adammandic87's picture
Training in progress, step 200, checkpoint
cadf002 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.2946593001841621,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0014732965009208103,
"grad_norm": 3.1541404724121094,
"learning_rate": 2e-05,
"loss": 8.9189,
"step": 1
},
{
"epoch": 0.0014732965009208103,
"eval_loss": 3.2565059661865234,
"eval_runtime": 9.4566,
"eval_samples_per_second": 30.244,
"eval_steps_per_second": 15.122,
"step": 1
},
{
"epoch": 0.0029465930018416206,
"grad_norm": 1.7702511548995972,
"learning_rate": 4e-05,
"loss": 9.741,
"step": 2
},
{
"epoch": 0.004419889502762431,
"grad_norm": 2.489617109298706,
"learning_rate": 6e-05,
"loss": 12.075,
"step": 3
},
{
"epoch": 0.005893186003683241,
"grad_norm": 6.4327898025512695,
"learning_rate": 8e-05,
"loss": 13.4888,
"step": 4
},
{
"epoch": 0.007366482504604052,
"grad_norm": 3.635437250137329,
"learning_rate": 0.0001,
"loss": 15.0644,
"step": 5
},
{
"epoch": 0.008839779005524863,
"grad_norm": 5.8415045738220215,
"learning_rate": 0.00012,
"loss": 14.4951,
"step": 6
},
{
"epoch": 0.010313075506445672,
"grad_norm": 6.604334831237793,
"learning_rate": 0.00014,
"loss": 15.9952,
"step": 7
},
{
"epoch": 0.011786372007366482,
"grad_norm": 4.3601579666137695,
"learning_rate": 0.00016,
"loss": 11.8052,
"step": 8
},
{
"epoch": 0.013259668508287293,
"grad_norm": 4.953864097595215,
"learning_rate": 0.00018,
"loss": 12.0071,
"step": 9
},
{
"epoch": 0.014732965009208104,
"grad_norm": 7.948404312133789,
"learning_rate": 0.0002,
"loss": 11.1713,
"step": 10
},
{
"epoch": 0.016206261510128914,
"grad_norm": 6.616621971130371,
"learning_rate": 0.0001999863304992469,
"loss": 9.3546,
"step": 11
},
{
"epoch": 0.017679558011049725,
"grad_norm": 3.6598548889160156,
"learning_rate": 0.00019994532573409262,
"loss": 9.7632,
"step": 12
},
{
"epoch": 0.019152854511970532,
"grad_norm": 5.915988445281982,
"learning_rate": 0.00019987699691483048,
"loss": 14.6365,
"step": 13
},
{
"epoch": 0.020626151012891343,
"grad_norm": 6.100218772888184,
"learning_rate": 0.00019978136272187747,
"loss": 10.4504,
"step": 14
},
{
"epoch": 0.022099447513812154,
"grad_norm": 3.99997615814209,
"learning_rate": 0.000199658449300667,
"loss": 9.436,
"step": 15
},
{
"epoch": 0.023572744014732964,
"grad_norm": 4.781832695007324,
"learning_rate": 0.00019950829025450114,
"loss": 9.5615,
"step": 16
},
{
"epoch": 0.025046040515653775,
"grad_norm": 4.316699504852295,
"learning_rate": 0.00019933092663536382,
"loss": 9.8006,
"step": 17
},
{
"epoch": 0.026519337016574586,
"grad_norm": 5.100368976593018,
"learning_rate": 0.00019912640693269752,
"loss": 10.0697,
"step": 18
},
{
"epoch": 0.027992633517495397,
"grad_norm": 11.279586791992188,
"learning_rate": 0.00019889478706014687,
"loss": 9.8463,
"step": 19
},
{
"epoch": 0.029465930018416207,
"grad_norm": 5.626986026763916,
"learning_rate": 0.00019863613034027224,
"loss": 9.7286,
"step": 20
},
{
"epoch": 0.030939226519337018,
"grad_norm": 11.165328025817871,
"learning_rate": 0.00019835050748723824,
"loss": 10.1978,
"step": 21
},
{
"epoch": 0.03241252302025783,
"grad_norm": 9.0336275100708,
"learning_rate": 0.00019803799658748094,
"loss": 7.924,
"step": 22
},
{
"epoch": 0.03388581952117864,
"grad_norm": 7.770285129547119,
"learning_rate": 0.00019769868307835994,
"loss": 11.2543,
"step": 23
},
{
"epoch": 0.03535911602209945,
"grad_norm": 9.521552085876465,
"learning_rate": 0.0001973326597248006,
"loss": 12.0127,
"step": 24
},
{
"epoch": 0.03683241252302026,
"grad_norm": 11.501378059387207,
"learning_rate": 0.00019694002659393305,
"loss": 9.5224,
"step": 25
},
{
"epoch": 0.038305709023941065,
"grad_norm": 4.7648515701293945,
"learning_rate": 0.00019652089102773488,
"loss": 9.2757,
"step": 26
},
{
"epoch": 0.039779005524861875,
"grad_norm": 10.825995445251465,
"learning_rate": 0.00019607536761368484,
"loss": 10.0724,
"step": 27
},
{
"epoch": 0.041252302025782686,
"grad_norm": 7.209076404571533,
"learning_rate": 0.00019560357815343577,
"loss": 8.9072,
"step": 28
},
{
"epoch": 0.0427255985267035,
"grad_norm": 10.064898490905762,
"learning_rate": 0.00019510565162951537,
"loss": 11.1213,
"step": 29
},
{
"epoch": 0.04419889502762431,
"grad_norm": 10.006102561950684,
"learning_rate": 0.00019458172417006347,
"loss": 9.3537,
"step": 30
},
{
"epoch": 0.04567219152854512,
"grad_norm": 2.8803489208221436,
"learning_rate": 0.00019403193901161613,
"loss": 6.3467,
"step": 31
},
{
"epoch": 0.04714548802946593,
"grad_norm": 9.666797637939453,
"learning_rate": 0.0001934564464599461,
"loss": 9.9114,
"step": 32
},
{
"epoch": 0.04861878453038674,
"grad_norm": 7.411388874053955,
"learning_rate": 0.00019285540384897073,
"loss": 12.8765,
"step": 33
},
{
"epoch": 0.05009208103130755,
"grad_norm": 5.952574729919434,
"learning_rate": 0.00019222897549773848,
"loss": 8.1026,
"step": 34
},
{
"epoch": 0.05156537753222836,
"grad_norm": 9.048133850097656,
"learning_rate": 0.00019157733266550575,
"loss": 9.8412,
"step": 35
},
{
"epoch": 0.05303867403314917,
"grad_norm": 8.200292587280273,
"learning_rate": 0.00019090065350491626,
"loss": 8.7816,
"step": 36
},
{
"epoch": 0.05451197053406998,
"grad_norm": 9.098681449890137,
"learning_rate": 0.00019019912301329592,
"loss": 11.8605,
"step": 37
},
{
"epoch": 0.05598526703499079,
"grad_norm": 3.642021656036377,
"learning_rate": 0.00018947293298207635,
"loss": 7.211,
"step": 38
},
{
"epoch": 0.057458563535911604,
"grad_norm": 5.9573974609375,
"learning_rate": 0.0001887222819443612,
"loss": 8.0583,
"step": 39
},
{
"epoch": 0.058931860036832415,
"grad_norm": 5.869434833526611,
"learning_rate": 0.0001879473751206489,
"loss": 10.2234,
"step": 40
},
{
"epoch": 0.060405156537753225,
"grad_norm": 8.367606163024902,
"learning_rate": 0.00018714842436272773,
"loss": 9.9171,
"step": 41
},
{
"epoch": 0.061878453038674036,
"grad_norm": 3.8573427200317383,
"learning_rate": 0.00018632564809575742,
"loss": 6.9693,
"step": 42
},
{
"epoch": 0.06335174953959484,
"grad_norm": 5.08005952835083,
"learning_rate": 0.0001854792712585539,
"loss": 8.545,
"step": 43
},
{
"epoch": 0.06482504604051566,
"grad_norm": 5.412344455718994,
"learning_rate": 0.00018460952524209355,
"loss": 6.0708,
"step": 44
},
{
"epoch": 0.06629834254143646,
"grad_norm": 5.560658931732178,
"learning_rate": 0.00018371664782625287,
"loss": 8.6937,
"step": 45
},
{
"epoch": 0.06777163904235728,
"grad_norm": 5.4355149269104,
"learning_rate": 0.00018280088311480201,
"loss": 7.2302,
"step": 46
},
{
"epoch": 0.06924493554327808,
"grad_norm": 5.770148277282715,
"learning_rate": 0.00018186248146866927,
"loss": 10.6754,
"step": 47
},
{
"epoch": 0.0707182320441989,
"grad_norm": 6.869553565979004,
"learning_rate": 0.00018090169943749476,
"loss": 9.2739,
"step": 48
},
{
"epoch": 0.0721915285451197,
"grad_norm": 8.691353797912598,
"learning_rate": 0.0001799187996894925,
"loss": 9.0793,
"step": 49
},
{
"epoch": 0.07366482504604052,
"grad_norm": 8.788375854492188,
"learning_rate": 0.00017891405093963938,
"loss": 9.0745,
"step": 50
},
{
"epoch": 0.07366482504604052,
"eval_loss": 2.2372069358825684,
"eval_runtime": 9.4565,
"eval_samples_per_second": 30.244,
"eval_steps_per_second": 15.122,
"step": 50
},
{
"epoch": 0.07513812154696133,
"grad_norm": 7.550640106201172,
"learning_rate": 0.00017788772787621126,
"loss": 12.7868,
"step": 51
},
{
"epoch": 0.07661141804788213,
"grad_norm": 7.088727951049805,
"learning_rate": 0.00017684011108568592,
"loss": 6.6456,
"step": 52
},
{
"epoch": 0.07808471454880295,
"grad_norm": 6.3660101890563965,
"learning_rate": 0.0001757714869760335,
"loss": 9.7407,
"step": 53
},
{
"epoch": 0.07955801104972375,
"grad_norm": 6.493173599243164,
"learning_rate": 0.0001746821476984154,
"loss": 8.9581,
"step": 54
},
{
"epoch": 0.08103130755064457,
"grad_norm": 13.058594703674316,
"learning_rate": 0.00017357239106731317,
"loss": 7.4741,
"step": 55
},
{
"epoch": 0.08250460405156537,
"grad_norm": 9.218979835510254,
"learning_rate": 0.00017244252047910892,
"loss": 10.1216,
"step": 56
},
{
"epoch": 0.08397790055248619,
"grad_norm": 8.803467750549316,
"learning_rate": 0.00017129284482913972,
"loss": 10.4821,
"step": 57
},
{
"epoch": 0.085451197053407,
"grad_norm": 7.895155429840088,
"learning_rate": 0.00017012367842724887,
"loss": 8.5694,
"step": 58
},
{
"epoch": 0.08692449355432781,
"grad_norm": 8.486394882202148,
"learning_rate": 0.0001689353409118566,
"loss": 10.1866,
"step": 59
},
{
"epoch": 0.08839779005524862,
"grad_norm": 8.857569694519043,
"learning_rate": 0.00016772815716257412,
"loss": 8.1711,
"step": 60
},
{
"epoch": 0.08987108655616943,
"grad_norm": 5.87221622467041,
"learning_rate": 0.0001665024572113848,
"loss": 8.2002,
"step": 61
},
{
"epoch": 0.09134438305709024,
"grad_norm": 7.224503993988037,
"learning_rate": 0.00016525857615241687,
"loss": 9.4081,
"step": 62
},
{
"epoch": 0.09281767955801105,
"grad_norm": 9.808675765991211,
"learning_rate": 0.00016399685405033167,
"loss": 7.1058,
"step": 63
},
{
"epoch": 0.09429097605893186,
"grad_norm": 12.092679977416992,
"learning_rate": 0.0001627176358473537,
"loss": 10.0414,
"step": 64
},
{
"epoch": 0.09576427255985268,
"grad_norm": 8.735736846923828,
"learning_rate": 0.0001614212712689668,
"loss": 10.7128,
"step": 65
},
{
"epoch": 0.09723756906077348,
"grad_norm": 9.30666446685791,
"learning_rate": 0.00016010811472830252,
"loss": 8.9495,
"step": 66
},
{
"epoch": 0.0987108655616943,
"grad_norm": 8.964729309082031,
"learning_rate": 0.00015877852522924732,
"loss": 6.9074,
"step": 67
},
{
"epoch": 0.1001841620626151,
"grad_norm": 8.615819931030273,
"learning_rate": 0.00015743286626829437,
"loss": 7.6531,
"step": 68
},
{
"epoch": 0.10165745856353592,
"grad_norm": 9.311439514160156,
"learning_rate": 0.0001560715057351673,
"loss": 10.6691,
"step": 69
},
{
"epoch": 0.10313075506445672,
"grad_norm": 7.247087478637695,
"learning_rate": 0.00015469481581224272,
"loss": 7.229,
"step": 70
},
{
"epoch": 0.10460405156537753,
"grad_norm": 6.454756259918213,
"learning_rate": 0.0001533031728727994,
"loss": 7.7774,
"step": 71
},
{
"epoch": 0.10607734806629834,
"grad_norm": 6.882237911224365,
"learning_rate": 0.00015189695737812152,
"loss": 7.7409,
"step": 72
},
{
"epoch": 0.10755064456721915,
"grad_norm": 6.786222457885742,
"learning_rate": 0.0001504765537734844,
"loss": 7.0605,
"step": 73
},
{
"epoch": 0.10902394106813997,
"grad_norm": 7.709743499755859,
"learning_rate": 0.00014904235038305083,
"loss": 9.9043,
"step": 74
},
{
"epoch": 0.11049723756906077,
"grad_norm": 6.459442138671875,
"learning_rate": 0.00014759473930370736,
"loss": 8.6428,
"step": 75
},
{
"epoch": 0.11197053406998159,
"grad_norm": 9.24147891998291,
"learning_rate": 0.0001461341162978688,
"loss": 9.9,
"step": 76
},
{
"epoch": 0.11344383057090239,
"grad_norm": 6.457151889801025,
"learning_rate": 0.00014466088068528068,
"loss": 10.7196,
"step": 77
},
{
"epoch": 0.11491712707182321,
"grad_norm": 3.3985164165496826,
"learning_rate": 0.00014317543523384928,
"loss": 4.1652,
"step": 78
},
{
"epoch": 0.11639042357274401,
"grad_norm": 12.46141242980957,
"learning_rate": 0.00014167818604952906,
"loss": 7.9478,
"step": 79
},
{
"epoch": 0.11786372007366483,
"grad_norm": 8.607696533203125,
"learning_rate": 0.00014016954246529696,
"loss": 8.3695,
"step": 80
},
{
"epoch": 0.11933701657458563,
"grad_norm": 8.640053749084473,
"learning_rate": 0.00013864991692924523,
"loss": 6.5266,
"step": 81
},
{
"epoch": 0.12081031307550645,
"grad_norm": 8.049505233764648,
"learning_rate": 0.00013711972489182208,
"loss": 9.0633,
"step": 82
},
{
"epoch": 0.12228360957642725,
"grad_norm": 8.616392135620117,
"learning_rate": 0.00013557938469225167,
"loss": 5.9323,
"step": 83
},
{
"epoch": 0.12375690607734807,
"grad_norm": 5.472959995269775,
"learning_rate": 0.00013402931744416433,
"loss": 6.0568,
"step": 84
},
{
"epoch": 0.1252302025782689,
"grad_norm": 7.378502368927002,
"learning_rate": 0.00013246994692046836,
"loss": 6.6528,
"step": 85
},
{
"epoch": 0.12670349907918968,
"grad_norm": 8.463314056396484,
"learning_rate": 0.00013090169943749476,
"loss": 7.2891,
"step": 86
},
{
"epoch": 0.1281767955801105,
"grad_norm": 6.927599906921387,
"learning_rate": 0.0001293250037384465,
"loss": 8.9668,
"step": 87
},
{
"epoch": 0.12965009208103132,
"grad_norm": 7.007180213928223,
"learning_rate": 0.00012774029087618446,
"loss": 6.3727,
"step": 88
},
{
"epoch": 0.1311233885819521,
"grad_norm": 8.22607135772705,
"learning_rate": 0.00012614799409538198,
"loss": 7.8068,
"step": 89
},
{
"epoch": 0.13259668508287292,
"grad_norm": 5.844438552856445,
"learning_rate": 0.00012454854871407994,
"loss": 5.3604,
"step": 90
},
{
"epoch": 0.13406998158379374,
"grad_norm": 11.601090431213379,
"learning_rate": 0.00012294239200467516,
"loss": 10.1369,
"step": 91
},
{
"epoch": 0.13554327808471456,
"grad_norm": 7.081054210662842,
"learning_rate": 0.0001213299630743747,
"loss": 8.1575,
"step": 92
},
{
"epoch": 0.13701657458563535,
"grad_norm": 11.263205528259277,
"learning_rate": 0.00011971170274514802,
"loss": 9.0753,
"step": 93
},
{
"epoch": 0.13848987108655617,
"grad_norm": 8.47836685180664,
"learning_rate": 0.000118088053433211,
"loss": 7.837,
"step": 94
},
{
"epoch": 0.13996316758747698,
"grad_norm": 7.94907283782959,
"learning_rate": 0.00011645945902807341,
"loss": 6.2531,
"step": 95
},
{
"epoch": 0.1414364640883978,
"grad_norm": 14.959242820739746,
"learning_rate": 0.0001148263647711842,
"loss": 9.7477,
"step": 96
},
{
"epoch": 0.1429097605893186,
"grad_norm": 9.983634948730469,
"learning_rate": 0.00011318921713420691,
"loss": 6.9798,
"step": 97
},
{
"epoch": 0.1443830570902394,
"grad_norm": 10.852173805236816,
"learning_rate": 0.00011154846369695863,
"loss": 7.873,
"step": 98
},
{
"epoch": 0.14585635359116023,
"grad_norm": 8.277898788452148,
"learning_rate": 0.0001099045530250463,
"loss": 6.3715,
"step": 99
},
{
"epoch": 0.14732965009208104,
"grad_norm": 6.592026710510254,
"learning_rate": 0.00010825793454723325,
"loss": 8.1482,
"step": 100
},
{
"epoch": 0.14732965009208104,
"eval_loss": 1.9596363306045532,
"eval_runtime": 9.4182,
"eval_samples_per_second": 30.367,
"eval_steps_per_second": 15.183,
"step": 100
},
{
"epoch": 0.14880294659300183,
"grad_norm": 7.7546186447143555,
"learning_rate": 0.00010660905843256994,
"loss": 7.1284,
"step": 101
},
{
"epoch": 0.15027624309392265,
"grad_norm": 8.040283203125,
"learning_rate": 0.00010495837546732224,
"loss": 7.7712,
"step": 102
},
{
"epoch": 0.15174953959484347,
"grad_norm": 5.6713547706604,
"learning_rate": 0.00010330633693173082,
"loss": 5.3149,
"step": 103
},
{
"epoch": 0.15322283609576426,
"grad_norm": 7.573396682739258,
"learning_rate": 0.00010165339447663587,
"loss": 8.7858,
"step": 104
},
{
"epoch": 0.15469613259668508,
"grad_norm": 9.673140525817871,
"learning_rate": 0.0001,
"loss": 7.4904,
"step": 105
},
{
"epoch": 0.1561694290976059,
"grad_norm": 13.609859466552734,
"learning_rate": 9.834660552336415e-05,
"loss": 9.5067,
"step": 106
},
{
"epoch": 0.1576427255985267,
"grad_norm": 9.656366348266602,
"learning_rate": 9.669366306826919e-05,
"loss": 10.8401,
"step": 107
},
{
"epoch": 0.1591160220994475,
"grad_norm": 12.622513771057129,
"learning_rate": 9.504162453267777e-05,
"loss": 7.4235,
"step": 108
},
{
"epoch": 0.16058931860036832,
"grad_norm": 6.947592258453369,
"learning_rate": 9.339094156743007e-05,
"loss": 8.8876,
"step": 109
},
{
"epoch": 0.16206261510128914,
"grad_norm": 7.011374473571777,
"learning_rate": 9.174206545276677e-05,
"loss": 5.4014,
"step": 110
},
{
"epoch": 0.16353591160220995,
"grad_norm": 4.517526626586914,
"learning_rate": 9.009544697495374e-05,
"loss": 5.814,
"step": 111
},
{
"epoch": 0.16500920810313074,
"grad_norm": 6.089804172515869,
"learning_rate": 8.845153630304139e-05,
"loss": 6.8508,
"step": 112
},
{
"epoch": 0.16648250460405156,
"grad_norm": 10.510293006896973,
"learning_rate": 8.681078286579311e-05,
"loss": 9.7658,
"step": 113
},
{
"epoch": 0.16795580110497238,
"grad_norm": 9.174927711486816,
"learning_rate": 8.517363522881579e-05,
"loss": 7.1456,
"step": 114
},
{
"epoch": 0.1694290976058932,
"grad_norm": 7.33340311050415,
"learning_rate": 8.35405409719266e-05,
"loss": 6.902,
"step": 115
},
{
"epoch": 0.170902394106814,
"grad_norm": 6.4531779289245605,
"learning_rate": 8.191194656678904e-05,
"loss": 6.6226,
"step": 116
},
{
"epoch": 0.1723756906077348,
"grad_norm": 9.962913513183594,
"learning_rate": 8.028829725485199e-05,
"loss": 9.6444,
"step": 117
},
{
"epoch": 0.17384898710865562,
"grad_norm": 5.590907573699951,
"learning_rate": 7.867003692562534e-05,
"loss": 7.2986,
"step": 118
},
{
"epoch": 0.17532228360957644,
"grad_norm": 10.6129150390625,
"learning_rate": 7.705760799532485e-05,
"loss": 7.5536,
"step": 119
},
{
"epoch": 0.17679558011049723,
"grad_norm": 14.160097122192383,
"learning_rate": 7.54514512859201e-05,
"loss": 12.2425,
"step": 120
},
{
"epoch": 0.17826887661141805,
"grad_norm": 10.54971694946289,
"learning_rate": 7.385200590461803e-05,
"loss": 6.7272,
"step": 121
},
{
"epoch": 0.17974217311233887,
"grad_norm": 6.65580415725708,
"learning_rate": 7.225970912381556e-05,
"loss": 6.8475,
"step": 122
},
{
"epoch": 0.18121546961325966,
"grad_norm": 10.194478034973145,
"learning_rate": 7.067499626155354e-05,
"loss": 8.6189,
"step": 123
},
{
"epoch": 0.18268876611418047,
"grad_norm": 11.780241012573242,
"learning_rate": 6.909830056250527e-05,
"loss": 8.392,
"step": 124
},
{
"epoch": 0.1841620626151013,
"grad_norm": 6.544031143188477,
"learning_rate": 6.753005307953167e-05,
"loss": 7.9356,
"step": 125
},
{
"epoch": 0.1856353591160221,
"grad_norm": 5.778688430786133,
"learning_rate": 6.59706825558357e-05,
"loss": 4.8296,
"step": 126
},
{
"epoch": 0.1871086556169429,
"grad_norm": 13.133682250976562,
"learning_rate": 6.442061530774834e-05,
"loss": 8.4469,
"step": 127
},
{
"epoch": 0.18858195211786372,
"grad_norm": 5.862144947052002,
"learning_rate": 6.28802751081779e-05,
"loss": 5.7135,
"step": 128
},
{
"epoch": 0.19005524861878453,
"grad_norm": 5.824400901794434,
"learning_rate": 6.135008307075481e-05,
"loss": 7.4102,
"step": 129
},
{
"epoch": 0.19152854511970535,
"grad_norm": 7.972049713134766,
"learning_rate": 5.983045753470308e-05,
"loss": 7.9903,
"step": 130
},
{
"epoch": 0.19300184162062614,
"grad_norm": 7.148801803588867,
"learning_rate": 5.832181395047098e-05,
"loss": 4.9407,
"step": 131
},
{
"epoch": 0.19447513812154696,
"grad_norm": 4.160274028778076,
"learning_rate": 5.6824564766150726e-05,
"loss": 7.0311,
"step": 132
},
{
"epoch": 0.19594843462246778,
"grad_norm": 4.829346656799316,
"learning_rate": 5.533911931471936e-05,
"loss": 5.5874,
"step": 133
},
{
"epoch": 0.1974217311233886,
"grad_norm": 8.297733306884766,
"learning_rate": 5.386588370213124e-05,
"loss": 6.3769,
"step": 134
},
{
"epoch": 0.19889502762430938,
"grad_norm": 5.839636325836182,
"learning_rate": 5.240526069629265e-05,
"loss": 6.8749,
"step": 135
},
{
"epoch": 0.2003683241252302,
"grad_norm": 7.078559398651123,
"learning_rate": 5.095764961694922e-05,
"loss": 6.4378,
"step": 136
},
{
"epoch": 0.20184162062615102,
"grad_norm": 5.329637050628662,
"learning_rate": 4.952344622651566e-05,
"loss": 6.1027,
"step": 137
},
{
"epoch": 0.20331491712707184,
"grad_norm": 10.604938507080078,
"learning_rate": 4.810304262187852e-05,
"loss": 9.6319,
"step": 138
},
{
"epoch": 0.20478821362799263,
"grad_norm": 10.23065185546875,
"learning_rate": 4.669682712720065e-05,
"loss": 10.1313,
"step": 139
},
{
"epoch": 0.20626151012891344,
"grad_norm": 14.528596878051758,
"learning_rate": 4.530518418775733e-05,
"loss": 8.1347,
"step": 140
},
{
"epoch": 0.20773480662983426,
"grad_norm": 5.988021373748779,
"learning_rate": 4.392849426483274e-05,
"loss": 8.9566,
"step": 141
},
{
"epoch": 0.20920810313075505,
"grad_norm": 13.86946964263916,
"learning_rate": 4.256713373170564e-05,
"loss": 7.2571,
"step": 142
},
{
"epoch": 0.21068139963167587,
"grad_norm": 8.190982818603516,
"learning_rate": 4.12214747707527e-05,
"loss": 6.508,
"step": 143
},
{
"epoch": 0.2121546961325967,
"grad_norm": 8.50158405303955,
"learning_rate": 3.9891885271697496e-05,
"loss": 5.1829,
"step": 144
},
{
"epoch": 0.2136279926335175,
"grad_norm": 9.470782279968262,
"learning_rate": 3.857872873103322e-05,
"loss": 6.3869,
"step": 145
},
{
"epoch": 0.2151012891344383,
"grad_norm": 9.785574913024902,
"learning_rate": 3.7282364152646297e-05,
"loss": 7.6541,
"step": 146
},
{
"epoch": 0.2165745856353591,
"grad_norm": 5.911442756652832,
"learning_rate": 3.600314594966834e-05,
"loss": 5.7766,
"step": 147
},
{
"epoch": 0.21804788213627993,
"grad_norm": 5.854257583618164,
"learning_rate": 3.4741423847583134e-05,
"loss": 4.5367,
"step": 148
},
{
"epoch": 0.21952117863720075,
"grad_norm": 12.969705581665039,
"learning_rate": 3.349754278861517e-05,
"loss": 8.9383,
"step": 149
},
{
"epoch": 0.22099447513812154,
"grad_norm": 9.376482963562012,
"learning_rate": 3.227184283742591e-05,
"loss": 9.8813,
"step": 150
},
{
"epoch": 0.22099447513812154,
"eval_loss": 1.8338268995285034,
"eval_runtime": 9.4611,
"eval_samples_per_second": 30.229,
"eval_steps_per_second": 15.115,
"step": 150
},
{
"epoch": 0.22246777163904236,
"grad_norm": 7.644078731536865,
"learning_rate": 3.106465908814342e-05,
"loss": 6.0862,
"step": 151
},
{
"epoch": 0.22394106813996317,
"grad_norm": 10.181632995605469,
"learning_rate": 2.9876321572751144e-05,
"loss": 11.6419,
"step": 152
},
{
"epoch": 0.225414364640884,
"grad_norm": 10.395967483520508,
"learning_rate": 2.87071551708603e-05,
"loss": 7.4106,
"step": 153
},
{
"epoch": 0.22688766114180478,
"grad_norm": 9.284590721130371,
"learning_rate": 2.7557479520891104e-05,
"loss": 9.6296,
"step": 154
},
{
"epoch": 0.2283609576427256,
"grad_norm": 9.491522789001465,
"learning_rate": 2.6427608932686843e-05,
"loss": 7.7744,
"step": 155
},
{
"epoch": 0.22983425414364642,
"grad_norm": 14.384906768798828,
"learning_rate": 2.5317852301584643e-05,
"loss": 8.2422,
"step": 156
},
{
"epoch": 0.2313075506445672,
"grad_norm": 9.905705451965332,
"learning_rate": 2.422851302396655e-05,
"loss": 9.2604,
"step": 157
},
{
"epoch": 0.23278084714548802,
"grad_norm": 4.367447853088379,
"learning_rate": 2.315988891431412e-05,
"loss": 4.1067,
"step": 158
},
{
"epoch": 0.23425414364640884,
"grad_norm": 11.153772354125977,
"learning_rate": 2.2112272123788768e-05,
"loss": 7.3027,
"step": 159
},
{
"epoch": 0.23572744014732966,
"grad_norm": 8.646809577941895,
"learning_rate": 2.1085949060360654e-05,
"loss": 6.6389,
"step": 160
},
{
"epoch": 0.23720073664825045,
"grad_norm": 15.441944122314453,
"learning_rate": 2.008120031050753e-05,
"loss": 7.037,
"step": 161
},
{
"epoch": 0.23867403314917127,
"grad_norm": 10.072053909301758,
"learning_rate": 1.9098300562505266e-05,
"loss": 7.1396,
"step": 162
},
{
"epoch": 0.24014732965009208,
"grad_norm": 6.161656379699707,
"learning_rate": 1.8137518531330767e-05,
"loss": 5.8051,
"step": 163
},
{
"epoch": 0.2416206261510129,
"grad_norm": 9.943297386169434,
"learning_rate": 1.7199116885197995e-05,
"loss": 8.8631,
"step": 164
},
{
"epoch": 0.2430939226519337,
"grad_norm": 12.956791877746582,
"learning_rate": 1.6283352173747145e-05,
"loss": 5.8573,
"step": 165
},
{
"epoch": 0.2445672191528545,
"grad_norm": 6.923314571380615,
"learning_rate": 1.5390474757906446e-05,
"loss": 7.4056,
"step": 166
},
{
"epoch": 0.24604051565377533,
"grad_norm": 14.149099349975586,
"learning_rate": 1.4520728741446089e-05,
"loss": 10.0937,
"step": 167
},
{
"epoch": 0.24751381215469614,
"grad_norm": 9.165054321289062,
"learning_rate": 1.3674351904242611e-05,
"loss": 8.1644,
"step": 168
},
{
"epoch": 0.24898710865561693,
"grad_norm": 9.420945167541504,
"learning_rate": 1.2851575637272262e-05,
"loss": 7.6371,
"step": 169
},
{
"epoch": 0.2504604051565378,
"grad_norm": 6.907212734222412,
"learning_rate": 1.2052624879351104e-05,
"loss": 6.2545,
"step": 170
},
{
"epoch": 0.25193370165745854,
"grad_norm": 6.471442699432373,
"learning_rate": 1.1277718055638819e-05,
"loss": 7.0496,
"step": 171
},
{
"epoch": 0.25340699815837936,
"grad_norm": 7.961968421936035,
"learning_rate": 1.0527067017923654e-05,
"loss": 7.9685,
"step": 172
},
{
"epoch": 0.2548802946593002,
"grad_norm": 6.750203609466553,
"learning_rate": 9.80087698670411e-06,
"loss": 4.4272,
"step": 173
},
{
"epoch": 0.256353591160221,
"grad_norm": 7.331230163574219,
"learning_rate": 9.09934649508375e-06,
"loss": 4.6844,
"step": 174
},
{
"epoch": 0.2578268876611418,
"grad_norm": 8.612319946289062,
"learning_rate": 8.422667334494249e-06,
"loss": 6.4878,
"step": 175
},
{
"epoch": 0.25930018416206263,
"grad_norm": 15.962565422058105,
"learning_rate": 7.771024502261526e-06,
"loss": 10.4547,
"step": 176
},
{
"epoch": 0.26077348066298345,
"grad_norm": 11.007623672485352,
"learning_rate": 7.144596151029303e-06,
"loss": 8.9079,
"step": 177
},
{
"epoch": 0.2622467771639042,
"grad_norm": 5.049574375152588,
"learning_rate": 6.543553540053926e-06,
"loss": 5.1004,
"step": 178
},
{
"epoch": 0.263720073664825,
"grad_norm": 7.689352035522461,
"learning_rate": 5.968060988383883e-06,
"loss": 6.4234,
"step": 179
},
{
"epoch": 0.26519337016574585,
"grad_norm": 12.746678352355957,
"learning_rate": 5.418275829936537e-06,
"loss": 10.7555,
"step": 180
},
{
"epoch": 0.26666666666666666,
"grad_norm": 8.217164039611816,
"learning_rate": 4.8943483704846475e-06,
"loss": 6.3151,
"step": 181
},
{
"epoch": 0.2681399631675875,
"grad_norm": 8.921655654907227,
"learning_rate": 4.3964218465642355e-06,
"loss": 8.7948,
"step": 182
},
{
"epoch": 0.2696132596685083,
"grad_norm": 7.391983509063721,
"learning_rate": 3.924632386315186e-06,
"loss": 5.6443,
"step": 183
},
{
"epoch": 0.2710865561694291,
"grad_norm": 6.958240032196045,
"learning_rate": 3.4791089722651436e-06,
"loss": 6.8103,
"step": 184
},
{
"epoch": 0.27255985267034993,
"grad_norm": 9.752053260803223,
"learning_rate": 3.059973406066963e-06,
"loss": 5.7348,
"step": 185
},
{
"epoch": 0.2740331491712707,
"grad_norm": 7.452392578125,
"learning_rate": 2.667340275199426e-06,
"loss": 8.5893,
"step": 186
},
{
"epoch": 0.2755064456721915,
"grad_norm": 8.648473739624023,
"learning_rate": 2.3013169216400733e-06,
"loss": 8.2165,
"step": 187
},
{
"epoch": 0.27697974217311233,
"grad_norm": 10.441420555114746,
"learning_rate": 1.9620034125190644e-06,
"loss": 6.9184,
"step": 188
},
{
"epoch": 0.27845303867403315,
"grad_norm": 9.087239265441895,
"learning_rate": 1.6494925127617634e-06,
"loss": 9.28,
"step": 189
},
{
"epoch": 0.27992633517495397,
"grad_norm": 7.3535542488098145,
"learning_rate": 1.3638696597277679e-06,
"loss": 6.3341,
"step": 190
},
{
"epoch": 0.2813996316758748,
"grad_norm": 8.444154739379883,
"learning_rate": 1.1052129398531507e-06,
"loss": 7.9693,
"step": 191
},
{
"epoch": 0.2828729281767956,
"grad_norm": 9.900870323181152,
"learning_rate": 8.735930673024806e-07,
"loss": 5.7817,
"step": 192
},
{
"epoch": 0.28434622467771636,
"grad_norm": 14.024637222290039,
"learning_rate": 6.690733646361857e-07,
"loss": 9.6444,
"step": 193
},
{
"epoch": 0.2858195211786372,
"grad_norm": 5.964371204376221,
"learning_rate": 4.917097454988584e-07,
"loss": 5.2127,
"step": 194
},
{
"epoch": 0.287292817679558,
"grad_norm": 8.721577644348145,
"learning_rate": 3.415506993330153e-07,
"loss": 9.1063,
"step": 195
},
{
"epoch": 0.2887661141804788,
"grad_norm": 6.445766925811768,
"learning_rate": 2.1863727812254653e-07,
"loss": 5.1139,
"step": 196
},
{
"epoch": 0.29023941068139963,
"grad_norm": 6.205690860748291,
"learning_rate": 1.230030851695263e-07,
"loss": 4.9742,
"step": 197
},
{
"epoch": 0.29171270718232045,
"grad_norm": 8.137059211730957,
"learning_rate": 5.467426590739511e-08,
"loss": 8.3932,
"step": 198
},
{
"epoch": 0.29318600368324127,
"grad_norm": 5.232216835021973,
"learning_rate": 1.3669500753099585e-08,
"loss": 6.5716,
"step": 199
},
{
"epoch": 0.2946593001841621,
"grad_norm": 7.499634265899658,
"learning_rate": 0.0,
"loss": 6.5585,
"step": 200
},
{
"epoch": 0.2946593001841621,
"eval_loss": 1.8100769519805908,
"eval_runtime": 9.4494,
"eval_samples_per_second": 30.266,
"eval_steps_per_second": 15.133,
"step": 200
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 3.2900734689214464e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}