{
  "best_metric": 0.9298770427703857,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.2121212121212122,
  "eval_steps": 25,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006060606060606061,
      "grad_norm": 0.33500415086746216,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 3.8146,
      "step": 1
    },
    {
      "epoch": 0.006060606060606061,
      "eval_loss": 1.2686991691589355,
      "eval_runtime": 8.638,
      "eval_samples_per_second": 5.788,
      "eval_steps_per_second": 0.81,
      "step": 1
    },
    {
      "epoch": 0.012121212121212121,
      "grad_norm": 0.48386213183403015,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 4.3313,
      "step": 2
    },
    {
      "epoch": 0.01818181818181818,
      "grad_norm": 0.6906216740608215,
      "learning_rate": 8.999999999999999e-05,
      "loss": 4.5878,
      "step": 3
    },
    {
      "epoch": 0.024242424242424242,
      "grad_norm": 0.33841270208358765,
      "learning_rate": 0.00011999999999999999,
      "loss": 3.9734,
      "step": 4
    },
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 0.7029704451560974,
      "learning_rate": 0.00015,
      "loss": 4.2674,
      "step": 5
    },
    {
      "epoch": 0.03636363636363636,
      "grad_norm": 0.3333696126937866,
      "learning_rate": 0.00017999999999999998,
      "loss": 4.1348,
      "step": 6
    },
    {
      "epoch": 0.04242424242424243,
      "grad_norm": 0.40864428877830505,
      "learning_rate": 0.00020999999999999998,
      "loss": 4.6588,
      "step": 7
    },
    {
      "epoch": 0.048484848484848485,
      "grad_norm": 0.43301916122436523,
      "learning_rate": 0.00023999999999999998,
      "loss": 4.7322,
      "step": 8
    },
    {
      "epoch": 0.05454545454545454,
      "grad_norm": 0.5013192892074585,
      "learning_rate": 0.00027,
      "loss": 4.8769,
      "step": 9
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 0.493767112493515,
      "learning_rate": 0.0003,
      "loss": 5.2981,
      "step": 10
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 0.50211501121521,
      "learning_rate": 0.0002999794957488703,
      "loss": 5.0141,
      "step": 11
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": 0.6502489447593689,
      "learning_rate": 0.0002999179886011389,
      "loss": 4.85,
      "step": 12
    },
    {
      "epoch": 0.07878787878787878,
      "grad_norm": 0.6038459539413452,
      "learning_rate": 0.0002998154953722457,
      "loss": 4.7728,
      "step": 13
    },
    {
      "epoch": 0.08484848484848485,
      "grad_norm": 0.5247741341590881,
      "learning_rate": 0.00029967204408281613,
      "loss": 4.8096,
      "step": 14
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 1.0044686794281006,
      "learning_rate": 0.00029948767395100045,
      "loss": 4.8118,
      "step": 15
    },
    {
      "epoch": 0.09696969696969697,
      "grad_norm": 1.0723237991333008,
      "learning_rate": 0.0002992624353817517,
      "loss": 4.9058,
      "step": 16
    },
    {
      "epoch": 0.10303030303030303,
      "grad_norm": 0.9577345848083496,
      "learning_rate": 0.0002989963899530457,
      "loss": 3.9803,
      "step": 17
    },
    {
      "epoch": 0.10909090909090909,
      "grad_norm": 1.0182474851608276,
      "learning_rate": 0.00029868961039904624,
      "loss": 4.428,
      "step": 18
    },
    {
      "epoch": 0.11515151515151516,
      "grad_norm": 1.0470702648162842,
      "learning_rate": 0.00029834218059022024,
      "loss": 3.896,
      "step": 19
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 1.2511624097824097,
      "learning_rate": 0.00029795419551040833,
      "loss": 4.2984,
      "step": 20
    },
    {
      "epoch": 0.12727272727272726,
      "grad_norm": 1.0913665294647217,
      "learning_rate": 0.00029752576123085736,
      "loss": 3.9277,
      "step": 21
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 1.1771706342697144,
      "learning_rate": 0.0002970569948812214,
      "loss": 4.2702,
      "step": 22
    },
    {
      "epoch": 0.1393939393939394,
      "grad_norm": 1.2473974227905273,
      "learning_rate": 0.0002965480246175399,
      "loss": 4.1467,
      "step": 23
    },
    {
      "epoch": 0.14545454545454545,
      "grad_norm": 1.2550790309906006,
      "learning_rate": 0.0002959989895872009,
      "loss": 3.8834,
      "step": 24
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 1.1687055826187134,
      "learning_rate": 0.0002954100398908995,
      "loss": 4.0057,
      "step": 25
    },
    {
      "epoch": 0.15151515151515152,
      "eval_loss": 1.0932072401046753,
      "eval_runtime": 8.802,
      "eval_samples_per_second": 5.681,
      "eval_steps_per_second": 0.795,
      "step": 25
    },
    {
      "epoch": 0.15757575757575756,
      "grad_norm": 1.3486429452896118,
      "learning_rate": 0.0002947813365416023,
      "loss": 4.2109,
      "step": 26
    },
    {
      "epoch": 0.16363636363636364,
      "grad_norm": 1.247335433959961,
      "learning_rate": 0.0002941130514205272,
      "loss": 3.8738,
      "step": 27
    },
    {
      "epoch": 0.1696969696969697,
      "grad_norm": 1.3320882320404053,
      "learning_rate": 0.0002934053672301536,
      "loss": 3.8869,
      "step": 28
    },
    {
      "epoch": 0.17575757575757575,
      "grad_norm": 1.0924450159072876,
      "learning_rate": 0.00029265847744427303,
      "loss": 4.2688,
      "step": 29
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 1.3163838386535645,
      "learning_rate": 0.00029187258625509513,
      "loss": 4.0793,
      "step": 30
    },
    {
      "epoch": 0.18787878787878787,
      "grad_norm": 1.5160199403762817,
      "learning_rate": 0.00029104790851742417,
      "loss": 4.1991,
      "step": 31
    },
    {
      "epoch": 0.19393939393939394,
      "grad_norm": 1.4316421747207642,
      "learning_rate": 0.0002901846696899191,
      "loss": 4.4843,
      "step": 32
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.2584881782531738,
      "learning_rate": 0.00028928310577345606,
      "loss": 4.3776,
      "step": 33
    },
    {
      "epoch": 0.20606060606060606,
      "grad_norm": 1.262694239616394,
      "learning_rate": 0.0002883434632466077,
      "loss": 4.2511,
      "step": 34
    },
    {
      "epoch": 0.21212121212121213,
      "grad_norm": 1.1281782388687134,
      "learning_rate": 0.00028736599899825856,
      "loss": 4.1313,
      "step": 35
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 1.2134889364242554,
      "learning_rate": 0.00028635098025737434,
      "loss": 4.2228,
      "step": 36
    },
    {
      "epoch": 0.22424242424242424,
      "grad_norm": 1.2678911685943604,
      "learning_rate": 0.00028529868451994384,
      "loss": 3.964,
      "step": 37
    },
    {
      "epoch": 0.23030303030303031,
      "grad_norm": 1.2652699947357178,
      "learning_rate": 0.0002842093994731145,
      "loss": 4.3013,
      "step": 38
    },
    {
      "epoch": 0.23636363636363636,
      "grad_norm": 1.3240559101104736,
      "learning_rate": 0.00028308342291654174,
      "loss": 4.1894,
      "step": 39
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 1.4998846054077148,
      "learning_rate": 0.00028192106268097334,
      "loss": 4.8843,
      "step": 40
    },
    {
      "epoch": 0.24848484848484848,
      "grad_norm": 9.243223190307617,
      "learning_rate": 0.00028072263654409154,
      "loss": 9.5322,
      "step": 41
    },
    {
      "epoch": 0.2545454545454545,
      "grad_norm": 0.6159828901290894,
      "learning_rate": 0.0002794884721436361,
      "loss": 3.7742,
      "step": 42
    },
    {
      "epoch": 0.2606060606060606,
      "grad_norm": 0.68132483959198,
      "learning_rate": 0.00027821890688783083,
      "loss": 4.0241,
      "step": 43
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.5653589963912964,
      "learning_rate": 0.0002769142878631403,
      "loss": 3.7525,
      "step": 44
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.9037842750549316,
      "learning_rate": 0.00027557497173937923,
      "loss": 3.4875,
      "step": 45
    },
    {
      "epoch": 0.2787878787878788,
      "grad_norm": 0.5621453523635864,
      "learning_rate": 0.000274201324672203,
      "loss": 3.5225,
      "step": 46
    },
    {
      "epoch": 0.28484848484848485,
      "grad_norm": 0.49410945177078247,
      "learning_rate": 0.00027279372220300385,
      "loss": 3.5886,
      "step": 47
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": 0.5745173096656799,
      "learning_rate": 0.0002713525491562421,
      "loss": 3.8441,
      "step": 48
    },
    {
      "epoch": 0.296969696969697,
      "grad_norm": 0.44604888558387756,
      "learning_rate": 0.00026987819953423867,
      "loss": 4.2,
      "step": 49
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 0.5468507409095764,
      "learning_rate": 0.00026837107640945905,
      "loss": 4.3589,
      "step": 50
    },
    {
      "epoch": 0.30303030303030304,
      "eval_loss": 1.0433467626571655,
      "eval_runtime": 8.8148,
      "eval_samples_per_second": 5.672,
      "eval_steps_per_second": 0.794,
      "step": 50
    },
    {
      "epoch": 0.3090909090909091,
      "grad_norm": 0.5188127160072327,
      "learning_rate": 0.0002668315918143169,
      "loss": 4.7106,
      "step": 51
    },
    {
      "epoch": 0.3151515151515151,
      "grad_norm": 0.6510715484619141,
      "learning_rate": 0.00026526016662852886,
      "loss": 4.5007,
      "step": 52
    },
    {
      "epoch": 0.3212121212121212,
      "grad_norm": 0.4716251492500305,
      "learning_rate": 0.00026365723046405023,
      "loss": 4.7915,
      "step": 53
    },
    {
      "epoch": 0.32727272727272727,
      "grad_norm": 0.5564483404159546,
      "learning_rate": 0.0002620232215476231,
      "loss": 4.9668,
      "step": 54
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.4775807559490204,
      "learning_rate": 0.0002603585866009697,
      "loss": 4.5621,
      "step": 55
    },
    {
      "epoch": 0.3393939393939394,
      "grad_norm": 0.5238752961158752,
      "learning_rate": 0.00025866378071866334,
      "loss": 4.4043,
      "step": 56
    },
    {
      "epoch": 0.34545454545454546,
      "grad_norm": 1.0805952548980713,
      "learning_rate": 0.00025693926724370956,
      "loss": 4.2704,
      "step": 57
    },
    {
      "epoch": 0.3515151515151515,
      "grad_norm": 1.3409287929534912,
      "learning_rate": 0.00025518551764087326,
      "loss": 3.6826,
      "step": 58
    },
    {
      "epoch": 0.3575757575757576,
      "grad_norm": 1.1066865921020508,
      "learning_rate": 0.00025340301136778483,
      "loss": 3.5727,
      "step": 59
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 1.2089401483535767,
      "learning_rate": 0.00025159223574386114,
      "loss": 3.7346,
      "step": 60
    },
    {
      "epoch": 0.3696969696969697,
      "grad_norm": 1.174935221672058,
      "learning_rate": 0.0002497536858170772,
      "loss": 4.0991,
      "step": 61
    },
    {
      "epoch": 0.37575757575757573,
      "grad_norm": 1.0671157836914062,
      "learning_rate": 0.00024788786422862526,
      "loss": 4.0129,
      "step": 62
    },
    {
      "epoch": 0.38181818181818183,
      "grad_norm": 1.153749942779541,
      "learning_rate": 0.00024599528107549745,
      "loss": 3.7239,
      "step": 63
    },
    {
      "epoch": 0.3878787878787879,
      "grad_norm": 1.122606635093689,
      "learning_rate": 0.00024407645377103054,
      "loss": 3.7086,
      "step": 64
    },
    {
      "epoch": 0.3939393939393939,
      "grad_norm": 1.0730392932891846,
      "learning_rate": 0.00024213190690345018,
      "loss": 3.9138,
      "step": 65
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.1631901264190674,
      "learning_rate": 0.00024016217209245374,
      "loss": 4.1343,
      "step": 66
    },
    {
      "epoch": 0.40606060606060607,
      "grad_norm": 1.2196776866912842,
      "learning_rate": 0.00023816778784387094,
      "loss": 3.5967,
      "step": 67
    },
    {
      "epoch": 0.4121212121212121,
      "grad_norm": 1.195727825164795,
      "learning_rate": 0.0002361492994024415,
      "loss": 3.8869,
      "step": 68
    },
    {
      "epoch": 0.41818181818181815,
      "grad_norm": 1.1967164278030396,
      "learning_rate": 0.0002341072586027509,
      "loss": 3.9028,
      "step": 69
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 1.1707066297531128,
      "learning_rate": 0.00023204222371836405,
      "loss": 4.0078,
      "step": 70
    },
    {
      "epoch": 0.4303030303030303,
      "grad_norm": 1.1968343257904053,
      "learning_rate": 0.00022995475930919905,
      "loss": 3.8004,
      "step": 71
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 1.2005783319473267,
      "learning_rate": 0.00022784543606718227,
      "loss": 3.8738,
      "step": 72
    },
    {
      "epoch": 0.44242424242424244,
      "grad_norm": 1.1619346141815186,
      "learning_rate": 0.00022571483066022657,
      "loss": 3.5391,
      "step": 73
    },
    {
      "epoch": 0.4484848484848485,
      "grad_norm": 1.1371430158615112,
      "learning_rate": 0.0002235635255745762,
      "loss": 3.7221,
      "step": 74
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 1.3344109058380127,
      "learning_rate": 0.00022139210895556104,
      "loss": 4.469,
      "step": 75
    },
    {
      "epoch": 0.45454545454545453,
      "eval_loss": 1.0359444618225098,
      "eval_runtime": 8.8102,
      "eval_samples_per_second": 5.675,
      "eval_steps_per_second": 0.795,
      "step": 75
    },
    {
      "epoch": 0.46060606060606063,
      "grad_norm": 1.2577054500579834,
      "learning_rate": 0.00021920117444680317,
      "loss": 3.7,
      "step": 76
    },
    {
      "epoch": 0.4666666666666667,
      "grad_norm": 1.3546791076660156,
      "learning_rate": 0.00021699132102792097,
      "loss": 4.0149,
      "step": 77
    },
    {
      "epoch": 0.4727272727272727,
      "grad_norm": 1.242742657661438,
      "learning_rate": 0.0002147631528507739,
      "loss": 4.1827,
      "step": 78
    },
    {
      "epoch": 0.47878787878787876,
      "grad_norm": 1.360210657119751,
      "learning_rate": 0.00021251727907429355,
      "loss": 4.3523,
      "step": 79
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 1.2846087217330933,
      "learning_rate": 0.0002102543136979454,
      "loss": 4.1916,
      "step": 80
    },
    {
      "epoch": 0.4909090909090909,
      "grad_norm": 1.4472957849502563,
      "learning_rate": 0.0002079748753938678,
      "loss": 4.4552,
      "step": 81
    },
    {
      "epoch": 0.49696969696969695,
      "grad_norm": 5.005261421203613,
      "learning_rate": 0.0002056795873377331,
      "loss": 5.966,
      "step": 82
    },
    {
      "epoch": 0.503030303030303,
      "grad_norm": 1.1476707458496094,
      "learning_rate": 0.00020336907703837748,
      "loss": 3.5971,
      "step": 83
    },
    {
      "epoch": 0.509090909090909,
      "grad_norm": 0.804432213306427,
      "learning_rate": 0.00020104397616624645,
      "loss": 3.0387,
      "step": 84
    },
    {
      "epoch": 0.5151515151515151,
      "grad_norm": 0.8131891489028931,
      "learning_rate": 0.00019870492038070252,
      "loss": 2.9173,
      "step": 85
    },
    {
      "epoch": 0.5212121212121212,
      "grad_norm": 1.010606050491333,
      "learning_rate": 0.0001963525491562421,
      "loss": 2.8759,
      "step": 86
    },
    {
      "epoch": 0.5272727272727272,
      "grad_norm": 0.8777551651000977,
      "learning_rate": 0.0001939875056076697,
      "loss": 3.594,
      "step": 87
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.5638920664787292,
      "learning_rate": 0.00019161043631427666,
      "loss": 3.623,
      "step": 88
    },
    {
      "epoch": 0.5393939393939394,
      "grad_norm": 0.514066755771637,
      "learning_rate": 0.00018922199114307294,
      "loss": 3.8677,
      "step": 89
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.5469452142715454,
      "learning_rate": 0.00018682282307111987,
      "loss": 4.0559,
      "step": 90
    },
    {
      "epoch": 0.5515151515151515,
      "grad_norm": 0.5149753093719482,
      "learning_rate": 0.00018441358800701273,
      "loss": 4.2973,
      "step": 91
    },
    {
      "epoch": 0.5575757575757576,
      "grad_norm": 0.5648798942565918,
      "learning_rate": 0.00018199494461156203,
      "loss": 4.7064,
      "step": 92
    },
    {
      "epoch": 0.5636363636363636,
      "grad_norm": 0.5099785923957825,
      "learning_rate": 0.000179567554117722,
      "loss": 4.3301,
      "step": 93
    },
    {
      "epoch": 0.5696969696969697,
      "grad_norm": 0.48161858320236206,
      "learning_rate": 0.00017713208014981648,
      "loss": 4.7289,
      "step": 94
    },
    {
      "epoch": 0.5757575757575758,
      "grad_norm": 0.5203522443771362,
      "learning_rate": 0.00017468918854211007,
      "loss": 4.6148,
      "step": 95
    },
    {
      "epoch": 0.5818181818181818,
      "grad_norm": 0.5482717156410217,
      "learning_rate": 0.00017223954715677627,
      "loss": 4.4521,
      "step": 96
    },
    {
      "epoch": 0.5878787878787879,
      "grad_norm": 1.1732290983200073,
      "learning_rate": 0.00016978382570131034,
      "loss": 4.1579,
      "step": 97
    },
    {
      "epoch": 0.593939393939394,
      "grad_norm": 0.9861870408058167,
      "learning_rate": 0.00016732269554543794,
      "loss": 3.9791,
      "step": 98
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.9701457023620605,
      "learning_rate": 0.00016485682953756942,
      "loss": 4.0135,
      "step": 99
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 1.2375657558441162,
      "learning_rate": 0.00016238690182084986,
      "loss": 3.7663,
      "step": 100
    },
    {
      "epoch": 0.6060606060606061,
      "eval_loss": 0.9876666069030762,
      "eval_runtime": 8.8168,
      "eval_samples_per_second": 5.671,
      "eval_steps_per_second": 0.794,
      "step": 100
    },
    {
      "epoch": 0.6121212121212121,
      "grad_norm": 1.087836503982544,
      "learning_rate": 0.0001599135876488549,
      "loss": 3.5446,
      "step": 101
    },
    {
      "epoch": 0.6181818181818182,
      "grad_norm": 1.0186785459518433,
      "learning_rate": 0.00015743756320098332,
      "loss": 4.3509,
      "step": 102
    },
    {
      "epoch": 0.6242424242424243,
      "grad_norm": 1.0360673666000366,
      "learning_rate": 0.0001549595053975962,
      "loss": 3.8389,
      "step": 103
    },
    {
      "epoch": 0.6303030303030303,
      "grad_norm": 1.106460690498352,
      "learning_rate": 0.00015248009171495378,
      "loss": 3.6617,
      "step": 104
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 1.2066973447799683,
      "learning_rate": 0.00015,
      "loss": 3.4257,
      "step": 105
    },
    {
      "epoch": 0.6424242424242425,
      "grad_norm": 1.3430566787719727,
      "learning_rate": 0.00014751990828504622,
      "loss": 3.6877,
      "step": 106
    },
    {
      "epoch": 0.6484848484848484,
      "grad_norm": 1.2599773406982422,
      "learning_rate": 0.00014504049460240375,
      "loss": 4.1472,
      "step": 107
    },
    {
      "epoch": 0.6545454545454545,
      "grad_norm": 1.4013822078704834,
      "learning_rate": 0.00014256243679901663,
      "loss": 3.7716,
      "step": 108
    },
    {
      "epoch": 0.6606060606060606,
      "grad_norm": 1.6531068086624146,
      "learning_rate": 0.00014008641235114508,
      "loss": 3.8997,
      "step": 109
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.2556439638137817,
      "learning_rate": 0.00013761309817915014,
      "loss": 3.4263,
      "step": 110
    },
    {
      "epoch": 0.6727272727272727,
      "grad_norm": 1.1586471796035767,
      "learning_rate": 0.00013514317046243058,
      "loss": 3.9411,
      "step": 111
    },
    {
      "epoch": 0.6787878787878788,
      "grad_norm": 1.1945208311080933,
      "learning_rate": 0.00013267730445456208,
      "loss": 3.8398,
      "step": 112
    },
    {
      "epoch": 0.6848484848484848,
      "grad_norm": 1.3857640027999878,
      "learning_rate": 0.00013021617429868963,
      "loss": 3.4325,
      "step": 113
    },
    {
      "epoch": 0.6909090909090909,
      "grad_norm": 1.3398420810699463,
      "learning_rate": 0.00012776045284322368,
      "loss": 3.75,
      "step": 114
    },
    {
      "epoch": 0.696969696969697,
      "grad_norm": 1.5814698934555054,
      "learning_rate": 0.00012531081145788987,
      "loss": 3.8676,
      "step": 115
    },
    {
      "epoch": 0.703030303030303,
      "grad_norm": 1.3087879419326782,
      "learning_rate": 0.00012286791985018355,
      "loss": 3.8505,
      "step": 116
    },
    {
      "epoch": 0.7090909090909091,
      "grad_norm": 1.168992280960083,
      "learning_rate": 0.00012043244588227796,
      "loss": 3.4915,
      "step": 117
    },
    {
      "epoch": 0.7151515151515152,
      "grad_norm": 1.402132511138916,
      "learning_rate": 0.00011800505538843798,
      "loss": 4.2502,
      "step": 118
    },
    {
      "epoch": 0.7212121212121212,
      "grad_norm": 1.338773250579834,
      "learning_rate": 0.00011558641199298727,
      "loss": 4.3477,
      "step": 119
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 1.3770555257797241,
      "learning_rate": 0.00011317717692888012,
      "loss": 4.0962,
      "step": 120
    },
    {
      "epoch": 0.7333333333333333,
      "grad_norm": 1.5494691133499146,
      "learning_rate": 0.00011077800885692702,
      "loss": 4.1531,
      "step": 121
    },
    {
      "epoch": 0.7393939393939394,
      "grad_norm": 1.306699275970459,
      "learning_rate": 0.00010838956368572334,
      "loss": 3.9953,
      "step": 122
    },
    {
      "epoch": 0.7454545454545455,
      "grad_norm": 6.255343914031982,
      "learning_rate": 0.0001060124943923303,
      "loss": 5.1458,
      "step": 123
    },
    {
      "epoch": 0.7515151515151515,
      "grad_norm": 0.7911396026611328,
      "learning_rate": 0.0001036474508437579,
      "loss": 2.3816,
      "step": 124
    },
    {
      "epoch": 0.7575757575757576,
      "grad_norm": 0.829796314239502,
      "learning_rate": 0.00010129507961929748,
      "loss": 2.5348,
      "step": 125
    },
    {
      "epoch": 0.7575757575757576,
      "eval_loss": 0.9475884437561035,
      "eval_runtime": 8.8169,
      "eval_samples_per_second": 5.671,
      "eval_steps_per_second": 0.794,
      "step": 125
    },
    {
      "epoch": 0.7636363636363637,
      "grad_norm": 0.708293080329895,
      "learning_rate": 9.895602383375353e-05,
      "loss": 2.2235,
      "step": 126
    },
    {
      "epoch": 0.7696969696969697,
      "grad_norm": 0.834475576877594,
      "learning_rate": 9.663092296162251e-05,
      "loss": 2.9316,
      "step": 127
    },
    {
      "epoch": 0.7757575757575758,
      "grad_norm": 0.5371659994125366,
      "learning_rate": 9.432041266226686e-05,
      "loss": 2.9679,
      "step": 128
    },
    {
      "epoch": 0.7818181818181819,
      "grad_norm": 0.6697002053260803,
      "learning_rate": 9.202512460613219e-05,
      "loss": 3.8351,
      "step": 129
    },
    {
      "epoch": 0.7878787878787878,
      "grad_norm": 0.6024027466773987,
      "learning_rate": 8.97456863020546e-05,
      "loss": 4.0773,
      "step": 130
    },
    {
      "epoch": 0.793939393939394,
      "grad_norm": 0.5722142457962036,
      "learning_rate": 8.748272092570646e-05,
      "loss": 4.4074,
      "step": 131
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.5958192944526672,
      "learning_rate": 8.523684714922608e-05,
      "loss": 4.657,
      "step": 132
    },
    {
      "epoch": 0.806060606060606,
      "grad_norm": 0.5286346077919006,
      "learning_rate": 8.300867897207903e-05,
      "loss": 3.7848,
      "step": 133
    },
    {
      "epoch": 0.8121212121212121,
      "grad_norm": 0.5522734522819519,
      "learning_rate": 8.079882555319684e-05,
      "loss": 4.7628,
      "step": 134
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.5736743807792664,
      "learning_rate": 7.860789104443896e-05,
      "loss": 4.6601,
      "step": 135
    },
    {
      "epoch": 0.8242424242424242,
      "grad_norm": 0.4430980384349823,
      "learning_rate": 7.643647442542382e-05,
      "loss": 4.655,
      "step": 136
    },
    {
      "epoch": 0.8303030303030303,
      "grad_norm": 0.5080361366271973,
      "learning_rate": 7.428516933977347e-05,
      "loss": 4.5731,
      "step": 137
    },
    {
      "epoch": 0.8363636363636363,
      "grad_norm": 0.7352221608161926,
      "learning_rate": 7.215456393281776e-05,
      "loss": 4.3219,
      "step": 138
    },
    {
      "epoch": 0.8424242424242424,
      "grad_norm": 1.1054418087005615,
      "learning_rate": 7.004524069080096e-05,
      "loss": 3.4271,
      "step": 139
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 1.1359199285507202,
      "learning_rate": 6.795777628163599e-05,
      "loss": 3.4999,
      "step": 140
    },
    {
      "epoch": 0.8545454545454545,
      "grad_norm": 1.0794568061828613,
      "learning_rate": 6.58927413972491e-05,
      "loss": 3.5732,
      "step": 141
    },
    {
      "epoch": 0.8606060606060606,
      "grad_norm": 1.0967761278152466,
      "learning_rate": 6.385070059755846e-05,
      "loss": 3.3325,
      "step": 142
    },
    {
      "epoch": 0.8666666666666667,
      "grad_norm": 1.059601902961731,
      "learning_rate": 6.183221215612904e-05,
      "loss": 3.3545,
      "step": 143
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": 1.0655397176742554,
      "learning_rate": 5.983782790754623e-05,
      "loss": 3.8531,
      "step": 144
    },
    {
      "epoch": 0.8787878787878788,
      "grad_norm": 1.1529344320297241,
      "learning_rate": 5.786809309654982e-05,
      "loss": 3.737,
      "step": 145
    },
    {
      "epoch": 0.8848484848484849,
      "grad_norm": 1.377535343170166,
      "learning_rate": 5.592354622896944e-05,
      "loss": 4.1927,
      "step": 146
    },
    {
      "epoch": 0.8909090909090909,
      "grad_norm": 1.2239060401916504,
      "learning_rate": 5.40047189245025e-05,
      "loss": 3.6735,
      "step": 147
    },
    {
      "epoch": 0.896969696969697,
      "grad_norm": 1.1639585494995117,
      "learning_rate": 5.211213577137469e-05,
      "loss": 3.3595,
      "step": 148
    },
    {
      "epoch": 0.9030303030303031,
      "grad_norm": 1.2083743810653687,
      "learning_rate": 5.024631418292274e-05,
      "loss": 3.6973,
      "step": 149
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 1.2493572235107422,
      "learning_rate": 4.840776425613886e-05,
      "loss": 3.6517,
      "step": 150
    },
    {
      "epoch": 0.9090909090909091,
      "eval_loss": 0.9506127238273621,
      "eval_runtime": 8.8109,
      "eval_samples_per_second": 5.675,
      "eval_steps_per_second": 0.794,
      "step": 150
    },
    {
      "epoch": 0.9151515151515152,
      "grad_norm": 1.1755346059799194,
      "learning_rate": 4.659698863221513e-05,
      "loss": 3.6364,
      "step": 151
    },
    {
      "epoch": 0.9212121212121213,
      "grad_norm": 1.2692265510559082,
      "learning_rate": 4.481448235912671e-05,
      "loss": 3.727,
      "step": 152
    },
    {
      "epoch": 0.9272727272727272,
      "grad_norm": 1.140787959098816,
      "learning_rate": 4.306073275629044e-05,
      "loss": 3.6425,
      "step": 153
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 1.1743643283843994,
      "learning_rate": 4.133621928133665e-05,
      "loss": 4.3752,
      "step": 154
    },
    {
      "epoch": 0.9393939393939394,
      "grad_norm": 1.1625086069107056,
      "learning_rate": 3.964141339903026e-05,
      "loss": 3.5581,
      "step": 155
    },
    {
      "epoch": 0.9454545454545454,
      "grad_norm": 1.2037782669067383,
      "learning_rate": 3.797677845237696e-05,
      "loss": 3.9433,
      "step": 156
    },
    {
      "epoch": 0.9515151515151515,
      "grad_norm": 1.213274598121643,
      "learning_rate": 3.634276953594982e-05,
      "loss": 4.0385,
      "step": 157
    },
    {
      "epoch": 0.9575757575757575,
      "grad_norm": 1.2573509216308594,
      "learning_rate": 3.473983337147118e-05,
      "loss": 3.9195,
      "step": 158
    },
    {
      "epoch": 0.9636363636363636,
      "grad_norm": 1.1490145921707153,
      "learning_rate": 3.316840818568315e-05,
      "loss": 3.9835,
      "step": 159
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 1.2340681552886963,
      "learning_rate": 3.162892359054098e-05,
      "loss": 3.8201,
      "step": 160
    },
    {
      "epoch": 0.9757575757575757,
      "grad_norm": 1.6921660900115967,
      "learning_rate": 3.0121800465761293e-05,
      "loss": 4.168,
      "step": 161
    },
    {
      "epoch": 0.9818181818181818,
      "grad_norm": 1.3426408767700195,
      "learning_rate": 2.8647450843757897e-05,
      "loss": 4.4568,
      "step": 162
    },
    {
      "epoch": 0.9878787878787879,
      "grad_norm": 1.1291062831878662,
      "learning_rate": 2.7206277796996144e-05,
      "loss": 2.9587,
      "step": 163
    },
    {
      "epoch": 0.9939393939393939,
      "grad_norm": 5.067478179931641,
      "learning_rate": 2.5798675327796993e-05,
      "loss": 5.7136,
      "step": 164
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.9252928495407104,
      "learning_rate": 2.4425028260620715e-05,
      "loss": 3.5246,
      "step": 165
    },
    {
      "epoch": 1.006060606060606,
      "grad_norm": 0.745075523853302,
      "learning_rate": 2.3085712136859668e-05,
      "loss": 2.1109,
      "step": 166
    },
    {
      "epoch": 1.0121212121212122,
      "grad_norm": 0.7394888997077942,
      "learning_rate": 2.178109311216913e-05,
      "loss": 2.4167,
      "step": 167
    },
    {
      "epoch": 1.018181818181818,
      "grad_norm": 0.7494075894355774,
      "learning_rate": 2.0511527856363912e-05,
      "loss": 2.0683,
      "step": 168
    },
    {
      "epoch": 1.0242424242424242,
      "grad_norm": 0.4794514775276184,
      "learning_rate": 1.927736345590839e-05,
      "loss": 2.6452,
      "step": 169
    },
    {
      "epoch": 1.0303030303030303,
      "grad_norm": 0.5055110454559326,
      "learning_rate": 1.8078937319026654e-05,
      "loss": 3.154,
      "step": 170
    },
    {
      "epoch": 1.0363636363636364,
      "grad_norm": 0.43595442175865173,
      "learning_rate": 1.6916577083458228e-05,
      "loss": 3.5276,
      "step": 171
    },
    {
      "epoch": 1.0424242424242425,
      "grad_norm": 0.4404388666152954,
      "learning_rate": 1.579060052688548e-05,
      "loss": 3.8259,
      "step": 172
    },
    {
      "epoch": 1.0484848484848486,
      "grad_norm": 0.4553149342536926,
      "learning_rate": 1.4701315480056164e-05,
      "loss": 3.9166,
      "step": 173
    },
    {
      "epoch": 1.0545454545454545,
      "grad_norm": 0.5771802663803101,
      "learning_rate": 1.3649019742625623e-05,
      "loss": 3.8935,
      "step": 174
    },
    {
      "epoch": 1.0606060606060606,
      "grad_norm": 0.4853135645389557,
      "learning_rate": 1.2634001001741373e-05,
      "loss": 4.3058,
      "step": 175
    },
    {
      "epoch": 1.0606060606060606,
      "eval_loss": 0.929128110408783,
      "eval_runtime": 8.8122,
      "eval_samples_per_second": 5.674,
      "eval_steps_per_second": 0.794,
      "step": 175
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.4742906987667084,
      "learning_rate": 1.1656536753392287e-05,
      "loss": 4.0653,
      "step": 176
    },
    {
      "epoch": 1.0727272727272728,
      "grad_norm": 0.4662216901779175,
      "learning_rate": 1.0716894226543953e-05,
      "loss": 4.6002,
      "step": 177
    },
    {
      "epoch": 1.0787878787878789,
      "grad_norm": 0.4336952865123749,
      "learning_rate": 9.815330310080887e-06,
      "loss": 4.5435,
      "step": 178
    },
    {
      "epoch": 1.084848484848485,
      "grad_norm": 0.472969114780426,
      "learning_rate": 8.952091482575824e-06,
      "loss": 4.2765,
      "step": 179
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.5912119150161743,
      "learning_rate": 8.127413744904804e-06,
      "loss": 3.6061,
      "step": 180
    },
    {
      "epoch": 1.096969696969697,
      "grad_norm": 0.8748385906219482,
      "learning_rate": 7.34152255572697e-06,
      "loss": 3.612,
      "step": 181
    },
    {
      "epoch": 1.103030303030303,
      "grad_norm": 0.7963136434555054,
      "learning_rate": 6.594632769846353e-06,
      "loss": 2.6961,
      "step": 182
    },
    {
      "epoch": 1.1090909090909091,
      "grad_norm": 1.059278964996338,
      "learning_rate": 5.886948579472778e-06,
      "loss": 2.7539,
      "step": 183
    },
    {
      "epoch": 1.1151515151515152,
      "grad_norm": 0.8208073377609253,
      "learning_rate": 5.218663458397715e-06,
      "loss": 3.0603,
      "step": 184
    },
    {
      "epoch": 1.121212121212121,
      "grad_norm": 0.8458943963050842,
      "learning_rate": 4.589960109100444e-06,
      "loss": 2.9592,
      "step": 185
    },
    {
      "epoch": 1.1272727272727272,
      "grad_norm": 0.8511922359466553,
      "learning_rate": 4.001010412799138e-06,
      "loss": 3.3705,
      "step": 186
    },
    {
      "epoch": 1.1333333333333333,
      "grad_norm": 0.8590157628059387,
      "learning_rate": 3.451975382460109e-06,
      "loss": 2.7145,
      "step": 187
    },
    {
      "epoch": 1.1393939393939394,
      "grad_norm": 0.862501859664917,
      "learning_rate": 2.9430051187785962e-06,
      "loss": 3.4529,
      "step": 188
    },
    {
      "epoch": 1.1454545454545455,
      "grad_norm": 0.8538833856582642,
      "learning_rate": 2.4742387691426445e-06,
      "loss": 3.336,
      "step": 189
    },
    {
      "epoch": 1.1515151515151516,
      "grad_norm": 1.0022493600845337,
      "learning_rate": 2.0458044895916513e-06,
      "loss": 2.8941,
      "step": 190
    },
    {
      "epoch": 1.1575757575757575,
      "grad_norm": 1.0205844640731812,
      "learning_rate": 1.6578194097797258e-06,
      "loss": 2.904,
      "step": 191
    },
    {
      "epoch": 1.1636363636363636,
      "grad_norm": 1.2487444877624512,
      "learning_rate": 1.3103896009537207e-06,
      "loss": 2.4457,
      "step": 192
    },
    {
      "epoch": 1.1696969696969697,
      "grad_norm": 1.0014578104019165,
      "learning_rate": 1.0036100469542786e-06,
      "loss": 2.9078,
      "step": 193
    },
    {
      "epoch": 1.1757575757575758,
      "grad_norm": 0.9595588445663452,
      "learning_rate": 7.375646182482875e-07,
      "loss": 2.9862,
      "step": 194
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 0.959829568862915,
      "learning_rate": 5.123260489995229e-07,
      "loss": 3.4768,
      "step": 195
    },
    {
      "epoch": 1.187878787878788,
      "grad_norm": 1.1415780782699585,
      "learning_rate": 3.2795591718381975e-07,
      "loss": 2.9397,
      "step": 196
    },
    {
      "epoch": 1.1939393939393939,
      "grad_norm": 1.0246975421905518,
      "learning_rate": 1.8450462775428942e-07,
      "loss": 3.4324,
      "step": 197
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.1691887378692627,
      "learning_rate": 8.201139886109264e-08,
      "loss": 2.9577,
      "step": 198
    },
    {
      "epoch": 1.206060606060606,
      "grad_norm": 1.4010579586029053,
      "learning_rate": 2.0504251129649374e-08,
      "loss": 3.0046,
      "step": 199
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 0.9462568759918213,
      "learning_rate": 0.0,
      "loss": 3.2705,
      "step": 200
    },
    {
      "epoch": 1.2121212121212122,
      "eval_loss": 0.9298770427703857,
      "eval_runtime": 8.8168,
      "eval_samples_per_second": 5.671,
      "eval_steps_per_second": 0.794,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 5.78625695465472e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}