{
  "best_metric": 0.852659285068512,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.042492917847025496,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00028328611898016995,
      "grad_norm": 2.422705888748169,
      "learning_rate": 5e-06,
      "loss": 1.0328,
      "step": 1
    },
    {
      "epoch": 0.00028328611898016995,
      "eval_loss": 1.364790678024292,
      "eval_runtime": 484.4145,
      "eval_samples_per_second": 12.275,
      "eval_steps_per_second": 6.137,
      "step": 1
    },
    {
      "epoch": 0.0005665722379603399,
      "grad_norm": 0.7268726825714111,
      "learning_rate": 1e-05,
      "loss": 1.044,
      "step": 2
    },
    {
      "epoch": 0.0008498583569405099,
      "grad_norm": 0.5093448162078857,
      "learning_rate": 1.5e-05,
      "loss": 1.0228,
      "step": 3
    },
    {
      "epoch": 0.0011331444759206798,
      "grad_norm": 1.0861634016036987,
      "learning_rate": 2e-05,
      "loss": 1.0906,
      "step": 4
    },
    {
      "epoch": 0.00141643059490085,
      "grad_norm": 0.7751361131668091,
      "learning_rate": 2.5e-05,
      "loss": 1.1224,
      "step": 5
    },
    {
      "epoch": 0.0016997167138810198,
      "grad_norm": 0.5604671239852905,
      "learning_rate": 3e-05,
      "loss": 1.0556,
      "step": 6
    },
    {
      "epoch": 0.00198300283286119,
      "grad_norm": 0.7147814631462097,
      "learning_rate": 3.5e-05,
      "loss": 1.0777,
      "step": 7
    },
    {
      "epoch": 0.0022662889518413596,
      "grad_norm": 0.4986502230167389,
      "learning_rate": 4e-05,
      "loss": 1.021,
      "step": 8
    },
    {
      "epoch": 0.0025495750708215297,
      "grad_norm": 0.41371020674705505,
      "learning_rate": 4.5e-05,
      "loss": 1.0412,
      "step": 9
    },
    {
      "epoch": 0.0028328611898017,
      "grad_norm": 0.37283027172088623,
      "learning_rate": 5e-05,
      "loss": 0.9762,
      "step": 10
    },
    {
      "epoch": 0.0031161473087818695,
      "grad_norm": 0.4067866802215576,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.9969,
      "step": 11
    },
    {
      "epoch": 0.0033994334277620396,
      "grad_norm": 0.385970801115036,
      "learning_rate": 6e-05,
      "loss": 1.0198,
      "step": 12
    },
    {
      "epoch": 0.0036827195467422098,
      "grad_norm": 0.4271886348724365,
      "learning_rate": 6.500000000000001e-05,
      "loss": 0.9821,
      "step": 13
    },
    {
      "epoch": 0.00396600566572238,
      "grad_norm": 0.42523813247680664,
      "learning_rate": 7e-05,
      "loss": 0.9635,
      "step": 14
    },
    {
      "epoch": 0.00424929178470255,
      "grad_norm": 0.4127529263496399,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.9045,
      "step": 15
    },
    {
      "epoch": 0.004532577903682719,
      "grad_norm": 0.4004879891872406,
      "learning_rate": 8e-05,
      "loss": 0.8857,
      "step": 16
    },
    {
      "epoch": 0.004815864022662889,
      "grad_norm": 0.41450199484825134,
      "learning_rate": 8.5e-05,
      "loss": 0.9951,
      "step": 17
    },
    {
      "epoch": 0.0050991501416430595,
      "grad_norm": 0.3953557312488556,
      "learning_rate": 9e-05,
      "loss": 0.9797,
      "step": 18
    },
    {
      "epoch": 0.00538243626062323,
      "grad_norm": 0.3351423144340515,
      "learning_rate": 9.5e-05,
      "loss": 0.88,
      "step": 19
    },
    {
      "epoch": 0.0056657223796034,
      "grad_norm": 0.3079324960708618,
      "learning_rate": 0.0001,
      "loss": 0.8787,
      "step": 20
    },
    {
      "epoch": 0.00594900849858357,
      "grad_norm": 0.3389316201210022,
      "learning_rate": 9.999238475781957e-05,
      "loss": 0.8825,
      "step": 21
    },
    {
      "epoch": 0.006232294617563739,
      "grad_norm": 0.3355834484100342,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.862,
      "step": 22
    },
    {
      "epoch": 0.006515580736543909,
      "grad_norm": 0.36853089928627014,
      "learning_rate": 9.99314767377287e-05,
      "loss": 0.8856,
      "step": 23
    },
    {
      "epoch": 0.006798866855524079,
      "grad_norm": 0.3685651123523712,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.9131,
      "step": 24
    },
    {
      "epoch": 0.007082152974504249,
      "grad_norm": 0.3667776882648468,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.8799,
      "step": 25
    },
    {
      "epoch": 0.0073654390934844195,
      "grad_norm": 0.32032638788223267,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.8648,
      "step": 26
    },
    {
      "epoch": 0.00764872521246459,
      "grad_norm": 0.37414008378982544,
      "learning_rate": 9.962730758206611e-05,
      "loss": 0.9018,
      "step": 27
    },
    {
      "epoch": 0.00793201133144476,
      "grad_norm": 0.3966204524040222,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.919,
      "step": 28
    },
    {
      "epoch": 0.00821529745042493,
      "grad_norm": 0.30121907591819763,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.865,
      "step": 29
    },
    {
      "epoch": 0.0084985835694051,
      "grad_norm": 0.3925679624080658,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.9049,
      "step": 30
    },
    {
      "epoch": 0.008781869688385268,
      "grad_norm": 0.46123215556144714,
      "learning_rate": 9.908135917238321e-05,
      "loss": 0.9485,
      "step": 31
    },
    {
      "epoch": 0.009065155807365438,
      "grad_norm": 0.4016572833061218,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.9092,
      "step": 32
    },
    {
      "epoch": 0.009348441926345609,
      "grad_norm": 0.4379897713661194,
      "learning_rate": 9.871850323926177e-05,
      "loss": 0.9522,
      "step": 33
    },
    {
      "epoch": 0.009631728045325779,
      "grad_norm": 0.5109198093414307,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.8604,
      "step": 34
    },
    {
      "epoch": 0.009915014164305949,
      "grad_norm": 0.6811182498931885,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.0205,
      "step": 35
    },
    {
      "epoch": 0.010198300283286119,
      "grad_norm": 0.5827723741531372,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.9693,
      "step": 36
    },
    {
      "epoch": 0.010481586402266289,
      "grad_norm": 0.6237921714782715,
      "learning_rate": 9.781523779815179e-05,
      "loss": 1.0805,
      "step": 37
    },
    {
      "epoch": 0.01076487252124646,
      "grad_norm": 0.49926280975341797,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.9162,
      "step": 38
    },
    {
      "epoch": 0.01104815864022663,
      "grad_norm": 0.5666930079460144,
      "learning_rate": 9.727592877996585e-05,
      "loss": 1.0134,
      "step": 39
    },
    {
      "epoch": 0.0113314447592068,
      "grad_norm": 0.7310525178909302,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.9952,
      "step": 40
    },
    {
      "epoch": 0.01161473087818697,
      "grad_norm": 0.690876841545105,
      "learning_rate": 9.667902132486009e-05,
      "loss": 1.0255,
      "step": 41
    },
    {
      "epoch": 0.01189801699716714,
      "grad_norm": 0.78537517786026,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.142,
      "step": 42
    },
    {
      "epoch": 0.012181303116147308,
      "grad_norm": 0.642960786819458,
      "learning_rate": 9.602524267262203e-05,
      "loss": 1.0393,
      "step": 43
    },
    {
      "epoch": 0.012464589235127478,
      "grad_norm": 0.7761110663414001,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.0948,
      "step": 44
    },
    {
      "epoch": 0.012747875354107648,
      "grad_norm": 0.806307315826416,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.9368,
      "step": 45
    },
    {
      "epoch": 0.013031161473087818,
      "grad_norm": 0.9588708281517029,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.2338,
      "step": 46
    },
    {
      "epoch": 0.013314447592067988,
      "grad_norm": 1.0133678913116455,
      "learning_rate": 9.45503262094184e-05,
      "loss": 1.0226,
      "step": 47
    },
    {
      "epoch": 0.013597733711048159,
      "grad_norm": 1.4568854570388794,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.1832,
      "step": 48
    },
    {
      "epoch": 0.013881019830028329,
      "grad_norm": 1.5190199613571167,
      "learning_rate": 9.373098535696979e-05,
      "loss": 1.0672,
      "step": 49
    },
    {
      "epoch": 0.014164305949008499,
      "grad_norm": 2.2922451496124268,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.0612,
      "step": 50
    },
    {
      "epoch": 0.014164305949008499,
      "eval_loss": 0.9715701341629028,
      "eval_runtime": 487.2655,
      "eval_samples_per_second": 12.203,
      "eval_steps_per_second": 6.101,
      "step": 50
    },
    {
      "epoch": 0.014447592067988669,
      "grad_norm": 0.3135802149772644,
      "learning_rate": 9.285836503510562e-05,
      "loss": 0.766,
      "step": 51
    },
    {
      "epoch": 0.014730878186968839,
      "grad_norm": 0.3779487609863281,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.8885,
      "step": 52
    },
    {
      "epoch": 0.01501416430594901,
      "grad_norm": 0.36846062541007996,
      "learning_rate": 9.193352839727121e-05,
      "loss": 0.8047,
      "step": 53
    },
    {
      "epoch": 0.01529745042492918,
      "grad_norm": 0.31726038455963135,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.8349,
      "step": 54
    },
    {
      "epoch": 0.015580736543909348,
      "grad_norm": 0.28584522008895874,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.8631,
      "step": 55
    },
    {
      "epoch": 0.01586402266288952,
      "grad_norm": 0.2794337570667267,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8686,
      "step": 56
    },
    {
      "epoch": 0.01614730878186969,
      "grad_norm": 0.2729143500328064,
      "learning_rate": 8.993177550236464e-05,
      "loss": 0.8548,
      "step": 57
    },
    {
      "epoch": 0.01643059490084986,
      "grad_norm": 0.2711362838745117,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.8192,
      "step": 58
    },
    {
      "epoch": 0.01671388101983003,
      "grad_norm": 0.2740928828716278,
      "learning_rate": 8.885729807284856e-05,
      "loss": 0.8194,
      "step": 59
    },
    {
      "epoch": 0.0169971671388102,
      "grad_norm": 0.2796076536178589,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.8068,
      "step": 60
    },
    {
      "epoch": 0.017280453257790367,
      "grad_norm": 0.26431265473365784,
      "learning_rate": 8.773547901113862e-05,
      "loss": 0.7775,
      "step": 61
    },
    {
      "epoch": 0.017563739376770537,
      "grad_norm": 0.30060914158821106,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.8566,
      "step": 62
    },
    {
      "epoch": 0.017847025495750707,
      "grad_norm": 0.2443016916513443,
      "learning_rate": 8.656768508095853e-05,
      "loss": 0.7605,
      "step": 63
    },
    {
      "epoch": 0.018130311614730877,
      "grad_norm": 0.25989943742752075,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.8236,
      "step": 64
    },
    {
      "epoch": 0.018413597733711047,
      "grad_norm": 0.23830537497997284,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.8392,
      "step": 65
    },
    {
      "epoch": 0.018696883852691217,
      "grad_norm": 0.24592608213424683,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.7824,
      "step": 66
    },
    {
      "epoch": 0.018980169971671387,
      "grad_norm": 0.26153719425201416,
      "learning_rate": 8.409991800312493e-05,
      "loss": 0.818,
      "step": 67
    },
    {
      "epoch": 0.019263456090651557,
      "grad_norm": 0.24824227392673492,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.8314,
      "step": 68
    },
    {
      "epoch": 0.019546742209631728,
      "grad_norm": 0.25583964586257935,
      "learning_rate": 8.280295144952536e-05,
      "loss": 0.8195,
      "step": 69
    },
    {
      "epoch": 0.019830028328611898,
      "grad_norm": 0.25367268919944763,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.7953,
      "step": 70
    },
    {
      "epoch": 0.020113314447592068,
      "grad_norm": 0.243778795003891,
      "learning_rate": 8.146601955249188e-05,
      "loss": 0.8102,
      "step": 71
    },
    {
      "epoch": 0.020396600566572238,
      "grad_norm": 0.2857438623905182,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.7829,
      "step": 72
    },
    {
      "epoch": 0.020679886685552408,
      "grad_norm": 0.2727109491825104,
      "learning_rate": 8.009075115760243e-05,
      "loss": 0.7808,
      "step": 73
    },
    {
      "epoch": 0.020963172804532578,
      "grad_norm": 0.27792826294898987,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8499,
      "step": 74
    },
    {
      "epoch": 0.021246458923512748,
      "grad_norm": 0.3149773180484772,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.8924,
      "step": 75
    },
    {
      "epoch": 0.02152974504249292,
      "grad_norm": 0.31959497928619385,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.7988,
      "step": 76
    },
    {
      "epoch": 0.02181303116147309,
      "grad_norm": 0.31561532616615295,
      "learning_rate": 7.723195175075136e-05,
      "loss": 0.8649,
      "step": 77
    },
    {
      "epoch": 0.02209631728045326,
      "grad_norm": 0.3440646827220917,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.8113,
      "step": 78
    },
    {
      "epoch": 0.02237960339943343,
      "grad_norm": 0.31110891699790955,
      "learning_rate": 7.575190374550272e-05,
      "loss": 0.8855,
      "step": 79
    },
    {
      "epoch": 0.0226628895184136,
      "grad_norm": 0.340699166059494,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.8403,
      "step": 80
    },
    {
      "epoch": 0.02294617563739377,
      "grad_norm": 0.3189809322357178,
      "learning_rate": 7.424048101231686e-05,
      "loss": 0.8159,
      "step": 81
    },
    {
      "epoch": 0.02322946175637394,
      "grad_norm": 0.42338067293167114,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.9046,
      "step": 82
    },
    {
      "epoch": 0.02351274787535411,
      "grad_norm": 0.40287211537361145,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.9228,
      "step": 83
    },
    {
      "epoch": 0.02379603399433428,
      "grad_norm": 0.4458402097225189,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.9427,
      "step": 84
    },
    {
      "epoch": 0.024079320113314446,
      "grad_norm": 0.4975302219390869,
      "learning_rate": 7.113091308703498e-05,
      "loss": 0.899,
      "step": 85
    },
    {
      "epoch": 0.024362606232294616,
      "grad_norm": 0.5405599474906921,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.0635,
      "step": 86
    },
    {
      "epoch": 0.024645892351274786,
      "grad_norm": 0.4603264331817627,
      "learning_rate": 6.953655642446368e-05,
      "loss": 0.8846,
      "step": 87
    },
    {
      "epoch": 0.024929178470254956,
      "grad_norm": 0.6046383380889893,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.9368,
      "step": 88
    },
    {
      "epoch": 0.025212464589235126,
      "grad_norm": 0.571029782295227,
      "learning_rate": 6.7918397477265e-05,
      "loss": 0.89,
      "step": 89
    },
    {
      "epoch": 0.025495750708215296,
      "grad_norm": 0.5111197233200073,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.9897,
      "step": 90
    },
    {
      "epoch": 0.025779036827195467,
      "grad_norm": 0.5967260599136353,
      "learning_rate": 6.627840772285784e-05,
      "loss": 0.9284,
      "step": 91
    },
    {
      "epoch": 0.026062322946175637,
      "grad_norm": 0.6245043873786926,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.9981,
      "step": 92
    },
    {
      "epoch": 0.026345609065155807,
      "grad_norm": 0.684574544429779,
      "learning_rate": 6.461858523613684e-05,
      "loss": 0.936,
      "step": 93
    },
    {
      "epoch": 0.026628895184135977,
      "grad_norm": 0.7181544303894043,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.0066,
      "step": 94
    },
    {
      "epoch": 0.026912181303116147,
      "grad_norm": 0.7557126879692078,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.8433,
      "step": 95
    },
    {
      "epoch": 0.027195467422096317,
      "grad_norm": 0.8560205101966858,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.9708,
      "step": 96
    },
    {
      "epoch": 0.027478753541076487,
      "grad_norm": 0.9604125618934631,
      "learning_rate": 6.124755271719325e-05,
      "loss": 1.006,
      "step": 97
    },
    {
      "epoch": 0.027762039660056657,
      "grad_norm": 0.9789381623268127,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.9541,
      "step": 98
    },
    {
      "epoch": 0.028045325779036828,
      "grad_norm": 1.579649806022644,
      "learning_rate": 5.9540449768827246e-05,
      "loss": 1.0308,
      "step": 99
    },
    {
      "epoch": 0.028328611898016998,
      "grad_norm": 3.0697805881500244,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.9688,
      "step": 100
    },
    {
      "epoch": 0.028328611898016998,
      "eval_loss": 0.8945009708404541,
      "eval_runtime": 487.7408,
      "eval_samples_per_second": 12.191,
      "eval_steps_per_second": 6.095,
      "step": 100
    },
    {
      "epoch": 0.028611898016997168,
      "grad_norm": 0.2576821446418762,
      "learning_rate": 5.782172325201155e-05,
      "loss": 0.7176,
      "step": 101
    },
    {
      "epoch": 0.028895184135977338,
      "grad_norm": 0.2731870114803314,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.7854,
      "step": 102
    },
    {
      "epoch": 0.029178470254957508,
      "grad_norm": 0.27251136302948,
      "learning_rate": 5.6093467170257374e-05,
      "loss": 0.7804,
      "step": 103
    },
    {
      "epoch": 0.029461756373937678,
      "grad_norm": 0.265346497297287,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.7832,
      "step": 104
    },
    {
      "epoch": 0.029745042492917848,
      "grad_norm": 0.25714778900146484,
      "learning_rate": 5.435778713738292e-05,
      "loss": 0.7435,
      "step": 105
    },
    {
      "epoch": 0.03002832861189802,
      "grad_norm": 0.22653083503246307,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.7781,
      "step": 106
    },
    {
      "epoch": 0.03031161473087819,
      "grad_norm": 0.23241588473320007,
      "learning_rate": 5.26167978121472e-05,
      "loss": 0.8233,
      "step": 107
    },
    {
      "epoch": 0.03059490084985836,
      "grad_norm": 0.23362793028354645,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.754,
      "step": 108
    },
    {
      "epoch": 0.030878186968838525,
      "grad_norm": 0.22889818251132965,
      "learning_rate": 5.0872620321864185e-05,
      "loss": 0.8616,
      "step": 109
    },
    {
      "epoch": 0.031161473087818695,
      "grad_norm": 0.23722627758979797,
      "learning_rate": 5e-05,
      "loss": 0.8771,
      "step": 110
    },
    {
      "epoch": 0.031444759206798865,
      "grad_norm": 0.24426664412021637,
      "learning_rate": 4.912737967813583e-05,
      "loss": 0.8262,
      "step": 111
    },
    {
      "epoch": 0.03172804532577904,
      "grad_norm": 0.23950670659542084,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.7927,
      "step": 112
    },
    {
      "epoch": 0.032011331444759206,
      "grad_norm": 0.2488234043121338,
      "learning_rate": 4.738320218785281e-05,
      "loss": 0.7867,
      "step": 113
    },
    {
      "epoch": 0.03229461756373938,
      "grad_norm": 0.2525029182434082,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.8698,
      "step": 114
    },
    {
      "epoch": 0.032577903682719546,
      "grad_norm": 0.2562684416770935,
      "learning_rate": 4.564221286261709e-05,
      "loss": 0.8997,
      "step": 115
    },
    {
      "epoch": 0.03286118980169972,
      "grad_norm": 0.24841320514678955,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.7312,
      "step": 116
    },
    {
      "epoch": 0.033144475920679886,
      "grad_norm": 0.24395093321800232,
      "learning_rate": 4.390653282974264e-05,
      "loss": 0.8052,
      "step": 117
    },
    {
      "epoch": 0.03342776203966006,
      "grad_norm": 0.2734987735748291,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.8105,
      "step": 118
    },
    {
      "epoch": 0.033711048158640226,
      "grad_norm": 0.26797905564308167,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.8152,
      "step": 119
    },
    {
      "epoch": 0.0339943342776204,
      "grad_norm": 0.2523004114627838,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.8278,
      "step": 120
    },
    {
      "epoch": 0.03427762039660057,
      "grad_norm": 0.29165706038475037,
      "learning_rate": 4.045955023117276e-05,
      "loss": 0.8036,
      "step": 121
    },
    {
      "epoch": 0.03456090651558073,
      "grad_norm": 0.2852994501590729,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.819,
      "step": 122
    },
    {
      "epoch": 0.03484419263456091,
      "grad_norm": 0.26738786697387695,
      "learning_rate": 3.875244728280676e-05,
      "loss": 0.725,
      "step": 123
    },
    {
      "epoch": 0.03512747875354107,
      "grad_norm": 0.32836487889289856,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.8763,
      "step": 124
    },
    {
      "epoch": 0.03541076487252125,
      "grad_norm": 0.3035292625427246,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.8163,
      "step": 125
    },
    {
      "epoch": 0.035694050991501414,
      "grad_norm": 0.28376927971839905,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.8035,
      "step": 126
    },
    {
      "epoch": 0.03597733711048159,
      "grad_norm": 0.2992241680622101,
      "learning_rate": 3.5381414763863166e-05,
      "loss": 0.8246,
      "step": 127
    },
    {
      "epoch": 0.036260623229461754,
      "grad_norm": 0.2853834331035614,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.8592,
      "step": 128
    },
    {
      "epoch": 0.03654390934844193,
      "grad_norm": 0.29611217975616455,
      "learning_rate": 3.372159227714218e-05,
      "loss": 0.8047,
      "step": 129
    },
    {
      "epoch": 0.036827195467422094,
      "grad_norm": 0.3206999599933624,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.8674,
      "step": 130
    },
    {
      "epoch": 0.03711048158640227,
      "grad_norm": 0.3229055106639862,
      "learning_rate": 3.2081602522734986e-05,
      "loss": 0.8302,
      "step": 131
    },
    {
      "epoch": 0.037393767705382434,
      "grad_norm": 0.3764430284500122,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.9401,
      "step": 132
    },
    {
      "epoch": 0.03767705382436261,
      "grad_norm": 0.4034396708011627,
      "learning_rate": 3.046344357553632e-05,
      "loss": 0.896,
      "step": 133
    },
    {
      "epoch": 0.037960339943342775,
      "grad_norm": 0.44587916135787964,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.8274,
      "step": 134
    },
    {
      "epoch": 0.03824362606232295,
      "grad_norm": 0.4763351082801819,
      "learning_rate": 2.886908691296504e-05,
      "loss": 0.7875,
      "step": 135
    },
    {
      "epoch": 0.038526912181303115,
      "grad_norm": 0.5333124399185181,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.8866,
      "step": 136
    },
    {
      "epoch": 0.03881019830028329,
      "grad_norm": 0.4944680333137512,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 0.9163,
      "step": 137
    },
    {
      "epoch": 0.039093484419263455,
      "grad_norm": 0.5071774125099182,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.8415,
      "step": 138
    },
    {
      "epoch": 0.03937677053824363,
      "grad_norm": 0.5598042607307434,
      "learning_rate": 2.575951898768315e-05,
      "loss": 0.9715,
      "step": 139
    },
    {
      "epoch": 0.039660056657223795,
      "grad_norm": 0.5540819764137268,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.9824,
      "step": 140
    },
    {
      "epoch": 0.03994334277620397,
      "grad_norm": 0.5741395354270935,
      "learning_rate": 2.4248096254497288e-05,
      "loss": 0.9971,
      "step": 141
    },
    {
      "epoch": 0.040226628895184136,
      "grad_norm": 0.6620638370513916,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.9701,
      "step": 142
    },
    {
      "epoch": 0.04050991501416431,
      "grad_norm": 0.7596579790115356,
      "learning_rate": 2.2768048249248648e-05,
      "loss": 0.9779,
      "step": 143
    },
    {
      "epoch": 0.040793201133144476,
      "grad_norm": 0.7054856419563293,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.0068,
      "step": 144
    },
    {
      "epoch": 0.04107648725212465,
      "grad_norm": 0.7791336178779602,
      "learning_rate": 2.132117818244771e-05,
      "loss": 0.8515,
      "step": 145
    },
    {
      "epoch": 0.041359773371104816,
      "grad_norm": 0.843451976776123,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.9189,
      "step": 146
    },
    {
      "epoch": 0.04164305949008498,
      "grad_norm": 0.9110656976699829,
      "learning_rate": 1.9909248842397584e-05,
      "loss": 0.9361,
      "step": 147
    },
    {
      "epoch": 0.041926345609065156,
      "grad_norm": 1.0195434093475342,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.8717,
      "step": 148
    },
    {
      "epoch": 0.04220963172804532,
      "grad_norm": 1.243166446685791,
      "learning_rate": 1.8533980447508137e-05,
      "loss": 0.8591,
      "step": 149
    },
    {
      "epoch": 0.042492917847025496,
      "grad_norm": 2.237396717071533,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.8577,
      "step": 150
    },
    {
      "epoch": 0.042492917847025496,
      "eval_loss": 0.852659285068512,
      "eval_runtime": 488.0569,
      "eval_samples_per_second": 12.183,
      "eval_steps_per_second": 6.092,
      "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": 2.06575327248384e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}