{
  "best_metric": 0.9601866602897644,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.07561436672967864,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005040957781978576,
      "grad_norm": 0.7851808667182922,
      "learning_rate": 1e-05,
      "loss": 0.9219,
      "step": 1
    },
    {
      "epoch": 0.0005040957781978576,
      "eval_loss": 1.1706854104995728,
      "eval_runtime": 70.2236,
      "eval_samples_per_second": 47.577,
      "eval_steps_per_second": 11.905,
      "step": 1
    },
    {
      "epoch": 0.0010081915563957152,
      "grad_norm": 0.8648802042007446,
      "learning_rate": 2e-05,
      "loss": 1.0097,
      "step": 2
    },
    {
      "epoch": 0.0015122873345935729,
      "grad_norm": 0.731093168258667,
      "learning_rate": 3e-05,
      "loss": 0.9617,
      "step": 3
    },
    {
      "epoch": 0.0020163831127914303,
      "grad_norm": 0.6446400880813599,
      "learning_rate": 4e-05,
      "loss": 0.9963,
      "step": 4
    },
    {
      "epoch": 0.002520478890989288,
      "grad_norm": 0.6305974125862122,
      "learning_rate": 5e-05,
      "loss": 0.956,
      "step": 5
    },
    {
      "epoch": 0.0030245746691871457,
      "grad_norm": 0.852928876876831,
      "learning_rate": 6e-05,
      "loss": 0.9513,
      "step": 6
    },
    {
      "epoch": 0.003528670447385003,
      "grad_norm": 0.8347710371017456,
      "learning_rate": 7e-05,
      "loss": 0.9826,
      "step": 7
    },
    {
      "epoch": 0.004032766225582861,
      "grad_norm": 0.7358830571174622,
      "learning_rate": 8e-05,
      "loss": 1.0078,
      "step": 8
    },
    {
      "epoch": 0.004536862003780718,
      "grad_norm": 0.6131141185760498,
      "learning_rate": 9e-05,
      "loss": 0.966,
      "step": 9
    },
    {
      "epoch": 0.005040957781978576,
      "grad_norm": 0.6628008484840393,
      "learning_rate": 0.0001,
      "loss": 1.0056,
      "step": 10
    },
    {
      "epoch": 0.005545053560176433,
      "grad_norm": 0.6426183581352234,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.0338,
      "step": 11
    },
    {
      "epoch": 0.0060491493383742915,
      "grad_norm": 0.6265701651573181,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.9388,
      "step": 12
    },
    {
      "epoch": 0.006553245116572149,
      "grad_norm": 0.6738749146461487,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.9911,
      "step": 13
    },
    {
      "epoch": 0.007057340894770006,
      "grad_norm": 0.6448192000389099,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.9823,
      "step": 14
    },
    {
      "epoch": 0.007561436672967864,
      "grad_norm": 0.5898854732513428,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.9779,
      "step": 15
    },
    {
      "epoch": 0.008065532451165721,
      "grad_norm": 0.5653546452522278,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.9173,
      "step": 16
    },
    {
      "epoch": 0.00856962822936358,
      "grad_norm": 0.5700259804725647,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.9083,
      "step": 17
    },
    {
      "epoch": 0.009073724007561436,
      "grad_norm": 0.5963847041130066,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.0042,
      "step": 18
    },
    {
      "epoch": 0.009577819785759294,
      "grad_norm": 0.5476916432380676,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.9457,
      "step": 19
    },
    {
      "epoch": 0.010081915563957152,
      "grad_norm": 0.5964701771736145,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.9946,
      "step": 20
    },
    {
      "epoch": 0.01058601134215501,
      "grad_norm": 0.6130715012550354,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.9332,
      "step": 21
    },
    {
      "epoch": 0.011090107120352867,
      "grad_norm": 0.6350668668746948,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.0227,
      "step": 22
    },
    {
      "epoch": 0.011594202898550725,
      "grad_norm": 0.6542335152626038,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.9471,
      "step": 23
    },
    {
      "epoch": 0.012098298676748583,
      "grad_norm": 0.624995768070221,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.9539,
      "step": 24
    },
    {
      "epoch": 0.01260239445494644,
      "grad_norm": 0.6840269565582275,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.9486,
      "step": 25
    },
    {
      "epoch": 0.013106490233144297,
      "grad_norm": 0.7418709397315979,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.9635,
      "step": 26
    },
    {
      "epoch": 0.013610586011342156,
      "grad_norm": 0.7369248867034912,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.035,
      "step": 27
    },
    {
      "epoch": 0.014114681789540012,
      "grad_norm": 0.6638664603233337,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.8968,
      "step": 28
    },
    {
      "epoch": 0.01461877756773787,
      "grad_norm": 0.741362988948822,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.9482,
      "step": 29
    },
    {
      "epoch": 0.015122873345935728,
      "grad_norm": 0.8223165273666382,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.0101,
      "step": 30
    },
    {
      "epoch": 0.015626969124133586,
      "grad_norm": 0.8499884009361267,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.0493,
      "step": 31
    },
    {
      "epoch": 0.016131064902331443,
      "grad_norm": 0.8594983816146851,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.0085,
      "step": 32
    },
    {
      "epoch": 0.0166351606805293,
      "grad_norm": 1.0113023519515991,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.939,
      "step": 33
    },
    {
      "epoch": 0.01713925645872716,
      "grad_norm": 1.016897439956665,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.1272,
      "step": 34
    },
    {
      "epoch": 0.017643352236925015,
      "grad_norm": 1.1077070236206055,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.1256,
      "step": 35
    },
    {
      "epoch": 0.018147448015122872,
      "grad_norm": 1.234421968460083,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.0987,
      "step": 36
    },
    {
      "epoch": 0.01865154379332073,
      "grad_norm": 1.2606217861175537,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.9812,
      "step": 37
    },
    {
      "epoch": 0.019155639571518588,
      "grad_norm": 1.360200047492981,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.9274,
      "step": 38
    },
    {
      "epoch": 0.019659735349716444,
      "grad_norm": 1.617262840270996,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.08,
      "step": 39
    },
    {
      "epoch": 0.020163831127914304,
      "grad_norm": 1.4929728507995605,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.9906,
      "step": 40
    },
    {
      "epoch": 0.02066792690611216,
      "grad_norm": 1.6736871004104614,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.114,
      "step": 41
    },
    {
      "epoch": 0.02117202268431002,
      "grad_norm": 1.995395541191101,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.8387,
      "step": 42
    },
    {
      "epoch": 0.021676118462507877,
      "grad_norm": 2.214477777481079,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.1417,
      "step": 43
    },
    {
      "epoch": 0.022180214240705733,
      "grad_norm": 2.147244453430176,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.1272,
      "step": 44
    },
    {
      "epoch": 0.022684310018903593,
      "grad_norm": 2.3361599445343018,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.1843,
      "step": 45
    },
    {
      "epoch": 0.02318840579710145,
      "grad_norm": 2.324315071105957,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.234,
      "step": 46
    },
    {
      "epoch": 0.023692501575299306,
      "grad_norm": 2.6563589572906494,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.0599,
      "step": 47
    },
    {
      "epoch": 0.024196597353497166,
      "grad_norm": 3.113487482070923,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.5183,
      "step": 48
    },
    {
      "epoch": 0.024700693131695022,
      "grad_norm": 3.193916082382202,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.2843,
      "step": 49
    },
    {
      "epoch": 0.02520478890989288,
      "grad_norm": 4.234517574310303,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.4933,
      "step": 50
    },
    {
      "epoch": 0.02520478890989288,
      "eval_loss": 1.1050190925598145,
      "eval_runtime": 70.0275,
      "eval_samples_per_second": 47.71,
      "eval_steps_per_second": 11.938,
      "step": 50
    },
    {
      "epoch": 0.02570888468809074,
      "grad_norm": 1.292781949043274,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.9901,
      "step": 51
    },
    {
      "epoch": 0.026212980466288595,
      "grad_norm": 1.1206916570663452,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.0152,
      "step": 52
    },
    {
      "epoch": 0.02671707624448645,
      "grad_norm": 0.8595021367073059,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.9863,
      "step": 53
    },
    {
      "epoch": 0.02722117202268431,
      "grad_norm": 0.6013736724853516,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.0146,
      "step": 54
    },
    {
      "epoch": 0.027725267800882167,
      "grad_norm": 0.5559196472167969,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.9531,
      "step": 55
    },
    {
      "epoch": 0.028229363579080024,
      "grad_norm": 0.5038899779319763,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.9519,
      "step": 56
    },
    {
      "epoch": 0.028733459357277884,
      "grad_norm": 0.44719502329826355,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.9766,
      "step": 57
    },
    {
      "epoch": 0.02923755513547574,
      "grad_norm": 0.4539150297641754,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.9853,
      "step": 58
    },
    {
      "epoch": 0.029741650913673597,
      "grad_norm": 0.45345962047576904,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.9229,
      "step": 59
    },
    {
      "epoch": 0.030245746691871456,
      "grad_norm": 0.4743633568286896,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.9564,
      "step": 60
    },
    {
      "epoch": 0.030749842470069313,
      "grad_norm": 0.484157532453537,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.9582,
      "step": 61
    },
    {
      "epoch": 0.03125393824826717,
      "grad_norm": 0.44355064630508423,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.9991,
      "step": 62
    },
    {
      "epoch": 0.03175803402646503,
      "grad_norm": 0.40092796087265015,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.915,
      "step": 63
    },
    {
      "epoch": 0.032262129804662885,
      "grad_norm": 0.3976602554321289,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.891,
      "step": 64
    },
    {
      "epoch": 0.03276622558286074,
      "grad_norm": 0.41375917196273804,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.9286,
      "step": 65
    },
    {
      "epoch": 0.0332703213610586,
      "grad_norm": 0.4368148148059845,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.9392,
      "step": 66
    },
    {
      "epoch": 0.03377441713925646,
      "grad_norm": 0.4674438536167145,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.9399,
      "step": 67
    },
    {
      "epoch": 0.03427851291745432,
      "grad_norm": 0.4300023913383484,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.9015,
      "step": 68
    },
    {
      "epoch": 0.034782608695652174,
      "grad_norm": 0.44563958048820496,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.9133,
      "step": 69
    },
    {
      "epoch": 0.03528670447385003,
      "grad_norm": 0.4508240222930908,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.9124,
      "step": 70
    },
    {
      "epoch": 0.03579080025204789,
      "grad_norm": 0.48746979236602783,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.9495,
      "step": 71
    },
    {
      "epoch": 0.036294896030245744,
      "grad_norm": 0.5286091566085815,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.9482,
      "step": 72
    },
    {
      "epoch": 0.03679899180844361,
      "grad_norm": 0.5450381636619568,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.9255,
      "step": 73
    },
    {
      "epoch": 0.03730308758664146,
      "grad_norm": 0.5480132102966309,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.9612,
      "step": 74
    },
    {
      "epoch": 0.03780718336483932,
      "grad_norm": 0.5725929737091064,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.0166,
      "step": 75
    },
    {
      "epoch": 0.038311279143037176,
      "grad_norm": 0.5540945529937744,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.9842,
      "step": 76
    },
    {
      "epoch": 0.03881537492123503,
      "grad_norm": 0.593117356300354,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.9666,
      "step": 77
    },
    {
      "epoch": 0.03931947069943289,
      "grad_norm": 0.7941222190856934,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.9603,
      "step": 78
    },
    {
      "epoch": 0.03982356647763075,
      "grad_norm": 0.6581109166145325,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.9778,
      "step": 79
    },
    {
      "epoch": 0.04032766225582861,
      "grad_norm": 0.707141101360321,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.0769,
      "step": 80
    },
    {
      "epoch": 0.040831758034026465,
      "grad_norm": 0.7098904252052307,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.0253,
      "step": 81
    },
    {
      "epoch": 0.04133585381222432,
      "grad_norm": 0.725770115852356,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.9254,
      "step": 82
    },
    {
      "epoch": 0.04183994959042218,
      "grad_norm": 0.8920672535896301,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.9655,
      "step": 83
    },
    {
      "epoch": 0.04234404536862004,
      "grad_norm": 0.8527565002441406,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.924,
      "step": 84
    },
    {
      "epoch": 0.0428481411468179,
      "grad_norm": 0.9886060357093811,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.8559,
      "step": 85
    },
    {
      "epoch": 0.043352236925015754,
      "grad_norm": 0.9404958486557007,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7445,
      "step": 86
    },
    {
      "epoch": 0.04385633270321361,
      "grad_norm": 1.1955063343048096,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.0882,
      "step": 87
    },
    {
      "epoch": 0.04436042848141147,
      "grad_norm": 1.2329496145248413,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.8986,
      "step": 88
    },
    {
      "epoch": 0.04486452425960932,
      "grad_norm": 1.3696224689483643,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.0774,
      "step": 89
    },
    {
      "epoch": 0.045368620037807186,
      "grad_norm": 1.3210687637329102,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.8344,
      "step": 90
    },
    {
      "epoch": 0.04587271581600504,
      "grad_norm": 1.2450342178344727,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.9926,
      "step": 91
    },
    {
      "epoch": 0.0463768115942029,
      "grad_norm": 1.536271572113037,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.9797,
      "step": 92
    },
    {
      "epoch": 0.046880907372400756,
      "grad_norm": 1.8610961437225342,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.1009,
      "step": 93
    },
    {
      "epoch": 0.04738500315059861,
      "grad_norm": 1.8540403842926025,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.1389,
      "step": 94
    },
    {
      "epoch": 0.04788909892879647,
      "grad_norm": 2.1709673404693604,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.9783,
      "step": 95
    },
    {
      "epoch": 0.04839319470699433,
      "grad_norm": 2.641937494277954,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.1573,
      "step": 96
    },
    {
      "epoch": 0.04889729048519219,
      "grad_norm": 2.51130747795105,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.1294,
      "step": 97
    },
    {
      "epoch": 0.049401386263390044,
      "grad_norm": 2.792402505874634,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.3566,
      "step": 98
    },
    {
      "epoch": 0.0499054820415879,
      "grad_norm": 3.161710023880005,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.4144,
      "step": 99
    },
    {
      "epoch": 0.05040957781978576,
      "grad_norm": 6.212632656097412,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.7334,
      "step": 100
    },
    {
      "epoch": 0.05040957781978576,
      "eval_loss": 1.0116993188858032,
      "eval_runtime": 70.2364,
      "eval_samples_per_second": 47.568,
      "eval_steps_per_second": 11.903,
      "step": 100
    },
    {
      "epoch": 0.050913673597983614,
      "grad_norm": 0.7841265797615051,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.8478,
      "step": 101
    },
    {
      "epoch": 0.05141776937618148,
      "grad_norm": 0.7918402552604675,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.9741,
      "step": 102
    },
    {
      "epoch": 0.05192186515437933,
      "grad_norm": 0.7663191556930542,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.061,
      "step": 103
    },
    {
      "epoch": 0.05242596093257719,
      "grad_norm": 0.5820767879486084,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.9389,
      "step": 104
    },
    {
      "epoch": 0.052930056710775046,
      "grad_norm": 0.4415889084339142,
      "learning_rate": 5e-05,
      "loss": 0.9897,
      "step": 105
    },
    {
      "epoch": 0.0534341524889729,
      "grad_norm": 0.39681074023246765,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.9521,
      "step": 106
    },
    {
      "epoch": 0.053938248267170766,
      "grad_norm": 0.40437906980514526,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.9214,
      "step": 107
    },
    {
      "epoch": 0.05444234404536862,
      "grad_norm": 0.3815537095069885,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.94,
      "step": 108
    },
    {
      "epoch": 0.05494643982356648,
      "grad_norm": 0.38426071405410767,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.9144,
      "step": 109
    },
    {
      "epoch": 0.055450535601764335,
      "grad_norm": 0.38166847825050354,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.9569,
      "step": 110
    },
    {
      "epoch": 0.05595463137996219,
      "grad_norm": 0.3796461224555969,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.9856,
      "step": 111
    },
    {
      "epoch": 0.05645872715816005,
      "grad_norm": 0.3643120527267456,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.9217,
      "step": 112
    },
    {
      "epoch": 0.05696282293635791,
      "grad_norm": 0.384927362203598,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.911,
      "step": 113
    },
    {
      "epoch": 0.05746691871455577,
      "grad_norm": 0.38762205839157104,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.8977,
      "step": 114
    },
    {
      "epoch": 0.057971014492753624,
      "grad_norm": 0.3947840929031372,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.9479,
      "step": 115
    },
    {
      "epoch": 0.05847511027095148,
      "grad_norm": 0.40712770819664,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.9162,
      "step": 116
    },
    {
      "epoch": 0.05897920604914934,
      "grad_norm": 0.41037410497665405,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.9168,
      "step": 117
    },
    {
      "epoch": 0.05948330182734719,
      "grad_norm": 0.41304683685302734,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.8944,
      "step": 118
    },
    {
      "epoch": 0.059987397605545056,
      "grad_norm": 0.4369380474090576,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.9477,
      "step": 119
    },
    {
      "epoch": 0.06049149338374291,
      "grad_norm": 0.4551554322242737,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.9252,
      "step": 120
    },
    {
      "epoch": 0.06099558916194077,
      "grad_norm": 0.46176278591156006,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.9468,
      "step": 121
    },
    {
      "epoch": 0.061499684940138626,
      "grad_norm": 0.47067078948020935,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.9505,
      "step": 122
    },
    {
      "epoch": 0.06200378071833648,
      "grad_norm": 0.4589996635913849,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.918,
      "step": 123
    },
    {
      "epoch": 0.06250787649653435,
      "grad_norm": 0.47660380601882935,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.958,
      "step": 124
    },
    {
      "epoch": 0.0630119722747322,
      "grad_norm": 0.48685434460639954,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 1.0218,
      "step": 125
    },
    {
      "epoch": 0.06351606805293006,
      "grad_norm": 0.4912755787372589,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.9211,
      "step": 126
    },
    {
      "epoch": 0.06402016383112791,
      "grad_norm": 0.5366457104682922,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.978,
      "step": 127
    },
    {
      "epoch": 0.06452425960932577,
      "grad_norm": 0.5451323390007019,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.9386,
      "step": 128
    },
    {
      "epoch": 0.06502835538752363,
      "grad_norm": 0.5842207074165344,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 1.0105,
      "step": 129
    },
    {
      "epoch": 0.06553245116572148,
      "grad_norm": 0.555545449256897,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.9662,
      "step": 130
    },
    {
      "epoch": 0.06603654694391935,
      "grad_norm": 0.6450053453445435,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.0536,
      "step": 131
    },
    {
      "epoch": 0.0665406427221172,
      "grad_norm": 0.6146291494369507,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.8666,
      "step": 132
    },
    {
      "epoch": 0.06704473850031506,
      "grad_norm": 0.6321956515312195,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.9245,
      "step": 133
    },
    {
      "epoch": 0.06754883427851292,
      "grad_norm": 0.7116584181785583,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.8686,
      "step": 134
    },
    {
      "epoch": 0.06805293005671077,
      "grad_norm": 0.8101832866668701,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.8388,
      "step": 135
    },
    {
      "epoch": 0.06855702583490864,
      "grad_norm": 0.8933461904525757,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.9507,
      "step": 136
    },
    {
      "epoch": 0.06906112161310649,
      "grad_norm": 0.9112444519996643,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.8868,
      "step": 137
    },
    {
      "epoch": 0.06956521739130435,
      "grad_norm": 1.024316668510437,
      "learning_rate": 2.405152131093926e-05,
      "loss": 1.1932,
      "step": 138
    },
    {
      "epoch": 0.07006931316950221,
      "grad_norm": 1.1063545942306519,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 1.0144,
      "step": 139
    },
    {
      "epoch": 0.07057340894770006,
      "grad_norm": 1.094598412513733,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.9647,
      "step": 140
    },
    {
      "epoch": 0.07107750472589792,
      "grad_norm": 1.3245705366134644,
      "learning_rate": 2.196424713241637e-05,
      "loss": 1.092,
      "step": 141
    },
    {
      "epoch": 0.07158160050409577,
      "grad_norm": 1.3400907516479492,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.9654,
      "step": 142
    },
    {
      "epoch": 0.07208569628229364,
      "grad_norm": 1.3648507595062256,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.8774,
      "step": 143
    },
    {
      "epoch": 0.07258979206049149,
      "grad_norm": 1.505003571510315,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 1.0001,
      "step": 144
    },
    {
      "epoch": 0.07309388783868935,
      "grad_norm": 1.6857004165649414,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.9833,
      "step": 145
    },
    {
      "epoch": 0.07359798361688721,
      "grad_norm": 1.766623616218567,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.9873,
      "step": 146
    },
    {
      "epoch": 0.07410207939508506,
      "grad_norm": 2.1166927814483643,
      "learning_rate": 1.800157297483417e-05,
      "loss": 1.1829,
      "step": 147
    },
    {
      "epoch": 0.07460617517328293,
      "grad_norm": 3.463778495788574,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.3177,
      "step": 148
    },
    {
      "epoch": 0.07511027095148078,
      "grad_norm": 3.5200185775756836,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.236,
      "step": 149
    },
    {
      "epoch": 0.07561436672967864,
      "grad_norm": 4.4810872077941895,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.4402,
      "step": 150
    },
    {
      "epoch": 0.07561436672967864,
      "eval_loss": 0.9601866602897644,
      "eval_runtime": 70.1677,
      "eval_samples_per_second": 47.614,
      "eval_steps_per_second": 11.914,
      "step": 150
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4239728880582656e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}