{
  "best_metric": 0.31678396463394165,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.015429717636167259,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015429717636167257,
      "grad_norm": 12.706844329833984,
      "learning_rate": 1e-05,
      "loss": 4.608,
      "step": 1
    },
    {
      "epoch": 0.00015429717636167257,
      "eval_loss": 3.070103406906128,
      "eval_runtime": 1169.3669,
      "eval_samples_per_second": 9.335,
      "eval_steps_per_second": 2.334,
      "step": 1
    },
    {
      "epoch": 0.00030859435272334514,
      "grad_norm": 16.560190200805664,
      "learning_rate": 2e-05,
      "loss": 5.5859,
      "step": 2
    },
    {
      "epoch": 0.00046289152908501776,
      "grad_norm": 18.01679039001465,
      "learning_rate": 3e-05,
      "loss": 5.4102,
      "step": 3
    },
    {
      "epoch": 0.0006171887054466903,
      "grad_norm": 30.011011123657227,
      "learning_rate": 4e-05,
      "loss": 4.9208,
      "step": 4
    },
    {
      "epoch": 0.0007714858818083629,
      "grad_norm": 29.32415771484375,
      "learning_rate": 5e-05,
      "loss": 3.4069,
      "step": 5
    },
    {
      "epoch": 0.0009257830581700355,
      "grad_norm": 12.230011940002441,
      "learning_rate": 6e-05,
      "loss": 2.0698,
      "step": 6
    },
    {
      "epoch": 0.001080080234531708,
      "grad_norm": 13.992810249328613,
      "learning_rate": 7e-05,
      "loss": 2.0676,
      "step": 7
    },
    {
      "epoch": 0.0012343774108933806,
      "grad_norm": 11.746103286743164,
      "learning_rate": 8e-05,
      "loss": 2.0054,
      "step": 8
    },
    {
      "epoch": 0.0013886745872550533,
      "grad_norm": 5.419554233551025,
      "learning_rate": 9e-05,
      "loss": 1.8979,
      "step": 9
    },
    {
      "epoch": 0.0015429717636167258,
      "grad_norm": 5.806341171264648,
      "learning_rate": 0.0001,
      "loss": 1.9522,
      "step": 10
    },
    {
      "epoch": 0.0016972689399783983,
      "grad_norm": 7.385525226593018,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.589,
      "step": 11
    },
    {
      "epoch": 0.001851566116340071,
      "grad_norm": 5.675939083099365,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.7699,
      "step": 12
    },
    {
      "epoch": 0.0020058632927017436,
      "grad_norm": 4.296426773071289,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.5231,
      "step": 13
    },
    {
      "epoch": 0.002160160469063416,
      "grad_norm": 5.264349460601807,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.8276,
      "step": 14
    },
    {
      "epoch": 0.0023144576454250886,
      "grad_norm": 5.490671634674072,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.5318,
      "step": 15
    },
    {
      "epoch": 0.002468754821786761,
      "grad_norm": 4.8129563331604,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.5897,
      "step": 16
    },
    {
      "epoch": 0.002623051998148434,
      "grad_norm": 3.9995052814483643,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.6067,
      "step": 17
    },
    {
      "epoch": 0.0027773491745101066,
      "grad_norm": 4.961603164672852,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.9396,
      "step": 18
    },
    {
      "epoch": 0.002931646350871779,
      "grad_norm": 3.439866065979004,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.1821,
      "step": 19
    },
    {
      "epoch": 0.0030859435272334516,
      "grad_norm": 4.874931335449219,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.4247,
      "step": 20
    },
    {
      "epoch": 0.003240240703595124,
      "grad_norm": 3.7519924640655518,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.1099,
      "step": 21
    },
    {
      "epoch": 0.0033945378799567967,
      "grad_norm": 4.326531887054443,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.7054,
      "step": 22
    },
    {
      "epoch": 0.003548835056318469,
      "grad_norm": 4.211771011352539,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.281,
      "step": 23
    },
    {
      "epoch": 0.003703132232680142,
      "grad_norm": 4.3438568115234375,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.3471,
      "step": 24
    },
    {
      "epoch": 0.0038574294090418146,
      "grad_norm": 5.163262844085693,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.8818,
      "step": 25
    },
    {
      "epoch": 0.004011726585403487,
      "grad_norm": 7.394972324371338,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.3303,
      "step": 26
    },
    {
      "epoch": 0.00416602376176516,
      "grad_norm": 5.300237655639648,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.4994,
      "step": 27
    },
    {
      "epoch": 0.004320320938126832,
      "grad_norm": 4.644120216369629,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.686,
      "step": 28
    },
    {
      "epoch": 0.004474618114488505,
      "grad_norm": 5.880524158477783,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.9667,
      "step": 29
    },
    {
      "epoch": 0.004628915290850177,
      "grad_norm": 6.006555557250977,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.989,
      "step": 30
    },
    {
      "epoch": 0.00478321246721185,
      "grad_norm": 7.076709270477295,
      "learning_rate": 9.701596950580806e-05,
      "loss": 2.1825,
      "step": 31
    },
    {
      "epoch": 0.004937509643573522,
      "grad_norm": 6.064911842346191,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.9228,
      "step": 32
    },
    {
      "epoch": 0.005091806819935195,
      "grad_norm": 5.507473945617676,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.7599,
      "step": 33
    },
    {
      "epoch": 0.005246103996296868,
      "grad_norm": 5.350005626678467,
      "learning_rate": 9.611448774886924e-05,
      "loss": 2.1441,
      "step": 34
    },
    {
      "epoch": 0.00540040117265854,
      "grad_norm": 5.501663684844971,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.1429,
      "step": 35
    },
    {
      "epoch": 0.005554698349020213,
      "grad_norm": 5.796812534332275,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.9111,
      "step": 36
    },
    {
      "epoch": 0.005708995525381885,
      "grad_norm": 5.344413757324219,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.831,
      "step": 37
    },
    {
      "epoch": 0.005863292701743558,
      "grad_norm": 6.653753280639648,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.6803,
      "step": 38
    },
    {
      "epoch": 0.00601758987810523,
      "grad_norm": 4.20742130279541,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.5394,
      "step": 39
    },
    {
      "epoch": 0.006171887054466903,
      "grad_norm": 5.991011142730713,
      "learning_rate": 9.397368756032445e-05,
      "loss": 2.2672,
      "step": 40
    },
    {
      "epoch": 0.006326184230828576,
      "grad_norm": 4.891965389251709,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.8155,
      "step": 41
    },
    {
      "epoch": 0.006480481407190248,
      "grad_norm": 5.469320774078369,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.9008,
      "step": 42
    },
    {
      "epoch": 0.006634778583551921,
      "grad_norm": 7.096071243286133,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.3585,
      "step": 43
    },
    {
      "epoch": 0.006789075759913593,
      "grad_norm": 4.401372909545898,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.5414,
      "step": 44
    },
    {
      "epoch": 0.006943372936275266,
      "grad_norm": 6.570494174957275,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.7547,
      "step": 45
    },
    {
      "epoch": 0.007097670112636938,
      "grad_norm": 8.498213768005371,
      "learning_rate": 9.140044155740101e-05,
      "loss": 2.1191,
      "step": 46
    },
    {
      "epoch": 0.007251967288998611,
      "grad_norm": 5.842933177947998,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.9723,
      "step": 47
    },
    {
      "epoch": 0.007406264465360284,
      "grad_norm": 7.124216079711914,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.888,
      "step": 48
    },
    {
      "epoch": 0.007560561641721956,
      "grad_norm": 6.71003532409668,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.0109,
      "step": 49
    },
    {
      "epoch": 0.007714858818083629,
      "grad_norm": 6.386676788330078,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.615,
      "step": 50
    },
    {
      "epoch": 0.007714858818083629,
      "eval_loss": 0.3841496706008911,
      "eval_runtime": 1175.337,
      "eval_samples_per_second": 9.288,
      "eval_steps_per_second": 2.322,
      "step": 50
    },
    {
      "epoch": 0.007869155994445301,
      "grad_norm": 4.409550666809082,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.8821,
      "step": 51
    },
    {
      "epoch": 0.008023453170806974,
      "grad_norm": 2.9394142627716064,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.8637,
      "step": 52
    },
    {
      "epoch": 0.008177750347168647,
      "grad_norm": 2.488647937774658,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.9626,
      "step": 53
    },
    {
      "epoch": 0.00833204752353032,
      "grad_norm": 2.494393825531006,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.1078,
      "step": 54
    },
    {
      "epoch": 0.008486344699891991,
      "grad_norm": 2.6956214904785156,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.0952,
      "step": 55
    },
    {
      "epoch": 0.008640641876253664,
      "grad_norm": 3.117201328277588,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.0386,
      "step": 56
    },
    {
      "epoch": 0.008794939052615337,
      "grad_norm": 2.1398863792419434,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.9426,
      "step": 57
    },
    {
      "epoch": 0.00894923622897701,
      "grad_norm": 2.418407678604126,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.0638,
      "step": 58
    },
    {
      "epoch": 0.009103533405338681,
      "grad_norm": 2.813568353652954,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.1541,
      "step": 59
    },
    {
      "epoch": 0.009257830581700354,
      "grad_norm": 2.6573126316070557,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.1934,
      "step": 60
    },
    {
      "epoch": 0.009412127758062027,
      "grad_norm": 2.3146560192108154,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.9672,
      "step": 61
    },
    {
      "epoch": 0.0095664249344237,
      "grad_norm": 2.291538715362549,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.1188,
      "step": 62
    },
    {
      "epoch": 0.009720722110785373,
      "grad_norm": 2.7872464656829834,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.1053,
      "step": 63
    },
    {
      "epoch": 0.009875019287147044,
      "grad_norm": 2.609403610229492,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.9336,
      "step": 64
    },
    {
      "epoch": 0.010029316463508717,
      "grad_norm": 2.5787737369537354,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.0661,
      "step": 65
    },
    {
      "epoch": 0.01018361363987039,
      "grad_norm": 3.6095104217529297,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.3497,
      "step": 66
    },
    {
      "epoch": 0.010337910816232063,
      "grad_norm": 3.677929401397705,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.4522,
      "step": 67
    },
    {
      "epoch": 0.010492207992593736,
      "grad_norm": 2.962984561920166,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.2089,
      "step": 68
    },
    {
      "epoch": 0.010646505168955408,
      "grad_norm": 3.143599510192871,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.097,
      "step": 69
    },
    {
      "epoch": 0.01080080234531708,
      "grad_norm": 3.195793867111206,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.1503,
      "step": 70
    },
    {
      "epoch": 0.010955099521678753,
      "grad_norm": 2.6642329692840576,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.0405,
      "step": 71
    },
    {
      "epoch": 0.011109396698040426,
      "grad_norm": 4.560359954833984,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.5807,
      "step": 72
    },
    {
      "epoch": 0.0112636938744021,
      "grad_norm": 3.13012957572937,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.1245,
      "step": 73
    },
    {
      "epoch": 0.01141799105076377,
      "grad_norm": 3.594275951385498,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.2622,
      "step": 74
    },
    {
      "epoch": 0.011572288227125443,
      "grad_norm": 3.6462042331695557,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.4741,
      "step": 75
    },
    {
      "epoch": 0.011726585403487116,
      "grad_norm": 3.6718201637268066,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.1981,
      "step": 76
    },
    {
      "epoch": 0.01188088257984879,
      "grad_norm": 3.080090045928955,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.1866,
      "step": 77
    },
    {
      "epoch": 0.01203517975621046,
      "grad_norm": 3.771914482116699,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.3839,
      "step": 78
    },
    {
      "epoch": 0.012189476932572134,
      "grad_norm": 3.9206366539001465,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.4241,
      "step": 79
    },
    {
      "epoch": 0.012343774108933806,
      "grad_norm": 4.18848991394043,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.545,
      "step": 80
    },
    {
      "epoch": 0.01249807128529548,
      "grad_norm": 3.7853705883026123,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.084,
      "step": 81
    },
    {
      "epoch": 0.012652368461657152,
      "grad_norm": 3.4317362308502197,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.3917,
      "step": 82
    },
    {
      "epoch": 0.012806665638018824,
      "grad_norm": 4.1211066246032715,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.1474,
      "step": 83
    },
    {
      "epoch": 0.012960962814380497,
      "grad_norm": 3.795607089996338,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.5356,
      "step": 84
    },
    {
      "epoch": 0.01311525999074217,
      "grad_norm": 3.679100513458252,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.3502,
      "step": 85
    },
    {
      "epoch": 0.013269557167103842,
      "grad_norm": 3.6143267154693604,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.4,
      "step": 86
    },
    {
      "epoch": 0.013423854343465515,
      "grad_norm": 5.664407730102539,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.6533,
      "step": 87
    },
    {
      "epoch": 0.013578151519827187,
      "grad_norm": 3.5444133281707764,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.2159,
      "step": 88
    },
    {
      "epoch": 0.01373244869618886,
      "grad_norm": 6.730358600616455,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.918,
      "step": 89
    },
    {
      "epoch": 0.013886745872550533,
      "grad_norm": 5.462514877319336,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.8791,
      "step": 90
    },
    {
      "epoch": 0.014041043048912205,
      "grad_norm": 4.740200519561768,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.5691,
      "step": 91
    },
    {
      "epoch": 0.014195340225273877,
      "grad_norm": 6.033707141876221,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.8489,
      "step": 92
    },
    {
      "epoch": 0.01434963740163555,
      "grad_norm": 4.585402965545654,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.5508,
      "step": 93
    },
    {
      "epoch": 0.014503934577997223,
      "grad_norm": 4.964543342590332,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.7105,
      "step": 94
    },
    {
      "epoch": 0.014658231754358896,
      "grad_norm": 5.548606872558594,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.5941,
      "step": 95
    },
    {
      "epoch": 0.014812528930720568,
      "grad_norm": 4.768906116485596,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.6796,
      "step": 96
    },
    {
      "epoch": 0.01496682610708224,
      "grad_norm": 6.521129608154297,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.8663,
      "step": 97
    },
    {
      "epoch": 0.015121123283443913,
      "grad_norm": 5.308840751647949,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.6735,
      "step": 98
    },
    {
      "epoch": 0.015275420459805586,
      "grad_norm": 5.61121940612793,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.8388,
      "step": 99
    },
    {
      "epoch": 0.015429717636167259,
      "grad_norm": 7.996213436126709,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 2.1712,
      "step": 100
    },
    {
      "epoch": 0.015429717636167259,
      "eval_loss": 0.31678396463394165,
      "eval_runtime": 1176.1875,
      "eval_samples_per_second": 9.281,
      "eval_steps_per_second": 2.32,
      "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": 2.32091006533632e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}