{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2949852507374631,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0029498525073746312,
      "grad_norm": 2.6730434894561768,
      "learning_rate": 1e-05,
      "loss": 4.059,
      "step": 1
    },
    {
      "epoch": 0.0029498525073746312,
      "eval_loss": 2.0677247047424316,
      "eval_runtime": 44.3198,
      "eval_samples_per_second": 6.453,
      "eval_steps_per_second": 0.812,
      "step": 1
    },
    {
      "epoch": 0.0058997050147492625,
      "grad_norm": 1.780819296836853,
      "learning_rate": 2e-05,
      "loss": 3.1111,
      "step": 2
    },
    {
      "epoch": 0.008849557522123894,
      "grad_norm": 3.14420485496521,
      "learning_rate": 3e-05,
      "loss": 3.5452,
      "step": 3
    },
    {
      "epoch": 0.011799410029498525,
      "grad_norm": 4.393539905548096,
      "learning_rate": 4e-05,
      "loss": 4.6015,
      "step": 4
    },
    {
      "epoch": 0.014749262536873156,
      "grad_norm": 3.3870508670806885,
      "learning_rate": 5e-05,
      "loss": 4.1767,
      "step": 5
    },
    {
      "epoch": 0.017699115044247787,
      "grad_norm": 2.174534559249878,
      "learning_rate": 6e-05,
      "loss": 3.0682,
      "step": 6
    },
    {
      "epoch": 0.02064896755162242,
      "grad_norm": 2.650453567504883,
      "learning_rate": 7e-05,
      "loss": 3.5393,
      "step": 7
    },
    {
      "epoch": 0.02359882005899705,
      "grad_norm": 2.851867437362671,
      "learning_rate": 8e-05,
      "loss": 3.6709,
      "step": 8
    },
    {
      "epoch": 0.02654867256637168,
      "grad_norm": 5.362432956695557,
      "learning_rate": 9e-05,
      "loss": 3.7535,
      "step": 9
    },
    {
      "epoch": 0.02654867256637168,
      "eval_loss": 1.4621776342391968,
      "eval_runtime": 44.3203,
      "eval_samples_per_second": 6.453,
      "eval_steps_per_second": 0.812,
      "step": 9
    },
    {
      "epoch": 0.029498525073746312,
      "grad_norm": 3.1995365619659424,
      "learning_rate": 0.0001,
      "loss": 3.1976,
      "step": 10
    },
    {
      "epoch": 0.032448377581120944,
      "grad_norm": 2.1539673805236816,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.5042,
      "step": 11
    },
    {
      "epoch": 0.035398230088495575,
      "grad_norm": 2.2371580600738525,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.484,
      "step": 12
    },
    {
      "epoch": 0.038348082595870206,
      "grad_norm": 2.3283255100250244,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.8651,
      "step": 13
    },
    {
      "epoch": 0.04129793510324484,
      "grad_norm": 2.758920192718506,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.2593,
      "step": 14
    },
    {
      "epoch": 0.04424778761061947,
      "grad_norm": 2.5637218952178955,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.2398,
      "step": 15
    },
    {
      "epoch": 0.0471976401179941,
      "grad_norm": 3.0846474170684814,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.9655,
      "step": 16
    },
    {
      "epoch": 0.05014749262536873,
      "grad_norm": 3.055612087249756,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.5861,
      "step": 17
    },
    {
      "epoch": 0.05309734513274336,
      "grad_norm": 3.042341470718384,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.08,
      "step": 18
    },
    {
      "epoch": 0.05309734513274336,
      "eval_loss": 1.0477064847946167,
      "eval_runtime": 44.3486,
      "eval_samples_per_second": 6.449,
      "eval_steps_per_second": 0.812,
      "step": 18
    },
    {
      "epoch": 0.05604719764011799,
      "grad_norm": 2.4983811378479004,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.7399,
      "step": 19
    },
    {
      "epoch": 0.058997050147492625,
      "grad_norm": 2.7760469913482666,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.3545,
      "step": 20
    },
    {
      "epoch": 0.061946902654867256,
      "grad_norm": 2.5731499195098877,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.3881,
      "step": 21
    },
    {
      "epoch": 0.06489675516224189,
      "grad_norm": 1.8936318159103394,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.1502,
      "step": 22
    },
    {
      "epoch": 0.06784660766961652,
      "grad_norm": 1.976555585861206,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.1209,
      "step": 23
    },
    {
      "epoch": 0.07079646017699115,
      "grad_norm": 2.4951541423797607,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.9717,
      "step": 24
    },
    {
      "epoch": 0.07374631268436578,
      "grad_norm": 1.7388063669204712,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.8964,
      "step": 25
    },
    {
      "epoch": 0.07669616519174041,
      "grad_norm": 1.7615406513214111,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.5812,
      "step": 26
    },
    {
      "epoch": 0.07964601769911504,
      "grad_norm": 2.4763855934143066,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.2404,
      "step": 27
    },
    {
      "epoch": 0.07964601769911504,
      "eval_loss": 1.0080937147140503,
      "eval_runtime": 44.3909,
      "eval_samples_per_second": 6.443,
      "eval_steps_per_second": 0.811,
      "step": 27
    },
    {
      "epoch": 0.08259587020648967,
      "grad_norm": 2.52359676361084,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.7129,
      "step": 28
    },
    {
      "epoch": 0.0855457227138643,
      "grad_norm": 2.9214510917663574,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.0964,
      "step": 29
    },
    {
      "epoch": 0.08849557522123894,
      "grad_norm": 2.418994188308716,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.9937,
      "step": 30
    },
    {
      "epoch": 0.09144542772861357,
      "grad_norm": 2.003028154373169,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.5031,
      "step": 31
    },
    {
      "epoch": 0.0943952802359882,
      "grad_norm": 3.0602455139160156,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.8419,
      "step": 32
    },
    {
      "epoch": 0.09734513274336283,
      "grad_norm": 3.8223624229431152,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.7186,
      "step": 33
    },
    {
      "epoch": 0.10029498525073746,
      "grad_norm": 2.1360504627227783,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.8072,
      "step": 34
    },
    {
      "epoch": 0.10324483775811209,
      "grad_norm": 2.5613925457000732,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.4713,
      "step": 35
    },
    {
      "epoch": 0.10619469026548672,
      "grad_norm": 4.114505767822266,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.8798,
      "step": 36
    },
    {
      "epoch": 0.10619469026548672,
      "eval_loss": 0.9803729057312012,
      "eval_runtime": 44.3399,
      "eval_samples_per_second": 6.45,
      "eval_steps_per_second": 0.812,
      "step": 36
    },
    {
      "epoch": 0.10914454277286136,
      "grad_norm": 2.2606899738311768,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.1288,
      "step": 37
    },
    {
      "epoch": 0.11209439528023599,
      "grad_norm": 2.3474953174591064,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.8458,
      "step": 38
    },
    {
      "epoch": 0.11504424778761062,
      "grad_norm": 2.764202833175659,
      "learning_rate": 7.649596321166024e-05,
      "loss": 3.0195,
      "step": 39
    },
    {
      "epoch": 0.11799410029498525,
      "grad_norm": 2.4660158157348633,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.827,
      "step": 40
    },
    {
      "epoch": 0.12094395280235988,
      "grad_norm": 2.5078041553497314,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.3851,
      "step": 41
    },
    {
      "epoch": 0.12389380530973451,
      "grad_norm": 2.1289970874786377,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.4684,
      "step": 42
    },
    {
      "epoch": 0.12684365781710916,
      "grad_norm": 3.008479595184326,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.7663,
      "step": 43
    },
    {
      "epoch": 0.12979351032448377,
      "grad_norm": 2.681143045425415,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.6546,
      "step": 44
    },
    {
      "epoch": 0.13274336283185842,
      "grad_norm": 3.201345443725586,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.0512,
      "step": 45
    },
    {
      "epoch": 0.13274336283185842,
      "eval_loss": 0.9570127129554749,
      "eval_runtime": 44.365,
      "eval_samples_per_second": 6.447,
      "eval_steps_per_second": 0.811,
      "step": 45
    },
    {
      "epoch": 0.13569321533923304,
      "grad_norm": 1.8258627653121948,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.5324,
      "step": 46
    },
    {
      "epoch": 0.13864306784660768,
      "grad_norm": 1.8189584016799927,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.7706,
      "step": 47
    },
    {
      "epoch": 0.1415929203539823,
      "grad_norm": 2.40757155418396,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.6126,
      "step": 48
    },
    {
      "epoch": 0.14454277286135694,
      "grad_norm": 2.335020065307617,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.326,
      "step": 49
    },
    {
      "epoch": 0.14749262536873156,
      "grad_norm": 1.997075080871582,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.5148,
      "step": 50
    },
    {
      "epoch": 0.1504424778761062,
      "grad_norm": 1.5208971500396729,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.0899,
      "step": 51
    },
    {
      "epoch": 0.15339233038348082,
      "grad_norm": 3.4418222904205322,
      "learning_rate": 5.522642316338268e-05,
      "loss": 2.4397,
      "step": 52
    },
    {
      "epoch": 0.15634218289085547,
      "grad_norm": 2.2392663955688477,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.8609,
      "step": 53
    },
    {
      "epoch": 0.1592920353982301,
      "grad_norm": 2.139505386352539,
      "learning_rate": 5.174497483512506e-05,
      "loss": 2.0997,
      "step": 54
    },
    {
      "epoch": 0.1592920353982301,
      "eval_loss": 0.9444321990013123,
      "eval_runtime": 44.3343,
      "eval_samples_per_second": 6.451,
      "eval_steps_per_second": 0.812,
      "step": 54
    },
    {
      "epoch": 0.16224188790560473,
      "grad_norm": 2.0930261611938477,
      "learning_rate": 5e-05,
      "loss": 1.7881,
      "step": 55
    },
    {
      "epoch": 0.16519174041297935,
      "grad_norm": 2.2204813957214355,
      "learning_rate": 4.825502516487497e-05,
      "loss": 2.7174,
      "step": 56
    },
    {
      "epoch": 0.168141592920354,
      "grad_norm": 2.269932746887207,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.685,
      "step": 57
    },
    {
      "epoch": 0.1710914454277286,
      "grad_norm": 2.4379570484161377,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.3988,
      "step": 58
    },
    {
      "epoch": 0.17404129793510326,
      "grad_norm": 2.7614104747772217,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.7063,
      "step": 59
    },
    {
      "epoch": 0.17699115044247787,
      "grad_norm": 3.342813491821289,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.0876,
      "step": 60
    },
    {
      "epoch": 0.17994100294985252,
      "grad_norm": 1.874851107597351,
      "learning_rate": 3.960441545911204e-05,
      "loss": 2.41,
      "step": 61
    },
    {
      "epoch": 0.18289085545722714,
      "grad_norm": 2.886047124862671,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.7038,
      "step": 62
    },
    {
      "epoch": 0.18584070796460178,
      "grad_norm": 2.56038498878479,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.9275,
      "step": 63
    },
    {
      "epoch": 0.18584070796460178,
      "eval_loss": 0.9344019293785095,
      "eval_runtime": 44.3805,
      "eval_samples_per_second": 6.444,
      "eval_steps_per_second": 0.811,
      "step": 63
    },
    {
      "epoch": 0.1887905604719764,
      "grad_norm": 2.8928627967834473,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.076,
      "step": 64
    },
    {
      "epoch": 0.19174041297935104,
      "grad_norm": 2.5595240592956543,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.8227,
      "step": 65
    },
    {
      "epoch": 0.19469026548672566,
      "grad_norm": 2.3376636505126953,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.8931,
      "step": 66
    },
    {
      "epoch": 0.1976401179941003,
      "grad_norm": 1.9027594327926636,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.4452,
      "step": 67
    },
    {
      "epoch": 0.20058997050147492,
      "grad_norm": 2.5550875663757324,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.9689,
      "step": 68
    },
    {
      "epoch": 0.20353982300884957,
      "grad_norm": 2.062281608581543,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 2.372,
      "step": 69
    },
    {
      "epoch": 0.20648967551622419,
      "grad_norm": 2.665297508239746,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.7928,
      "step": 70
    },
    {
      "epoch": 0.20943952802359883,
      "grad_norm": 2.0745885372161865,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.4635,
      "step": 71
    },
    {
      "epoch": 0.21238938053097345,
      "grad_norm": 2.8449113368988037,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 2.0457,
      "step": 72
    },
    {
      "epoch": 0.21238938053097345,
      "eval_loss": 0.9305321574211121,
      "eval_runtime": 44.3666,
      "eval_samples_per_second": 6.446,
      "eval_steps_per_second": 0.811,
      "step": 72
    },
    {
      "epoch": 0.2153392330383481,
      "grad_norm": 2.6109533309936523,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.7443,
      "step": 73
    },
    {
      "epoch": 0.2182890855457227,
      "grad_norm": 2.955402135848999,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.8344,
      "step": 74
    },
    {
      "epoch": 0.22123893805309736,
      "grad_norm": 3.2939834594726562,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 2.3507,
      "step": 75
    },
    {
      "epoch": 0.22418879056047197,
      "grad_norm": 4.007279872894287,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 2.1104,
      "step": 76
    },
    {
      "epoch": 0.22713864306784662,
      "grad_norm": 1.9368032217025757,
      "learning_rate": 1.526708147705013e-05,
      "loss": 1.6227,
      "step": 77
    },
    {
      "epoch": 0.23008849557522124,
      "grad_norm": 2.9845495223999023,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.7561,
      "step": 78
    },
    {
      "epoch": 0.23303834808259588,
      "grad_norm": 2.2668330669403076,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 2.015,
      "step": 79
    },
    {
      "epoch": 0.2359882005899705,
      "grad_norm": 1.9236528873443604,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 1.1305,
      "step": 80
    },
    {
      "epoch": 0.23893805309734514,
      "grad_norm": 2.2773380279541016,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.778,
      "step": 81
    },
    {
      "epoch": 0.23893805309734514,
      "eval_loss": 0.92861008644104,
      "eval_runtime": 44.4064,
      "eval_samples_per_second": 6.441,
      "eval_steps_per_second": 0.811,
      "step": 81
    },
    {
      "epoch": 0.24188790560471976,
      "grad_norm": 1.7460155487060547,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.777,
      "step": 82
    },
    {
      "epoch": 0.2448377581120944,
      "grad_norm": 2.7454729080200195,
      "learning_rate": 8.548121372247918e-06,
      "loss": 1.1967,
      "step": 83
    },
    {
      "epoch": 0.24778761061946902,
      "grad_norm": 2.0686800479888916,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.6214,
      "step": 84
    },
    {
      "epoch": 0.25073746312684364,
      "grad_norm": 2.3937289714813232,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.7947,
      "step": 85
    },
    {
      "epoch": 0.2536873156342183,
      "grad_norm": 2.584099054336548,
      "learning_rate": 5.852620357053651e-06,
      "loss": 2.4677,
      "step": 86
    },
    {
      "epoch": 0.25663716814159293,
      "grad_norm": 3.2739224433898926,
      "learning_rate": 5.060297685041659e-06,
      "loss": 2.9313,
      "step": 87
    },
    {
      "epoch": 0.25958702064896755,
      "grad_norm": 2.9258463382720947,
      "learning_rate": 4.322727117869951e-06,
      "loss": 1.6279,
      "step": 88
    },
    {
      "epoch": 0.26253687315634217,
      "grad_norm": 2.1165103912353516,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 2.1038,
      "step": 89
    },
    {
      "epoch": 0.26548672566371684,
      "grad_norm": 1.7193412780761719,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.9531,
      "step": 90
    },
    {
      "epoch": 0.26548672566371684,
      "eval_loss": 0.928329586982727,
      "eval_runtime": 44.365,
      "eval_samples_per_second": 6.447,
      "eval_steps_per_second": 0.811,
      "step": 90
    },
    {
      "epoch": 0.26843657817109146,
      "grad_norm": 3.0313870906829834,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.409,
      "step": 91
    },
    {
      "epoch": 0.2713864306784661,
      "grad_norm": 2.6027047634124756,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 1.8437,
      "step": 92
    },
    {
      "epoch": 0.2743362831858407,
      "grad_norm": 1.7454715967178345,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 2.4698,
      "step": 93
    },
    {
      "epoch": 0.27728613569321536,
      "grad_norm": 4.085173606872559,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 1.5345,
      "step": 94
    },
    {
      "epoch": 0.28023598820059,
      "grad_norm": 1.4964895248413086,
      "learning_rate": 7.596123493895991e-07,
      "loss": 2.0551,
      "step": 95
    },
    {
      "epoch": 0.2831858407079646,
      "grad_norm": 2.6940832138061523,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.3975,
      "step": 96
    },
    {
      "epoch": 0.2861356932153392,
      "grad_norm": 2.0973100662231445,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 2.1289,
      "step": 97
    },
    {
      "epoch": 0.2890855457227139,
      "grad_norm": 2.0837435722351074,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.0609,
      "step": 98
    },
    {
      "epoch": 0.2920353982300885,
      "grad_norm": 2.236985921859741,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.6664,
      "step": 99
    },
    {
      "epoch": 0.2920353982300885,
      "eval_loss": 0.9275940656661987,
      "eval_runtime": 44.3545,
      "eval_samples_per_second": 6.448,
      "eval_steps_per_second": 0.812,
      "step": 99
    },
    {
      "epoch": 0.2949852507374631,
      "grad_norm": 2.534641981124878,
      "learning_rate": 0.0,
      "loss": 1.5521,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2695579394048e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}