{
  "best_metric": 1.090016484260559,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.9142857142857143,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004571428571428572,
      "grad_norm": 0.12384573370218277,
      "learning_rate": 1e-05,
      "loss": 0.7389,
      "step": 1
    },
    {
      "epoch": 0.004571428571428572,
      "eval_loss": 1.362682580947876,
      "eval_runtime": 40.2981,
      "eval_samples_per_second": 9.157,
      "eval_steps_per_second": 2.308,
      "step": 1
    },
    {
      "epoch": 0.009142857142857144,
      "grad_norm": 0.1931685507297516,
      "learning_rate": 2e-05,
      "loss": 1.263,
      "step": 2
    },
    {
      "epoch": 0.013714285714285714,
      "grad_norm": 0.24555817246437073,
      "learning_rate": 3e-05,
      "loss": 1.546,
      "step": 3
    },
    {
      "epoch": 0.018285714285714287,
      "grad_norm": 0.20846664905548096,
      "learning_rate": 4e-05,
      "loss": 1.4432,
      "step": 4
    },
    {
      "epoch": 0.022857142857142857,
      "grad_norm": 0.21662656962871552,
      "learning_rate": 5e-05,
      "loss": 1.4057,
      "step": 5
    },
    {
      "epoch": 0.027428571428571427,
      "grad_norm": 0.22502146661281586,
      "learning_rate": 6e-05,
      "loss": 1.4752,
      "step": 6
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.2199072688817978,
      "learning_rate": 7e-05,
      "loss": 1.5484,
      "step": 7
    },
    {
      "epoch": 0.036571428571428574,
      "grad_norm": 0.2088400423526764,
      "learning_rate": 8e-05,
      "loss": 1.376,
      "step": 8
    },
    {
      "epoch": 0.04114285714285714,
      "grad_norm": 0.1994723379611969,
      "learning_rate": 9e-05,
      "loss": 1.4309,
      "step": 9
    },
    {
      "epoch": 0.045714285714285714,
      "grad_norm": 0.17029602825641632,
      "learning_rate": 0.0001,
      "loss": 1.5372,
      "step": 10
    },
    {
      "epoch": 0.05028571428571429,
      "grad_norm": 0.17547327280044556,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.3906,
      "step": 11
    },
    {
      "epoch": 0.054857142857142854,
      "grad_norm": 0.16624683141708374,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.3834,
      "step": 12
    },
    {
      "epoch": 0.05942857142857143,
      "grad_norm": 0.20969858765602112,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.4273,
      "step": 13
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.20921021699905396,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.4157,
      "step": 14
    },
    {
      "epoch": 0.06857142857142857,
      "grad_norm": 0.19582298398017883,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.388,
      "step": 15
    },
    {
      "epoch": 0.07314285714285715,
      "grad_norm": 0.2045115977525711,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.2916,
      "step": 16
    },
    {
      "epoch": 0.07771428571428571,
      "grad_norm": 0.17086480557918549,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.3656,
      "step": 17
    },
    {
      "epoch": 0.08228571428571428,
      "grad_norm": 0.15559332072734833,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.3276,
      "step": 18
    },
    {
      "epoch": 0.08685714285714285,
      "grad_norm": 0.14628355205059052,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.1483,
      "step": 19
    },
    {
      "epoch": 0.09142857142857143,
      "grad_norm": 0.14557524025440216,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.2162,
      "step": 20
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.1672665923833847,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.1963,
      "step": 21
    },
    {
      "epoch": 0.10057142857142858,
      "grad_norm": 0.13945060968399048,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.2472,
      "step": 22
    },
    {
      "epoch": 0.10514285714285715,
      "grad_norm": 0.13727137446403503,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.0866,
      "step": 23
    },
    {
      "epoch": 0.10971428571428571,
      "grad_norm": 0.1319202333688736,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.1846,
      "step": 24
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 0.13479618728160858,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.1505,
      "step": 25
    },
    {
      "epoch": 0.11885714285714286,
      "grad_norm": 0.12670767307281494,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.2476,
      "step": 26
    },
    {
      "epoch": 0.12342857142857143,
      "grad_norm": 0.15373919904232025,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.1967,
      "step": 27
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.15247727930545807,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.9893,
      "step": 28
    },
    {
      "epoch": 0.13257142857142856,
      "grad_norm": 0.1301872432231903,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.2281,
      "step": 29
    },
    {
      "epoch": 0.13714285714285715,
      "grad_norm": 0.12188567966222763,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.1287,
      "step": 30
    },
    {
      "epoch": 0.1417142857142857,
      "grad_norm": 0.1177821233868599,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.19,
      "step": 31
    },
    {
      "epoch": 0.1462857142857143,
      "grad_norm": 0.12030963599681854,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.2389,
      "step": 32
    },
    {
      "epoch": 0.15085714285714286,
      "grad_norm": 0.12400416284799576,
      "learning_rate": 9.642770192448536e-05,
      "loss": 1.272,
      "step": 33
    },
    {
      "epoch": 0.15542857142857142,
      "grad_norm": 0.13301657140254974,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.2809,
      "step": 34
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.14115765690803528,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.2218,
      "step": 35
    },
    {
      "epoch": 0.16457142857142856,
      "grad_norm": 0.12093055248260498,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.115,
      "step": 36
    },
    {
      "epoch": 0.16914285714285715,
      "grad_norm": 0.12792570888996124,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.1204,
      "step": 37
    },
    {
      "epoch": 0.1737142857142857,
      "grad_norm": 0.1883489042520523,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.3103,
      "step": 38
    },
    {
      "epoch": 0.1782857142857143,
      "grad_norm": 0.14241398870944977,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.1938,
      "step": 39
    },
    {
      "epoch": 0.18285714285714286,
      "grad_norm": 0.1636561155319214,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.1379,
      "step": 40
    },
    {
      "epoch": 0.18742857142857142,
      "grad_norm": 0.17105966806411743,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.1285,
      "step": 41
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.17147573828697205,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.09,
      "step": 42
    },
    {
      "epoch": 0.19657142857142856,
      "grad_norm": 0.18589459359645844,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.0317,
      "step": 43
    },
    {
      "epoch": 0.20114285714285715,
      "grad_norm": 0.1729321926832199,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.8933,
      "step": 44
    },
    {
      "epoch": 0.2057142857142857,
      "grad_norm": 0.22401976585388184,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.8621,
      "step": 45
    },
    {
      "epoch": 0.2102857142857143,
      "grad_norm": 0.29440781474113464,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.8579,
      "step": 46
    },
    {
      "epoch": 0.21485714285714286,
      "grad_norm": 0.5384777188301086,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.6747,
      "step": 47
    },
    {
      "epoch": 0.21942857142857142,
      "grad_norm": 0.7473423480987549,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.5015,
      "step": 48
    },
    {
      "epoch": 0.224,
      "grad_norm": 0.5895587801933289,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.4012,
      "step": 49
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 0.7679787278175354,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.4151,
      "step": 50
    },
    {
      "epoch": 0.22857142857142856,
      "eval_loss": 1.1465318202972412,
      "eval_runtime": 41.0324,
      "eval_samples_per_second": 8.993,
      "eval_steps_per_second": 2.267,
      "step": 50
    },
    {
      "epoch": 0.23314285714285715,
      "grad_norm": 0.14895500242710114,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.5121,
      "step": 51
    },
    {
      "epoch": 0.2377142857142857,
      "grad_norm": 0.16254602372646332,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.118,
      "step": 52
    },
    {
      "epoch": 0.2422857142857143,
      "grad_norm": 0.17265716195106506,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.3765,
      "step": 53
    },
    {
      "epoch": 0.24685714285714286,
      "grad_norm": 0.18003533780574799,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.2285,
      "step": 54
    },
    {
      "epoch": 0.25142857142857145,
      "grad_norm": 0.15403780341148376,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.2193,
      "step": 55
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.141326904296875,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.2924,
      "step": 56
    },
    {
      "epoch": 0.26057142857142856,
      "grad_norm": 0.12267368286848068,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.2832,
      "step": 57
    },
    {
      "epoch": 0.2651428571428571,
      "grad_norm": 0.12160666286945343,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.3969,
      "step": 58
    },
    {
      "epoch": 0.26971428571428574,
      "grad_norm": 0.12419481575489044,
      "learning_rate": 8.44676704559283e-05,
      "loss": 1.4133,
      "step": 59
    },
    {
      "epoch": 0.2742857142857143,
      "grad_norm": 0.11516056209802628,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.3351,
      "step": 60
    },
    {
      "epoch": 0.27885714285714286,
      "grad_norm": 0.13372984528541565,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.3921,
      "step": 61
    },
    {
      "epoch": 0.2834285714285714,
      "grad_norm": 0.13296741247177124,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.3812,
      "step": 62
    },
    {
      "epoch": 0.288,
      "grad_norm": 0.14010053873062134,
      "learning_rate": 8.199842702516583e-05,
      "loss": 1.3304,
      "step": 63
    },
    {
      "epoch": 0.2925714285714286,
      "grad_norm": 0.1268775314092636,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.3265,
      "step": 64
    },
    {
      "epoch": 0.29714285714285715,
      "grad_norm": 0.12483099102973938,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.2259,
      "step": 65
    },
    {
      "epoch": 0.3017142857142857,
      "grad_norm": 0.13041441142559052,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.3675,
      "step": 66
    },
    {
      "epoch": 0.3062857142857143,
      "grad_norm": 0.12797042727470398,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.2383,
      "step": 67
    },
    {
      "epoch": 0.31085714285714283,
      "grad_norm": 0.13023968040943146,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.2535,
      "step": 68
    },
    {
      "epoch": 0.31542857142857145,
      "grad_norm": 0.12802593410015106,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.2855,
      "step": 69
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.12662489712238312,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.1503,
      "step": 70
    },
    {
      "epoch": 0.32457142857142857,
      "grad_norm": 0.13285095989704132,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.2358,
      "step": 71
    },
    {
      "epoch": 0.3291428571428571,
      "grad_norm": 0.12332078069448471,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.1553,
      "step": 72
    },
    {
      "epoch": 0.33371428571428574,
      "grad_norm": 0.12388018518686295,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.1739,
      "step": 73
    },
    {
      "epoch": 0.3382857142857143,
      "grad_norm": 0.14020569622516632,
      "learning_rate": 7.452117519152542e-05,
      "loss": 1.1668,
      "step": 74
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.1221918910741806,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.1935,
      "step": 75
    },
    {
      "epoch": 0.3474285714285714,
      "grad_norm": 0.1297471970319748,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.1603,
      "step": 76
    },
    {
      "epoch": 0.352,
      "grad_norm": 0.11684367805719376,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.0564,
      "step": 77
    },
    {
      "epoch": 0.3565714285714286,
      "grad_norm": 0.11793461441993713,
      "learning_rate": 7.158771761692464e-05,
      "loss": 1.1733,
      "step": 78
    },
    {
      "epoch": 0.36114285714285715,
      "grad_norm": 0.12452173233032227,
      "learning_rate": 7.083909302476453e-05,
      "loss": 1.2412,
      "step": 79
    },
    {
      "epoch": 0.3657142857142857,
      "grad_norm": 0.12887261807918549,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.2228,
      "step": 80
    },
    {
      "epoch": 0.3702857142857143,
      "grad_norm": 0.11742619425058365,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.263,
      "step": 81
    },
    {
      "epoch": 0.37485714285714283,
      "grad_norm": 0.11659453809261322,
      "learning_rate": 6.855986244591104e-05,
      "loss": 1.1504,
      "step": 82
    },
    {
      "epoch": 0.37942857142857145,
      "grad_norm": 0.12475767731666565,
      "learning_rate": 6.778969234612584e-05,
      "loss": 1.2661,
      "step": 83
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.1260615885257721,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.1136,
      "step": 84
    },
    {
      "epoch": 0.38857142857142857,
      "grad_norm": 0.13305872678756714,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.1865,
      "step": 85
    },
    {
      "epoch": 0.3931428571428571,
      "grad_norm": 0.1305752694606781,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.2529,
      "step": 86
    },
    {
      "epoch": 0.3977142857142857,
      "grad_norm": 0.12492652237415314,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.9044,
      "step": 87
    },
    {
      "epoch": 0.4022857142857143,
      "grad_norm": 0.12890726327896118,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.1121,
      "step": 88
    },
    {
      "epoch": 0.40685714285714286,
      "grad_norm": 0.12997473776340485,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.0347,
      "step": 89
    },
    {
      "epoch": 0.4114285714285714,
      "grad_norm": 0.12488750368356705,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.8619,
      "step": 90
    },
    {
      "epoch": 0.416,
      "grad_norm": 0.12945248186588287,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.9846,
      "step": 91
    },
    {
      "epoch": 0.4205714285714286,
      "grad_norm": 0.12920667231082916,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.0864,
      "step": 92
    },
    {
      "epoch": 0.42514285714285716,
      "grad_norm": 0.14830996096134186,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.0887,
      "step": 93
    },
    {
      "epoch": 0.4297142857142857,
      "grad_norm": 0.15009595453739166,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.7742,
      "step": 94
    },
    {
      "epoch": 0.4342857142857143,
      "grad_norm": 0.1972149759531021,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.7414,
      "step": 95
    },
    {
      "epoch": 0.43885714285714283,
      "grad_norm": 0.3312933146953583,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.6417,
      "step": 96
    },
    {
      "epoch": 0.44342857142857145,
      "grad_norm": 0.4016004502773285,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.4978,
      "step": 97
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.6031044721603394,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.2744,
      "step": 98
    },
    {
      "epoch": 0.45257142857142857,
      "grad_norm": 0.7307276725769043,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.2363,
      "step": 99
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 0.6628548502922058,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.2283,
      "step": 100
    },
    {
      "epoch": 0.45714285714285713,
      "eval_loss": 1.0969529151916504,
      "eval_runtime": 41.0178,
      "eval_samples_per_second": 8.996,
      "eval_steps_per_second": 2.267,
      "step": 100
    },
    {
      "epoch": 0.4617142857142857,
      "grad_norm": 0.07356088608503342,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.6322,
      "step": 101
    },
    {
      "epoch": 0.4662857142857143,
      "grad_norm": 0.08858072757720947,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.8521,
      "step": 102
    },
    {
      "epoch": 0.47085714285714286,
      "grad_norm": 0.11882416903972626,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.2533,
      "step": 103
    },
    {
      "epoch": 0.4754285714285714,
      "grad_norm": 0.1180044561624527,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.2151,
      "step": 104
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.12184524536132812,
      "learning_rate": 5e-05,
      "loss": 1.2656,
      "step": 105
    },
    {
      "epoch": 0.4845714285714286,
      "grad_norm": 0.1148492842912674,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.2092,
      "step": 106
    },
    {
      "epoch": 0.48914285714285716,
      "grad_norm": 0.11979564279317856,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.2576,
      "step": 107
    },
    {
      "epoch": 0.4937142857142857,
      "grad_norm": 0.12576784193515778,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 1.346,
      "step": 108
    },
    {
      "epoch": 0.4982857142857143,
      "grad_norm": 0.1572338193655014,
      "learning_rate": 4.669547078371504e-05,
      "loss": 1.3217,
      "step": 109
    },
    {
      "epoch": 0.5028571428571429,
      "grad_norm": 0.12395395338535309,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 1.265,
      "step": 110
    },
    {
      "epoch": 0.5074285714285715,
      "grad_norm": 0.1258736252784729,
      "learning_rate": 4.504772348747687e-05,
      "loss": 1.3359,
      "step": 111
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.12625716626644135,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 1.3728,
      "step": 112
    },
    {
      "epoch": 0.5165714285714286,
      "grad_norm": 0.11527693271636963,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.1624,
      "step": 113
    },
    {
      "epoch": 0.5211428571428571,
      "grad_norm": 0.1241602823138237,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 1.2432,
      "step": 114
    },
    {
      "epoch": 0.5257142857142857,
      "grad_norm": 0.12151399254798889,
      "learning_rate": 4.17702704859633e-05,
      "loss": 1.2808,
      "step": 115
    },
    {
      "epoch": 0.5302857142857142,
      "grad_norm": 0.12194976210594177,
      "learning_rate": 4.095597328339452e-05,
      "loss": 1.2309,
      "step": 116
    },
    {
      "epoch": 0.5348571428571428,
      "grad_norm": 0.12283765524625778,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 1.1096,
      "step": 117
    },
    {
      "epoch": 0.5394285714285715,
      "grad_norm": 0.11236543208360672,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.0665,
      "step": 118
    },
    {
      "epoch": 0.544,
      "grad_norm": 0.12428522109985352,
      "learning_rate": 3.852880399766243e-05,
      "loss": 1.1573,
      "step": 119
    },
    {
      "epoch": 0.5485714285714286,
      "grad_norm": 0.12272154539823532,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.1603,
      "step": 120
    },
    {
      "epoch": 0.5531428571428572,
      "grad_norm": 0.12912262976169586,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 1.1983,
      "step": 121
    },
    {
      "epoch": 0.5577142857142857,
      "grad_norm": 0.13225367665290833,
      "learning_rate": 3.612985456190778e-05,
      "loss": 1.1522,
      "step": 122
    },
    {
      "epoch": 0.5622857142857143,
      "grad_norm": 0.13284333050251007,
      "learning_rate": 3.533749813077677e-05,
      "loss": 1.1714,
      "step": 123
    },
    {
      "epoch": 0.5668571428571428,
      "grad_norm": 0.13020169734954834,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.2706,
      "step": 124
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.12579239904880524,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.2584,
      "step": 125
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.1312934309244156,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.2707,
      "step": 126
    },
    {
      "epoch": 0.5805714285714285,
      "grad_norm": 0.13396725058555603,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.2616,
      "step": 127
    },
    {
      "epoch": 0.5851428571428572,
      "grad_norm": 0.1308090090751648,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.2362,
      "step": 128
    },
    {
      "epoch": 0.5897142857142857,
      "grad_norm": 0.11060762405395508,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.1191,
      "step": 129
    },
    {
      "epoch": 0.5942857142857143,
      "grad_norm": 0.13338711857795715,
      "learning_rate": 2.991522876735154e-05,
      "loss": 1.2162,
      "step": 130
    },
    {
      "epoch": 0.5988571428571429,
      "grad_norm": 0.1284119039773941,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.3136,
      "step": 131
    },
    {
      "epoch": 0.6034285714285714,
      "grad_norm": 0.12226075679063797,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 1.1002,
      "step": 132
    },
    {
      "epoch": 0.608,
      "grad_norm": 0.1143375039100647,
      "learning_rate": 2.766955965735968e-05,
      "loss": 1.0917,
      "step": 133
    },
    {
      "epoch": 0.6125714285714285,
      "grad_norm": 0.13799656927585602,
      "learning_rate": 2.693294185106562e-05,
      "loss": 1.2661,
      "step": 134
    },
    {
      "epoch": 0.6171428571428571,
      "grad_norm": 0.13987775146961212,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 1.1622,
      "step": 135
    },
    {
      "epoch": 0.6217142857142857,
      "grad_norm": 0.13219866156578064,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.1466,
      "step": 136
    },
    {
      "epoch": 0.6262857142857143,
      "grad_norm": 0.1437901109457016,
      "learning_rate": 2.476172311325783e-05,
      "loss": 1.1516,
      "step": 137
    },
    {
      "epoch": 0.6308571428571429,
      "grad_norm": 0.12056322395801544,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.1359,
      "step": 138
    },
    {
      "epoch": 0.6354285714285715,
      "grad_norm": 0.1460120677947998,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.0824,
      "step": 139
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.1357252597808838,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.9541,
      "step": 140
    },
    {
      "epoch": 0.6445714285714286,
      "grad_norm": 0.1352461874485016,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.8611,
      "step": 141
    },
    {
      "epoch": 0.6491428571428571,
      "grad_norm": 0.14072394371032715,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.9675,
      "step": 142
    },
    {
      "epoch": 0.6537142857142857,
      "grad_norm": 0.13421207666397095,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.8375,
      "step": 143
    },
    {
      "epoch": 0.6582857142857143,
      "grad_norm": 0.19829463958740234,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.8216,
      "step": 144
    },
    {
      "epoch": 0.6628571428571428,
      "grad_norm": 0.26073214411735535,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.6624,
      "step": 145
    },
    {
      "epoch": 0.6674285714285715,
      "grad_norm": 0.5083465576171875,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.6684,
      "step": 146
    },
    {
      "epoch": 0.672,
      "grad_norm": 0.7992666959762573,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.7886,
      "step": 147
    },
    {
      "epoch": 0.6765714285714286,
      "grad_norm": 1.3631800413131714,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.5941,
      "step": 148
    },
    {
      "epoch": 0.6811428571428572,
      "grad_norm": 1.78507399559021,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.495,
      "step": 149
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.9834667444229126,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.2859,
      "step": 150
    },
    {
      "epoch": 0.6857142857142857,
      "eval_loss": 1.1018810272216797,
      "eval_runtime": 40.5385,
      "eval_samples_per_second": 9.102,
      "eval_steps_per_second": 2.294,
      "step": 150
    },
    {
      "epoch": 0.6902857142857143,
      "grad_norm": 0.06620239466428757,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.5693,
      "step": 151
    },
    {
      "epoch": 0.6948571428571428,
      "grad_norm": 0.10869189351797104,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.3286,
      "step": 152
    },
    {
      "epoch": 0.6994285714285714,
      "grad_norm": 0.11447346210479736,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.1723,
      "step": 153
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.1504087895154953,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.0937,
      "step": 154
    },
    {
      "epoch": 0.7085714285714285,
      "grad_norm": 0.11940091103315353,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.2761,
      "step": 155
    },
    {
      "epoch": 0.7131428571428572,
      "grad_norm": 0.1297205686569214,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.3768,
      "step": 156
    },
    {
      "epoch": 0.7177142857142857,
      "grad_norm": 0.1263613998889923,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.2449,
      "step": 157
    },
    {
      "epoch": 0.7222857142857143,
      "grad_norm": 0.12493669241666794,
      "learning_rate": 1.157994445715706e-05,
      "loss": 1.2967,
      "step": 158
    },
    {
      "epoch": 0.7268571428571429,
      "grad_norm": 0.12213616818189621,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 1.3456,
      "step": 159
    },
    {
      "epoch": 0.7314285714285714,
      "grad_norm": 0.1282569169998169,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 1.3448,
      "step": 160
    },
    {
      "epoch": 0.736,
      "grad_norm": 0.12678173184394836,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.2364,
      "step": 161
    },
    {
      "epoch": 0.7405714285714285,
      "grad_norm": 0.12824153900146484,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.2237,
      "step": 162
    },
    {
      "epoch": 0.7451428571428571,
      "grad_norm": 0.12507791817188263,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.3304,
      "step": 163
    },
    {
      "epoch": 0.7497142857142857,
      "grad_norm": 0.11987890303134918,
      "learning_rate": 8.599558442598998e-06,
      "loss": 1.2252,
      "step": 164
    },
    {
      "epoch": 0.7542857142857143,
      "grad_norm": 0.1251509189605713,
      "learning_rate": 8.141676086873572e-06,
      "loss": 1.1629,
      "step": 165
    },
    {
      "epoch": 0.7588571428571429,
      "grad_norm": 0.12663280963897705,
      "learning_rate": 7.695237378953223e-06,
      "loss": 1.2431,
      "step": 166
    },
    {
      "epoch": 0.7634285714285715,
      "grad_norm": 0.12671197950839996,
      "learning_rate": 7.260364370723044e-06,
      "loss": 1.3224,
      "step": 167
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.13048866391181946,
      "learning_rate": 6.837175952121306e-06,
      "loss": 1.102,
      "step": 168
    },
    {
      "epoch": 0.7725714285714286,
      "grad_norm": 0.12899628281593323,
      "learning_rate": 6.425787818636131e-06,
      "loss": 1.2586,
      "step": 169
    },
    {
      "epoch": 0.7771428571428571,
      "grad_norm": 0.12939657270908356,
      "learning_rate": 6.026312439675552e-06,
      "loss": 1.2227,
      "step": 170
    },
    {
      "epoch": 0.7817142857142857,
      "grad_norm": 0.12270830571651459,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 1.1114,
      "step": 171
    },
    {
      "epoch": 0.7862857142857143,
      "grad_norm": 0.1278485506772995,
      "learning_rate": 5.263533508961827e-06,
      "loss": 1.1537,
      "step": 172
    },
    {
      "epoch": 0.7908571428571428,
      "grad_norm": 0.12322932481765747,
      "learning_rate": 4.900438493352055e-06,
      "loss": 1.0861,
      "step": 173
    },
    {
      "epoch": 0.7954285714285714,
      "grad_norm": 0.12637890875339508,
      "learning_rate": 4.549673247541875e-06,
      "loss": 1.1709,
      "step": 174
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.12584732472896576,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.1896,
      "step": 175
    },
    {
      "epoch": 0.8045714285714286,
      "grad_norm": 0.12563082575798035,
      "learning_rate": 3.885512251130763e-06,
      "loss": 1.2973,
      "step": 176
    },
    {
      "epoch": 0.8091428571428572,
      "grad_norm": 0.13145104050636292,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 1.108,
      "step": 177
    },
    {
      "epoch": 0.8137142857142857,
      "grad_norm": 0.12037256360054016,
      "learning_rate": 3.271776770026963e-06,
      "loss": 1.1991,
      "step": 178
    },
    {
      "epoch": 0.8182857142857143,
      "grad_norm": 0.12561893463134766,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 1.2929,
      "step": 179
    },
    {
      "epoch": 0.8228571428571428,
      "grad_norm": 0.14148080348968506,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 1.3213,
      "step": 180
    },
    {
      "epoch": 0.8274285714285714,
      "grad_norm": 0.11910226941108704,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.1171,
      "step": 181
    },
    {
      "epoch": 0.832,
      "grad_norm": 0.12105397135019302,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 1.1978,
      "step": 182
    },
    {
      "epoch": 0.8365714285714285,
      "grad_norm": 0.12134953588247299,
      "learning_rate": 1.962316193157593e-06,
      "loss": 1.073,
      "step": 183
    },
    {
      "epoch": 0.8411428571428572,
      "grad_norm": 0.1257394552230835,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 1.1558,
      "step": 184
    },
    {
      "epoch": 0.8457142857142858,
      "grad_norm": 0.14201831817626953,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 1.2635,
      "step": 185
    },
    {
      "epoch": 0.8502857142857143,
      "grad_norm": 0.12398520857095718,
      "learning_rate": 1.333670137599713e-06,
      "loss": 1.1303,
      "step": 186
    },
    {
      "epoch": 0.8548571428571429,
      "grad_norm": 0.12353026121854782,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 1.0743,
      "step": 187
    },
    {
      "epoch": 0.8594285714285714,
      "grad_norm": 0.15189006924629211,
      "learning_rate": 9.810017062595322e-07,
      "loss": 1.0511,
      "step": 188
    },
    {
      "epoch": 0.864,
      "grad_norm": 0.1122622936964035,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.9406,
      "step": 189
    },
    {
      "epoch": 0.8685714285714285,
      "grad_norm": 0.12416361272335052,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.9768,
      "step": 190
    },
    {
      "epoch": 0.8731428571428571,
      "grad_norm": 0.15343773365020752,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.8199,
      "step": 191
    },
    {
      "epoch": 0.8777142857142857,
      "grad_norm": 0.1438433676958084,
      "learning_rate": 4.367965336512403e-07,
      "loss": 1.053,
      "step": 192
    },
    {
      "epoch": 0.8822857142857143,
      "grad_norm": 0.14729343354701996,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.8999,
      "step": 193
    },
    {
      "epoch": 0.8868571428571429,
      "grad_norm": 0.15465423464775085,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.8475,
      "step": 194
    },
    {
      "epoch": 0.8914285714285715,
      "grad_norm": 0.17870652675628662,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.8663,
      "step": 195
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.23823891580104828,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.624,
      "step": 196
    },
    {
      "epoch": 0.9005714285714286,
      "grad_norm": 0.36448702216148376,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.6617,
      "step": 197
    },
    {
      "epoch": 0.9051428571428571,
      "grad_norm": 0.4958615303039551,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.3012,
      "step": 198
    },
    {
      "epoch": 0.9097142857142857,
      "grad_norm": 0.8388349413871765,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.3156,
      "step": 199
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 0.7268200516700745,
      "learning_rate": 0.0,
      "loss": 0.3013,
      "step": 200
    },
    {
      "epoch": 0.9142857142857143,
      "eval_loss": 1.090016484260559,
      "eval_runtime": 40.9763,
      "eval_samples_per_second": 9.005,
      "eval_steps_per_second": 2.27,
      "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": 4.121849236511785e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}