{
  "best_metric": 2.1010799407958984,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.12535255405828893,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006267627702914447,
      "grad_norm": 0.17989306151866913,
      "learning_rate": 1e-05,
      "loss": 2.3289,
      "step": 1
    },
    {
      "epoch": 0.0006267627702914447,
      "eval_loss": 2.302502393722534,
      "eval_runtime": 191.9028,
      "eval_samples_per_second": 14.007,
      "eval_steps_per_second": 3.502,
      "step": 1
    },
    {
      "epoch": 0.0012535255405828893,
      "grad_norm": 0.2174198478460312,
      "learning_rate": 2e-05,
      "loss": 2.2725,
      "step": 2
    },
    {
      "epoch": 0.001880288310874334,
      "grad_norm": 0.2246280461549759,
      "learning_rate": 3e-05,
      "loss": 2.3316,
      "step": 3
    },
    {
      "epoch": 0.0025070510811657787,
      "grad_norm": 0.25297603011131287,
      "learning_rate": 4e-05,
      "loss": 2.3177,
      "step": 4
    },
    {
      "epoch": 0.0031338138514572234,
      "grad_norm": 0.2639065980911255,
      "learning_rate": 5e-05,
      "loss": 2.3036,
      "step": 5
    },
    {
      "epoch": 0.003760576621748668,
      "grad_norm": 0.25536519289016724,
      "learning_rate": 6e-05,
      "loss": 2.1546,
      "step": 6
    },
    {
      "epoch": 0.004387339392040113,
      "grad_norm": 0.2626669406890869,
      "learning_rate": 7e-05,
      "loss": 2.253,
      "step": 7
    },
    {
      "epoch": 0.005014102162331557,
      "grad_norm": 0.25562211871147156,
      "learning_rate": 8e-05,
      "loss": 2.2884,
      "step": 8
    },
    {
      "epoch": 0.005640864932623002,
      "grad_norm": 0.26706206798553467,
      "learning_rate": 9e-05,
      "loss": 2.3349,
      "step": 9
    },
    {
      "epoch": 0.006267627702914447,
      "grad_norm": 0.28348034620285034,
      "learning_rate": 0.0001,
      "loss": 2.2637,
      "step": 10
    },
    {
      "epoch": 0.006894390473205891,
      "grad_norm": 0.29069045186042786,
      "learning_rate": 9.999316524962345e-05,
      "loss": 2.2766,
      "step": 11
    },
    {
      "epoch": 0.007521153243497336,
      "grad_norm": 0.28807488083839417,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.2541,
      "step": 12
    },
    {
      "epoch": 0.00814791601378878,
      "grad_norm": 0.32378649711608887,
      "learning_rate": 9.993849845741524e-05,
      "loss": 2.1772,
      "step": 13
    },
    {
      "epoch": 0.008774678784080225,
      "grad_norm": 0.3082554340362549,
      "learning_rate": 9.989068136093873e-05,
      "loss": 2.2968,
      "step": 14
    },
    {
      "epoch": 0.00940144155437167,
      "grad_norm": 0.3320292830467224,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.1518,
      "step": 15
    },
    {
      "epoch": 0.010028204324663115,
      "grad_norm": 0.3083231449127197,
      "learning_rate": 9.975414512725057e-05,
      "loss": 2.1442,
      "step": 16
    },
    {
      "epoch": 0.01065496709495456,
      "grad_norm": 0.28040799498558044,
      "learning_rate": 9.966546331768191e-05,
      "loss": 2.2475,
      "step": 17
    },
    {
      "epoch": 0.011281729865246004,
      "grad_norm": 0.2757704257965088,
      "learning_rate": 9.956320346634876e-05,
      "loss": 2.2948,
      "step": 18
    },
    {
      "epoch": 0.011908492635537449,
      "grad_norm": 0.29858461022377014,
      "learning_rate": 9.944739353007344e-05,
      "loss": 2.2137,
      "step": 19
    },
    {
      "epoch": 0.012535255405828893,
      "grad_norm": 0.28068676590919495,
      "learning_rate": 9.931806517013612e-05,
      "loss": 2.3203,
      "step": 20
    },
    {
      "epoch": 0.013162018176120338,
      "grad_norm": 0.28311464190483093,
      "learning_rate": 9.917525374361912e-05,
      "loss": 2.221,
      "step": 21
    },
    {
      "epoch": 0.013788780946411783,
      "grad_norm": 0.2995685636997223,
      "learning_rate": 9.901899829374047e-05,
      "loss": 2.2551,
      "step": 22
    },
    {
      "epoch": 0.014415543716703227,
      "grad_norm": 0.2771846055984497,
      "learning_rate": 9.884934153917997e-05,
      "loss": 2.1774,
      "step": 23
    },
    {
      "epoch": 0.015042306486994672,
      "grad_norm": 0.2770800292491913,
      "learning_rate": 9.86663298624003e-05,
      "loss": 2.0918,
      "step": 24
    },
    {
      "epoch": 0.015669069257286117,
      "grad_norm": 0.27206823229789734,
      "learning_rate": 9.847001329696653e-05,
      "loss": 2.2587,
      "step": 25
    },
    {
      "epoch": 0.01629583202757756,
      "grad_norm": 0.2770025134086609,
      "learning_rate": 9.826044551386744e-05,
      "loss": 2.2041,
      "step": 26
    },
    {
      "epoch": 0.016922594797869006,
      "grad_norm": 0.3041519522666931,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.9802,
      "step": 27
    },
    {
      "epoch": 0.01754935756816045,
      "grad_norm": 0.2974833846092224,
      "learning_rate": 9.780178907671789e-05,
      "loss": 2.0782,
      "step": 28
    },
    {
      "epoch": 0.018176120338451895,
      "grad_norm": 0.31385889649391174,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.1746,
      "step": 29
    },
    {
      "epoch": 0.01880288310874334,
      "grad_norm": 0.306844562292099,
      "learning_rate": 9.729086208503174e-05,
      "loss": 2.0667,
      "step": 30
    },
    {
      "epoch": 0.019429645879034785,
      "grad_norm": 0.3041130006313324,
      "learning_rate": 9.701596950580806e-05,
      "loss": 2.1998,
      "step": 31
    },
    {
      "epoch": 0.02005640864932623,
      "grad_norm": 0.30600443482398987,
      "learning_rate": 9.672822322997305e-05,
      "loss": 2.2078,
      "step": 32
    },
    {
      "epoch": 0.020683171419617674,
      "grad_norm": 0.3181498348712921,
      "learning_rate": 9.642770192448536e-05,
      "loss": 2.1901,
      "step": 33
    },
    {
      "epoch": 0.02130993418990912,
      "grad_norm": 0.3058410584926605,
      "learning_rate": 9.611448774886924e-05,
      "loss": 2.1563,
      "step": 34
    },
    {
      "epoch": 0.021936696960200563,
      "grad_norm": 0.33542245626449585,
      "learning_rate": 9.578866633275288e-05,
      "loss": 2.009,
      "step": 35
    },
    {
      "epoch": 0.022563459730492008,
      "grad_norm": 0.3565526604652405,
      "learning_rate": 9.545032675245813e-05,
      "loss": 2.0079,
      "step": 36
    },
    {
      "epoch": 0.023190222500783453,
      "grad_norm": 0.3585152328014374,
      "learning_rate": 9.509956150664796e-05,
      "loss": 2.1162,
      "step": 37
    },
    {
      "epoch": 0.023816985271074897,
      "grad_norm": 0.35241132974624634,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.2078,
      "step": 38
    },
    {
      "epoch": 0.024443748041366342,
      "grad_norm": 0.3358365595340729,
      "learning_rate": 9.43611409721806e-05,
      "loss": 2.0413,
      "step": 39
    },
    {
      "epoch": 0.025070510811657787,
      "grad_norm": 0.3380126357078552,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.9823,
      "step": 40
    },
    {
      "epoch": 0.02569727358194923,
      "grad_norm": 0.3644865155220032,
      "learning_rate": 9.357421218136386e-05,
      "loss": 2.2637,
      "step": 41
    },
    {
      "epoch": 0.026324036352240676,
      "grad_norm": 0.3626578450202942,
      "learning_rate": 9.316282404787871e-05,
      "loss": 2.0835,
      "step": 42
    },
    {
      "epoch": 0.02695079912253212,
      "grad_norm": 0.3971650004386902,
      "learning_rate": 9.273963562927695e-05,
      "loss": 2.0848,
      "step": 43
    },
    {
      "epoch": 0.027577561892823566,
      "grad_norm": 0.3945768475532532,
      "learning_rate": 9.230476262104677e-05,
      "loss": 2.0735,
      "step": 44
    },
    {
      "epoch": 0.02820432466311501,
      "grad_norm": 0.4012565016746521,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.8303,
      "step": 45
    },
    {
      "epoch": 0.028831087433406455,
      "grad_norm": 0.4839591979980469,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.948,
      "step": 46
    },
    {
      "epoch": 0.0294578502036979,
      "grad_norm": 0.45469799637794495,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.8982,
      "step": 47
    },
    {
      "epoch": 0.030084612973989344,
      "grad_norm": 0.46748870611190796,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.7085,
      "step": 48
    },
    {
      "epoch": 0.03071137574428079,
      "grad_norm": 0.5330665111541748,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.9236,
      "step": 49
    },
    {
      "epoch": 0.031338138514572234,
      "grad_norm": 0.797656238079071,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.6827,
      "step": 50
    },
    {
      "epoch": 0.031338138514572234,
      "eval_loss": 2.200951337814331,
      "eval_runtime": 193.3394,
      "eval_samples_per_second": 13.903,
      "eval_steps_per_second": 3.476,
      "step": 50
    },
    {
      "epoch": 0.03196490128486368,
      "grad_norm": 0.36136865615844727,
      "learning_rate": 8.894386393810563e-05,
      "loss": 2.2829,
      "step": 51
    },
    {
      "epoch": 0.03259166405515512,
      "grad_norm": 0.49692055583000183,
      "learning_rate": 8.842005554284296e-05,
      "loss": 2.1721,
      "step": 52
    },
    {
      "epoch": 0.03321842682544657,
      "grad_norm": 0.41833043098449707,
      "learning_rate": 8.788574348801675e-05,
      "loss": 2.3135,
      "step": 53
    },
    {
      "epoch": 0.03384518959573801,
      "grad_norm": 0.3009094297885895,
      "learning_rate": 8.73410738492077e-05,
      "loss": 2.2245,
      "step": 54
    },
    {
      "epoch": 0.03447195236602946,
      "grad_norm": 0.2852473556995392,
      "learning_rate": 8.678619553365659e-05,
      "loss": 2.2262,
      "step": 55
    },
    {
      "epoch": 0.0350987151363209,
      "grad_norm": 0.23467257618904114,
      "learning_rate": 8.622126023955446e-05,
      "loss": 2.24,
      "step": 56
    },
    {
      "epoch": 0.035725477906612346,
      "grad_norm": 0.24446693062782288,
      "learning_rate": 8.564642241456986e-05,
      "loss": 2.2815,
      "step": 57
    },
    {
      "epoch": 0.03635224067690379,
      "grad_norm": 0.24829348921775818,
      "learning_rate": 8.506183921362443e-05,
      "loss": 2.1998,
      "step": 58
    },
    {
      "epoch": 0.036979003447195236,
      "grad_norm": 0.30868884921073914,
      "learning_rate": 8.44676704559283e-05,
      "loss": 2.1966,
      "step": 59
    },
    {
      "epoch": 0.03760576621748668,
      "grad_norm": 0.27063894271850586,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.2134,
      "step": 60
    },
    {
      "epoch": 0.038232528987778125,
      "grad_norm": 0.2834758460521698,
      "learning_rate": 8.32512286056924e-05,
      "loss": 2.1864,
      "step": 61
    },
    {
      "epoch": 0.03885929175806957,
      "grad_norm": 0.2596190869808197,
      "learning_rate": 8.262928807620843e-05,
      "loss": 2.1738,
      "step": 62
    },
    {
      "epoch": 0.039486054528361014,
      "grad_norm": 0.24739563465118408,
      "learning_rate": 8.199842702516583e-05,
      "loss": 2.3146,
      "step": 63
    },
    {
      "epoch": 0.04011281729865246,
      "grad_norm": 0.23661167919635773,
      "learning_rate": 8.135881792367686e-05,
      "loss": 2.2085,
      "step": 64
    },
    {
      "epoch": 0.040739580068943904,
      "grad_norm": 0.24701392650604248,
      "learning_rate": 8.07106356344834e-05,
      "loss": 2.2336,
      "step": 65
    },
    {
      "epoch": 0.04136634283923535,
      "grad_norm": 0.2873121201992035,
      "learning_rate": 8.005405736415126e-05,
      "loss": 2.0825,
      "step": 66
    },
    {
      "epoch": 0.04199310560952679,
      "grad_norm": 0.26905685663223267,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.2872,
      "step": 67
    },
    {
      "epoch": 0.04261986837981824,
      "grad_norm": 0.2525993287563324,
      "learning_rate": 7.871643313414718e-05,
      "loss": 2.1181,
      "step": 68
    },
    {
      "epoch": 0.04324663115010968,
      "grad_norm": 0.27378979325294495,
      "learning_rate": 7.803575286758364e-05,
      "loss": 2.2439,
      "step": 69
    },
    {
      "epoch": 0.04387339392040113,
      "grad_norm": 0.2507506310939789,
      "learning_rate": 7.734740790612136e-05,
      "loss": 2.2329,
      "step": 70
    },
    {
      "epoch": 0.04450015669069257,
      "grad_norm": 0.2653977572917938,
      "learning_rate": 7.66515864363997e-05,
      "loss": 2.2663,
      "step": 71
    },
    {
      "epoch": 0.045126919460984016,
      "grad_norm": 0.2759617865085602,
      "learning_rate": 7.594847868906076e-05,
      "loss": 2.1019,
      "step": 72
    },
    {
      "epoch": 0.04575368223127546,
      "grad_norm": 0.2704158425331116,
      "learning_rate": 7.52382768867422e-05,
      "loss": 2.2402,
      "step": 73
    },
    {
      "epoch": 0.046380445001566906,
      "grad_norm": 0.27358147501945496,
      "learning_rate": 7.452117519152542e-05,
      "loss": 2.1952,
      "step": 74
    },
    {
      "epoch": 0.04700720777185835,
      "grad_norm": 0.3097671866416931,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.999,
      "step": 75
    },
    {
      "epoch": 0.047633970542149795,
      "grad_norm": 0.29847580194473267,
      "learning_rate": 7.30670581489344e-05,
      "loss": 2.18,
      "step": 76
    },
    {
      "epoch": 0.04826073331244124,
      "grad_norm": 0.27924296259880066,
      "learning_rate": 7.233044034264034e-05,
      "loss": 2.0909,
      "step": 77
    },
    {
      "epoch": 0.048887496082732684,
      "grad_norm": 0.2707647383213043,
      "learning_rate": 7.158771761692464e-05,
      "loss": 2.2175,
      "step": 78
    },
    {
      "epoch": 0.04951425885302413,
      "grad_norm": 0.2772691249847412,
      "learning_rate": 7.083909302476453e-05,
      "loss": 2.1434,
      "step": 79
    },
    {
      "epoch": 0.050141021623315574,
      "grad_norm": 0.297712504863739,
      "learning_rate": 7.008477123264848e-05,
      "loss": 2.1916,
      "step": 80
    },
    {
      "epoch": 0.05076778439360702,
      "grad_norm": 0.309418261051178,
      "learning_rate": 6.932495846462261e-05,
      "loss": 2.0975,
      "step": 81
    },
    {
      "epoch": 0.05139454716389846,
      "grad_norm": 0.28480103611946106,
      "learning_rate": 6.855986244591104e-05,
      "loss": 2.1944,
      "step": 82
    },
    {
      "epoch": 0.05202130993418991,
      "grad_norm": 0.31346598267555237,
      "learning_rate": 6.778969234612584e-05,
      "loss": 2.121,
      "step": 83
    },
    {
      "epoch": 0.05264807270448135,
      "grad_norm": 0.29866620898246765,
      "learning_rate": 6.701465872208216e-05,
      "loss": 2.1574,
      "step": 84
    },
    {
      "epoch": 0.0532748354747728,
      "grad_norm": 0.32496243715286255,
      "learning_rate": 6.623497346023418e-05,
      "loss": 2.1377,
      "step": 85
    },
    {
      "epoch": 0.05390159824506424,
      "grad_norm": 0.3390509784221649,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.1521,
      "step": 86
    },
    {
      "epoch": 0.054528361015355686,
      "grad_norm": 0.3421640694141388,
      "learning_rate": 6.466250186922325e-05,
      "loss": 2.1287,
      "step": 87
    },
    {
      "epoch": 0.05515512378564713,
      "grad_norm": 0.3049539029598236,
      "learning_rate": 6.387014543809223e-05,
      "loss": 2.1163,
      "step": 88
    },
    {
      "epoch": 0.055781886555938576,
      "grad_norm": 0.3508740961551666,
      "learning_rate": 6.307399704769099e-05,
      "loss": 2.0607,
      "step": 89
    },
    {
      "epoch": 0.05640864932623002,
      "grad_norm": 0.3312886953353882,
      "learning_rate": 6.227427435703997e-05,
      "loss": 2.0475,
      "step": 90
    },
    {
      "epoch": 0.057035412096521465,
      "grad_norm": 0.3733045160770416,
      "learning_rate": 6.147119600233758e-05,
      "loss": 1.9031,
      "step": 91
    },
    {
      "epoch": 0.05766217486681291,
      "grad_norm": 0.38460567593574524,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.9746,
      "step": 92
    },
    {
      "epoch": 0.058288937637104354,
      "grad_norm": 0.3786461353302002,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.8889,
      "step": 93
    },
    {
      "epoch": 0.0589157004073958,
      "grad_norm": 0.36782363057136536,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.972,
      "step": 94
    },
    {
      "epoch": 0.059542463177687244,
      "grad_norm": 0.4207681119441986,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 2.0718,
      "step": 95
    },
    {
      "epoch": 0.06016922594797869,
      "grad_norm": 0.3895847499370575,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.8857,
      "step": 96
    },
    {
      "epoch": 0.06079598871827013,
      "grad_norm": 0.4799377918243408,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.7651,
      "step": 97
    },
    {
      "epoch": 0.06142275148856158,
      "grad_norm": 0.4324221611022949,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.7064,
      "step": 98
    },
    {
      "epoch": 0.06204951425885302,
      "grad_norm": 0.5074413418769836,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.8358,
      "step": 99
    },
    {
      "epoch": 0.06267627702914447,
      "grad_norm": 0.6014479994773865,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.6752,
      "step": 100
    },
    {
      "epoch": 0.06267627702914447,
      "eval_loss": 2.142481565475464,
      "eval_runtime": 193.3393,
      "eval_samples_per_second": 13.903,
      "eval_steps_per_second": 3.476,
      "step": 100
    },
    {
      "epoch": 0.06330303979943591,
      "grad_norm": 0.24511337280273438,
      "learning_rate": 5.330452921628497e-05,
      "loss": 2.2511,
      "step": 101
    },
    {
      "epoch": 0.06392980256972736,
      "grad_norm": 0.30373620986938477,
      "learning_rate": 5.247918773366112e-05,
      "loss": 2.1445,
      "step": 102
    },
    {
      "epoch": 0.0645565653400188,
      "grad_norm": 0.2737019956111908,
      "learning_rate": 5.165316846586541e-05,
      "loss": 2.2637,
      "step": 103
    },
    {
      "epoch": 0.06518332811031025,
      "grad_norm": 0.2908358871936798,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 2.3129,
      "step": 104
    },
    {
      "epoch": 0.06581009088060169,
      "grad_norm": 0.2830345332622528,
      "learning_rate": 5e-05,
      "loss": 2.213,
      "step": 105
    },
    {
      "epoch": 0.06643685365089314,
      "grad_norm": 0.26813745498657227,
      "learning_rate": 4.917330276168208e-05,
      "loss": 2.0659,
      "step": 106
    },
    {
      "epoch": 0.06706361642118458,
      "grad_norm": 0.2948745787143707,
      "learning_rate": 4.834683153413459e-05,
      "loss": 2.0276,
      "step": 107
    },
    {
      "epoch": 0.06769037919147602,
      "grad_norm": 0.21508187055587769,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 2.0788,
      "step": 108
    },
    {
      "epoch": 0.06831714196176747,
      "grad_norm": 0.22258371114730835,
      "learning_rate": 4.669547078371504e-05,
      "loss": 2.2253,
      "step": 109
    },
    {
      "epoch": 0.06894390473205891,
      "grad_norm": 0.2277946174144745,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 2.1928,
      "step": 110
    },
    {
      "epoch": 0.06957066750235036,
      "grad_norm": 0.25298231840133667,
      "learning_rate": 4.504772348747687e-05,
      "loss": 2.0377,
      "step": 111
    },
    {
      "epoch": 0.0701974302726418,
      "grad_norm": 0.2510852813720703,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 2.2317,
      "step": 112
    },
    {
      "epoch": 0.07082419304293325,
      "grad_norm": 0.23955367505550385,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 2.0757,
      "step": 113
    },
    {
      "epoch": 0.07145095581322469,
      "grad_norm": 0.24509812891483307,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 2.1759,
      "step": 114
    },
    {
      "epoch": 0.07207771858351614,
      "grad_norm": 0.2409505844116211,
      "learning_rate": 4.17702704859633e-05,
      "loss": 2.167,
      "step": 115
    },
    {
      "epoch": 0.07270448135380758,
      "grad_norm": 0.2525887191295624,
      "learning_rate": 4.095597328339452e-05,
      "loss": 2.3479,
      "step": 116
    },
    {
      "epoch": 0.07333124412409903,
      "grad_norm": 0.2509635090827942,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 2.2084,
      "step": 117
    },
    {
      "epoch": 0.07395800689439047,
      "grad_norm": 0.2599138021469116,
      "learning_rate": 3.933501846281267e-05,
      "loss": 2.1645,
      "step": 118
    },
    {
      "epoch": 0.07458476966468192,
      "grad_norm": 0.25593191385269165,
      "learning_rate": 3.852880399766243e-05,
      "loss": 2.3505,
      "step": 119
    },
    {
      "epoch": 0.07521153243497336,
      "grad_norm": 0.28572994470596313,
      "learning_rate": 3.772572564296005e-05,
      "loss": 2.184,
      "step": 120
    },
    {
      "epoch": 0.0758382952052648,
      "grad_norm": 0.2575468122959137,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 2.2049,
      "step": 121
    },
    {
      "epoch": 0.07646505797555625,
      "grad_norm": 0.24972902238368988,
      "learning_rate": 3.612985456190778e-05,
      "loss": 2.1388,
      "step": 122
    },
    {
      "epoch": 0.0770918207458477,
      "grad_norm": 0.2775946855545044,
      "learning_rate": 3.533749813077677e-05,
      "loss": 2.1076,
      "step": 123
    },
    {
      "epoch": 0.07771858351613914,
      "grad_norm": 0.28621363639831543,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.1554,
      "step": 124
    },
    {
      "epoch": 0.07834534628643058,
      "grad_norm": 0.2727704346179962,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 2.2113,
      "step": 125
    },
    {
      "epoch": 0.07897210905672203,
      "grad_norm": 0.2666371166706085,
      "learning_rate": 3.298534127791785e-05,
      "loss": 2.0763,
      "step": 126
    },
    {
      "epoch": 0.07959887182701347,
      "grad_norm": 0.2800726890563965,
      "learning_rate": 3.221030765387417e-05,
      "loss": 2.2606,
      "step": 127
    },
    {
      "epoch": 0.08022563459730492,
      "grad_norm": 0.31440141797065735,
      "learning_rate": 3.144013755408895e-05,
      "loss": 1.8982,
      "step": 128
    },
    {
      "epoch": 0.08085239736759636,
      "grad_norm": 0.28575003147125244,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 2.2189,
      "step": 129
    },
    {
      "epoch": 0.08147916013788781,
      "grad_norm": 0.30149340629577637,
      "learning_rate": 2.991522876735154e-05,
      "loss": 2.185,
      "step": 130
    },
    {
      "epoch": 0.08210592290817925,
      "grad_norm": 0.34790483117103577,
      "learning_rate": 2.916090697523549e-05,
      "loss": 2.1343,
      "step": 131
    },
    {
      "epoch": 0.0827326856784707,
      "grad_norm": 0.27599069476127625,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 2.2457,
      "step": 132
    },
    {
      "epoch": 0.08335944844876214,
      "grad_norm": 0.2841669023036957,
      "learning_rate": 2.766955965735968e-05,
      "loss": 2.0523,
      "step": 133
    },
    {
      "epoch": 0.08398621121905359,
      "grad_norm": 0.2984938323497772,
      "learning_rate": 2.693294185106562e-05,
      "loss": 2.1552,
      "step": 134
    },
    {
      "epoch": 0.08461297398934503,
      "grad_norm": 0.2967674732208252,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 2.1208,
      "step": 135
    },
    {
      "epoch": 0.08523973675963648,
      "grad_norm": 0.3244003653526306,
      "learning_rate": 2.547882480847461e-05,
      "loss": 1.9716,
      "step": 136
    },
    {
      "epoch": 0.08586649952992792,
      "grad_norm": 0.29553067684173584,
      "learning_rate": 2.476172311325783e-05,
      "loss": 2.2242,
      "step": 137
    },
    {
      "epoch": 0.08649326230021936,
      "grad_norm": 0.34778109192848206,
      "learning_rate": 2.405152131093926e-05,
      "loss": 2.1597,
      "step": 138
    },
    {
      "epoch": 0.08712002507051081,
      "grad_norm": 0.3166458308696747,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 2.0967,
      "step": 139
    },
    {
      "epoch": 0.08774678784080225,
      "grad_norm": 0.32084259390830994,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 2.1899,
      "step": 140
    },
    {
      "epoch": 0.0883735506110937,
      "grad_norm": 0.3056681454181671,
      "learning_rate": 2.196424713241637e-05,
      "loss": 2.0415,
      "step": 141
    },
    {
      "epoch": 0.08900031338138514,
      "grad_norm": 0.3349115550518036,
      "learning_rate": 2.128356686585282e-05,
      "loss": 2.1151,
      "step": 142
    },
    {
      "epoch": 0.08962707615167659,
      "grad_norm": 0.3600732088088989,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.0132,
      "step": 143
    },
    {
      "epoch": 0.09025383892196803,
      "grad_norm": 0.33642861247062683,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 2.0383,
      "step": 144
    },
    {
      "epoch": 0.09088060169225948,
      "grad_norm": 0.37459853291511536,
      "learning_rate": 1.928936436551661e-05,
      "loss": 2.0562,
      "step": 145
    },
    {
      "epoch": 0.09150736446255092,
      "grad_norm": 0.3649514615535736,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.7121,
      "step": 146
    },
    {
      "epoch": 0.09213412723284237,
      "grad_norm": 0.41538041830062866,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.7375,
      "step": 147
    },
    {
      "epoch": 0.09276089000313381,
      "grad_norm": 0.43311944603919983,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.9274,
      "step": 148
    },
    {
      "epoch": 0.09338765277342526,
      "grad_norm": 0.5375134944915771,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.6296,
      "step": 149
    },
    {
      "epoch": 0.0940144155437167,
      "grad_norm": 0.6179925799369812,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.7532,
      "step": 150
    },
    {
      "epoch": 0.0940144155437167,
      "eval_loss": 2.103527545928955,
      "eval_runtime": 193.3644,
      "eval_samples_per_second": 13.901,
      "eval_steps_per_second": 3.475,
      "step": 150
    },
    {
      "epoch": 0.09464117831400815,
      "grad_norm": 0.178644597530365,
      "learning_rate": 1.553232954407171e-05,
      "loss": 2.2018,
      "step": 151
    },
    {
      "epoch": 0.09526794108429959,
      "grad_norm": 0.17297278344631195,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 2.0842,
      "step": 152
    },
    {
      "epoch": 0.09589470385459103,
      "grad_norm": 0.19325771927833557,
      "learning_rate": 1.435357758543015e-05,
      "loss": 2.0762,
      "step": 153
    },
    {
      "epoch": 0.09652146662488248,
      "grad_norm": 0.21125328540802002,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 2.1893,
      "step": 154
    },
    {
      "epoch": 0.09714822939517392,
      "grad_norm": 0.19695769250392914,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 2.2716,
      "step": 155
    },
    {
      "epoch": 0.09777499216546537,
      "grad_norm": 0.2117329239845276,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 2.107,
      "step": 156
    },
    {
      "epoch": 0.09840175493575681,
      "grad_norm": 0.21075406670570374,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 2.1953,
      "step": 157
    },
    {
      "epoch": 0.09902851770604826,
      "grad_norm": 0.22738949954509735,
      "learning_rate": 1.157994445715706e-05,
      "loss": 2.1686,
      "step": 158
    },
    {
      "epoch": 0.0996552804763397,
      "grad_norm": 0.22872178256511688,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 2.1049,
      "step": 159
    },
    {
      "epoch": 0.10028204324663115,
      "grad_norm": 0.21845078468322754,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 2.2059,
      "step": 160
    },
    {
      "epoch": 0.10090880601692259,
      "grad_norm": 0.2587786912918091,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 1.9837,
      "step": 161
    },
    {
      "epoch": 0.10153556878721404,
      "grad_norm": 0.24059481918811798,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.1822,
      "step": 162
    },
    {
      "epoch": 0.10216233155750548,
      "grad_norm": 0.22659090161323547,
      "learning_rate": 9.068759265665384e-06,
      "loss": 2.2272,
      "step": 163
    },
    {
      "epoch": 0.10278909432779693,
      "grad_norm": 0.23145367205142975,
      "learning_rate": 8.599558442598998e-06,
      "loss": 2.1107,
      "step": 164
    },
    {
      "epoch": 0.10341585709808837,
      "grad_norm": 0.23539476096630096,
      "learning_rate": 8.141676086873572e-06,
      "loss": 2.135,
      "step": 165
    },
    {
      "epoch": 0.10404261986837982,
      "grad_norm": 0.2384565770626068,
      "learning_rate": 7.695237378953223e-06,
      "loss": 2.1837,
      "step": 166
    },
    {
      "epoch": 0.10466938263867126,
      "grad_norm": 0.2379898875951767,
      "learning_rate": 7.260364370723044e-06,
      "loss": 2.2388,
      "step": 167
    },
    {
      "epoch": 0.1052961454089627,
      "grad_norm": 0.2465192675590515,
      "learning_rate": 6.837175952121306e-06,
      "loss": 2.2426,
      "step": 168
    },
    {
      "epoch": 0.10592290817925415,
      "grad_norm": 0.2605994641780853,
      "learning_rate": 6.425787818636131e-06,
      "loss": 2.2758,
      "step": 169
    },
    {
      "epoch": 0.1065496709495456,
      "grad_norm": 0.24755504727363586,
      "learning_rate": 6.026312439675552e-06,
      "loss": 2.2216,
      "step": 170
    },
    {
      "epoch": 0.10717643371983704,
      "grad_norm": 0.23647242784500122,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 2.251,
      "step": 171
    },
    {
      "epoch": 0.10780319649012848,
      "grad_norm": 0.25359636545181274,
      "learning_rate": 5.263533508961827e-06,
      "loss": 2.2036,
      "step": 172
    },
    {
      "epoch": 0.10842995926041993,
      "grad_norm": 0.2837235927581787,
      "learning_rate": 4.900438493352055e-06,
      "loss": 2.1727,
      "step": 173
    },
    {
      "epoch": 0.10905672203071137,
      "grad_norm": 0.2665591835975647,
      "learning_rate": 4.549673247541875e-06,
      "loss": 2.1262,
      "step": 174
    },
    {
      "epoch": 0.10968348480100282,
      "grad_norm": 0.28027012944221497,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 2.2227,
      "step": 175
    },
    {
      "epoch": 0.11031024757129426,
      "grad_norm": 0.270376056432724,
      "learning_rate": 3.885512251130763e-06,
      "loss": 2.0273,
      "step": 176
    },
    {
      "epoch": 0.1109370103415857,
      "grad_norm": 0.25545623898506165,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 2.1781,
      "step": 177
    },
    {
      "epoch": 0.11156377311187715,
      "grad_norm": 0.27068108320236206,
      "learning_rate": 3.271776770026963e-06,
      "loss": 2.0085,
      "step": 178
    },
    {
      "epoch": 0.1121905358821686,
      "grad_norm": 0.29579684138298035,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 2.1708,
      "step": 179
    },
    {
      "epoch": 0.11281729865246004,
      "grad_norm": 0.2657506465911865,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 2.0764,
      "step": 180
    },
    {
      "epoch": 0.11344406142275149,
      "grad_norm": 0.29039308428764343,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.0757,
      "step": 181
    },
    {
      "epoch": 0.11407082419304293,
      "grad_norm": 0.27462437748908997,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 2.196,
      "step": 182
    },
    {
      "epoch": 0.11469758696333437,
      "grad_norm": 0.2879897654056549,
      "learning_rate": 1.962316193157593e-06,
      "loss": 2.105,
      "step": 183
    },
    {
      "epoch": 0.11532434973362582,
      "grad_norm": 0.2720460891723633,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 2.0262,
      "step": 184
    },
    {
      "epoch": 0.11595111250391726,
      "grad_norm": 0.2860749363899231,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 2.1216,
      "step": 185
    },
    {
      "epoch": 0.11657787527420871,
      "grad_norm": 0.28684544563293457,
      "learning_rate": 1.333670137599713e-06,
      "loss": 2.1004,
      "step": 186
    },
    {
      "epoch": 0.11720463804450015,
      "grad_norm": 0.30968979001045227,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 2.0824,
      "step": 187
    },
    {
      "epoch": 0.1178314008147916,
      "grad_norm": 0.29802393913269043,
      "learning_rate": 9.810017062595322e-07,
      "loss": 2.1483,
      "step": 188
    },
    {
      "epoch": 0.11845816358508304,
      "grad_norm": 0.32160425186157227,
      "learning_rate": 8.247462563808817e-07,
      "loss": 1.979,
      "step": 189
    },
    {
      "epoch": 0.11908492635537449,
      "grad_norm": 0.35226160287857056,
      "learning_rate": 6.819348298638839e-07,
      "loss": 1.9744,
      "step": 190
    },
    {
      "epoch": 0.11971168912566593,
      "grad_norm": 0.3430311977863312,
      "learning_rate": 5.526064699265753e-07,
      "loss": 1.9611,
      "step": 191
    },
    {
      "epoch": 0.12033845189595738,
      "grad_norm": 0.3476259708404541,
      "learning_rate": 4.367965336512403e-07,
      "loss": 2.0527,
      "step": 192
    },
    {
      "epoch": 0.12096521466624882,
      "grad_norm": 0.3412429392337799,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 2.0409,
      "step": 193
    },
    {
      "epoch": 0.12159197743654027,
      "grad_norm": 0.4125436842441559,
      "learning_rate": 2.458548727494292e-07,
      "loss": 1.8146,
      "step": 194
    },
    {
      "epoch": 0.12221874020683171,
      "grad_norm": 0.38578394055366516,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 1.9641,
      "step": 195
    },
    {
      "epoch": 0.12284550297712316,
      "grad_norm": 0.36802706122398376,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 1.937,
      "step": 196
    },
    {
      "epoch": 0.1234722657474146,
      "grad_norm": 0.405201256275177,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.9129,
      "step": 197
    },
    {
      "epoch": 0.12409902851770604,
      "grad_norm": 0.38855335116386414,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.7489,
      "step": 198
    },
    {
      "epoch": 0.12472579128799749,
      "grad_norm": 0.4571731686592102,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.8575,
      "step": 199
    },
    {
      "epoch": 0.12535255405828893,
      "grad_norm": 0.5389313101768494,
      "learning_rate": 0.0,
      "loss": 1.8074,
      "step": 200
    },
    {
      "epoch": 0.12535255405828893,
      "eval_loss": 2.1010799407958984,
      "eval_runtime": 193.7107,
      "eval_samples_per_second": 13.876,
      "eval_steps_per_second": 3.469,
      "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": 2.8651057009655808e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}