{
  "best_metric": 0.1450488567352295,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.25510204081632654,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017006802721088435,
      "grad_norm": 0.5269389748573303,
      "learning_rate": 1e-05,
      "loss": 0.1901,
      "step": 1
    },
    {
      "epoch": 0.0017006802721088435,
      "eval_loss": 0.5936321020126343,
      "eval_runtime": 99.436,
      "eval_samples_per_second": 9.956,
      "eval_steps_per_second": 2.494,
      "step": 1
    },
    {
      "epoch": 0.003401360544217687,
      "grad_norm": 0.46303698420524597,
      "learning_rate": 2e-05,
      "loss": 0.1959,
      "step": 2
    },
    {
      "epoch": 0.00510204081632653,
      "grad_norm": 0.5892171263694763,
      "learning_rate": 3e-05,
      "loss": 0.2197,
      "step": 3
    },
    {
      "epoch": 0.006802721088435374,
      "grad_norm": 0.5525668263435364,
      "learning_rate": 4e-05,
      "loss": 0.2315,
      "step": 4
    },
    {
      "epoch": 0.008503401360544218,
      "grad_norm": 0.5089474320411682,
      "learning_rate": 5e-05,
      "loss": 0.2095,
      "step": 5
    },
    {
      "epoch": 0.01020408163265306,
      "grad_norm": 0.49851194024086,
      "learning_rate": 6e-05,
      "loss": 0.2095,
      "step": 6
    },
    {
      "epoch": 0.011904761904761904,
      "grad_norm": 0.47188305854797363,
      "learning_rate": 7e-05,
      "loss": 0.1942,
      "step": 7
    },
    {
      "epoch": 0.013605442176870748,
      "grad_norm": 0.48552876710891724,
      "learning_rate": 8e-05,
      "loss": 0.2285,
      "step": 8
    },
    {
      "epoch": 0.015306122448979591,
      "grad_norm": 0.3960217833518982,
      "learning_rate": 9e-05,
      "loss": 0.1824,
      "step": 9
    },
    {
      "epoch": 0.017006802721088437,
      "grad_norm": 0.3507472276687622,
      "learning_rate": 0.0001,
      "loss": 0.1569,
      "step": 10
    },
    {
      "epoch": 0.01870748299319728,
      "grad_norm": 0.33635377883911133,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.184,
      "step": 11
    },
    {
      "epoch": 0.02040816326530612,
      "grad_norm": 0.4036436676979065,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.1587,
      "step": 12
    },
    {
      "epoch": 0.022108843537414966,
      "grad_norm": 0.5375078320503235,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.2424,
      "step": 13
    },
    {
      "epoch": 0.023809523809523808,
      "grad_norm": 0.4145143926143646,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.1819,
      "step": 14
    },
    {
      "epoch": 0.025510204081632654,
      "grad_norm": 0.4353350102901459,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.154,
      "step": 15
    },
    {
      "epoch": 0.027210884353741496,
      "grad_norm": 0.32249438762664795,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.1298,
      "step": 16
    },
    {
      "epoch": 0.02891156462585034,
      "grad_norm": 0.39720624685287476,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.1577,
      "step": 17
    },
    {
      "epoch": 0.030612244897959183,
      "grad_norm": 0.37612348794937134,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.1394,
      "step": 18
    },
    {
      "epoch": 0.03231292517006803,
      "grad_norm": 0.32927829027175903,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.1571,
      "step": 19
    },
    {
      "epoch": 0.034013605442176874,
      "grad_norm": 0.34154942631721497,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.1513,
      "step": 20
    },
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 0.2961677610874176,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.1267,
      "step": 21
    },
    {
      "epoch": 0.03741496598639456,
      "grad_norm": 0.30949026346206665,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.1611,
      "step": 22
    },
    {
      "epoch": 0.0391156462585034,
      "grad_norm": 0.34329307079315186,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.1478,
      "step": 23
    },
    {
      "epoch": 0.04081632653061224,
      "grad_norm": 0.33806389570236206,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.1604,
      "step": 24
    },
    {
      "epoch": 0.04251700680272109,
      "grad_norm": 0.3135806620121002,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.1218,
      "step": 25
    },
    {
      "epoch": 0.04421768707482993,
      "grad_norm": 0.5712440609931946,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.1603,
      "step": 26
    },
    {
      "epoch": 0.04591836734693878,
      "grad_norm": 0.545917272567749,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.2418,
      "step": 27
    },
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 0.3555242419242859,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.1463,
      "step": 28
    },
    {
      "epoch": 0.04931972789115646,
      "grad_norm": 0.39341312646865845,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.1591,
      "step": 29
    },
    {
      "epoch": 0.05102040816326531,
      "grad_norm": 0.36689674854278564,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.1539,
      "step": 30
    },
    {
      "epoch": 0.05272108843537415,
      "grad_norm": 0.46685174107551575,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.1796,
      "step": 31
    },
    {
      "epoch": 0.05442176870748299,
      "grad_norm": 0.48095518350601196,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.2008,
      "step": 32
    },
    {
      "epoch": 0.05612244897959184,
      "grad_norm": 0.4282090365886688,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.1706,
      "step": 33
    },
    {
      "epoch": 0.05782312925170068,
      "grad_norm": 0.7042590379714966,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.315,
      "step": 34
    },
    {
      "epoch": 0.05952380952380952,
      "grad_norm": 0.43822816014289856,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.1428,
      "step": 35
    },
    {
      "epoch": 0.061224489795918366,
      "grad_norm": 0.40582820773124695,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.1482,
      "step": 36
    },
    {
      "epoch": 0.06292517006802721,
      "grad_norm": 0.46641525626182556,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.2125,
      "step": 37
    },
    {
      "epoch": 0.06462585034013606,
      "grad_norm": 0.5421123504638672,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.1554,
      "step": 38
    },
    {
      "epoch": 0.0663265306122449,
      "grad_norm": 0.5820235013961792,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.1635,
      "step": 39
    },
    {
      "epoch": 0.06802721088435375,
      "grad_norm": 0.5159996151924133,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.2234,
      "step": 40
    },
    {
      "epoch": 0.06972789115646258,
      "grad_norm": 0.5390616059303284,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.2149,
      "step": 41
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 0.5398741364479065,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.2231,
      "step": 42
    },
    {
      "epoch": 0.07312925170068027,
      "grad_norm": 0.5961061716079712,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.1861,
      "step": 43
    },
    {
      "epoch": 0.07482993197278912,
      "grad_norm": 0.5682746767997742,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.2059,
      "step": 44
    },
    {
      "epoch": 0.07653061224489796,
      "grad_norm": 0.6431316137313843,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.2388,
      "step": 45
    },
    {
      "epoch": 0.0782312925170068,
      "grad_norm": 0.7409397959709167,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.26,
      "step": 46
    },
    {
      "epoch": 0.07993197278911565,
      "grad_norm": 1.0703874826431274,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.2309,
      "step": 47
    },
    {
      "epoch": 0.08163265306122448,
      "grad_norm": 0.7176180481910706,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.2351,
      "step": 48
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 1.2472457885742188,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.2577,
      "step": 49
    },
    {
      "epoch": 0.08503401360544217,
      "grad_norm": 1.9959722757339478,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.3351,
      "step": 50
    },
    {
      "epoch": 0.08503401360544217,
      "eval_loss": 0.18127788603305817,
      "eval_runtime": 100.6415,
      "eval_samples_per_second": 9.837,
      "eval_steps_per_second": 2.464,
      "step": 50
    },
    {
      "epoch": 0.08673469387755102,
      "grad_norm": 0.32864144444465637,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.1396,
      "step": 51
    },
    {
      "epoch": 0.08843537414965986,
      "grad_norm": 0.3204747438430786,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.0863,
      "step": 52
    },
    {
      "epoch": 0.09013605442176871,
      "grad_norm": 0.2585567831993103,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.1298,
      "step": 53
    },
    {
      "epoch": 0.09183673469387756,
      "grad_norm": 0.1529138833284378,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.067,
      "step": 54
    },
    {
      "epoch": 0.0935374149659864,
      "grad_norm": 0.2032083421945572,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.123,
      "step": 55
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 0.25678551197052,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.1174,
      "step": 56
    },
    {
      "epoch": 0.09693877551020408,
      "grad_norm": 0.2589610815048218,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.1145,
      "step": 57
    },
    {
      "epoch": 0.09863945578231292,
      "grad_norm": 0.3110625743865967,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.14,
      "step": 58
    },
    {
      "epoch": 0.10034013605442177,
      "grad_norm": 0.20775605738162994,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.1232,
      "step": 59
    },
    {
      "epoch": 0.10204081632653061,
      "grad_norm": 0.17721042037010193,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.1048,
      "step": 60
    },
    {
      "epoch": 0.10374149659863946,
      "grad_norm": 0.20299284160137177,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.1269,
      "step": 61
    },
    {
      "epoch": 0.1054421768707483,
      "grad_norm": 0.2592518627643585,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.1556,
      "step": 62
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 0.28578001260757446,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.1339,
      "step": 63
    },
    {
      "epoch": 0.10884353741496598,
      "grad_norm": 0.21084251999855042,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.1197,
      "step": 64
    },
    {
      "epoch": 0.11054421768707483,
      "grad_norm": 0.20630519092082977,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.1317,
      "step": 65
    },
    {
      "epoch": 0.11224489795918367,
      "grad_norm": 0.22667892277240753,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.1253,
      "step": 66
    },
    {
      "epoch": 0.11394557823129252,
      "grad_norm": 0.20838917791843414,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.1009,
      "step": 67
    },
    {
      "epoch": 0.11564625850340136,
      "grad_norm": 0.2214667648077011,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.1302,
      "step": 68
    },
    {
      "epoch": 0.11734693877551021,
      "grad_norm": 0.24575111269950867,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.1205,
      "step": 69
    },
    {
      "epoch": 0.11904761904761904,
      "grad_norm": 0.26279327273368835,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.131,
      "step": 70
    },
    {
      "epoch": 0.12074829931972789,
      "grad_norm": 0.25295835733413696,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.1435,
      "step": 71
    },
    {
      "epoch": 0.12244897959183673,
      "grad_norm": 0.23764437437057495,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.1187,
      "step": 72
    },
    {
      "epoch": 0.12414965986394558,
      "grad_norm": 0.20362688601016998,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.1213,
      "step": 73
    },
    {
      "epoch": 0.12585034013605442,
      "grad_norm": 0.2588404715061188,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.1361,
      "step": 74
    },
    {
      "epoch": 0.12755102040816327,
      "grad_norm": 0.48782673478126526,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.1394,
      "step": 75
    },
    {
      "epoch": 0.1292517006802721,
      "grad_norm": 0.3100239038467407,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.1434,
      "step": 76
    },
    {
      "epoch": 0.13095238095238096,
      "grad_norm": 0.28053736686706543,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.1234,
      "step": 77
    },
    {
      "epoch": 0.1326530612244898,
      "grad_norm": 0.26575592160224915,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.1418,
      "step": 78
    },
    {
      "epoch": 0.13435374149659865,
      "grad_norm": 0.26024481654167175,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.136,
      "step": 79
    },
    {
      "epoch": 0.1360544217687075,
      "grad_norm": 0.44965115189552307,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.2536,
      "step": 80
    },
    {
      "epoch": 0.1377551020408163,
      "grad_norm": 0.3972369134426117,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.2138,
      "step": 81
    },
    {
      "epoch": 0.13945578231292516,
      "grad_norm": 0.2681017518043518,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.1231,
      "step": 82
    },
    {
      "epoch": 0.141156462585034,
      "grad_norm": 0.42896729707717896,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.2301,
      "step": 83
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.28568339347839355,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.1233,
      "step": 84
    },
    {
      "epoch": 0.1445578231292517,
      "grad_norm": 0.38649600744247437,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.193,
      "step": 85
    },
    {
      "epoch": 0.14625850340136054,
      "grad_norm": 0.33405882120132446,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.1168,
      "step": 86
    },
    {
      "epoch": 0.14795918367346939,
      "grad_norm": 0.5408915281295776,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.1856,
      "step": 87
    },
    {
      "epoch": 0.14965986394557823,
      "grad_norm": 0.41401568055152893,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.1562,
      "step": 88
    },
    {
      "epoch": 0.15136054421768708,
      "grad_norm": 0.36673107743263245,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.1655,
      "step": 89
    },
    {
      "epoch": 0.15306122448979592,
      "grad_norm": 0.4040523171424866,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.1879,
      "step": 90
    },
    {
      "epoch": 0.15476190476190477,
      "grad_norm": 0.4495351314544678,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.2504,
      "step": 91
    },
    {
      "epoch": 0.1564625850340136,
      "grad_norm": 0.3567620515823364,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.1414,
      "step": 92
    },
    {
      "epoch": 0.15816326530612246,
      "grad_norm": 0.3996597230434418,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.1539,
      "step": 93
    },
    {
      "epoch": 0.1598639455782313,
      "grad_norm": 0.6240476965904236,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.3179,
      "step": 94
    },
    {
      "epoch": 0.16156462585034015,
      "grad_norm": 0.5150894522666931,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.2054,
      "step": 95
    },
    {
      "epoch": 0.16326530612244897,
      "grad_norm": 0.46117132902145386,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.1798,
      "step": 96
    },
    {
      "epoch": 0.1649659863945578,
      "grad_norm": 0.6154991984367371,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.196,
      "step": 97
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.5747442245483398,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.245,
      "step": 98
    },
    {
      "epoch": 0.1683673469387755,
      "grad_norm": 0.7409622669219971,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.2667,
      "step": 99
    },
    {
      "epoch": 0.17006802721088435,
      "grad_norm": 1.218652367591858,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.246,
      "step": 100
    },
    {
      "epoch": 0.17006802721088435,
      "eval_loss": 0.15341179072856903,
      "eval_runtime": 100.6674,
      "eval_samples_per_second": 9.834,
      "eval_steps_per_second": 2.464,
      "step": 100
    },
    {
      "epoch": 0.1717687074829932,
      "grad_norm": 0.13426078855991364,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.1057,
      "step": 101
    },
    {
      "epoch": 0.17346938775510204,
      "grad_norm": 0.1581740826368332,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.119,
      "step": 102
    },
    {
      "epoch": 0.17517006802721088,
      "grad_norm": 0.16823437809944153,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.1664,
      "step": 103
    },
    {
      "epoch": 0.17687074829931973,
      "grad_norm": 0.14816226065158844,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.0938,
      "step": 104
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 0.1594924032688141,
      "learning_rate": 5e-05,
      "loss": 0.1025,
      "step": 105
    },
    {
      "epoch": 0.18027210884353742,
      "grad_norm": 0.15495480597019196,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.1087,
      "step": 106
    },
    {
      "epoch": 0.18197278911564627,
      "grad_norm": 0.12521763145923615,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.0894,
      "step": 107
    },
    {
      "epoch": 0.1836734693877551,
      "grad_norm": 0.12601736187934875,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.0808,
      "step": 108
    },
    {
      "epoch": 0.18537414965986396,
      "grad_norm": 0.18192654848098755,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.1155,
      "step": 109
    },
    {
      "epoch": 0.1870748299319728,
      "grad_norm": 0.14074137806892395,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.0929,
      "step": 110
    },
    {
      "epoch": 0.18877551020408162,
      "grad_norm": 0.19746126234531403,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.1248,
      "step": 111
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.1834673285484314,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.1183,
      "step": 112
    },
    {
      "epoch": 0.1921768707482993,
      "grad_norm": 0.20125111937522888,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.1176,
      "step": 113
    },
    {
      "epoch": 0.19387755102040816,
      "grad_norm": 0.2673965096473694,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.1593,
      "step": 114
    },
    {
      "epoch": 0.195578231292517,
      "grad_norm": 0.18478697538375854,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.114,
      "step": 115
    },
    {
      "epoch": 0.19727891156462585,
      "grad_norm": 0.2274971902370453,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.1161,
      "step": 116
    },
    {
      "epoch": 0.1989795918367347,
      "grad_norm": 0.20548267662525177,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.1303,
      "step": 117
    },
    {
      "epoch": 0.20068027210884354,
      "grad_norm": 0.2045164704322815,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.1169,
      "step": 118
    },
    {
      "epoch": 0.20238095238095238,
      "grad_norm": 0.21133384108543396,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.107,
      "step": 119
    },
    {
      "epoch": 0.20408163265306123,
      "grad_norm": 0.23106807470321655,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.1418,
      "step": 120
    },
    {
      "epoch": 0.20578231292517007,
      "grad_norm": 0.27285704016685486,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.1784,
      "step": 121
    },
    {
      "epoch": 0.20748299319727892,
      "grad_norm": 0.2039409875869751,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.1132,
      "step": 122
    },
    {
      "epoch": 0.20918367346938777,
      "grad_norm": 0.26123031973838806,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.1673,
      "step": 123
    },
    {
      "epoch": 0.2108843537414966,
      "grad_norm": 0.2377399057149887,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.1207,
      "step": 124
    },
    {
      "epoch": 0.21258503401360543,
      "grad_norm": 0.3176490366458893,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.2086,
      "step": 125
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 0.3887050449848175,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.1304,
      "step": 126
    },
    {
      "epoch": 0.21598639455782312,
      "grad_norm": 0.33405062556266785,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.2149,
      "step": 127
    },
    {
      "epoch": 0.21768707482993196,
      "grad_norm": 0.2403564751148224,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.1357,
      "step": 128
    },
    {
      "epoch": 0.2193877551020408,
      "grad_norm": 0.29959097504615784,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.1783,
      "step": 129
    },
    {
      "epoch": 0.22108843537414966,
      "grad_norm": 0.28348225355148315,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.157,
      "step": 130
    },
    {
      "epoch": 0.2227891156462585,
      "grad_norm": 0.4001818895339966,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.2555,
      "step": 131
    },
    {
      "epoch": 0.22448979591836735,
      "grad_norm": 0.33200711011886597,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.1585,
      "step": 132
    },
    {
      "epoch": 0.2261904761904762,
      "grad_norm": 0.5564277768135071,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.1547,
      "step": 133
    },
    {
      "epoch": 0.22789115646258504,
      "grad_norm": 0.2881430685520172,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.126,
      "step": 134
    },
    {
      "epoch": 0.22959183673469388,
      "grad_norm": 0.3916719853878021,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.1664,
      "step": 135
    },
    {
      "epoch": 0.23129251700680273,
      "grad_norm": 0.35243332386016846,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.1547,
      "step": 136
    },
    {
      "epoch": 0.23299319727891157,
      "grad_norm": 0.28927794098854065,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.1258,
      "step": 137
    },
    {
      "epoch": 0.23469387755102042,
      "grad_norm": 0.3159042000770569,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.1418,
      "step": 138
    },
    {
      "epoch": 0.23639455782312926,
      "grad_norm": 0.35158154368400574,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.1515,
      "step": 139
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 0.4585651755332947,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.2258,
      "step": 140
    },
    {
      "epoch": 0.23979591836734693,
      "grad_norm": 0.39558088779449463,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.1377,
      "step": 141
    },
    {
      "epoch": 0.24149659863945577,
      "grad_norm": 0.35692715644836426,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.1466,
      "step": 142
    },
    {
      "epoch": 0.24319727891156462,
      "grad_norm": 0.47575652599334717,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.2366,
      "step": 143
    },
    {
      "epoch": 0.24489795918367346,
      "grad_norm": 0.5705416202545166,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.3062,
      "step": 144
    },
    {
      "epoch": 0.2465986394557823,
      "grad_norm": 0.42908549308776855,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.1863,
      "step": 145
    },
    {
      "epoch": 0.24829931972789115,
      "grad_norm": 0.5684940814971924,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.1986,
      "step": 146
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.5118395090103149,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.226,
      "step": 147
    },
    {
      "epoch": 0.25170068027210885,
      "grad_norm": 0.5201008915901184,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.164,
      "step": 148
    },
    {
      "epoch": 0.2534013605442177,
      "grad_norm": 1.024444341659546,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.1797,
      "step": 149
    },
    {
      "epoch": 0.25510204081632654,
      "grad_norm": 1.1646174192428589,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.2457,
      "step": 150
    },
    {
      "epoch": 0.25510204081632654,
      "eval_loss": 0.1450488567352295,
      "eval_runtime": 100.2405,
      "eval_samples_per_second": 9.876,
      "eval_steps_per_second": 2.474,
      "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": 2.7635550454284288e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}