{
  "best_metric": 0.7902164459228516,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 0.4727103094386565,
  "eval_steps": 25,
  "global_step": 95,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004975897994091121,
      "grad_norm": 0.23871222138404846,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.0835,
      "step": 1
    },
    {
      "epoch": 0.004975897994091121,
      "eval_loss": 1.137823224067688,
      "eval_runtime": 1.0224,
      "eval_samples_per_second": 48.904,
      "eval_steps_per_second": 12.715,
      "step": 1
    },
    {
      "epoch": 0.009951795988182242,
      "grad_norm": 0.41071704030036926,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.9659,
      "step": 2
    },
    {
      "epoch": 0.014927693982273364,
      "grad_norm": 0.39753258228302,
      "learning_rate": 0.0001,
      "loss": 1.0785,
      "step": 3
    },
    {
      "epoch": 0.019903591976364484,
      "grad_norm": 0.3230868875980377,
      "learning_rate": 9.997376600647783e-05,
      "loss": 1.0597,
      "step": 4
    },
    {
      "epoch": 0.024879489970455606,
      "grad_norm": 0.27026239037513733,
      "learning_rate": 9.989509461357426e-05,
      "loss": 1.0604,
      "step": 5
    },
    {
      "epoch": 0.029855387964546728,
      "grad_norm": 0.43072497844696045,
      "learning_rate": 9.976407754861426e-05,
      "loss": 1.088,
      "step": 6
    },
    {
      "epoch": 0.034831285958637846,
      "grad_norm": 0.2670774459838867,
      "learning_rate": 9.958086757163489e-05,
      "loss": 1.0971,
      "step": 7
    },
    {
      "epoch": 0.03980718395272897,
      "grad_norm": 0.2514101266860962,
      "learning_rate": 9.934567829727386e-05,
      "loss": 1.1188,
      "step": 8
    },
    {
      "epoch": 0.04478308194682009,
      "grad_norm": 0.23422400653362274,
      "learning_rate": 9.905878394570453e-05,
      "loss": 1.1227,
      "step": 9
    },
    {
      "epoch": 0.04975897994091121,
      "grad_norm": 0.28173166513442993,
      "learning_rate": 9.872051902290737e-05,
      "loss": 1.1324,
      "step": 10
    },
    {
      "epoch": 0.054734877935002334,
      "grad_norm": 0.2882803976535797,
      "learning_rate": 9.833127793065098e-05,
      "loss": 1.1169,
      "step": 11
    },
    {
      "epoch": 0.059710775929093456,
      "grad_norm": 0.38014933466911316,
      "learning_rate": 9.789151450663723e-05,
      "loss": 1.0644,
      "step": 12
    },
    {
      "epoch": 0.06468667392318457,
      "grad_norm": 0.19597893953323364,
      "learning_rate": 9.740174149534693e-05,
      "loss": 1.0606,
      "step": 13
    },
    {
      "epoch": 0.06966257191727569,
      "grad_norm": 0.20651479065418243,
      "learning_rate": 9.686252995020249e-05,
      "loss": 0.866,
      "step": 14
    },
    {
      "epoch": 0.07463846991136681,
      "grad_norm": 0.22201478481292725,
      "learning_rate": 9.627450856774539e-05,
      "loss": 0.943,
      "step": 15
    },
    {
      "epoch": 0.07961436790545794,
      "grad_norm": 0.19648012518882751,
      "learning_rate": 9.563836295460398e-05,
      "loss": 0.8928,
      "step": 16
    },
    {
      "epoch": 0.08459026589954906,
      "grad_norm": 0.1876300871372223,
      "learning_rate": 9.495483482810688e-05,
      "loss": 0.964,
      "step": 17
    },
    {
      "epoch": 0.08956616389364018,
      "grad_norm": 0.19657588005065918,
      "learning_rate": 9.422472115147382e-05,
      "loss": 0.9633,
      "step": 18
    },
    {
      "epoch": 0.0945420618877313,
      "grad_norm": 0.19236579537391663,
      "learning_rate": 9.3448873204592e-05,
      "loss": 0.9711,
      "step": 19
    },
    {
      "epoch": 0.09951795988182242,
      "grad_norm": 0.2960802912712097,
      "learning_rate": 9.2628195591462e-05,
      "loss": 1.042,
      "step": 20
    },
    {
      "epoch": 0.10449385787591355,
      "grad_norm": 0.22051385045051575,
      "learning_rate": 9.176364518546989e-05,
      "loss": 0.9778,
      "step": 21
    },
    {
      "epoch": 0.10946975587000467,
      "grad_norm": 0.22082725167274475,
      "learning_rate": 9.08562300137157e-05,
      "loss": 1.0256,
      "step": 22
    },
    {
      "epoch": 0.11444565386409579,
      "grad_norm": 0.23512785136699677,
      "learning_rate": 8.990700808169889e-05,
      "loss": 1.0135,
      "step": 23
    },
    {
      "epoch": 0.11942155185818691,
      "grad_norm": 0.25989964604377747,
      "learning_rate": 8.891708613973126e-05,
      "loss": 0.9302,
      "step": 24
    },
    {
      "epoch": 0.12439744985227803,
      "grad_norm": 0.3857329487800598,
      "learning_rate": 8.788761839251559e-05,
      "loss": 0.9751,
      "step": 25
    },
    {
      "epoch": 0.12439744985227803,
      "eval_loss": 0.871764600276947,
      "eval_runtime": 1.0251,
      "eval_samples_per_second": 48.774,
      "eval_steps_per_second": 12.681,
      "step": 25
    },
    {
      "epoch": 0.12937334784636914,
      "grad_norm": 0.1513061821460724,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.0278,
      "step": 26
    },
    {
      "epoch": 0.13434924584046026,
      "grad_norm": 0.1964515596628189,
      "learning_rate": 8.571489144483944e-05,
      "loss": 0.8645,
      "step": 27
    },
    {
      "epoch": 0.13932514383455138,
      "grad_norm": 0.24235105514526367,
      "learning_rate": 8.457416554680877e-05,
      "loss": 0.8915,
      "step": 28
    },
    {
      "epoch": 0.1443010418286425,
      "grad_norm": 0.20897287130355835,
      "learning_rate": 8.339895749467238e-05,
      "loss": 0.9104,
      "step": 29
    },
    {
      "epoch": 0.14927693982273363,
      "grad_norm": 0.20914201438426971,
      "learning_rate": 8.219063752844926e-05,
      "loss": 0.9081,
      "step": 30
    },
    {
      "epoch": 0.15425283781682475,
      "grad_norm": 0.20824605226516724,
      "learning_rate": 8.095061449516903e-05,
      "loss": 0.9098,
      "step": 31
    },
    {
      "epoch": 0.15922873581091587,
      "grad_norm": 0.19852378964424133,
      "learning_rate": 7.968033420621935e-05,
      "loss": 0.9486,
      "step": 32
    },
    {
      "epoch": 0.164204633805007,
      "grad_norm": 0.306395024061203,
      "learning_rate": 7.838127775159452e-05,
      "loss": 0.955,
      "step": 33
    },
    {
      "epoch": 0.16918053179909812,
      "grad_norm": 0.2190617471933365,
      "learning_rate": 7.705495977301078e-05,
      "loss": 0.9907,
      "step": 34
    },
    {
      "epoch": 0.17415642979318924,
      "grad_norm": 0.21145637333393097,
      "learning_rate": 7.570292669790186e-05,
      "loss": 0.9608,
      "step": 35
    },
    {
      "epoch": 0.17913232778728036,
      "grad_norm": 0.24957385659217834,
      "learning_rate": 7.43267549363537e-05,
      "loss": 0.9218,
      "step": 36
    },
    {
      "epoch": 0.18410822578137148,
      "grad_norm": 0.2624641954898834,
      "learning_rate": 7.292804904308087e-05,
      "loss": 0.8877,
      "step": 37
    },
    {
      "epoch": 0.1890841237754626,
      "grad_norm": 0.15153071284294128,
      "learning_rate": 7.150843984658754e-05,
      "loss": 1.0023,
      "step": 38
    },
    {
      "epoch": 0.19406002176955373,
      "grad_norm": 0.1561977118253708,
      "learning_rate": 7.006958254769438e-05,
      "loss": 0.8461,
      "step": 39
    },
    {
      "epoch": 0.19903591976364485,
      "grad_norm": 0.18604518473148346,
      "learning_rate": 6.861315478964841e-05,
      "loss": 0.8691,
      "step": 40
    },
    {
      "epoch": 0.20401181775773597,
      "grad_norm": 0.16946768760681152,
      "learning_rate": 6.714085470206609e-05,
      "loss": 0.8581,
      "step": 41
    },
    {
      "epoch": 0.2089877157518271,
      "grad_norm": 0.1662844568490982,
      "learning_rate": 6.56543989209901e-05,
      "loss": 0.8686,
      "step": 42
    },
    {
      "epoch": 0.2139636137459182,
      "grad_norm": 0.16444341838359833,
      "learning_rate": 6.415552058736854e-05,
      "loss": 0.8854,
      "step": 43
    },
    {
      "epoch": 0.21893951174000933,
      "grad_norm": 0.17267289757728577,
      "learning_rate": 6.264596732629e-05,
      "loss": 0.8595,
      "step": 44
    },
    {
      "epoch": 0.22391540973410046,
      "grad_norm": 0.20546430349349976,
      "learning_rate": 6.112749920933111e-05,
      "loss": 0.9038,
      "step": 45
    },
    {
      "epoch": 0.22889130772819158,
      "grad_norm": 0.1972435861825943,
      "learning_rate": 5.960188670239154e-05,
      "loss": 0.9723,
      "step": 46
    },
    {
      "epoch": 0.2338672057222827,
      "grad_norm": 0.2849563658237457,
      "learning_rate": 5.80709086014102e-05,
      "loss": 0.9412,
      "step": 47
    },
    {
      "epoch": 0.23884310371637382,
      "grad_norm": 0.2184210568666458,
      "learning_rate": 5.653634995836856e-05,
      "loss": 0.9191,
      "step": 48
    },
    {
      "epoch": 0.24381900171046494,
      "grad_norm": 0.23135943710803986,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.8842,
      "step": 49
    },
    {
      "epoch": 0.24879489970455607,
      "grad_norm": 0.3442687690258026,
      "learning_rate": 5.346365004163145e-05,
      "loss": 0.8583,
      "step": 50
    },
    {
      "epoch": 0.24879489970455607,
      "eval_loss": 0.8090626001358032,
      "eval_runtime": 1.0254,
      "eval_samples_per_second": 48.761,
      "eval_steps_per_second": 12.678,
      "step": 50
    },
    {
      "epoch": 0.2537707976986472,
      "grad_norm": 0.12577220797538757,
      "learning_rate": 5.192909139858981e-05,
      "loss": 1.0566,
      "step": 51
    },
    {
      "epoch": 0.2587466956927383,
      "grad_norm": 0.16750161349773407,
      "learning_rate": 5.0398113297608465e-05,
      "loss": 0.8238,
      "step": 52
    },
    {
      "epoch": 0.26372259368682943,
      "grad_norm": 0.17324009537696838,
      "learning_rate": 4.887250079066892e-05,
      "loss": 0.8423,
      "step": 53
    },
    {
      "epoch": 0.2686984916809205,
      "grad_norm": 0.17715862393379211,
      "learning_rate": 4.7354032673710005e-05,
      "loss": 0.8862,
      "step": 54
    },
    {
      "epoch": 0.2736743896750117,
      "grad_norm": 0.17103923857212067,
      "learning_rate": 4.584447941263149e-05,
      "loss": 0.8712,
      "step": 55
    },
    {
      "epoch": 0.27865028766910277,
      "grad_norm": 0.16644009947776794,
      "learning_rate": 4.43456010790099e-05,
      "loss": 0.8458,
      "step": 56
    },
    {
      "epoch": 0.2836261856631939,
      "grad_norm": 0.17309409379959106,
      "learning_rate": 4.285914529793391e-05,
      "loss": 0.8803,
      "step": 57
    },
    {
      "epoch": 0.288602083657285,
      "grad_norm": 0.1786348819732666,
      "learning_rate": 4.13868452103516e-05,
      "loss": 0.8838,
      "step": 58
    },
    {
      "epoch": 0.29357798165137616,
      "grad_norm": 0.19110921025276184,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 0.9268,
      "step": 59
    },
    {
      "epoch": 0.29855387964546726,
      "grad_norm": 0.198200523853302,
      "learning_rate": 3.8491560153412466e-05,
      "loss": 0.9084,
      "step": 60
    },
    {
      "epoch": 0.3035297776395584,
      "grad_norm": 0.22449031472206116,
      "learning_rate": 3.707195095691913e-05,
      "loss": 0.8733,
      "step": 61
    },
    {
      "epoch": 0.3085056756336495,
      "grad_norm": 0.26478344202041626,
      "learning_rate": 3.567324506364632e-05,
      "loss": 0.8939,
      "step": 62
    },
    {
      "epoch": 0.31348157362774065,
      "grad_norm": 0.13545911014080048,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 1.0545,
      "step": 63
    },
    {
      "epoch": 0.31845747162183174,
      "grad_norm": 0.1377517431974411,
      "learning_rate": 3.2945040226989244e-05,
      "loss": 0.8699,
      "step": 64
    },
    {
      "epoch": 0.3234333696159229,
      "grad_norm": 0.1665552407503128,
      "learning_rate": 3.16187222484055e-05,
      "loss": 0.8334,
      "step": 65
    },
    {
      "epoch": 0.328409267610014,
      "grad_norm": 0.15971739590168,
      "learning_rate": 3.0319665793780648e-05,
      "loss": 0.8595,
      "step": 66
    },
    {
      "epoch": 0.33338516560410514,
      "grad_norm": 0.1528182327747345,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 0.8277,
      "step": 67
    },
    {
      "epoch": 0.33836106359819623,
      "grad_norm": 0.1469763070344925,
      "learning_rate": 2.7809362471550748e-05,
      "loss": 0.8526,
      "step": 68
    },
    {
      "epoch": 0.3433369615922874,
      "grad_norm": 0.14643485844135284,
      "learning_rate": 2.660104250532764e-05,
      "loss": 0.8201,
      "step": 69
    },
    {
      "epoch": 0.3483128595863785,
      "grad_norm": 0.1613270789384842,
      "learning_rate": 2.5425834453191232e-05,
      "loss": 0.8523,
      "step": 70
    },
    {
      "epoch": 0.3532887575804696,
      "grad_norm": 0.17931152880191803,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 0.8531,
      "step": 71
    },
    {
      "epoch": 0.3582646555745607,
      "grad_norm": 0.1984926164150238,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.8898,
      "step": 72
    },
    {
      "epoch": 0.36324055356865187,
      "grad_norm": 0.20060153305530548,
      "learning_rate": 2.2112381607484417e-05,
      "loss": 0.8438,
      "step": 73
    },
    {
      "epoch": 0.36821645156274296,
      "grad_norm": 0.24903373420238495,
      "learning_rate": 2.1082913860268765e-05,
      "loss": 0.8631,
      "step": 74
    },
    {
      "epoch": 0.37319234955683406,
      "grad_norm": 0.31300994753837585,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 0.8392,
      "step": 75
    },
    {
      "epoch": 0.37319234955683406,
      "eval_loss": 0.7902164459228516,
      "eval_runtime": 1.0566,
      "eval_samples_per_second": 47.321,
      "eval_steps_per_second": 12.304,
      "step": 75
    },
    {
      "epoch": 0.3781682475509252,
      "grad_norm": 0.1049114391207695,
      "learning_rate": 1.91437699862843e-05,
      "loss": 0.9218,
      "step": 76
    },
    {
      "epoch": 0.3831441455450163,
      "grad_norm": 0.12478011101484299,
      "learning_rate": 1.8236354814530112e-05,
      "loss": 0.7758,
      "step": 77
    },
    {
      "epoch": 0.38812004353910745,
      "grad_norm": 0.1491149365901947,
      "learning_rate": 1.7371804408538024e-05,
      "loss": 0.8426,
      "step": 78
    },
    {
      "epoch": 0.39309594153319855,
      "grad_norm": 0.1671927273273468,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 0.8121,
      "step": 79
    },
    {
      "epoch": 0.3980718395272897,
      "grad_norm": 0.17548252642154694,
      "learning_rate": 1.577527884852619e-05,
      "loss": 0.8689,
      "step": 80
    },
    {
      "epoch": 0.4030477375213808,
      "grad_norm": 0.1623646467924118,
      "learning_rate": 1.5045165171893116e-05,
      "loss": 0.8746,
      "step": 81
    },
    {
      "epoch": 0.40802363551547194,
      "grad_norm": 0.17200708389282227,
      "learning_rate": 1.4361637045396029e-05,
      "loss": 0.907,
      "step": 82
    },
    {
      "epoch": 0.41299953350956303,
      "grad_norm": 0.1750720888376236,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 0.8647,
      "step": 83
    },
    {
      "epoch": 0.4179754315036542,
      "grad_norm": 0.16917237639427185,
      "learning_rate": 1.313747004979751e-05,
      "loss": 0.8754,
      "step": 84
    },
    {
      "epoch": 0.4229513294977453,
      "grad_norm": 0.19028206169605255,
      "learning_rate": 1.2598258504653081e-05,
      "loss": 0.8705,
      "step": 85
    },
    {
      "epoch": 0.4279272274918364,
      "grad_norm": 0.20847304165363312,
      "learning_rate": 1.2108485493362765e-05,
      "loss": 0.8799,
      "step": 86
    },
    {
      "epoch": 0.4329031254859275,
      "grad_norm": 0.2649713456630707,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 0.7941,
      "step": 87
    },
    {
      "epoch": 0.43787902348001867,
      "grad_norm": 0.12713563442230225,
      "learning_rate": 1.1279480977092635e-05,
      "loss": 0.8887,
      "step": 88
    },
    {
      "epoch": 0.44285492147410976,
      "grad_norm": 0.11893071234226227,
      "learning_rate": 1.094121605429547e-05,
      "loss": 0.9033,
      "step": 89
    },
    {
      "epoch": 0.4478308194682009,
      "grad_norm": 0.12651102244853973,
      "learning_rate": 1.0654321702726141e-05,
      "loss": 0.782,
      "step": 90
    },
    {
      "epoch": 0.452806717462292,
      "grad_norm": 0.12543635070323944,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 0.781,
      "step": 91
    },
    {
      "epoch": 0.45778261545638316,
      "grad_norm": 0.12762346863746643,
      "learning_rate": 1.0235922451385733e-05,
      "loss": 0.8043,
      "step": 92
    },
    {
      "epoch": 0.46275851345047425,
      "grad_norm": 0.1441301554441452,
      "learning_rate": 1.0104905386425733e-05,
      "loss": 0.8657,
      "step": 93
    },
    {
      "epoch": 0.4677344114445654,
      "grad_norm": 0.2067331075668335,
      "learning_rate": 1.002623399352217e-05,
      "loss": 0.8734,
      "step": 94
    },
    {
      "epoch": 0.4727103094386565,
      "grad_norm": 0.1604580581188202,
      "learning_rate": 1e-05,
      "loss": 0.8626,
      "step": 95
    }
  ],
  "logging_steps": 1,
  "max_steps": 95,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 1.5834911449546752e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}