{
  "best_metric": 0.022141076624393463,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.23323615160349853,
  "eval_steps": 25,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011661807580174927,
      "grad_norm": 2.554990291595459,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 4.0712,
      "step": 1
    },
    {
      "epoch": 0.0011661807580174927,
      "eval_loss": 1.4862829446792603,
      "eval_runtime": 3.9694,
      "eval_samples_per_second": 12.596,
      "eval_steps_per_second": 1.764,
      "step": 1
    },
    {
      "epoch": 0.0023323615160349854,
      "grad_norm": 2.956717014312744,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 4.5853,
      "step": 2
    },
    {
      "epoch": 0.003498542274052478,
      "grad_norm": 2.9694676399230957,
      "learning_rate": 8.999999999999999e-05,
      "loss": 4.8361,
      "step": 3
    },
    {
      "epoch": 0.004664723032069971,
      "grad_norm": 3.1446948051452637,
      "learning_rate": 0.00011999999999999999,
      "loss": 4.5491,
      "step": 4
    },
    {
      "epoch": 0.0058309037900874635,
      "grad_norm": 3.4145169258117676,
      "learning_rate": 0.00015,
      "loss": 4.1682,
      "step": 5
    },
    {
      "epoch": 0.006997084548104956,
      "grad_norm": 3.5542359352111816,
      "learning_rate": 0.00017999999999999998,
      "loss": 4.3101,
      "step": 6
    },
    {
      "epoch": 0.00816326530612245,
      "grad_norm": 3.1839475631713867,
      "learning_rate": 0.00020999999999999998,
      "loss": 3.5274,
      "step": 7
    },
    {
      "epoch": 0.009329446064139942,
      "grad_norm": 2.5565991401672363,
      "learning_rate": 0.00023999999999999998,
      "loss": 2.8382,
      "step": 8
    },
    {
      "epoch": 0.010495626822157435,
      "grad_norm": 2.105700969696045,
      "learning_rate": 0.00027,
      "loss": 2.4445,
      "step": 9
    },
    {
      "epoch": 0.011661807580174927,
      "grad_norm": 2.1994636058807373,
      "learning_rate": 0.0003,
      "loss": 1.9226,
      "step": 10
    },
    {
      "epoch": 0.01282798833819242,
      "grad_norm": 2.032122850418091,
      "learning_rate": 0.0002999794957488703,
      "loss": 1.7695,
      "step": 11
    },
    {
      "epoch": 0.013994169096209912,
      "grad_norm": 2.2895238399505615,
      "learning_rate": 0.0002999179886011389,
      "loss": 1.449,
      "step": 12
    },
    {
      "epoch": 0.015160349854227406,
      "grad_norm": 2.2719714641571045,
      "learning_rate": 0.0002998154953722457,
      "loss": 1.2782,
      "step": 13
    },
    {
      "epoch": 0.0163265306122449,
      "grad_norm": 2.4435462951660156,
      "learning_rate": 0.00029967204408281613,
      "loss": 1.1559,
      "step": 14
    },
    {
      "epoch": 0.01749271137026239,
      "grad_norm": 1.767961025238037,
      "learning_rate": 0.00029948767395100045,
      "loss": 0.934,
      "step": 15
    },
    {
      "epoch": 0.018658892128279883,
      "grad_norm": 1.5300686359405518,
      "learning_rate": 0.0002992624353817517,
      "loss": 0.8139,
      "step": 16
    },
    {
      "epoch": 0.019825072886297375,
      "grad_norm": 1.4481428861618042,
      "learning_rate": 0.0002989963899530457,
      "loss": 0.5988,
      "step": 17
    },
    {
      "epoch": 0.02099125364431487,
      "grad_norm": 1.2570189237594604,
      "learning_rate": 0.00029868961039904624,
      "loss": 0.517,
      "step": 18
    },
    {
      "epoch": 0.022157434402332362,
      "grad_norm": 1.2609643936157227,
      "learning_rate": 0.00029834218059022024,
      "loss": 0.5352,
      "step": 19
    },
    {
      "epoch": 0.023323615160349854,
      "grad_norm": 1.3622685670852661,
      "learning_rate": 0.00029795419551040833,
      "loss": 0.556,
      "step": 20
    },
    {
      "epoch": 0.024489795918367346,
      "grad_norm": 1.3317028284072876,
      "learning_rate": 0.00029752576123085736,
      "loss": 0.5296,
      "step": 21
    },
    {
      "epoch": 0.02565597667638484,
      "grad_norm": 1.7528598308563232,
      "learning_rate": 0.0002970569948812214,
      "loss": 0.4917,
      "step": 22
    },
    {
      "epoch": 0.026822157434402333,
      "grad_norm": 1.4835094213485718,
      "learning_rate": 0.0002965480246175399,
      "loss": 0.5714,
      "step": 23
    },
    {
      "epoch": 0.027988338192419825,
      "grad_norm": 1.1915653944015503,
      "learning_rate": 0.0002959989895872009,
      "loss": 0.4087,
      "step": 24
    },
    {
      "epoch": 0.029154518950437316,
      "grad_norm": 1.7672362327575684,
      "learning_rate": 0.0002954100398908995,
      "loss": 0.4552,
      "step": 25
    },
    {
      "epoch": 0.029154518950437316,
      "eval_loss": 0.10565981268882751,
      "eval_runtime": 4.003,
      "eval_samples_per_second": 12.491,
      "eval_steps_per_second": 1.749,
      "step": 25
    },
    {
      "epoch": 0.030320699708454812,
      "grad_norm": 1.1271257400512695,
      "learning_rate": 0.0002947813365416023,
      "loss": 0.4098,
      "step": 26
    },
    {
      "epoch": 0.0314868804664723,
      "grad_norm": 0.8774544596672058,
      "learning_rate": 0.0002941130514205272,
      "loss": 0.3692,
      "step": 27
    },
    {
      "epoch": 0.0326530612244898,
      "grad_norm": 1.4422640800476074,
      "learning_rate": 0.0002934053672301536,
      "loss": 0.3807,
      "step": 28
    },
    {
      "epoch": 0.03381924198250729,
      "grad_norm": 1.6437548398971558,
      "learning_rate": 0.00029265847744427303,
      "loss": 0.5096,
      "step": 29
    },
    {
      "epoch": 0.03498542274052478,
      "grad_norm": 1.068761944770813,
      "learning_rate": 0.00029187258625509513,
      "loss": 0.3511,
      "step": 30
    },
    {
      "epoch": 0.036151603498542274,
      "grad_norm": 1.1477739810943604,
      "learning_rate": 0.00029104790851742417,
      "loss": 0.2803,
      "step": 31
    },
    {
      "epoch": 0.037317784256559766,
      "grad_norm": 1.1783934831619263,
      "learning_rate": 0.0002901846696899191,
      "loss": 0.3285,
      "step": 32
    },
    {
      "epoch": 0.03848396501457726,
      "grad_norm": 1.0616635084152222,
      "learning_rate": 0.00028928310577345606,
      "loss": 0.3726,
      "step": 33
    },
    {
      "epoch": 0.03965014577259475,
      "grad_norm": 1.1421316862106323,
      "learning_rate": 0.0002883434632466077,
      "loss": 0.3735,
      "step": 34
    },
    {
      "epoch": 0.04081632653061224,
      "grad_norm": 1.1839216947555542,
      "learning_rate": 0.00028736599899825856,
      "loss": 0.3197,
      "step": 35
    },
    {
      "epoch": 0.04198250728862974,
      "grad_norm": 1.2092596292495728,
      "learning_rate": 0.00028635098025737434,
      "loss": 0.2477,
      "step": 36
    },
    {
      "epoch": 0.04314868804664723,
      "grad_norm": 0.8171605467796326,
      "learning_rate": 0.00028529868451994384,
      "loss": 0.2024,
      "step": 37
    },
    {
      "epoch": 0.044314868804664724,
      "grad_norm": 1.2580074071884155,
      "learning_rate": 0.0002842093994731145,
      "loss": 0.3252,
      "step": 38
    },
    {
      "epoch": 0.045481049562682216,
      "grad_norm": 1.0628515481948853,
      "learning_rate": 0.00028308342291654174,
      "loss": 0.2453,
      "step": 39
    },
    {
      "epoch": 0.04664723032069971,
      "grad_norm": 1.0713222026824951,
      "learning_rate": 0.00028192106268097334,
      "loss": 0.2456,
      "step": 40
    },
    {
      "epoch": 0.0478134110787172,
      "grad_norm": 0.8610000014305115,
      "learning_rate": 0.00028072263654409154,
      "loss": 0.208,
      "step": 41
    },
    {
      "epoch": 0.04897959183673469,
      "grad_norm": 1.1830765008926392,
      "learning_rate": 0.0002794884721436361,
      "loss": 0.2812,
      "step": 42
    },
    {
      "epoch": 0.05014577259475218,
      "grad_norm": 1.502504587173462,
      "learning_rate": 0.00027821890688783083,
      "loss": 0.3256,
      "step": 43
    },
    {
      "epoch": 0.05131195335276968,
      "grad_norm": 1.0644171237945557,
      "learning_rate": 0.0002769142878631403,
      "loss": 0.2005,
      "step": 44
    },
    {
      "epoch": 0.052478134110787174,
      "grad_norm": 1.3860845565795898,
      "learning_rate": 0.00027557497173937923,
      "loss": 0.3659,
      "step": 45
    },
    {
      "epoch": 0.053644314868804666,
      "grad_norm": 1.6274828910827637,
      "learning_rate": 0.000274201324672203,
      "loss": 0.2457,
      "step": 46
    },
    {
      "epoch": 0.05481049562682216,
      "grad_norm": 1.4343786239624023,
      "learning_rate": 0.00027279372220300385,
      "loss": 0.1633,
      "step": 47
    },
    {
      "epoch": 0.05597667638483965,
      "grad_norm": 1.486754059791565,
      "learning_rate": 0.0002713525491562421,
      "loss": 0.3238,
      "step": 48
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 1.6676969528198242,
      "learning_rate": 0.00026987819953423867,
      "loss": 0.2933,
      "step": 49
    },
    {
      "epoch": 0.05830903790087463,
      "grad_norm": 1.2559738159179688,
      "learning_rate": 0.00026837107640945905,
      "loss": 0.242,
      "step": 50
    },
    {
      "epoch": 0.05830903790087463,
      "eval_loss": 0.05707281455397606,
      "eval_runtime": 4.0058,
      "eval_samples_per_second": 12.482,
      "eval_steps_per_second": 1.747,
      "step": 50
    },
    {
      "epoch": 0.05947521865889213,
      "grad_norm": 1.1948297023773193,
      "learning_rate": 0.0002668315918143169,
      "loss": 0.2766,
      "step": 51
    },
    {
      "epoch": 0.060641399416909623,
      "grad_norm": 0.8477262258529663,
      "learning_rate": 0.00026526016662852886,
      "loss": 0.2336,
      "step": 52
    },
    {
      "epoch": 0.061807580174927115,
      "grad_norm": 0.8877068161964417,
      "learning_rate": 0.00026365723046405023,
      "loss": 0.2752,
      "step": 53
    },
    {
      "epoch": 0.0629737609329446,
      "grad_norm": 0.8205435872077942,
      "learning_rate": 0.0002620232215476231,
      "loss": 0.1893,
      "step": 54
    },
    {
      "epoch": 0.0641399416909621,
      "grad_norm": 0.7490160465240479,
      "learning_rate": 0.0002603585866009697,
      "loss": 0.1667,
      "step": 55
    },
    {
      "epoch": 0.0653061224489796,
      "grad_norm": 0.7503515481948853,
      "learning_rate": 0.00025866378071866334,
      "loss": 0.1956,
      "step": 56
    },
    {
      "epoch": 0.06647230320699708,
      "grad_norm": 0.6858531832695007,
      "learning_rate": 0.00025693926724370956,
      "loss": 0.1719,
      "step": 57
    },
    {
      "epoch": 0.06763848396501458,
      "grad_norm": 0.8311856985092163,
      "learning_rate": 0.00025518551764087326,
      "loss": 0.183,
      "step": 58
    },
    {
      "epoch": 0.06880466472303207,
      "grad_norm": 0.9343290328979492,
      "learning_rate": 0.00025340301136778483,
      "loss": 0.2954,
      "step": 59
    },
    {
      "epoch": 0.06997084548104957,
      "grad_norm": 0.5970677733421326,
      "learning_rate": 0.00025159223574386114,
      "loss": 0.1717,
      "step": 60
    },
    {
      "epoch": 0.07113702623906705,
      "grad_norm": 0.827585756778717,
      "learning_rate": 0.0002497536858170772,
      "loss": 0.1993,
      "step": 61
    },
    {
      "epoch": 0.07230320699708455,
      "grad_norm": 0.6803846955299377,
      "learning_rate": 0.00024788786422862526,
      "loss": 0.1745,
      "step": 62
    },
    {
      "epoch": 0.07346938775510205,
      "grad_norm": 0.7233137488365173,
      "learning_rate": 0.00024599528107549745,
      "loss": 0.152,
      "step": 63
    },
    {
      "epoch": 0.07463556851311953,
      "grad_norm": 0.7259588837623596,
      "learning_rate": 0.00024407645377103054,
      "loss": 0.1527,
      "step": 64
    },
    {
      "epoch": 0.07580174927113703,
      "grad_norm": 0.9491218328475952,
      "learning_rate": 0.00024213190690345018,
      "loss": 0.1799,
      "step": 65
    },
    {
      "epoch": 0.07696793002915452,
      "grad_norm": 0.690780520439148,
      "learning_rate": 0.00024016217209245374,
      "loss": 0.1717,
      "step": 66
    },
    {
      "epoch": 0.07813411078717201,
      "grad_norm": 0.9484719038009644,
      "learning_rate": 0.00023816778784387094,
      "loss": 0.1454,
      "step": 67
    },
    {
      "epoch": 0.0793002915451895,
      "grad_norm": 0.9980589151382446,
      "learning_rate": 0.0002361492994024415,
      "loss": 0.1507,
      "step": 68
    },
    {
      "epoch": 0.080466472303207,
      "grad_norm": 0.8357101082801819,
      "learning_rate": 0.0002341072586027509,
      "loss": 0.2017,
      "step": 69
    },
    {
      "epoch": 0.08163265306122448,
      "grad_norm": 0.48945724964141846,
      "learning_rate": 0.00023204222371836405,
      "loss": 0.1052,
      "step": 70
    },
    {
      "epoch": 0.08279883381924198,
      "grad_norm": 0.6741676330566406,
      "learning_rate": 0.00022995475930919905,
      "loss": 0.1291,
      "step": 71
    },
    {
      "epoch": 0.08396501457725948,
      "grad_norm": 1.096218228340149,
      "learning_rate": 0.00022784543606718227,
      "loss": 0.2207,
      "step": 72
    },
    {
      "epoch": 0.08513119533527697,
      "grad_norm": 0.6741714477539062,
      "learning_rate": 0.00022571483066022657,
      "loss": 0.153,
      "step": 73
    },
    {
      "epoch": 0.08629737609329446,
      "grad_norm": 0.7549245953559875,
      "learning_rate": 0.0002235635255745762,
      "loss": 0.1438,
      "step": 74
    },
    {
      "epoch": 0.08746355685131195,
      "grad_norm": 0.7919449210166931,
      "learning_rate": 0.00022139210895556104,
      "loss": 0.1413,
      "step": 75
    },
    {
      "epoch": 0.08746355685131195,
      "eval_loss": 0.03973253443837166,
      "eval_runtime": 4.0008,
      "eval_samples_per_second": 12.498,
      "eval_steps_per_second": 1.75,
      "step": 75
    },
    {
      "epoch": 0.08862973760932945,
      "grad_norm": 1.083053469657898,
      "learning_rate": 0.00021920117444680317,
      "loss": 0.2133,
      "step": 76
    },
    {
      "epoch": 0.08979591836734693,
      "grad_norm": 1.0475046634674072,
      "learning_rate": 0.00021699132102792097,
      "loss": 0.1902,
      "step": 77
    },
    {
      "epoch": 0.09096209912536443,
      "grad_norm": 0.6452376246452332,
      "learning_rate": 0.0002147631528507739,
      "loss": 0.1426,
      "step": 78
    },
    {
      "epoch": 0.09212827988338193,
      "grad_norm": 0.7142217755317688,
      "learning_rate": 0.00021251727907429355,
      "loss": 0.1283,
      "step": 79
    },
    {
      "epoch": 0.09329446064139942,
      "grad_norm": 0.7024627327919006,
      "learning_rate": 0.0002102543136979454,
      "loss": 0.1713,
      "step": 80
    },
    {
      "epoch": 0.09446064139941691,
      "grad_norm": 0.7869638800621033,
      "learning_rate": 0.0002079748753938678,
      "loss": 0.1799,
      "step": 81
    },
    {
      "epoch": 0.0956268221574344,
      "grad_norm": 0.7052518129348755,
      "learning_rate": 0.0002056795873377331,
      "loss": 0.1051,
      "step": 82
    },
    {
      "epoch": 0.0967930029154519,
      "grad_norm": 1.1069566011428833,
      "learning_rate": 0.00020336907703837748,
      "loss": 0.1352,
      "step": 83
    },
    {
      "epoch": 0.09795918367346938,
      "grad_norm": 0.91618812084198,
      "learning_rate": 0.00020104397616624645,
      "loss": 0.1072,
      "step": 84
    },
    {
      "epoch": 0.09912536443148688,
      "grad_norm": 0.8095090985298157,
      "learning_rate": 0.00019870492038070252,
      "loss": 0.1497,
      "step": 85
    },
    {
      "epoch": 0.10029154518950437,
      "grad_norm": 0.8736909031867981,
      "learning_rate": 0.0001963525491562421,
      "loss": 0.2094,
      "step": 86
    },
    {
      "epoch": 0.10145772594752187,
      "grad_norm": 0.7386978268623352,
      "learning_rate": 0.0001939875056076697,
      "loss": 0.1399,
      "step": 87
    },
    {
      "epoch": 0.10262390670553936,
      "grad_norm": 0.7307138442993164,
      "learning_rate": 0.00019161043631427666,
      "loss": 0.1094,
      "step": 88
    },
    {
      "epoch": 0.10379008746355685,
      "grad_norm": 0.6576569676399231,
      "learning_rate": 0.00018922199114307294,
      "loss": 0.0942,
      "step": 89
    },
    {
      "epoch": 0.10495626822157435,
      "grad_norm": 0.8513264656066895,
      "learning_rate": 0.00018682282307111987,
      "loss": 0.1392,
      "step": 90
    },
    {
      "epoch": 0.10612244897959183,
      "grad_norm": 1.0551713705062866,
      "learning_rate": 0.00018441358800701273,
      "loss": 0.1446,
      "step": 91
    },
    {
      "epoch": 0.10728862973760933,
      "grad_norm": 0.6383885145187378,
      "learning_rate": 0.00018199494461156203,
      "loss": 0.0923,
      "step": 92
    },
    {
      "epoch": 0.10845481049562682,
      "grad_norm": 0.7290708422660828,
      "learning_rate": 0.000179567554117722,
      "loss": 0.1174,
      "step": 93
    },
    {
      "epoch": 0.10962099125364431,
      "grad_norm": 0.9666843414306641,
      "learning_rate": 0.00017713208014981648,
      "loss": 0.2278,
      "step": 94
    },
    {
      "epoch": 0.11078717201166181,
      "grad_norm": 0.8649985790252686,
      "learning_rate": 0.00017468918854211007,
      "loss": 0.168,
      "step": 95
    },
    {
      "epoch": 0.1119533527696793,
      "grad_norm": 1.0846383571624756,
      "learning_rate": 0.00017223954715677627,
      "loss": 0.2659,
      "step": 96
    },
    {
      "epoch": 0.1131195335276968,
      "grad_norm": 1.0130985975265503,
      "learning_rate": 0.00016978382570131034,
      "loss": 0.1467,
      "step": 97
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 0.7710073590278625,
      "learning_rate": 0.00016732269554543794,
      "loss": 0.098,
      "step": 98
    },
    {
      "epoch": 0.11545189504373178,
      "grad_norm": 1.1743874549865723,
      "learning_rate": 0.00016485682953756942,
      "loss": 0.2133,
      "step": 99
    },
    {
      "epoch": 0.11661807580174927,
      "grad_norm": 1.0854040384292603,
      "learning_rate": 0.00016238690182084986,
      "loss": 0.1515,
      "step": 100
    },
    {
      "epoch": 0.11661807580174927,
      "eval_loss": 0.03872062638401985,
      "eval_runtime": 4.0032,
      "eval_samples_per_second": 12.49,
      "eval_steps_per_second": 1.749,
      "step": 100
    },
    {
      "epoch": 0.11778425655976676,
      "grad_norm": 0.8156564235687256,
      "learning_rate": 0.0001599135876488549,
      "loss": 0.1744,
      "step": 101
    },
    {
      "epoch": 0.11895043731778426,
      "grad_norm": 0.6660405397415161,
      "learning_rate": 0.00015743756320098332,
      "loss": 0.18,
      "step": 102
    },
    {
      "epoch": 0.12011661807580175,
      "grad_norm": 0.4631388187408447,
      "learning_rate": 0.0001549595053975962,
      "loss": 0.1118,
      "step": 103
    },
    {
      "epoch": 0.12128279883381925,
      "grad_norm": 0.4799237549304962,
      "learning_rate": 0.00015248009171495378,
      "loss": 0.1265,
      "step": 104
    },
    {
      "epoch": 0.12244897959183673,
      "grad_norm": 0.5591108202934265,
      "learning_rate": 0.00015,
      "loss": 0.1463,
      "step": 105
    },
    {
      "epoch": 0.12361516034985423,
      "grad_norm": 0.8220224380493164,
      "learning_rate": 0.00014751990828504622,
      "loss": 0.1581,
      "step": 106
    },
    {
      "epoch": 0.12478134110787172,
      "grad_norm": 0.5697378516197205,
      "learning_rate": 0.00014504049460240375,
      "loss": 0.1467,
      "step": 107
    },
    {
      "epoch": 0.1259475218658892,
      "grad_norm": 0.5734126567840576,
      "learning_rate": 0.00014256243679901663,
      "loss": 0.141,
      "step": 108
    },
    {
      "epoch": 0.1271137026239067,
      "grad_norm": 0.5020325779914856,
      "learning_rate": 0.00014008641235114508,
      "loss": 0.1339,
      "step": 109
    },
    {
      "epoch": 0.1282798833819242,
      "grad_norm": 0.8357808589935303,
      "learning_rate": 0.00013761309817915014,
      "loss": 0.1824,
      "step": 110
    },
    {
      "epoch": 0.1294460641399417,
      "grad_norm": 0.6975669860839844,
      "learning_rate": 0.00013514317046243058,
      "loss": 0.138,
      "step": 111
    },
    {
      "epoch": 0.1306122448979592,
      "grad_norm": 0.6384928226470947,
      "learning_rate": 0.00013267730445456208,
      "loss": 0.1614,
      "step": 112
    },
    {
      "epoch": 0.13177842565597667,
      "grad_norm": 0.7099884152412415,
      "learning_rate": 0.00013021617429868963,
      "loss": 0.1201,
      "step": 113
    },
    {
      "epoch": 0.13294460641399417,
      "grad_norm": 0.6534522771835327,
      "learning_rate": 0.00012776045284322368,
      "loss": 0.1675,
      "step": 114
    },
    {
      "epoch": 0.13411078717201166,
      "grad_norm": 0.8089350461959839,
      "learning_rate": 0.00012531081145788987,
      "loss": 0.1155,
      "step": 115
    },
    {
      "epoch": 0.13527696793002916,
      "grad_norm": 0.47548821568489075,
      "learning_rate": 0.00012286791985018355,
      "loss": 0.1038,
      "step": 116
    },
    {
      "epoch": 0.13644314868804663,
      "grad_norm": 0.46297696232795715,
      "learning_rate": 0.00012043244588227796,
      "loss": 0.0776,
      "step": 117
    },
    {
      "epoch": 0.13760932944606413,
      "grad_norm": 0.4016755223274231,
      "learning_rate": 0.00011800505538843798,
      "loss": 0.0749,
      "step": 118
    },
    {
      "epoch": 0.13877551020408163,
      "grad_norm": 0.47245705127716064,
      "learning_rate": 0.00011558641199298727,
      "loss": 0.0846,
      "step": 119
    },
    {
      "epoch": 0.13994169096209913,
      "grad_norm": 0.556612491607666,
      "learning_rate": 0.00011317717692888012,
      "loss": 0.114,
      "step": 120
    },
    {
      "epoch": 0.14110787172011663,
      "grad_norm": 0.517553985118866,
      "learning_rate": 0.00011077800885692702,
      "loss": 0.1155,
      "step": 121
    },
    {
      "epoch": 0.1422740524781341,
      "grad_norm": 0.48796433210372925,
      "learning_rate": 0.00010838956368572334,
      "loss": 0.0955,
      "step": 122
    },
    {
      "epoch": 0.1434402332361516,
      "grad_norm": 0.6439377069473267,
      "learning_rate": 0.0001060124943923303,
      "loss": 0.1209,
      "step": 123
    },
    {
      "epoch": 0.1446064139941691,
      "grad_norm": 0.46093374490737915,
      "learning_rate": 0.0001036474508437579,
      "loss": 0.0752,
      "step": 124
    },
    {
      "epoch": 0.1457725947521866,
      "grad_norm": 0.5111440420150757,
      "learning_rate": 0.00010129507961929748,
      "loss": 0.0929,
      "step": 125
    },
    {
      "epoch": 0.1457725947521866,
      "eval_loss": 0.026817088946700096,
      "eval_runtime": 4.0181,
      "eval_samples_per_second": 12.444,
      "eval_steps_per_second": 1.742,
      "step": 125
    },
    {
      "epoch": 0.1469387755102041,
      "grad_norm": 0.5236866474151611,
      "learning_rate": 9.895602383375353e-05,
      "loss": 0.1264,
      "step": 126
    },
    {
      "epoch": 0.14810495626822157,
      "grad_norm": 0.5848910212516785,
      "learning_rate": 9.663092296162251e-05,
      "loss": 0.0906,
      "step": 127
    },
    {
      "epoch": 0.14927113702623906,
      "grad_norm": 0.5240556001663208,
      "learning_rate": 9.432041266226686e-05,
      "loss": 0.0848,
      "step": 128
    },
    {
      "epoch": 0.15043731778425656,
      "grad_norm": 0.460149884223938,
      "learning_rate": 9.202512460613219e-05,
      "loss": 0.0839,
      "step": 129
    },
    {
      "epoch": 0.15160349854227406,
      "grad_norm": 0.39112961292266846,
      "learning_rate": 8.97456863020546e-05,
      "loss": 0.0738,
      "step": 130
    },
    {
      "epoch": 0.15276967930029153,
      "grad_norm": 0.6523007154464722,
      "learning_rate": 8.748272092570646e-05,
      "loss": 0.1582,
      "step": 131
    },
    {
      "epoch": 0.15393586005830903,
      "grad_norm": 0.6076743006706238,
      "learning_rate": 8.523684714922608e-05,
      "loss": 0.1167,
      "step": 132
    },
    {
      "epoch": 0.15510204081632653,
      "grad_norm": 0.602942943572998,
      "learning_rate": 8.300867897207903e-05,
      "loss": 0.1364,
      "step": 133
    },
    {
      "epoch": 0.15626822157434403,
      "grad_norm": 0.7307475805282593,
      "learning_rate": 8.079882555319684e-05,
      "loss": 0.1224,
      "step": 134
    },
    {
      "epoch": 0.15743440233236153,
      "grad_norm": 0.6195316910743713,
      "learning_rate": 7.860789104443896e-05,
      "loss": 0.1179,
      "step": 135
    },
    {
      "epoch": 0.158600583090379,
      "grad_norm": 0.7356706261634827,
      "learning_rate": 7.643647442542382e-05,
      "loss": 0.132,
      "step": 136
    },
    {
      "epoch": 0.1597667638483965,
      "grad_norm": 0.8393650650978088,
      "learning_rate": 7.428516933977347e-05,
      "loss": 0.1226,
      "step": 137
    },
    {
      "epoch": 0.160932944606414,
      "grad_norm": 0.682489812374115,
      "learning_rate": 7.215456393281776e-05,
      "loss": 0.087,
      "step": 138
    },
    {
      "epoch": 0.1620991253644315,
      "grad_norm": 0.7237318754196167,
      "learning_rate": 7.004524069080096e-05,
      "loss": 0.0832,
      "step": 139
    },
    {
      "epoch": 0.16326530612244897,
      "grad_norm": 0.5046043992042542,
      "learning_rate": 6.795777628163599e-05,
      "loss": 0.0652,
      "step": 140
    },
    {
      "epoch": 0.16443148688046647,
      "grad_norm": 0.6155825257301331,
      "learning_rate": 6.58927413972491e-05,
      "loss": 0.0933,
      "step": 141
    },
    {
      "epoch": 0.16559766763848396,
      "grad_norm": 0.7118250727653503,
      "learning_rate": 6.385070059755846e-05,
      "loss": 0.0742,
      "step": 142
    },
    {
      "epoch": 0.16676384839650146,
      "grad_norm": 0.8736699223518372,
      "learning_rate": 6.183221215612904e-05,
      "loss": 0.165,
      "step": 143
    },
    {
      "epoch": 0.16793002915451896,
      "grad_norm": 0.6333112716674805,
      "learning_rate": 5.983782790754623e-05,
      "loss": 0.0973,
      "step": 144
    },
    {
      "epoch": 0.16909620991253643,
      "grad_norm": 0.7457235455513,
      "learning_rate": 5.786809309654982e-05,
      "loss": 0.1133,
      "step": 145
    },
    {
      "epoch": 0.17026239067055393,
      "grad_norm": 0.6335854530334473,
      "learning_rate": 5.592354622896944e-05,
      "loss": 0.0979,
      "step": 146
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.737917423248291,
      "learning_rate": 5.40047189245025e-05,
      "loss": 0.1114,
      "step": 147
    },
    {
      "epoch": 0.17259475218658893,
      "grad_norm": 0.8127499222755432,
      "learning_rate": 5.211213577137469e-05,
      "loss": 0.1297,
      "step": 148
    },
    {
      "epoch": 0.17376093294460643,
      "grad_norm": 0.5944234132766724,
      "learning_rate": 5.024631418292274e-05,
      "loss": 0.0848,
      "step": 149
    },
    {
      "epoch": 0.1749271137026239,
      "grad_norm": 0.586091160774231,
      "learning_rate": 4.840776425613886e-05,
      "loss": 0.1056,
      "step": 150
    },
    {
      "epoch": 0.1749271137026239,
      "eval_loss": 0.02346547693014145,
      "eval_runtime": 4.0045,
      "eval_samples_per_second": 12.486,
      "eval_steps_per_second": 1.748,
      "step": 150
    },
    {
      "epoch": 0.1760932944606414,
      "grad_norm": 0.5324685573577881,
      "learning_rate": 4.659698863221513e-05,
      "loss": 0.1031,
      "step": 151
    },
    {
      "epoch": 0.1772594752186589,
      "grad_norm": 0.5855106115341187,
      "learning_rate": 4.481448235912671e-05,
      "loss": 0.1073,
      "step": 152
    },
    {
      "epoch": 0.1784256559766764,
      "grad_norm": 0.4815344214439392,
      "learning_rate": 4.306073275629044e-05,
      "loss": 0.0935,
      "step": 153
    },
    {
      "epoch": 0.17959183673469387,
      "grad_norm": 0.689025342464447,
      "learning_rate": 4.133621928133665e-05,
      "loss": 0.1476,
      "step": 154
    },
    {
      "epoch": 0.18075801749271136,
      "grad_norm": 0.5561751127243042,
      "learning_rate": 3.964141339903026e-05,
      "loss": 0.0755,
      "step": 155
    },
    {
      "epoch": 0.18192419825072886,
      "grad_norm": 0.8513990640640259,
      "learning_rate": 3.797677845237696e-05,
      "loss": 0.1196,
      "step": 156
    },
    {
      "epoch": 0.18309037900874636,
      "grad_norm": 0.31501975655555725,
      "learning_rate": 3.634276953594982e-05,
      "loss": 0.0691,
      "step": 157
    },
    {
      "epoch": 0.18425655976676386,
      "grad_norm": 0.7259876728057861,
      "learning_rate": 3.473983337147118e-05,
      "loss": 0.0916,
      "step": 158
    },
    {
      "epoch": 0.18542274052478133,
      "grad_norm": 0.4419352114200592,
      "learning_rate": 3.316840818568315e-05,
      "loss": 0.102,
      "step": 159
    },
    {
      "epoch": 0.18658892128279883,
      "grad_norm": 0.37751099467277527,
      "learning_rate": 3.162892359054098e-05,
      "loss": 0.068,
      "step": 160
    },
    {
      "epoch": 0.18775510204081633,
      "grad_norm": 0.392983615398407,
      "learning_rate": 3.0121800465761293e-05,
      "loss": 0.0571,
      "step": 161
    },
    {
      "epoch": 0.18892128279883383,
      "grad_norm": 0.43586814403533936,
      "learning_rate": 2.8647450843757897e-05,
      "loss": 0.0839,
      "step": 162
    },
    {
      "epoch": 0.1900874635568513,
      "grad_norm": 0.6984807848930359,
      "learning_rate": 2.7206277796996144e-05,
      "loss": 0.123,
      "step": 163
    },
    {
      "epoch": 0.1912536443148688,
      "grad_norm": 0.5872179865837097,
      "learning_rate": 2.5798675327796993e-05,
      "loss": 0.1425,
      "step": 164
    },
    {
      "epoch": 0.1924198250728863,
      "grad_norm": 1.0605107545852661,
      "learning_rate": 2.4425028260620715e-05,
      "loss": 0.0886,
      "step": 165
    },
    {
      "epoch": 0.1935860058309038,
      "grad_norm": 0.48068931698799133,
      "learning_rate": 2.3085712136859668e-05,
      "loss": 0.0962,
      "step": 166
    },
    {
      "epoch": 0.1947521865889213,
      "grad_norm": 0.461968332529068,
      "learning_rate": 2.178109311216913e-05,
      "loss": 0.0826,
      "step": 167
    },
    {
      "epoch": 0.19591836734693877,
      "grad_norm": 0.5407118201255798,
      "learning_rate": 2.0511527856363912e-05,
      "loss": 0.1119,
      "step": 168
    },
    {
      "epoch": 0.19708454810495626,
      "grad_norm": 0.5588830709457397,
      "learning_rate": 1.927736345590839e-05,
      "loss": 0.0869,
      "step": 169
    },
    {
      "epoch": 0.19825072886297376,
      "grad_norm": 0.5016293525695801,
      "learning_rate": 1.8078937319026654e-05,
      "loss": 0.0957,
      "step": 170
    },
    {
      "epoch": 0.19941690962099126,
      "grad_norm": 0.6214388608932495,
      "learning_rate": 1.6916577083458228e-05,
      "loss": 0.0993,
      "step": 171
    },
    {
      "epoch": 0.20058309037900873,
      "grad_norm": 0.7279790639877319,
      "learning_rate": 1.579060052688548e-05,
      "loss": 0.106,
      "step": 172
    },
    {
      "epoch": 0.20174927113702623,
      "grad_norm": 0.9763917326927185,
      "learning_rate": 1.4701315480056164e-05,
      "loss": 0.0949,
      "step": 173
    },
    {
      "epoch": 0.20291545189504373,
      "grad_norm": 0.6181830763816833,
      "learning_rate": 1.3649019742625623e-05,
      "loss": 0.0667,
      "step": 174
    },
    {
      "epoch": 0.20408163265306123,
      "grad_norm": 0.6389032602310181,
      "learning_rate": 1.2634001001741373e-05,
      "loss": 0.1028,
      "step": 175
    },
    {
      "epoch": 0.20408163265306123,
      "eval_loss": 0.02201712131500244,
      "eval_runtime": 4.0027,
      "eval_samples_per_second": 12.492,
      "eval_steps_per_second": 1.749,
      "step": 175
    },
    {
      "epoch": 0.20524781341107873,
      "grad_norm": 1.2925844192504883,
      "learning_rate": 1.1656536753392287e-05,
      "loss": 0.0852,
      "step": 176
    },
    {
      "epoch": 0.2064139941690962,
      "grad_norm": 0.5534648895263672,
      "learning_rate": 1.0716894226543953e-05,
      "loss": 0.0539,
      "step": 177
    },
    {
      "epoch": 0.2075801749271137,
      "grad_norm": 0.5580933094024658,
      "learning_rate": 9.815330310080887e-06,
      "loss": 0.0745,
      "step": 178
    },
    {
      "epoch": 0.2087463556851312,
      "grad_norm": 0.36139044165611267,
      "learning_rate": 8.952091482575824e-06,
      "loss": 0.0587,
      "step": 179
    },
    {
      "epoch": 0.2099125364431487,
      "grad_norm": 1.2585941553115845,
      "learning_rate": 8.127413744904804e-06,
      "loss": 0.1,
      "step": 180
    },
    {
      "epoch": 0.2110787172011662,
      "grad_norm": 0.5603790879249573,
      "learning_rate": 7.34152255572697e-06,
      "loss": 0.1171,
      "step": 181
    },
    {
      "epoch": 0.21224489795918366,
      "grad_norm": 0.6374752521514893,
      "learning_rate": 6.594632769846353e-06,
      "loss": 0.0884,
      "step": 182
    },
    {
      "epoch": 0.21341107871720116,
      "grad_norm": 0.6897931694984436,
      "learning_rate": 5.886948579472778e-06,
      "loss": 0.112,
      "step": 183
    },
    {
      "epoch": 0.21457725947521866,
      "grad_norm": 0.5416719913482666,
      "learning_rate": 5.218663458397715e-06,
      "loss": 0.0881,
      "step": 184
    },
    {
      "epoch": 0.21574344023323616,
      "grad_norm": 0.5751515030860901,
      "learning_rate": 4.589960109100444e-06,
      "loss": 0.0606,
      "step": 185
    },
    {
      "epoch": 0.21690962099125363,
      "grad_norm": 0.5498355031013489,
      "learning_rate": 4.001010412799138e-06,
      "loss": 0.0689,
      "step": 186
    },
    {
      "epoch": 0.21807580174927113,
      "grad_norm": 0.5167911052703857,
      "learning_rate": 3.451975382460109e-06,
      "loss": 0.0862,
      "step": 187
    },
    {
      "epoch": 0.21924198250728863,
      "grad_norm": 0.5562227368354797,
      "learning_rate": 2.9430051187785962e-06,
      "loss": 0.0787,
      "step": 188
    },
    {
      "epoch": 0.22040816326530613,
      "grad_norm": 0.40250152349472046,
      "learning_rate": 2.4742387691426445e-06,
      "loss": 0.051,
      "step": 189
    },
    {
      "epoch": 0.22157434402332363,
      "grad_norm": 0.9296673536300659,
      "learning_rate": 2.0458044895916513e-06,
      "loss": 0.1198,
      "step": 190
    },
    {
      "epoch": 0.2227405247813411,
      "grad_norm": 0.6195962429046631,
      "learning_rate": 1.6578194097797258e-06,
      "loss": 0.0652,
      "step": 191
    },
    {
      "epoch": 0.2239067055393586,
      "grad_norm": 0.9358689785003662,
      "learning_rate": 1.3103896009537207e-06,
      "loss": 0.1701,
      "step": 192
    },
    {
      "epoch": 0.2250728862973761,
      "grad_norm": 0.5886805653572083,
      "learning_rate": 1.0036100469542786e-06,
      "loss": 0.0877,
      "step": 193
    },
    {
      "epoch": 0.2262390670553936,
      "grad_norm": 0.7409729361534119,
      "learning_rate": 7.375646182482875e-07,
      "loss": 0.0589,
      "step": 194
    },
    {
      "epoch": 0.22740524781341107,
      "grad_norm": 0.8037596344947815,
      "learning_rate": 5.123260489995229e-07,
      "loss": 0.128,
      "step": 195
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 0.5771517157554626,
      "learning_rate": 3.2795591718381975e-07,
      "loss": 0.0986,
      "step": 196
    },
    {
      "epoch": 0.22973760932944606,
      "grad_norm": 0.8286700248718262,
      "learning_rate": 1.8450462775428942e-07,
      "loss": 0.1479,
      "step": 197
    },
    {
      "epoch": 0.23090379008746356,
      "grad_norm": 0.8538609743118286,
      "learning_rate": 8.201139886109264e-08,
      "loss": 0.1026,
      "step": 198
    },
    {
      "epoch": 0.23206997084548106,
      "grad_norm": 1.0193771123886108,
      "learning_rate": 2.0504251129649374e-08,
      "loss": 0.1886,
      "step": 199
    },
    {
      "epoch": 0.23323615160349853,
      "grad_norm": 0.727829098701477,
      "learning_rate": 0.0,
      "loss": 0.0868,
      "step": 200
    },
    {
      "epoch": 0.23323615160349853,
      "eval_loss": 0.022141076624393463,
      "eval_runtime": 4.0065,
      "eval_samples_per_second": 12.48,
      "eval_steps_per_second": 1.747,
      "step": 200
    }
  ],
  "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": 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": 1.5677350043398963e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}