{
  "best_metric": 11.038614273071289,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.09813542688910697,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009813542688910696,
      "grad_norm": 4.1202497482299805,
      "learning_rate": 5.000000000000001e-07,
      "loss": 44.3701,
      "step": 1
    },
    {
      "epoch": 0.0009813542688910696,
      "eval_loss": 11.094230651855469,
      "eval_runtime": 5.8483,
      "eval_samples_per_second": 293.417,
      "eval_steps_per_second": 36.763,
      "step": 1
    },
    {
      "epoch": 0.001962708537782139,
      "grad_norm": 4.6952314376831055,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 44.357,
      "step": 2
    },
    {
      "epoch": 0.002944062806673209,
      "grad_norm": 4.975703239440918,
      "learning_rate": 1.5e-06,
      "loss": 44.3399,
      "step": 3
    },
    {
      "epoch": 0.003925417075564278,
      "grad_norm": 4.898032188415527,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 44.3496,
      "step": 4
    },
    {
      "epoch": 0.004906771344455349,
      "grad_norm": 4.699200630187988,
      "learning_rate": 2.5e-06,
      "loss": 44.3727,
      "step": 5
    },
    {
      "epoch": 0.005888125613346418,
      "grad_norm": 4.840972423553467,
      "learning_rate": 3e-06,
      "loss": 44.3562,
      "step": 6
    },
    {
      "epoch": 0.0068694798822374874,
      "grad_norm": 4.837454795837402,
      "learning_rate": 3.5e-06,
      "loss": 44.3481,
      "step": 7
    },
    {
      "epoch": 0.007850834151128557,
      "grad_norm": 4.493252754211426,
      "learning_rate": 4.000000000000001e-06,
      "loss": 44.3513,
      "step": 8
    },
    {
      "epoch": 0.008832188420019628,
      "grad_norm": 4.787064552307129,
      "learning_rate": 4.5e-06,
      "loss": 44.3664,
      "step": 9
    },
    {
      "epoch": 0.009813542688910697,
      "grad_norm": 4.681407928466797,
      "learning_rate": 5e-06,
      "loss": 44.3545,
      "step": 10
    },
    {
      "epoch": 0.010794896957801767,
      "grad_norm": 4.4647321701049805,
      "learning_rate": 4.99847706754774e-06,
      "loss": 44.3586,
      "step": 11
    },
    {
      "epoch": 0.011776251226692836,
      "grad_norm": 4.408224105834961,
      "learning_rate": 4.993910125649561e-06,
      "loss": 44.3444,
      "step": 12
    },
    {
      "epoch": 0.012757605495583905,
      "grad_norm": 4.694049835205078,
      "learning_rate": 4.986304738420684e-06,
      "loss": 44.3296,
      "step": 13
    },
    {
      "epoch": 0.013738959764474975,
      "grad_norm": 4.30063009262085,
      "learning_rate": 4.975670171853926e-06,
      "loss": 44.3525,
      "step": 14
    },
    {
      "epoch": 0.014720314033366046,
      "grad_norm": 4.59287691116333,
      "learning_rate": 4.962019382530521e-06,
      "loss": 44.3156,
      "step": 15
    },
    {
      "epoch": 0.015701668302257114,
      "grad_norm": 4.614467620849609,
      "learning_rate": 4.9453690018345144e-06,
      "loss": 44.3097,
      "step": 16
    },
    {
      "epoch": 0.016683022571148183,
      "grad_norm": 4.312943935394287,
      "learning_rate": 4.925739315689991e-06,
      "loss": 44.3131,
      "step": 17
    },
    {
      "epoch": 0.017664376840039256,
      "grad_norm": 4.630992412567139,
      "learning_rate": 4.903154239845798e-06,
      "loss": 44.3009,
      "step": 18
    },
    {
      "epoch": 0.018645731108930325,
      "grad_norm": 4.261321544647217,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 44.294,
      "step": 19
    },
    {
      "epoch": 0.019627085377821395,
      "grad_norm": 4.367868423461914,
      "learning_rate": 4.849231551964771e-06,
      "loss": 44.3004,
      "step": 20
    },
    {
      "epoch": 0.020608439646712464,
      "grad_norm": 4.4335503578186035,
      "learning_rate": 4.817959636416969e-06,
      "loss": 44.3056,
      "step": 21
    },
    {
      "epoch": 0.021589793915603533,
      "grad_norm": 4.420947074890137,
      "learning_rate": 4.783863644106502e-06,
      "loss": 44.2962,
      "step": 22
    },
    {
      "epoch": 0.022571148184494603,
      "grad_norm": 4.479759693145752,
      "learning_rate": 4.746985115747918e-06,
      "loss": 44.2849,
      "step": 23
    },
    {
      "epoch": 0.023552502453385672,
      "grad_norm": 4.4245805740356445,
      "learning_rate": 4.707368982147318e-06,
      "loss": 44.3022,
      "step": 24
    },
    {
      "epoch": 0.02453385672227674,
      "grad_norm": 4.920063495635986,
      "learning_rate": 4.665063509461098e-06,
      "loss": 44.2652,
      "step": 25
    },
    {
      "epoch": 0.02551521099116781,
      "grad_norm": 4.60530424118042,
      "learning_rate": 4.620120240391065e-06,
      "loss": 44.2587,
      "step": 26
    },
    {
      "epoch": 0.02649656526005888,
      "grad_norm": 4.810507774353027,
      "learning_rate": 4.572593931387604e-06,
      "loss": 44.2725,
      "step": 27
    },
    {
      "epoch": 0.02747791952894995,
      "grad_norm": 4.324153900146484,
      "learning_rate": 4.522542485937369e-06,
      "loss": 44.2904,
      "step": 28
    },
    {
      "epoch": 0.02845927379784102,
      "grad_norm": 4.457505226135254,
      "learning_rate": 4.470026884016805e-06,
      "loss": 44.2651,
      "step": 29
    },
    {
      "epoch": 0.029440628066732092,
      "grad_norm": 4.2836151123046875,
      "learning_rate": 4.415111107797445e-06,
      "loss": 44.272,
      "step": 30
    },
    {
      "epoch": 0.03042198233562316,
      "grad_norm": 4.381106853485107,
      "learning_rate": 4.357862063693486e-06,
      "loss": 44.2687,
      "step": 31
    },
    {
      "epoch": 0.03140333660451423,
      "grad_norm": 4.747635841369629,
      "learning_rate": 4.2983495008466285e-06,
      "loss": 44.2819,
      "step": 32
    },
    {
      "epoch": 0.0323846908734053,
      "grad_norm": 4.578216075897217,
      "learning_rate": 4.236645926147493e-06,
      "loss": 44.2072,
      "step": 33
    },
    {
      "epoch": 0.033366045142296366,
      "grad_norm": 4.499361515045166,
      "learning_rate": 4.172826515897146e-06,
      "loss": 44.2359,
      "step": 34
    },
    {
      "epoch": 0.03434739941118744,
      "grad_norm": 4.1071553230285645,
      "learning_rate": 4.106969024216348e-06,
      "loss": 44.2548,
      "step": 35
    },
    {
      "epoch": 0.03532875368007851,
      "grad_norm": 4.5971550941467285,
      "learning_rate": 4.039153688314146e-06,
      "loss": 44.2519,
      "step": 36
    },
    {
      "epoch": 0.03631010794896958,
      "grad_norm": 4.54329776763916,
      "learning_rate": 3.969463130731183e-06,
      "loss": 44.2257,
      "step": 37
    },
    {
      "epoch": 0.03729146221786065,
      "grad_norm": 4.047177791595459,
      "learning_rate": 3.897982258676867e-06,
      "loss": 44.2495,
      "step": 38
    },
    {
      "epoch": 0.038272816486751716,
      "grad_norm": 3.584639549255371,
      "learning_rate": 3.824798160583012e-06,
      "loss": 44.2784,
      "step": 39
    },
    {
      "epoch": 0.03925417075564279,
      "grad_norm": 3.700026750564575,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 44.2736,
      "step": 40
    },
    {
      "epoch": 0.040235525024533855,
      "grad_norm": 4.082536220550537,
      "learning_rate": 3.6736789069647273e-06,
      "loss": 44.2867,
      "step": 41
    },
    {
      "epoch": 0.04121687929342493,
      "grad_norm": 3.2533934116363525,
      "learning_rate": 3.595927866972694e-06,
      "loss": 44.319,
      "step": 42
    },
    {
      "epoch": 0.042198233562315994,
      "grad_norm": 3.820909261703491,
      "learning_rate": 3.516841607689501e-06,
      "loss": 44.2602,
      "step": 43
    },
    {
      "epoch": 0.04317958783120707,
      "grad_norm": 3.5113043785095215,
      "learning_rate": 3.436516483539781e-06,
      "loss": 44.2805,
      "step": 44
    },
    {
      "epoch": 0.04416094210009813,
      "grad_norm": 3.5770328044891357,
      "learning_rate": 3.3550503583141726e-06,
      "loss": 44.3724,
      "step": 45
    },
    {
      "epoch": 0.045142296368989206,
      "grad_norm": 3.635390043258667,
      "learning_rate": 3.272542485937369e-06,
      "loss": 44.4049,
      "step": 46
    },
    {
      "epoch": 0.04612365063788027,
      "grad_norm": 3.494272232055664,
      "learning_rate": 3.189093389542498e-06,
      "loss": 44.3339,
      "step": 47
    },
    {
      "epoch": 0.047105004906771344,
      "grad_norm": 4.5640668869018555,
      "learning_rate": 3.1048047389991693e-06,
      "loss": 44.3798,
      "step": 48
    },
    {
      "epoch": 0.04808635917566242,
      "grad_norm": 5.724422931671143,
      "learning_rate": 3.019779227044398e-06,
      "loss": 44.29,
      "step": 49
    },
    {
      "epoch": 0.04906771344455348,
      "grad_norm": 6.1241936683654785,
      "learning_rate": 2.9341204441673267e-06,
      "loss": 44.4495,
      "step": 50
    },
    {
      "epoch": 0.04906771344455348,
      "eval_loss": 11.050891876220703,
      "eval_runtime": 5.0876,
      "eval_samples_per_second": 337.292,
      "eval_steps_per_second": 42.26,
      "step": 50
    },
    {
      "epoch": 0.050049067713444556,
      "grad_norm": 4.3872294425964355,
      "learning_rate": 2.847932752400164e-06,
      "loss": 44.1583,
      "step": 51
    },
    {
      "epoch": 0.05103042198233562,
      "grad_norm": 4.958473205566406,
      "learning_rate": 2.761321158169134e-06,
      "loss": 44.1556,
      "step": 52
    },
    {
      "epoch": 0.052011776251226695,
      "grad_norm": 4.641199588775635,
      "learning_rate": 2.6743911843603134e-06,
      "loss": 44.1518,
      "step": 53
    },
    {
      "epoch": 0.05299313052011776,
      "grad_norm": 4.831917762756348,
      "learning_rate": 2.587248741756253e-06,
      "loss": 44.1574,
      "step": 54
    },
    {
      "epoch": 0.053974484789008834,
      "grad_norm": 4.641740322113037,
      "learning_rate": 2.5e-06,
      "loss": 44.177,
      "step": 55
    },
    {
      "epoch": 0.0549558390578999,
      "grad_norm": 5.027724742889404,
      "learning_rate": 2.4127512582437486e-06,
      "loss": 44.1403,
      "step": 56
    },
    {
      "epoch": 0.05593719332679097,
      "grad_norm": 4.93941068649292,
      "learning_rate": 2.325608815639687e-06,
      "loss": 44.1304,
      "step": 57
    },
    {
      "epoch": 0.05691854759568204,
      "grad_norm": 4.8098063468933105,
      "learning_rate": 2.238678841830867e-06,
      "loss": 44.1245,
      "step": 58
    },
    {
      "epoch": 0.05789990186457311,
      "grad_norm": 4.973179340362549,
      "learning_rate": 2.1520672475998374e-06,
      "loss": 44.141,
      "step": 59
    },
    {
      "epoch": 0.058881256133464184,
      "grad_norm": 4.688238620758057,
      "learning_rate": 2.0658795558326745e-06,
      "loss": 44.154,
      "step": 60
    },
    {
      "epoch": 0.05986261040235525,
      "grad_norm": 4.850657939910889,
      "learning_rate": 1.9802207729556023e-06,
      "loss": 44.1483,
      "step": 61
    },
    {
      "epoch": 0.06084396467124632,
      "grad_norm": 4.537477016448975,
      "learning_rate": 1.895195261000831e-06,
      "loss": 44.1491,
      "step": 62
    },
    {
      "epoch": 0.06182531894013739,
      "grad_norm": 4.47567081451416,
      "learning_rate": 1.8109066104575023e-06,
      "loss": 44.1562,
      "step": 63
    },
    {
      "epoch": 0.06280667320902845,
      "grad_norm": 4.615531921386719,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 44.1694,
      "step": 64
    },
    {
      "epoch": 0.06378802747791953,
      "grad_norm": 4.739807605743408,
      "learning_rate": 1.6449496416858285e-06,
      "loss": 44.1339,
      "step": 65
    },
    {
      "epoch": 0.0647693817468106,
      "grad_norm": 4.978174686431885,
      "learning_rate": 1.56348351646022e-06,
      "loss": 44.1016,
      "step": 66
    },
    {
      "epoch": 0.06575073601570167,
      "grad_norm": 4.427630424499512,
      "learning_rate": 1.4831583923105e-06,
      "loss": 44.1453,
      "step": 67
    },
    {
      "epoch": 0.06673209028459273,
      "grad_norm": 4.460508823394775,
      "learning_rate": 1.4040721330273063e-06,
      "loss": 44.1541,
      "step": 68
    },
    {
      "epoch": 0.06771344455348381,
      "grad_norm": 4.592861175537109,
      "learning_rate": 1.3263210930352737e-06,
      "loss": 44.1361,
      "step": 69
    },
    {
      "epoch": 0.06869479882237488,
      "grad_norm": 4.343865394592285,
      "learning_rate": 1.2500000000000007e-06,
      "loss": 44.1732,
      "step": 70
    },
    {
      "epoch": 0.06967615309126594,
      "grad_norm": 4.420068264007568,
      "learning_rate": 1.1752018394169882e-06,
      "loss": 44.1383,
      "step": 71
    },
    {
      "epoch": 0.07065750736015702,
      "grad_norm": 4.614556789398193,
      "learning_rate": 1.1020177413231334e-06,
      "loss": 44.142,
      "step": 72
    },
    {
      "epoch": 0.07163886162904809,
      "grad_norm": 4.291627883911133,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 44.1535,
      "step": 73
    },
    {
      "epoch": 0.07262021589793916,
      "grad_norm": 4.367705345153809,
      "learning_rate": 9.608463116858544e-07,
      "loss": 44.1653,
      "step": 74
    },
    {
      "epoch": 0.07360157016683022,
      "grad_norm": 4.751893997192383,
      "learning_rate": 8.930309757836517e-07,
      "loss": 44.1325,
      "step": 75
    },
    {
      "epoch": 0.0745829244357213,
      "grad_norm": 4.403656959533691,
      "learning_rate": 8.271734841028553e-07,
      "loss": 44.1413,
      "step": 76
    },
    {
      "epoch": 0.07556427870461237,
      "grad_norm": 4.389298915863037,
      "learning_rate": 7.633540738525066e-07,
      "loss": 44.1718,
      "step": 77
    },
    {
      "epoch": 0.07654563297350343,
      "grad_norm": 4.401954174041748,
      "learning_rate": 7.016504991533727e-07,
      "loss": 44.1616,
      "step": 78
    },
    {
      "epoch": 0.0775269872423945,
      "grad_norm": 4.580694198608398,
      "learning_rate": 6.421379363065142e-07,
      "loss": 44.1418,
      "step": 79
    },
    {
      "epoch": 0.07850834151128558,
      "grad_norm": 4.462921619415283,
      "learning_rate": 5.848888922025553e-07,
      "loss": 44.1092,
      "step": 80
    },
    {
      "epoch": 0.07948969578017664,
      "grad_norm": 4.829708099365234,
      "learning_rate": 5.299731159831953e-07,
      "loss": 44.1295,
      "step": 81
    },
    {
      "epoch": 0.08047105004906771,
      "grad_norm": 4.394340991973877,
      "learning_rate": 4.774575140626317e-07,
      "loss": 44.1685,
      "step": 82
    },
    {
      "epoch": 0.08145240431795878,
      "grad_norm": 4.454510688781738,
      "learning_rate": 4.27406068612396e-07,
      "loss": 44.1542,
      "step": 83
    },
    {
      "epoch": 0.08243375858684986,
      "grad_norm": 4.497045040130615,
      "learning_rate": 3.798797596089351e-07,
      "loss": 44.1375,
      "step": 84
    },
    {
      "epoch": 0.08341511285574092,
      "grad_norm": 4.434609889984131,
      "learning_rate": 3.3493649053890325e-07,
      "loss": 44.1345,
      "step": 85
    },
    {
      "epoch": 0.08439646712463199,
      "grad_norm": 4.5244035720825195,
      "learning_rate": 2.9263101785268253e-07,
      "loss": 44.1467,
      "step": 86
    },
    {
      "epoch": 0.08537782139352307,
      "grad_norm": 4.269883632659912,
      "learning_rate": 2.53014884252083e-07,
      "loss": 44.1526,
      "step": 87
    },
    {
      "epoch": 0.08635917566241413,
      "grad_norm": 4.184451103210449,
      "learning_rate": 2.1613635589349756e-07,
      "loss": 44.1822,
      "step": 88
    },
    {
      "epoch": 0.0873405299313052,
      "grad_norm": 4.249412536621094,
      "learning_rate": 1.8204036358303173e-07,
      "loss": 44.1716,
      "step": 89
    },
    {
      "epoch": 0.08832188420019627,
      "grad_norm": 3.827402114868164,
      "learning_rate": 1.507684480352292e-07,
      "loss": 44.1924,
      "step": 90
    },
    {
      "epoch": 0.08930323846908735,
      "grad_norm": 4.114834785461426,
      "learning_rate": 1.223587092621162e-07,
      "loss": 44.2127,
      "step": 91
    },
    {
      "epoch": 0.09028459273797841,
      "grad_norm": 3.819640636444092,
      "learning_rate": 9.684576015420277e-08,
      "loss": 44.2051,
      "step": 92
    },
    {
      "epoch": 0.09126594700686948,
      "grad_norm": 4.212294578552246,
      "learning_rate": 7.426068431000883e-08,
      "loss": 44.1976,
      "step": 93
    },
    {
      "epoch": 0.09224730127576054,
      "grad_norm": 3.624086618423462,
      "learning_rate": 5.463099816548578e-08,
      "loss": 44.2229,
      "step": 94
    },
    {
      "epoch": 0.09322865554465162,
      "grad_norm": 3.4577605724334717,
      "learning_rate": 3.798061746947995e-08,
      "loss": 44.2466,
      "step": 95
    },
    {
      "epoch": 0.09421000981354269,
      "grad_norm": 3.643979072570801,
      "learning_rate": 2.4329828146074096e-08,
      "loss": 44.3109,
      "step": 96
    },
    {
      "epoch": 0.09519136408243375,
      "grad_norm": 4.863288879394531,
      "learning_rate": 1.3695261579316776e-08,
      "loss": 44.1834,
      "step": 97
    },
    {
      "epoch": 0.09617271835132483,
      "grad_norm": 3.8488268852233887,
      "learning_rate": 6.089874350439507e-09,
      "loss": 44.2992,
      "step": 98
    },
    {
      "epoch": 0.0971540726202159,
      "grad_norm": 4.9372148513793945,
      "learning_rate": 1.5229324522605949e-09,
      "loss": 44.3093,
      "step": 99
    },
    {
      "epoch": 0.09813542688910697,
      "grad_norm": 5.151540756225586,
      "learning_rate": 0.0,
      "loss": 44.4666,
      "step": 100
    },
    {
      "epoch": 0.09813542688910697,
      "eval_loss": 11.038614273071289,
      "eval_runtime": 5.0993,
      "eval_samples_per_second": 336.516,
      "eval_steps_per_second": 42.163,
      "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": 15407373090816.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}