{
  "best_metric": 11.739458084106445,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.4480955937266617,
  "eval_steps": 25,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002987303958177745,
      "grad_norm": 0.050279781222343445,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 11.7651,
      "step": 1
    },
    {
      "epoch": 0.002987303958177745,
      "eval_loss": 11.768967628479004,
      "eval_runtime": 0.2337,
      "eval_samples_per_second": 213.923,
      "eval_steps_per_second": 29.949,
      "step": 1
    },
    {
      "epoch": 0.00597460791635549,
      "grad_norm": 0.04214675724506378,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 11.7627,
      "step": 2
    },
    {
      "epoch": 0.008961911874533234,
      "grad_norm": 0.03950486704707146,
      "learning_rate": 8.999999999999999e-05,
      "loss": 11.7646,
      "step": 3
    },
    {
      "epoch": 0.01194921583271098,
      "grad_norm": 0.039772190153598785,
      "learning_rate": 0.00011999999999999999,
      "loss": 11.7649,
      "step": 4
    },
    {
      "epoch": 0.014936519790888723,
      "grad_norm": 0.05151067301630974,
      "learning_rate": 0.00015,
      "loss": 11.7684,
      "step": 5
    },
    {
      "epoch": 0.017923823749066467,
      "grad_norm": 0.04411710798740387,
      "learning_rate": 0.00017999999999999998,
      "loss": 11.765,
      "step": 6
    },
    {
      "epoch": 0.020911127707244213,
      "grad_norm": 0.04754095524549484,
      "learning_rate": 0.00020999999999999998,
      "loss": 11.761,
      "step": 7
    },
    {
      "epoch": 0.02389843166542196,
      "grad_norm": 0.04582458361983299,
      "learning_rate": 0.00023999999999999998,
      "loss": 11.7646,
      "step": 8
    },
    {
      "epoch": 0.0268857356235997,
      "grad_norm": 0.05337909236550331,
      "learning_rate": 0.00027,
      "loss": 11.7618,
      "step": 9
    },
    {
      "epoch": 0.029873039581777446,
      "grad_norm": 0.03585939109325409,
      "learning_rate": 0.0003,
      "loss": 11.7668,
      "step": 10
    },
    {
      "epoch": 0.03286034353995519,
      "grad_norm": 0.05732989311218262,
      "learning_rate": 0.0002999794957488703,
      "loss": 11.7637,
      "step": 11
    },
    {
      "epoch": 0.035847647498132934,
      "grad_norm": 0.05058005452156067,
      "learning_rate": 0.0002999179886011389,
      "loss": 11.761,
      "step": 12
    },
    {
      "epoch": 0.038834951456310676,
      "grad_norm": 0.060499612241983414,
      "learning_rate": 0.0002998154953722457,
      "loss": 11.7666,
      "step": 13
    },
    {
      "epoch": 0.041822255414488425,
      "grad_norm": 0.05672263726592064,
      "learning_rate": 0.00029967204408281613,
      "loss": 11.7624,
      "step": 14
    },
    {
      "epoch": 0.04480955937266617,
      "grad_norm": 0.06420541554689407,
      "learning_rate": 0.00029948767395100045,
      "loss": 11.7663,
      "step": 15
    },
    {
      "epoch": 0.04779686333084392,
      "grad_norm": 0.05906285345554352,
      "learning_rate": 0.0002992624353817517,
      "loss": 11.7607,
      "step": 16
    },
    {
      "epoch": 0.05078416728902166,
      "grad_norm": 0.07341849058866501,
      "learning_rate": 0.0002989963899530457,
      "loss": 11.7604,
      "step": 17
    },
    {
      "epoch": 0.0537714712471994,
      "grad_norm": 0.054468028247356415,
      "learning_rate": 0.00029868961039904624,
      "loss": 11.7631,
      "step": 18
    },
    {
      "epoch": 0.05675877520537715,
      "grad_norm": 0.08134905993938446,
      "learning_rate": 0.00029834218059022024,
      "loss": 11.762,
      "step": 19
    },
    {
      "epoch": 0.05974607916355489,
      "grad_norm": 0.07785852998495102,
      "learning_rate": 0.00029795419551040833,
      "loss": 11.7655,
      "step": 20
    },
    {
      "epoch": 0.06273338312173264,
      "grad_norm": 0.0745876133441925,
      "learning_rate": 0.00029752576123085736,
      "loss": 11.7585,
      "step": 21
    },
    {
      "epoch": 0.06572068707991038,
      "grad_norm": 0.08235619217157364,
      "learning_rate": 0.0002970569948812214,
      "loss": 11.7613,
      "step": 22
    },
    {
      "epoch": 0.06870799103808813,
      "grad_norm": 0.12161055207252502,
      "learning_rate": 0.0002965480246175399,
      "loss": 11.7645,
      "step": 23
    },
    {
      "epoch": 0.07169529499626587,
      "grad_norm": 0.10470264405012131,
      "learning_rate": 0.0002959989895872009,
      "loss": 11.7589,
      "step": 24
    },
    {
      "epoch": 0.07468259895444361,
      "grad_norm": 0.1003669872879982,
      "learning_rate": 0.0002954100398908995,
      "loss": 11.7509,
      "step": 25
    },
    {
      "epoch": 0.07468259895444361,
      "eval_loss": 11.760871887207031,
      "eval_runtime": 0.2345,
      "eval_samples_per_second": 213.203,
      "eval_steps_per_second": 29.848,
      "step": 25
    },
    {
      "epoch": 0.07766990291262135,
      "grad_norm": 0.1197424978017807,
      "learning_rate": 0.0002947813365416023,
      "loss": 11.7523,
      "step": 26
    },
    {
      "epoch": 0.08065720687079911,
      "grad_norm": 0.13335414230823517,
      "learning_rate": 0.0002941130514205272,
      "loss": 11.7591,
      "step": 27
    },
    {
      "epoch": 0.08364451082897685,
      "grad_norm": 0.12114610522985458,
      "learning_rate": 0.0002934053672301536,
      "loss": 11.7516,
      "step": 28
    },
    {
      "epoch": 0.08663181478715459,
      "grad_norm": 0.12356773018836975,
      "learning_rate": 0.00029265847744427303,
      "loss": 11.7526,
      "step": 29
    },
    {
      "epoch": 0.08961911874533234,
      "grad_norm": 0.13285435736179352,
      "learning_rate": 0.00029187258625509513,
      "loss": 11.7537,
      "step": 30
    },
    {
      "epoch": 0.09260642270351008,
      "grad_norm": 0.13829363882541656,
      "learning_rate": 0.00029104790851742417,
      "loss": 11.7502,
      "step": 31
    },
    {
      "epoch": 0.09559372666168783,
      "grad_norm": 0.17766043543815613,
      "learning_rate": 0.0002901846696899191,
      "loss": 11.7495,
      "step": 32
    },
    {
      "epoch": 0.09858103061986558,
      "grad_norm": 0.1606810837984085,
      "learning_rate": 0.00028928310577345606,
      "loss": 11.746,
      "step": 33
    },
    {
      "epoch": 0.10156833457804332,
      "grad_norm": 0.16132605075836182,
      "learning_rate": 0.0002883434632466077,
      "loss": 11.7532,
      "step": 34
    },
    {
      "epoch": 0.10455563853622106,
      "grad_norm": 0.1281188726425171,
      "learning_rate": 0.00028736599899825856,
      "loss": 11.7442,
      "step": 35
    },
    {
      "epoch": 0.1075429424943988,
      "grad_norm": 0.15466101467609406,
      "learning_rate": 0.00028635098025737434,
      "loss": 11.74,
      "step": 36
    },
    {
      "epoch": 0.11053024645257654,
      "grad_norm": 0.17401939630508423,
      "learning_rate": 0.00028529868451994384,
      "loss": 11.7439,
      "step": 37
    },
    {
      "epoch": 0.1135175504107543,
      "grad_norm": 0.15141968429088593,
      "learning_rate": 0.0002842093994731145,
      "loss": 11.7393,
      "step": 38
    },
    {
      "epoch": 0.11650485436893204,
      "grad_norm": 0.11766830831766129,
      "learning_rate": 0.00028308342291654174,
      "loss": 11.7396,
      "step": 39
    },
    {
      "epoch": 0.11949215832710978,
      "grad_norm": 0.13227562606334686,
      "learning_rate": 0.00028192106268097334,
      "loss": 11.7448,
      "step": 40
    },
    {
      "epoch": 0.12247946228528753,
      "grad_norm": 0.13436053693294525,
      "learning_rate": 0.00028072263654409154,
      "loss": 11.7376,
      "step": 41
    },
    {
      "epoch": 0.12546676624346528,
      "grad_norm": 0.13591481745243073,
      "learning_rate": 0.0002794884721436361,
      "loss": 11.7385,
      "step": 42
    },
    {
      "epoch": 0.128454070201643,
      "grad_norm": 0.12949644029140472,
      "learning_rate": 0.00027821890688783083,
      "loss": 11.7412,
      "step": 43
    },
    {
      "epoch": 0.13144137415982077,
      "grad_norm": 0.10022609680891037,
      "learning_rate": 0.0002769142878631403,
      "loss": 11.7423,
      "step": 44
    },
    {
      "epoch": 0.1344286781179985,
      "grad_norm": 0.10337765514850616,
      "learning_rate": 0.00027557497173937923,
      "loss": 11.7303,
      "step": 45
    },
    {
      "epoch": 0.13741598207617625,
      "grad_norm": 0.1025676354765892,
      "learning_rate": 0.000274201324672203,
      "loss": 11.7365,
      "step": 46
    },
    {
      "epoch": 0.140403286034354,
      "grad_norm": 0.07143431901931763,
      "learning_rate": 0.00027279372220300385,
      "loss": 11.7367,
      "step": 47
    },
    {
      "epoch": 0.14339058999253174,
      "grad_norm": 0.08283191174268723,
      "learning_rate": 0.0002713525491562421,
      "loss": 11.7324,
      "step": 48
    },
    {
      "epoch": 0.1463778939507095,
      "grad_norm": 0.0993882492184639,
      "learning_rate": 0.00026987819953423867,
      "loss": 11.737,
      "step": 49
    },
    {
      "epoch": 0.14936519790888722,
      "grad_norm": 0.08174671232700348,
      "learning_rate": 0.00026837107640945905,
      "loss": 11.7366,
      "step": 50
    },
    {
      "epoch": 0.14936519790888722,
      "eval_loss": 11.742301940917969,
      "eval_runtime": 0.2324,
      "eval_samples_per_second": 215.14,
      "eval_steps_per_second": 30.12,
      "step": 50
    },
    {
      "epoch": 0.15235250186706498,
      "grad_norm": 0.05863728001713753,
      "learning_rate": 0.0002668315918143169,
      "loss": 11.7427,
      "step": 51
    },
    {
      "epoch": 0.1553398058252427,
      "grad_norm": 0.08516336977481842,
      "learning_rate": 0.00026526016662852886,
      "loss": 11.737,
      "step": 52
    },
    {
      "epoch": 0.15832710978342046,
      "grad_norm": 0.07930774241685867,
      "learning_rate": 0.00026365723046405023,
      "loss": 11.7377,
      "step": 53
    },
    {
      "epoch": 0.16131441374159822,
      "grad_norm": 0.11191349476575851,
      "learning_rate": 0.0002620232215476231,
      "loss": 11.7357,
      "step": 54
    },
    {
      "epoch": 0.16430171769977595,
      "grad_norm": 0.0899188220500946,
      "learning_rate": 0.0002603585866009697,
      "loss": 11.7345,
      "step": 55
    },
    {
      "epoch": 0.1672890216579537,
      "grad_norm": 0.08646669238805771,
      "learning_rate": 0.00025866378071866334,
      "loss": 11.7354,
      "step": 56
    },
    {
      "epoch": 0.17027632561613143,
      "grad_norm": 0.07171917706727982,
      "learning_rate": 0.00025693926724370956,
      "loss": 11.7327,
      "step": 57
    },
    {
      "epoch": 0.17326362957430919,
      "grad_norm": 0.06329602003097534,
      "learning_rate": 0.00025518551764087326,
      "loss": 11.7374,
      "step": 58
    },
    {
      "epoch": 0.17625093353248694,
      "grad_norm": 0.061299942433834076,
      "learning_rate": 0.00025340301136778483,
      "loss": 11.7343,
      "step": 59
    },
    {
      "epoch": 0.17923823749066467,
      "grad_norm": 0.05308694764971733,
      "learning_rate": 0.00025159223574386114,
      "loss": 11.7311,
      "step": 60
    },
    {
      "epoch": 0.18222554144884243,
      "grad_norm": 0.06978456676006317,
      "learning_rate": 0.0002497536858170772,
      "loss": 11.7349,
      "step": 61
    },
    {
      "epoch": 0.18521284540702015,
      "grad_norm": 0.05760927125811577,
      "learning_rate": 0.00024788786422862526,
      "loss": 11.7355,
      "step": 62
    },
    {
      "epoch": 0.1882001493651979,
      "grad_norm": 0.09571195393800735,
      "learning_rate": 0.00024599528107549745,
      "loss": 11.7325,
      "step": 63
    },
    {
      "epoch": 0.19118745332337567,
      "grad_norm": 0.08274524658918381,
      "learning_rate": 0.00024407645377103054,
      "loss": 11.7321,
      "step": 64
    },
    {
      "epoch": 0.1941747572815534,
      "grad_norm": 0.0729244127869606,
      "learning_rate": 0.00024213190690345018,
      "loss": 11.7349,
      "step": 65
    },
    {
      "epoch": 0.19716206123973115,
      "grad_norm": 0.06066494062542915,
      "learning_rate": 0.00024016217209245374,
      "loss": 11.7288,
      "step": 66
    },
    {
      "epoch": 0.20014936519790888,
      "grad_norm": 0.05633550509810448,
      "learning_rate": 0.00023816778784387094,
      "loss": 11.7271,
      "step": 67
    },
    {
      "epoch": 0.20313666915608664,
      "grad_norm": 0.0472554937005043,
      "learning_rate": 0.0002361492994024415,
      "loss": 11.7314,
      "step": 68
    },
    {
      "epoch": 0.20612397311426436,
      "grad_norm": 0.05586111918091774,
      "learning_rate": 0.0002341072586027509,
      "loss": 11.7336,
      "step": 69
    },
    {
      "epoch": 0.20911127707244212,
      "grad_norm": 0.06293191015720367,
      "learning_rate": 0.00023204222371836405,
      "loss": 11.7356,
      "step": 70
    },
    {
      "epoch": 0.21209858103061988,
      "grad_norm": 0.05642852932214737,
      "learning_rate": 0.00022995475930919905,
      "loss": 11.7305,
      "step": 71
    },
    {
      "epoch": 0.2150858849887976,
      "grad_norm": 0.0764235407114029,
      "learning_rate": 0.00022784543606718227,
      "loss": 11.7305,
      "step": 72
    },
    {
      "epoch": 0.21807318894697536,
      "grad_norm": 0.07327850908041,
      "learning_rate": 0.00022571483066022657,
      "loss": 11.733,
      "step": 73
    },
    {
      "epoch": 0.2210604929051531,
      "grad_norm": 0.07356076687574387,
      "learning_rate": 0.0002235635255745762,
      "loss": 11.7303,
      "step": 74
    },
    {
      "epoch": 0.22404779686333084,
      "grad_norm": 0.07389409840106964,
      "learning_rate": 0.00022139210895556104,
      "loss": 11.7303,
      "step": 75
    },
    {
      "epoch": 0.22404779686333084,
      "eval_loss": 11.738842010498047,
      "eval_runtime": 0.2326,
      "eval_samples_per_second": 214.956,
      "eval_steps_per_second": 30.094,
      "step": 75
    },
    {
      "epoch": 0.2270351008215086,
      "grad_norm": 0.0627259910106659,
      "learning_rate": 0.00021920117444680317,
      "loss": 11.7321,
      "step": 76
    },
    {
      "epoch": 0.23002240477968633,
      "grad_norm": 0.054782044142484665,
      "learning_rate": 0.00021699132102792097,
      "loss": 11.7296,
      "step": 77
    },
    {
      "epoch": 0.23300970873786409,
      "grad_norm": 0.06865760684013367,
      "learning_rate": 0.0002147631528507739,
      "loss": 11.7302,
      "step": 78
    },
    {
      "epoch": 0.2359970126960418,
      "grad_norm": 0.04532450810074806,
      "learning_rate": 0.00021251727907429355,
      "loss": 11.7361,
      "step": 79
    },
    {
      "epoch": 0.23898431665421957,
      "grad_norm": 0.0644555389881134,
      "learning_rate": 0.0002102543136979454,
      "loss": 11.7367,
      "step": 80
    },
    {
      "epoch": 0.2419716206123973,
      "grad_norm": 0.05777858942747116,
      "learning_rate": 0.0002079748753938678,
      "loss": 11.7266,
      "step": 81
    },
    {
      "epoch": 0.24495892457057505,
      "grad_norm": 0.053388163447380066,
      "learning_rate": 0.0002056795873377331,
      "loss": 11.7327,
      "step": 82
    },
    {
      "epoch": 0.2479462285287528,
      "grad_norm": 0.05843821540474892,
      "learning_rate": 0.00020336907703837748,
      "loss": 11.7404,
      "step": 83
    },
    {
      "epoch": 0.25093353248693057,
      "grad_norm": 0.04513482376933098,
      "learning_rate": 0.00020104397616624645,
      "loss": 11.7258,
      "step": 84
    },
    {
      "epoch": 0.25392083644510827,
      "grad_norm": 0.06672092527151108,
      "learning_rate": 0.00019870492038070252,
      "loss": 11.7323,
      "step": 85
    },
    {
      "epoch": 0.256908140403286,
      "grad_norm": 0.05716870725154877,
      "learning_rate": 0.0001963525491562421,
      "loss": 11.7365,
      "step": 86
    },
    {
      "epoch": 0.2598954443614638,
      "grad_norm": 0.06132333725690842,
      "learning_rate": 0.0001939875056076697,
      "loss": 11.7262,
      "step": 87
    },
    {
      "epoch": 0.26288274831964153,
      "grad_norm": 0.054851192981004715,
      "learning_rate": 0.00019161043631427666,
      "loss": 11.7298,
      "step": 88
    },
    {
      "epoch": 0.2658700522778193,
      "grad_norm": 0.06756322830915451,
      "learning_rate": 0.00018922199114307294,
      "loss": 11.7329,
      "step": 89
    },
    {
      "epoch": 0.268857356235997,
      "grad_norm": 0.06136691942811012,
      "learning_rate": 0.00018682282307111987,
      "loss": 11.7356,
      "step": 90
    },
    {
      "epoch": 0.27184466019417475,
      "grad_norm": 0.08219900727272034,
      "learning_rate": 0.00018441358800701273,
      "loss": 11.7299,
      "step": 91
    },
    {
      "epoch": 0.2748319641523525,
      "grad_norm": 0.05855937302112579,
      "learning_rate": 0.00018199494461156203,
      "loss": 11.7359,
      "step": 92
    },
    {
      "epoch": 0.27781926811053026,
      "grad_norm": 0.07266417145729065,
      "learning_rate": 0.000179567554117722,
      "loss": 11.7415,
      "step": 93
    },
    {
      "epoch": 0.280806572068708,
      "grad_norm": 0.05537813529372215,
      "learning_rate": 0.00017713208014981648,
      "loss": 11.7326,
      "step": 94
    },
    {
      "epoch": 0.2837938760268857,
      "grad_norm": 0.08542138338088989,
      "learning_rate": 0.00017468918854211007,
      "loss": 11.7287,
      "step": 95
    },
    {
      "epoch": 0.2867811799850635,
      "grad_norm": 0.07435545325279236,
      "learning_rate": 0.00017223954715677627,
      "loss": 11.7319,
      "step": 96
    },
    {
      "epoch": 0.28976848394324123,
      "grad_norm": 0.09765500575304031,
      "learning_rate": 0.00016978382570131034,
      "loss": 11.7341,
      "step": 97
    },
    {
      "epoch": 0.292755787901419,
      "grad_norm": 0.07671134918928146,
      "learning_rate": 0.00016732269554543794,
      "loss": 11.7282,
      "step": 98
    },
    {
      "epoch": 0.29574309185959674,
      "grad_norm": 0.07551033049821854,
      "learning_rate": 0.00016485682953756942,
      "loss": 11.7371,
      "step": 99
    },
    {
      "epoch": 0.29873039581777444,
      "grad_norm": 0.08473823964595795,
      "learning_rate": 0.00016238690182084986,
      "loss": 11.7369,
      "step": 100
    },
    {
      "epoch": 0.29873039581777444,
      "eval_loss": 11.739458084106445,
      "eval_runtime": 0.2327,
      "eval_samples_per_second": 214.873,
      "eval_steps_per_second": 30.082,
      "step": 100
    },
    {
      "epoch": 0.3017176997759522,
      "grad_norm": 0.04943777620792389,
      "learning_rate": 0.0001599135876488549,
      "loss": 11.7339,
      "step": 101
    },
    {
      "epoch": 0.30470500373412995,
      "grad_norm": 0.054680634289979935,
      "learning_rate": 0.00015743756320098332,
      "loss": 11.7267,
      "step": 102
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.05804002285003662,
      "learning_rate": 0.0001549595053975962,
      "loss": 11.7335,
      "step": 103
    },
    {
      "epoch": 0.3106796116504854,
      "grad_norm": 0.0672604963183403,
      "learning_rate": 0.00015248009171495378,
      "loss": 11.7349,
      "step": 104
    },
    {
      "epoch": 0.31366691560866317,
      "grad_norm": 0.07119660079479218,
      "learning_rate": 0.00015,
      "loss": 11.7343,
      "step": 105
    },
    {
      "epoch": 0.3166542195668409,
      "grad_norm": 0.04083291441202164,
      "learning_rate": 0.00014751990828504622,
      "loss": 11.7277,
      "step": 106
    },
    {
      "epoch": 0.3196415235250187,
      "grad_norm": 0.036932576447725296,
      "learning_rate": 0.00014504049460240375,
      "loss": 11.737,
      "step": 107
    },
    {
      "epoch": 0.32262882748319643,
      "grad_norm": 0.052398402243852615,
      "learning_rate": 0.00014256243679901663,
      "loss": 11.7312,
      "step": 108
    },
    {
      "epoch": 0.32561613144137413,
      "grad_norm": 0.05291014164686203,
      "learning_rate": 0.00014008641235114508,
      "loss": 11.7318,
      "step": 109
    },
    {
      "epoch": 0.3286034353995519,
      "grad_norm": 0.059045929461717606,
      "learning_rate": 0.00013761309817915014,
      "loss": 11.7285,
      "step": 110
    },
    {
      "epoch": 0.33159073935772965,
      "grad_norm": 0.05819769203662872,
      "learning_rate": 0.00013514317046243058,
      "loss": 11.7326,
      "step": 111
    },
    {
      "epoch": 0.3345780433159074,
      "grad_norm": 0.04030715301632881,
      "learning_rate": 0.00013267730445456208,
      "loss": 11.734,
      "step": 112
    },
    {
      "epoch": 0.33756534727408516,
      "grad_norm": 0.0659136176109314,
      "learning_rate": 0.00013021617429868963,
      "loss": 11.729,
      "step": 113
    },
    {
      "epoch": 0.34055265123226286,
      "grad_norm": 0.07895601540803909,
      "learning_rate": 0.00012776045284322368,
      "loss": 11.729,
      "step": 114
    },
    {
      "epoch": 0.3435399551904406,
      "grad_norm": 0.0704202726483345,
      "learning_rate": 0.00012531081145788987,
      "loss": 11.7313,
      "step": 115
    },
    {
      "epoch": 0.34652725914861837,
      "grad_norm": 0.06143911927938461,
      "learning_rate": 0.00012286791985018355,
      "loss": 11.7299,
      "step": 116
    },
    {
      "epoch": 0.34951456310679613,
      "grad_norm": 0.05541631951928139,
      "learning_rate": 0.00012043244588227796,
      "loss": 11.7298,
      "step": 117
    },
    {
      "epoch": 0.3525018670649739,
      "grad_norm": 0.05119694769382477,
      "learning_rate": 0.00011800505538843798,
      "loss": 11.7336,
      "step": 118
    },
    {
      "epoch": 0.3554891710231516,
      "grad_norm": 0.08862697333097458,
      "learning_rate": 0.00011558641199298727,
      "loss": 11.7332,
      "step": 119
    },
    {
      "epoch": 0.35847647498132934,
      "grad_norm": 0.06034471467137337,
      "learning_rate": 0.00011317717692888012,
      "loss": 11.7318,
      "step": 120
    },
    {
      "epoch": 0.3614637789395071,
      "grad_norm": 0.07613560557365417,
      "learning_rate": 0.00011077800885692702,
      "loss": 11.7318,
      "step": 121
    },
    {
      "epoch": 0.36445108289768485,
      "grad_norm": 0.06295211613178253,
      "learning_rate": 0.00010838956368572334,
      "loss": 11.7327,
      "step": 122
    },
    {
      "epoch": 0.3674383868558626,
      "grad_norm": 0.06508342921733856,
      "learning_rate": 0.0001060124943923303,
      "loss": 11.727,
      "step": 123
    },
    {
      "epoch": 0.3704256908140403,
      "grad_norm": 0.05190775543451309,
      "learning_rate": 0.0001036474508437579,
      "loss": 11.7293,
      "step": 124
    },
    {
      "epoch": 0.37341299477221807,
      "grad_norm": 0.050209056586027145,
      "learning_rate": 0.00010129507961929748,
      "loss": 11.7416,
      "step": 125
    },
    {
      "epoch": 0.37341299477221807,
      "eval_loss": 11.739356994628906,
      "eval_runtime": 0.2323,
      "eval_samples_per_second": 215.284,
      "eval_steps_per_second": 30.14,
      "step": 125
    },
    {
      "epoch": 0.3764002987303958,
      "grad_norm": 0.051851410418748856,
      "learning_rate": 9.895602383375353e-05,
      "loss": 11.733,
      "step": 126
    },
    {
      "epoch": 0.3793876026885736,
      "grad_norm": 0.05971072241663933,
      "learning_rate": 9.663092296162251e-05,
      "loss": 11.7354,
      "step": 127
    },
    {
      "epoch": 0.38237490664675133,
      "grad_norm": 0.06602457910776138,
      "learning_rate": 9.432041266226686e-05,
      "loss": 11.7317,
      "step": 128
    },
    {
      "epoch": 0.38536221060492903,
      "grad_norm": 0.04962695762515068,
      "learning_rate": 9.202512460613219e-05,
      "loss": 11.7383,
      "step": 129
    },
    {
      "epoch": 0.3883495145631068,
      "grad_norm": 0.03992868959903717,
      "learning_rate": 8.97456863020546e-05,
      "loss": 11.7359,
      "step": 130
    },
    {
      "epoch": 0.39133681852128455,
      "grad_norm": 0.05924927815794945,
      "learning_rate": 8.748272092570646e-05,
      "loss": 11.7318,
      "step": 131
    },
    {
      "epoch": 0.3943241224794623,
      "grad_norm": 0.06533338129520416,
      "learning_rate": 8.523684714922608e-05,
      "loss": 11.7293,
      "step": 132
    },
    {
      "epoch": 0.39731142643764,
      "grad_norm": 0.06650632619857788,
      "learning_rate": 8.300867897207903e-05,
      "loss": 11.73,
      "step": 133
    },
    {
      "epoch": 0.40029873039581776,
      "grad_norm": 0.06344565004110336,
      "learning_rate": 8.079882555319684e-05,
      "loss": 11.7308,
      "step": 134
    },
    {
      "epoch": 0.4032860343539955,
      "grad_norm": 0.05324974283576012,
      "learning_rate": 7.860789104443896e-05,
      "loss": 11.7335,
      "step": 135
    },
    {
      "epoch": 0.40627333831217327,
      "grad_norm": 0.06353279948234558,
      "learning_rate": 7.643647442542382e-05,
      "loss": 11.7315,
      "step": 136
    },
    {
      "epoch": 0.409260642270351,
      "grad_norm": 0.04688692092895508,
      "learning_rate": 7.428516933977347e-05,
      "loss": 11.7319,
      "step": 137
    },
    {
      "epoch": 0.4122479462285287,
      "grad_norm": 0.05019501596689224,
      "learning_rate": 7.215456393281776e-05,
      "loss": 11.7341,
      "step": 138
    },
    {
      "epoch": 0.4152352501867065,
      "grad_norm": 0.060236912220716476,
      "learning_rate": 7.004524069080096e-05,
      "loss": 11.7314,
      "step": 139
    },
    {
      "epoch": 0.41822255414488424,
      "grad_norm": 0.055881600826978683,
      "learning_rate": 6.795777628163599e-05,
      "loss": 11.7287,
      "step": 140
    },
    {
      "epoch": 0.421209858103062,
      "grad_norm": 0.08500529080629349,
      "learning_rate": 6.58927413972491e-05,
      "loss": 11.7392,
      "step": 141
    },
    {
      "epoch": 0.42419716206123975,
      "grad_norm": 0.07128537446260452,
      "learning_rate": 6.385070059755846e-05,
      "loss": 11.7311,
      "step": 142
    },
    {
      "epoch": 0.42718446601941745,
      "grad_norm": 0.06923889368772507,
      "learning_rate": 6.183221215612904e-05,
      "loss": 11.7377,
      "step": 143
    },
    {
      "epoch": 0.4301717699775952,
      "grad_norm": 0.06836023926734924,
      "learning_rate": 5.983782790754623e-05,
      "loss": 11.7349,
      "step": 144
    },
    {
      "epoch": 0.43315907393577296,
      "grad_norm": 0.0223074983805418,
      "learning_rate": 5.786809309654982e-05,
      "loss": 11.7347,
      "step": 145
    },
    {
      "epoch": 0.4361463778939507,
      "grad_norm": 0.052147138863801956,
      "learning_rate": 5.592354622896944e-05,
      "loss": 11.7346,
      "step": 146
    },
    {
      "epoch": 0.4391336818521285,
      "grad_norm": 0.06598974019289017,
      "learning_rate": 5.40047189245025e-05,
      "loss": 11.7292,
      "step": 147
    },
    {
      "epoch": 0.4421209858103062,
      "grad_norm": 0.04568225517868996,
      "learning_rate": 5.211213577137469e-05,
      "loss": 11.7323,
      "step": 148
    },
    {
      "epoch": 0.44510828976848393,
      "grad_norm": 0.07579030841588974,
      "learning_rate": 5.024631418292274e-05,
      "loss": 11.7332,
      "step": 149
    },
    {
      "epoch": 0.4480955937266617,
      "grad_norm": 0.09643328189849854,
      "learning_rate": 4.840776425613886e-05,
      "loss": 11.7357,
      "step": 150
    },
    {
      "epoch": 0.4480955937266617,
      "eval_loss": 11.739721298217773,
      "eval_runtime": 0.2327,
      "eval_samples_per_second": 214.843,
      "eval_steps_per_second": 30.078,
      "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": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 64929388953600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}