{
  "best_metric": 2.357637882232666,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.9659038550145906,
  "eval_steps": 25,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009829519275072954,
      "grad_norm": 2.6821541786193848,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 3.4332,
      "step": 1
    },
    {
      "epoch": 0.009829519275072954,
      "eval_loss": 4.630801200866699,
      "eval_runtime": 0.698,
      "eval_samples_per_second": 71.632,
      "eval_steps_per_second": 18.624,
      "step": 1
    },
    {
      "epoch": 0.019659038550145908,
      "grad_norm": 3.109013319015503,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 3.6809,
      "step": 2
    },
    {
      "epoch": 0.02948855782521886,
      "grad_norm": 3.3269290924072266,
      "learning_rate": 5e-05,
      "loss": 3.8116,
      "step": 3
    },
    {
      "epoch": 0.039318077100291816,
      "grad_norm": 3.2339508533477783,
      "learning_rate": 6.666666666666667e-05,
      "loss": 3.7141,
      "step": 4
    },
    {
      "epoch": 0.04914759637536477,
      "grad_norm": 3.194000482559204,
      "learning_rate": 8.333333333333334e-05,
      "loss": 3.7467,
      "step": 5
    },
    {
      "epoch": 0.05897711565043772,
      "grad_norm": 3.2596042156219482,
      "learning_rate": 0.0001,
      "loss": 3.6488,
      "step": 6
    },
    {
      "epoch": 0.06880663492551067,
      "grad_norm": 2.7639877796173096,
      "learning_rate": 0.00011666666666666668,
      "loss": 3.4483,
      "step": 7
    },
    {
      "epoch": 0.07863615420058363,
      "grad_norm": 2.3510923385620117,
      "learning_rate": 0.00013333333333333334,
      "loss": 3.2237,
      "step": 8
    },
    {
      "epoch": 0.08846567347565658,
      "grad_norm": 2.3857412338256836,
      "learning_rate": 0.00015000000000000001,
      "loss": 3.289,
      "step": 9
    },
    {
      "epoch": 0.09829519275072954,
      "grad_norm": 3.4331414699554443,
      "learning_rate": 0.0001666666666666667,
      "loss": 3.1625,
      "step": 10
    },
    {
      "epoch": 0.10812471202580248,
      "grad_norm": 3.1604197025299072,
      "learning_rate": 0.00018333333333333334,
      "loss": 3.2429,
      "step": 11
    },
    {
      "epoch": 0.11795423130087544,
      "grad_norm": 2.682563304901123,
      "learning_rate": 0.0002,
      "loss": 3.4042,
      "step": 12
    },
    {
      "epoch": 0.1277837505759484,
      "grad_norm": 1.3882246017456055,
      "learning_rate": 0.00019999486177088252,
      "loss": 2.6979,
      "step": 13
    },
    {
      "epoch": 0.13761326985102135,
      "grad_norm": 1.0993757247924805,
      "learning_rate": 0.00019997944767022771,
      "loss": 2.5693,
      "step": 14
    },
    {
      "epoch": 0.1474427891260943,
      "grad_norm": 0.979709804058075,
      "learning_rate": 0.00019995375945806192,
      "loss": 2.5269,
      "step": 15
    },
    {
      "epoch": 0.15727230840116727,
      "grad_norm": 0.9595231413841248,
      "learning_rate": 0.00019991780006753883,
      "loss": 2.6667,
      "step": 16
    },
    {
      "epoch": 0.1671018276762402,
      "grad_norm": 0.832266092300415,
      "learning_rate": 0.0001998715736046049,
      "loss": 2.4709,
      "step": 17
    },
    {
      "epoch": 0.17693134695131316,
      "grad_norm": 1.0170220136642456,
      "learning_rate": 0.00019981508534753028,
      "loss": 2.4992,
      "step": 18
    },
    {
      "epoch": 0.18676086622638613,
      "grad_norm": 0.8332740068435669,
      "learning_rate": 0.00019974834174630622,
      "loss": 2.5776,
      "step": 19
    },
    {
      "epoch": 0.19659038550145908,
      "grad_norm": 0.8824642300605774,
      "learning_rate": 0.00019967135042190862,
      "loss": 2.5329,
      "step": 20
    },
    {
      "epoch": 0.20641990477653202,
      "grad_norm": 0.8353331089019775,
      "learning_rate": 0.00019958412016542784,
      "loss": 2.5575,
      "step": 21
    },
    {
      "epoch": 0.21624942405160497,
      "grad_norm": 0.9471293091773987,
      "learning_rate": 0.00019948666093706484,
      "loss": 2.6083,
      "step": 22
    },
    {
      "epoch": 0.22607894332667794,
      "grad_norm": 1.0592094659805298,
      "learning_rate": 0.00019937898386499393,
      "loss": 2.6781,
      "step": 23
    },
    {
      "epoch": 0.23590846260175088,
      "grad_norm": 1.2304210662841797,
      "learning_rate": 0.00019926110124409216,
      "loss": 2.7943,
      "step": 24
    },
    {
      "epoch": 0.24573798187682383,
      "grad_norm": 2.681989908218384,
      "learning_rate": 0.00019913302653453544,
      "loss": 3.2206,
      "step": 25
    },
    {
      "epoch": 0.24573798187682383,
      "eval_loss": 2.6977789402008057,
      "eval_runtime": 0.6963,
      "eval_samples_per_second": 71.804,
      "eval_steps_per_second": 18.669,
      "step": 25
    },
    {
      "epoch": 0.2555675011518968,
      "grad_norm": 1.0680567026138306,
      "learning_rate": 0.00019899477436026157,
      "loss": 2.386,
      "step": 26
    },
    {
      "epoch": 0.2653970204269697,
      "grad_norm": 1.146119236946106,
      "learning_rate": 0.00019884636050730055,
      "loss": 2.4147,
      "step": 27
    },
    {
      "epoch": 0.2752265397020427,
      "grad_norm": 1.0828416347503662,
      "learning_rate": 0.00019868780192197182,
      "loss": 2.4808,
      "step": 28
    },
    {
      "epoch": 0.28505605897711567,
      "grad_norm": 1.0389188528060913,
      "learning_rate": 0.00019851911670894977,
      "loss": 2.4491,
      "step": 29
    },
    {
      "epoch": 0.2948855782521886,
      "grad_norm": 0.9195923805236816,
      "learning_rate": 0.0001983403241291959,
      "loss": 2.3826,
      "step": 30
    },
    {
      "epoch": 0.30471509752726156,
      "grad_norm": 0.8912298083305359,
      "learning_rate": 0.00019815144459776,
      "loss": 2.4857,
      "step": 31
    },
    {
      "epoch": 0.31454461680233453,
      "grad_norm": 0.8696074485778809,
      "learning_rate": 0.00019795249968144896,
      "loss": 2.4644,
      "step": 32
    },
    {
      "epoch": 0.32437413607740745,
      "grad_norm": 0.8864859938621521,
      "learning_rate": 0.00019774351209636413,
      "loss": 2.5214,
      "step": 33
    },
    {
      "epoch": 0.3342036553524804,
      "grad_norm": 0.9830371737480164,
      "learning_rate": 0.0001975245057053076,
      "loss": 2.5429,
      "step": 34
    },
    {
      "epoch": 0.3440331746275534,
      "grad_norm": 1.0698072910308838,
      "learning_rate": 0.00019729550551505752,
      "loss": 2.655,
      "step": 35
    },
    {
      "epoch": 0.3538626939026263,
      "grad_norm": 1.177764892578125,
      "learning_rate": 0.00019705653767351265,
      "loss": 2.6462,
      "step": 36
    },
    {
      "epoch": 0.3636922131776993,
      "grad_norm": 1.5564563274383545,
      "learning_rate": 0.00019680762946670683,
      "loss": 2.8865,
      "step": 37
    },
    {
      "epoch": 0.37352173245277226,
      "grad_norm": 1.0166500806808472,
      "learning_rate": 0.0001965488093156933,
      "loss": 2.3889,
      "step": 38
    },
    {
      "epoch": 0.3833512517278452,
      "grad_norm": 0.7780814170837402,
      "learning_rate": 0.00019628010677329947,
      "loss": 2.22,
      "step": 39
    },
    {
      "epoch": 0.39318077100291815,
      "grad_norm": 0.7663058638572693,
      "learning_rate": 0.00019600155252075268,
      "loss": 2.2794,
      "step": 40
    },
    {
      "epoch": 0.40301029027799107,
      "grad_norm": 0.9589061737060547,
      "learning_rate": 0.0001957131783641767,
      "loss": 2.4648,
      "step": 41
    },
    {
      "epoch": 0.41283980955306404,
      "grad_norm": 0.8198392391204834,
      "learning_rate": 0.00019541501723096017,
      "loss": 2.4522,
      "step": 42
    },
    {
      "epoch": 0.422669328828137,
      "grad_norm": 0.7783530354499817,
      "learning_rate": 0.0001951071031659968,
      "loss": 2.4004,
      "step": 43
    },
    {
      "epoch": 0.43249884810320993,
      "grad_norm": 0.9277461767196655,
      "learning_rate": 0.000194789471327798,
      "loss": 2.4421,
      "step": 44
    },
    {
      "epoch": 0.4423283673782829,
      "grad_norm": 0.8785288333892822,
      "learning_rate": 0.00019446215798447845,
      "loss": 2.3626,
      "step": 45
    },
    {
      "epoch": 0.4521578866533559,
      "grad_norm": 0.9237145781517029,
      "learning_rate": 0.00019412520050961481,
      "loss": 2.4119,
      "step": 46
    },
    {
      "epoch": 0.4619874059284288,
      "grad_norm": 0.9750041961669922,
      "learning_rate": 0.00019377863737797839,
      "loss": 2.4959,
      "step": 47
    },
    {
      "epoch": 0.47181692520350177,
      "grad_norm": 1.1339645385742188,
      "learning_rate": 0.00019342250816114197,
      "loss": 2.4285,
      "step": 48
    },
    {
      "epoch": 0.48164644447857474,
      "grad_norm": 1.3169782161712646,
      "learning_rate": 0.00019305685352296134,
      "loss": 2.667,
      "step": 49
    },
    {
      "epoch": 0.49147596375364766,
      "grad_norm": 2.7065019607543945,
      "learning_rate": 0.00019268171521493225,
      "loss": 3.0527,
      "step": 50
    },
    {
      "epoch": 0.49147596375364766,
      "eval_loss": 2.54618239402771,
      "eval_runtime": 0.6959,
      "eval_samples_per_second": 71.852,
      "eval_steps_per_second": 18.682,
      "step": 50
    },
    {
      "epoch": 0.5013054830287206,
      "grad_norm": 1.095455288887024,
      "learning_rate": 0.0001922971360714231,
      "loss": 2.2371,
      "step": 51
    },
    {
      "epoch": 0.5111350023037936,
      "grad_norm": 0.9260361790657043,
      "learning_rate": 0.00019190316000478402,
      "loss": 2.3674,
      "step": 52
    },
    {
      "epoch": 0.5209645215788665,
      "grad_norm": 0.8077250123023987,
      "learning_rate": 0.0001914998320003326,
      "loss": 2.3025,
      "step": 53
    },
    {
      "epoch": 0.5307940408539394,
      "grad_norm": 0.8684698939323425,
      "learning_rate": 0.00019108719811121772,
      "loss": 2.3124,
      "step": 54
    },
    {
      "epoch": 0.5406235601290125,
      "grad_norm": 1.095186471939087,
      "learning_rate": 0.0001906653054531608,
      "loss": 2.3331,
      "step": 55
    },
    {
      "epoch": 0.5504530794040854,
      "grad_norm": 1.0066113471984863,
      "learning_rate": 0.00019023420219907607,
      "loss": 2.3205,
      "step": 56
    },
    {
      "epoch": 0.5602825986791583,
      "grad_norm": 0.84846431016922,
      "learning_rate": 0.00018979393757357003,
      "loss": 2.3889,
      "step": 57
    },
    {
      "epoch": 0.5701121179542313,
      "grad_norm": 0.8877599835395813,
      "learning_rate": 0.00018934456184732082,
      "loss": 2.3474,
      "step": 58
    },
    {
      "epoch": 0.5799416372293043,
      "grad_norm": 1.066555142402649,
      "learning_rate": 0.00018888612633133827,
      "loss": 2.4563,
      "step": 59
    },
    {
      "epoch": 0.5897711565043772,
      "grad_norm": 1.1691265106201172,
      "learning_rate": 0.00018841868337110508,
      "loss": 2.4273,
      "step": 60
    },
    {
      "epoch": 0.5996006757794502,
      "grad_norm": 1.2215334177017212,
      "learning_rate": 0.0001879422863405995,
      "loss": 2.4515,
      "step": 61
    },
    {
      "epoch": 0.6094301950545231,
      "grad_norm": 1.5334198474884033,
      "learning_rate": 0.00018745698963620145,
      "loss": 2.7499,
      "step": 62
    },
    {
      "epoch": 0.619259714329596,
      "grad_norm": 0.930508553981781,
      "learning_rate": 0.00018696284867048118,
      "loss": 2.3011,
      "step": 63
    },
    {
      "epoch": 0.6290892336046691,
      "grad_norm": 0.732704222202301,
      "learning_rate": 0.00018645991986587185,
      "loss": 2.2053,
      "step": 64
    },
    {
      "epoch": 0.638918752879742,
      "grad_norm": 0.7689364552497864,
      "learning_rate": 0.0001859482606482275,
      "loss": 2.2696,
      "step": 65
    },
    {
      "epoch": 0.6487482721548149,
      "grad_norm": 0.8270861506462097,
      "learning_rate": 0.00018542792944026566,
      "loss": 2.3104,
      "step": 66
    },
    {
      "epoch": 0.6585777914298879,
      "grad_norm": 0.8585655689239502,
      "learning_rate": 0.00018489898565489664,
      "loss": 2.2854,
      "step": 67
    },
    {
      "epoch": 0.6684073107049608,
      "grad_norm": 0.958391010761261,
      "learning_rate": 0.00018436148968843956,
      "loss": 2.3815,
      "step": 68
    },
    {
      "epoch": 0.6782368299800338,
      "grad_norm": 0.8035868406295776,
      "learning_rate": 0.00018381550291372603,
      "loss": 2.3304,
      "step": 69
    },
    {
      "epoch": 0.6880663492551068,
      "grad_norm": 0.8527224063873291,
      "learning_rate": 0.00018326108767309266,
      "loss": 2.2976,
      "step": 70
    },
    {
      "epoch": 0.6978958685301797,
      "grad_norm": 1.0419751405715942,
      "learning_rate": 0.00018269830727126233,
      "loss": 2.3254,
      "step": 71
    },
    {
      "epoch": 0.7077253878052526,
      "grad_norm": 1.060821533203125,
      "learning_rate": 0.0001821272259681161,
      "loss": 2.3873,
      "step": 72
    },
    {
      "epoch": 0.7175549070803257,
      "grad_norm": 1.11903977394104,
      "learning_rate": 0.00018154790897135581,
      "loss": 2.425,
      "step": 73
    },
    {
      "epoch": 0.7273844263553986,
      "grad_norm": 1.2984219789505005,
      "learning_rate": 0.00018096042242905832,
      "loss": 2.5535,
      "step": 74
    },
    {
      "epoch": 0.7372139456304715,
      "grad_norm": 2.152036428451538,
      "learning_rate": 0.00018036483342212268,
      "loss": 2.8375,
      "step": 75
    },
    {
      "epoch": 0.7372139456304715,
      "eval_loss": 2.4736454486846924,
      "eval_runtime": 0.6958,
      "eval_samples_per_second": 71.864,
      "eval_steps_per_second": 18.685,
      "step": 75
    },
    {
      "epoch": 0.7470434649055445,
      "grad_norm": 0.7806919813156128,
      "learning_rate": 0.00017976120995661068,
      "loss": 2.2532,
      "step": 76
    },
    {
      "epoch": 0.7568729841806174,
      "grad_norm": 0.7151602506637573,
      "learning_rate": 0.00017914962095598151,
      "loss": 2.2544,
      "step": 77
    },
    {
      "epoch": 0.7667025034556904,
      "grad_norm": 0.7725361585617065,
      "learning_rate": 0.0001785301362532221,
      "loss": 2.2388,
      "step": 78
    },
    {
      "epoch": 0.7765320227307633,
      "grad_norm": 0.8105177879333496,
      "learning_rate": 0.00017790282658287332,
      "loss": 2.3032,
      "step": 79
    },
    {
      "epoch": 0.7863615420058363,
      "grad_norm": 0.8750107884407043,
      "learning_rate": 0.00017726776357295318,
      "loss": 2.252,
      "step": 80
    },
    {
      "epoch": 0.7961910612809092,
      "grad_norm": 0.8127192854881287,
      "learning_rate": 0.0001766250197367784,
      "loss": 2.3539,
      "step": 81
    },
    {
      "epoch": 0.8060205805559821,
      "grad_norm": 0.8602331280708313,
      "learning_rate": 0.00017597466846468437,
      "loss": 2.3433,
      "step": 82
    },
    {
      "epoch": 0.8158500998310552,
      "grad_norm": 0.8889239430427551,
      "learning_rate": 0.0001753167840156454,
      "loss": 2.3318,
      "step": 83
    },
    {
      "epoch": 0.8256796191061281,
      "grad_norm": 1.038681149482727,
      "learning_rate": 0.00017465144150879548,
      "loss": 2.4018,
      "step": 84
    },
    {
      "epoch": 0.835509138381201,
      "grad_norm": 1.0794991254806519,
      "learning_rate": 0.00017397871691485117,
      "loss": 2.3722,
      "step": 85
    },
    {
      "epoch": 0.845338657656274,
      "grad_norm": 1.2361195087432861,
      "learning_rate": 0.00017329868704743677,
      "loss": 2.4939,
      "step": 86
    },
    {
      "epoch": 0.855168176931347,
      "grad_norm": 1.5107554197311401,
      "learning_rate": 0.0001726114295543138,
      "loss": 2.6408,
      "step": 87
    },
    {
      "epoch": 0.8649976962064199,
      "grad_norm": 0.9424665570259094,
      "learning_rate": 0.00017191702290851469,
      "loss": 2.2892,
      "step": 88
    },
    {
      "epoch": 0.8748272154814929,
      "grad_norm": 0.8208919763565063,
      "learning_rate": 0.00017121554639938272,
      "loss": 2.2319,
      "step": 89
    },
    {
      "epoch": 0.8846567347565658,
      "grad_norm": 0.811772882938385,
      "learning_rate": 0.00017050708012351852,
      "loss": 2.1431,
      "step": 90
    },
    {
      "epoch": 0.8944862540316387,
      "grad_norm": 0.7872000336647034,
      "learning_rate": 0.00016979170497563416,
      "loss": 2.3565,
      "step": 91
    },
    {
      "epoch": 0.9043157733067118,
      "grad_norm": 0.8809075355529785,
      "learning_rate": 0.00016906950263931663,
      "loss": 2.3408,
      "step": 92
    },
    {
      "epoch": 0.9141452925817847,
      "grad_norm": 0.8811956644058228,
      "learning_rate": 0.00016834055557770096,
      "loss": 2.2743,
      "step": 93
    },
    {
      "epoch": 0.9239748118568576,
      "grad_norm": 0.8447458148002625,
      "learning_rate": 0.00016760494702405416,
      "loss": 2.2628,
      "step": 94
    },
    {
      "epoch": 0.9338043311319306,
      "grad_norm": 0.8538081049919128,
      "learning_rate": 0.00016686276097227154,
      "loss": 2.2477,
      "step": 95
    },
    {
      "epoch": 0.9436338504070035,
      "grad_norm": 0.895717442035675,
      "learning_rate": 0.00016611408216728603,
      "loss": 2.3793,
      "step": 96
    },
    {
      "epoch": 0.9534633696820765,
      "grad_norm": 1.01509428024292,
      "learning_rate": 0.00016535899609539177,
      "loss": 2.3649,
      "step": 97
    },
    {
      "epoch": 0.9632928889571495,
      "grad_norm": 1.1379575729370117,
      "learning_rate": 0.00016459758897448298,
      "loss": 2.4999,
      "step": 98
    },
    {
      "epoch": 0.9731224082322224,
      "grad_norm": 1.2544729709625244,
      "learning_rate": 0.00016382994774420947,
      "loss": 2.4487,
      "step": 99
    },
    {
      "epoch": 0.9829519275072953,
      "grad_norm": 2.1138370037078857,
      "learning_rate": 0.0001630561600560494,
      "loss": 2.8294,
      "step": 100
    },
    {
      "epoch": 0.9829519275072953,
      "eval_loss": 2.4398374557495117,
      "eval_runtime": 0.6951,
      "eval_samples_per_second": 71.931,
      "eval_steps_per_second": 18.702,
      "step": 100
    },
    {
      "epoch": 0.9927814467823683,
      "grad_norm": 0.9641188383102417,
      "learning_rate": 0.00016227631426330124,
      "loss": 2.2486,
      "step": 101
    },
    {
      "epoch": 1.0026109660574412,
      "grad_norm": 1.2361067533493042,
      "learning_rate": 0.00016149049941099528,
      "loss": 3.1568,
      "step": 102
    },
    {
      "epoch": 1.0124404853325142,
      "grad_norm": 0.6794304251670837,
      "learning_rate": 0.00016069880522572597,
      "loss": 2.0051,
      "step": 103
    },
    {
      "epoch": 1.0222700046075872,
      "grad_norm": 0.7373532056808472,
      "learning_rate": 0.00015990132210540707,
      "loss": 2.1212,
      "step": 104
    },
    {
      "epoch": 1.03209952388266,
      "grad_norm": 0.7815002202987671,
      "learning_rate": 0.00015909814110894938,
      "loss": 2.1963,
      "step": 105
    },
    {
      "epoch": 1.041929043157733,
      "grad_norm": 0.8411288261413574,
      "learning_rate": 0.00015828935394586365,
      "loss": 2.108,
      "step": 106
    },
    {
      "epoch": 1.051758562432806,
      "grad_norm": 0.9140182137489319,
      "learning_rate": 0.00015747505296578884,
      "loss": 2.014,
      "step": 107
    },
    {
      "epoch": 1.0615880817078789,
      "grad_norm": 0.8995840549468994,
      "learning_rate": 0.0001566553311479473,
      "loss": 2.1216,
      "step": 108
    },
    {
      "epoch": 1.071417600982952,
      "grad_norm": 0.8572644591331482,
      "learning_rate": 0.0001558302820905281,
      "loss": 2.1224,
      "step": 109
    },
    {
      "epoch": 1.081247120258025,
      "grad_norm": 0.8983514904975891,
      "learning_rate": 0.000155,
      "loss": 2.0613,
      "step": 110
    },
    {
      "epoch": 1.0910766395330977,
      "grad_norm": 1.0163862705230713,
      "learning_rate": 0.00015416457968035443,
      "loss": 2.0615,
      "step": 111
    },
    {
      "epoch": 1.1009061588081708,
      "grad_norm": 1.1525602340698242,
      "learning_rate": 0.0001533241165222805,
      "loss": 2.0906,
      "step": 112
    },
    {
      "epoch": 1.1107356780832438,
      "grad_norm": 1.3764214515686035,
      "learning_rate": 0.00015247870649227308,
      "loss": 2.1388,
      "step": 113
    },
    {
      "epoch": 1.1205651973583166,
      "grad_norm": 1.391831398010254,
      "learning_rate": 0.0001516284461216752,
      "loss": 1.7508,
      "step": 114
    },
    {
      "epoch": 1.1303947166333896,
      "grad_norm": 1.578629970550537,
      "learning_rate": 0.00015077343249565554,
      "loss": 2.4968,
      "step": 115
    },
    {
      "epoch": 1.1402242359084627,
      "grad_norm": 1.0895462036132812,
      "learning_rate": 0.0001499137632421232,
      "loss": 2.0435,
      "step": 116
    },
    {
      "epoch": 1.1500537551835355,
      "grad_norm": 1.0212132930755615,
      "learning_rate": 0.00014904953652058022,
      "loss": 2.0891,
      "step": 117
    },
    {
      "epoch": 1.1598832744586085,
      "grad_norm": 0.9461895227432251,
      "learning_rate": 0.00014818085101091336,
      "loss": 2.1364,
      "step": 118
    },
    {
      "epoch": 1.1697127937336815,
      "grad_norm": 0.8605825901031494,
      "learning_rate": 0.0001473078059021266,
      "loss": 2.0956,
      "step": 119
    },
    {
      "epoch": 1.1795423130087543,
      "grad_norm": 1.0641827583312988,
      "learning_rate": 0.00014643050088101545,
      "loss": 1.984,
      "step": 120
    },
    {
      "epoch": 1.1893718322838274,
      "grad_norm": 0.9965870380401611,
      "learning_rate": 0.00014554903612078448,
      "loss": 2.0469,
      "step": 121
    },
    {
      "epoch": 1.1992013515589004,
      "grad_norm": 1.0630478858947754,
      "learning_rate": 0.00014466351226960917,
      "loss": 2.0305,
      "step": 122
    },
    {
      "epoch": 1.2090308708339732,
      "grad_norm": 1.062567949295044,
      "learning_rate": 0.0001437740304391437,
      "loss": 2.024,
      "step": 123
    },
    {
      "epoch": 1.2188603901090462,
      "grad_norm": 1.1082484722137451,
      "learning_rate": 0.0001428806921929756,
      "loss": 2.0846,
      "step": 124
    },
    {
      "epoch": 1.2286899093841193,
      "grad_norm": 1.236946702003479,
      "learning_rate": 0.000141983599535029,
      "loss": 1.9621,
      "step": 125
    },
    {
      "epoch": 1.2286899093841193,
      "eval_loss": 2.4299097061157227,
      "eval_runtime": 0.6964,
      "eval_samples_per_second": 71.798,
      "eval_steps_per_second": 18.667,
      "step": 125
    },
    {
      "epoch": 1.238519428659192,
      "grad_norm": 1.6171234846115112,
      "learning_rate": 0.00014108285489791768,
      "loss": 2.2414,
      "step": 126
    },
    {
      "epoch": 1.248348947934265,
      "grad_norm": 2.209141254425049,
      "learning_rate": 0.0001401785611312488,
      "loss": 2.4781,
      "step": 127
    },
    {
      "epoch": 1.2581784672093381,
      "grad_norm": 1.0709174871444702,
      "learning_rate": 0.00013927082148987925,
      "loss": 1.9901,
      "step": 128
    },
    {
      "epoch": 1.268007986484411,
      "grad_norm": 1.1437026262283325,
      "learning_rate": 0.0001383597396221259,
      "loss": 1.9849,
      "step": 129
    },
    {
      "epoch": 1.277837505759484,
      "grad_norm": 1.181343674659729,
      "learning_rate": 0.00013744541955793045,
      "loss": 2.0997,
      "step": 130
    },
    {
      "epoch": 1.287667025034557,
      "grad_norm": 1.113682508468628,
      "learning_rate": 0.0001365279656969814,
      "loss": 2.0418,
      "step": 131
    },
    {
      "epoch": 1.2974965443096298,
      "grad_norm": 1.067321538925171,
      "learning_rate": 0.0001356074827967929,
      "loss": 2.0363,
      "step": 132
    },
    {
      "epoch": 1.3073260635847028,
      "grad_norm": 0.9680085182189941,
      "learning_rate": 0.00013468407596074376,
      "loss": 2.0136,
      "step": 133
    },
    {
      "epoch": 1.3171555828597756,
      "grad_norm": 1.076326608657837,
      "learning_rate": 0.0001337578506260759,
      "loss": 2.03,
      "step": 134
    },
    {
      "epoch": 1.3269851021348487,
      "grad_norm": 1.0561034679412842,
      "learning_rate": 0.00013282891255185565,
      "loss": 1.9895,
      "step": 135
    },
    {
      "epoch": 1.3368146214099217,
      "grad_norm": 1.1942148208618164,
      "learning_rate": 0.0001318973678068978,
      "loss": 2.0359,
      "step": 136
    },
    {
      "epoch": 1.3466441406849947,
      "grad_norm": 1.1791845560073853,
      "learning_rate": 0.00013096332275765407,
      "loss": 2.0042,
      "step": 137
    },
    {
      "epoch": 1.3564736599600675,
      "grad_norm": 1.4035441875457764,
      "learning_rate": 0.00013002688405606828,
      "loss": 2.1086,
      "step": 138
    },
    {
      "epoch": 1.3663031792351406,
      "grad_norm": 1.4087142944335938,
      "learning_rate": 0.00012908815862739835,
      "loss": 1.7052,
      "step": 139
    },
    {
      "epoch": 1.3761326985102134,
      "grad_norm": 1.3538085222244263,
      "learning_rate": 0.00012814725365800698,
      "loss": 2.5688,
      "step": 140
    },
    {
      "epoch": 1.3859622177852864,
      "grad_norm": 0.9382008910179138,
      "learning_rate": 0.00012720427658312352,
      "loss": 2.0208,
      "step": 141
    },
    {
      "epoch": 1.3957917370603594,
      "grad_norm": 0.8642036318778992,
      "learning_rate": 0.0001262593350745759,
      "loss": 2.0409,
      "step": 142
    },
    {
      "epoch": 1.4056212563354324,
      "grad_norm": 0.9334009289741516,
      "learning_rate": 0.00012531253702849696,
      "loss": 2.028,
      "step": 143
    },
    {
      "epoch": 1.4154507756105053,
      "grad_norm": 0.9900059700012207,
      "learning_rate": 0.00012436399055300415,
      "loss": 2.0542,
      "step": 144
    },
    {
      "epoch": 1.4252802948855783,
      "grad_norm": 1.1152311563491821,
      "learning_rate": 0.0001234138039558557,
      "loss": 2.0503,
      "step": 145
    },
    {
      "epoch": 1.435109814160651,
      "grad_norm": 1.132704496383667,
      "learning_rate": 0.00012246208573208367,
      "loss": 2.019,
      "step": 146
    },
    {
      "epoch": 1.4449393334357241,
      "grad_norm": 1.0074613094329834,
      "learning_rate": 0.00012150894455160555,
      "loss": 1.9423,
      "step": 147
    },
    {
      "epoch": 1.4547688527107971,
      "grad_norm": 1.2089931964874268,
      "learning_rate": 0.00012055448924681618,
      "loss": 2.0784,
      "step": 148
    },
    {
      "epoch": 1.4645983719858702,
      "grad_norm": 1.1703325510025024,
      "learning_rate": 0.00011959882880016083,
      "loss": 1.9828,
      "step": 149
    },
    {
      "epoch": 1.474427891260943,
      "grad_norm": 1.3632087707519531,
      "learning_rate": 0.00011864207233169136,
      "loss": 2.1095,
      "step": 150
    },
    {
      "epoch": 1.474427891260943,
      "eval_loss": 2.4083755016326904,
      "eval_runtime": 0.6963,
      "eval_samples_per_second": 71.812,
      "eval_steps_per_second": 18.671,
      "step": 150
    },
    {
      "epoch": 1.484257410536016,
      "grad_norm": 1.773645281791687,
      "learning_rate": 0.00011768432908660658,
      "loss": 2.3309,
      "step": 151
    },
    {
      "epoch": 1.4940869298110888,
      "grad_norm": 2.4841768741607666,
      "learning_rate": 0.0001167257084227782,
      "loss": 2.4843,
      "step": 152
    },
    {
      "epoch": 1.5039164490861618,
      "grad_norm": 0.9996944665908813,
      "learning_rate": 0.00011576631979826418,
      "loss": 1.9544,
      "step": 153
    },
    {
      "epoch": 1.5137459683612349,
      "grad_norm": 1.0130380392074585,
      "learning_rate": 0.00011480627275881042,
      "loss": 2.0417,
      "step": 154
    },
    {
      "epoch": 1.523575487636308,
      "grad_norm": 0.939575731754303,
      "learning_rate": 0.00011384567692534251,
      "loss": 2.0705,
      "step": 155
    },
    {
      "epoch": 1.5334050069113807,
      "grad_norm": 0.929763913154602,
      "learning_rate": 0.000112884641981449,
      "loss": 2.0803,
      "step": 156
    },
    {
      "epoch": 1.5432345261864537,
      "grad_norm": 0.9794033765792847,
      "learning_rate": 0.00011192327766085715,
      "loss": 1.9835,
      "step": 157
    },
    {
      "epoch": 1.5530640454615265,
      "grad_norm": 1.0879063606262207,
      "learning_rate": 0.00011096169373490361,
      "loss": 2.0013,
      "step": 158
    },
    {
      "epoch": 1.5628935647365996,
      "grad_norm": 1.06622314453125,
      "learning_rate": 0.00011000000000000002,
      "loss": 2.0374,
      "step": 159
    },
    {
      "epoch": 1.5727230840116726,
      "grad_norm": 1.0707110166549683,
      "learning_rate": 0.00010903830626509644,
      "loss": 2.0073,
      "step": 160
    },
    {
      "epoch": 1.5825526032867456,
      "grad_norm": 1.1493885517120361,
      "learning_rate": 0.00010807672233914287,
      "loss": 2.0256,
      "step": 161
    },
    {
      "epoch": 1.5923821225618184,
      "grad_norm": 1.2368179559707642,
      "learning_rate": 0.00010711535801855104,
      "loss": 2.0373,
      "step": 162
    },
    {
      "epoch": 1.6022116418368915,
      "grad_norm": 1.444209337234497,
      "learning_rate": 0.00010615432307465751,
      "loss": 2.2538,
      "step": 163
    },
    {
      "epoch": 1.6120411611119643,
      "grad_norm": 1.398610234260559,
      "learning_rate": 0.00010519372724118961,
      "loss": 1.7089,
      "step": 164
    },
    {
      "epoch": 1.6218706803870373,
      "grad_norm": 1.2919524908065796,
      "learning_rate": 0.00010423368020173585,
      "loss": 2.4992,
      "step": 165
    },
    {
      "epoch": 1.6317001996621103,
      "grad_norm": 1.1141935586929321,
      "learning_rate": 0.00010327429157722181,
      "loss": 1.9982,
      "step": 166
    },
    {
      "epoch": 1.6415297189371834,
      "grad_norm": 0.9911397099494934,
      "learning_rate": 0.00010231567091339343,
      "loss": 2.0274,
      "step": 167
    },
    {
      "epoch": 1.6513592382122562,
      "grad_norm": 0.9675605893135071,
      "learning_rate": 0.00010135792766830865,
      "loss": 1.9756,
      "step": 168
    },
    {
      "epoch": 1.661188757487329,
      "grad_norm": 0.9353333711624146,
      "learning_rate": 0.00010040117119983918,
      "loss": 1.934,
      "step": 169
    },
    {
      "epoch": 1.671018276762402,
      "grad_norm": 1.0085963010787964,
      "learning_rate": 9.944551075318384e-05,
      "loss": 2.0595,
      "step": 170
    },
    {
      "epoch": 1.680847796037475,
      "grad_norm": 1.0311287641525269,
      "learning_rate": 9.849105544839445e-05,
      "loss": 1.9757,
      "step": 171
    },
    {
      "epoch": 1.690677315312548,
      "grad_norm": 1.0677305459976196,
      "learning_rate": 9.753791426791632e-05,
      "loss": 1.9551,
      "step": 172
    },
    {
      "epoch": 1.700506834587621,
      "grad_norm": 1.1577661037445068,
      "learning_rate": 9.65861960441443e-05,
      "loss": 2.0813,
      "step": 173
    },
    {
      "epoch": 1.710336353862694,
      "grad_norm": 1.2702162265777588,
      "learning_rate": 9.563600944699588e-05,
      "loss": 2.0461,
      "step": 174
    },
    {
      "epoch": 1.7201658731377667,
      "grad_norm": 1.3127394914627075,
      "learning_rate": 9.468746297150308e-05,
      "loss": 1.9524,
      "step": 175
    },
    {
      "epoch": 1.7201658731377667,
      "eval_loss": 2.385427951812744,
      "eval_runtime": 0.6961,
      "eval_samples_per_second": 71.824,
      "eval_steps_per_second": 18.674,
      "step": 175
    },
    {
      "epoch": 1.7299953924128397,
      "grad_norm": 1.6161891222000122,
      "learning_rate": 9.374066492542412e-05,
      "loss": 2.2694,
      "step": 176
    },
    {
      "epoch": 1.7398249116879128,
      "grad_norm": 2.1535022258758545,
      "learning_rate": 9.279572341687653e-05,
      "loss": 2.2855,
      "step": 177
    },
    {
      "epoch": 1.7496544309629858,
      "grad_norm": 1.000197410583496,
      "learning_rate": 9.185274634199304e-05,
      "loss": 1.9217,
      "step": 178
    },
    {
      "epoch": 1.7594839502380588,
      "grad_norm": 1.2574663162231445,
      "learning_rate": 9.091184137260171e-05,
      "loss": 2.0003,
      "step": 179
    },
    {
      "epoch": 1.7693134695131316,
      "grad_norm": 1.0235072374343872,
      "learning_rate": 8.997311594393172e-05,
      "loss": 2.0596,
      "step": 180
    },
    {
      "epoch": 1.7791429887882044,
      "grad_norm": 0.9374403357505798,
      "learning_rate": 8.903667724234595e-05,
      "loss": 2.0426,
      "step": 181
    },
    {
      "epoch": 1.7889725080632775,
      "grad_norm": 0.9672537446022034,
      "learning_rate": 8.810263219310225e-05,
      "loss": 1.9895,
      "step": 182
    },
    {
      "epoch": 1.7988020273383505,
      "grad_norm": 1.1401046514511108,
      "learning_rate": 8.717108744814436e-05,
      "loss": 1.9909,
      "step": 183
    },
    {
      "epoch": 1.8086315466134235,
      "grad_norm": 1.2541248798370361,
      "learning_rate": 8.624214937392412e-05,
      "loss": 1.988,
      "step": 184
    },
    {
      "epoch": 1.8184610658884965,
      "grad_norm": 1.156072735786438,
      "learning_rate": 8.53159240392563e-05,
      "loss": 1.9679,
      "step": 185
    },
    {
      "epoch": 1.8282905851635693,
      "grad_norm": 1.271194577217102,
      "learning_rate": 8.439251720320709e-05,
      "loss": 2.0339,
      "step": 186
    },
    {
      "epoch": 1.8381201044386422,
      "grad_norm": 1.315255880355835,
      "learning_rate": 8.347203430301863e-05,
      "loss": 2.0626,
      "step": 187
    },
    {
      "epoch": 1.8479496237137152,
      "grad_norm": 1.4638818502426147,
      "learning_rate": 8.255458044206957e-05,
      "loss": 2.1827,
      "step": 188
    },
    {
      "epoch": 1.8577791429887882,
      "grad_norm": 1.450156569480896,
      "learning_rate": 8.164026037787415e-05,
      "loss": 1.6739,
      "step": 189
    },
    {
      "epoch": 1.8676086622638612,
      "grad_norm": 1.2157936096191406,
      "learning_rate": 8.072917851012078e-05,
      "loss": 2.45,
      "step": 190
    },
    {
      "epoch": 1.8774381815389343,
      "grad_norm": 1.1207431554794312,
      "learning_rate": 7.982143886875122e-05,
      "loss": 2.0453,
      "step": 191
    },
    {
      "epoch": 1.887267700814007,
      "grad_norm": 1.12586510181427,
      "learning_rate": 7.891714510208232e-05,
      "loss": 1.9761,
      "step": 192
    },
    {
      "epoch": 1.8970972200890799,
      "grad_norm": 1.021728754043579,
      "learning_rate": 7.801640046497103e-05,
      "loss": 2.0234,
      "step": 193
    },
    {
      "epoch": 1.906926739364153,
      "grad_norm": 1.0452762842178345,
      "learning_rate": 7.711930780702445e-05,
      "loss": 1.9967,
      "step": 194
    },
    {
      "epoch": 1.916756258639226,
      "grad_norm": 0.9748082756996155,
      "learning_rate": 7.622596956085635e-05,
      "loss": 1.9948,
      "step": 195
    },
    {
      "epoch": 1.926585777914299,
      "grad_norm": 1.0299899578094482,
      "learning_rate": 7.533648773039084e-05,
      "loss": 2.0412,
      "step": 196
    },
    {
      "epoch": 1.936415297189372,
      "grad_norm": 1.0700615644454956,
      "learning_rate": 7.445096387921553e-05,
      "loss": 1.9714,
      "step": 197
    },
    {
      "epoch": 1.9462448164644448,
      "grad_norm": 1.1362632513046265,
      "learning_rate": 7.356949911898456e-05,
      "loss": 1.94,
      "step": 198
    },
    {
      "epoch": 1.9560743357395176,
      "grad_norm": 1.336560845375061,
      "learning_rate": 7.269219409787342e-05,
      "loss": 1.9919,
      "step": 199
    },
    {
      "epoch": 1.9659038550145906,
      "grad_norm": 1.305739402770996,
      "learning_rate": 7.181914898908661e-05,
      "loss": 2.0634,
      "step": 200
    },
    {
      "epoch": 1.9659038550145906,
      "eval_loss": 2.357637882232666,
      "eval_runtime": 0.6963,
      "eval_samples_per_second": 71.809,
      "eval_steps_per_second": 18.67,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 306,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2592324420829184e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}