{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.037285607755406416,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003728560775540641,
      "grad_norm": 3.2273905277252197,
      "learning_rate": 1e-05,
      "loss": 3.4355,
      "step": 1
    },
    {
      "epoch": 0.0003728560775540641,
      "eval_loss": 1.8008577823638916,
      "eval_runtime": 353.1503,
      "eval_samples_per_second": 6.397,
      "eval_steps_per_second": 0.801,
      "step": 1
    },
    {
      "epoch": 0.0007457121551081282,
      "grad_norm": 4.027805805206299,
      "learning_rate": 2e-05,
      "loss": 4.0185,
      "step": 2
    },
    {
      "epoch": 0.0011185682326621924,
      "grad_norm": 3.179356575012207,
      "learning_rate": 3e-05,
      "loss": 3.541,
      "step": 3
    },
    {
      "epoch": 0.0014914243102162564,
      "grad_norm": 3.339418888092041,
      "learning_rate": 4e-05,
      "loss": 3.4222,
      "step": 4
    },
    {
      "epoch": 0.0018642803877703207,
      "grad_norm": 4.543241500854492,
      "learning_rate": 5e-05,
      "loss": 3.6497,
      "step": 5
    },
    {
      "epoch": 0.0022371364653243847,
      "grad_norm": 3.6381893157958984,
      "learning_rate": 6e-05,
      "loss": 3.4862,
      "step": 6
    },
    {
      "epoch": 0.002609992542878449,
      "grad_norm": 11.36868953704834,
      "learning_rate": 7e-05,
      "loss": 3.2618,
      "step": 7
    },
    {
      "epoch": 0.002982848620432513,
      "grad_norm": 4.990373134613037,
      "learning_rate": 8e-05,
      "loss": 3.0643,
      "step": 8
    },
    {
      "epoch": 0.003355704697986577,
      "grad_norm": 11.262433052062988,
      "learning_rate": 9e-05,
      "loss": 2.5547,
      "step": 9
    },
    {
      "epoch": 0.003355704697986577,
      "eval_loss": 1.2176220417022705,
      "eval_runtime": 353.0167,
      "eval_samples_per_second": 6.399,
      "eval_steps_per_second": 0.802,
      "step": 9
    },
    {
      "epoch": 0.0037285607755406414,
      "grad_norm": 4.229122161865234,
      "learning_rate": 0.0001,
      "loss": 2.5665,
      "step": 10
    },
    {
      "epoch": 0.004101416853094705,
      "grad_norm": 3.833820104598999,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.2817,
      "step": 11
    },
    {
      "epoch": 0.0044742729306487695,
      "grad_norm": 4.755269527435303,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.9641,
      "step": 12
    },
    {
      "epoch": 0.004847129008202834,
      "grad_norm": 4.510311603546143,
      "learning_rate": 9.972609476841367e-05,
      "loss": 1.7572,
      "step": 13
    },
    {
      "epoch": 0.005219985085756898,
      "grad_norm": 4.087654113769531,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.4029,
      "step": 14
    },
    {
      "epoch": 0.005592841163310962,
      "grad_norm": 4.565130710601807,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.1817,
      "step": 15
    },
    {
      "epoch": 0.005965697240865026,
      "grad_norm": 3.981370687484741,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.2368,
      "step": 16
    },
    {
      "epoch": 0.00633855331841909,
      "grad_norm": 4.3100972175598145,
      "learning_rate": 9.851478631379982e-05,
      "loss": 1.1073,
      "step": 17
    },
    {
      "epoch": 0.006711409395973154,
      "grad_norm": 9.070611953735352,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.239,
      "step": 18
    },
    {
      "epoch": 0.006711409395973154,
      "eval_loss": 0.49113982915878296,
      "eval_runtime": 352.9587,
      "eval_samples_per_second": 6.4,
      "eval_steps_per_second": 0.802,
      "step": 18
    },
    {
      "epoch": 0.0070842654735272185,
      "grad_norm": 3.0325357913970947,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7823,
      "step": 19
    },
    {
      "epoch": 0.007457121551081283,
      "grad_norm": 3.4878969192504883,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.7623,
      "step": 20
    },
    {
      "epoch": 0.007829977628635347,
      "grad_norm": 2.9287140369415283,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.8463,
      "step": 21
    },
    {
      "epoch": 0.00820283370618941,
      "grad_norm": 3.594860553741455,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.6903,
      "step": 22
    },
    {
      "epoch": 0.008575689783743476,
      "grad_norm": 4.352069854736328,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.927,
      "step": 23
    },
    {
      "epoch": 0.008948545861297539,
      "grad_norm": 2.5088510513305664,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.6223,
      "step": 24
    },
    {
      "epoch": 0.009321401938851604,
      "grad_norm": 2.696772813796997,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.7409,
      "step": 25
    },
    {
      "epoch": 0.009694258016405667,
      "grad_norm": 3.393937110900879,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.768,
      "step": 26
    },
    {
      "epoch": 0.010067114093959731,
      "grad_norm": 2.6685173511505127,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.6532,
      "step": 27
    },
    {
      "epoch": 0.010067114093959731,
      "eval_loss": 0.3525005280971527,
      "eval_runtime": 353.0466,
      "eval_samples_per_second": 6.399,
      "eval_steps_per_second": 0.802,
      "step": 27
    },
    {
      "epoch": 0.010439970171513796,
      "grad_norm": 2.637833595275879,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6783,
      "step": 28
    },
    {
      "epoch": 0.01081282624906786,
      "grad_norm": 2.6375908851623535,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.8731,
      "step": 29
    },
    {
      "epoch": 0.011185682326621925,
      "grad_norm": 3.6596407890319824,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.8254,
      "step": 30
    },
    {
      "epoch": 0.011558538404175988,
      "grad_norm": 2.597501754760742,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.6116,
      "step": 31
    },
    {
      "epoch": 0.011931394481730051,
      "grad_norm": 2.175229787826538,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.5833,
      "step": 32
    },
    {
      "epoch": 0.012304250559284116,
      "grad_norm": 2.7441792488098145,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.8438,
      "step": 33
    },
    {
      "epoch": 0.01267710663683818,
      "grad_norm": 2.9346845149993896,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.8046,
      "step": 34
    },
    {
      "epoch": 0.013049962714392245,
      "grad_norm": 2.7344934940338135,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.6102,
      "step": 35
    },
    {
      "epoch": 0.013422818791946308,
      "grad_norm": 2.4309346675872803,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.5593,
      "step": 36
    },
    {
      "epoch": 0.013422818791946308,
      "eval_loss": 0.30376312136650085,
      "eval_runtime": 353.0002,
      "eval_samples_per_second": 6.399,
      "eval_steps_per_second": 0.802,
      "step": 36
    },
    {
      "epoch": 0.013795674869500374,
      "grad_norm": 2.6589467525482178,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.5914,
      "step": 37
    },
    {
      "epoch": 0.014168530947054437,
      "grad_norm": 3.2474007606506348,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.6242,
      "step": 38
    },
    {
      "epoch": 0.0145413870246085,
      "grad_norm": 2.08449125289917,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.523,
      "step": 39
    },
    {
      "epoch": 0.014914243102162566,
      "grad_norm": 1.5239322185516357,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.4422,
      "step": 40
    },
    {
      "epoch": 0.015287099179716629,
      "grad_norm": 2.0777080059051514,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.5522,
      "step": 41
    },
    {
      "epoch": 0.015659955257270694,
      "grad_norm": 2.9804673194885254,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.8012,
      "step": 42
    },
    {
      "epoch": 0.01603281133482476,
      "grad_norm": 1.4776819944381714,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.3703,
      "step": 43
    },
    {
      "epoch": 0.01640566741237882,
      "grad_norm": 1.9899928569793701,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.4545,
      "step": 44
    },
    {
      "epoch": 0.016778523489932886,
      "grad_norm": 2.4433422088623047,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.5579,
      "step": 45
    },
    {
      "epoch": 0.016778523489932886,
      "eval_loss": 0.27536752820014954,
      "eval_runtime": 352.9507,
      "eval_samples_per_second": 6.4,
      "eval_steps_per_second": 0.802,
      "step": 45
    },
    {
      "epoch": 0.01715137956748695,
      "grad_norm": 3.4268898963928223,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.5382,
      "step": 46
    },
    {
      "epoch": 0.017524235645041013,
      "grad_norm": 2.0205821990966797,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.4476,
      "step": 47
    },
    {
      "epoch": 0.017897091722595078,
      "grad_norm": 3.0076658725738525,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.5125,
      "step": 48
    },
    {
      "epoch": 0.018269947800149143,
      "grad_norm": 3.84687876701355,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.5999,
      "step": 49
    },
    {
      "epoch": 0.018642803877703208,
      "grad_norm": 1.8309787511825562,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.4413,
      "step": 50
    },
    {
      "epoch": 0.01901565995525727,
      "grad_norm": 2.404618263244629,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.4902,
      "step": 51
    },
    {
      "epoch": 0.019388516032811335,
      "grad_norm": 2.2248353958129883,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.426,
      "step": 52
    },
    {
      "epoch": 0.0197613721103654,
      "grad_norm": 1.5294620990753174,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.3083,
      "step": 53
    },
    {
      "epoch": 0.020134228187919462,
      "grad_norm": 2.840945243835449,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.5174,
      "step": 54
    },
    {
      "epoch": 0.020134228187919462,
      "eval_loss": 0.256969153881073,
      "eval_runtime": 352.9528,
      "eval_samples_per_second": 6.4,
      "eval_steps_per_second": 0.802,
      "step": 54
    },
    {
      "epoch": 0.020507084265473527,
      "grad_norm": 2.9101431369781494,
      "learning_rate": 5e-05,
      "loss": 0.5569,
      "step": 55
    },
    {
      "epoch": 0.020879940343027592,
      "grad_norm": 2.4050216674804688,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.6652,
      "step": 56
    },
    {
      "epoch": 0.021252796420581657,
      "grad_norm": 2.165149211883545,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.4262,
      "step": 57
    },
    {
      "epoch": 0.02162565249813572,
      "grad_norm": 2.01960825920105,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.6341,
      "step": 58
    },
    {
      "epoch": 0.021998508575689784,
      "grad_norm": 1.9947001934051514,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.5419,
      "step": 59
    },
    {
      "epoch": 0.02237136465324385,
      "grad_norm": 2.3822672367095947,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.5953,
      "step": 60
    },
    {
      "epoch": 0.02274422073079791,
      "grad_norm": 2.9558725357055664,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.6823,
      "step": 61
    },
    {
      "epoch": 0.023117076808351976,
      "grad_norm": 2.5282161235809326,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.5637,
      "step": 62
    },
    {
      "epoch": 0.02348993288590604,
      "grad_norm": 2.7243053913116455,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.486,
      "step": 63
    },
    {
      "epoch": 0.02348993288590604,
      "eval_loss": 0.25008442997932434,
      "eval_runtime": 353.0164,
      "eval_samples_per_second": 6.399,
      "eval_steps_per_second": 0.802,
      "step": 63
    },
    {
      "epoch": 0.023862788963460103,
      "grad_norm": 2.5961456298828125,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.709,
      "step": 64
    },
    {
      "epoch": 0.024235645041014168,
      "grad_norm": 1.7899454832077026,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.3097,
      "step": 65
    },
    {
      "epoch": 0.024608501118568233,
      "grad_norm": 2.0271105766296387,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.5219,
      "step": 66
    },
    {
      "epoch": 0.024981357196122298,
      "grad_norm": 2.0244550704956055,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.449,
      "step": 67
    },
    {
      "epoch": 0.02535421327367636,
      "grad_norm": 2.342764377593994,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.5528,
      "step": 68
    },
    {
      "epoch": 0.025727069351230425,
      "grad_norm": 2.4467732906341553,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.5,
      "step": 69
    },
    {
      "epoch": 0.02609992542878449,
      "grad_norm": 1.8645575046539307,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.3163,
      "step": 70
    },
    {
      "epoch": 0.02647278150633855,
      "grad_norm": 2.5564777851104736,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.5877,
      "step": 71
    },
    {
      "epoch": 0.026845637583892617,
      "grad_norm": 2.0534887313842773,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.5893,
      "step": 72
    },
    {
      "epoch": 0.026845637583892617,
      "eval_loss": 0.24400091171264648,
      "eval_runtime": 352.9932,
      "eval_samples_per_second": 6.4,
      "eval_steps_per_second": 0.802,
      "step": 72
    },
    {
      "epoch": 0.027218493661446682,
      "grad_norm": 2.7727997303009033,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.5884,
      "step": 73
    },
    {
      "epoch": 0.027591349739000747,
      "grad_norm": 1.9303561449050903,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.6323,
      "step": 74
    },
    {
      "epoch": 0.02796420581655481,
      "grad_norm": 2.5347917079925537,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.4399,
      "step": 75
    },
    {
      "epoch": 0.028337061894108874,
      "grad_norm": 1.640629768371582,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.4401,
      "step": 76
    },
    {
      "epoch": 0.02870991797166294,
      "grad_norm": 2.2154061794281006,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.4543,
      "step": 77
    },
    {
      "epoch": 0.029082774049217,
      "grad_norm": 2.167428970336914,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.4523,
      "step": 78
    },
    {
      "epoch": 0.029455630126771066,
      "grad_norm": 1.528300166130066,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.3186,
      "step": 79
    },
    {
      "epoch": 0.02982848620432513,
      "grad_norm": 2.0265486240386963,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.3924,
      "step": 80
    },
    {
      "epoch": 0.030201342281879196,
      "grad_norm": 2.0504417419433594,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.6672,
      "step": 81
    },
    {
      "epoch": 0.030201342281879196,
      "eval_loss": 0.23957125842571259,
      "eval_runtime": 352.949,
      "eval_samples_per_second": 6.4,
      "eval_steps_per_second": 0.802,
      "step": 81
    },
    {
      "epoch": 0.030574198359433258,
      "grad_norm": 2.563886880874634,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7267,
      "step": 82
    },
    {
      "epoch": 0.030947054436987323,
      "grad_norm": 1.796322226524353,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.3949,
      "step": 83
    },
    {
      "epoch": 0.03131991051454139,
      "grad_norm": 1.647054672241211,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.417,
      "step": 84
    },
    {
      "epoch": 0.03169276659209545,
      "grad_norm": 1.86093270778656,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.5066,
      "step": 85
    },
    {
      "epoch": 0.03206562266964952,
      "grad_norm": 1.2961095571517944,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.3748,
      "step": 86
    },
    {
      "epoch": 0.03243847874720358,
      "grad_norm": 2.5816919803619385,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.5375,
      "step": 87
    },
    {
      "epoch": 0.03281133482475764,
      "grad_norm": 2.0271952152252197,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.5459,
      "step": 88
    },
    {
      "epoch": 0.03318419090231171,
      "grad_norm": 1.8496075868606567,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.5836,
      "step": 89
    },
    {
      "epoch": 0.03355704697986577,
      "grad_norm": 1.6776535511016846,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.2553,
      "step": 90
    },
    {
      "epoch": 0.03355704697986577,
      "eval_loss": 0.23708520829677582,
      "eval_runtime": 352.9201,
      "eval_samples_per_second": 6.401,
      "eval_steps_per_second": 0.802,
      "step": 90
    },
    {
      "epoch": 0.03392990305741984,
      "grad_norm": 2.3019521236419678,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.418,
      "step": 91
    },
    {
      "epoch": 0.0343027591349739,
      "grad_norm": 1.7794111967086792,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.4092,
      "step": 92
    },
    {
      "epoch": 0.03467561521252797,
      "grad_norm": 1.2687029838562012,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.3775,
      "step": 93
    },
    {
      "epoch": 0.035048471290082026,
      "grad_norm": 3.371903657913208,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.6589,
      "step": 94
    },
    {
      "epoch": 0.03542132736763609,
      "grad_norm": 4.147241592407227,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.3095,
      "step": 95
    },
    {
      "epoch": 0.035794183445190156,
      "grad_norm": 1.5110682249069214,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.3949,
      "step": 96
    },
    {
      "epoch": 0.03616703952274422,
      "grad_norm": 1.5129752159118652,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.387,
      "step": 97
    },
    {
      "epoch": 0.036539895600298286,
      "grad_norm": 2.31642484664917,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.7087,
      "step": 98
    },
    {
      "epoch": 0.03691275167785235,
      "grad_norm": 3.623220443725586,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.5247,
      "step": 99
    },
    {
      "epoch": 0.03691275167785235,
      "eval_loss": 0.23658187687397003,
      "eval_runtime": 352.981,
      "eval_samples_per_second": 6.4,
      "eval_steps_per_second": 0.802,
      "step": 99
    },
    {
      "epoch": 0.037285607755406416,
      "grad_norm": 1.4099475145339966,
      "learning_rate": 0.0,
      "loss": 0.3286,
      "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
}