{
  "best_metric": 0.562271237373352,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.013162874113562697,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.581437056781349e-05,
      "grad_norm": 1.0699650049209595,
      "learning_rate": 1e-05,
      "loss": 0.637,
      "step": 1
    },
    {
      "epoch": 6.581437056781349e-05,
      "eval_loss": 1.0002368688583374,
      "eval_runtime": 551.1643,
      "eval_samples_per_second": 46.429,
      "eval_steps_per_second": 11.608,
      "step": 1
    },
    {
      "epoch": 0.00013162874113562697,
      "grad_norm": 2.1881673336029053,
      "learning_rate": 2e-05,
      "loss": 0.9542,
      "step": 2
    },
    {
      "epoch": 0.00019744311170344044,
      "grad_norm": 2.023360013961792,
      "learning_rate": 3e-05,
      "loss": 0.9932,
      "step": 3
    },
    {
      "epoch": 0.00026325748227125394,
      "grad_norm": 0.9622493982315063,
      "learning_rate": 4e-05,
      "loss": 0.7212,
      "step": 4
    },
    {
      "epoch": 0.0003290718528390674,
      "grad_norm": 0.841331422328949,
      "learning_rate": 5e-05,
      "loss": 0.6929,
      "step": 5
    },
    {
      "epoch": 0.0003948862234068809,
      "grad_norm": 0.6500568985939026,
      "learning_rate": 6e-05,
      "loss": 0.8744,
      "step": 6
    },
    {
      "epoch": 0.0004607005939746944,
      "grad_norm": 0.5632097721099854,
      "learning_rate": 7e-05,
      "loss": 0.8446,
      "step": 7
    },
    {
      "epoch": 0.0005265149645425079,
      "grad_norm": 0.6277199387550354,
      "learning_rate": 8e-05,
      "loss": 0.8581,
      "step": 8
    },
    {
      "epoch": 0.0005923293351103214,
      "grad_norm": 0.6068065762519836,
      "learning_rate": 9e-05,
      "loss": 0.7305,
      "step": 9
    },
    {
      "epoch": 0.0006581437056781348,
      "grad_norm": 0.5233731865882874,
      "learning_rate": 0.0001,
      "loss": 0.7564,
      "step": 10
    },
    {
      "epoch": 0.0007239580762459483,
      "grad_norm": 0.6165419220924377,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.7751,
      "step": 11
    },
    {
      "epoch": 0.0007897724468137618,
      "grad_norm": 0.6531275510787964,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.8675,
      "step": 12
    },
    {
      "epoch": 0.0008555868173815753,
      "grad_norm": 0.9979423880577087,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.901,
      "step": 13
    },
    {
      "epoch": 0.0009214011879493888,
      "grad_norm": 0.6355984210968018,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.7066,
      "step": 14
    },
    {
      "epoch": 0.0009872155585172022,
      "grad_norm": 0.6977342963218689,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.7965,
      "step": 15
    },
    {
      "epoch": 0.0010530299290850158,
      "grad_norm": 0.7177662253379822,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.797,
      "step": 16
    },
    {
      "epoch": 0.0011188442996528292,
      "grad_norm": 0.7751869559288025,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.8976,
      "step": 17
    },
    {
      "epoch": 0.0011846586702206428,
      "grad_norm": 0.5987713932991028,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.7623,
      "step": 18
    },
    {
      "epoch": 0.0012504730407884562,
      "grad_norm": 0.6170699000358582,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.6535,
      "step": 19
    },
    {
      "epoch": 0.0013162874113562695,
      "grad_norm": 0.6360906362533569,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.7772,
      "step": 20
    },
    {
      "epoch": 0.0013821017819240832,
      "grad_norm": 0.6145769357681274,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.6495,
      "step": 21
    },
    {
      "epoch": 0.0014479161524918965,
      "grad_norm": 0.6427063941955566,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.704,
      "step": 22
    },
    {
      "epoch": 0.0015137305230597102,
      "grad_norm": 0.6871214509010315,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.8987,
      "step": 23
    },
    {
      "epoch": 0.0015795448936275235,
      "grad_norm": 0.5951144695281982,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.6902,
      "step": 24
    },
    {
      "epoch": 0.0016453592641953371,
      "grad_norm": 0.6500367522239685,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.7799,
      "step": 25
    },
    {
      "epoch": 0.0017111736347631505,
      "grad_norm": 0.6611123085021973,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.797,
      "step": 26
    },
    {
      "epoch": 0.001776988005330964,
      "grad_norm": 0.7094174027442932,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.7681,
      "step": 27
    },
    {
      "epoch": 0.0018428023758987775,
      "grad_norm": 0.6624967455863953,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.7345,
      "step": 28
    },
    {
      "epoch": 0.001908616746466591,
      "grad_norm": 0.7387915253639221,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8583,
      "step": 29
    },
    {
      "epoch": 0.0019744311170344043,
      "grad_norm": 0.6667190194129944,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.7071,
      "step": 30
    },
    {
      "epoch": 0.002040245487602218,
      "grad_norm": 0.9777696132659912,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.8538,
      "step": 31
    },
    {
      "epoch": 0.0021060598581700315,
      "grad_norm": 0.8049740791320801,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.8842,
      "step": 32
    },
    {
      "epoch": 0.002171874228737845,
      "grad_norm": 0.7881101369857788,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.8156,
      "step": 33
    },
    {
      "epoch": 0.0022376885993056583,
      "grad_norm": 0.7451800107955933,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.915,
      "step": 34
    },
    {
      "epoch": 0.0023035029698734717,
      "grad_norm": 0.7947197556495667,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.8311,
      "step": 35
    },
    {
      "epoch": 0.0023693173404412855,
      "grad_norm": 0.7360652089118958,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8241,
      "step": 36
    },
    {
      "epoch": 0.002435131711009099,
      "grad_norm": 0.9908323884010315,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.9708,
      "step": 37
    },
    {
      "epoch": 0.0025009460815769123,
      "grad_norm": 0.7604827880859375,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.7927,
      "step": 38
    },
    {
      "epoch": 0.0025667604521447257,
      "grad_norm": 0.9196210503578186,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.9204,
      "step": 39
    },
    {
      "epoch": 0.002632574822712539,
      "grad_norm": 0.9090496301651001,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.8129,
      "step": 40
    },
    {
      "epoch": 0.002698389193280353,
      "grad_norm": 0.9374238848686218,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.8409,
      "step": 41
    },
    {
      "epoch": 0.0027642035638481663,
      "grad_norm": 1.0455806255340576,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.9103,
      "step": 42
    },
    {
      "epoch": 0.0028300179344159797,
      "grad_norm": 0.8809170722961426,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.7275,
      "step": 43
    },
    {
      "epoch": 0.002895832304983793,
      "grad_norm": 1.0520704984664917,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.7394,
      "step": 44
    },
    {
      "epoch": 0.0029616466755516065,
      "grad_norm": 1.284458875656128,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.7696,
      "step": 45
    },
    {
      "epoch": 0.0030274610461194203,
      "grad_norm": 1.0618311166763306,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.7598,
      "step": 46
    },
    {
      "epoch": 0.0030932754166872337,
      "grad_norm": 1.1072180271148682,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.6633,
      "step": 47
    },
    {
      "epoch": 0.003159089787255047,
      "grad_norm": 1.2657697200775146,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8497,
      "step": 48
    },
    {
      "epoch": 0.0032249041578228605,
      "grad_norm": 1.1808794736862183,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.6705,
      "step": 49
    },
    {
      "epoch": 0.0032907185283906743,
      "grad_norm": 1.749930739402771,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.7677,
      "step": 50
    },
    {
      "epoch": 0.0032907185283906743,
      "eval_loss": 0.737312912940979,
      "eval_runtime": 553.3987,
      "eval_samples_per_second": 46.242,
      "eval_steps_per_second": 11.561,
      "step": 50
    },
    {
      "epoch": 0.0033565328989584877,
      "grad_norm": 0.6965735554695129,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.5879,
      "step": 51
    },
    {
      "epoch": 0.003422347269526301,
      "grad_norm": 0.8206866383552551,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.9297,
      "step": 52
    },
    {
      "epoch": 0.0034881616400941145,
      "grad_norm": 0.559311032295227,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.7155,
      "step": 53
    },
    {
      "epoch": 0.003553976010661928,
      "grad_norm": 0.6048831939697266,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.789,
      "step": 54
    },
    {
      "epoch": 0.0036197903812297417,
      "grad_norm": 0.4044651985168457,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.587,
      "step": 55
    },
    {
      "epoch": 0.003685604751797555,
      "grad_norm": 0.44206809997558594,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.6626,
      "step": 56
    },
    {
      "epoch": 0.0037514191223653685,
      "grad_norm": 0.4153965711593628,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.7381,
      "step": 57
    },
    {
      "epoch": 0.003817233492933182,
      "grad_norm": 0.48236000537872314,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.7118,
      "step": 58
    },
    {
      "epoch": 0.0038830478635009952,
      "grad_norm": 0.4431040287017822,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.674,
      "step": 59
    },
    {
      "epoch": 0.003948862234068809,
      "grad_norm": 0.42442092299461365,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.6296,
      "step": 60
    },
    {
      "epoch": 0.004014676604636622,
      "grad_norm": 0.5674850940704346,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.6847,
      "step": 61
    },
    {
      "epoch": 0.004080490975204436,
      "grad_norm": 0.6120259761810303,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.7442,
      "step": 62
    },
    {
      "epoch": 0.00414630534577225,
      "grad_norm": 0.5356990694999695,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.7836,
      "step": 63
    },
    {
      "epoch": 0.004212119716340063,
      "grad_norm": 0.7407199740409851,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.6663,
      "step": 64
    },
    {
      "epoch": 0.0042779340869078765,
      "grad_norm": 0.5050602555274963,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.6194,
      "step": 65
    },
    {
      "epoch": 0.00434374845747569,
      "grad_norm": 0.4929707944393158,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.6663,
      "step": 66
    },
    {
      "epoch": 0.004409562828043503,
      "grad_norm": 0.5779139399528503,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.7414,
      "step": 67
    },
    {
      "epoch": 0.004475377198611317,
      "grad_norm": 0.7830822467803955,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.7149,
      "step": 68
    },
    {
      "epoch": 0.00454119156917913,
      "grad_norm": 0.6778038144111633,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.6326,
      "step": 69
    },
    {
      "epoch": 0.004607005939746943,
      "grad_norm": 0.49016252160072327,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.611,
      "step": 70
    },
    {
      "epoch": 0.004672820310314757,
      "grad_norm": 0.5830350518226624,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.6988,
      "step": 71
    },
    {
      "epoch": 0.004738634680882571,
      "grad_norm": 0.6419764757156372,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.5652,
      "step": 72
    },
    {
      "epoch": 0.0048044490514503845,
      "grad_norm": 0.6941208243370056,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.7051,
      "step": 73
    },
    {
      "epoch": 0.004870263422018198,
      "grad_norm": 0.6661511659622192,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.7116,
      "step": 74
    },
    {
      "epoch": 0.004936077792586011,
      "grad_norm": 0.5485235452651978,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.5837,
      "step": 75
    },
    {
      "epoch": 0.005001892163153825,
      "grad_norm": 0.7659062147140503,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.7282,
      "step": 76
    },
    {
      "epoch": 0.005067706533721638,
      "grad_norm": 0.7303984761238098,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.7298,
      "step": 77
    },
    {
      "epoch": 0.005133520904289451,
      "grad_norm": 0.6489834785461426,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.6417,
      "step": 78
    },
    {
      "epoch": 0.005199335274857265,
      "grad_norm": 0.7203121781349182,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.6828,
      "step": 79
    },
    {
      "epoch": 0.005265149645425078,
      "grad_norm": 0.5644537806510925,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.6446,
      "step": 80
    },
    {
      "epoch": 0.0053309640159928924,
      "grad_norm": 0.714026153087616,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7403,
      "step": 81
    },
    {
      "epoch": 0.005396778386560706,
      "grad_norm": 0.6471198201179504,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.6569,
      "step": 82
    },
    {
      "epoch": 0.005462592757128519,
      "grad_norm": 0.9100525379180908,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.6769,
      "step": 83
    },
    {
      "epoch": 0.005528407127696333,
      "grad_norm": 0.674645721912384,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.6862,
      "step": 84
    },
    {
      "epoch": 0.005594221498264146,
      "grad_norm": 0.6320260167121887,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.6752,
      "step": 85
    },
    {
      "epoch": 0.005660035868831959,
      "grad_norm": 0.692147970199585,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7769,
      "step": 86
    },
    {
      "epoch": 0.005725850239399773,
      "grad_norm": 0.8295859098434448,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.6455,
      "step": 87
    },
    {
      "epoch": 0.005791664609967586,
      "grad_norm": 0.7497966289520264,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.7241,
      "step": 88
    },
    {
      "epoch": 0.0058574789805354,
      "grad_norm": 0.7630535364151001,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.6203,
      "step": 89
    },
    {
      "epoch": 0.005923293351103213,
      "grad_norm": 1.431287169456482,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.7686,
      "step": 90
    },
    {
      "epoch": 0.005989107721671027,
      "grad_norm": 0.9013983607292175,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.7115,
      "step": 91
    },
    {
      "epoch": 0.006054922092238841,
      "grad_norm": 0.8418143391609192,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.6184,
      "step": 92
    },
    {
      "epoch": 0.006120736462806654,
      "grad_norm": 0.8123591542243958,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.6693,
      "step": 93
    },
    {
      "epoch": 0.006186550833374467,
      "grad_norm": 0.8375664353370667,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.6005,
      "step": 94
    },
    {
      "epoch": 0.006252365203942281,
      "grad_norm": 0.8595738410949707,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.5287,
      "step": 95
    },
    {
      "epoch": 0.006318179574510094,
      "grad_norm": 0.8303048014640808,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.5881,
      "step": 96
    },
    {
      "epoch": 0.0063839939450779076,
      "grad_norm": 0.9408706426620483,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.5535,
      "step": 97
    },
    {
      "epoch": 0.006449808315645721,
      "grad_norm": 1.3673332929611206,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.6219,
      "step": 98
    },
    {
      "epoch": 0.006515622686213534,
      "grad_norm": 0.9500559568405151,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.5175,
      "step": 99
    },
    {
      "epoch": 0.006581437056781349,
      "grad_norm": 1.6167755126953125,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.5601,
      "step": 100
    },
    {
      "epoch": 0.006581437056781349,
      "eval_loss": 0.6281580328941345,
      "eval_runtime": 553.4582,
      "eval_samples_per_second": 46.237,
      "eval_steps_per_second": 11.56,
      "step": 100
    },
    {
      "epoch": 0.006647251427349162,
      "grad_norm": 0.41185927391052246,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.6323,
      "step": 101
    },
    {
      "epoch": 0.006713065797916975,
      "grad_norm": 0.5667064189910889,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.7606,
      "step": 102
    },
    {
      "epoch": 0.006778880168484789,
      "grad_norm": 0.5387095808982849,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.722,
      "step": 103
    },
    {
      "epoch": 0.006844694539052602,
      "grad_norm": 0.552873969078064,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.7744,
      "step": 104
    },
    {
      "epoch": 0.0069105089096204156,
      "grad_norm": 0.4560691714286804,
      "learning_rate": 5e-05,
      "loss": 0.5847,
      "step": 105
    },
    {
      "epoch": 0.006976323280188229,
      "grad_norm": 0.5347249507904053,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.6936,
      "step": 106
    },
    {
      "epoch": 0.007042137650756042,
      "grad_norm": 0.5728479623794556,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.8053,
      "step": 107
    },
    {
      "epoch": 0.007107952021323856,
      "grad_norm": 0.44795462489128113,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.611,
      "step": 108
    },
    {
      "epoch": 0.007173766391891669,
      "grad_norm": 0.5209128856658936,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.6785,
      "step": 109
    },
    {
      "epoch": 0.007239580762459483,
      "grad_norm": 0.5290679931640625,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.5595,
      "step": 110
    },
    {
      "epoch": 0.007305395133027297,
      "grad_norm": 0.5243308544158936,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.6204,
      "step": 111
    },
    {
      "epoch": 0.00737120950359511,
      "grad_norm": 0.5704305768013,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.7303,
      "step": 112
    },
    {
      "epoch": 0.0074370238741629235,
      "grad_norm": 0.5222331881523132,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.621,
      "step": 113
    },
    {
      "epoch": 0.007502838244730737,
      "grad_norm": 0.46589380502700806,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.5347,
      "step": 114
    },
    {
      "epoch": 0.00756865261529855,
      "grad_norm": 0.5662083029747009,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.725,
      "step": 115
    },
    {
      "epoch": 0.007634466985866364,
      "grad_norm": 0.5767953991889954,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.6495,
      "step": 116
    },
    {
      "epoch": 0.007700281356434177,
      "grad_norm": 0.5558140277862549,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.5876,
      "step": 117
    },
    {
      "epoch": 0.0077660957270019905,
      "grad_norm": 0.6843581795692444,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.7425,
      "step": 118
    },
    {
      "epoch": 0.007831910097569804,
      "grad_norm": 0.7375394105911255,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.7097,
      "step": 119
    },
    {
      "epoch": 0.007897724468137617,
      "grad_norm": 0.6485143899917603,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.6329,
      "step": 120
    },
    {
      "epoch": 0.00796353883870543,
      "grad_norm": 0.5743327140808105,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.6943,
      "step": 121
    },
    {
      "epoch": 0.008029353209273244,
      "grad_norm": 0.6702543497085571,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.7359,
      "step": 122
    },
    {
      "epoch": 0.008095167579841057,
      "grad_norm": 0.6396421194076538,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.5619,
      "step": 123
    },
    {
      "epoch": 0.008160981950408873,
      "grad_norm": 0.6337171792984009,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7238,
      "step": 124
    },
    {
      "epoch": 0.008226796320976686,
      "grad_norm": 0.6197124123573303,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.6401,
      "step": 125
    },
    {
      "epoch": 0.0082926106915445,
      "grad_norm": 0.615145206451416,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.5739,
      "step": 126
    },
    {
      "epoch": 0.008358425062112313,
      "grad_norm": 0.6297168135643005,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.5333,
      "step": 127
    },
    {
      "epoch": 0.008424239432680126,
      "grad_norm": 0.6640601754188538,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.6602,
      "step": 128
    },
    {
      "epoch": 0.00849005380324794,
      "grad_norm": 0.6419907808303833,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.605,
      "step": 129
    },
    {
      "epoch": 0.008555868173815753,
      "grad_norm": 0.7055049538612366,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.6048,
      "step": 130
    },
    {
      "epoch": 0.008621682544383566,
      "grad_norm": 0.6677399277687073,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.6465,
      "step": 131
    },
    {
      "epoch": 0.00868749691495138,
      "grad_norm": 0.7924658060073853,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.5897,
      "step": 132
    },
    {
      "epoch": 0.008753311285519193,
      "grad_norm": 0.8668441772460938,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.7018,
      "step": 133
    },
    {
      "epoch": 0.008819125656087006,
      "grad_norm": 0.7262378334999084,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.6495,
      "step": 134
    },
    {
      "epoch": 0.00888494002665482,
      "grad_norm": 0.8412954807281494,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.6038,
      "step": 135
    },
    {
      "epoch": 0.008950754397222633,
      "grad_norm": 0.8177767992019653,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.6028,
      "step": 136
    },
    {
      "epoch": 0.009016568767790447,
      "grad_norm": 0.8152193427085876,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.6051,
      "step": 137
    },
    {
      "epoch": 0.00908238313835826,
      "grad_norm": 0.8891797065734863,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.7115,
      "step": 138
    },
    {
      "epoch": 0.009148197508926073,
      "grad_norm": 0.8816660046577454,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.6827,
      "step": 139
    },
    {
      "epoch": 0.009214011879493887,
      "grad_norm": 1.2722572088241577,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.7122,
      "step": 140
    },
    {
      "epoch": 0.0092798262500617,
      "grad_norm": 0.9090240597724915,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.574,
      "step": 141
    },
    {
      "epoch": 0.009345640620629514,
      "grad_norm": 1.0362657308578491,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.5447,
      "step": 142
    },
    {
      "epoch": 0.009411454991197329,
      "grad_norm": 0.8651535511016846,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6241,
      "step": 143
    },
    {
      "epoch": 0.009477269361765142,
      "grad_norm": 0.8616403937339783,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.5031,
      "step": 144
    },
    {
      "epoch": 0.009543083732332956,
      "grad_norm": 1.0660407543182373,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.4611,
      "step": 145
    },
    {
      "epoch": 0.009608898102900769,
      "grad_norm": 1.0348179340362549,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.6015,
      "step": 146
    },
    {
      "epoch": 0.009674712473468582,
      "grad_norm": 1.0817776918411255,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.5383,
      "step": 147
    },
    {
      "epoch": 0.009740526844036396,
      "grad_norm": 1.0472996234893799,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.4064,
      "step": 148
    },
    {
      "epoch": 0.009806341214604209,
      "grad_norm": 0.7829207181930542,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.3483,
      "step": 149
    },
    {
      "epoch": 0.009872155585172022,
      "grad_norm": 1.3173916339874268,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.3241,
      "step": 150
    },
    {
      "epoch": 0.009872155585172022,
      "eval_loss": 0.5717162489891052,
      "eval_runtime": 553.4017,
      "eval_samples_per_second": 46.241,
      "eval_steps_per_second": 11.561,
      "step": 150
    },
    {
      "epoch": 0.009937969955739836,
      "grad_norm": 0.3278624713420868,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.5442,
      "step": 151
    },
    {
      "epoch": 0.01000378432630765,
      "grad_norm": 0.4341107904911041,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.627,
      "step": 152
    },
    {
      "epoch": 0.010069598696875463,
      "grad_norm": 0.4436691999435425,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.5784,
      "step": 153
    },
    {
      "epoch": 0.010135413067443276,
      "grad_norm": 0.5091243982315063,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.716,
      "step": 154
    },
    {
      "epoch": 0.01020122743801109,
      "grad_norm": 0.46876412630081177,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.5737,
      "step": 155
    },
    {
      "epoch": 0.010267041808578903,
      "grad_norm": 0.4417664408683777,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.5466,
      "step": 156
    },
    {
      "epoch": 0.010332856179146716,
      "grad_norm": 0.5275467038154602,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.6402,
      "step": 157
    },
    {
      "epoch": 0.01039867054971453,
      "grad_norm": 0.5370584726333618,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.5601,
      "step": 158
    },
    {
      "epoch": 0.010464484920282343,
      "grad_norm": 0.4674217402935028,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.5362,
      "step": 159
    },
    {
      "epoch": 0.010530299290850156,
      "grad_norm": 0.5034341812133789,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.6606,
      "step": 160
    },
    {
      "epoch": 0.01059611366141797,
      "grad_norm": 0.5963544249534607,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.634,
      "step": 161
    },
    {
      "epoch": 0.010661928031985785,
      "grad_norm": 0.517716646194458,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.3996,
      "step": 162
    },
    {
      "epoch": 0.010727742402553598,
      "grad_norm": 0.4941765069961548,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.49,
      "step": 163
    },
    {
      "epoch": 0.010793556773121412,
      "grad_norm": 0.5404846668243408,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.6224,
      "step": 164
    },
    {
      "epoch": 0.010859371143689225,
      "grad_norm": 0.6639435291290283,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.5783,
      "step": 165
    },
    {
      "epoch": 0.010925185514257038,
      "grad_norm": 0.7051387429237366,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.7042,
      "step": 166
    },
    {
      "epoch": 0.010990999884824852,
      "grad_norm": 0.6842628717422485,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.6254,
      "step": 167
    },
    {
      "epoch": 0.011056814255392665,
      "grad_norm": 0.617725670337677,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.5744,
      "step": 168
    },
    {
      "epoch": 0.011122628625960479,
      "grad_norm": 0.6109086871147156,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.5963,
      "step": 169
    },
    {
      "epoch": 0.011188442996528292,
      "grad_norm": 0.661851167678833,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.6629,
      "step": 170
    },
    {
      "epoch": 0.011254257367096105,
      "grad_norm": 0.6781044602394104,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.4886,
      "step": 171
    },
    {
      "epoch": 0.011320071737663919,
      "grad_norm": 0.8734434843063354,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.8021,
      "step": 172
    },
    {
      "epoch": 0.011385886108231732,
      "grad_norm": 0.8503665924072266,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.7123,
      "step": 173
    },
    {
      "epoch": 0.011451700478799546,
      "grad_norm": 0.6418806910514832,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.4615,
      "step": 174
    },
    {
      "epoch": 0.011517514849367359,
      "grad_norm": 0.6718797087669373,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.598,
      "step": 175
    },
    {
      "epoch": 0.011583329219935172,
      "grad_norm": 0.6802588701248169,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.6231,
      "step": 176
    },
    {
      "epoch": 0.011649143590502986,
      "grad_norm": 0.8462066650390625,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.6946,
      "step": 177
    },
    {
      "epoch": 0.0117149579610708,
      "grad_norm": 0.870962917804718,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.6493,
      "step": 178
    },
    {
      "epoch": 0.011780772331638613,
      "grad_norm": 0.6191343665122986,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.5133,
      "step": 179
    },
    {
      "epoch": 0.011846586702206426,
      "grad_norm": 0.8624259233474731,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.6162,
      "step": 180
    },
    {
      "epoch": 0.011912401072774241,
      "grad_norm": 0.6586230993270874,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.4597,
      "step": 181
    },
    {
      "epoch": 0.011978215443342054,
      "grad_norm": 0.75957190990448,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.5504,
      "step": 182
    },
    {
      "epoch": 0.012044029813909868,
      "grad_norm": 0.894268810749054,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.6579,
      "step": 183
    },
    {
      "epoch": 0.012109844184477681,
      "grad_norm": 0.6885512471199036,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.5243,
      "step": 184
    },
    {
      "epoch": 0.012175658555045495,
      "grad_norm": 0.8117612600326538,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.5347,
      "step": 185
    },
    {
      "epoch": 0.012241472925613308,
      "grad_norm": 0.9484195709228516,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.5887,
      "step": 186
    },
    {
      "epoch": 0.012307287296181121,
      "grad_norm": 0.8544667959213257,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.6189,
      "step": 187
    },
    {
      "epoch": 0.012373101666748935,
      "grad_norm": 0.7418527603149414,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.561,
      "step": 188
    },
    {
      "epoch": 0.012438916037316748,
      "grad_norm": 0.8641708493232727,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.4965,
      "step": 189
    },
    {
      "epoch": 0.012504730407884562,
      "grad_norm": 0.9523416757583618,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.6498,
      "step": 190
    },
    {
      "epoch": 0.012570544778452375,
      "grad_norm": 0.8362764716148376,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.4882,
      "step": 191
    },
    {
      "epoch": 0.012636359149020188,
      "grad_norm": 0.9696873426437378,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.6087,
      "step": 192
    },
    {
      "epoch": 0.012702173519588002,
      "grad_norm": 0.9047473669052124,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.5516,
      "step": 193
    },
    {
      "epoch": 0.012767987890155815,
      "grad_norm": 0.7550218105316162,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.4225,
      "step": 194
    },
    {
      "epoch": 0.012833802260723629,
      "grad_norm": 0.9002018570899963,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.3978,
      "step": 195
    },
    {
      "epoch": 0.012899616631291442,
      "grad_norm": 0.8559175729751587,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.4371,
      "step": 196
    },
    {
      "epoch": 0.012965431001859255,
      "grad_norm": 0.9855750799179077,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.4347,
      "step": 197
    },
    {
      "epoch": 0.013031245372427069,
      "grad_norm": 1.4084457159042358,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.4691,
      "step": 198
    },
    {
      "epoch": 0.013097059742994882,
      "grad_norm": 1.090868592262268,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.371,
      "step": 199
    },
    {
      "epoch": 0.013162874113562697,
      "grad_norm": 1.0222355127334595,
      "learning_rate": 0.0,
      "loss": 0.2822,
      "step": 200
    },
    {
      "epoch": 0.013162874113562697,
      "eval_loss": 0.562271237373352,
      "eval_runtime": 553.2574,
      "eval_samples_per_second": 46.253,
      "eval_steps_per_second": 11.564,
      "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": 4.07893488697344e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}