{
  "best_metric": 0.7314529418945312,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.13110455588331696,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006555227794165847,
      "grad_norm": 0.235550656914711,
      "learning_rate": 5e-06,
      "loss": 0.8465,
      "step": 1
    },
    {
      "epoch": 0.0006555227794165847,
      "eval_loss": 1.0142732858657837,
      "eval_runtime": 197.6114,
      "eval_samples_per_second": 13.005,
      "eval_steps_per_second": 6.503,
      "step": 1
    },
    {
      "epoch": 0.0013110455588331695,
      "grad_norm": 0.2758314907550812,
      "learning_rate": 1e-05,
      "loss": 0.9051,
      "step": 2
    },
    {
      "epoch": 0.0019665683382497543,
      "grad_norm": 0.353505939245224,
      "learning_rate": 1.5e-05,
      "loss": 0.9246,
      "step": 3
    },
    {
      "epoch": 0.002622091117666339,
      "grad_norm": 0.41009101271629333,
      "learning_rate": 2e-05,
      "loss": 0.9182,
      "step": 4
    },
    {
      "epoch": 0.0032776138970829235,
      "grad_norm": 0.27966585755348206,
      "learning_rate": 2.5e-05,
      "loss": 0.8971,
      "step": 5
    },
    {
      "epoch": 0.003933136676499509,
      "grad_norm": 0.29553648829460144,
      "learning_rate": 3e-05,
      "loss": 0.9396,
      "step": 6
    },
    {
      "epoch": 0.004588659455916093,
      "grad_norm": 0.30871671438217163,
      "learning_rate": 3.5e-05,
      "loss": 0.9267,
      "step": 7
    },
    {
      "epoch": 0.005244182235332678,
      "grad_norm": 0.2765592038631439,
      "learning_rate": 4e-05,
      "loss": 0.9701,
      "step": 8
    },
    {
      "epoch": 0.0058997050147492625,
      "grad_norm": 0.28029540181159973,
      "learning_rate": 4.5e-05,
      "loss": 0.9126,
      "step": 9
    },
    {
      "epoch": 0.006555227794165847,
      "grad_norm": 0.2668909430503845,
      "learning_rate": 5e-05,
      "loss": 0.9425,
      "step": 10
    },
    {
      "epoch": 0.007210750573582432,
      "grad_norm": 0.24829484522342682,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.9111,
      "step": 11
    },
    {
      "epoch": 0.007866273352999017,
      "grad_norm": 0.22676482796669006,
      "learning_rate": 6e-05,
      "loss": 0.8698,
      "step": 12
    },
    {
      "epoch": 0.008521796132415601,
      "grad_norm": 0.2559908330440521,
      "learning_rate": 6.500000000000001e-05,
      "loss": 0.8578,
      "step": 13
    },
    {
      "epoch": 0.009177318911832186,
      "grad_norm": 0.25041428208351135,
      "learning_rate": 7e-05,
      "loss": 0.8731,
      "step": 14
    },
    {
      "epoch": 0.00983284169124877,
      "grad_norm": 0.25653332471847534,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.8058,
      "step": 15
    },
    {
      "epoch": 0.010488364470665356,
      "grad_norm": 0.26476186513900757,
      "learning_rate": 8e-05,
      "loss": 0.8617,
      "step": 16
    },
    {
      "epoch": 0.011143887250081941,
      "grad_norm": 0.27621665596961975,
      "learning_rate": 8.5e-05,
      "loss": 0.8623,
      "step": 17
    },
    {
      "epoch": 0.011799410029498525,
      "grad_norm": 0.2501699924468994,
      "learning_rate": 9e-05,
      "loss": 0.8358,
      "step": 18
    },
    {
      "epoch": 0.01245493280891511,
      "grad_norm": 0.2805434465408325,
      "learning_rate": 9.5e-05,
      "loss": 0.8303,
      "step": 19
    },
    {
      "epoch": 0.013110455588331694,
      "grad_norm": 0.26726552844047546,
      "learning_rate": 0.0001,
      "loss": 0.8374,
      "step": 20
    },
    {
      "epoch": 0.01376597836774828,
      "grad_norm": 0.25650665163993835,
      "learning_rate": 9.999238475781957e-05,
      "loss": 0.809,
      "step": 21
    },
    {
      "epoch": 0.014421501147164863,
      "grad_norm": 0.2529831528663635,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.8062,
      "step": 22
    },
    {
      "epoch": 0.015077023926581449,
      "grad_norm": 0.2601158320903778,
      "learning_rate": 9.99314767377287e-05,
      "loss": 0.8543,
      "step": 23
    },
    {
      "epoch": 0.015732546705998034,
      "grad_norm": 0.22991959750652313,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.8133,
      "step": 24
    },
    {
      "epoch": 0.01638806948541462,
      "grad_norm": 0.2492550164461136,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.8063,
      "step": 25
    },
    {
      "epoch": 0.017043592264831202,
      "grad_norm": 0.24826645851135254,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.793,
      "step": 26
    },
    {
      "epoch": 0.017699115044247787,
      "grad_norm": 0.24337033927440643,
      "learning_rate": 9.962730758206611e-05,
      "loss": 0.8356,
      "step": 27
    },
    {
      "epoch": 0.018354637823664373,
      "grad_norm": 0.24566523730754852,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.8135,
      "step": 28
    },
    {
      "epoch": 0.01901016060308096,
      "grad_norm": 0.23468296229839325,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.816,
      "step": 29
    },
    {
      "epoch": 0.01966568338249754,
      "grad_norm": 0.2509690225124359,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.7622,
      "step": 30
    },
    {
      "epoch": 0.020321206161914126,
      "grad_norm": 0.2616191804409027,
      "learning_rate": 9.908135917238321e-05,
      "loss": 0.7873,
      "step": 31
    },
    {
      "epoch": 0.02097672894133071,
      "grad_norm": 0.2554737329483032,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.7737,
      "step": 32
    },
    {
      "epoch": 0.021632251720747297,
      "grad_norm": 0.26420480012893677,
      "learning_rate": 9.871850323926177e-05,
      "loss": 0.8324,
      "step": 33
    },
    {
      "epoch": 0.022287774500163882,
      "grad_norm": 0.287476509809494,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.7953,
      "step": 34
    },
    {
      "epoch": 0.022943297279580464,
      "grad_norm": 0.2667132318019867,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.7759,
      "step": 35
    },
    {
      "epoch": 0.02359882005899705,
      "grad_norm": 0.26211854815483093,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.7792,
      "step": 36
    },
    {
      "epoch": 0.024254342838413635,
      "grad_norm": 0.2618478834629059,
      "learning_rate": 9.781523779815179e-05,
      "loss": 0.7601,
      "step": 37
    },
    {
      "epoch": 0.02490986561783022,
      "grad_norm": 0.2587236762046814,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7905,
      "step": 38
    },
    {
      "epoch": 0.025565388397246803,
      "grad_norm": 0.2682913541793823,
      "learning_rate": 9.727592877996585e-05,
      "loss": 0.7605,
      "step": 39
    },
    {
      "epoch": 0.02622091117666339,
      "grad_norm": 0.3010149300098419,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.8133,
      "step": 40
    },
    {
      "epoch": 0.026876433956079974,
      "grad_norm": 0.269761860370636,
      "learning_rate": 9.667902132486009e-05,
      "loss": 0.7322,
      "step": 41
    },
    {
      "epoch": 0.02753195673549656,
      "grad_norm": 0.3124874234199524,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.7736,
      "step": 42
    },
    {
      "epoch": 0.028187479514913145,
      "grad_norm": 0.35831648111343384,
      "learning_rate": 9.602524267262203e-05,
      "loss": 0.756,
      "step": 43
    },
    {
      "epoch": 0.028843002294329727,
      "grad_norm": 0.3162555992603302,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.7631,
      "step": 44
    },
    {
      "epoch": 0.029498525073746312,
      "grad_norm": 0.3109850585460663,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.7962,
      "step": 45
    },
    {
      "epoch": 0.030154047853162898,
      "grad_norm": 0.4582791030406952,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.8059,
      "step": 46
    },
    {
      "epoch": 0.030809570632579483,
      "grad_norm": 0.6955217123031616,
      "learning_rate": 9.45503262094184e-05,
      "loss": 0.743,
      "step": 47
    },
    {
      "epoch": 0.03146509341199607,
      "grad_norm": 0.4150660037994385,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.7962,
      "step": 48
    },
    {
      "epoch": 0.032120616191412654,
      "grad_norm": 0.6555883288383484,
      "learning_rate": 9.373098535696979e-05,
      "loss": 0.7481,
      "step": 49
    },
    {
      "epoch": 0.03277613897082924,
      "grad_norm": 0.8971114158630371,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.7733,
      "step": 50
    },
    {
      "epoch": 0.03277613897082924,
      "eval_loss": 0.8451602458953857,
      "eval_runtime": 198.9823,
      "eval_samples_per_second": 12.916,
      "eval_steps_per_second": 6.458,
      "step": 50
    },
    {
      "epoch": 0.03343166175024582,
      "grad_norm": 0.4766312539577484,
      "learning_rate": 9.285836503510562e-05,
      "loss": 0.8995,
      "step": 51
    },
    {
      "epoch": 0.034087184529662404,
      "grad_norm": 0.39536991715431213,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.8676,
      "step": 52
    },
    {
      "epoch": 0.03474270730907899,
      "grad_norm": 0.31390702724456787,
      "learning_rate": 9.193352839727121e-05,
      "loss": 0.828,
      "step": 53
    },
    {
      "epoch": 0.035398230088495575,
      "grad_norm": 0.22811783850193024,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.7869,
      "step": 54
    },
    {
      "epoch": 0.03605375286791216,
      "grad_norm": 0.20999696850776672,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.7506,
      "step": 55
    },
    {
      "epoch": 0.036709275647328746,
      "grad_norm": 0.19338922202587128,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7783,
      "step": 56
    },
    {
      "epoch": 0.03736479842674533,
      "grad_norm": 0.19408264756202698,
      "learning_rate": 8.993177550236464e-05,
      "loss": 0.7937,
      "step": 57
    },
    {
      "epoch": 0.03802032120616192,
      "grad_norm": 0.20640671253204346,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.8187,
      "step": 58
    },
    {
      "epoch": 0.0386758439855785,
      "grad_norm": 0.22669357061386108,
      "learning_rate": 8.885729807284856e-05,
      "loss": 0.7998,
      "step": 59
    },
    {
      "epoch": 0.03933136676499508,
      "grad_norm": 0.20648466050624847,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.7925,
      "step": 60
    },
    {
      "epoch": 0.039986889544411666,
      "grad_norm": 0.2173505574464798,
      "learning_rate": 8.773547901113862e-05,
      "loss": 0.8002,
      "step": 61
    },
    {
      "epoch": 0.04064241232382825,
      "grad_norm": 0.2065979391336441,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.8012,
      "step": 62
    },
    {
      "epoch": 0.04129793510324484,
      "grad_norm": 0.1957106590270996,
      "learning_rate": 8.656768508095853e-05,
      "loss": 0.8364,
      "step": 63
    },
    {
      "epoch": 0.04195345788266142,
      "grad_norm": 0.20308098196983337,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.7903,
      "step": 64
    },
    {
      "epoch": 0.04260898066207801,
      "grad_norm": 0.19192680716514587,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.7738,
      "step": 65
    },
    {
      "epoch": 0.043264503441494594,
      "grad_norm": 0.19954106211662292,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.7868,
      "step": 66
    },
    {
      "epoch": 0.04392002622091118,
      "grad_norm": 0.20240260660648346,
      "learning_rate": 8.409991800312493e-05,
      "loss": 0.8114,
      "step": 67
    },
    {
      "epoch": 0.044575549000327765,
      "grad_norm": 0.21940922737121582,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.8217,
      "step": 68
    },
    {
      "epoch": 0.04523107177974434,
      "grad_norm": 0.19955359399318695,
      "learning_rate": 8.280295144952536e-05,
      "loss": 0.7524,
      "step": 69
    },
    {
      "epoch": 0.04588659455916093,
      "grad_norm": 0.20132817327976227,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.7341,
      "step": 70
    },
    {
      "epoch": 0.046542117338577514,
      "grad_norm": 0.2130366563796997,
      "learning_rate": 8.146601955249188e-05,
      "loss": 0.7965,
      "step": 71
    },
    {
      "epoch": 0.0471976401179941,
      "grad_norm": 0.2073906809091568,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.7719,
      "step": 72
    },
    {
      "epoch": 0.047853162897410685,
      "grad_norm": 0.21725565195083618,
      "learning_rate": 8.009075115760243e-05,
      "loss": 0.7322,
      "step": 73
    },
    {
      "epoch": 0.04850868567682727,
      "grad_norm": 0.22413761913776398,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.7669,
      "step": 74
    },
    {
      "epoch": 0.049164208456243856,
      "grad_norm": 0.2267717570066452,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.7911,
      "step": 75
    },
    {
      "epoch": 0.04981973123566044,
      "grad_norm": 0.21038523316383362,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.7865,
      "step": 76
    },
    {
      "epoch": 0.05047525401507703,
      "grad_norm": 0.22771699726581573,
      "learning_rate": 7.723195175075136e-05,
      "loss": 0.7747,
      "step": 77
    },
    {
      "epoch": 0.051130776794493606,
      "grad_norm": 0.232252299785614,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.7708,
      "step": 78
    },
    {
      "epoch": 0.05178629957391019,
      "grad_norm": 0.23539628088474274,
      "learning_rate": 7.575190374550272e-05,
      "loss": 0.7329,
      "step": 79
    },
    {
      "epoch": 0.05244182235332678,
      "grad_norm": 0.22794273495674133,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.7372,
      "step": 80
    },
    {
      "epoch": 0.05309734513274336,
      "grad_norm": 0.2243579924106598,
      "learning_rate": 7.424048101231686e-05,
      "loss": 0.7102,
      "step": 81
    },
    {
      "epoch": 0.05375286791215995,
      "grad_norm": 0.22993320226669312,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.7273,
      "step": 82
    },
    {
      "epoch": 0.05440839069157653,
      "grad_norm": 0.24748313426971436,
      "learning_rate": 7.269952498697734e-05,
      "loss": 0.7605,
      "step": 83
    },
    {
      "epoch": 0.05506391347099312,
      "grad_norm": 0.24593451619148254,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.7755,
      "step": 84
    },
    {
      "epoch": 0.055719436250409704,
      "grad_norm": 0.2471831887960434,
      "learning_rate": 7.113091308703498e-05,
      "loss": 0.7309,
      "step": 85
    },
    {
      "epoch": 0.05637495902982629,
      "grad_norm": 0.2624872624874115,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.7426,
      "step": 86
    },
    {
      "epoch": 0.05703048180924287,
      "grad_norm": 0.2791620194911957,
      "learning_rate": 6.953655642446368e-05,
      "loss": 0.7445,
      "step": 87
    },
    {
      "epoch": 0.057686004588659454,
      "grad_norm": 0.2620280981063843,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.7389,
      "step": 88
    },
    {
      "epoch": 0.05834152736807604,
      "grad_norm": 0.2604498863220215,
      "learning_rate": 6.7918397477265e-05,
      "loss": 0.7425,
      "step": 89
    },
    {
      "epoch": 0.058997050147492625,
      "grad_norm": 0.2729211151599884,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.7878,
      "step": 90
    },
    {
      "epoch": 0.05965257292690921,
      "grad_norm": 0.2708818018436432,
      "learning_rate": 6.627840772285784e-05,
      "loss": 0.7393,
      "step": 91
    },
    {
      "epoch": 0.060308095706325796,
      "grad_norm": 0.28677260875701904,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7121,
      "step": 92
    },
    {
      "epoch": 0.06096361848574238,
      "grad_norm": 0.2563154697418213,
      "learning_rate": 6.461858523613684e-05,
      "loss": 0.7231,
      "step": 93
    },
    {
      "epoch": 0.061619141265158967,
      "grad_norm": 0.2770698070526123,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.7838,
      "step": 94
    },
    {
      "epoch": 0.06227466404457555,
      "grad_norm": 0.290865033864975,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.7899,
      "step": 95
    },
    {
      "epoch": 0.06293018682399214,
      "grad_norm": 0.30099108815193176,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.7436,
      "step": 96
    },
    {
      "epoch": 0.06358570960340872,
      "grad_norm": 0.3311876654624939,
      "learning_rate": 6.124755271719325e-05,
      "loss": 0.703,
      "step": 97
    },
    {
      "epoch": 0.06424123238282531,
      "grad_norm": 0.3758433163166046,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.742,
      "step": 98
    },
    {
      "epoch": 0.06489675516224189,
      "grad_norm": 0.4289000630378723,
      "learning_rate": 5.9540449768827246e-05,
      "loss": 0.7348,
      "step": 99
    },
    {
      "epoch": 0.06555227794165848,
      "grad_norm": 0.9882183074951172,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.7164,
      "step": 100
    },
    {
      "epoch": 0.06555227794165848,
      "eval_loss": 0.7744090557098389,
      "eval_runtime": 199.1483,
      "eval_samples_per_second": 12.905,
      "eval_steps_per_second": 6.452,
      "step": 100
    },
    {
      "epoch": 0.06620780072107506,
      "grad_norm": 0.3230420649051666,
      "learning_rate": 5.782172325201155e-05,
      "loss": 0.8107,
      "step": 101
    },
    {
      "epoch": 0.06686332350049164,
      "grad_norm": 0.33954355120658875,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.7725,
      "step": 102
    },
    {
      "epoch": 0.06751884627990823,
      "grad_norm": 0.29015445709228516,
      "learning_rate": 5.6093467170257374e-05,
      "loss": 0.7894,
      "step": 103
    },
    {
      "epoch": 0.06817436905932481,
      "grad_norm": 0.24934352934360504,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.7275,
      "step": 104
    },
    {
      "epoch": 0.0688298918387414,
      "grad_norm": 0.2048061341047287,
      "learning_rate": 5.435778713738292e-05,
      "loss": 0.7744,
      "step": 105
    },
    {
      "epoch": 0.06948541461815798,
      "grad_norm": 0.18044789135456085,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.774,
      "step": 106
    },
    {
      "epoch": 0.07014093739757457,
      "grad_norm": 0.18927855789661407,
      "learning_rate": 5.26167978121472e-05,
      "loss": 0.7609,
      "step": 107
    },
    {
      "epoch": 0.07079646017699115,
      "grad_norm": 0.1957709938287735,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.7573,
      "step": 108
    },
    {
      "epoch": 0.07145198295640774,
      "grad_norm": 0.1963825523853302,
      "learning_rate": 5.0872620321864185e-05,
      "loss": 0.7636,
      "step": 109
    },
    {
      "epoch": 0.07210750573582432,
      "grad_norm": 0.19426244497299194,
      "learning_rate": 5e-05,
      "loss": 0.7661,
      "step": 110
    },
    {
      "epoch": 0.0727630285152409,
      "grad_norm": 0.1983892321586609,
      "learning_rate": 4.912737967813583e-05,
      "loss": 0.716,
      "step": 111
    },
    {
      "epoch": 0.07341855129465749,
      "grad_norm": 0.19750836491584778,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.7446,
      "step": 112
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.2106139063835144,
      "learning_rate": 4.738320218785281e-05,
      "loss": 0.73,
      "step": 113
    },
    {
      "epoch": 0.07472959685349066,
      "grad_norm": 0.21055595576763153,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.7844,
      "step": 114
    },
    {
      "epoch": 0.07538511963290724,
      "grad_norm": 0.20702974498271942,
      "learning_rate": 4.564221286261709e-05,
      "loss": 0.74,
      "step": 115
    },
    {
      "epoch": 0.07604064241232383,
      "grad_norm": 0.20417121052742004,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.7675,
      "step": 116
    },
    {
      "epoch": 0.07669616519174041,
      "grad_norm": 0.20810063183307648,
      "learning_rate": 4.390653282974264e-05,
      "loss": 0.7569,
      "step": 117
    },
    {
      "epoch": 0.077351687971157,
      "grad_norm": 0.2064942717552185,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.7624,
      "step": 118
    },
    {
      "epoch": 0.07800721075057358,
      "grad_norm": 0.2109329104423523,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.7538,
      "step": 119
    },
    {
      "epoch": 0.07866273352999016,
      "grad_norm": 0.22467385232448578,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.7801,
      "step": 120
    },
    {
      "epoch": 0.07931825630940675,
      "grad_norm": 0.2120361477136612,
      "learning_rate": 4.045955023117276e-05,
      "loss": 0.7862,
      "step": 121
    },
    {
      "epoch": 0.07997377908882333,
      "grad_norm": 0.22147348523139954,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.7786,
      "step": 122
    },
    {
      "epoch": 0.08062930186823992,
      "grad_norm": 0.2166486382484436,
      "learning_rate": 3.875244728280676e-05,
      "loss": 0.7497,
      "step": 123
    },
    {
      "epoch": 0.0812848246476565,
      "grad_norm": 0.22515670955181122,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.7653,
      "step": 124
    },
    {
      "epoch": 0.0819403474270731,
      "grad_norm": 0.2231398969888687,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.7337,
      "step": 125
    },
    {
      "epoch": 0.08259587020648967,
      "grad_norm": 0.23349618911743164,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.7699,
      "step": 126
    },
    {
      "epoch": 0.08325139298590627,
      "grad_norm": 0.2265060395002365,
      "learning_rate": 3.5381414763863166e-05,
      "loss": 0.7221,
      "step": 127
    },
    {
      "epoch": 0.08390691576532285,
      "grad_norm": 0.234450101852417,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7509,
      "step": 128
    },
    {
      "epoch": 0.08456243854473942,
      "grad_norm": 0.2428438514471054,
      "learning_rate": 3.372159227714218e-05,
      "loss": 0.7748,
      "step": 129
    },
    {
      "epoch": 0.08521796132415602,
      "grad_norm": 0.22536177933216095,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.703,
      "step": 130
    },
    {
      "epoch": 0.0858734841035726,
      "grad_norm": 0.2375769019126892,
      "learning_rate": 3.2081602522734986e-05,
      "loss": 0.7989,
      "step": 131
    },
    {
      "epoch": 0.08652900688298919,
      "grad_norm": 0.2428019642829895,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.7635,
      "step": 132
    },
    {
      "epoch": 0.08718452966240577,
      "grad_norm": 0.24135881662368774,
      "learning_rate": 3.046344357553632e-05,
      "loss": 0.7199,
      "step": 133
    },
    {
      "epoch": 0.08784005244182236,
      "grad_norm": 0.2383740097284317,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.7019,
      "step": 134
    },
    {
      "epoch": 0.08849557522123894,
      "grad_norm": 0.24633391201496124,
      "learning_rate": 2.886908691296504e-05,
      "loss": 0.7445,
      "step": 135
    },
    {
      "epoch": 0.08915109800065553,
      "grad_norm": 0.2432476133108139,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.7244,
      "step": 136
    },
    {
      "epoch": 0.08980662078007211,
      "grad_norm": 0.24993503093719482,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 0.7597,
      "step": 137
    },
    {
      "epoch": 0.09046214355948869,
      "grad_norm": 0.24975240230560303,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.7094,
      "step": 138
    },
    {
      "epoch": 0.09111766633890528,
      "grad_norm": 0.25752413272857666,
      "learning_rate": 2.575951898768315e-05,
      "loss": 0.7113,
      "step": 139
    },
    {
      "epoch": 0.09177318911832186,
      "grad_norm": 0.26039180159568787,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.7213,
      "step": 140
    },
    {
      "epoch": 0.09242871189773845,
      "grad_norm": 0.2756704092025757,
      "learning_rate": 2.4248096254497288e-05,
      "loss": 0.7592,
      "step": 141
    },
    {
      "epoch": 0.09308423467715503,
      "grad_norm": 0.26630955934524536,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.7139,
      "step": 142
    },
    {
      "epoch": 0.09373975745657162,
      "grad_norm": 0.2901815176010132,
      "learning_rate": 2.2768048249248648e-05,
      "loss": 0.7464,
      "step": 143
    },
    {
      "epoch": 0.0943952802359882,
      "grad_norm": 0.34002649784088135,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.7968,
      "step": 144
    },
    {
      "epoch": 0.09505080301540479,
      "grad_norm": 0.3794809579849243,
      "learning_rate": 2.132117818244771e-05,
      "loss": 0.7225,
      "step": 145
    },
    {
      "epoch": 0.09570632579482137,
      "grad_norm": 0.2886137366294861,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.703,
      "step": 146
    },
    {
      "epoch": 0.09636184857423795,
      "grad_norm": 0.32145318388938904,
      "learning_rate": 1.9909248842397584e-05,
      "loss": 0.7085,
      "step": 147
    },
    {
      "epoch": 0.09701737135365454,
      "grad_norm": 0.35929107666015625,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.7983,
      "step": 148
    },
    {
      "epoch": 0.09767289413307112,
      "grad_norm": 0.46539416909217834,
      "learning_rate": 1.8533980447508137e-05,
      "loss": 0.713,
      "step": 149
    },
    {
      "epoch": 0.09832841691248771,
      "grad_norm": 1.5912036895751953,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.7509,
      "step": 150
    },
    {
      "epoch": 0.09832841691248771,
      "eval_loss": 0.738473653793335,
      "eval_runtime": 199.4164,
      "eval_samples_per_second": 12.888,
      "eval_steps_per_second": 6.444,
      "step": 150
    },
    {
      "epoch": 0.09898393969190429,
      "grad_norm": 0.15162894129753113,
      "learning_rate": 1.7197048550474643e-05,
      "loss": 0.7582,
      "step": 151
    },
    {
      "epoch": 0.09963946247132088,
      "grad_norm": 0.16039323806762695,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.7372,
      "step": 152
    },
    {
      "epoch": 0.10029498525073746,
      "grad_norm": 0.17895907163619995,
      "learning_rate": 1.5900081996875083e-05,
      "loss": 0.7133,
      "step": 153
    },
    {
      "epoch": 0.10095050803015405,
      "grad_norm": 0.1802811175584793,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.7564,
      "step": 154
    },
    {
      "epoch": 0.10160603080957063,
      "grad_norm": 0.18295489251613617,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.751,
      "step": 155
    },
    {
      "epoch": 0.10226155358898721,
      "grad_norm": 0.2046223133802414,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.7479,
      "step": 156
    },
    {
      "epoch": 0.1029170763684038,
      "grad_norm": 0.2062293291091919,
      "learning_rate": 1.3432314919041478e-05,
      "loss": 0.7741,
      "step": 157
    },
    {
      "epoch": 0.10357259914782038,
      "grad_norm": 0.21057236194610596,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.7542,
      "step": 158
    },
    {
      "epoch": 0.10422812192723697,
      "grad_norm": 0.2081954926252365,
      "learning_rate": 1.22645209888614e-05,
      "loss": 0.7351,
      "step": 159
    },
    {
      "epoch": 0.10488364470665355,
      "grad_norm": 0.2035297006368637,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.7107,
      "step": 160
    },
    {
      "epoch": 0.10553916748607015,
      "grad_norm": 0.22912153601646423,
      "learning_rate": 1.1142701927151456e-05,
      "loss": 0.7621,
      "step": 161
    },
    {
      "epoch": 0.10619469026548672,
      "grad_norm": 0.22100181877613068,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.7919,
      "step": 162
    },
    {
      "epoch": 0.10685021304490332,
      "grad_norm": 0.21412691473960876,
      "learning_rate": 1.006822449763537e-05,
      "loss": 0.7787,
      "step": 163
    },
    {
      "epoch": 0.1075057358243199,
      "grad_norm": 0.20946674048900604,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7378,
      "step": 164
    },
    {
      "epoch": 0.10816125860373647,
      "grad_norm": 0.2101847380399704,
      "learning_rate": 9.042397785550405e-06,
      "loss": 0.7333,
      "step": 165
    },
    {
      "epoch": 0.10881678138315307,
      "grad_norm": 0.21179062128067017,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.7441,
      "step": 166
    },
    {
      "epoch": 0.10947230416256964,
      "grad_norm": 0.21928472816944122,
      "learning_rate": 8.066471602728803e-06,
      "loss": 0.747,
      "step": 167
    },
    {
      "epoch": 0.11012782694198624,
      "grad_norm": 0.22222241759300232,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.7177,
      "step": 168
    },
    {
      "epoch": 0.11078334972140282,
      "grad_norm": 0.21160081028938293,
      "learning_rate": 7.1416349648943894e-06,
      "loss": 0.6983,
      "step": 169
    },
    {
      "epoch": 0.11143887250081941,
      "grad_norm": 0.2066689431667328,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.77,
      "step": 170
    },
    {
      "epoch": 0.11209439528023599,
      "grad_norm": 0.20904311537742615,
      "learning_rate": 6.269014643030213e-06,
      "loss": 0.714,
      "step": 171
    },
    {
      "epoch": 0.11274991805965258,
      "grad_norm": 0.20662519335746765,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.7304,
      "step": 172
    },
    {
      "epoch": 0.11340544083906916,
      "grad_norm": 0.21941520273685455,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.7327,
      "step": 173
    },
    {
      "epoch": 0.11406096361848574,
      "grad_norm": 0.22719362378120422,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.6836,
      "step": 174
    },
    {
      "epoch": 0.11471648639790233,
      "grad_norm": 0.22123894095420837,
      "learning_rate": 4.684610648167503e-06,
      "loss": 0.7211,
      "step": 175
    },
    {
      "epoch": 0.11537200917731891,
      "grad_norm": 0.22673584520816803,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.7675,
      "step": 176
    },
    {
      "epoch": 0.1160275319567355,
      "grad_norm": 0.2243812084197998,
      "learning_rate": 3.974757327377981e-06,
      "loss": 0.7079,
      "step": 177
    },
    {
      "epoch": 0.11668305473615208,
      "grad_norm": 0.23104526102542877,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.7292,
      "step": 178
    },
    {
      "epoch": 0.11733857751556867,
      "grad_norm": 0.23834234476089478,
      "learning_rate": 3.3209786751399187e-06,
      "loss": 0.7476,
      "step": 179
    },
    {
      "epoch": 0.11799410029498525,
      "grad_norm": 0.22016264498233795,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.6939,
      "step": 180
    },
    {
      "epoch": 0.11864962307440184,
      "grad_norm": 0.22917792201042175,
      "learning_rate": 2.724071220034158e-06,
      "loss": 0.736,
      "step": 181
    },
    {
      "epoch": 0.11930514585381842,
      "grad_norm": 0.2416093945503235,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.7123,
      "step": 182
    },
    {
      "epoch": 0.119960668633235,
      "grad_norm": 0.3126245141029358,
      "learning_rate": 2.1847622018482283e-06,
      "loss": 0.7336,
      "step": 183
    },
    {
      "epoch": 0.12061619141265159,
      "grad_norm": 0.2426881045103073,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.6961,
      "step": 184
    },
    {
      "epoch": 0.12127171419206817,
      "grad_norm": 0.24644267559051514,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.714,
      "step": 185
    },
    {
      "epoch": 0.12192723697148476,
      "grad_norm": 0.25078660249710083,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.7384,
      "step": 186
    },
    {
      "epoch": 0.12258275975090134,
      "grad_norm": 0.24206167459487915,
      "learning_rate": 1.2814967607382432e-06,
      "loss": 0.6992,
      "step": 187
    },
    {
      "epoch": 0.12323828253031793,
      "grad_norm": 0.2712722718715668,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.7522,
      "step": 188
    },
    {
      "epoch": 0.12389380530973451,
      "grad_norm": 0.25732171535491943,
      "learning_rate": 9.186408276168013e-07,
      "loss": 0.6862,
      "step": 189
    },
    {
      "epoch": 0.1245493280891511,
      "grad_norm": 0.2646312415599823,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.7228,
      "step": 190
    },
    {
      "epoch": 0.1252048508685677,
      "grad_norm": 0.30237093567848206,
      "learning_rate": 6.15582970243117e-07,
      "loss": 0.7667,
      "step": 191
    },
    {
      "epoch": 0.12586037364798427,
      "grad_norm": 0.2784475088119507,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.7354,
      "step": 192
    },
    {
      "epoch": 0.12651589642740085,
      "grad_norm": 0.27990859746932983,
      "learning_rate": 3.7269241793390085e-07,
      "loss": 0.7249,
      "step": 193
    },
    {
      "epoch": 0.12717141920681743,
      "grad_norm": 0.2913055717945099,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.7434,
      "step": 194
    },
    {
      "epoch": 0.127826941986234,
      "grad_norm": 0.3054560124874115,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 0.7414,
      "step": 195
    },
    {
      "epoch": 0.12848246476565062,
      "grad_norm": 0.3870754837989807,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.7448,
      "step": 196
    },
    {
      "epoch": 0.1291379875450672,
      "grad_norm": 0.3209869861602783,
      "learning_rate": 6.852326227130834e-08,
      "loss": 0.676,
      "step": 197
    },
    {
      "epoch": 0.12979351032448377,
      "grad_norm": 0.36920166015625,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.693,
      "step": 198
    },
    {
      "epoch": 0.13044903310390035,
      "grad_norm": 0.4164353311061859,
      "learning_rate": 7.615242180436522e-09,
      "loss": 0.7864,
      "step": 199
    },
    {
      "epoch": 0.13110455588331696,
      "grad_norm": 0.43773046135902405,
      "learning_rate": 0.0,
      "loss": 0.6565,
      "step": 200
    },
    {
      "epoch": 0.13110455588331696,
      "eval_loss": 0.7314529418945312,
      "eval_runtime": 199.2298,
      "eval_samples_per_second": 12.9,
      "eval_steps_per_second": 6.45,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.6709961332699955e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}