{
  "best_metric": 2.543463706970215,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.01797187401716314,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017971874017163139,
      "grad_norm": 2.2578516006469727,
      "learning_rate": 1e-05,
      "loss": 4.1401,
      "step": 1
    },
    {
      "epoch": 0.00017971874017163139,
      "eval_loss": 4.801219940185547,
      "eval_runtime": 367.8891,
      "eval_samples_per_second": 25.475,
      "eval_steps_per_second": 6.369,
      "step": 1
    },
    {
      "epoch": 0.00035943748034326277,
      "grad_norm": 2.5639493465423584,
      "learning_rate": 2e-05,
      "loss": 4.1657,
      "step": 2
    },
    {
      "epoch": 0.0005391562205148942,
      "grad_norm": 2.663560628890991,
      "learning_rate": 3e-05,
      "loss": 4.4236,
      "step": 3
    },
    {
      "epoch": 0.0007188749606865255,
      "grad_norm": 2.5879647731781006,
      "learning_rate": 4e-05,
      "loss": 4.2015,
      "step": 4
    },
    {
      "epoch": 0.0008985937008581569,
      "grad_norm": 2.953747510910034,
      "learning_rate": 5e-05,
      "loss": 4.553,
      "step": 5
    },
    {
      "epoch": 0.0010783124410297883,
      "grad_norm": 2.942636489868164,
      "learning_rate": 6e-05,
      "loss": 4.6065,
      "step": 6
    },
    {
      "epoch": 0.0012580311812014197,
      "grad_norm": 2.7334063053131104,
      "learning_rate": 7e-05,
      "loss": 4.4443,
      "step": 7
    },
    {
      "epoch": 0.001437749921373051,
      "grad_norm": 2.822499990463257,
      "learning_rate": 8e-05,
      "loss": 4.668,
      "step": 8
    },
    {
      "epoch": 0.0016174686615446825,
      "grad_norm": 2.929219961166382,
      "learning_rate": 9e-05,
      "loss": 4.6229,
      "step": 9
    },
    {
      "epoch": 0.0017971874017163139,
      "grad_norm": 2.8781981468200684,
      "learning_rate": 0.0001,
      "loss": 4.6078,
      "step": 10
    },
    {
      "epoch": 0.0019769061418879455,
      "grad_norm": 3.6415092945098877,
      "learning_rate": 9.99695413509548e-05,
      "loss": 4.3571,
      "step": 11
    },
    {
      "epoch": 0.0021566248820595766,
      "grad_norm": 2.46899151802063,
      "learning_rate": 9.987820251299122e-05,
      "loss": 4.3218,
      "step": 12
    },
    {
      "epoch": 0.0023363436222312082,
      "grad_norm": 2.7327287197113037,
      "learning_rate": 9.972609476841367e-05,
      "loss": 4.6434,
      "step": 13
    },
    {
      "epoch": 0.0025160623624028394,
      "grad_norm": 3.258862257003784,
      "learning_rate": 9.951340343707852e-05,
      "loss": 4.4217,
      "step": 14
    },
    {
      "epoch": 0.002695781102574471,
      "grad_norm": 3.4570999145507812,
      "learning_rate": 9.924038765061042e-05,
      "loss": 4.7055,
      "step": 15
    },
    {
      "epoch": 0.002875499842746102,
      "grad_norm": 3.934077262878418,
      "learning_rate": 9.890738003669029e-05,
      "loss": 4.8773,
      "step": 16
    },
    {
      "epoch": 0.003055218582917734,
      "grad_norm": 4.6774163246154785,
      "learning_rate": 9.851478631379982e-05,
      "loss": 5.6978,
      "step": 17
    },
    {
      "epoch": 0.003234937323089365,
      "grad_norm": 5.593666076660156,
      "learning_rate": 9.806308479691595e-05,
      "loss": 4.3083,
      "step": 18
    },
    {
      "epoch": 0.0034146560632609966,
      "grad_norm": 6.528815746307373,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.6124,
      "step": 19
    },
    {
      "epoch": 0.0035943748034326277,
      "grad_norm": 5.437340259552002,
      "learning_rate": 9.698463103929542e-05,
      "loss": 3.3371,
      "step": 20
    },
    {
      "epoch": 0.0037740935436042593,
      "grad_norm": 3.9103472232818604,
      "learning_rate": 9.635919272833938e-05,
      "loss": 3.4655,
      "step": 21
    },
    {
      "epoch": 0.003953812283775891,
      "grad_norm": 3.729229211807251,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.9374,
      "step": 22
    },
    {
      "epoch": 0.004133531023947522,
      "grad_norm": 3.5457568168640137,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.954,
      "step": 23
    },
    {
      "epoch": 0.004313249764119153,
      "grad_norm": 3.179713487625122,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.623,
      "step": 24
    },
    {
      "epoch": 0.004492968504290785,
      "grad_norm": 2.981762409210205,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.6878,
      "step": 25
    },
    {
      "epoch": 0.0046726872444624165,
      "grad_norm": 2.9266059398651123,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.7867,
      "step": 26
    },
    {
      "epoch": 0.004852405984634048,
      "grad_norm": 2.7733054161071777,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.6444,
      "step": 27
    },
    {
      "epoch": 0.005032124724805679,
      "grad_norm": 3.0727224349975586,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.6041,
      "step": 28
    },
    {
      "epoch": 0.005211843464977311,
      "grad_norm": 2.8358943462371826,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.3593,
      "step": 29
    },
    {
      "epoch": 0.005391562205148942,
      "grad_norm": 2.822882890701294,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.3585,
      "step": 30
    },
    {
      "epoch": 0.005571280945320573,
      "grad_norm": 3.0162363052368164,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.7616,
      "step": 31
    },
    {
      "epoch": 0.005750999685492204,
      "grad_norm": 2.5073037147521973,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.2075,
      "step": 32
    },
    {
      "epoch": 0.005930718425663836,
      "grad_norm": 2.8125205039978027,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.7952,
      "step": 33
    },
    {
      "epoch": 0.006110437165835468,
      "grad_norm": 2.533489227294922,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.4959,
      "step": 34
    },
    {
      "epoch": 0.006290155906007099,
      "grad_norm": 2.484999179840088,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.3936,
      "step": 35
    },
    {
      "epoch": 0.00646987464617873,
      "grad_norm": 2.747763156890869,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.757,
      "step": 36
    },
    {
      "epoch": 0.006649593386350362,
      "grad_norm": 2.4683239459991455,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.2322,
      "step": 37
    },
    {
      "epoch": 0.006829312126521993,
      "grad_norm": 2.535304546356201,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.2977,
      "step": 38
    },
    {
      "epoch": 0.007009030866693624,
      "grad_norm": 2.9011669158935547,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.6045,
      "step": 39
    },
    {
      "epoch": 0.0071887496068652555,
      "grad_norm": 2.4643850326538086,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.3071,
      "step": 40
    },
    {
      "epoch": 0.0073684683470368875,
      "grad_norm": 2.931058645248413,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.8353,
      "step": 41
    },
    {
      "epoch": 0.007548187087208519,
      "grad_norm": 2.6232857704162598,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.4672,
      "step": 42
    },
    {
      "epoch": 0.00772790582738015,
      "grad_norm": 2.5271997451782227,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.4418,
      "step": 43
    },
    {
      "epoch": 0.007907624567551782,
      "grad_norm": 2.7675743103027344,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.3251,
      "step": 44
    },
    {
      "epoch": 0.008087343307723413,
      "grad_norm": 2.661940813064575,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.2531,
      "step": 45
    },
    {
      "epoch": 0.008267062047895044,
      "grad_norm": 2.481865406036377,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.9369,
      "step": 46
    },
    {
      "epoch": 0.008446780788066675,
      "grad_norm": 2.444103956222534,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.0198,
      "step": 47
    },
    {
      "epoch": 0.008626499528238307,
      "grad_norm": 3.11004376411438,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.026,
      "step": 48
    },
    {
      "epoch": 0.008806218268409938,
      "grad_norm": 2.6639597415924072,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.2112,
      "step": 49
    },
    {
      "epoch": 0.00898593700858157,
      "grad_norm": 2.8253867626190186,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.3106,
      "step": 50
    },
    {
      "epoch": 0.00898593700858157,
      "eval_loss": 2.702011823654175,
      "eval_runtime": 369.1223,
      "eval_samples_per_second": 25.39,
      "eval_steps_per_second": 6.347,
      "step": 50
    },
    {
      "epoch": 0.009165655748753202,
      "grad_norm": 4.447997570037842,
      "learning_rate": 5.695865504800327e-05,
      "loss": 3.1439,
      "step": 51
    },
    {
      "epoch": 0.009345374488924833,
      "grad_norm": 4.879358291625977,
      "learning_rate": 5.522642316338268e-05,
      "loss": 3.0015,
      "step": 52
    },
    {
      "epoch": 0.009525093229096464,
      "grad_norm": 3.736008882522583,
      "learning_rate": 5.348782368720626e-05,
      "loss": 2.9797,
      "step": 53
    },
    {
      "epoch": 0.009704811969268095,
      "grad_norm": 3.3615059852600098,
      "learning_rate": 5.174497483512506e-05,
      "loss": 3.3752,
      "step": 54
    },
    {
      "epoch": 0.009884530709439726,
      "grad_norm": 2.5511536598205566,
      "learning_rate": 5e-05,
      "loss": 2.8825,
      "step": 55
    },
    {
      "epoch": 0.010064249449611358,
      "grad_norm": 2.8620405197143555,
      "learning_rate": 4.825502516487497e-05,
      "loss": 2.9289,
      "step": 56
    },
    {
      "epoch": 0.010243968189782989,
      "grad_norm": 2.905618190765381,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 3.1637,
      "step": 57
    },
    {
      "epoch": 0.010423686929954622,
      "grad_norm": 3.0646848678588867,
      "learning_rate": 4.477357683661734e-05,
      "loss": 3.0125,
      "step": 58
    },
    {
      "epoch": 0.010603405670126253,
      "grad_norm": 3.3001129627227783,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 3.1014,
      "step": 59
    },
    {
      "epoch": 0.010783124410297884,
      "grad_norm": 3.306954860687256,
      "learning_rate": 4.131759111665349e-05,
      "loss": 3.4818,
      "step": 60
    },
    {
      "epoch": 0.010962843150469515,
      "grad_norm": 3.376537561416626,
      "learning_rate": 3.960441545911204e-05,
      "loss": 3.5095,
      "step": 61
    },
    {
      "epoch": 0.011142561890641146,
      "grad_norm": 3.216480016708374,
      "learning_rate": 3.790390522001662e-05,
      "loss": 3.4539,
      "step": 62
    },
    {
      "epoch": 0.011322280630812778,
      "grad_norm": 3.4549150466918945,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 3.3442,
      "step": 63
    },
    {
      "epoch": 0.011501999370984409,
      "grad_norm": 3.040135145187378,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 3.3466,
      "step": 64
    },
    {
      "epoch": 0.011681718111156042,
      "grad_norm": 3.064269542694092,
      "learning_rate": 3.289899283371657e-05,
      "loss": 3.2623,
      "step": 65
    },
    {
      "epoch": 0.011861436851327673,
      "grad_norm": 3.851158618927002,
      "learning_rate": 3.12696703292044e-05,
      "loss": 3.8449,
      "step": 66
    },
    {
      "epoch": 0.012041155591499304,
      "grad_norm": 3.46075177192688,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 3.4347,
      "step": 67
    },
    {
      "epoch": 0.012220874331670935,
      "grad_norm": 3.6675915718078613,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 4.0072,
      "step": 68
    },
    {
      "epoch": 0.012400593071842566,
      "grad_norm": 3.480902671813965,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 2.4953,
      "step": 69
    },
    {
      "epoch": 0.012580311812014197,
      "grad_norm": 4.579424858093262,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.6752,
      "step": 70
    },
    {
      "epoch": 0.012760030552185829,
      "grad_norm": 3.595804214477539,
      "learning_rate": 2.350403678833976e-05,
      "loss": 2.4067,
      "step": 71
    },
    {
      "epoch": 0.01293974929235746,
      "grad_norm": 3.2332661151885986,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 2.1416,
      "step": 72
    },
    {
      "epoch": 0.013119468032529093,
      "grad_norm": 3.2234134674072266,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.7848,
      "step": 73
    },
    {
      "epoch": 0.013299186772700724,
      "grad_norm": 3.04959774017334,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 2.432,
      "step": 74
    },
    {
      "epoch": 0.013478905512872355,
      "grad_norm": 2.643514633178711,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 2.0934,
      "step": 75
    },
    {
      "epoch": 0.013658624253043986,
      "grad_norm": 3.055098056793213,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 2.3272,
      "step": 76
    },
    {
      "epoch": 0.013838342993215617,
      "grad_norm": 2.4809956550598145,
      "learning_rate": 1.526708147705013e-05,
      "loss": 2.2483,
      "step": 77
    },
    {
      "epoch": 0.014018061733387249,
      "grad_norm": 2.64147686958313,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 2.3055,
      "step": 78
    },
    {
      "epoch": 0.01419778047355888,
      "grad_norm": 2.2932167053222656,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 2.0433,
      "step": 79
    },
    {
      "epoch": 0.014377499213730511,
      "grad_norm": 2.3609931468963623,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 2.3359,
      "step": 80
    },
    {
      "epoch": 0.014557217953902144,
      "grad_norm": 2.249638080596924,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 2.1387,
      "step": 81
    },
    {
      "epoch": 0.014736936694073775,
      "grad_norm": 2.8411879539489746,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.463,
      "step": 82
    },
    {
      "epoch": 0.014916655434245406,
      "grad_norm": 2.662808418273926,
      "learning_rate": 8.548121372247918e-06,
      "loss": 2.5389,
      "step": 83
    },
    {
      "epoch": 0.015096374174417037,
      "grad_norm": 2.8071436882019043,
      "learning_rate": 7.597595192178702e-06,
      "loss": 2.1706,
      "step": 84
    },
    {
      "epoch": 0.015276092914588668,
      "grad_norm": 2.656956911087036,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.3759,
      "step": 85
    },
    {
      "epoch": 0.0154558116547603,
      "grad_norm": 3.031149387359619,
      "learning_rate": 5.852620357053651e-06,
      "loss": 2.2298,
      "step": 86
    },
    {
      "epoch": 0.015635530394931933,
      "grad_norm": 2.755890369415283,
      "learning_rate": 5.060297685041659e-06,
      "loss": 2.4255,
      "step": 87
    },
    {
      "epoch": 0.015815249135103564,
      "grad_norm": 2.5731019973754883,
      "learning_rate": 4.322727117869951e-06,
      "loss": 2.2818,
      "step": 88
    },
    {
      "epoch": 0.015994967875275195,
      "grad_norm": 2.7685189247131348,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 2.3691,
      "step": 89
    },
    {
      "epoch": 0.016174686615446826,
      "grad_norm": 2.6368041038513184,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.4944,
      "step": 90
    },
    {
      "epoch": 0.016354405355618457,
      "grad_norm": 2.858224630355835,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.2883,
      "step": 91
    },
    {
      "epoch": 0.01653412409579009,
      "grad_norm": 2.793339252471924,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 2.4953,
      "step": 92
    },
    {
      "epoch": 0.01671384283596172,
      "grad_norm": 2.8187801837921143,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 2.2414,
      "step": 93
    },
    {
      "epoch": 0.01689356157613335,
      "grad_norm": 2.9361603260040283,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.4021,
      "step": 94
    },
    {
      "epoch": 0.017073280316304982,
      "grad_norm": 2.7744662761688232,
      "learning_rate": 7.596123493895991e-07,
      "loss": 2.1991,
      "step": 95
    },
    {
      "epoch": 0.017252999056476613,
      "grad_norm": 2.6500556468963623,
      "learning_rate": 4.865965629214819e-07,
      "loss": 2.2625,
      "step": 96
    },
    {
      "epoch": 0.017432717796648244,
      "grad_norm": 2.4501571655273438,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 2.1335,
      "step": 97
    },
    {
      "epoch": 0.017612436536819875,
      "grad_norm": 2.76723575592041,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.0047,
      "step": 98
    },
    {
      "epoch": 0.017792155276991507,
      "grad_norm": 2.838305711746216,
      "learning_rate": 3.04586490452119e-08,
      "loss": 2.3863,
      "step": 99
    },
    {
      "epoch": 0.01797187401716314,
      "grad_norm": 3.0587007999420166,
      "learning_rate": 0.0,
      "loss": 2.2002,
      "step": 100
    },
    {
      "epoch": 0.01797187401716314,
      "eval_loss": 2.543463706970215,
      "eval_runtime": 368.7,
      "eval_samples_per_second": 25.419,
      "eval_steps_per_second": 6.355,
      "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": 3.609045705424896e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}