{
  "best_metric": 0.713728129863739,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.019689399719426053,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.844699859713026e-05,
      "grad_norm": 0.21931447088718414,
      "learning_rate": 1e-05,
      "loss": 0.7888,
      "step": 1
    },
    {
      "epoch": 9.844699859713026e-05,
      "eval_loss": 1.0887796878814697,
      "eval_runtime": 1225.9081,
      "eval_samples_per_second": 13.955,
      "eval_steps_per_second": 3.489,
      "step": 1
    },
    {
      "epoch": 0.00019689399719426053,
      "grad_norm": 0.26548096537590027,
      "learning_rate": 2e-05,
      "loss": 0.9205,
      "step": 2
    },
    {
      "epoch": 0.0002953409957913908,
      "grad_norm": 0.26687607169151306,
      "learning_rate": 3e-05,
      "loss": 0.9964,
      "step": 3
    },
    {
      "epoch": 0.00039378799438852106,
      "grad_norm": 0.26905152201652527,
      "learning_rate": 4e-05,
      "loss": 0.9028,
      "step": 4
    },
    {
      "epoch": 0.0004922349929856513,
      "grad_norm": 0.26587173342704773,
      "learning_rate": 5e-05,
      "loss": 0.9232,
      "step": 5
    },
    {
      "epoch": 0.0005906819915827816,
      "grad_norm": 0.2885933518409729,
      "learning_rate": 6e-05,
      "loss": 1.0167,
      "step": 6
    },
    {
      "epoch": 0.0006891289901799119,
      "grad_norm": 0.27875348925590515,
      "learning_rate": 7e-05,
      "loss": 1.0199,
      "step": 7
    },
    {
      "epoch": 0.0007875759887770421,
      "grad_norm": 0.24131590127944946,
      "learning_rate": 8e-05,
      "loss": 0.8616,
      "step": 8
    },
    {
      "epoch": 0.0008860229873741724,
      "grad_norm": 0.21532802283763885,
      "learning_rate": 9e-05,
      "loss": 0.9318,
      "step": 9
    },
    {
      "epoch": 0.0009844699859713026,
      "grad_norm": 0.22973798215389252,
      "learning_rate": 0.0001,
      "loss": 0.868,
      "step": 10
    },
    {
      "epoch": 0.001082916984568433,
      "grad_norm": 0.2846701145172119,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.9823,
      "step": 11
    },
    {
      "epoch": 0.0011813639831655632,
      "grad_norm": 0.3354521691799164,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.9845,
      "step": 12
    },
    {
      "epoch": 0.0012798109817626934,
      "grad_norm": 0.2753160297870636,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.9054,
      "step": 13
    },
    {
      "epoch": 0.0013782579803598238,
      "grad_norm": 0.21714510023593903,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.7706,
      "step": 14
    },
    {
      "epoch": 0.001476704978956954,
      "grad_norm": 0.21817247569561005,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.8375,
      "step": 15
    },
    {
      "epoch": 0.0015751519775540842,
      "grad_norm": 0.2212737500667572,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.8784,
      "step": 16
    },
    {
      "epoch": 0.0016735989761512146,
      "grad_norm": 0.23956288397312164,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.9197,
      "step": 17
    },
    {
      "epoch": 0.0017720459747483448,
      "grad_norm": 0.2610548138618469,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.9417,
      "step": 18
    },
    {
      "epoch": 0.001870492973345475,
      "grad_norm": 0.2320639193058014,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.8603,
      "step": 19
    },
    {
      "epoch": 0.0019689399719426052,
      "grad_norm": 0.2706211507320404,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.8138,
      "step": 20
    },
    {
      "epoch": 0.002067386970539736,
      "grad_norm": 0.22753411531448364,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.871,
      "step": 21
    },
    {
      "epoch": 0.002165833969136866,
      "grad_norm": 0.22386279702186584,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.8374,
      "step": 22
    },
    {
      "epoch": 0.0022642809677339963,
      "grad_norm": 0.2489483803510666,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.8537,
      "step": 23
    },
    {
      "epoch": 0.0023627279663311265,
      "grad_norm": 0.2448405921459198,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.8944,
      "step": 24
    },
    {
      "epoch": 0.0024611749649282567,
      "grad_norm": 0.2511995732784271,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.8951,
      "step": 25
    },
    {
      "epoch": 0.002559621963525387,
      "grad_norm": 0.24290135502815247,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.8243,
      "step": 26
    },
    {
      "epoch": 0.0026580689621225175,
      "grad_norm": 0.27473941445350647,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.797,
      "step": 27
    },
    {
      "epoch": 0.0027565159607196477,
      "grad_norm": 0.2677643895149231,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.9295,
      "step": 28
    },
    {
      "epoch": 0.002854962959316778,
      "grad_norm": 0.2784513533115387,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8641,
      "step": 29
    },
    {
      "epoch": 0.002953409957913908,
      "grad_norm": 0.3006579577922821,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.808,
      "step": 30
    },
    {
      "epoch": 0.0030518569565110383,
      "grad_norm": 0.3181014657020569,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.9131,
      "step": 31
    },
    {
      "epoch": 0.0031503039551081685,
      "grad_norm": 0.3053674101829529,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.9137,
      "step": 32
    },
    {
      "epoch": 0.003248750953705299,
      "grad_norm": 0.2928068935871124,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.8306,
      "step": 33
    },
    {
      "epoch": 0.0033471979523024293,
      "grad_norm": 0.315559059381485,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.8669,
      "step": 34
    },
    {
      "epoch": 0.0034456449508995595,
      "grad_norm": 0.3292270600795746,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.8381,
      "step": 35
    },
    {
      "epoch": 0.0035440919494966897,
      "grad_norm": 0.31969425082206726,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8713,
      "step": 36
    },
    {
      "epoch": 0.00364253894809382,
      "grad_norm": 0.32400229573249817,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.9098,
      "step": 37
    },
    {
      "epoch": 0.00374098594669095,
      "grad_norm": 0.33021485805511475,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.8431,
      "step": 38
    },
    {
      "epoch": 0.0038394329452880807,
      "grad_norm": 0.3541294038295746,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.7387,
      "step": 39
    },
    {
      "epoch": 0.0039378799438852105,
      "grad_norm": 0.3819873034954071,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7871,
      "step": 40
    },
    {
      "epoch": 0.004036326942482341,
      "grad_norm": 0.35937681794166565,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.8384,
      "step": 41
    },
    {
      "epoch": 0.004134773941079472,
      "grad_norm": 0.35174474120140076,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.8232,
      "step": 42
    },
    {
      "epoch": 0.0042332209396766015,
      "grad_norm": 0.45559900999069214,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.8174,
      "step": 43
    },
    {
      "epoch": 0.004331667938273732,
      "grad_norm": 0.4459435045719147,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.9198,
      "step": 44
    },
    {
      "epoch": 0.004430114936870862,
      "grad_norm": 0.37780049443244934,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.7686,
      "step": 45
    },
    {
      "epoch": 0.0045285619354679925,
      "grad_norm": 0.396392285823822,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.8127,
      "step": 46
    },
    {
      "epoch": 0.004627008934065122,
      "grad_norm": 0.3875143527984619,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.7936,
      "step": 47
    },
    {
      "epoch": 0.004725455932662253,
      "grad_norm": 0.5138399004936218,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8257,
      "step": 48
    },
    {
      "epoch": 0.0048239029312593835,
      "grad_norm": 0.6057048439979553,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.7578,
      "step": 49
    },
    {
      "epoch": 0.004922349929856513,
      "grad_norm": 0.5793030261993408,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.7371,
      "step": 50
    },
    {
      "epoch": 0.004922349929856513,
      "eval_loss": 0.8369074463844299,
      "eval_runtime": 1233.2391,
      "eval_samples_per_second": 13.872,
      "eval_steps_per_second": 3.468,
      "step": 50
    },
    {
      "epoch": 0.005020796928453644,
      "grad_norm": 0.3462163209915161,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.7456,
      "step": 51
    },
    {
      "epoch": 0.005119243927050774,
      "grad_norm": 0.32229095697402954,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.7375,
      "step": 52
    },
    {
      "epoch": 0.005217690925647904,
      "grad_norm": 0.3058626651763916,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.8969,
      "step": 53
    },
    {
      "epoch": 0.005316137924245035,
      "grad_norm": 0.23967932164669037,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.901,
      "step": 54
    },
    {
      "epoch": 0.005414584922842165,
      "grad_norm": 0.20258808135986328,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.7634,
      "step": 55
    },
    {
      "epoch": 0.005513031921439295,
      "grad_norm": 0.19637243449687958,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.7824,
      "step": 56
    },
    {
      "epoch": 0.005611478920036425,
      "grad_norm": 0.1921221762895584,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.8371,
      "step": 57
    },
    {
      "epoch": 0.005709925918633556,
      "grad_norm": 0.2011428028345108,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.839,
      "step": 58
    },
    {
      "epoch": 0.0058083729172306855,
      "grad_norm": 0.1979961395263672,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.8902,
      "step": 59
    },
    {
      "epoch": 0.005906819915827816,
      "grad_norm": 0.19705188274383545,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.7727,
      "step": 60
    },
    {
      "epoch": 0.006005266914424947,
      "grad_norm": 0.25883176922798157,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.8138,
      "step": 61
    },
    {
      "epoch": 0.0061037139130220765,
      "grad_norm": 0.20465119183063507,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.9098,
      "step": 62
    },
    {
      "epoch": 0.006202160911619207,
      "grad_norm": 0.3072572350502014,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.8513,
      "step": 63
    },
    {
      "epoch": 0.006300607910216337,
      "grad_norm": 0.19361186027526855,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.7853,
      "step": 64
    },
    {
      "epoch": 0.0063990549088134676,
      "grad_norm": 0.21530841290950775,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.7405,
      "step": 65
    },
    {
      "epoch": 0.006497501907410598,
      "grad_norm": 0.2175769805908203,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.8465,
      "step": 66
    },
    {
      "epoch": 0.006595948906007728,
      "grad_norm": 0.2128111720085144,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.7373,
      "step": 67
    },
    {
      "epoch": 0.006694395904604859,
      "grad_norm": 0.20716065168380737,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.7449,
      "step": 68
    },
    {
      "epoch": 0.006792842903201988,
      "grad_norm": 0.21437467634677887,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.8706,
      "step": 69
    },
    {
      "epoch": 0.006891289901799119,
      "grad_norm": 0.23659253120422363,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.8256,
      "step": 70
    },
    {
      "epoch": 0.006989736900396249,
      "grad_norm": 0.22335539758205414,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.7551,
      "step": 71
    },
    {
      "epoch": 0.007088183898993379,
      "grad_norm": 0.26969385147094727,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.8186,
      "step": 72
    },
    {
      "epoch": 0.00718663089759051,
      "grad_norm": 0.2806910276412964,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.8851,
      "step": 73
    },
    {
      "epoch": 0.00728507789618764,
      "grad_norm": 0.23838673532009125,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.8316,
      "step": 74
    },
    {
      "epoch": 0.00738352489478477,
      "grad_norm": 0.26035404205322266,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.7435,
      "step": 75
    },
    {
      "epoch": 0.0074819718933819,
      "grad_norm": 0.2508975565433502,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.7958,
      "step": 76
    },
    {
      "epoch": 0.007580418891979031,
      "grad_norm": 0.27082180976867676,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.8741,
      "step": 77
    },
    {
      "epoch": 0.007678865890576161,
      "grad_norm": 0.24881905317306519,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.7674,
      "step": 78
    },
    {
      "epoch": 0.007777312889173291,
      "grad_norm": 0.26742738485336304,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.6847,
      "step": 79
    },
    {
      "epoch": 0.007875759887770421,
      "grad_norm": 0.26285481452941895,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.8207,
      "step": 80
    },
    {
      "epoch": 0.007974206886367552,
      "grad_norm": 0.290134459733963,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.8198,
      "step": 81
    },
    {
      "epoch": 0.008072653884964682,
      "grad_norm": 0.2928304076194763,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.8518,
      "step": 82
    },
    {
      "epoch": 0.008171100883561813,
      "grad_norm": 0.29648715257644653,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.8232,
      "step": 83
    },
    {
      "epoch": 0.008269547882158943,
      "grad_norm": 0.29686883091926575,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.8235,
      "step": 84
    },
    {
      "epoch": 0.008367994880756072,
      "grad_norm": 0.3135792016983032,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.7695,
      "step": 85
    },
    {
      "epoch": 0.008466441879353203,
      "grad_norm": 0.3304945230484009,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8505,
      "step": 86
    },
    {
      "epoch": 0.008564888877950334,
      "grad_norm": 0.38309305906295776,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.7619,
      "step": 87
    },
    {
      "epoch": 0.008663335876547464,
      "grad_norm": 0.3567273020744324,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.7721,
      "step": 88
    },
    {
      "epoch": 0.008761782875144595,
      "grad_norm": 0.3431703448295593,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.6386,
      "step": 89
    },
    {
      "epoch": 0.008860229873741724,
      "grad_norm": 0.3653334975242615,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.74,
      "step": 90
    },
    {
      "epoch": 0.008958676872338854,
      "grad_norm": 0.3862167000770569,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.7903,
      "step": 91
    },
    {
      "epoch": 0.009057123870935985,
      "grad_norm": 0.37674641609191895,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.6979,
      "step": 92
    },
    {
      "epoch": 0.009155570869533116,
      "grad_norm": 0.37031859159469604,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.6201,
      "step": 93
    },
    {
      "epoch": 0.009254017868130245,
      "grad_norm": 0.38617950677871704,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.639,
      "step": 94
    },
    {
      "epoch": 0.009352464866727375,
      "grad_norm": 0.44909027218818665,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.7816,
      "step": 95
    },
    {
      "epoch": 0.009450911865324506,
      "grad_norm": 0.4494996666908264,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.6847,
      "step": 96
    },
    {
      "epoch": 0.009549358863921636,
      "grad_norm": 0.47614672780036926,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.7828,
      "step": 97
    },
    {
      "epoch": 0.009647805862518767,
      "grad_norm": 0.5278090238571167,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.6683,
      "step": 98
    },
    {
      "epoch": 0.009746252861115896,
      "grad_norm": 0.5096602439880371,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.6374,
      "step": 99
    },
    {
      "epoch": 0.009844699859713027,
      "grad_norm": 0.6213982105255127,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.6035,
      "step": 100
    },
    {
      "epoch": 0.009844699859713027,
      "eval_loss": 0.7712443470954895,
      "eval_runtime": 1234.1667,
      "eval_samples_per_second": 13.862,
      "eval_steps_per_second": 3.465,
      "step": 100
    },
    {
      "epoch": 0.009943146858310157,
      "grad_norm": 0.2117316722869873,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.6478,
      "step": 101
    },
    {
      "epoch": 0.010041593856907288,
      "grad_norm": 0.29028409719467163,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.757,
      "step": 102
    },
    {
      "epoch": 0.010140040855504419,
      "grad_norm": 0.2632291913032532,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.6999,
      "step": 103
    },
    {
      "epoch": 0.010238487854101547,
      "grad_norm": 0.2688608467578888,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.7563,
      "step": 104
    },
    {
      "epoch": 0.010336934852698678,
      "grad_norm": 0.22561930119991302,
      "learning_rate": 5e-05,
      "loss": 0.663,
      "step": 105
    },
    {
      "epoch": 0.010435381851295809,
      "grad_norm": 0.28118276596069336,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.7275,
      "step": 106
    },
    {
      "epoch": 0.01053382884989294,
      "grad_norm": 0.2120283544063568,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.7665,
      "step": 107
    },
    {
      "epoch": 0.01063227584849007,
      "grad_norm": 0.19612029194831848,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.7318,
      "step": 108
    },
    {
      "epoch": 0.010730722847087199,
      "grad_norm": 0.1973535418510437,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.7975,
      "step": 109
    },
    {
      "epoch": 0.01082916984568433,
      "grad_norm": 0.2121182233095169,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.6979,
      "step": 110
    },
    {
      "epoch": 0.01092761684428146,
      "grad_norm": 0.20742741227149963,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.7165,
      "step": 111
    },
    {
      "epoch": 0.01102606384287859,
      "grad_norm": 0.22906772792339325,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.8266,
      "step": 112
    },
    {
      "epoch": 0.011124510841475721,
      "grad_norm": 0.22140882909297943,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.8134,
      "step": 113
    },
    {
      "epoch": 0.01122295784007285,
      "grad_norm": 0.22913554310798645,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.8219,
      "step": 114
    },
    {
      "epoch": 0.011321404838669981,
      "grad_norm": 0.25358617305755615,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.7703,
      "step": 115
    },
    {
      "epoch": 0.011419851837267112,
      "grad_norm": 0.22755038738250732,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.769,
      "step": 116
    },
    {
      "epoch": 0.011518298835864242,
      "grad_norm": 0.23056480288505554,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.7024,
      "step": 117
    },
    {
      "epoch": 0.011616745834461371,
      "grad_norm": 0.2450796663761139,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.7878,
      "step": 118
    },
    {
      "epoch": 0.011715192833058502,
      "grad_norm": 0.2423289567232132,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.7674,
      "step": 119
    },
    {
      "epoch": 0.011813639831655632,
      "grad_norm": 0.22621075809001923,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.7652,
      "step": 120
    },
    {
      "epoch": 0.011912086830252763,
      "grad_norm": 0.28432223200798035,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.7937,
      "step": 121
    },
    {
      "epoch": 0.012010533828849894,
      "grad_norm": 0.27227315306663513,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.8418,
      "step": 122
    },
    {
      "epoch": 0.012108980827447022,
      "grad_norm": 0.23853737115859985,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.7369,
      "step": 123
    },
    {
      "epoch": 0.012207427826044153,
      "grad_norm": 0.2696349322795868,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.8422,
      "step": 124
    },
    {
      "epoch": 0.012305874824641284,
      "grad_norm": 0.2551944851875305,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.765,
      "step": 125
    },
    {
      "epoch": 0.012404321823238414,
      "grad_norm": 0.28944340348243713,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.7678,
      "step": 126
    },
    {
      "epoch": 0.012502768821835545,
      "grad_norm": 0.2647569179534912,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.7824,
      "step": 127
    },
    {
      "epoch": 0.012601215820432674,
      "grad_norm": 0.29205837845802307,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.7412,
      "step": 128
    },
    {
      "epoch": 0.012699662819029804,
      "grad_norm": 0.3454453647136688,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.7736,
      "step": 129
    },
    {
      "epoch": 0.012798109817626935,
      "grad_norm": 0.3326926529407501,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.8246,
      "step": 130
    },
    {
      "epoch": 0.012896556816224066,
      "grad_norm": 0.35409486293792725,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.8073,
      "step": 131
    },
    {
      "epoch": 0.012995003814821196,
      "grad_norm": 0.29852956533432007,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.7263,
      "step": 132
    },
    {
      "epoch": 0.013093450813418325,
      "grad_norm": 0.3574008643627167,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.7699,
      "step": 133
    },
    {
      "epoch": 0.013191897812015456,
      "grad_norm": 0.30899107456207275,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.7821,
      "step": 134
    },
    {
      "epoch": 0.013290344810612587,
      "grad_norm": 0.330030232667923,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.7219,
      "step": 135
    },
    {
      "epoch": 0.013388791809209717,
      "grad_norm": 0.32822635769844055,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.7673,
      "step": 136
    },
    {
      "epoch": 0.013487238807806848,
      "grad_norm": 0.33065301179885864,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.7216,
      "step": 137
    },
    {
      "epoch": 0.013585685806403977,
      "grad_norm": 0.3378041386604309,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.6875,
      "step": 138
    },
    {
      "epoch": 0.013684132805001107,
      "grad_norm": 0.34303590655326843,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.6645,
      "step": 139
    },
    {
      "epoch": 0.013782579803598238,
      "grad_norm": 0.36415809392929077,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.6703,
      "step": 140
    },
    {
      "epoch": 0.013881026802195369,
      "grad_norm": 0.36245423555374146,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.6921,
      "step": 141
    },
    {
      "epoch": 0.013979473800792497,
      "grad_norm": 0.35383275151252747,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.6395,
      "step": 142
    },
    {
      "epoch": 0.014077920799389628,
      "grad_norm": 0.39118605852127075,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6994,
      "step": 143
    },
    {
      "epoch": 0.014176367797986759,
      "grad_norm": 0.4375452995300293,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.6698,
      "step": 144
    },
    {
      "epoch": 0.01427481479658389,
      "grad_norm": 0.39722150564193726,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.618,
      "step": 145
    },
    {
      "epoch": 0.01437326179518102,
      "grad_norm": 0.4284271001815796,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.5216,
      "step": 146
    },
    {
      "epoch": 0.014471708793778149,
      "grad_norm": 0.41560518741607666,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.6147,
      "step": 147
    },
    {
      "epoch": 0.01457015579237528,
      "grad_norm": 0.5448368191719055,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.5794,
      "step": 148
    },
    {
      "epoch": 0.01466860279097241,
      "grad_norm": 0.534804105758667,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.588,
      "step": 149
    },
    {
      "epoch": 0.01476704978956954,
      "grad_norm": 0.6259521245956421,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.5034,
      "step": 150
    },
    {
      "epoch": 0.01476704978956954,
      "eval_loss": 0.7229796648025513,
      "eval_runtime": 1233.2694,
      "eval_samples_per_second": 13.872,
      "eval_steps_per_second": 3.468,
      "step": 150
    },
    {
      "epoch": 0.014865496788166671,
      "grad_norm": 0.11872990429401398,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.5381,
      "step": 151
    },
    {
      "epoch": 0.0149639437867638,
      "grad_norm": 0.16087226569652557,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.6219,
      "step": 152
    },
    {
      "epoch": 0.015062390785360931,
      "grad_norm": 0.19276151061058044,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.7852,
      "step": 153
    },
    {
      "epoch": 0.015160837783958062,
      "grad_norm": 0.2047249972820282,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.7678,
      "step": 154
    },
    {
      "epoch": 0.015259284782555192,
      "grad_norm": 0.2235117405653,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.7006,
      "step": 155
    },
    {
      "epoch": 0.015357731781152323,
      "grad_norm": 0.22259381413459778,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.6795,
      "step": 156
    },
    {
      "epoch": 0.015456178779749452,
      "grad_norm": 0.24540109932422638,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.6765,
      "step": 157
    },
    {
      "epoch": 0.015554625778346582,
      "grad_norm": 0.2322072684764862,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.7638,
      "step": 158
    },
    {
      "epoch": 0.01565307277694371,
      "grad_norm": 0.24919632077217102,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.8343,
      "step": 159
    },
    {
      "epoch": 0.015751519775540842,
      "grad_norm": 0.26711204648017883,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.7332,
      "step": 160
    },
    {
      "epoch": 0.015849966774137973,
      "grad_norm": 0.27582719922065735,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.7006,
      "step": 161
    },
    {
      "epoch": 0.015948413772735103,
      "grad_norm": 0.25303563475608826,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7576,
      "step": 162
    },
    {
      "epoch": 0.016046860771332234,
      "grad_norm": 0.23663845658302307,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.7167,
      "step": 163
    },
    {
      "epoch": 0.016145307769929364,
      "grad_norm": 0.285932719707489,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.7727,
      "step": 164
    },
    {
      "epoch": 0.016243754768526495,
      "grad_norm": 0.25797122716903687,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.6777,
      "step": 165
    },
    {
      "epoch": 0.016342201767123626,
      "grad_norm": 0.24491192400455475,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.7126,
      "step": 166
    },
    {
      "epoch": 0.016440648765720756,
      "grad_norm": 0.2528302073478699,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.6801,
      "step": 167
    },
    {
      "epoch": 0.016539095764317887,
      "grad_norm": 0.33477237820625305,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.8003,
      "step": 168
    },
    {
      "epoch": 0.016637542762915014,
      "grad_norm": 0.27678564190864563,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.752,
      "step": 169
    },
    {
      "epoch": 0.016735989761512145,
      "grad_norm": 0.27296182513237,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.7445,
      "step": 170
    },
    {
      "epoch": 0.016834436760109275,
      "grad_norm": 0.2851509749889374,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.8134,
      "step": 171
    },
    {
      "epoch": 0.016932883758706406,
      "grad_norm": 0.27287691831588745,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.7649,
      "step": 172
    },
    {
      "epoch": 0.017031330757303537,
      "grad_norm": 0.31331783533096313,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.8844,
      "step": 173
    },
    {
      "epoch": 0.017129777755900667,
      "grad_norm": 0.2980450987815857,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.7613,
      "step": 174
    },
    {
      "epoch": 0.017228224754497798,
      "grad_norm": 0.2932511568069458,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.8145,
      "step": 175
    },
    {
      "epoch": 0.01732667175309493,
      "grad_norm": 0.26983147859573364,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.7504,
      "step": 176
    },
    {
      "epoch": 0.01742511875169206,
      "grad_norm": 0.3088527023792267,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.7319,
      "step": 177
    },
    {
      "epoch": 0.01752356575028919,
      "grad_norm": 0.2998616695404053,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.7396,
      "step": 178
    },
    {
      "epoch": 0.017622012748886317,
      "grad_norm": 0.3141413927078247,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.7231,
      "step": 179
    },
    {
      "epoch": 0.017720459747483448,
      "grad_norm": 0.3180513083934784,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.6967,
      "step": 180
    },
    {
      "epoch": 0.017818906746080578,
      "grad_norm": 0.32801559567451477,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.7065,
      "step": 181
    },
    {
      "epoch": 0.01791735374467771,
      "grad_norm": 0.3204004466533661,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.7107,
      "step": 182
    },
    {
      "epoch": 0.01801580074327484,
      "grad_norm": 0.3612644374370575,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.7675,
      "step": 183
    },
    {
      "epoch": 0.01811424774187197,
      "grad_norm": 0.3181191682815552,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.6571,
      "step": 184
    },
    {
      "epoch": 0.0182126947404691,
      "grad_norm": 0.3326819837093353,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.7096,
      "step": 185
    },
    {
      "epoch": 0.01831114173906623,
      "grad_norm": 0.34928813576698303,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.7198,
      "step": 186
    },
    {
      "epoch": 0.018409588737663362,
      "grad_norm": 0.43668922781944275,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.7843,
      "step": 187
    },
    {
      "epoch": 0.01850803573626049,
      "grad_norm": 0.36991435289382935,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.6687,
      "step": 188
    },
    {
      "epoch": 0.01860648273485762,
      "grad_norm": 0.339884489774704,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.7962,
      "step": 189
    },
    {
      "epoch": 0.01870492973345475,
      "grad_norm": 0.38791707158088684,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.6737,
      "step": 190
    },
    {
      "epoch": 0.01880337673205188,
      "grad_norm": 0.370029091835022,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.6745,
      "step": 191
    },
    {
      "epoch": 0.01890182373064901,
      "grad_norm": 0.37151530385017395,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.6329,
      "step": 192
    },
    {
      "epoch": 0.019000270729246142,
      "grad_norm": 0.4121430218219757,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.6694,
      "step": 193
    },
    {
      "epoch": 0.019098717727843273,
      "grad_norm": 0.4079233407974243,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.6507,
      "step": 194
    },
    {
      "epoch": 0.019197164726440404,
      "grad_norm": 0.39050987362861633,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.5617,
      "step": 195
    },
    {
      "epoch": 0.019295611725037534,
      "grad_norm": 0.4618993401527405,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.6162,
      "step": 196
    },
    {
      "epoch": 0.019394058723634665,
      "grad_norm": 0.5539295077323914,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.6005,
      "step": 197
    },
    {
      "epoch": 0.019492505722231792,
      "grad_norm": 0.5024732351303101,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.7001,
      "step": 198
    },
    {
      "epoch": 0.019590952720828923,
      "grad_norm": 0.5344691872596741,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.6903,
      "step": 199
    },
    {
      "epoch": 0.019689399719426053,
      "grad_norm": 0.6154693961143494,
      "learning_rate": 0.0,
      "loss": 0.4907,
      "step": 200
    },
    {
      "epoch": 0.019689399719426053,
      "eval_loss": 0.713728129863739,
      "eval_runtime": 1233.5004,
      "eval_samples_per_second": 13.869,
      "eval_steps_per_second": 3.467,
      "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": 2.6909537631574426e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}