{
  "best_metric": 0.19901393353939056,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.7835455435847208,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0039177277179236044,
      "grad_norm": 1.8852784633636475,
      "learning_rate": 1e-05,
      "loss": 0.566,
      "step": 1
    },
    {
      "epoch": 0.0039177277179236044,
      "eval_loss": 1.1338591575622559,
      "eval_runtime": 30.3958,
      "eval_samples_per_second": 14.147,
      "eval_steps_per_second": 3.553,
      "step": 1
    },
    {
      "epoch": 0.007835455435847209,
      "grad_norm": 2.1375176906585693,
      "learning_rate": 2e-05,
      "loss": 0.6077,
      "step": 2
    },
    {
      "epoch": 0.011753183153770812,
      "grad_norm": 2.4307785034179688,
      "learning_rate": 3e-05,
      "loss": 0.6468,
      "step": 3
    },
    {
      "epoch": 0.015670910871694418,
      "grad_norm": 1.6710383892059326,
      "learning_rate": 4e-05,
      "loss": 0.6096,
      "step": 4
    },
    {
      "epoch": 0.019588638589618023,
      "grad_norm": 1.1004407405853271,
      "learning_rate": 5e-05,
      "loss": 0.5654,
      "step": 5
    },
    {
      "epoch": 0.023506366307541625,
      "grad_norm": 0.8005902767181396,
      "learning_rate": 6e-05,
      "loss": 0.507,
      "step": 6
    },
    {
      "epoch": 0.02742409402546523,
      "grad_norm": 0.6864309906959534,
      "learning_rate": 7e-05,
      "loss": 0.4359,
      "step": 7
    },
    {
      "epoch": 0.031341821743388835,
      "grad_norm": 0.5759547352790833,
      "learning_rate": 8e-05,
      "loss": 0.3684,
      "step": 8
    },
    {
      "epoch": 0.03525954946131244,
      "grad_norm": 0.5559453368186951,
      "learning_rate": 9e-05,
      "loss": 0.2992,
      "step": 9
    },
    {
      "epoch": 0.039177277179236046,
      "grad_norm": 0.45677122473716736,
      "learning_rate": 0.0001,
      "loss": 0.3171,
      "step": 10
    },
    {
      "epoch": 0.043095004897159644,
      "grad_norm": 0.4299398958683014,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.2381,
      "step": 11
    },
    {
      "epoch": 0.04701273261508325,
      "grad_norm": 0.46053996682167053,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.2621,
      "step": 12
    },
    {
      "epoch": 0.050930460333006855,
      "grad_norm": 0.4198647141456604,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.2627,
      "step": 13
    },
    {
      "epoch": 0.05484818805093046,
      "grad_norm": 0.4670664370059967,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.2714,
      "step": 14
    },
    {
      "epoch": 0.058765915768854066,
      "grad_norm": 0.4880349338054657,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.2967,
      "step": 15
    },
    {
      "epoch": 0.06268364348677767,
      "grad_norm": 0.4248405992984772,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.2579,
      "step": 16
    },
    {
      "epoch": 0.06660137120470128,
      "grad_norm": 0.3383243978023529,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.2347,
      "step": 17
    },
    {
      "epoch": 0.07051909892262488,
      "grad_norm": 0.35473519563674927,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.262,
      "step": 18
    },
    {
      "epoch": 0.07443682664054849,
      "grad_norm": 0.3173123896121979,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.2338,
      "step": 19
    },
    {
      "epoch": 0.07835455435847209,
      "grad_norm": 0.265165776014328,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.2018,
      "step": 20
    },
    {
      "epoch": 0.08227228207639568,
      "grad_norm": 0.3182852864265442,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.2448,
      "step": 21
    },
    {
      "epoch": 0.08619000979431929,
      "grad_norm": 0.3236335217952728,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.2436,
      "step": 22
    },
    {
      "epoch": 0.0901077375122429,
      "grad_norm": 0.3044229745864868,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.2346,
      "step": 23
    },
    {
      "epoch": 0.0940254652301665,
      "grad_norm": 0.3187413811683655,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.2235,
      "step": 24
    },
    {
      "epoch": 0.0979431929480901,
      "grad_norm": 0.30984315276145935,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.2264,
      "step": 25
    },
    {
      "epoch": 0.10186092066601371,
      "grad_norm": 0.31016555428504944,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.246,
      "step": 26
    },
    {
      "epoch": 0.10577864838393732,
      "grad_norm": 0.26590695977211,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.1999,
      "step": 27
    },
    {
      "epoch": 0.10969637610186092,
      "grad_norm": 0.30056583881378174,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.192,
      "step": 28
    },
    {
      "epoch": 0.11361410381978453,
      "grad_norm": 0.3029792010784149,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.2181,
      "step": 29
    },
    {
      "epoch": 0.11753183153770813,
      "grad_norm": 0.3302125632762909,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.2541,
      "step": 30
    },
    {
      "epoch": 0.12144955925563174,
      "grad_norm": 0.319118469953537,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.2353,
      "step": 31
    },
    {
      "epoch": 0.12536728697355534,
      "grad_norm": 0.28191623091697693,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.2172,
      "step": 32
    },
    {
      "epoch": 0.12928501469147893,
      "grad_norm": 0.29677310585975647,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.1899,
      "step": 33
    },
    {
      "epoch": 0.13320274240940255,
      "grad_norm": 0.31013473868370056,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.2306,
      "step": 34
    },
    {
      "epoch": 0.13712047012732614,
      "grad_norm": 0.2878459095954895,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.2022,
      "step": 35
    },
    {
      "epoch": 0.14103819784524976,
      "grad_norm": 0.33466026186943054,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.2265,
      "step": 36
    },
    {
      "epoch": 0.14495592556317335,
      "grad_norm": 0.3114774823188782,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.2205,
      "step": 37
    },
    {
      "epoch": 0.14887365328109697,
      "grad_norm": 0.3086097836494446,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.219,
      "step": 38
    },
    {
      "epoch": 0.15279138099902057,
      "grad_norm": 0.3135780692100525,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.2127,
      "step": 39
    },
    {
      "epoch": 0.15670910871694418,
      "grad_norm": 0.3326824903488159,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.2188,
      "step": 40
    },
    {
      "epoch": 0.16062683643486778,
      "grad_norm": 0.32781073451042175,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.1977,
      "step": 41
    },
    {
      "epoch": 0.16454456415279137,
      "grad_norm": 0.28032639622688293,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.1697,
      "step": 42
    },
    {
      "epoch": 0.168462291870715,
      "grad_norm": 0.3333728313446045,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.2064,
      "step": 43
    },
    {
      "epoch": 0.17238001958863858,
      "grad_norm": 0.3924904763698578,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.2361,
      "step": 44
    },
    {
      "epoch": 0.1762977473065622,
      "grad_norm": 0.3277755677700043,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.1875,
      "step": 45
    },
    {
      "epoch": 0.1802154750244858,
      "grad_norm": 0.3343450725078583,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.2309,
      "step": 46
    },
    {
      "epoch": 0.1841332027424094,
      "grad_norm": 0.32793891429901123,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.1868,
      "step": 47
    },
    {
      "epoch": 0.188050930460333,
      "grad_norm": 0.3633979558944702,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.2438,
      "step": 48
    },
    {
      "epoch": 0.19196865817825662,
      "grad_norm": 0.4049578011035919,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.2207,
      "step": 49
    },
    {
      "epoch": 0.1958863858961802,
      "grad_norm": 0.4200000464916229,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.2359,
      "step": 50
    },
    {
      "epoch": 0.1958863858961802,
      "eval_loss": 0.22570562362670898,
      "eval_runtime": 30.9852,
      "eval_samples_per_second": 13.878,
      "eval_steps_per_second": 3.486,
      "step": 50
    },
    {
      "epoch": 0.19980411361410383,
      "grad_norm": 0.24829831719398499,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.1821,
      "step": 51
    },
    {
      "epoch": 0.20372184133202742,
      "grad_norm": 0.2801470160484314,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.2146,
      "step": 52
    },
    {
      "epoch": 0.20763956904995104,
      "grad_norm": 0.21458657085895538,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.1779,
      "step": 53
    },
    {
      "epoch": 0.21155729676787463,
      "grad_norm": 0.18969576060771942,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.1856,
      "step": 54
    },
    {
      "epoch": 0.21547502448579825,
      "grad_norm": 0.17954787611961365,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.1518,
      "step": 55
    },
    {
      "epoch": 0.21939275220372184,
      "grad_norm": 0.22029854357242584,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.1991,
      "step": 56
    },
    {
      "epoch": 0.22331047992164543,
      "grad_norm": 0.26318979263305664,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.2624,
      "step": 57
    },
    {
      "epoch": 0.22722820763956905,
      "grad_norm": 0.24021010100841522,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.1807,
      "step": 58
    },
    {
      "epoch": 0.23114593535749264,
      "grad_norm": 0.2362748384475708,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.1915,
      "step": 59
    },
    {
      "epoch": 0.23506366307541626,
      "grad_norm": 0.24779574573040009,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.2138,
      "step": 60
    },
    {
      "epoch": 0.23898139079333985,
      "grad_norm": 0.21544711291790009,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.1808,
      "step": 61
    },
    {
      "epoch": 0.24289911851126347,
      "grad_norm": 0.20996569097042084,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.1997,
      "step": 62
    },
    {
      "epoch": 0.24681684622918706,
      "grad_norm": 0.2478071004152298,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.2175,
      "step": 63
    },
    {
      "epoch": 0.2507345739471107,
      "grad_norm": 0.22997638583183289,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.216,
      "step": 64
    },
    {
      "epoch": 0.2546523016650343,
      "grad_norm": 0.2578161656856537,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.2145,
      "step": 65
    },
    {
      "epoch": 0.25857002938295787,
      "grad_norm": 0.21929015219211578,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.2018,
      "step": 66
    },
    {
      "epoch": 0.2624877571008815,
      "grad_norm": 0.24211132526397705,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.2364,
      "step": 67
    },
    {
      "epoch": 0.2664054848188051,
      "grad_norm": 0.23147591948509216,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.2265,
      "step": 68
    },
    {
      "epoch": 0.2703232125367287,
      "grad_norm": 0.2782161235809326,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.2349,
      "step": 69
    },
    {
      "epoch": 0.2742409402546523,
      "grad_norm": 0.2190636545419693,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.1925,
      "step": 70
    },
    {
      "epoch": 0.2781586679725759,
      "grad_norm": 0.2392660230398178,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.2163,
      "step": 71
    },
    {
      "epoch": 0.2820763956904995,
      "grad_norm": 0.2863052785396576,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.2458,
      "step": 72
    },
    {
      "epoch": 0.2859941234084231,
      "grad_norm": 0.2509170472621918,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.2095,
      "step": 73
    },
    {
      "epoch": 0.2899118511263467,
      "grad_norm": 0.2125522941350937,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.1732,
      "step": 74
    },
    {
      "epoch": 0.2938295788442703,
      "grad_norm": 0.22826635837554932,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.1946,
      "step": 75
    },
    {
      "epoch": 0.29774730656219395,
      "grad_norm": 0.24489618837833405,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.207,
      "step": 76
    },
    {
      "epoch": 0.30166503428011754,
      "grad_norm": 0.273649662733078,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.2396,
      "step": 77
    },
    {
      "epoch": 0.30558276199804113,
      "grad_norm": 0.22216695547103882,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.1786,
      "step": 78
    },
    {
      "epoch": 0.3095004897159647,
      "grad_norm": 0.242794468998909,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.1993,
      "step": 79
    },
    {
      "epoch": 0.31341821743388837,
      "grad_norm": 0.2536708414554596,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.223,
      "step": 80
    },
    {
      "epoch": 0.31733594515181196,
      "grad_norm": 0.2624150812625885,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.217,
      "step": 81
    },
    {
      "epoch": 0.32125367286973555,
      "grad_norm": 0.276886910200119,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.2133,
      "step": 82
    },
    {
      "epoch": 0.32517140058765914,
      "grad_norm": 0.25303804874420166,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.2234,
      "step": 83
    },
    {
      "epoch": 0.32908912830558273,
      "grad_norm": 0.2886090576648712,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.2191,
      "step": 84
    },
    {
      "epoch": 0.3330068560235064,
      "grad_norm": 0.2524021565914154,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.1956,
      "step": 85
    },
    {
      "epoch": 0.33692458374143,
      "grad_norm": 0.2742237448692322,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.2212,
      "step": 86
    },
    {
      "epoch": 0.34084231145935356,
      "grad_norm": 0.2550947666168213,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.1954,
      "step": 87
    },
    {
      "epoch": 0.34476003917727716,
      "grad_norm": 0.2245587408542633,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.1604,
      "step": 88
    },
    {
      "epoch": 0.3486777668952008,
      "grad_norm": 0.25625982880592346,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.1943,
      "step": 89
    },
    {
      "epoch": 0.3525954946131244,
      "grad_norm": 0.2976544499397278,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.2208,
      "step": 90
    },
    {
      "epoch": 0.356513222331048,
      "grad_norm": 0.2829359173774719,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.209,
      "step": 91
    },
    {
      "epoch": 0.3604309500489716,
      "grad_norm": 0.29276043176651,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.211,
      "step": 92
    },
    {
      "epoch": 0.3643486777668952,
      "grad_norm": 0.27638500928878784,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.1938,
      "step": 93
    },
    {
      "epoch": 0.3682664054848188,
      "grad_norm": 0.3386843800544739,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.2103,
      "step": 94
    },
    {
      "epoch": 0.3721841332027424,
      "grad_norm": 0.31644755601882935,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.2288,
      "step": 95
    },
    {
      "epoch": 0.376101860920666,
      "grad_norm": 0.3131150007247925,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.235,
      "step": 96
    },
    {
      "epoch": 0.38001958863858964,
      "grad_norm": 0.2897909879684448,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.2213,
      "step": 97
    },
    {
      "epoch": 0.38393731635651324,
      "grad_norm": 0.3157711327075958,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.2127,
      "step": 98
    },
    {
      "epoch": 0.3878550440744368,
      "grad_norm": 0.2988574802875519,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.2074,
      "step": 99
    },
    {
      "epoch": 0.3917727717923604,
      "grad_norm": 0.3278951048851013,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.1956,
      "step": 100
    },
    {
      "epoch": 0.3917727717923604,
      "eval_loss": 0.21531742811203003,
      "eval_runtime": 30.9165,
      "eval_samples_per_second": 13.908,
      "eval_steps_per_second": 3.493,
      "step": 100
    },
    {
      "epoch": 0.395690499510284,
      "grad_norm": 0.20064860582351685,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.1711,
      "step": 101
    },
    {
      "epoch": 0.39960822722820766,
      "grad_norm": 0.23195140063762665,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.1819,
      "step": 102
    },
    {
      "epoch": 0.40352595494613125,
      "grad_norm": 0.23917965590953827,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.2197,
      "step": 103
    },
    {
      "epoch": 0.40744368266405484,
      "grad_norm": 0.21499581634998322,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.1997,
      "step": 104
    },
    {
      "epoch": 0.41136141038197843,
      "grad_norm": 0.21412873268127441,
      "learning_rate": 5e-05,
      "loss": 0.195,
      "step": 105
    },
    {
      "epoch": 0.4152791380999021,
      "grad_norm": 0.202995166182518,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.1993,
      "step": 106
    },
    {
      "epoch": 0.41919686581782567,
      "grad_norm": 0.1878906935453415,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.1707,
      "step": 107
    },
    {
      "epoch": 0.42311459353574926,
      "grad_norm": 0.18439991772174835,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.1912,
      "step": 108
    },
    {
      "epoch": 0.42703232125367285,
      "grad_norm": 0.21011324226856232,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.2005,
      "step": 109
    },
    {
      "epoch": 0.4309500489715965,
      "grad_norm": 0.20166954398155212,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.1943,
      "step": 110
    },
    {
      "epoch": 0.4348677766895201,
      "grad_norm": 0.23377470672130585,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.2181,
      "step": 111
    },
    {
      "epoch": 0.4387855044074437,
      "grad_norm": 0.2309298813343048,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.2053,
      "step": 112
    },
    {
      "epoch": 0.4427032321253673,
      "grad_norm": 0.2293408364057541,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.2417,
      "step": 113
    },
    {
      "epoch": 0.44662095984329087,
      "grad_norm": 0.2312147170305252,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.2091,
      "step": 114
    },
    {
      "epoch": 0.4505386875612145,
      "grad_norm": 0.23771147429943085,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.2172,
      "step": 115
    },
    {
      "epoch": 0.4544564152791381,
      "grad_norm": 0.2387521117925644,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.2277,
      "step": 116
    },
    {
      "epoch": 0.4583741429970617,
      "grad_norm": 0.23206967115402222,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.2031,
      "step": 117
    },
    {
      "epoch": 0.4622918707149853,
      "grad_norm": 0.21480651199817657,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.1942,
      "step": 118
    },
    {
      "epoch": 0.46620959843290893,
      "grad_norm": 0.23633764684200287,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.2219,
      "step": 119
    },
    {
      "epoch": 0.4701273261508325,
      "grad_norm": 0.22307758033275604,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.2005,
      "step": 120
    },
    {
      "epoch": 0.4740450538687561,
      "grad_norm": 0.21873673796653748,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.2051,
      "step": 121
    },
    {
      "epoch": 0.4779627815866797,
      "grad_norm": 0.22618165612220764,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.206,
      "step": 122
    },
    {
      "epoch": 0.48188050930460335,
      "grad_norm": 0.2384374588727951,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.2305,
      "step": 123
    },
    {
      "epoch": 0.48579823702252695,
      "grad_norm": 0.23990829288959503,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2048,
      "step": 124
    },
    {
      "epoch": 0.48971596474045054,
      "grad_norm": 0.2451409250497818,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.2012,
      "step": 125
    },
    {
      "epoch": 0.49363369245837413,
      "grad_norm": 0.22672268748283386,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.1858,
      "step": 126
    },
    {
      "epoch": 0.4975514201762977,
      "grad_norm": 0.22970569133758545,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.1968,
      "step": 127
    },
    {
      "epoch": 0.5014691478942214,
      "grad_norm": 0.22287768125534058,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.1793,
      "step": 128
    },
    {
      "epoch": 0.5053868756121449,
      "grad_norm": 0.2533530592918396,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.2138,
      "step": 129
    },
    {
      "epoch": 0.5093046033300686,
      "grad_norm": 0.21004705131053925,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.1868,
      "step": 130
    },
    {
      "epoch": 0.5132223310479922,
      "grad_norm": 0.23376432061195374,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.2196,
      "step": 131
    },
    {
      "epoch": 0.5171400587659157,
      "grad_norm": 0.23468714952468872,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.2099,
      "step": 132
    },
    {
      "epoch": 0.5210577864838394,
      "grad_norm": 0.2770167291164398,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.1991,
      "step": 133
    },
    {
      "epoch": 0.524975514201763,
      "grad_norm": 0.23524515330791473,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.2031,
      "step": 134
    },
    {
      "epoch": 0.5288932419196866,
      "grad_norm": 0.27464473247528076,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.2265,
      "step": 135
    },
    {
      "epoch": 0.5328109696376102,
      "grad_norm": 0.2592555284500122,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.2397,
      "step": 136
    },
    {
      "epoch": 0.5367286973555337,
      "grad_norm": 0.2436974197626114,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.2028,
      "step": 137
    },
    {
      "epoch": 0.5406464250734574,
      "grad_norm": 0.24311093986034393,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.1875,
      "step": 138
    },
    {
      "epoch": 0.544564152791381,
      "grad_norm": 0.2521592974662781,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.1916,
      "step": 139
    },
    {
      "epoch": 0.5484818805093046,
      "grad_norm": 0.24356143176555634,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.1816,
      "step": 140
    },
    {
      "epoch": 0.5523996082272282,
      "grad_norm": 0.2411893606185913,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.1913,
      "step": 141
    },
    {
      "epoch": 0.5563173359451518,
      "grad_norm": 0.2832423150539398,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.2254,
      "step": 142
    },
    {
      "epoch": 0.5602350636630754,
      "grad_norm": 0.259825199842453,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.2001,
      "step": 143
    },
    {
      "epoch": 0.564152791380999,
      "grad_norm": 0.27368223667144775,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.2072,
      "step": 144
    },
    {
      "epoch": 0.5680705190989226,
      "grad_norm": 0.24412360787391663,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.1505,
      "step": 145
    },
    {
      "epoch": 0.5719882468168462,
      "grad_norm": 0.24218587577342987,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.1724,
      "step": 146
    },
    {
      "epoch": 0.5759059745347699,
      "grad_norm": 0.2929390072822571,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.2143,
      "step": 147
    },
    {
      "epoch": 0.5798237022526934,
      "grad_norm": 0.2985309064388275,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.1865,
      "step": 148
    },
    {
      "epoch": 0.5837414299706171,
      "grad_norm": 0.316037654876709,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.219,
      "step": 149
    },
    {
      "epoch": 0.5876591576885406,
      "grad_norm": 0.3837650716304779,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.1932,
      "step": 150
    },
    {
      "epoch": 0.5876591576885406,
      "eval_loss": 0.2032872885465622,
      "eval_runtime": 30.9645,
      "eval_samples_per_second": 13.887,
      "eval_steps_per_second": 3.488,
      "step": 150
    },
    {
      "epoch": 0.5915768854064642,
      "grad_norm": 0.17521683871746063,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.1644,
      "step": 151
    },
    {
      "epoch": 0.5954946131243879,
      "grad_norm": 0.22602012753486633,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.1967,
      "step": 152
    },
    {
      "epoch": 0.5994123408423114,
      "grad_norm": 0.2156466841697693,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.1927,
      "step": 153
    },
    {
      "epoch": 0.6033300685602351,
      "grad_norm": 0.23327474296092987,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.1741,
      "step": 154
    },
    {
      "epoch": 0.6072477962781586,
      "grad_norm": 0.2326485812664032,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.2029,
      "step": 155
    },
    {
      "epoch": 0.6111655239960823,
      "grad_norm": 0.22402341663837433,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.202,
      "step": 156
    },
    {
      "epoch": 0.6150832517140059,
      "grad_norm": 0.21372468769550323,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.1812,
      "step": 157
    },
    {
      "epoch": 0.6190009794319294,
      "grad_norm": 0.24581901729106903,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.2378,
      "step": 158
    },
    {
      "epoch": 0.6229187071498531,
      "grad_norm": 0.20854702591896057,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.186,
      "step": 159
    },
    {
      "epoch": 0.6268364348677767,
      "grad_norm": 0.21091414988040924,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.197,
      "step": 160
    },
    {
      "epoch": 0.6307541625857003,
      "grad_norm": 0.19905956089496613,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.1891,
      "step": 161
    },
    {
      "epoch": 0.6346718903036239,
      "grad_norm": 0.23800963163375854,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.2287,
      "step": 162
    },
    {
      "epoch": 0.6385896180215475,
      "grad_norm": 0.19856347143650055,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.1841,
      "step": 163
    },
    {
      "epoch": 0.6425073457394711,
      "grad_norm": 0.22460336983203888,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.1999,
      "step": 164
    },
    {
      "epoch": 0.6464250734573947,
      "grad_norm": 0.2177763134241104,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.2009,
      "step": 165
    },
    {
      "epoch": 0.6503428011753183,
      "grad_norm": 0.23553279042243958,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.2134,
      "step": 166
    },
    {
      "epoch": 0.6542605288932419,
      "grad_norm": 0.21213515102863312,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.2055,
      "step": 167
    },
    {
      "epoch": 0.6581782566111655,
      "grad_norm": 0.2308291792869568,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.2416,
      "step": 168
    },
    {
      "epoch": 0.6620959843290891,
      "grad_norm": 0.22472918033599854,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.2064,
      "step": 169
    },
    {
      "epoch": 0.6660137120470128,
      "grad_norm": 0.2193082571029663,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.2217,
      "step": 170
    },
    {
      "epoch": 0.6699314397649363,
      "grad_norm": 0.23800432682037354,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.2269,
      "step": 171
    },
    {
      "epoch": 0.67384916748286,
      "grad_norm": 0.28809383511543274,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.2531,
      "step": 172
    },
    {
      "epoch": 0.6777668952007836,
      "grad_norm": 0.21529562771320343,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.2019,
      "step": 173
    },
    {
      "epoch": 0.6816846229187071,
      "grad_norm": 0.19516241550445557,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.17,
      "step": 174
    },
    {
      "epoch": 0.6856023506366308,
      "grad_norm": 0.2077867090702057,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.1949,
      "step": 175
    },
    {
      "epoch": 0.6895200783545543,
      "grad_norm": 0.22601889073848724,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.1997,
      "step": 176
    },
    {
      "epoch": 0.693437806072478,
      "grad_norm": 0.1992337852716446,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.1902,
      "step": 177
    },
    {
      "epoch": 0.6973555337904016,
      "grad_norm": 0.2275264710187912,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.1773,
      "step": 178
    },
    {
      "epoch": 0.7012732615083251,
      "grad_norm": 0.26915407180786133,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.2128,
      "step": 179
    },
    {
      "epoch": 0.7051909892262488,
      "grad_norm": 0.21038304269313812,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.1786,
      "step": 180
    },
    {
      "epoch": 0.7091087169441724,
      "grad_norm": 0.2332298457622528,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.2274,
      "step": 181
    },
    {
      "epoch": 0.713026444662096,
      "grad_norm": 0.22484558820724487,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.192,
      "step": 182
    },
    {
      "epoch": 0.7169441723800196,
      "grad_norm": 0.23130182921886444,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.2106,
      "step": 183
    },
    {
      "epoch": 0.7208619000979432,
      "grad_norm": 0.244379460811615,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.2192,
      "step": 184
    },
    {
      "epoch": 0.7247796278158668,
      "grad_norm": 0.24704770743846893,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.2122,
      "step": 185
    },
    {
      "epoch": 0.7286973555337904,
      "grad_norm": 0.23436692357063293,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.1914,
      "step": 186
    },
    {
      "epoch": 0.732615083251714,
      "grad_norm": 0.25661128759384155,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.1883,
      "step": 187
    },
    {
      "epoch": 0.7365328109696376,
      "grad_norm": 0.24355946481227875,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.2007,
      "step": 188
    },
    {
      "epoch": 0.7404505386875612,
      "grad_norm": 0.23361624777317047,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.1825,
      "step": 189
    },
    {
      "epoch": 0.7443682664054848,
      "grad_norm": 0.23288552463054657,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.1822,
      "step": 190
    },
    {
      "epoch": 0.7482859941234085,
      "grad_norm": 0.25495779514312744,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.2024,
      "step": 191
    },
    {
      "epoch": 0.752203721841332,
      "grad_norm": 0.2501349449157715,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.2002,
      "step": 192
    },
    {
      "epoch": 0.7561214495592556,
      "grad_norm": 0.2571689784526825,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.2123,
      "step": 193
    },
    {
      "epoch": 0.7600391772771793,
      "grad_norm": 0.27444779872894287,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.2078,
      "step": 194
    },
    {
      "epoch": 0.7639569049951028,
      "grad_norm": 0.23089942336082458,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.1625,
      "step": 195
    },
    {
      "epoch": 0.7678746327130265,
      "grad_norm": 0.2593623399734497,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.179,
      "step": 196
    },
    {
      "epoch": 0.77179236043095,
      "grad_norm": 0.2842453420162201,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.1992,
      "step": 197
    },
    {
      "epoch": 0.7757100881488737,
      "grad_norm": 0.3110094964504242,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.1961,
      "step": 198
    },
    {
      "epoch": 0.7796278158667973,
      "grad_norm": 0.36238640546798706,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.2357,
      "step": 199
    },
    {
      "epoch": 0.7835455435847208,
      "grad_norm": 0.4677375555038452,
      "learning_rate": 0.0,
      "loss": 0.222,
      "step": 200
    },
    {
      "epoch": 0.7835455435847208,
      "eval_loss": 0.19901393353939056,
      "eval_runtime": 30.9706,
      "eval_samples_per_second": 13.884,
      "eval_steps_per_second": 3.487,
      "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": 2.84377737068544e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}