      "step": 88
    },
    {
      "epoch": 0.29716193656093487,
      "grad_norm": 1.2803572416305542,
      "learning_rate": 2.98511170358155e-07,
      "loss": 0.5471,
      "step": 89
    },
    {
      "epoch": 0.3005008347245409,
      "grad_norm": 1.4874416589736938,
      "learning_rate": 2.4757783024395244e-07,
      "loss": 0.548,
      "step": 90
    },
    {
      "epoch": 0.3038397328881469,
      "grad_norm": 1.5271040201187134,
      "learning_rate": 2.0118056862137358e-07,
      "loss": 0.5197,
      "step": 91
    },
    {
      "epoch": 0.3071786310517529,
      "grad_norm": 1.6254510879516602,
      "learning_rate": 1.59412823400657e-07,
      "loss": 0.6227,
      "step": 92
    },
    {
      "epoch": 0.3105175292153589,
      "grad_norm": 1.617385983467102,
      "learning_rate": 1.223587092621162e-07,
      "loss": 0.5972,
      "step": 93
    },
    {
      "epoch": 0.31385642737896496,
      "grad_norm": 1.9136462211608887,
      "learning_rate": 9.00928482603669e-08,
      "loss": 0.7396,
      "step": 94
    },
    {
      "epoch": 0.31719532554257096,
      "grad_norm": 2.216195821762085,
      "learning_rate": 6.268021954544095e-08,
      "loss": 0.6338,
      "step": 95
    },
    {
      "epoch": 0.32053422370617696,
      "grad_norm": 2.8479862213134766,
      "learning_rate": 4.017602850342584e-08,
      "loss": 0.725,
      "step": 96
    },
    {
      "epoch": 0.32387312186978295,
      "grad_norm": 4.363030910491943,
      "learning_rate": 2.262559558016325e-08,
      "loss": 1.1272,
      "step": 97
    },
    {
      "epoch": 0.327212020033389,
      "grad_norm": 8.434501647949219,
      "learning_rate": 1.006426501190233e-08,
      "loss": 1.9515,
      "step": 98
    },
    {
      "epoch": 0.330550918196995,
      "grad_norm": 16.16083335876465,
      "learning_rate": 2.5173336467135266e-09,
      "loss": 3.21,
      "step": 99
    },
    {
      "epoch": 0.333889816360601,
      "grad_norm": 50.90562057495117,
      "learning_rate": 0.0,
      "loss": 7.3095,
      "step": 100
    },
    {
      "epoch": 0.333889816360601,
      "eval_loss": 0.6673134565353394,
      "eval_runtime": 14.2635,
      "eval_samples_per_second": 35.405,
      "eval_steps_per_second": 4.487,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.728250925121536e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}