{
  "best_metric": 0.5681252479553223,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.05273218640827895,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002636609320413948,
      "grad_norm": 0.42368844151496887,
      "learning_rate": 1e-05,
      "loss": 0.7281,
      "step": 1
    },
    {
      "epoch": 0.0002636609320413948,
      "eval_loss": 0.9909459352493286,
      "eval_runtime": 492.2452,
      "eval_samples_per_second": 12.977,
      "eval_steps_per_second": 3.244,
      "step": 1
    },
    {
      "epoch": 0.0005273218640827896,
      "grad_norm": 0.46486958861351013,
      "learning_rate": 2e-05,
      "loss": 0.961,
      "step": 2
    },
    {
      "epoch": 0.0007909827961241843,
      "grad_norm": 0.587650716304779,
      "learning_rate": 3e-05,
      "loss": 1.0776,
      "step": 3
    },
    {
      "epoch": 0.0010546437281655791,
      "grad_norm": 0.5921438336372375,
      "learning_rate": 4e-05,
      "loss": 1.0235,
      "step": 4
    },
    {
      "epoch": 0.001318304660206974,
      "grad_norm": 0.5741214156150818,
      "learning_rate": 5e-05,
      "loss": 0.9422,
      "step": 5
    },
    {
      "epoch": 0.0015819655922483687,
      "grad_norm": 0.4628746807575226,
      "learning_rate": 6e-05,
      "loss": 0.7179,
      "step": 6
    },
    {
      "epoch": 0.0018456265242897635,
      "grad_norm": 0.4745940566062927,
      "learning_rate": 7e-05,
      "loss": 0.8582,
      "step": 7
    },
    {
      "epoch": 0.0021092874563311582,
      "grad_norm": 0.45114797353744507,
      "learning_rate": 8e-05,
      "loss": 0.8733,
      "step": 8
    },
    {
      "epoch": 0.002372948388372553,
      "grad_norm": 0.42949607968330383,
      "learning_rate": 9e-05,
      "loss": 0.7367,
      "step": 9
    },
    {
      "epoch": 0.002636609320413948,
      "grad_norm": 0.47053250670433044,
      "learning_rate": 0.0001,
      "loss": 0.7125,
      "step": 10
    },
    {
      "epoch": 0.0029002702524553426,
      "grad_norm": 0.3443538248538971,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.6392,
      "step": 11
    },
    {
      "epoch": 0.0031639311844967374,
      "grad_norm": 0.3921029269695282,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.8571,
      "step": 12
    },
    {
      "epoch": 0.003427592116538132,
      "grad_norm": 0.35075482726097107,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.5938,
      "step": 13
    },
    {
      "epoch": 0.003691253048579527,
      "grad_norm": 0.4001588225364685,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.5581,
      "step": 14
    },
    {
      "epoch": 0.003954913980620921,
      "grad_norm": 0.37732943892478943,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.4143,
      "step": 15
    },
    {
      "epoch": 0.0042185749126623165,
      "grad_norm": 0.3273317813873291,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.3003,
      "step": 16
    },
    {
      "epoch": 0.004482235844703711,
      "grad_norm": 0.4367177188396454,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.6534,
      "step": 17
    },
    {
      "epoch": 0.004745896776745106,
      "grad_norm": 0.3668208122253418,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.5758,
      "step": 18
    },
    {
      "epoch": 0.0050095577087865,
      "grad_norm": 0.5543003082275391,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.7271,
      "step": 19
    },
    {
      "epoch": 0.005273218640827896,
      "grad_norm": 0.35206472873687744,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.3342,
      "step": 20
    },
    {
      "epoch": 0.00553687957286929,
      "grad_norm": 0.4017099440097809,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.4906,
      "step": 21
    },
    {
      "epoch": 0.005800540504910685,
      "grad_norm": 0.3458331525325775,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.3458,
      "step": 22
    },
    {
      "epoch": 0.0060642014369520795,
      "grad_norm": 0.4361138641834259,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.6598,
      "step": 23
    },
    {
      "epoch": 0.006327862368993475,
      "grad_norm": 0.42285528779029846,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.5426,
      "step": 24
    },
    {
      "epoch": 0.006591523301034869,
      "grad_norm": 0.5279005765914917,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.7054,
      "step": 25
    },
    {
      "epoch": 0.006855184233076264,
      "grad_norm": 0.5394160747528076,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.6374,
      "step": 26
    },
    {
      "epoch": 0.007118845165117659,
      "grad_norm": 0.49474841356277466,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.5271,
      "step": 27
    },
    {
      "epoch": 0.007382506097159054,
      "grad_norm": 0.5591098070144653,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.6295,
      "step": 28
    },
    {
      "epoch": 0.007646167029200448,
      "grad_norm": 0.5342866778373718,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.5163,
      "step": 29
    },
    {
      "epoch": 0.007909827961241843,
      "grad_norm": 0.5543274879455566,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.4283,
      "step": 30
    },
    {
      "epoch": 0.008173488893283237,
      "grad_norm": 0.5129711031913757,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.6255,
      "step": 31
    },
    {
      "epoch": 0.008437149825324633,
      "grad_norm": 0.4841585159301758,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.5332,
      "step": 32
    },
    {
      "epoch": 0.008700810757366027,
      "grad_norm": 0.571419358253479,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.5225,
      "step": 33
    },
    {
      "epoch": 0.008964471689407422,
      "grad_norm": 0.6632012724876404,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.5468,
      "step": 34
    },
    {
      "epoch": 0.009228132621448816,
      "grad_norm": 0.5761999487876892,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.5607,
      "step": 35
    },
    {
      "epoch": 0.009491793553490212,
      "grad_norm": 0.4825720191001892,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.433,
      "step": 36
    },
    {
      "epoch": 0.009755454485531606,
      "grad_norm": 0.4596071243286133,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.4358,
      "step": 37
    },
    {
      "epoch": 0.010019115417573,
      "grad_norm": 0.5392119884490967,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.4013,
      "step": 38
    },
    {
      "epoch": 0.010282776349614395,
      "grad_norm": 0.5163045525550842,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.4154,
      "step": 39
    },
    {
      "epoch": 0.010546437281655791,
      "grad_norm": 0.7249284386634827,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.5879,
      "step": 40
    },
    {
      "epoch": 0.010810098213697186,
      "grad_norm": 0.7025389075279236,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.6978,
      "step": 41
    },
    {
      "epoch": 0.01107375914573858,
      "grad_norm": 0.5616132616996765,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.4331,
      "step": 42
    },
    {
      "epoch": 0.011337420077779974,
      "grad_norm": 0.5949772596359253,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.5046,
      "step": 43
    },
    {
      "epoch": 0.01160108100982137,
      "grad_norm": 0.6255516409873962,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.5814,
      "step": 44
    },
    {
      "epoch": 0.011864741941862765,
      "grad_norm": 0.701810896396637,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.7204,
      "step": 45
    },
    {
      "epoch": 0.012128402873904159,
      "grad_norm": 0.7462292313575745,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.5541,
      "step": 46
    },
    {
      "epoch": 0.012392063805945553,
      "grad_norm": 0.8259117007255554,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.847,
      "step": 47
    },
    {
      "epoch": 0.01265572473798695,
      "grad_norm": 0.8656020164489746,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7545,
      "step": 48
    },
    {
      "epoch": 0.012919385670028344,
      "grad_norm": 1.1974518299102783,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.6208,
      "step": 49
    },
    {
      "epoch": 0.013183046602069738,
      "grad_norm": 1.1019841432571411,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.7442,
      "step": 50
    },
    {
      "epoch": 0.013183046602069738,
      "eval_loss": 0.6172179579734802,
      "eval_runtime": 495.8864,
      "eval_samples_per_second": 12.882,
      "eval_steps_per_second": 3.22,
      "step": 50
    },
    {
      "epoch": 0.013446707534111133,
      "grad_norm": 0.5082623958587646,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.7005,
      "step": 51
    },
    {
      "epoch": 0.013710368466152529,
      "grad_norm": 0.476169615983963,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.928,
      "step": 52
    },
    {
      "epoch": 0.013974029398193923,
      "grad_norm": 0.2860334813594818,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.5938,
      "step": 53
    },
    {
      "epoch": 0.014237690330235317,
      "grad_norm": 0.2745681405067444,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.8951,
      "step": 54
    },
    {
      "epoch": 0.014501351262276712,
      "grad_norm": 0.26113906502723694,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.8588,
      "step": 55
    },
    {
      "epoch": 0.014765012194318108,
      "grad_norm": 0.2770431935787201,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.9023,
      "step": 56
    },
    {
      "epoch": 0.015028673126359502,
      "grad_norm": 0.2783281207084656,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.8281,
      "step": 57
    },
    {
      "epoch": 0.015292334058400896,
      "grad_norm": 0.28697606921195984,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.5815,
      "step": 58
    },
    {
      "epoch": 0.01555599499044229,
      "grad_norm": 0.26399940252304077,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.7129,
      "step": 59
    },
    {
      "epoch": 0.015819655922483685,
      "grad_norm": 0.32216542959213257,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.7329,
      "step": 60
    },
    {
      "epoch": 0.01608331685452508,
      "grad_norm": 0.31373080611228943,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.6249,
      "step": 61
    },
    {
      "epoch": 0.016346977786566474,
      "grad_norm": 0.316427618265152,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.5462,
      "step": 62
    },
    {
      "epoch": 0.01661063871860787,
      "grad_norm": 0.34677332639694214,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.5795,
      "step": 63
    },
    {
      "epoch": 0.016874299650649266,
      "grad_norm": 0.3238438069820404,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.7369,
      "step": 64
    },
    {
      "epoch": 0.01713796058269066,
      "grad_norm": 0.3749651610851288,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.7599,
      "step": 65
    },
    {
      "epoch": 0.017401621514732055,
      "grad_norm": 0.3531327545642853,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.7076,
      "step": 66
    },
    {
      "epoch": 0.01766528244677345,
      "grad_norm": 0.32737159729003906,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.574,
      "step": 67
    },
    {
      "epoch": 0.017928943378814843,
      "grad_norm": 0.33576861023902893,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.649,
      "step": 68
    },
    {
      "epoch": 0.018192604310856238,
      "grad_norm": 0.2908865511417389,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.4644,
      "step": 69
    },
    {
      "epoch": 0.018456265242897632,
      "grad_norm": 0.32684531807899475,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.5422,
      "step": 70
    },
    {
      "epoch": 0.01871992617493903,
      "grad_norm": 0.2767927050590515,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.4214,
      "step": 71
    },
    {
      "epoch": 0.018983587106980424,
      "grad_norm": 0.36388060450553894,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.6487,
      "step": 72
    },
    {
      "epoch": 0.01924724803902182,
      "grad_norm": 0.348962664604187,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.5621,
      "step": 73
    },
    {
      "epoch": 0.019510908971063213,
      "grad_norm": 0.31299272179603577,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.4207,
      "step": 74
    },
    {
      "epoch": 0.019774569903104607,
      "grad_norm": 0.3468606472015381,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.4331,
      "step": 75
    },
    {
      "epoch": 0.020038230835146,
      "grad_norm": 0.33953729271888733,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.3414,
      "step": 76
    },
    {
      "epoch": 0.020301891767187396,
      "grad_norm": 0.411404550075531,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.6224,
      "step": 77
    },
    {
      "epoch": 0.02056555269922879,
      "grad_norm": 0.3891073167324066,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.4588,
      "step": 78
    },
    {
      "epoch": 0.020829213631270188,
      "grad_norm": 0.40103307366371155,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.5342,
      "step": 79
    },
    {
      "epoch": 0.021092874563311582,
      "grad_norm": 0.3814127743244171,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.4189,
      "step": 80
    },
    {
      "epoch": 0.021356535495352977,
      "grad_norm": 0.43291643261909485,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.4195,
      "step": 81
    },
    {
      "epoch": 0.02162019642739437,
      "grad_norm": 0.4319145977497101,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.6456,
      "step": 82
    },
    {
      "epoch": 0.021883857359435765,
      "grad_norm": 0.32079795002937317,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.2631,
      "step": 83
    },
    {
      "epoch": 0.02214751829147716,
      "grad_norm": 0.4687003195285797,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.3876,
      "step": 84
    },
    {
      "epoch": 0.022411179223518554,
      "grad_norm": 0.43122172355651855,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.4608,
      "step": 85
    },
    {
      "epoch": 0.02267484015555995,
      "grad_norm": 0.5144528150558472,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.4508,
      "step": 86
    },
    {
      "epoch": 0.022938501087601346,
      "grad_norm": 0.41717734932899475,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.3648,
      "step": 87
    },
    {
      "epoch": 0.02320216201964274,
      "grad_norm": 0.46487149596214294,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.4615,
      "step": 88
    },
    {
      "epoch": 0.023465822951684135,
      "grad_norm": 0.5289758443832397,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.5524,
      "step": 89
    },
    {
      "epoch": 0.02372948388372553,
      "grad_norm": 0.6123440861701965,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.4823,
      "step": 90
    },
    {
      "epoch": 0.023993144815766924,
      "grad_norm": 0.5002554655075073,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.4227,
      "step": 91
    },
    {
      "epoch": 0.024256805747808318,
      "grad_norm": 0.47287604212760925,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.3916,
      "step": 92
    },
    {
      "epoch": 0.024520466679849712,
      "grad_norm": 0.6406527757644653,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.5738,
      "step": 93
    },
    {
      "epoch": 0.024784127611891107,
      "grad_norm": 0.6350550055503845,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.4628,
      "step": 94
    },
    {
      "epoch": 0.0250477885439325,
      "grad_norm": 0.6158288717269897,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.4376,
      "step": 95
    },
    {
      "epoch": 0.0253114494759739,
      "grad_norm": 0.6873517632484436,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.5019,
      "step": 96
    },
    {
      "epoch": 0.025575110408015293,
      "grad_norm": 0.6422527432441711,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.4336,
      "step": 97
    },
    {
      "epoch": 0.025838771340056688,
      "grad_norm": 1.0383780002593994,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.6436,
      "step": 98
    },
    {
      "epoch": 0.026102432272098082,
      "grad_norm": 1.2029714584350586,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.743,
      "step": 99
    },
    {
      "epoch": 0.026366093204139476,
      "grad_norm": 1.4151502847671509,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.9906,
      "step": 100
    },
    {
      "epoch": 0.026366093204139476,
      "eval_loss": 0.5898199081420898,
      "eval_runtime": 495.8553,
      "eval_samples_per_second": 12.883,
      "eval_steps_per_second": 3.221,
      "step": 100
    },
    {
      "epoch": 0.02662975413618087,
      "grad_norm": 0.36152973771095276,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.4925,
      "step": 101
    },
    {
      "epoch": 0.026893415068222265,
      "grad_norm": 0.22115398943424225,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.0963,
      "step": 102
    },
    {
      "epoch": 0.02715707600026366,
      "grad_norm": 0.2406070977449417,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.6396,
      "step": 103
    },
    {
      "epoch": 0.027420736932305057,
      "grad_norm": 0.238611102104187,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.6986,
      "step": 104
    },
    {
      "epoch": 0.02768439786434645,
      "grad_norm": 0.2574085295200348,
      "learning_rate": 5e-05,
      "loss": 0.696,
      "step": 105
    },
    {
      "epoch": 0.027948058796387846,
      "grad_norm": 0.25945642590522766,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.7409,
      "step": 106
    },
    {
      "epoch": 0.02821171972842924,
      "grad_norm": 0.2767218351364136,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.9037,
      "step": 107
    },
    {
      "epoch": 0.028475380660470635,
      "grad_norm": 0.271837055683136,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.8678,
      "step": 108
    },
    {
      "epoch": 0.02873904159251203,
      "grad_norm": 0.2815798223018646,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.6653,
      "step": 109
    },
    {
      "epoch": 0.029002702524553423,
      "grad_norm": 0.24357305467128754,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.8375,
      "step": 110
    },
    {
      "epoch": 0.029266363456594818,
      "grad_norm": 0.20489011704921722,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.3579,
      "step": 111
    },
    {
      "epoch": 0.029530024388636215,
      "grad_norm": 0.29460063576698303,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.7047,
      "step": 112
    },
    {
      "epoch": 0.02979368532067761,
      "grad_norm": 0.2935718297958374,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.6283,
      "step": 113
    },
    {
      "epoch": 0.030057346252719004,
      "grad_norm": 0.49486255645751953,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.6777,
      "step": 114
    },
    {
      "epoch": 0.0303210071847604,
      "grad_norm": 0.3212812840938568,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.6966,
      "step": 115
    },
    {
      "epoch": 0.030584668116801793,
      "grad_norm": 0.255010724067688,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.6469,
      "step": 116
    },
    {
      "epoch": 0.030848329048843187,
      "grad_norm": 0.2829441726207733,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.5129,
      "step": 117
    },
    {
      "epoch": 0.03111198998088458,
      "grad_norm": 0.27641287446022034,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.5065,
      "step": 118
    },
    {
      "epoch": 0.031375650912925976,
      "grad_norm": 0.2954306900501251,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.5628,
      "step": 119
    },
    {
      "epoch": 0.03163931184496737,
      "grad_norm": 0.30299311876296997,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.6416,
      "step": 120
    },
    {
      "epoch": 0.031902972777008765,
      "grad_norm": 0.32437580823898315,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.5755,
      "step": 121
    },
    {
      "epoch": 0.03216663370905016,
      "grad_norm": 0.2981416583061218,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.4612,
      "step": 122
    },
    {
      "epoch": 0.03243029464109155,
      "grad_norm": 0.38622263073921204,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.5701,
      "step": 123
    },
    {
      "epoch": 0.03269395557313295,
      "grad_norm": 0.3319215476512909,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.475,
      "step": 124
    },
    {
      "epoch": 0.03295761650517435,
      "grad_norm": 0.35353654623031616,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.4939,
      "step": 125
    },
    {
      "epoch": 0.03322127743721574,
      "grad_norm": 0.3070884048938751,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.41,
      "step": 126
    },
    {
      "epoch": 0.03348493836925714,
      "grad_norm": 0.3445681929588318,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.4273,
      "step": 127
    },
    {
      "epoch": 0.03374859930129853,
      "grad_norm": 0.47943946719169617,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.5697,
      "step": 128
    },
    {
      "epoch": 0.034012260233339926,
      "grad_norm": 0.3207570016384125,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.4009,
      "step": 129
    },
    {
      "epoch": 0.03427592116538132,
      "grad_norm": 0.3537805676460266,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.5655,
      "step": 130
    },
    {
      "epoch": 0.034539582097422715,
      "grad_norm": 0.28048697113990784,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.2869,
      "step": 131
    },
    {
      "epoch": 0.03480324302946411,
      "grad_norm": 0.37943679094314575,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.3578,
      "step": 132
    },
    {
      "epoch": 0.035066903961505504,
      "grad_norm": 0.39380770921707153,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.4122,
      "step": 133
    },
    {
      "epoch": 0.0353305648935469,
      "grad_norm": 0.5841915607452393,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.7733,
      "step": 134
    },
    {
      "epoch": 0.03559422582558829,
      "grad_norm": 0.47341108322143555,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.5886,
      "step": 135
    },
    {
      "epoch": 0.03585788675762969,
      "grad_norm": 0.4565005898475647,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.5382,
      "step": 136
    },
    {
      "epoch": 0.03612154768967108,
      "grad_norm": 0.4016457498073578,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.4053,
      "step": 137
    },
    {
      "epoch": 0.036385208621712475,
      "grad_norm": 0.4420446753501892,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.4808,
      "step": 138
    },
    {
      "epoch": 0.03664886955375387,
      "grad_norm": 0.5043056607246399,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.6891,
      "step": 139
    },
    {
      "epoch": 0.036912530485795264,
      "grad_norm": 0.42550402879714966,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.3983,
      "step": 140
    },
    {
      "epoch": 0.037176191417836665,
      "grad_norm": 0.4835595488548279,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.5536,
      "step": 141
    },
    {
      "epoch": 0.03743985234987806,
      "grad_norm": 0.549207866191864,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.632,
      "step": 142
    },
    {
      "epoch": 0.037703513281919454,
      "grad_norm": 0.53291916847229,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.4724,
      "step": 143
    },
    {
      "epoch": 0.03796717421396085,
      "grad_norm": 0.5026512145996094,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.4151,
      "step": 144
    },
    {
      "epoch": 0.03823083514600224,
      "grad_norm": 0.639258086681366,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.6331,
      "step": 145
    },
    {
      "epoch": 0.03849449607804364,
      "grad_norm": 0.5291179418563843,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.4685,
      "step": 146
    },
    {
      "epoch": 0.03875815701008503,
      "grad_norm": 0.6299116015434265,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.4966,
      "step": 147
    },
    {
      "epoch": 0.039021817942126426,
      "grad_norm": 0.6671526432037354,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.4524,
      "step": 148
    },
    {
      "epoch": 0.03928547887416782,
      "grad_norm": 0.7377102375030518,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.4995,
      "step": 149
    },
    {
      "epoch": 0.039549139806209214,
      "grad_norm": 1.2966046333312988,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.6838,
      "step": 150
    },
    {
      "epoch": 0.039549139806209214,
      "eval_loss": 0.5702028274536133,
      "eval_runtime": 495.0811,
      "eval_samples_per_second": 12.903,
      "eval_steps_per_second": 3.226,
      "step": 150
    },
    {
      "epoch": 0.03981280073825061,
      "grad_norm": 0.10684983432292938,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.3825,
      "step": 151
    },
    {
      "epoch": 0.040076461670292,
      "grad_norm": 0.16391943395137787,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.6977,
      "step": 152
    },
    {
      "epoch": 0.0403401226023334,
      "grad_norm": 0.160983607172966,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.8048,
      "step": 153
    },
    {
      "epoch": 0.04060378353437479,
      "grad_norm": 0.17758332192897797,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.613,
      "step": 154
    },
    {
      "epoch": 0.040867444466416186,
      "grad_norm": 0.1992490142583847,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.6357,
      "step": 155
    },
    {
      "epoch": 0.04113110539845758,
      "grad_norm": 0.22437208890914917,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.6389,
      "step": 156
    },
    {
      "epoch": 0.041394766330498975,
      "grad_norm": 0.2498214691877365,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.6737,
      "step": 157
    },
    {
      "epoch": 0.041658427262540376,
      "grad_norm": 0.27671244740486145,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.7536,
      "step": 158
    },
    {
      "epoch": 0.04192208819458177,
      "grad_norm": 0.288952499628067,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.7413,
      "step": 159
    },
    {
      "epoch": 0.042185749126623165,
      "grad_norm": 0.2826245427131653,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.613,
      "step": 160
    },
    {
      "epoch": 0.04244941005866456,
      "grad_norm": 0.3109495937824249,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.7929,
      "step": 161
    },
    {
      "epoch": 0.042713070990705954,
      "grad_norm": 0.30872705578804016,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.654,
      "step": 162
    },
    {
      "epoch": 0.04297673192274735,
      "grad_norm": 0.27852779626846313,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.4808,
      "step": 163
    },
    {
      "epoch": 0.04324039285478874,
      "grad_norm": 0.2739834487438202,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.4303,
      "step": 164
    },
    {
      "epoch": 0.04350405378683014,
      "grad_norm": 0.29270297288894653,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.5114,
      "step": 165
    },
    {
      "epoch": 0.04376771471887153,
      "grad_norm": 0.44330957531929016,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.524,
      "step": 166
    },
    {
      "epoch": 0.044031375650912925,
      "grad_norm": 0.31058692932128906,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.5357,
      "step": 167
    },
    {
      "epoch": 0.04429503658295432,
      "grad_norm": 0.2848276197910309,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.4307,
      "step": 168
    },
    {
      "epoch": 0.044558697514995714,
      "grad_norm": 0.30231791734695435,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.5543,
      "step": 169
    },
    {
      "epoch": 0.04482235844703711,
      "grad_norm": 0.3995198905467987,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.5159,
      "step": 170
    },
    {
      "epoch": 0.0450860193790785,
      "grad_norm": 0.47199520468711853,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.5438,
      "step": 171
    },
    {
      "epoch": 0.0453496803111199,
      "grad_norm": 0.3752422630786896,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.6378,
      "step": 172
    },
    {
      "epoch": 0.04561334124316129,
      "grad_norm": 0.3017498850822449,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.4429,
      "step": 173
    },
    {
      "epoch": 0.04587700217520269,
      "grad_norm": 0.298752099275589,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.3303,
      "step": 174
    },
    {
      "epoch": 0.04614066310724409,
      "grad_norm": 0.41403594613075256,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.7195,
      "step": 175
    },
    {
      "epoch": 0.04640432403928548,
      "grad_norm": 0.4239666163921356,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.4471,
      "step": 176
    },
    {
      "epoch": 0.046667984971326876,
      "grad_norm": 0.31571587920188904,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.4218,
      "step": 177
    },
    {
      "epoch": 0.04693164590336827,
      "grad_norm": 0.3147188127040863,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.3724,
      "step": 178
    },
    {
      "epoch": 0.047195306835409664,
      "grad_norm": 0.39683017134666443,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.5709,
      "step": 179
    },
    {
      "epoch": 0.04745896776745106,
      "grad_norm": 0.40285035967826843,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.5661,
      "step": 180
    },
    {
      "epoch": 0.04772262869949245,
      "grad_norm": 0.3275766670703888,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.3526,
      "step": 181
    },
    {
      "epoch": 0.04798628963153385,
      "grad_norm": 0.35848158597946167,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.2825,
      "step": 182
    },
    {
      "epoch": 0.04824995056357524,
      "grad_norm": 0.3489744961261749,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.4479,
      "step": 183
    },
    {
      "epoch": 0.048513611495616636,
      "grad_norm": 0.44639351963996887,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.4804,
      "step": 184
    },
    {
      "epoch": 0.04877727242765803,
      "grad_norm": 0.44339853525161743,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.4626,
      "step": 185
    },
    {
      "epoch": 0.049040933359699425,
      "grad_norm": 0.3834573030471802,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.4483,
      "step": 186
    },
    {
      "epoch": 0.04930459429174082,
      "grad_norm": 0.3693370521068573,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.411,
      "step": 187
    },
    {
      "epoch": 0.049568255223782214,
      "grad_norm": 0.5548495650291443,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.6036,
      "step": 188
    },
    {
      "epoch": 0.04983191615582361,
      "grad_norm": 0.36186012625694275,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.2713,
      "step": 189
    },
    {
      "epoch": 0.050095577087865,
      "grad_norm": 0.46153709292411804,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.4592,
      "step": 190
    },
    {
      "epoch": 0.050359238019906404,
      "grad_norm": 0.4668102562427521,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.5007,
      "step": 191
    },
    {
      "epoch": 0.0506228989519478,
      "grad_norm": 0.4957490563392639,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.4898,
      "step": 192
    },
    {
      "epoch": 0.05088655988398919,
      "grad_norm": 0.43817606568336487,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.3587,
      "step": 193
    },
    {
      "epoch": 0.05115022081603059,
      "grad_norm": 0.5043736696243286,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.4334,
      "step": 194
    },
    {
      "epoch": 0.05141388174807198,
      "grad_norm": 0.5509034991264343,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.4383,
      "step": 195
    },
    {
      "epoch": 0.051677542680113375,
      "grad_norm": 0.6229900121688843,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.5876,
      "step": 196
    },
    {
      "epoch": 0.05194120361215477,
      "grad_norm": 0.8143970370292664,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.675,
      "step": 197
    },
    {
      "epoch": 0.052204864544196164,
      "grad_norm": 0.8275181651115417,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.677,
      "step": 198
    },
    {
      "epoch": 0.05246852547623756,
      "grad_norm": 0.8400267958641052,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.6788,
      "step": 199
    },
    {
      "epoch": 0.05273218640827895,
      "grad_norm": 1.113344430923462,
      "learning_rate": 0.0,
      "loss": 0.8408,
      "step": 200
    },
    {
      "epoch": 0.05273218640827895,
      "eval_loss": 0.5681252479553223,
      "eval_runtime": 494.9915,
      "eval_samples_per_second": 12.905,
      "eval_steps_per_second": 3.226,
      "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": 2.7707591269495603e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}