{
  "best_metric": 11.932085037231445,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.16214025131738954,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016214025131738954,
      "grad_norm": 0.06148737668991089,
      "learning_rate": 5.000000000000001e-07,
      "loss": 11.937,
      "step": 1
    },
    {
      "epoch": 0.0016214025131738954,
      "eval_loss": 11.932759284973145,
      "eval_runtime": 5.5329,
      "eval_samples_per_second": 187.787,
      "eval_steps_per_second": 23.496,
      "step": 1
    },
    {
      "epoch": 0.0032428050263477908,
      "grad_norm": 0.04782642051577568,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 11.9386,
      "step": 2
    },
    {
      "epoch": 0.004864207539521687,
      "grad_norm": 0.06458375602960587,
      "learning_rate": 1.5e-06,
      "loss": 11.9403,
      "step": 3
    },
    {
      "epoch": 0.0064856100526955816,
      "grad_norm": 0.0695745050907135,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 11.9382,
      "step": 4
    },
    {
      "epoch": 0.008107012565869477,
      "grad_norm": 0.07331092655658722,
      "learning_rate": 2.5e-06,
      "loss": 11.9409,
      "step": 5
    },
    {
      "epoch": 0.009728415079043373,
      "grad_norm": 0.06527193635702133,
      "learning_rate": 3e-06,
      "loss": 11.9391,
      "step": 6
    },
    {
      "epoch": 0.011349817592217268,
      "grad_norm": 0.06476838886737823,
      "learning_rate": 3.5e-06,
      "loss": 11.9388,
      "step": 7
    },
    {
      "epoch": 0.012971220105391163,
      "grad_norm": 0.08535204827785492,
      "learning_rate": 4.000000000000001e-06,
      "loss": 11.9395,
      "step": 8
    },
    {
      "epoch": 0.014592622618565058,
      "grad_norm": 0.08116604387760162,
      "learning_rate": 4.5e-06,
      "loss": 11.9395,
      "step": 9
    },
    {
      "epoch": 0.016214025131738953,
      "grad_norm": 0.07606469094753265,
      "learning_rate": 5e-06,
      "loss": 11.9402,
      "step": 10
    },
    {
      "epoch": 0.01783542764491285,
      "grad_norm": 0.06500118225812912,
      "learning_rate": 4.99847706754774e-06,
      "loss": 11.9375,
      "step": 11
    },
    {
      "epoch": 0.019456830158086746,
      "grad_norm": 0.04997660592198372,
      "learning_rate": 4.993910125649561e-06,
      "loss": 11.9373,
      "step": 12
    },
    {
      "epoch": 0.02107823267126064,
      "grad_norm": 0.0678182914853096,
      "learning_rate": 4.986304738420684e-06,
      "loss": 11.9364,
      "step": 13
    },
    {
      "epoch": 0.022699635184434536,
      "grad_norm": 0.0676642581820488,
      "learning_rate": 4.975670171853926e-06,
      "loss": 11.9381,
      "step": 14
    },
    {
      "epoch": 0.02432103769760843,
      "grad_norm": 0.07154196500778198,
      "learning_rate": 4.962019382530521e-06,
      "loss": 11.9372,
      "step": 15
    },
    {
      "epoch": 0.025942440210782326,
      "grad_norm": 0.05947857350111008,
      "learning_rate": 4.9453690018345144e-06,
      "loss": 11.9374,
      "step": 16
    },
    {
      "epoch": 0.027563842723956223,
      "grad_norm": 0.0858941599726677,
      "learning_rate": 4.925739315689991e-06,
      "loss": 11.9382,
      "step": 17
    },
    {
      "epoch": 0.029185245237130116,
      "grad_norm": 0.08636289834976196,
      "learning_rate": 4.903154239845798e-06,
      "loss": 11.9327,
      "step": 18
    },
    {
      "epoch": 0.030806647750304013,
      "grad_norm": 0.09262266755104065,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 11.9362,
      "step": 19
    },
    {
      "epoch": 0.032428050263477906,
      "grad_norm": 0.07391153275966644,
      "learning_rate": 4.849231551964771e-06,
      "loss": 11.9341,
      "step": 20
    },
    {
      "epoch": 0.034049452776651806,
      "grad_norm": 0.0751374289393425,
      "learning_rate": 4.817959636416969e-06,
      "loss": 11.9347,
      "step": 21
    },
    {
      "epoch": 0.0356708552898257,
      "grad_norm": 0.0785205066204071,
      "learning_rate": 4.783863644106502e-06,
      "loss": 11.9299,
      "step": 22
    },
    {
      "epoch": 0.03729225780299959,
      "grad_norm": 0.05841010808944702,
      "learning_rate": 4.746985115747918e-06,
      "loss": 11.9302,
      "step": 23
    },
    {
      "epoch": 0.03891366031617349,
      "grad_norm": 0.062468521296978,
      "learning_rate": 4.707368982147318e-06,
      "loss": 11.9343,
      "step": 24
    },
    {
      "epoch": 0.040535062829347386,
      "grad_norm": 0.06350651383399963,
      "learning_rate": 4.665063509461098e-06,
      "loss": 11.9273,
      "step": 25
    },
    {
      "epoch": 0.04215646534252128,
      "grad_norm": 0.07266425341367722,
      "learning_rate": 4.620120240391065e-06,
      "loss": 11.9273,
      "step": 26
    },
    {
      "epoch": 0.04377786785569518,
      "grad_norm": 0.07261718064546585,
      "learning_rate": 4.572593931387604e-06,
      "loss": 11.9324,
      "step": 27
    },
    {
      "epoch": 0.04539927036886907,
      "grad_norm": 0.08380614221096039,
      "learning_rate": 4.522542485937369e-06,
      "loss": 11.9287,
      "step": 28
    },
    {
      "epoch": 0.047020672882042966,
      "grad_norm": 0.08229350298643112,
      "learning_rate": 4.470026884016805e-06,
      "loss": 11.9283,
      "step": 29
    },
    {
      "epoch": 0.04864207539521686,
      "grad_norm": 0.07520421594381332,
      "learning_rate": 4.415111107797445e-06,
      "loss": 11.9224,
      "step": 30
    },
    {
      "epoch": 0.05026347790839076,
      "grad_norm": 0.11293678730726242,
      "learning_rate": 4.357862063693486e-06,
      "loss": 11.9268,
      "step": 31
    },
    {
      "epoch": 0.05188488042156465,
      "grad_norm": 0.09202712029218674,
      "learning_rate": 4.2983495008466285e-06,
      "loss": 11.9304,
      "step": 32
    },
    {
      "epoch": 0.053506282934738546,
      "grad_norm": 0.09367135912179947,
      "learning_rate": 4.236645926147493e-06,
      "loss": 11.923,
      "step": 33
    },
    {
      "epoch": 0.055127685447912446,
      "grad_norm": 0.08824901282787323,
      "learning_rate": 4.172826515897146e-06,
      "loss": 11.9329,
      "step": 34
    },
    {
      "epoch": 0.05674908796108634,
      "grad_norm": 0.08749401569366455,
      "learning_rate": 4.106969024216348e-06,
      "loss": 11.9262,
      "step": 35
    },
    {
      "epoch": 0.05837049047426023,
      "grad_norm": 0.08584518730640411,
      "learning_rate": 4.039153688314146e-06,
      "loss": 11.9275,
      "step": 36
    },
    {
      "epoch": 0.05999189298743413,
      "grad_norm": 0.08267547190189362,
      "learning_rate": 3.969463130731183e-06,
      "loss": 11.9278,
      "step": 37
    },
    {
      "epoch": 0.061613295500608026,
      "grad_norm": 0.08701630681753159,
      "learning_rate": 3.897982258676867e-06,
      "loss": 11.9249,
      "step": 38
    },
    {
      "epoch": 0.06323469801378193,
      "grad_norm": 0.08931490033864975,
      "learning_rate": 3.824798160583012e-06,
      "loss": 11.9325,
      "step": 39
    },
    {
      "epoch": 0.06485610052695581,
      "grad_norm": 0.11539775133132935,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 11.9238,
      "step": 40
    },
    {
      "epoch": 0.06647750304012971,
      "grad_norm": 0.10175476223230362,
      "learning_rate": 3.6736789069647273e-06,
      "loss": 11.9282,
      "step": 41
    },
    {
      "epoch": 0.06809890555330361,
      "grad_norm": 0.11972854286432266,
      "learning_rate": 3.595927866972694e-06,
      "loss": 11.9298,
      "step": 42
    },
    {
      "epoch": 0.0697203080664775,
      "grad_norm": 0.11182477325201035,
      "learning_rate": 3.516841607689501e-06,
      "loss": 11.934,
      "step": 43
    },
    {
      "epoch": 0.0713417105796514,
      "grad_norm": 0.09574752300977707,
      "learning_rate": 3.436516483539781e-06,
      "loss": 11.9356,
      "step": 44
    },
    {
      "epoch": 0.0729631130928253,
      "grad_norm": 0.13956184685230255,
      "learning_rate": 3.3550503583141726e-06,
      "loss": 11.9262,
      "step": 45
    },
    {
      "epoch": 0.07458451560599919,
      "grad_norm": 0.1027691513299942,
      "learning_rate": 3.272542485937369e-06,
      "loss": 11.9351,
      "step": 46
    },
    {
      "epoch": 0.07620591811917309,
      "grad_norm": 0.13854406774044037,
      "learning_rate": 3.189093389542498e-06,
      "loss": 11.9253,
      "step": 47
    },
    {
      "epoch": 0.07782732063234699,
      "grad_norm": 0.12041836977005005,
      "learning_rate": 3.1048047389991693e-06,
      "loss": 11.9411,
      "step": 48
    },
    {
      "epoch": 0.07944872314552087,
      "grad_norm": 0.11676981300115585,
      "learning_rate": 3.019779227044398e-06,
      "loss": 11.939,
      "step": 49
    },
    {
      "epoch": 0.08107012565869477,
      "grad_norm": 0.13951873779296875,
      "learning_rate": 2.9341204441673267e-06,
      "loss": 11.9339,
      "step": 50
    },
    {
      "epoch": 0.08107012565869477,
      "eval_loss": 11.932246208190918,
      "eval_runtime": 5.5126,
      "eval_samples_per_second": 188.476,
      "eval_steps_per_second": 23.582,
      "step": 50
    },
    {
      "epoch": 0.08269152817186867,
      "grad_norm": 0.06557369232177734,
      "learning_rate": 2.847932752400164e-06,
      "loss": 11.9359,
      "step": 51
    },
    {
      "epoch": 0.08431293068504256,
      "grad_norm": 0.054183050990104675,
      "learning_rate": 2.761321158169134e-06,
      "loss": 11.9378,
      "step": 52
    },
    {
      "epoch": 0.08593433319821646,
      "grad_norm": 0.06125367805361748,
      "learning_rate": 2.6743911843603134e-06,
      "loss": 11.9401,
      "step": 53
    },
    {
      "epoch": 0.08755573571139036,
      "grad_norm": 0.07734334468841553,
      "learning_rate": 2.587248741756253e-06,
      "loss": 11.9367,
      "step": 54
    },
    {
      "epoch": 0.08917713822456425,
      "grad_norm": 0.07164815068244934,
      "learning_rate": 2.5e-06,
      "loss": 11.9412,
      "step": 55
    },
    {
      "epoch": 0.09079854073773815,
      "grad_norm": 0.07205943763256073,
      "learning_rate": 2.4127512582437486e-06,
      "loss": 11.9377,
      "step": 56
    },
    {
      "epoch": 0.09241994325091205,
      "grad_norm": 0.06834626942873001,
      "learning_rate": 2.325608815639687e-06,
      "loss": 11.9395,
      "step": 57
    },
    {
      "epoch": 0.09404134576408593,
      "grad_norm": 0.07087212055921555,
      "learning_rate": 2.238678841830867e-06,
      "loss": 11.9404,
      "step": 58
    },
    {
      "epoch": 0.09566274827725983,
      "grad_norm": 0.06267399340867996,
      "learning_rate": 2.1520672475998374e-06,
      "loss": 11.9416,
      "step": 59
    },
    {
      "epoch": 0.09728415079043372,
      "grad_norm": 0.05978712439537048,
      "learning_rate": 2.0658795558326745e-06,
      "loss": 11.9396,
      "step": 60
    },
    {
      "epoch": 0.09890555330360762,
      "grad_norm": 0.06278885900974274,
      "learning_rate": 1.9802207729556023e-06,
      "loss": 11.938,
      "step": 61
    },
    {
      "epoch": 0.10052695581678152,
      "grad_norm": 0.06936422735452652,
      "learning_rate": 1.895195261000831e-06,
      "loss": 11.9391,
      "step": 62
    },
    {
      "epoch": 0.1021483583299554,
      "grad_norm": 0.06972584128379822,
      "learning_rate": 1.8109066104575023e-06,
      "loss": 11.9379,
      "step": 63
    },
    {
      "epoch": 0.1037697608431293,
      "grad_norm": 0.06474191695451736,
      "learning_rate": 1.7274575140626318e-06,
      "loss": 11.9415,
      "step": 64
    },
    {
      "epoch": 0.1053911633563032,
      "grad_norm": 0.0643126517534256,
      "learning_rate": 1.6449496416858285e-06,
      "loss": 11.9368,
      "step": 65
    },
    {
      "epoch": 0.10701256586947709,
      "grad_norm": 0.060131411999464035,
      "learning_rate": 1.56348351646022e-06,
      "loss": 11.9366,
      "step": 66
    },
    {
      "epoch": 0.10863396838265099,
      "grad_norm": 0.07099177688360214,
      "learning_rate": 1.4831583923105e-06,
      "loss": 11.9369,
      "step": 67
    },
    {
      "epoch": 0.11025537089582489,
      "grad_norm": 0.0853051170706749,
      "learning_rate": 1.4040721330273063e-06,
      "loss": 11.9387,
      "step": 68
    },
    {
      "epoch": 0.11187677340899878,
      "grad_norm": 0.07782307267189026,
      "learning_rate": 1.3263210930352737e-06,
      "loss": 11.9346,
      "step": 69
    },
    {
      "epoch": 0.11349817592217268,
      "grad_norm": 0.07038868218660355,
      "learning_rate": 1.2500000000000007e-06,
      "loss": 11.9369,
      "step": 70
    },
    {
      "epoch": 0.11511957843534658,
      "grad_norm": 0.06611315160989761,
      "learning_rate": 1.1752018394169882e-06,
      "loss": 11.9369,
      "step": 71
    },
    {
      "epoch": 0.11674098094852046,
      "grad_norm": 0.06813161075115204,
      "learning_rate": 1.1020177413231334e-06,
      "loss": 11.9355,
      "step": 72
    },
    {
      "epoch": 0.11836238346169436,
      "grad_norm": 0.07219278067350388,
      "learning_rate": 1.0305368692688175e-06,
      "loss": 11.9318,
      "step": 73
    },
    {
      "epoch": 0.11998378597486827,
      "grad_norm": 0.07824105024337769,
      "learning_rate": 9.608463116858544e-07,
      "loss": 11.9312,
      "step": 74
    },
    {
      "epoch": 0.12160518848804215,
      "grad_norm": 0.08129618316888809,
      "learning_rate": 8.930309757836517e-07,
      "loss": 11.9319,
      "step": 75
    },
    {
      "epoch": 0.12322659100121605,
      "grad_norm": 0.06890939921140671,
      "learning_rate": 8.271734841028553e-07,
      "loss": 11.9365,
      "step": 76
    },
    {
      "epoch": 0.12484799351438995,
      "grad_norm": 0.08247758448123932,
      "learning_rate": 7.633540738525066e-07,
      "loss": 11.9334,
      "step": 77
    },
    {
      "epoch": 0.12646939602756385,
      "grad_norm": 0.09313575178384781,
      "learning_rate": 7.016504991533727e-07,
      "loss": 11.9232,
      "step": 78
    },
    {
      "epoch": 0.12809079854073774,
      "grad_norm": 0.05831461772322655,
      "learning_rate": 6.421379363065142e-07,
      "loss": 11.9322,
      "step": 79
    },
    {
      "epoch": 0.12971220105391162,
      "grad_norm": 0.06037887558341026,
      "learning_rate": 5.848888922025553e-07,
      "loss": 11.9308,
      "step": 80
    },
    {
      "epoch": 0.13133360356708554,
      "grad_norm": 0.07506049424409866,
      "learning_rate": 5.299731159831953e-07,
      "loss": 11.9268,
      "step": 81
    },
    {
      "epoch": 0.13295500608025942,
      "grad_norm": 0.0684242770075798,
      "learning_rate": 4.774575140626317e-07,
      "loss": 11.9232,
      "step": 82
    },
    {
      "epoch": 0.1345764085934333,
      "grad_norm": 0.07387068122625351,
      "learning_rate": 4.27406068612396e-07,
      "loss": 11.9302,
      "step": 83
    },
    {
      "epoch": 0.13619781110660723,
      "grad_norm": 0.09172695875167847,
      "learning_rate": 3.798797596089351e-07,
      "loss": 11.9247,
      "step": 84
    },
    {
      "epoch": 0.1378192136197811,
      "grad_norm": 0.07359951734542847,
      "learning_rate": 3.3493649053890325e-07,
      "loss": 11.9305,
      "step": 85
    },
    {
      "epoch": 0.139440616132955,
      "grad_norm": 0.09183831512928009,
      "learning_rate": 2.9263101785268253e-07,
      "loss": 11.9322,
      "step": 86
    },
    {
      "epoch": 0.1410620186461289,
      "grad_norm": 0.0872773602604866,
      "learning_rate": 2.53014884252083e-07,
      "loss": 11.9244,
      "step": 87
    },
    {
      "epoch": 0.1426834211593028,
      "grad_norm": 0.10315699130296707,
      "learning_rate": 2.1613635589349756e-07,
      "loss": 11.9244,
      "step": 88
    },
    {
      "epoch": 0.14430482367247668,
      "grad_norm": 0.10300548374652863,
      "learning_rate": 1.8204036358303173e-07,
      "loss": 11.9305,
      "step": 89
    },
    {
      "epoch": 0.1459262261856506,
      "grad_norm": 0.09078492969274521,
      "learning_rate": 1.507684480352292e-07,
      "loss": 11.9307,
      "step": 90
    },
    {
      "epoch": 0.14754762869882448,
      "grad_norm": 0.08630198240280151,
      "learning_rate": 1.223587092621162e-07,
      "loss": 11.9279,
      "step": 91
    },
    {
      "epoch": 0.14916903121199837,
      "grad_norm": 0.11776189506053925,
      "learning_rate": 9.684576015420277e-08,
      "loss": 11.928,
      "step": 92
    },
    {
      "epoch": 0.15079043372517228,
      "grad_norm": 0.11010502278804779,
      "learning_rate": 7.426068431000883e-08,
      "loss": 11.9303,
      "step": 93
    },
    {
      "epoch": 0.15241183623834617,
      "grad_norm": 0.10045027732849121,
      "learning_rate": 5.463099816548578e-08,
      "loss": 11.9332,
      "step": 94
    },
    {
      "epoch": 0.15403323875152006,
      "grad_norm": 0.10060346871614456,
      "learning_rate": 3.798061746947995e-08,
      "loss": 11.9345,
      "step": 95
    },
    {
      "epoch": 0.15565464126469397,
      "grad_norm": 0.092365562915802,
      "learning_rate": 2.4329828146074096e-08,
      "loss": 11.9306,
      "step": 96
    },
    {
      "epoch": 0.15727604377786786,
      "grad_norm": 0.13334056735038757,
      "learning_rate": 1.3695261579316776e-08,
      "loss": 11.9357,
      "step": 97
    },
    {
      "epoch": 0.15889744629104174,
      "grad_norm": 0.1075684055685997,
      "learning_rate": 6.089874350439507e-09,
      "loss": 11.9331,
      "step": 98
    },
    {
      "epoch": 0.16051884880421566,
      "grad_norm": 0.1268085241317749,
      "learning_rate": 1.5229324522605949e-09,
      "loss": 11.936,
      "step": 99
    },
    {
      "epoch": 0.16214025131738954,
      "grad_norm": 0.13361109793186188,
      "learning_rate": 0.0,
      "loss": 11.9422,
      "step": 100
    },
    {
      "epoch": 0.16214025131738954,
      "eval_loss": 11.932085037231445,
      "eval_runtime": 5.5292,
      "eval_samples_per_second": 187.91,
      "eval_steps_per_second": 23.511,
      "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": 484493230080.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}