{
  "best_metric": 0.35382401943206787,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.9900990099009901,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0049504950495049506,
      "grad_norm": 4.0363922119140625,
      "learning_rate": 1e-05,
      "loss": 1.5231,
      "step": 1
    },
    {
      "epoch": 0.0049504950495049506,
      "eval_loss": 2.3876399993896484,
      "eval_runtime": 7.6773,
      "eval_samples_per_second": 44.287,
      "eval_steps_per_second": 11.072,
      "step": 1
    },
    {
      "epoch": 0.009900990099009901,
      "grad_norm": 5.379367351531982,
      "learning_rate": 2e-05,
      "loss": 1.7801,
      "step": 2
    },
    {
      "epoch": 0.01485148514851485,
      "grad_norm": 5.2716546058654785,
      "learning_rate": 3e-05,
      "loss": 1.9039,
      "step": 3
    },
    {
      "epoch": 0.019801980198019802,
      "grad_norm": 5.414140224456787,
      "learning_rate": 4e-05,
      "loss": 2.0719,
      "step": 4
    },
    {
      "epoch": 0.024752475247524754,
      "grad_norm": 4.245809555053711,
      "learning_rate": 5e-05,
      "loss": 1.7895,
      "step": 5
    },
    {
      "epoch": 0.0297029702970297,
      "grad_norm": 3.29105281829834,
      "learning_rate": 6e-05,
      "loss": 1.4551,
      "step": 6
    },
    {
      "epoch": 0.034653465346534656,
      "grad_norm": 3.049424409866333,
      "learning_rate": 7e-05,
      "loss": 1.4211,
      "step": 7
    },
    {
      "epoch": 0.039603960396039604,
      "grad_norm": 3.128674268722534,
      "learning_rate": 8e-05,
      "loss": 1.2435,
      "step": 8
    },
    {
      "epoch": 0.04455445544554455,
      "grad_norm": 3.60176420211792,
      "learning_rate": 9e-05,
      "loss": 1.2535,
      "step": 9
    },
    {
      "epoch": 0.04950495049504951,
      "grad_norm": 3.4779539108276367,
      "learning_rate": 0.0001,
      "loss": 1.2348,
      "step": 10
    },
    {
      "epoch": 0.054455445544554455,
      "grad_norm": 4.186489105224609,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.5862,
      "step": 11
    },
    {
      "epoch": 0.0594059405940594,
      "grad_norm": 3.794402837753296,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.2125,
      "step": 12
    },
    {
      "epoch": 0.06435643564356436,
      "grad_norm": 3.6841089725494385,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.1257,
      "step": 13
    },
    {
      "epoch": 0.06930693069306931,
      "grad_norm": 3.541832447052002,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.9643,
      "step": 14
    },
    {
      "epoch": 0.07425742574257425,
      "grad_norm": 2.9282495975494385,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.8972,
      "step": 15
    },
    {
      "epoch": 0.07920792079207921,
      "grad_norm": 3.8906664848327637,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.9592,
      "step": 16
    },
    {
      "epoch": 0.08415841584158416,
      "grad_norm": 3.1675353050231934,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.0074,
      "step": 17
    },
    {
      "epoch": 0.0891089108910891,
      "grad_norm": 3.6370787620544434,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.9837,
      "step": 18
    },
    {
      "epoch": 0.09405940594059406,
      "grad_norm": 4.912875652313232,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.0028,
      "step": 19
    },
    {
      "epoch": 0.09900990099009901,
      "grad_norm": 4.489631175994873,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.9957,
      "step": 20
    },
    {
      "epoch": 0.10396039603960396,
      "grad_norm": 5.736670017242432,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.0093,
      "step": 21
    },
    {
      "epoch": 0.10891089108910891,
      "grad_norm": 4.6281914710998535,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.9519,
      "step": 22
    },
    {
      "epoch": 0.11386138613861387,
      "grad_norm": 2.9127309322357178,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.8644,
      "step": 23
    },
    {
      "epoch": 0.1188118811881188,
      "grad_norm": 2.7192933559417725,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.8126,
      "step": 24
    },
    {
      "epoch": 0.12376237623762376,
      "grad_norm": 2.676409959793091,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.8211,
      "step": 25
    },
    {
      "epoch": 0.12871287128712872,
      "grad_norm": 2.654803514480591,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.9392,
      "step": 26
    },
    {
      "epoch": 0.13366336633663367,
      "grad_norm": 2.25703763961792,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.6847,
      "step": 27
    },
    {
      "epoch": 0.13861386138613863,
      "grad_norm": 1.4357645511627197,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.6258,
      "step": 28
    },
    {
      "epoch": 0.14356435643564355,
      "grad_norm": 1.5949382781982422,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.6638,
      "step": 29
    },
    {
      "epoch": 0.1485148514851485,
      "grad_norm": 1.9037044048309326,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.7578,
      "step": 30
    },
    {
      "epoch": 0.15346534653465346,
      "grad_norm": 2.5311505794525146,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.6685,
      "step": 31
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 1.7887130975723267,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.6084,
      "step": 32
    },
    {
      "epoch": 0.16336633663366337,
      "grad_norm": 1.8337292671203613,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.6913,
      "step": 33
    },
    {
      "epoch": 0.16831683168316833,
      "grad_norm": 1.5724831819534302,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.5982,
      "step": 34
    },
    {
      "epoch": 0.17326732673267325,
      "grad_norm": 2.1188621520996094,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.6669,
      "step": 35
    },
    {
      "epoch": 0.1782178217821782,
      "grad_norm": 1.9037306308746338,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.7758,
      "step": 36
    },
    {
      "epoch": 0.18316831683168316,
      "grad_norm": 1.5339856147766113,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.5242,
      "step": 37
    },
    {
      "epoch": 0.18811881188118812,
      "grad_norm": 1.557191252708435,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.5665,
      "step": 38
    },
    {
      "epoch": 0.19306930693069307,
      "grad_norm": 1.2079412937164307,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.4749,
      "step": 39
    },
    {
      "epoch": 0.19801980198019803,
      "grad_norm": 1.3262015581130981,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.4319,
      "step": 40
    },
    {
      "epoch": 0.20297029702970298,
      "grad_norm": 1.26003897190094,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.448,
      "step": 41
    },
    {
      "epoch": 0.2079207920792079,
      "grad_norm": 1.5719279050827026,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.525,
      "step": 42
    },
    {
      "epoch": 0.21287128712871287,
      "grad_norm": 1.5337423086166382,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.4581,
      "step": 43
    },
    {
      "epoch": 0.21782178217821782,
      "grad_norm": 1.473077654838562,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.4919,
      "step": 44
    },
    {
      "epoch": 0.22277227722772278,
      "grad_norm": 1.8897618055343628,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.5695,
      "step": 45
    },
    {
      "epoch": 0.22772277227722773,
      "grad_norm": 1.5810127258300781,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.4473,
      "step": 46
    },
    {
      "epoch": 0.23267326732673269,
      "grad_norm": 2.028890609741211,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.5805,
      "step": 47
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 2.4297709465026855,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6408,
      "step": 48
    },
    {
      "epoch": 0.24257425742574257,
      "grad_norm": 1.9278923273086548,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.612,
      "step": 49
    },
    {
      "epoch": 0.24752475247524752,
      "grad_norm": 2.2322072982788086,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.5853,
      "step": 50
    },
    {
      "epoch": 0.24752475247524752,
      "eval_loss": 0.603557288646698,
      "eval_runtime": 7.6278,
      "eval_samples_per_second": 44.574,
      "eval_steps_per_second": 11.143,
      "step": 50
    },
    {
      "epoch": 0.2524752475247525,
      "grad_norm": 1.3016430139541626,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.6657,
      "step": 51
    },
    {
      "epoch": 0.25742574257425743,
      "grad_norm": 1.5994071960449219,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.8031,
      "step": 52
    },
    {
      "epoch": 0.2623762376237624,
      "grad_norm": 1.3239331245422363,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.6418,
      "step": 53
    },
    {
      "epoch": 0.26732673267326734,
      "grad_norm": 1.3597594499588013,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.6376,
      "step": 54
    },
    {
      "epoch": 0.2722772277227723,
      "grad_norm": 1.7413444519042969,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.787,
      "step": 55
    },
    {
      "epoch": 0.27722772277227725,
      "grad_norm": 1.236748218536377,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.5946,
      "step": 56
    },
    {
      "epoch": 0.28217821782178215,
      "grad_norm": 1.2144122123718262,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.5822,
      "step": 57
    },
    {
      "epoch": 0.2871287128712871,
      "grad_norm": 1.0981810092926025,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.5158,
      "step": 58
    },
    {
      "epoch": 0.29207920792079206,
      "grad_norm": 1.2142820358276367,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.5081,
      "step": 59
    },
    {
      "epoch": 0.297029702970297,
      "grad_norm": 1.4330949783325195,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.6918,
      "step": 60
    },
    {
      "epoch": 0.30198019801980197,
      "grad_norm": 1.489686131477356,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.6629,
      "step": 61
    },
    {
      "epoch": 0.3069306930693069,
      "grad_norm": 1.8493682146072388,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.7268,
      "step": 62
    },
    {
      "epoch": 0.3118811881188119,
      "grad_norm": 2.448539972305298,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.962,
      "step": 63
    },
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 2.0100409984588623,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.7228,
      "step": 64
    },
    {
      "epoch": 0.3217821782178218,
      "grad_norm": 1.7911760807037354,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.6958,
      "step": 65
    },
    {
      "epoch": 0.32673267326732675,
      "grad_norm": 1.8181976079940796,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.594,
      "step": 66
    },
    {
      "epoch": 0.3316831683168317,
      "grad_norm": 1.4809890985488892,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.5055,
      "step": 67
    },
    {
      "epoch": 0.33663366336633666,
      "grad_norm": 1.8599486351013184,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.6233,
      "step": 68
    },
    {
      "epoch": 0.3415841584158416,
      "grad_norm": 1.8311388492584229,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.5805,
      "step": 69
    },
    {
      "epoch": 0.3465346534653465,
      "grad_norm": 1.7418789863586426,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.6203,
      "step": 70
    },
    {
      "epoch": 0.35148514851485146,
      "grad_norm": 1.6825860738754272,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.4149,
      "step": 71
    },
    {
      "epoch": 0.3564356435643564,
      "grad_norm": 1.9092538356781006,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.5753,
      "step": 72
    },
    {
      "epoch": 0.3613861386138614,
      "grad_norm": 1.8987771272659302,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.5498,
      "step": 73
    },
    {
      "epoch": 0.36633663366336633,
      "grad_norm": 1.8307002782821655,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.5679,
      "step": 74
    },
    {
      "epoch": 0.3712871287128713,
      "grad_norm": 1.374563217163086,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.4248,
      "step": 75
    },
    {
      "epoch": 0.37623762376237624,
      "grad_norm": 1.5833649635314941,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.4819,
      "step": 76
    },
    {
      "epoch": 0.3811881188118812,
      "grad_norm": 1.6210107803344727,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.5125,
      "step": 77
    },
    {
      "epoch": 0.38613861386138615,
      "grad_norm": 1.1265801191329956,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.431,
      "step": 78
    },
    {
      "epoch": 0.3910891089108911,
      "grad_norm": 1.1712349653244019,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.4512,
      "step": 79
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 1.5375431776046753,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.4655,
      "step": 80
    },
    {
      "epoch": 0.400990099009901,
      "grad_norm": 1.3137829303741455,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.4053,
      "step": 81
    },
    {
      "epoch": 0.40594059405940597,
      "grad_norm": 1.5218427181243896,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.4578,
      "step": 82
    },
    {
      "epoch": 0.41089108910891087,
      "grad_norm": 0.9855346083641052,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.3715,
      "step": 83
    },
    {
      "epoch": 0.4158415841584158,
      "grad_norm": 1.6310359239578247,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.4805,
      "step": 84
    },
    {
      "epoch": 0.4207920792079208,
      "grad_norm": 1.4267241954803467,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.4109,
      "step": 85
    },
    {
      "epoch": 0.42574257425742573,
      "grad_norm": 1.4972106218338013,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.4521,
      "step": 86
    },
    {
      "epoch": 0.4306930693069307,
      "grad_norm": 1.5471174716949463,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.5076,
      "step": 87
    },
    {
      "epoch": 0.43564356435643564,
      "grad_norm": 1.2221630811691284,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.3226,
      "step": 88
    },
    {
      "epoch": 0.4405940594059406,
      "grad_norm": 1.1430009603500366,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.3329,
      "step": 89
    },
    {
      "epoch": 0.44554455445544555,
      "grad_norm": 0.8016707301139832,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.2989,
      "step": 90
    },
    {
      "epoch": 0.4504950495049505,
      "grad_norm": 1.0852112770080566,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.3596,
      "step": 91
    },
    {
      "epoch": 0.45544554455445546,
      "grad_norm": 1.1672810316085815,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.2913,
      "step": 92
    },
    {
      "epoch": 0.4603960396039604,
      "grad_norm": 1.1112481355667114,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.3453,
      "step": 93
    },
    {
      "epoch": 0.46534653465346537,
      "grad_norm": 1.0123038291931152,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.3255,
      "step": 94
    },
    {
      "epoch": 0.47029702970297027,
      "grad_norm": 1.550141453742981,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.3183,
      "step": 95
    },
    {
      "epoch": 0.4752475247524752,
      "grad_norm": 1.3755995035171509,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.3333,
      "step": 96
    },
    {
      "epoch": 0.4801980198019802,
      "grad_norm": 1.4137283563613892,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.3131,
      "step": 97
    },
    {
      "epoch": 0.48514851485148514,
      "grad_norm": 1.32696533203125,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.353,
      "step": 98
    },
    {
      "epoch": 0.4900990099009901,
      "grad_norm": 1.5690231323242188,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.4638,
      "step": 99
    },
    {
      "epoch": 0.49504950495049505,
      "grad_norm": 1.8760040998458862,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.5072,
      "step": 100
    },
    {
      "epoch": 0.49504950495049505,
      "eval_loss": 0.45519131422042847,
      "eval_runtime": 7.6006,
      "eval_samples_per_second": 44.733,
      "eval_steps_per_second": 11.183,
      "step": 100
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.0711307525634766,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.4319,
      "step": 101
    },
    {
      "epoch": 0.504950495049505,
      "grad_norm": 1.2302770614624023,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.6094,
      "step": 102
    },
    {
      "epoch": 0.5099009900990099,
      "grad_norm": 1.1764334440231323,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.5585,
      "step": 103
    },
    {
      "epoch": 0.5148514851485149,
      "grad_norm": 1.1770914793014526,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.487,
      "step": 104
    },
    {
      "epoch": 0.5198019801980198,
      "grad_norm": 1.222314476966858,
      "learning_rate": 5e-05,
      "loss": 0.5521,
      "step": 105
    },
    {
      "epoch": 0.5247524752475248,
      "grad_norm": 1.0521180629730225,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.5166,
      "step": 106
    },
    {
      "epoch": 0.5297029702970297,
      "grad_norm": 1.0855156183242798,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.5261,
      "step": 107
    },
    {
      "epoch": 0.5346534653465347,
      "grad_norm": 1.021121859550476,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.4556,
      "step": 108
    },
    {
      "epoch": 0.5396039603960396,
      "grad_norm": 1.0278337001800537,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.4073,
      "step": 109
    },
    {
      "epoch": 0.5445544554455446,
      "grad_norm": 1.205743432044983,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.5291,
      "step": 110
    },
    {
      "epoch": 0.5495049504950495,
      "grad_norm": 1.442887544631958,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.5629,
      "step": 111
    },
    {
      "epoch": 0.5544554455445545,
      "grad_norm": 1.8858586549758911,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.6189,
      "step": 112
    },
    {
      "epoch": 0.5594059405940595,
      "grad_norm": 1.7816182374954224,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.5683,
      "step": 113
    },
    {
      "epoch": 0.5643564356435643,
      "grad_norm": 1.6784852743148804,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.5997,
      "step": 114
    },
    {
      "epoch": 0.5693069306930693,
      "grad_norm": 1.636926531791687,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.5848,
      "step": 115
    },
    {
      "epoch": 0.5742574257425742,
      "grad_norm": 1.5364916324615479,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.5075,
      "step": 116
    },
    {
      "epoch": 0.5792079207920792,
      "grad_norm": 1.72401762008667,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.5998,
      "step": 117
    },
    {
      "epoch": 0.5841584158415841,
      "grad_norm": 1.6688166856765747,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.5977,
      "step": 118
    },
    {
      "epoch": 0.5891089108910891,
      "grad_norm": 1.5685595273971558,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.4558,
      "step": 119
    },
    {
      "epoch": 0.594059405940594,
      "grad_norm": 1.9494913816452026,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.3729,
      "step": 120
    },
    {
      "epoch": 0.599009900990099,
      "grad_norm": 2.340848922729492,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.5815,
      "step": 121
    },
    {
      "epoch": 0.6039603960396039,
      "grad_norm": 1.736649990081787,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.4583,
      "step": 122
    },
    {
      "epoch": 0.6089108910891089,
      "grad_norm": 1.1544440984725952,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.3527,
      "step": 123
    },
    {
      "epoch": 0.6138613861386139,
      "grad_norm": 1.5685001611709595,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.427,
      "step": 124
    },
    {
      "epoch": 0.6188118811881188,
      "grad_norm": 1.3388676643371582,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.3869,
      "step": 125
    },
    {
      "epoch": 0.6237623762376238,
      "grad_norm": 1.3992398977279663,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.365,
      "step": 126
    },
    {
      "epoch": 0.6287128712871287,
      "grad_norm": 1.3279718160629272,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.3935,
      "step": 127
    },
    {
      "epoch": 0.6336633663366337,
      "grad_norm": 1.3103578090667725,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.3945,
      "step": 128
    },
    {
      "epoch": 0.6386138613861386,
      "grad_norm": 1.1902642250061035,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.3283,
      "step": 129
    },
    {
      "epoch": 0.6435643564356436,
      "grad_norm": 1.2739412784576416,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.4179,
      "step": 130
    },
    {
      "epoch": 0.6485148514851485,
      "grad_norm": 1.1381021738052368,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.3612,
      "step": 131
    },
    {
      "epoch": 0.6534653465346535,
      "grad_norm": 1.169979453086853,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.326,
      "step": 132
    },
    {
      "epoch": 0.6584158415841584,
      "grad_norm": 1.1667051315307617,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.3006,
      "step": 133
    },
    {
      "epoch": 0.6633663366336634,
      "grad_norm": 1.0904052257537842,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.3061,
      "step": 134
    },
    {
      "epoch": 0.6683168316831684,
      "grad_norm": 1.1661401987075806,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.3772,
      "step": 135
    },
    {
      "epoch": 0.6732673267326733,
      "grad_norm": 1.229990005493164,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.3597,
      "step": 136
    },
    {
      "epoch": 0.6782178217821783,
      "grad_norm": 1.1400713920593262,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.3278,
      "step": 137
    },
    {
      "epoch": 0.6831683168316832,
      "grad_norm": 0.8900376558303833,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.2503,
      "step": 138
    },
    {
      "epoch": 0.6881188118811881,
      "grad_norm": 0.8603771328926086,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.2201,
      "step": 139
    },
    {
      "epoch": 0.693069306930693,
      "grad_norm": 1.010969877243042,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.2685,
      "step": 140
    },
    {
      "epoch": 0.698019801980198,
      "grad_norm": 1.0002667903900146,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.279,
      "step": 141
    },
    {
      "epoch": 0.7029702970297029,
      "grad_norm": 0.814689576625824,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.2339,
      "step": 142
    },
    {
      "epoch": 0.7079207920792079,
      "grad_norm": 0.9436227083206177,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.2686,
      "step": 143
    },
    {
      "epoch": 0.7128712871287128,
      "grad_norm": 1.1621214151382446,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.3032,
      "step": 144
    },
    {
      "epoch": 0.7178217821782178,
      "grad_norm": 0.9282111525535583,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.2794,
      "step": 145
    },
    {
      "epoch": 0.7227722772277227,
      "grad_norm": 1.688370704650879,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.2644,
      "step": 146
    },
    {
      "epoch": 0.7277227722772277,
      "grad_norm": 1.4502309560775757,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.3211,
      "step": 147
    },
    {
      "epoch": 0.7326732673267327,
      "grad_norm": 1.0946471691131592,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.2686,
      "step": 148
    },
    {
      "epoch": 0.7376237623762376,
      "grad_norm": 1.3394910097122192,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.3568,
      "step": 149
    },
    {
      "epoch": 0.7425742574257426,
      "grad_norm": 1.6002285480499268,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.3511,
      "step": 150
    },
    {
      "epoch": 0.7425742574257426,
      "eval_loss": 0.385884553194046,
      "eval_runtime": 7.6067,
      "eval_samples_per_second": 44.698,
      "eval_steps_per_second": 11.174,
      "step": 150
    },
    {
      "epoch": 0.7475247524752475,
      "grad_norm": 0.8451173901557922,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.3671,
      "step": 151
    },
    {
      "epoch": 0.7524752475247525,
      "grad_norm": 1.1665725708007812,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.4342,
      "step": 152
    },
    {
      "epoch": 0.7574257425742574,
      "grad_norm": 1.3639039993286133,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.5431,
      "step": 153
    },
    {
      "epoch": 0.7623762376237624,
      "grad_norm": 1.141710877418518,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.4302,
      "step": 154
    },
    {
      "epoch": 0.7673267326732673,
      "grad_norm": 1.1131010055541992,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.4746,
      "step": 155
    },
    {
      "epoch": 0.7722772277227723,
      "grad_norm": 1.3508762121200562,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.5165,
      "step": 156
    },
    {
      "epoch": 0.7772277227722773,
      "grad_norm": 1.143507480621338,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.5402,
      "step": 157
    },
    {
      "epoch": 0.7821782178217822,
      "grad_norm": 1.0732407569885254,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.4144,
      "step": 158
    },
    {
      "epoch": 0.7871287128712872,
      "grad_norm": 1.130454659461975,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.3842,
      "step": 159
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 1.368780493736267,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.452,
      "step": 160
    },
    {
      "epoch": 0.7970297029702971,
      "grad_norm": 1.3407702445983887,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.4884,
      "step": 161
    },
    {
      "epoch": 0.801980198019802,
      "grad_norm": 2.0520031452178955,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.5803,
      "step": 162
    },
    {
      "epoch": 0.806930693069307,
      "grad_norm": 1.4588428735733032,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.4168,
      "step": 163
    },
    {
      "epoch": 0.8118811881188119,
      "grad_norm": 1.639197826385498,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.4113,
      "step": 164
    },
    {
      "epoch": 0.8168316831683168,
      "grad_norm": 1.9827513694763184,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.6263,
      "step": 165
    },
    {
      "epoch": 0.8217821782178217,
      "grad_norm": 1.9295234680175781,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.5485,
      "step": 166
    },
    {
      "epoch": 0.8267326732673267,
      "grad_norm": 1.7602345943450928,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.4543,
      "step": 167
    },
    {
      "epoch": 0.8316831683168316,
      "grad_norm": 1.925018548965454,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.4899,
      "step": 168
    },
    {
      "epoch": 0.8366336633663366,
      "grad_norm": 1.8085609674453735,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.4055,
      "step": 169
    },
    {
      "epoch": 0.8415841584158416,
      "grad_norm": 2.4782073497772217,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.4601,
      "step": 170
    },
    {
      "epoch": 0.8465346534653465,
      "grad_norm": 2.6012320518493652,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.573,
      "step": 171
    },
    {
      "epoch": 0.8514851485148515,
      "grad_norm": 1.1226013898849487,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.2693,
      "step": 172
    },
    {
      "epoch": 0.8564356435643564,
      "grad_norm": 1.288741946220398,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.3039,
      "step": 173
    },
    {
      "epoch": 0.8613861386138614,
      "grad_norm": 1.3318202495574951,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.29,
      "step": 174
    },
    {
      "epoch": 0.8663366336633663,
      "grad_norm": 0.9293093085289001,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.3127,
      "step": 175
    },
    {
      "epoch": 0.8712871287128713,
      "grad_norm": 1.2437506914138794,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.3347,
      "step": 176
    },
    {
      "epoch": 0.8762376237623762,
      "grad_norm": 0.9891517758369446,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.325,
      "step": 177
    },
    {
      "epoch": 0.8811881188118812,
      "grad_norm": 0.9279931783676147,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.2567,
      "step": 178
    },
    {
      "epoch": 0.8861386138613861,
      "grad_norm": 0.9913224577903748,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.3129,
      "step": 179
    },
    {
      "epoch": 0.8910891089108911,
      "grad_norm": 1.4739348888397217,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.343,
      "step": 180
    },
    {
      "epoch": 0.8960396039603961,
      "grad_norm": 1.0805634260177612,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.2615,
      "step": 181
    },
    {
      "epoch": 0.900990099009901,
      "grad_norm": 1.5693432092666626,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.2474,
      "step": 182
    },
    {
      "epoch": 0.905940594059406,
      "grad_norm": 0.9433674216270447,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.2278,
      "step": 183
    },
    {
      "epoch": 0.9108910891089109,
      "grad_norm": 1.083784580230713,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.2215,
      "step": 184
    },
    {
      "epoch": 0.9158415841584159,
      "grad_norm": 0.9377012252807617,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.2708,
      "step": 185
    },
    {
      "epoch": 0.9207920792079208,
      "grad_norm": 1.4501932859420776,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.3994,
      "step": 186
    },
    {
      "epoch": 0.9257425742574258,
      "grad_norm": 0.8963311910629272,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.184,
      "step": 187
    },
    {
      "epoch": 0.9306930693069307,
      "grad_norm": 1.0104416608810425,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.2406,
      "step": 188
    },
    {
      "epoch": 0.9356435643564357,
      "grad_norm": 0.8953194618225098,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.2624,
      "step": 189
    },
    {
      "epoch": 0.9405940594059405,
      "grad_norm": 0.7648220062255859,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.1689,
      "step": 190
    },
    {
      "epoch": 0.9455445544554455,
      "grad_norm": 0.8482292294502258,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.233,
      "step": 191
    },
    {
      "epoch": 0.9504950495049505,
      "grad_norm": 0.7362913489341736,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.2294,
      "step": 192
    },
    {
      "epoch": 0.9554455445544554,
      "grad_norm": 1.4631099700927734,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.304,
      "step": 193
    },
    {
      "epoch": 0.9603960396039604,
      "grad_norm": 1.2280524969100952,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.2425,
      "step": 194
    },
    {
      "epoch": 0.9653465346534653,
      "grad_norm": 1.192132592201233,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.2704,
      "step": 195
    },
    {
      "epoch": 0.9702970297029703,
      "grad_norm": 1.471929669380188,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.2572,
      "step": 196
    },
    {
      "epoch": 0.9752475247524752,
      "grad_norm": 1.4014310836791992,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.2678,
      "step": 197
    },
    {
      "epoch": 0.9801980198019802,
      "grad_norm": 0.9789382219314575,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.2376,
      "step": 198
    },
    {
      "epoch": 0.9851485148514851,
      "grad_norm": 1.4011307954788208,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.3814,
      "step": 199
    },
    {
      "epoch": 0.9900990099009901,
      "grad_norm": 1.5571109056472778,
      "learning_rate": 0.0,
      "loss": 0.264,
      "step": 200
    },
    {
      "epoch": 0.9900990099009901,
      "eval_loss": 0.35382401943206787,
      "eval_runtime": 7.5827,
      "eval_samples_per_second": 44.839,
      "eval_steps_per_second": 11.21,
      "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": 1.892757182349312e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}