{
  "best_metric": 1.382582664489746,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.02160818950382195,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010804094751910974,
      "grad_norm": 0.6411097049713135,
      "learning_rate": 1e-05,
      "loss": 1.5052,
      "step": 1
    },
    {
      "epoch": 0.00010804094751910974,
      "eval_loss": 1.7889565229415894,
      "eval_runtime": 535.7197,
      "eval_samples_per_second": 29.099,
      "eval_steps_per_second": 7.276,
      "step": 1
    },
    {
      "epoch": 0.00021608189503821948,
      "grad_norm": 0.8562445640563965,
      "learning_rate": 2e-05,
      "loss": 1.6454,
      "step": 2
    },
    {
      "epoch": 0.00032412284255732923,
      "grad_norm": 0.824120044708252,
      "learning_rate": 3e-05,
      "loss": 1.5598,
      "step": 3
    },
    {
      "epoch": 0.00043216379007643895,
      "grad_norm": 0.8745611310005188,
      "learning_rate": 4e-05,
      "loss": 1.6791,
      "step": 4
    },
    {
      "epoch": 0.0005402047375955487,
      "grad_norm": 0.8825092315673828,
      "learning_rate": 5e-05,
      "loss": 1.7996,
      "step": 5
    },
    {
      "epoch": 0.0006482456851146585,
      "grad_norm": 0.8375336527824402,
      "learning_rate": 6e-05,
      "loss": 1.876,
      "step": 6
    },
    {
      "epoch": 0.0007562866326337682,
      "grad_norm": 0.8731200695037842,
      "learning_rate": 7e-05,
      "loss": 1.8317,
      "step": 7
    },
    {
      "epoch": 0.0008643275801528779,
      "grad_norm": 0.8659582734107971,
      "learning_rate": 8e-05,
      "loss": 1.8515,
      "step": 8
    },
    {
      "epoch": 0.0009723685276719876,
      "grad_norm": 0.8471695184707642,
      "learning_rate": 9e-05,
      "loss": 1.785,
      "step": 9
    },
    {
      "epoch": 0.0010804094751910975,
      "grad_norm": 0.8195250034332275,
      "learning_rate": 0.0001,
      "loss": 1.8211,
      "step": 10
    },
    {
      "epoch": 0.001188450422710207,
      "grad_norm": 0.837657630443573,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.8297,
      "step": 11
    },
    {
      "epoch": 0.001296491370229317,
      "grad_norm": 0.858310341835022,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.8252,
      "step": 12
    },
    {
      "epoch": 0.0014045323177484267,
      "grad_norm": 0.8768934011459351,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.8806,
      "step": 13
    },
    {
      "epoch": 0.0015125732652675364,
      "grad_norm": 0.8768404126167297,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.6913,
      "step": 14
    },
    {
      "epoch": 0.0016206142127866462,
      "grad_norm": 0.8145396709442139,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.7643,
      "step": 15
    },
    {
      "epoch": 0.0017286551603057558,
      "grad_norm": 0.7942981719970703,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.739,
      "step": 16
    },
    {
      "epoch": 0.0018366961078248656,
      "grad_norm": 0.7425942420959473,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.8478,
      "step": 17
    },
    {
      "epoch": 0.0019447370553439753,
      "grad_norm": 0.6934517621994019,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.6101,
      "step": 18
    },
    {
      "epoch": 0.002052778002863085,
      "grad_norm": 0.6720507144927979,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.6726,
      "step": 19
    },
    {
      "epoch": 0.002160818950382195,
      "grad_norm": 0.7327187657356262,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.7972,
      "step": 20
    },
    {
      "epoch": 0.0022688598979013048,
      "grad_norm": 0.7793174386024475,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.7455,
      "step": 21
    },
    {
      "epoch": 0.002376900845420414,
      "grad_norm": 0.7572932243347168,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.6134,
      "step": 22
    },
    {
      "epoch": 0.002484941792939524,
      "grad_norm": 0.7290782332420349,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.4038,
      "step": 23
    },
    {
      "epoch": 0.002592982740458634,
      "grad_norm": 0.6722505688667297,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.3272,
      "step": 24
    },
    {
      "epoch": 0.0027010236879777437,
      "grad_norm": 0.741421103477478,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.5779,
      "step": 25
    },
    {
      "epoch": 0.0028090646354968535,
      "grad_norm": 0.6199491620063782,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.3542,
      "step": 26
    },
    {
      "epoch": 0.002917105583015963,
      "grad_norm": 0.7175855040550232,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.3952,
      "step": 27
    },
    {
      "epoch": 0.0030251465305350727,
      "grad_norm": 0.6949482560157776,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.3785,
      "step": 28
    },
    {
      "epoch": 0.0031331874780541826,
      "grad_norm": 0.6010020971298218,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.3659,
      "step": 29
    },
    {
      "epoch": 0.0032412284255732924,
      "grad_norm": 0.5330593585968018,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.3109,
      "step": 30
    },
    {
      "epoch": 0.0033492693730924022,
      "grad_norm": 0.5859575271606445,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.3098,
      "step": 31
    },
    {
      "epoch": 0.0034573103206115116,
      "grad_norm": 0.5428658723831177,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.2296,
      "step": 32
    },
    {
      "epoch": 0.0035653512681306215,
      "grad_norm": 0.5114771127700806,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.2435,
      "step": 33
    },
    {
      "epoch": 0.0036733922156497313,
      "grad_norm": 0.558093786239624,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.4116,
      "step": 34
    },
    {
      "epoch": 0.003781433163168841,
      "grad_norm": 0.5544277429580688,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.2653,
      "step": 35
    },
    {
      "epoch": 0.0038894741106879505,
      "grad_norm": 0.6144501566886902,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.3809,
      "step": 36
    },
    {
      "epoch": 0.003997515058207061,
      "grad_norm": 0.5559041500091553,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.4059,
      "step": 37
    },
    {
      "epoch": 0.00410555600572617,
      "grad_norm": 0.606239914894104,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.3873,
      "step": 38
    },
    {
      "epoch": 0.00421359695324528,
      "grad_norm": 0.5906782746315002,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.3119,
      "step": 39
    },
    {
      "epoch": 0.00432163790076439,
      "grad_norm": 0.6354760527610779,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.2816,
      "step": 40
    },
    {
      "epoch": 0.004429678848283499,
      "grad_norm": 0.6075758934020996,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.4081,
      "step": 41
    },
    {
      "epoch": 0.0045377197958026095,
      "grad_norm": 0.6049405932426453,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.3034,
      "step": 42
    },
    {
      "epoch": 0.004645760743321719,
      "grad_norm": 0.5708485245704651,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.3411,
      "step": 43
    },
    {
      "epoch": 0.004753801690840828,
      "grad_norm": 0.5880483388900757,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.2835,
      "step": 44
    },
    {
      "epoch": 0.004861842638359939,
      "grad_norm": 0.5617298483848572,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.3749,
      "step": 45
    },
    {
      "epoch": 0.004969883585879048,
      "grad_norm": 0.599293053150177,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.3293,
      "step": 46
    },
    {
      "epoch": 0.005077924533398158,
      "grad_norm": 0.5648579597473145,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.2301,
      "step": 47
    },
    {
      "epoch": 0.005185965480917268,
      "grad_norm": 0.5536026358604431,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.2069,
      "step": 48
    },
    {
      "epoch": 0.005294006428436377,
      "grad_norm": 0.5456497073173523,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.1081,
      "step": 49
    },
    {
      "epoch": 0.005402047375955487,
      "grad_norm": 0.6124342083930969,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.3318,
      "step": 50
    },
    {
      "epoch": 0.005402047375955487,
      "eval_loss": 1.4472647905349731,
      "eval_runtime": 538.4928,
      "eval_samples_per_second": 28.949,
      "eval_steps_per_second": 7.239,
      "step": 50
    },
    {
      "epoch": 0.005510088323474597,
      "grad_norm": 0.5724785923957825,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.5719,
      "step": 51
    },
    {
      "epoch": 0.005618129270993707,
      "grad_norm": 0.5202212929725647,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.6062,
      "step": 52
    },
    {
      "epoch": 0.005726170218512816,
      "grad_norm": 0.5109375715255737,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.4072,
      "step": 53
    },
    {
      "epoch": 0.005834211166031926,
      "grad_norm": 0.49153491854667664,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.4472,
      "step": 54
    },
    {
      "epoch": 0.005942252113551036,
      "grad_norm": 0.5157988667488098,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.4969,
      "step": 55
    },
    {
      "epoch": 0.0060502930610701455,
      "grad_norm": 0.5498408675193787,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.6005,
      "step": 56
    },
    {
      "epoch": 0.006158334008589256,
      "grad_norm": 0.5869506001472473,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.746,
      "step": 57
    },
    {
      "epoch": 0.006266374956108365,
      "grad_norm": 0.5549739003181458,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.5946,
      "step": 58
    },
    {
      "epoch": 0.0063744159036274745,
      "grad_norm": 0.508307695388794,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.6111,
      "step": 59
    },
    {
      "epoch": 0.006482456851146585,
      "grad_norm": 0.5015324354171753,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.6921,
      "step": 60
    },
    {
      "epoch": 0.006590497798665694,
      "grad_norm": 0.5559808015823364,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.7278,
      "step": 61
    },
    {
      "epoch": 0.0066985387461848045,
      "grad_norm": 0.5375747084617615,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.6452,
      "step": 62
    },
    {
      "epoch": 0.006806579693703914,
      "grad_norm": 0.5635334849357605,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.6882,
      "step": 63
    },
    {
      "epoch": 0.006914620641223023,
      "grad_norm": 0.5800416469573975,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.6832,
      "step": 64
    },
    {
      "epoch": 0.0070226615887421335,
      "grad_norm": 0.6070132255554199,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.763,
      "step": 65
    },
    {
      "epoch": 0.007130702536261243,
      "grad_norm": 0.5629101395606995,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.4637,
      "step": 66
    },
    {
      "epoch": 0.007238743483780352,
      "grad_norm": 0.5806207656860352,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.5195,
      "step": 67
    },
    {
      "epoch": 0.007346784431299463,
      "grad_norm": 0.6087584495544434,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.5393,
      "step": 68
    },
    {
      "epoch": 0.007454825378818572,
      "grad_norm": 0.6380349397659302,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.5773,
      "step": 69
    },
    {
      "epoch": 0.007562866326337682,
      "grad_norm": 0.6220327615737915,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.5909,
      "step": 70
    },
    {
      "epoch": 0.007670907273856792,
      "grad_norm": 0.6914963126182556,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.7632,
      "step": 71
    },
    {
      "epoch": 0.007778948221375901,
      "grad_norm": 0.6657575368881226,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.5215,
      "step": 72
    },
    {
      "epoch": 0.007886989168895011,
      "grad_norm": 0.6277755498886108,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.3684,
      "step": 73
    },
    {
      "epoch": 0.007995030116414122,
      "grad_norm": 0.7497745752334595,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.3881,
      "step": 74
    },
    {
      "epoch": 0.00810307106393323,
      "grad_norm": 0.6374635100364685,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.322,
      "step": 75
    },
    {
      "epoch": 0.00821111201145234,
      "grad_norm": 0.668455958366394,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.3848,
      "step": 76
    },
    {
      "epoch": 0.00831915295897145,
      "grad_norm": 0.5366008877754211,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.2807,
      "step": 77
    },
    {
      "epoch": 0.00842719390649056,
      "grad_norm": 0.5630325078964233,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.3645,
      "step": 78
    },
    {
      "epoch": 0.00853523485400967,
      "grad_norm": 0.5944975018501282,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.3041,
      "step": 79
    },
    {
      "epoch": 0.00864327580152878,
      "grad_norm": 0.6403332352638245,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.4156,
      "step": 80
    },
    {
      "epoch": 0.00875131674904789,
      "grad_norm": 0.5775466561317444,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.401,
      "step": 81
    },
    {
      "epoch": 0.008859357696566999,
      "grad_norm": 0.5093110799789429,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.3779,
      "step": 82
    },
    {
      "epoch": 0.008967398644086109,
      "grad_norm": 0.5032273530960083,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.2792,
      "step": 83
    },
    {
      "epoch": 0.009075439591605219,
      "grad_norm": 0.5436679720878601,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.1895,
      "step": 84
    },
    {
      "epoch": 0.009183480539124328,
      "grad_norm": 0.5496953725814819,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.279,
      "step": 85
    },
    {
      "epoch": 0.009291521486643438,
      "grad_norm": 0.4856758713722229,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.1795,
      "step": 86
    },
    {
      "epoch": 0.009399562434162548,
      "grad_norm": 0.5258938074111938,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.2899,
      "step": 87
    },
    {
      "epoch": 0.009507603381681657,
      "grad_norm": 0.5205855965614319,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.1558,
      "step": 88
    },
    {
      "epoch": 0.009615644329200767,
      "grad_norm": 0.49661728739738464,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.2421,
      "step": 89
    },
    {
      "epoch": 0.009723685276719877,
      "grad_norm": 0.5139006972312927,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.215,
      "step": 90
    },
    {
      "epoch": 0.009831726224238986,
      "grad_norm": 0.5055752992630005,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.1881,
      "step": 91
    },
    {
      "epoch": 0.009939767171758096,
      "grad_norm": 0.5600236058235168,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.338,
      "step": 92
    },
    {
      "epoch": 0.010047808119277206,
      "grad_norm": 0.4925087094306946,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.2178,
      "step": 93
    },
    {
      "epoch": 0.010155849066796317,
      "grad_norm": 0.5316876173019409,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.31,
      "step": 94
    },
    {
      "epoch": 0.010263890014315425,
      "grad_norm": 0.5395605564117432,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 1.3661,
      "step": 95
    },
    {
      "epoch": 0.010371930961834535,
      "grad_norm": 0.5037703514099121,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.1829,
      "step": 96
    },
    {
      "epoch": 0.010479971909353646,
      "grad_norm": 0.5071983933448792,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.2487,
      "step": 97
    },
    {
      "epoch": 0.010588012856872754,
      "grad_norm": 0.561583936214447,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.2686,
      "step": 98
    },
    {
      "epoch": 0.010696053804391864,
      "grad_norm": 0.5371668338775635,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.1905,
      "step": 99
    },
    {
      "epoch": 0.010804094751910975,
      "grad_norm": 0.5955190062522888,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.198,
      "step": 100
    },
    {
      "epoch": 0.010804094751910975,
      "eval_loss": 1.4100725650787354,
      "eval_runtime": 538.1805,
      "eval_samples_per_second": 28.966,
      "eval_steps_per_second": 7.243,
      "step": 100
    },
    {
      "epoch": 0.010912135699430083,
      "grad_norm": 0.5693991184234619,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.5698,
      "step": 101
    },
    {
      "epoch": 0.011020176646949193,
      "grad_norm": 0.49347609281539917,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.4305,
      "step": 102
    },
    {
      "epoch": 0.011128217594468304,
      "grad_norm": 0.5346347093582153,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.5587,
      "step": 103
    },
    {
      "epoch": 0.011236258541987414,
      "grad_norm": 0.5068135261535645,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.5091,
      "step": 104
    },
    {
      "epoch": 0.011344299489506523,
      "grad_norm": 0.4623704254627228,
      "learning_rate": 5e-05,
      "loss": 1.5017,
      "step": 105
    },
    {
      "epoch": 0.011452340437025633,
      "grad_norm": 0.5210311412811279,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.36,
      "step": 106
    },
    {
      "epoch": 0.011560381384544743,
      "grad_norm": 0.5300119519233704,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.6299,
      "step": 107
    },
    {
      "epoch": 0.011668422332063852,
      "grad_norm": 0.5147326588630676,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.4485,
      "step": 108
    },
    {
      "epoch": 0.011776463279582962,
      "grad_norm": 0.5882423520088196,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.7687,
      "step": 109
    },
    {
      "epoch": 0.011884504227102072,
      "grad_norm": 0.5375576019287109,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.4911,
      "step": 110
    },
    {
      "epoch": 0.01199254517462118,
      "grad_norm": 0.5624399185180664,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.5786,
      "step": 111
    },
    {
      "epoch": 0.012100586122140291,
      "grad_norm": 0.6138778924942017,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.6166,
      "step": 112
    },
    {
      "epoch": 0.012208627069659401,
      "grad_norm": 0.5514253973960876,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.5979,
      "step": 113
    },
    {
      "epoch": 0.012316668017178511,
      "grad_norm": 0.564391016960144,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.5839,
      "step": 114
    },
    {
      "epoch": 0.01242470896469762,
      "grad_norm": 0.5756611824035645,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.5276,
      "step": 115
    },
    {
      "epoch": 0.01253274991221673,
      "grad_norm": 0.57477205991745,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.6878,
      "step": 116
    },
    {
      "epoch": 0.01264079085973584,
      "grad_norm": 0.5562359094619751,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.6031,
      "step": 117
    },
    {
      "epoch": 0.012748831807254949,
      "grad_norm": 0.5711321234703064,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.604,
      "step": 118
    },
    {
      "epoch": 0.01285687275477406,
      "grad_norm": 0.5932537317276001,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.5897,
      "step": 119
    },
    {
      "epoch": 0.01296491370229317,
      "grad_norm": 0.6095288395881653,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.5861,
      "step": 120
    },
    {
      "epoch": 0.013072954649812278,
      "grad_norm": 0.5559149384498596,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.4496,
      "step": 121
    },
    {
      "epoch": 0.013180995597331388,
      "grad_norm": 0.6278871297836304,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.3942,
      "step": 122
    },
    {
      "epoch": 0.013289036544850499,
      "grad_norm": 0.7265165448188782,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.5126,
      "step": 123
    },
    {
      "epoch": 0.013397077492369609,
      "grad_norm": 0.5562739968299866,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.4249,
      "step": 124
    },
    {
      "epoch": 0.013505118439888717,
      "grad_norm": 0.5824069380760193,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.3123,
      "step": 125
    },
    {
      "epoch": 0.013613159387407828,
      "grad_norm": 0.5717520117759705,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.3415,
      "step": 126
    },
    {
      "epoch": 0.013721200334926938,
      "grad_norm": 0.5535140037536621,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.3216,
      "step": 127
    },
    {
      "epoch": 0.013829241282446047,
      "grad_norm": 0.5388808846473694,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.3851,
      "step": 128
    },
    {
      "epoch": 0.013937282229965157,
      "grad_norm": 0.5416645407676697,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.3414,
      "step": 129
    },
    {
      "epoch": 0.014045323177484267,
      "grad_norm": 0.5166726112365723,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.342,
      "step": 130
    },
    {
      "epoch": 0.014153364125003376,
      "grad_norm": 0.527347981929779,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.3069,
      "step": 131
    },
    {
      "epoch": 0.014261405072522486,
      "grad_norm": 0.4782974421977997,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.1905,
      "step": 132
    },
    {
      "epoch": 0.014369446020041596,
      "grad_norm": 0.477867990732193,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.2083,
      "step": 133
    },
    {
      "epoch": 0.014477486967560705,
      "grad_norm": 0.5195420980453491,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.3235,
      "step": 134
    },
    {
      "epoch": 0.014585527915079815,
      "grad_norm": 0.5254411697387695,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.2766,
      "step": 135
    },
    {
      "epoch": 0.014693568862598925,
      "grad_norm": 0.5908624529838562,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.2454,
      "step": 136
    },
    {
      "epoch": 0.014801609810118035,
      "grad_norm": 0.49801841378211975,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.1768,
      "step": 137
    },
    {
      "epoch": 0.014909650757637144,
      "grad_norm": 0.5246025919914246,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.2514,
      "step": 138
    },
    {
      "epoch": 0.015017691705156254,
      "grad_norm": 0.5168302655220032,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.2134,
      "step": 139
    },
    {
      "epoch": 0.015125732652675365,
      "grad_norm": 0.6382246017456055,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.3435,
      "step": 140
    },
    {
      "epoch": 0.015233773600194473,
      "grad_norm": 0.5208078026771545,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.2451,
      "step": 141
    },
    {
      "epoch": 0.015341814547713583,
      "grad_norm": 0.5606635808944702,
      "learning_rate": 2.128356686585282e-05,
      "loss": 1.2622,
      "step": 142
    },
    {
      "epoch": 0.015449855495232694,
      "grad_norm": 0.5353780388832092,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.1051,
      "step": 143
    },
    {
      "epoch": 0.015557896442751802,
      "grad_norm": 0.5248527526855469,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.2632,
      "step": 144
    },
    {
      "epoch": 0.015665937390270914,
      "grad_norm": 0.5635786056518555,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.2632,
      "step": 145
    },
    {
      "epoch": 0.015773978337790023,
      "grad_norm": 0.5712494254112244,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.2468,
      "step": 146
    },
    {
      "epoch": 0.01588201928530913,
      "grad_norm": 0.4934338927268982,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.1091,
      "step": 147
    },
    {
      "epoch": 0.015990060232828243,
      "grad_norm": 0.5326967239379883,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.1771,
      "step": 148
    },
    {
      "epoch": 0.01609810118034735,
      "grad_norm": 0.5374605059623718,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.0806,
      "step": 149
    },
    {
      "epoch": 0.01620614212786646,
      "grad_norm": 0.6305158734321594,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.2577,
      "step": 150
    },
    {
      "epoch": 0.01620614212786646,
      "eval_loss": 1.3888720273971558,
      "eval_runtime": 538.0843,
      "eval_samples_per_second": 28.971,
      "eval_steps_per_second": 7.244,
      "step": 150
    },
    {
      "epoch": 0.016314183075385572,
      "grad_norm": 0.6311864852905273,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.6077,
      "step": 151
    },
    {
      "epoch": 0.01642222402290468,
      "grad_norm": 0.5558664202690125,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.4707,
      "step": 152
    },
    {
      "epoch": 0.01653026497042379,
      "grad_norm": 0.5201897621154785,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.4714,
      "step": 153
    },
    {
      "epoch": 0.0166383059179429,
      "grad_norm": 0.47984135150909424,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.4047,
      "step": 154
    },
    {
      "epoch": 0.01674634686546201,
      "grad_norm": 0.5219176411628723,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.5159,
      "step": 155
    },
    {
      "epoch": 0.01685438781298112,
      "grad_norm": 0.5342748165130615,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.572,
      "step": 156
    },
    {
      "epoch": 0.01696242876050023,
      "grad_norm": 0.5403715968132019,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.5249,
      "step": 157
    },
    {
      "epoch": 0.01707046970801934,
      "grad_norm": 0.5489739775657654,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.5563,
      "step": 158
    },
    {
      "epoch": 0.017178510655538447,
      "grad_norm": 0.5305431485176086,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.6324,
      "step": 159
    },
    {
      "epoch": 0.01728655160305756,
      "grad_norm": 0.6527482271194458,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.6655,
      "step": 160
    },
    {
      "epoch": 0.017394592550576668,
      "grad_norm": 0.5631136298179626,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.5716,
      "step": 161
    },
    {
      "epoch": 0.01750263349809578,
      "grad_norm": 0.5855433344841003,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.444,
      "step": 162
    },
    {
      "epoch": 0.01761067444561489,
      "grad_norm": 0.5254190564155579,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.4447,
      "step": 163
    },
    {
      "epoch": 0.017718715393133997,
      "grad_norm": 0.6083276867866516,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.6265,
      "step": 164
    },
    {
      "epoch": 0.01782675634065311,
      "grad_norm": 0.5765725374221802,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.6773,
      "step": 165
    },
    {
      "epoch": 0.017934797288172218,
      "grad_norm": 0.6261915564537048,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.5837,
      "step": 166
    },
    {
      "epoch": 0.018042838235691326,
      "grad_norm": 0.654827892780304,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.7147,
      "step": 167
    },
    {
      "epoch": 0.018150879183210438,
      "grad_norm": 0.6623985171318054,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.6411,
      "step": 168
    },
    {
      "epoch": 0.018258920130729547,
      "grad_norm": 0.6037927865982056,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.5413,
      "step": 169
    },
    {
      "epoch": 0.018366961078248655,
      "grad_norm": 0.7128688097000122,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.6461,
      "step": 170
    },
    {
      "epoch": 0.018475002025767767,
      "grad_norm": 0.6954914331436157,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.5687,
      "step": 171
    },
    {
      "epoch": 0.018583042973286876,
      "grad_norm": 0.6771354079246521,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.5815,
      "step": 172
    },
    {
      "epoch": 0.018691083920805984,
      "grad_norm": 0.5649444460868835,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.4371,
      "step": 173
    },
    {
      "epoch": 0.018799124868325096,
      "grad_norm": 0.5973221063613892,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.4132,
      "step": 174
    },
    {
      "epoch": 0.018907165815844205,
      "grad_norm": 0.5261447429656982,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.3926,
      "step": 175
    },
    {
      "epoch": 0.019015206763363313,
      "grad_norm": 0.47035321593284607,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.2558,
      "step": 176
    },
    {
      "epoch": 0.019123247710882425,
      "grad_norm": 0.43934720754623413,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.0844,
      "step": 177
    },
    {
      "epoch": 0.019231288658401534,
      "grad_norm": 0.48290756344795227,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.2157,
      "step": 178
    },
    {
      "epoch": 0.019339329605920642,
      "grad_norm": 0.44663211703300476,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.1288,
      "step": 179
    },
    {
      "epoch": 0.019447370553439754,
      "grad_norm": 0.5053387880325317,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.3092,
      "step": 180
    },
    {
      "epoch": 0.019555411500958863,
      "grad_norm": 0.4832550585269928,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.1962,
      "step": 181
    },
    {
      "epoch": 0.01966345244847797,
      "grad_norm": 0.5169121623039246,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.3546,
      "step": 182
    },
    {
      "epoch": 0.019771493395997083,
      "grad_norm": 0.4790319800376892,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.186,
      "step": 183
    },
    {
      "epoch": 0.019879534343516192,
      "grad_norm": 0.5148804187774658,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.3691,
      "step": 184
    },
    {
      "epoch": 0.019987575291035304,
      "grad_norm": 0.5392192602157593,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.341,
      "step": 185
    },
    {
      "epoch": 0.020095616238554413,
      "grad_norm": 0.5352830290794373,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.3299,
      "step": 186
    },
    {
      "epoch": 0.02020365718607352,
      "grad_norm": 0.4771963953971863,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.2217,
      "step": 187
    },
    {
      "epoch": 0.020311698133592633,
      "grad_norm": 0.5207287073135376,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.2842,
      "step": 188
    },
    {
      "epoch": 0.02041973908111174,
      "grad_norm": 0.5134222507476807,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.2791,
      "step": 189
    },
    {
      "epoch": 0.02052778002863085,
      "grad_norm": 0.5317819118499756,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.303,
      "step": 190
    },
    {
      "epoch": 0.020635820976149962,
      "grad_norm": 0.5181210041046143,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.3626,
      "step": 191
    },
    {
      "epoch": 0.02074386192366907,
      "grad_norm": 0.4858943223953247,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.2487,
      "step": 192
    },
    {
      "epoch": 0.02085190287118818,
      "grad_norm": 0.5556133389472961,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 1.3508,
      "step": 193
    },
    {
      "epoch": 0.02095994381870729,
      "grad_norm": 0.5138974785804749,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.1609,
      "step": 194
    },
    {
      "epoch": 0.0210679847662264,
      "grad_norm": 0.5383747816085815,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.2078,
      "step": 195
    },
    {
      "epoch": 0.021176025713745508,
      "grad_norm": 0.5176827311515808,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.2208,
      "step": 196
    },
    {
      "epoch": 0.02128406666126462,
      "grad_norm": 0.572370707988739,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.2815,
      "step": 197
    },
    {
      "epoch": 0.02139210760878373,
      "grad_norm": 0.549521267414093,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.3001,
      "step": 198
    },
    {
      "epoch": 0.021500148556302837,
      "grad_norm": 0.5516470670700073,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.2547,
      "step": 199
    },
    {
      "epoch": 0.02160818950382195,
      "grad_norm": 0.549034059047699,
      "learning_rate": 0.0,
      "loss": 1.2254,
      "step": 200
    },
    {
      "epoch": 0.02160818950382195,
      "eval_loss": 1.382582664489746,
      "eval_runtime": 538.403,
      "eval_samples_per_second": 28.954,
      "eval_steps_per_second": 7.24,
      "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": 5,
        "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": 7.8039887118336e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}