{
  "best_metric": 9.585326194763184,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.007664156655362036,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.664156655362036e-05,
      "grad_norm": 3.0833306312561035,
      "learning_rate": 1.5000000000000002e-07,
      "loss": 10.2038,
      "step": 1
    },
    {
      "epoch": 7.664156655362036e-05,
      "eval_loss": 10.22679328918457,
      "eval_runtime": 416.8959,
      "eval_samples_per_second": 52.713,
      "eval_steps_per_second": 6.589,
      "step": 1
    },
    {
      "epoch": 0.0001532831331072407,
      "grad_norm": 2.9026267528533936,
      "learning_rate": 3.0000000000000004e-07,
      "loss": 10.2123,
      "step": 2
    },
    {
      "epoch": 0.00022992469966086107,
      "grad_norm": 2.717977523803711,
      "learning_rate": 4.5e-07,
      "loss": 10.2573,
      "step": 3
    },
    {
      "epoch": 0.0003065662662144814,
      "grad_norm": 2.9277496337890625,
      "learning_rate": 6.000000000000001e-07,
      "loss": 10.2601,
      "step": 4
    },
    {
      "epoch": 0.00038320783276810176,
      "grad_norm": 2.9612338542938232,
      "learning_rate": 7.5e-07,
      "loss": 10.1693,
      "step": 5
    },
    {
      "epoch": 0.00045984939932172214,
      "grad_norm": 2.873253583908081,
      "learning_rate": 9e-07,
      "loss": 10.2514,
      "step": 6
    },
    {
      "epoch": 0.0005364909658753425,
      "grad_norm": 2.8762059211730957,
      "learning_rate": 1.0500000000000001e-06,
      "loss": 10.3508,
      "step": 7
    },
    {
      "epoch": 0.0006131325324289629,
      "grad_norm": 2.795992851257324,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 10.2734,
      "step": 8
    },
    {
      "epoch": 0.0006897740989825832,
      "grad_norm": 2.769205331802368,
      "learning_rate": 1.35e-06,
      "loss": 10.0884,
      "step": 9
    },
    {
      "epoch": 0.0007664156655362035,
      "grad_norm": 2.8631913661956787,
      "learning_rate": 1.5e-06,
      "loss": 10.1913,
      "step": 10
    },
    {
      "epoch": 0.000843057232089824,
      "grad_norm": 2.778069019317627,
      "learning_rate": 1.65e-06,
      "loss": 10.3434,
      "step": 11
    },
    {
      "epoch": 0.0009196987986434443,
      "grad_norm": 2.8693792819976807,
      "learning_rate": 1.8e-06,
      "loss": 10.2631,
      "step": 12
    },
    {
      "epoch": 0.0009963403651970647,
      "grad_norm": 3.109616756439209,
      "learning_rate": 1.95e-06,
      "loss": 10.3441,
      "step": 13
    },
    {
      "epoch": 0.001072981931750685,
      "grad_norm": 3.0356502532958984,
      "learning_rate": 2.1000000000000002e-06,
      "loss": 10.1493,
      "step": 14
    },
    {
      "epoch": 0.0011496234983043054,
      "grad_norm": 2.9254584312438965,
      "learning_rate": 2.25e-06,
      "loss": 10.2948,
      "step": 15
    },
    {
      "epoch": 0.0012262650648579257,
      "grad_norm": 2.876832962036133,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 10.1155,
      "step": 16
    },
    {
      "epoch": 0.001302906631411546,
      "grad_norm": 2.9504146575927734,
      "learning_rate": 2.55e-06,
      "loss": 10.1583,
      "step": 17
    },
    {
      "epoch": 0.0013795481979651664,
      "grad_norm": 2.836592435836792,
      "learning_rate": 2.7e-06,
      "loss": 10.1299,
      "step": 18
    },
    {
      "epoch": 0.0014561897645187867,
      "grad_norm": 3.039888381958008,
      "learning_rate": 2.8500000000000002e-06,
      "loss": 10.1638,
      "step": 19
    },
    {
      "epoch": 0.001532831331072407,
      "grad_norm": 2.7712507247924805,
      "learning_rate": 3e-06,
      "loss": 10.2074,
      "step": 20
    },
    {
      "epoch": 0.0016094728976260276,
      "grad_norm": 2.803617238998413,
      "learning_rate": 3.15e-06,
      "loss": 10.2651,
      "step": 21
    },
    {
      "epoch": 0.001686114464179648,
      "grad_norm": 2.9304254055023193,
      "learning_rate": 3.3e-06,
      "loss": 10.2377,
      "step": 22
    },
    {
      "epoch": 0.0017627560307332682,
      "grad_norm": 2.8531479835510254,
      "learning_rate": 3.4500000000000004e-06,
      "loss": 10.2657,
      "step": 23
    },
    {
      "epoch": 0.0018393975972868886,
      "grad_norm": 2.846740245819092,
      "learning_rate": 3.6e-06,
      "loss": 10.2348,
      "step": 24
    },
    {
      "epoch": 0.001916039163840509,
      "grad_norm": 3.0314481258392334,
      "learning_rate": 3.75e-06,
      "loss": 10.2579,
      "step": 25
    },
    {
      "epoch": 0.0019926807303941294,
      "grad_norm": 3.0108513832092285,
      "learning_rate": 3.9e-06,
      "loss": 10.2788,
      "step": 26
    },
    {
      "epoch": 0.0020693222969477496,
      "grad_norm": 2.8648674488067627,
      "learning_rate": 4.05e-06,
      "loss": 10.16,
      "step": 27
    },
    {
      "epoch": 0.00214596386350137,
      "grad_norm": 2.820892095565796,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 10.1158,
      "step": 28
    },
    {
      "epoch": 0.00222260543005499,
      "grad_norm": 2.9025187492370605,
      "learning_rate": 4.35e-06,
      "loss": 10.3069,
      "step": 29
    },
    {
      "epoch": 0.0022992469966086108,
      "grad_norm": 2.791337490081787,
      "learning_rate": 4.5e-06,
      "loss": 10.1772,
      "step": 30
    },
    {
      "epoch": 0.002375888563162231,
      "grad_norm": 2.826338768005371,
      "learning_rate": 4.65e-06,
      "loss": 10.1847,
      "step": 31
    },
    {
      "epoch": 0.0024525301297158514,
      "grad_norm": 2.5365052223205566,
      "learning_rate": 4.800000000000001e-06,
      "loss": 10.2665,
      "step": 32
    },
    {
      "epoch": 0.002529171696269472,
      "grad_norm": 2.9171478748321533,
      "learning_rate": 4.95e-06,
      "loss": 10.2147,
      "step": 33
    },
    {
      "epoch": 0.002605813262823092,
      "grad_norm": 3.2460930347442627,
      "learning_rate": 5.1e-06,
      "loss": 10.0759,
      "step": 34
    },
    {
      "epoch": 0.0026824548293767126,
      "grad_norm": 2.8777740001678467,
      "learning_rate": 5.25e-06,
      "loss": 10.214,
      "step": 35
    },
    {
      "epoch": 0.0027590963959303327,
      "grad_norm": 2.959735155105591,
      "learning_rate": 5.4e-06,
      "loss": 10.266,
      "step": 36
    },
    {
      "epoch": 0.0028357379624839533,
      "grad_norm": 2.900165319442749,
      "learning_rate": 5.55e-06,
      "loss": 10.0336,
      "step": 37
    },
    {
      "epoch": 0.0029123795290375734,
      "grad_norm": 2.9267468452453613,
      "learning_rate": 5.7000000000000005e-06,
      "loss": 10.1848,
      "step": 38
    },
    {
      "epoch": 0.002989021095591194,
      "grad_norm": 2.95743727684021,
      "learning_rate": 5.850000000000001e-06,
      "loss": 10.1497,
      "step": 39
    },
    {
      "epoch": 0.003065662662144814,
      "grad_norm": 2.9404218196868896,
      "learning_rate": 6e-06,
      "loss": 10.1824,
      "step": 40
    },
    {
      "epoch": 0.0031423042286984346,
      "grad_norm": 3.076639413833618,
      "learning_rate": 6.1499999999999996e-06,
      "loss": 10.1815,
      "step": 41
    },
    {
      "epoch": 0.003218945795252055,
      "grad_norm": 3.1609745025634766,
      "learning_rate": 6.3e-06,
      "loss": 10.1391,
      "step": 42
    },
    {
      "epoch": 0.0032955873618056753,
      "grad_norm": 3.024962902069092,
      "learning_rate": 6.45e-06,
      "loss": 10.1044,
      "step": 43
    },
    {
      "epoch": 0.003372228928359296,
      "grad_norm": 2.7803852558135986,
      "learning_rate": 6.6e-06,
      "loss": 10.1082,
      "step": 44
    },
    {
      "epoch": 0.003448870494912916,
      "grad_norm": 2.9283249378204346,
      "learning_rate": 6.750000000000001e-06,
      "loss": 10.0209,
      "step": 45
    },
    {
      "epoch": 0.0035255120614665365,
      "grad_norm": 2.9342944622039795,
      "learning_rate": 6.900000000000001e-06,
      "loss": 10.1783,
      "step": 46
    },
    {
      "epoch": 0.0036021536280201566,
      "grad_norm": 2.911269187927246,
      "learning_rate": 7.049999999999999e-06,
      "loss": 10.1705,
      "step": 47
    },
    {
      "epoch": 0.003678795194573777,
      "grad_norm": 2.9178407192230225,
      "learning_rate": 7.2e-06,
      "loss": 10.185,
      "step": 48
    },
    {
      "epoch": 0.0037554367611273972,
      "grad_norm": 3.2789461612701416,
      "learning_rate": 7.35e-06,
      "loss": 10.1262,
      "step": 49
    },
    {
      "epoch": 0.003832078327681018,
      "grad_norm": 2.9491851329803467,
      "learning_rate": 7.5e-06,
      "loss": 9.9911,
      "step": 50
    },
    {
      "epoch": 0.003832078327681018,
      "eval_loss": 10.096914291381836,
      "eval_runtime": 417.99,
      "eval_samples_per_second": 52.575,
      "eval_steps_per_second": 6.572,
      "step": 50
    },
    {
      "epoch": 0.003908719894234638,
      "grad_norm": 2.9691355228424072,
      "learning_rate": 7.65e-06,
      "loss": 10.012,
      "step": 51
    },
    {
      "epoch": 0.003985361460788259,
      "grad_norm": 3.0408084392547607,
      "learning_rate": 7.8e-06,
      "loss": 10.1541,
      "step": 52
    },
    {
      "epoch": 0.0040620030273418786,
      "grad_norm": 2.865037441253662,
      "learning_rate": 7.95e-06,
      "loss": 10.1152,
      "step": 53
    },
    {
      "epoch": 0.004138644593895499,
      "grad_norm": 3.0118324756622314,
      "learning_rate": 8.1e-06,
      "loss": 10.056,
      "step": 54
    },
    {
      "epoch": 0.00421528616044912,
      "grad_norm": 3.0567305088043213,
      "learning_rate": 8.25e-06,
      "loss": 10.1187,
      "step": 55
    },
    {
      "epoch": 0.00429192772700274,
      "grad_norm": 3.090759038925171,
      "learning_rate": 8.400000000000001e-06,
      "loss": 9.9549,
      "step": 56
    },
    {
      "epoch": 0.00436856929355636,
      "grad_norm": 3.094413995742798,
      "learning_rate": 8.55e-06,
      "loss": 10.0912,
      "step": 57
    },
    {
      "epoch": 0.00444521086010998,
      "grad_norm": 2.8803794384002686,
      "learning_rate": 8.7e-06,
      "loss": 10.0612,
      "step": 58
    },
    {
      "epoch": 0.004521852426663601,
      "grad_norm": 3.1622092723846436,
      "learning_rate": 8.85e-06,
      "loss": 10.0883,
      "step": 59
    },
    {
      "epoch": 0.0045984939932172215,
      "grad_norm": 3.1270225048065186,
      "learning_rate": 9e-06,
      "loss": 10.0202,
      "step": 60
    },
    {
      "epoch": 0.004675135559770842,
      "grad_norm": 3.1323904991149902,
      "learning_rate": 9.15e-06,
      "loss": 9.9491,
      "step": 61
    },
    {
      "epoch": 0.004751777126324462,
      "grad_norm": 3.130385637283325,
      "learning_rate": 9.3e-06,
      "loss": 9.9419,
      "step": 62
    },
    {
      "epoch": 0.004828418692878082,
      "grad_norm": 2.9450523853302,
      "learning_rate": 9.450000000000001e-06,
      "loss": 9.9549,
      "step": 63
    },
    {
      "epoch": 0.004905060259431703,
      "grad_norm": 2.9594674110412598,
      "learning_rate": 9.600000000000001e-06,
      "loss": 9.9597,
      "step": 64
    },
    {
      "epoch": 0.004981701825985323,
      "grad_norm": 2.946688413619995,
      "learning_rate": 9.75e-06,
      "loss": 10.0721,
      "step": 65
    },
    {
      "epoch": 0.005058343392538944,
      "grad_norm": 3.045152425765991,
      "learning_rate": 9.9e-06,
      "loss": 9.8657,
      "step": 66
    },
    {
      "epoch": 0.005134984959092564,
      "grad_norm": 3.0098981857299805,
      "learning_rate": 1.005e-05,
      "loss": 9.8488,
      "step": 67
    },
    {
      "epoch": 0.005211626525646184,
      "grad_norm": 2.9197866916656494,
      "learning_rate": 1.02e-05,
      "loss": 9.858,
      "step": 68
    },
    {
      "epoch": 0.005288268092199805,
      "grad_norm": 3.026247501373291,
      "learning_rate": 1.035e-05,
      "loss": 9.9475,
      "step": 69
    },
    {
      "epoch": 0.005364909658753425,
      "grad_norm": 2.9125189781188965,
      "learning_rate": 1.05e-05,
      "loss": 9.9352,
      "step": 70
    },
    {
      "epoch": 0.005441551225307045,
      "grad_norm": 2.881605863571167,
      "learning_rate": 1.065e-05,
      "loss": 10.0641,
      "step": 71
    },
    {
      "epoch": 0.0055181927918606655,
      "grad_norm": 3.004376173019409,
      "learning_rate": 1.08e-05,
      "loss": 10.0225,
      "step": 72
    },
    {
      "epoch": 0.005594834358414286,
      "grad_norm": 3.101276159286499,
      "learning_rate": 1.095e-05,
      "loss": 9.9834,
      "step": 73
    },
    {
      "epoch": 0.0056714759249679066,
      "grad_norm": 2.9609551429748535,
      "learning_rate": 1.11e-05,
      "loss": 9.942,
      "step": 74
    },
    {
      "epoch": 0.005748117491521527,
      "grad_norm": 2.913710594177246,
      "learning_rate": 1.125e-05,
      "loss": 9.864,
      "step": 75
    },
    {
      "epoch": 0.005824759058075147,
      "grad_norm": 2.971576452255249,
      "learning_rate": 1.1400000000000001e-05,
      "loss": 9.9609,
      "step": 76
    },
    {
      "epoch": 0.005901400624628767,
      "grad_norm": 3.054107904434204,
      "learning_rate": 1.1550000000000001e-05,
      "loss": 10.0123,
      "step": 77
    },
    {
      "epoch": 0.005978042191182388,
      "grad_norm": 2.910504102706909,
      "learning_rate": 1.1700000000000001e-05,
      "loss": 9.8387,
      "step": 78
    },
    {
      "epoch": 0.006054683757736008,
      "grad_norm": 2.9695205688476562,
      "learning_rate": 1.185e-05,
      "loss": 9.8195,
      "step": 79
    },
    {
      "epoch": 0.006131325324289628,
      "grad_norm": 2.9118409156799316,
      "learning_rate": 1.2e-05,
      "loss": 9.7845,
      "step": 80
    },
    {
      "epoch": 0.006207966890843249,
      "grad_norm": 3.0323214530944824,
      "learning_rate": 1.215e-05,
      "loss": 9.8386,
      "step": 81
    },
    {
      "epoch": 0.006284608457396869,
      "grad_norm": 2.9126343727111816,
      "learning_rate": 1.2299999999999999e-05,
      "loss": 9.8635,
      "step": 82
    },
    {
      "epoch": 0.00636125002395049,
      "grad_norm": 3.027489185333252,
      "learning_rate": 1.245e-05,
      "loss": 9.8263,
      "step": 83
    },
    {
      "epoch": 0.00643789159050411,
      "grad_norm": 2.968306064605713,
      "learning_rate": 1.26e-05,
      "loss": 9.7821,
      "step": 84
    },
    {
      "epoch": 0.00651453315705773,
      "grad_norm": 3.212526321411133,
      "learning_rate": 1.275e-05,
      "loss": 9.8742,
      "step": 85
    },
    {
      "epoch": 0.0065911747236113505,
      "grad_norm": 3.0750510692596436,
      "learning_rate": 1.29e-05,
      "loss": 9.756,
      "step": 86
    },
    {
      "epoch": 0.006667816290164971,
      "grad_norm": 3.143045425415039,
      "learning_rate": 1.305e-05,
      "loss": 9.733,
      "step": 87
    },
    {
      "epoch": 0.006744457856718592,
      "grad_norm": 3.0339534282684326,
      "learning_rate": 1.32e-05,
      "loss": 9.7565,
      "step": 88
    },
    {
      "epoch": 0.006821099423272211,
      "grad_norm": 2.8683807849884033,
      "learning_rate": 1.3350000000000001e-05,
      "loss": 9.673,
      "step": 89
    },
    {
      "epoch": 0.006897740989825832,
      "grad_norm": 3.0948848724365234,
      "learning_rate": 1.3500000000000001e-05,
      "loss": 9.6999,
      "step": 90
    },
    {
      "epoch": 0.006974382556379452,
      "grad_norm": 3.123711347579956,
      "learning_rate": 1.3650000000000001e-05,
      "loss": 9.868,
      "step": 91
    },
    {
      "epoch": 0.007051024122933073,
      "grad_norm": 3.072702169418335,
      "learning_rate": 1.3800000000000002e-05,
      "loss": 9.6111,
      "step": 92
    },
    {
      "epoch": 0.0071276656894866935,
      "grad_norm": 3.133103609085083,
      "learning_rate": 1.395e-05,
      "loss": 9.7074,
      "step": 93
    },
    {
      "epoch": 0.007204307256040313,
      "grad_norm": 3.1256680488586426,
      "learning_rate": 1.4099999999999999e-05,
      "loss": 9.7523,
      "step": 94
    },
    {
      "epoch": 0.007280948822593934,
      "grad_norm": 3.0179288387298584,
      "learning_rate": 1.4249999999999999e-05,
      "loss": 9.6325,
      "step": 95
    },
    {
      "epoch": 0.007357590389147554,
      "grad_norm": 3.047670841217041,
      "learning_rate": 1.44e-05,
      "loss": 9.7347,
      "step": 96
    },
    {
      "epoch": 0.007434231955701175,
      "grad_norm": 3.1137807369232178,
      "learning_rate": 1.455e-05,
      "loss": 9.5914,
      "step": 97
    },
    {
      "epoch": 0.0075108735222547945,
      "grad_norm": 2.887342929840088,
      "learning_rate": 1.47e-05,
      "loss": 9.6417,
      "step": 98
    },
    {
      "epoch": 0.007587515088808415,
      "grad_norm": 3.202164888381958,
      "learning_rate": 1.485e-05,
      "loss": 9.4693,
      "step": 99
    },
    {
      "epoch": 0.007664156655362036,
      "grad_norm": 3.069445848464966,
      "learning_rate": 1.5e-05,
      "loss": 9.5667,
      "step": 100
    },
    {
      "epoch": 0.007664156655362036,
      "eval_loss": 9.585326194763184,
      "eval_runtime": 418.1777,
      "eval_samples_per_second": 52.552,
      "eval_steps_per_second": 6.569,
      "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": 2,
        "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": 130824536064000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}