{
  "best_metric": 0.11460215598344803,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 2.012802275960171,
  "eval_steps": 25,
  "global_step": 88,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02275960170697013,
      "grad_norm": 1.7416112422943115,
      "learning_rate": 0.00015,
      "loss": 3.3287,
      "step": 1
    },
    {
      "epoch": 0.02275960170697013,
      "eval_loss": 3.4932775497436523,
      "eval_runtime": 0.2862,
      "eval_samples_per_second": 174.715,
      "eval_steps_per_second": 45.426,
      "step": 1
    },
    {
      "epoch": 0.04551920341394026,
      "grad_norm": 1.6345694065093994,
      "learning_rate": 0.0003,
      "loss": 3.318,
      "step": 2
    },
    {
      "epoch": 0.06827880512091039,
      "grad_norm": 1.726089358329773,
      "learning_rate": 0.00029990993452998227,
      "loss": 3.3113,
      "step": 3
    },
    {
      "epoch": 0.09103840682788052,
      "grad_norm": 1.496631145477295,
      "learning_rate": 0.00029963985829457943,
      "loss": 2.956,
      "step": 4
    },
    {
      "epoch": 0.11379800853485064,
      "grad_norm": 1.4868099689483643,
      "learning_rate": 0.0002991901316573927,
      "loss": 2.7203,
      "step": 5
    },
    {
      "epoch": 0.13655761024182078,
      "grad_norm": 1.4169163703918457,
      "learning_rate": 0.00029856135469013987,
      "loss": 2.394,
      "step": 6
    },
    {
      "epoch": 0.1593172119487909,
      "grad_norm": 1.5401833057403564,
      "learning_rate": 0.0002977543663719779,
      "loss": 2.1829,
      "step": 7
    },
    {
      "epoch": 0.18207681365576103,
      "grad_norm": 1.8458465337753296,
      "learning_rate": 0.00029677024347005013,
      "loss": 2.0323,
      "step": 8
    },
    {
      "epoch": 0.20483641536273114,
      "grad_norm": 2.272869110107422,
      "learning_rate": 0.0002956102991027524,
      "loss": 1.7811,
      "step": 9
    },
    {
      "epoch": 0.22759601706970128,
      "grad_norm": 2.5353314876556396,
      "learning_rate": 0.0002942760809876348,
      "loss": 1.5327,
      "step": 10
    },
    {
      "epoch": 0.2503556187766714,
      "grad_norm": 2.5102078914642334,
      "learning_rate": 0.00029276936937627725,
      "loss": 1.2993,
      "step": 11
    },
    {
      "epoch": 0.27311522048364156,
      "grad_norm": 2.5022499561309814,
      "learning_rate": 0.000291092174678894,
      "loss": 1.1518,
      "step": 12
    },
    {
      "epoch": 0.2958748221906117,
      "grad_norm": 1.592368483543396,
      "learning_rate": 0.00028924673478183645,
      "loss": 0.966,
      "step": 13
    },
    {
      "epoch": 0.3186344238975818,
      "grad_norm": 1.51223623752594,
      "learning_rate": 0.0002872355120615748,
      "loss": 0.8205,
      "step": 14
    },
    {
      "epoch": 0.3413940256045519,
      "grad_norm": 1.5905065536499023,
      "learning_rate": 0.00028506119009914,
      "loss": 0.7043,
      "step": 15
    },
    {
      "epoch": 0.36415362731152207,
      "grad_norm": 1.3329778909683228,
      "learning_rate": 0.000282726670099414,
      "loss": 0.661,
      "step": 16
    },
    {
      "epoch": 0.3869132290184922,
      "grad_norm": 0.8890392780303955,
      "learning_rate": 0.00028023506702004174,
      "loss": 0.4706,
      "step": 17
    },
    {
      "epoch": 0.4096728307254623,
      "grad_norm": 0.8749057650566101,
      "learning_rate": 0.0002775897054151335,
      "loss": 0.4197,
      "step": 18
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 0.8308561444282532,
      "learning_rate": 0.00027479411499930134,
      "loss": 0.4065,
      "step": 19
    },
    {
      "epoch": 0.45519203413940257,
      "grad_norm": 0.8073086142539978,
      "learning_rate": 0.00027185202593794927,
      "loss": 0.3595,
      "step": 20
    },
    {
      "epoch": 0.4779516358463727,
      "grad_norm": 0.6640134453773499,
      "learning_rate": 0.0002687673638701018,
      "loss": 0.3145,
      "step": 21
    },
    {
      "epoch": 0.5007112375533428,
      "grad_norm": 0.9070307612419128,
      "learning_rate": 0.00026554424467041055,
      "loss": 0.4087,
      "step": 22
    },
    {
      "epoch": 0.5234708392603129,
      "grad_norm": 0.810393750667572,
      "learning_rate": 0.00026218696895732944,
      "loss": 0.3313,
      "step": 23
    },
    {
      "epoch": 0.5462304409672831,
      "grad_norm": 0.5537192821502686,
      "learning_rate": 0.0002587000163547856,
      "loss": 0.2993,
      "step": 24
    },
    {
      "epoch": 0.5689900426742532,
      "grad_norm": 0.7400078177452087,
      "learning_rate": 0.0002550880395150023,
      "loss": 0.292,
      "step": 25
    },
    {
      "epoch": 0.5689900426742532,
      "eval_loss": 0.27180495858192444,
      "eval_runtime": 0.2794,
      "eval_samples_per_second": 178.941,
      "eval_steps_per_second": 46.525,
      "step": 25
    },
    {
      "epoch": 0.5917496443812233,
      "grad_norm": 0.6441358923912048,
      "learning_rate": 0.0002513558579104503,
      "loss": 0.2836,
      "step": 26
    },
    {
      "epoch": 0.6145092460881935,
      "grad_norm": 0.5371875166893005,
      "learning_rate": 0.00024750845140320964,
      "loss": 0.2955,
      "step": 27
    },
    {
      "epoch": 0.6372688477951636,
      "grad_norm": 0.4502342939376831,
      "learning_rate": 0.00024355095360032364,
      "loss": 0.2183,
      "step": 28
    },
    {
      "epoch": 0.6600284495021337,
      "grad_norm": 0.38916662335395813,
      "learning_rate": 0.00023948864500401016,
      "loss": 0.2134,
      "step": 29
    },
    {
      "epoch": 0.6827880512091038,
      "grad_norm": 0.48821350932121277,
      "learning_rate": 0.00023532694596587055,
      "loss": 0.1972,
      "step": 30
    },
    {
      "epoch": 0.705547652916074,
      "grad_norm": 0.43508380651474,
      "learning_rate": 0.00023107140945449652,
      "loss": 0.1729,
      "step": 31
    },
    {
      "epoch": 0.7283072546230441,
      "grad_norm": 0.5526984333992004,
      "learning_rate": 0.0002267277136461262,
      "loss": 0.1241,
      "step": 32
    },
    {
      "epoch": 0.7510668563300142,
      "grad_norm": 0.38419315218925476,
      "learning_rate": 0.00022230165434823502,
      "loss": 0.2296,
      "step": 33
    },
    {
      "epoch": 0.7738264580369844,
      "grad_norm": 0.5567602515220642,
      "learning_rate": 0.00021779913726617102,
      "loss": 0.2295,
      "step": 34
    },
    {
      "epoch": 0.7965860597439545,
      "grad_norm": 0.4326823651790619,
      "learning_rate": 0.00021322617012315288,
      "loss": 0.1703,
      "step": 35
    },
    {
      "epoch": 0.8193456614509246,
      "grad_norm": 0.4207884669303894,
      "learning_rate": 0.00020858885464414522,
      "loss": 0.178,
      "step": 36
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.47066789865493774,
      "learning_rate": 0.00020389337841430707,
      "loss": 0.1736,
      "step": 37
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 0.4035787284374237,
      "learning_rate": 0.00019914600662287684,
      "loss": 0.1759,
      "step": 38
    },
    {
      "epoch": 0.887624466571835,
      "grad_norm": 0.32935065031051636,
      "learning_rate": 0.00019435307370351017,
      "loss": 0.1141,
      "step": 39
    },
    {
      "epoch": 0.9103840682788051,
      "grad_norm": 0.26641812920570374,
      "learning_rate": 0.0001895209748822239,
      "loss": 0.1083,
      "step": 40
    },
    {
      "epoch": 0.9331436699857752,
      "grad_norm": 0.32735541462898254,
      "learning_rate": 0.00018465615764422566,
      "loss": 0.132,
      "step": 41
    },
    {
      "epoch": 0.9559032716927454,
      "grad_norm": 0.21898917853832245,
      "learning_rate": 0.00017976511313101307,
      "loss": 0.1019,
      "step": 42
    },
    {
      "epoch": 0.9786628733997155,
      "grad_norm": 0.2621893882751465,
      "learning_rate": 0.00017485436747922248,
      "loss": 0.0869,
      "step": 43
    },
    {
      "epoch": 1.0064011379800855,
      "grad_norm": 0.27739080786705017,
      "learning_rate": 0.00016993047311278397,
      "loss": 0.2184,
      "step": 44
    },
    {
      "epoch": 1.0291607396870555,
      "grad_norm": 0.3383594751358032,
      "learning_rate": 0.000165,
      "loss": 0.1592,
      "step": 45
    },
    {
      "epoch": 1.0519203413940257,
      "grad_norm": 0.3034259080886841,
      "learning_rate": 0.00016006952688721603,
      "loss": 0.1443,
      "step": 46
    },
    {
      "epoch": 1.0746799431009957,
      "grad_norm": 0.27324768900871277,
      "learning_rate": 0.0001551456325207775,
      "loss": 0.1408,
      "step": 47
    },
    {
      "epoch": 1.097439544807966,
      "grad_norm": 0.22992853820323944,
      "learning_rate": 0.00015023488686898698,
      "loss": 0.1433,
      "step": 48
    },
    {
      "epoch": 1.120199146514936,
      "grad_norm": 0.24354040622711182,
      "learning_rate": 0.00014534384235577436,
      "loss": 0.1316,
      "step": 49
    },
    {
      "epoch": 1.1429587482219061,
      "grad_norm": 0.28851574659347534,
      "learning_rate": 0.0001404790251177761,
      "loss": 0.1076,
      "step": 50
    },
    {
      "epoch": 1.1429587482219061,
      "eval_loss": 0.11460215598344803,
      "eval_runtime": 0.2861,
      "eval_samples_per_second": 174.765,
      "eval_steps_per_second": 45.439,
      "step": 50
    },
    {
      "epoch": 1.1657183499288761,
      "grad_norm": 0.2691490352153778,
      "learning_rate": 0.00013564692629648982,
      "loss": 0.0852,
      "step": 51
    },
    {
      "epoch": 1.1884779516358464,
      "grad_norm": 0.1689569503068924,
      "learning_rate": 0.00013085399337712307,
      "loss": 0.0964,
      "step": 52
    },
    {
      "epoch": 1.2112375533428166,
      "grad_norm": 0.22519923746585846,
      "learning_rate": 0.00012610662158569293,
      "loss": 0.0914,
      "step": 53
    },
    {
      "epoch": 1.2339971550497866,
      "grad_norm": 0.2679944634437561,
      "learning_rate": 0.0001214111453558548,
      "loss": 0.0706,
      "step": 54
    },
    {
      "epoch": 1.2567567567567568,
      "grad_norm": 0.28117287158966064,
      "learning_rate": 0.00011677382987684708,
      "loss": 0.182,
      "step": 55
    },
    {
      "epoch": 1.2795163584637268,
      "grad_norm": 0.2838458716869354,
      "learning_rate": 0.00011220086273382896,
      "loss": 0.1417,
      "step": 56
    },
    {
      "epoch": 1.302275960170697,
      "grad_norm": 0.3674065172672272,
      "learning_rate": 0.00010769834565176498,
      "loss": 0.1263,
      "step": 57
    },
    {
      "epoch": 1.3250355618776672,
      "grad_norm": 0.24421556293964386,
      "learning_rate": 0.0001032722863538738,
      "loss": 0.1178,
      "step": 58
    },
    {
      "epoch": 1.3477951635846372,
      "grad_norm": 0.2171713262796402,
      "learning_rate": 9.892859054550347e-05,
      "loss": 0.1202,
      "step": 59
    },
    {
      "epoch": 1.3705547652916075,
      "grad_norm": 0.2513107657432556,
      "learning_rate": 9.467305403412942e-05,
      "loss": 0.1421,
      "step": 60
    },
    {
      "epoch": 1.3933143669985775,
      "grad_norm": 0.1986607015132904,
      "learning_rate": 9.05113549959898e-05,
      "loss": 0.0953,
      "step": 61
    },
    {
      "epoch": 1.4160739687055477,
      "grad_norm": 0.2196892499923706,
      "learning_rate": 8.644904639967639e-05,
      "loss": 0.0852,
      "step": 62
    },
    {
      "epoch": 1.438833570412518,
      "grad_norm": 0.21326187252998352,
      "learning_rate": 8.249154859679033e-05,
      "loss": 0.0821,
      "step": 63
    },
    {
      "epoch": 1.461593172119488,
      "grad_norm": 0.21575187146663666,
      "learning_rate": 7.864414208954971e-05,
      "loss": 0.0865,
      "step": 64
    },
    {
      "epoch": 1.484352773826458,
      "grad_norm": 0.17554332315921783,
      "learning_rate": 7.491196048499769e-05,
      "loss": 0.0701,
      "step": 65
    },
    {
      "epoch": 1.5071123755334281,
      "grad_norm": 0.3326629400253296,
      "learning_rate": 7.12999836452144e-05,
      "loss": 0.1359,
      "step": 66
    },
    {
      "epoch": 1.5298719772403984,
      "grad_norm": 0.242942675948143,
      "learning_rate": 6.781303104267059e-05,
      "loss": 0.1213,
      "step": 67
    },
    {
      "epoch": 1.5526315789473686,
      "grad_norm": 0.15724237263202667,
      "learning_rate": 6.445575532958945e-05,
      "loss": 0.0944,
      "step": 68
    },
    {
      "epoch": 1.5753911806543386,
      "grad_norm": 0.1837826371192932,
      "learning_rate": 6.123263612989815e-05,
      "loss": 0.1227,
      "step": 69
    },
    {
      "epoch": 1.5981507823613086,
      "grad_norm": 0.16875876486301422,
      "learning_rate": 5.81479740620507e-05,
      "loss": 0.1012,
      "step": 70
    },
    {
      "epoch": 1.6209103840682788,
      "grad_norm": 0.2034892439842224,
      "learning_rate": 5.520588500069867e-05,
      "loss": 0.1228,
      "step": 71
    },
    {
      "epoch": 1.643669985775249,
      "grad_norm": 0.18250970542430878,
      "learning_rate": 5.241029458486649e-05,
      "loss": 0.0753,
      "step": 72
    },
    {
      "epoch": 1.666429587482219,
      "grad_norm": 0.12507431209087372,
      "learning_rate": 4.976493297995823e-05,
      "loss": 0.0749,
      "step": 73
    },
    {
      "epoch": 1.689189189189189,
      "grad_norm": 0.16313859820365906,
      "learning_rate": 4.7273329900585954e-05,
      "loss": 0.0812,
      "step": 74
    },
    {
      "epoch": 1.7119487908961593,
      "grad_norm": 0.14435066282749176,
      "learning_rate": 4.4938809900859955e-05,
      "loss": 0.0737,
      "step": 75
    },
    {
      "epoch": 1.7119487908961593,
      "eval_loss": 0.09484730660915375,
      "eval_runtime": 0.2949,
      "eval_samples_per_second": 169.544,
      "eval_steps_per_second": 44.081,
      "step": 75
    },
    {
      "epoch": 1.7347083926031295,
      "grad_norm": 0.1676023304462433,
      "learning_rate": 4.2764487938425205e-05,
      "loss": 0.0561,
      "step": 76
    },
    {
      "epoch": 1.7574679943100997,
      "grad_norm": 0.26078304648399353,
      "learning_rate": 4.0753265218163486e-05,
      "loss": 0.1575,
      "step": 77
    },
    {
      "epoch": 1.7802275960170697,
      "grad_norm": 0.23101890087127686,
      "learning_rate": 3.890782532110603e-05,
      "loss": 0.1118,
      "step": 78
    },
    {
      "epoch": 1.8029871977240397,
      "grad_norm": 0.22551748156547546,
      "learning_rate": 3.7230630623722724e-05,
      "loss": 0.101,
      "step": 79
    },
    {
      "epoch": 1.82574679943101,
      "grad_norm": 0.21574518084526062,
      "learning_rate": 3.572391901236521e-05,
      "loss": 0.1012,
      "step": 80
    },
    {
      "epoch": 1.8485064011379801,
      "grad_norm": 0.15184852480888367,
      "learning_rate": 3.4389700897247595e-05,
      "loss": 0.1,
      "step": 81
    },
    {
      "epoch": 1.8712660028449504,
      "grad_norm": 0.1621236801147461,
      "learning_rate": 3.322975652994985e-05,
      "loss": 0.083,
      "step": 82
    },
    {
      "epoch": 1.8940256045519204,
      "grad_norm": 0.19756773114204407,
      "learning_rate": 3.2245633628022074e-05,
      "loss": 0.0676,
      "step": 83
    },
    {
      "epoch": 1.9167852062588904,
      "grad_norm": 0.15019188821315765,
      "learning_rate": 3.143864530986012e-05,
      "loss": 0.0717,
      "step": 84
    },
    {
      "epoch": 1.9395448079658606,
      "grad_norm": 0.1473209261894226,
      "learning_rate": 3.08098683426073e-05,
      "loss": 0.0856,
      "step": 85
    },
    {
      "epoch": 1.9623044096728308,
      "grad_norm": 0.22414885461330414,
      "learning_rate": 3.0360141705420527e-05,
      "loss": 0.0729,
      "step": 86
    },
    {
      "epoch": 1.9850640113798008,
      "grad_norm": 0.21767638623714447,
      "learning_rate": 3.009006547001768e-05,
      "loss": 0.0847,
      "step": 87
    },
    {
      "epoch": 2.012802275960171,
      "grad_norm": 0.23539167642593384,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 0.1202,
      "step": 88
    }
  ],
  "logging_steps": 1,
  "max_steps": 88,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "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": 3.909666424120934e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}