masatochi's picture
Training in progress, step 195, checkpoint
10c5dd7 verified
raw
history blame
35.8 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.0953603520997616,
"eval_steps": 34,
"global_step": 195,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0004890274466654441,
"grad_norm": 1.7833456993103027,
"learning_rate": 6.666666666666667e-06,
"loss": 2.9376,
"step": 1
},
{
"epoch": 0.0004890274466654441,
"eval_loss": 3.230164051055908,
"eval_runtime": 359.3683,
"eval_samples_per_second": 7.188,
"eval_steps_per_second": 2.396,
"step": 1
},
{
"epoch": 0.0009780548933308881,
"grad_norm": 2.0391061305999756,
"learning_rate": 1.3333333333333333e-05,
"loss": 3.3263,
"step": 2
},
{
"epoch": 0.0014670823399963323,
"grad_norm": 1.8410208225250244,
"learning_rate": 2e-05,
"loss": 3.3569,
"step": 3
},
{
"epoch": 0.0019561097866617762,
"grad_norm": 1.743186593055725,
"learning_rate": 2.6666666666666667e-05,
"loss": 2.7792,
"step": 4
},
{
"epoch": 0.0024451372333272204,
"grad_norm": 1.8234602212905884,
"learning_rate": 3.3333333333333335e-05,
"loss": 3.3146,
"step": 5
},
{
"epoch": 0.0029341646799926646,
"grad_norm": 1.7488245964050293,
"learning_rate": 4e-05,
"loss": 3.3458,
"step": 6
},
{
"epoch": 0.0034231921266581087,
"grad_norm": 1.7737092971801758,
"learning_rate": 4.666666666666667e-05,
"loss": 3.1208,
"step": 7
},
{
"epoch": 0.0039122195733235525,
"grad_norm": 2.4333255290985107,
"learning_rate": 5.333333333333333e-05,
"loss": 3.9434,
"step": 8
},
{
"epoch": 0.004401247019988997,
"grad_norm": 1.9338016510009766,
"learning_rate": 6e-05,
"loss": 3.1182,
"step": 9
},
{
"epoch": 0.004890274466654441,
"grad_norm": 2.025571584701538,
"learning_rate": 6.666666666666667e-05,
"loss": 2.8125,
"step": 10
},
{
"epoch": 0.005379301913319885,
"grad_norm": 2.0819053649902344,
"learning_rate": 7.333333333333333e-05,
"loss": 3.2407,
"step": 11
},
{
"epoch": 0.005868329359985329,
"grad_norm": 2.082847833633423,
"learning_rate": 8e-05,
"loss": 2.8353,
"step": 12
},
{
"epoch": 0.006357356806650773,
"grad_norm": 2.3587448596954346,
"learning_rate": 8.666666666666667e-05,
"loss": 2.9856,
"step": 13
},
{
"epoch": 0.0068463842533162175,
"grad_norm": 2.4387998580932617,
"learning_rate": 9.333333333333334e-05,
"loss": 2.9301,
"step": 14
},
{
"epoch": 0.007335411699981661,
"grad_norm": 2.9760613441467285,
"learning_rate": 0.0001,
"loss": 3.1079,
"step": 15
},
{
"epoch": 0.007824439146647105,
"grad_norm": 3.227975368499756,
"learning_rate": 0.00010666666666666667,
"loss": 2.6794,
"step": 16
},
{
"epoch": 0.00831346659331255,
"grad_norm": 2.7716498374938965,
"learning_rate": 0.00011333333333333334,
"loss": 2.5439,
"step": 17
},
{
"epoch": 0.008802494039977994,
"grad_norm": 3.163443088531494,
"learning_rate": 0.00012,
"loss": 2.2788,
"step": 18
},
{
"epoch": 0.009291521486643438,
"grad_norm": 2.4735147953033447,
"learning_rate": 0.00012666666666666666,
"loss": 2.1162,
"step": 19
},
{
"epoch": 0.009780548933308882,
"grad_norm": 3.1054129600524902,
"learning_rate": 0.00013333333333333334,
"loss": 2.0727,
"step": 20
},
{
"epoch": 0.010269576379974325,
"grad_norm": 3.356247663497925,
"learning_rate": 0.00014,
"loss": 1.9824,
"step": 21
},
{
"epoch": 0.01075860382663977,
"grad_norm": 2.9118664264678955,
"learning_rate": 0.00014666666666666666,
"loss": 1.8217,
"step": 22
},
{
"epoch": 0.011247631273305215,
"grad_norm": 2.7468883991241455,
"learning_rate": 0.00015333333333333334,
"loss": 1.6995,
"step": 23
},
{
"epoch": 0.011736658719970658,
"grad_norm": 2.3634603023529053,
"learning_rate": 0.00016,
"loss": 1.227,
"step": 24
},
{
"epoch": 0.012225686166636102,
"grad_norm": 3.037814140319824,
"learning_rate": 0.0001666666666666667,
"loss": 1.8027,
"step": 25
},
{
"epoch": 0.012714713613301546,
"grad_norm": 2.752764940261841,
"learning_rate": 0.00017333333333333334,
"loss": 1.7639,
"step": 26
},
{
"epoch": 0.013203741059966991,
"grad_norm": 2.892385959625244,
"learning_rate": 0.00018,
"loss": 1.6834,
"step": 27
},
{
"epoch": 0.013692768506632435,
"grad_norm": 2.9906463623046875,
"learning_rate": 0.0001866666666666667,
"loss": 1.4218,
"step": 28
},
{
"epoch": 0.014181795953297879,
"grad_norm": 2.9632151126861572,
"learning_rate": 0.00019333333333333333,
"loss": 1.3927,
"step": 29
},
{
"epoch": 0.014670823399963322,
"grad_norm": 2.448162317276001,
"learning_rate": 0.0002,
"loss": 1.4403,
"step": 30
},
{
"epoch": 0.015159850846628768,
"grad_norm": 2.5981829166412354,
"learning_rate": 0.00019998292504580528,
"loss": 1.4423,
"step": 31
},
{
"epoch": 0.01564887829329421,
"grad_norm": 2.8459675312042236,
"learning_rate": 0.0001999317060143023,
"loss": 1.7064,
"step": 32
},
{
"epoch": 0.016137905739959654,
"grad_norm": 2.421919584274292,
"learning_rate": 0.0001998463603967434,
"loss": 1.3588,
"step": 33
},
{
"epoch": 0.0166269331866251,
"grad_norm": 1.9193148612976074,
"learning_rate": 0.00019972691733857883,
"loss": 1.2639,
"step": 34
},
{
"epoch": 0.0166269331866251,
"eval_loss": 1.3727614879608154,
"eval_runtime": 359.4969,
"eval_samples_per_second": 7.185,
"eval_steps_per_second": 2.395,
"step": 34
},
{
"epoch": 0.017115960633290545,
"grad_norm": 1.920526385307312,
"learning_rate": 0.00019957341762950344,
"loss": 1.2483,
"step": 35
},
{
"epoch": 0.017604988079955988,
"grad_norm": 1.9913910627365112,
"learning_rate": 0.0001993859136895274,
"loss": 1.3637,
"step": 36
},
{
"epoch": 0.018094015526621432,
"grad_norm": 1.9702675342559814,
"learning_rate": 0.00019916446955107428,
"loss": 1.1832,
"step": 37
},
{
"epoch": 0.018583042973286876,
"grad_norm": 2.1708314418792725,
"learning_rate": 0.0001989091608371146,
"loss": 1.152,
"step": 38
},
{
"epoch": 0.01907207041995232,
"grad_norm": 2.122941493988037,
"learning_rate": 0.00019862007473534025,
"loss": 1.3422,
"step": 39
},
{
"epoch": 0.019561097866617763,
"grad_norm": 2.145552396774292,
"learning_rate": 0.0001982973099683902,
"loss": 1.3505,
"step": 40
},
{
"epoch": 0.020050125313283207,
"grad_norm": 1.833509087562561,
"learning_rate": 0.0001979409767601366,
"loss": 1.2202,
"step": 41
},
{
"epoch": 0.02053915275994865,
"grad_norm": 1.7310895919799805,
"learning_rate": 0.00019755119679804367,
"loss": 1.195,
"step": 42
},
{
"epoch": 0.021028180206614098,
"grad_norm": 1.8683947324752808,
"learning_rate": 0.0001971281031916114,
"loss": 1.1253,
"step": 43
},
{
"epoch": 0.02151720765327954,
"grad_norm": 2.3223490715026855,
"learning_rate": 0.00019667184042691875,
"loss": 1.3399,
"step": 44
},
{
"epoch": 0.022006235099944985,
"grad_norm": 2.210232734680176,
"learning_rate": 0.00019618256431728194,
"loss": 1.4471,
"step": 45
},
{
"epoch": 0.02249526254661043,
"grad_norm": 2.205853223800659,
"learning_rate": 0.0001956604419500441,
"loss": 1.3604,
"step": 46
},
{
"epoch": 0.022984289993275873,
"grad_norm": 1.8296672105789185,
"learning_rate": 0.00019510565162951537,
"loss": 1.2646,
"step": 47
},
{
"epoch": 0.023473317439941317,
"grad_norm": 2.1027016639709473,
"learning_rate": 0.00019451838281608197,
"loss": 1.3886,
"step": 48
},
{
"epoch": 0.02396234488660676,
"grad_norm": 2.2461299896240234,
"learning_rate": 0.00019389883606150566,
"loss": 1.3794,
"step": 49
},
{
"epoch": 0.024451372333272204,
"grad_norm": 1.745917558670044,
"learning_rate": 0.00019324722294043558,
"loss": 1.2026,
"step": 50
},
{
"epoch": 0.024940399779937648,
"grad_norm": 2.0499846935272217,
"learning_rate": 0.00019256376597815564,
"loss": 1.1625,
"step": 51
},
{
"epoch": 0.02542942722660309,
"grad_norm": 1.8696260452270508,
"learning_rate": 0.00019184869857459232,
"loss": 1.3136,
"step": 52
},
{
"epoch": 0.02591845467326854,
"grad_norm": 1.7452571392059326,
"learning_rate": 0.00019110226492460885,
"loss": 1.1156,
"step": 53
},
{
"epoch": 0.026407482119933982,
"grad_norm": 1.8465955257415771,
"learning_rate": 0.0001903247199346129,
"loss": 1.3804,
"step": 54
},
{
"epoch": 0.026896509566599426,
"grad_norm": 1.8307727575302124,
"learning_rate": 0.00018951632913550626,
"loss": 1.1383,
"step": 55
},
{
"epoch": 0.02738553701326487,
"grad_norm": 1.838446021080017,
"learning_rate": 0.0001886773685920062,
"loss": 1.2084,
"step": 56
},
{
"epoch": 0.027874564459930314,
"grad_norm": 1.735639214515686,
"learning_rate": 0.0001878081248083698,
"loss": 1.2512,
"step": 57
},
{
"epoch": 0.028363591906595757,
"grad_norm": 1.6714195013046265,
"learning_rate": 0.00018690889463055283,
"loss": 1.3269,
"step": 58
},
{
"epoch": 0.0288526193532612,
"grad_norm": 1.6168848276138306,
"learning_rate": 0.00018597998514483725,
"loss": 1.098,
"step": 59
},
{
"epoch": 0.029341646799926645,
"grad_norm": 1.738674521446228,
"learning_rate": 0.00018502171357296144,
"loss": 1.3552,
"step": 60
},
{
"epoch": 0.02983067424659209,
"grad_norm": 1.772955060005188,
"learning_rate": 0.00018403440716378928,
"loss": 1.1874,
"step": 61
},
{
"epoch": 0.030319701693257536,
"grad_norm": 1.692875862121582,
"learning_rate": 0.00018301840308155507,
"loss": 1.3587,
"step": 62
},
{
"epoch": 0.03080872913992298,
"grad_norm": 1.8497170209884644,
"learning_rate": 0.00018197404829072215,
"loss": 1.4933,
"step": 63
},
{
"epoch": 0.03129775658658842,
"grad_norm": 1.5033533573150635,
"learning_rate": 0.00018090169943749476,
"loss": 1.0175,
"step": 64
},
{
"epoch": 0.03178678403325386,
"grad_norm": 1.7840133905410767,
"learning_rate": 0.000179801722728024,
"loss": 1.4609,
"step": 65
},
{
"epoch": 0.03227581147991931,
"grad_norm": 1.770972728729248,
"learning_rate": 0.00017867449380334834,
"loss": 1.2546,
"step": 66
},
{
"epoch": 0.03276483892658476,
"grad_norm": 1.7338752746582031,
"learning_rate": 0.00017752039761111297,
"loss": 1.3215,
"step": 67
},
{
"epoch": 0.0332538663732502,
"grad_norm": 1.7595053911209106,
"learning_rate": 0.00017633982827411032,
"loss": 1.3889,
"step": 68
},
{
"epoch": 0.0332538663732502,
"eval_loss": 1.235534906387329,
"eval_runtime": 358.2205,
"eval_samples_per_second": 7.211,
"eval_steps_per_second": 2.404,
"step": 68
},
{
"epoch": 0.033742893819915645,
"grad_norm": 1.5258216857910156,
"learning_rate": 0.00017513318895568737,
"loss": 1.1886,
"step": 69
},
{
"epoch": 0.03423192126658109,
"grad_norm": 1.972506046295166,
"learning_rate": 0.00017390089172206592,
"loss": 1.5285,
"step": 70
},
{
"epoch": 0.03472094871324653,
"grad_norm": 1.6796947717666626,
"learning_rate": 0.00017264335740162242,
"loss": 1.3502,
"step": 71
},
{
"epoch": 0.035209976159911976,
"grad_norm": 1.4769248962402344,
"learning_rate": 0.00017136101544117525,
"loss": 1.4497,
"step": 72
},
{
"epoch": 0.03569900360657742,
"grad_norm": 1.5520527362823486,
"learning_rate": 0.0001700543037593291,
"loss": 1.0656,
"step": 73
},
{
"epoch": 0.036188031053242864,
"grad_norm": 1.7418780326843262,
"learning_rate": 0.00016872366859692627,
"loss": 1.5151,
"step": 74
},
{
"epoch": 0.03667705849990831,
"grad_norm": 1.6695711612701416,
"learning_rate": 0.00016736956436465573,
"loss": 1.531,
"step": 75
},
{
"epoch": 0.03716608594657375,
"grad_norm": 1.574851155281067,
"learning_rate": 0.0001659924534878723,
"loss": 0.8986,
"step": 76
},
{
"epoch": 0.037655113393239195,
"grad_norm": 1.5195201635360718,
"learning_rate": 0.00016459280624867874,
"loss": 1.145,
"step": 77
},
{
"epoch": 0.03814414083990464,
"grad_norm": 1.6742786169052124,
"learning_rate": 0.0001631711006253251,
"loss": 1.436,
"step": 78
},
{
"epoch": 0.03863316828657008,
"grad_norm": 1.506365418434143,
"learning_rate": 0.0001617278221289793,
"loss": 1.1164,
"step": 79
},
{
"epoch": 0.039122195733235526,
"grad_norm": 1.5771400928497314,
"learning_rate": 0.00016026346363792567,
"loss": 1.2573,
"step": 80
},
{
"epoch": 0.03961122317990097,
"grad_norm": 1.5452238321304321,
"learning_rate": 0.00015877852522924732,
"loss": 1.3623,
"step": 81
},
{
"epoch": 0.040100250626566414,
"grad_norm": 1.357657551765442,
"learning_rate": 0.00015727351400805052,
"loss": 0.9288,
"step": 82
},
{
"epoch": 0.04058927807323186,
"grad_norm": 1.673086166381836,
"learning_rate": 0.00015574894393428855,
"loss": 1.2445,
"step": 83
},
{
"epoch": 0.0410783055198973,
"grad_norm": 1.8412545919418335,
"learning_rate": 0.00015420533564724495,
"loss": 1.5749,
"step": 84
},
{
"epoch": 0.041567332966562745,
"grad_norm": 1.6450231075286865,
"learning_rate": 0.0001526432162877356,
"loss": 1.2591,
"step": 85
},
{
"epoch": 0.042056360413228196,
"grad_norm": 1.3985604047775269,
"learning_rate": 0.0001510631193180907,
"loss": 1.0892,
"step": 86
},
{
"epoch": 0.04254538785989364,
"grad_norm": 1.7090120315551758,
"learning_rate": 0.0001494655843399779,
"loss": 1.1302,
"step": 87
},
{
"epoch": 0.04303441530655908,
"grad_norm": 1.8884952068328857,
"learning_rate": 0.00014785115691012864,
"loss": 1.2456,
"step": 88
},
{
"epoch": 0.04352344275322453,
"grad_norm": 1.6783995628356934,
"learning_rate": 0.00014622038835403133,
"loss": 1.5719,
"step": 89
},
{
"epoch": 0.04401247019988997,
"grad_norm": 1.613410234451294,
"learning_rate": 0.00014457383557765386,
"loss": 1.1634,
"step": 90
},
{
"epoch": 0.044501497646555414,
"grad_norm": 1.611494779586792,
"learning_rate": 0.0001429120608772609,
"loss": 1.3624,
"step": 91
},
{
"epoch": 0.04499052509322086,
"grad_norm": 1.3502241373062134,
"learning_rate": 0.00014123563174739037,
"loss": 1.2014,
"step": 92
},
{
"epoch": 0.0454795525398863,
"grad_norm": 1.5110281705856323,
"learning_rate": 0.00013954512068705424,
"loss": 1.0874,
"step": 93
},
{
"epoch": 0.045968579986551746,
"grad_norm": 1.3031861782073975,
"learning_rate": 0.00013784110500423104,
"loss": 1.0143,
"step": 94
},
{
"epoch": 0.04645760743321719,
"grad_norm": 1.5285643339157104,
"learning_rate": 0.00013612416661871533,
"loss": 1.2189,
"step": 95
},
{
"epoch": 0.04694663487988263,
"grad_norm": 1.6296824216842651,
"learning_rate": 0.00013439489186339282,
"loss": 1.0745,
"step": 96
},
{
"epoch": 0.04743566232654808,
"grad_norm": 2.1351568698883057,
"learning_rate": 0.0001326538712840083,
"loss": 1.1673,
"step": 97
},
{
"epoch": 0.04792468977321352,
"grad_norm": 1.6928352117538452,
"learning_rate": 0.00013090169943749476,
"loss": 1.2757,
"step": 98
},
{
"epoch": 0.048413717219878964,
"grad_norm": 1.6213932037353516,
"learning_rate": 0.00012913897468893248,
"loss": 1.3475,
"step": 99
},
{
"epoch": 0.04890274466654441,
"grad_norm": 1.3512767553329468,
"learning_rate": 0.0001273662990072083,
"loss": 0.9948,
"step": 100
},
{
"epoch": 0.04939177211320985,
"grad_norm": 1.4925191402435303,
"learning_rate": 0.00012558427775944357,
"loss": 1.2981,
"step": 101
},
{
"epoch": 0.049880799559875295,
"grad_norm": 1.6407502889633179,
"learning_rate": 0.00012379351950426187,
"loss": 1.084,
"step": 102
},
{
"epoch": 0.049880799559875295,
"eval_loss": 1.1849300861358643,
"eval_runtime": 357.7786,
"eval_samples_per_second": 7.22,
"eval_steps_per_second": 2.407,
"step": 102
},
{
"epoch": 0.05036982700654074,
"grad_norm": 1.4403208494186401,
"learning_rate": 0.00012199463578396688,
"loss": 0.9287,
"step": 103
},
{
"epoch": 0.05085885445320618,
"grad_norm": 1.788495421409607,
"learning_rate": 0.00012018824091570103,
"loss": 1.3749,
"step": 104
},
{
"epoch": 0.051347881899871634,
"grad_norm": 1.3187726736068726,
"learning_rate": 0.00011837495178165706,
"loss": 0.9059,
"step": 105
},
{
"epoch": 0.05183690934653708,
"grad_norm": 1.8266162872314453,
"learning_rate": 0.000116555387618413,
"loss": 1.1925,
"step": 106
},
{
"epoch": 0.05232593679320252,
"grad_norm": 1.780070424079895,
"learning_rate": 0.00011473016980546377,
"loss": 1.248,
"step": 107
},
{
"epoch": 0.052814964239867965,
"grad_norm": 2.0775444507598877,
"learning_rate": 0.00011289992165302035,
"loss": 1.3379,
"step": 108
},
{
"epoch": 0.05330399168653341,
"grad_norm": 1.8501131534576416,
"learning_rate": 0.00011106526818915008,
"loss": 1.3934,
"step": 109
},
{
"epoch": 0.05379301913319885,
"grad_norm": 1.610377311706543,
"learning_rate": 0.00010922683594633021,
"loss": 1.2629,
"step": 110
},
{
"epoch": 0.054282046579864296,
"grad_norm": 1.4681098461151123,
"learning_rate": 0.00010738525274748741,
"loss": 1.0759,
"step": 111
},
{
"epoch": 0.05477107402652974,
"grad_norm": 1.531042456626892,
"learning_rate": 0.000105541147491597,
"loss": 1.2869,
"step": 112
},
{
"epoch": 0.05526010147319518,
"grad_norm": 1.6074343919754028,
"learning_rate": 0.00010369514993891452,
"loss": 1.1934,
"step": 113
},
{
"epoch": 0.05574912891986063,
"grad_norm": 1.7573381662368774,
"learning_rate": 0.00010184789049591299,
"loss": 1.3637,
"step": 114
},
{
"epoch": 0.05623815636652607,
"grad_norm": 1.6174389123916626,
"learning_rate": 0.0001,
"loss": 1.0625,
"step": 115
},
{
"epoch": 0.056727183813191515,
"grad_norm": 1.5200375318527222,
"learning_rate": 9.815210950408704e-05,
"loss": 1.1155,
"step": 116
},
{
"epoch": 0.05721621125985696,
"grad_norm": 1.8069548606872559,
"learning_rate": 9.630485006108553e-05,
"loss": 1.226,
"step": 117
},
{
"epoch": 0.0577052387065224,
"grad_norm": 1.832614779472351,
"learning_rate": 9.4458852508403e-05,
"loss": 1.3931,
"step": 118
},
{
"epoch": 0.058194266153187846,
"grad_norm": 1.797018051147461,
"learning_rate": 9.261474725251261e-05,
"loss": 1.3913,
"step": 119
},
{
"epoch": 0.05868329359985329,
"grad_norm": 1.7891651391983032,
"learning_rate": 9.077316405366981e-05,
"loss": 1.1728,
"step": 120
},
{
"epoch": 0.05917232104651873,
"grad_norm": 1.6011669635772705,
"learning_rate": 8.893473181084994e-05,
"loss": 1.2445,
"step": 121
},
{
"epoch": 0.05966134849318418,
"grad_norm": 1.504120945930481,
"learning_rate": 8.710007834697969e-05,
"loss": 1.1279,
"step": 122
},
{
"epoch": 0.06015037593984962,
"grad_norm": 1.4930016994476318,
"learning_rate": 8.526983019453623e-05,
"loss": 1.4165,
"step": 123
},
{
"epoch": 0.06063940338651507,
"grad_norm": 1.8281480073928833,
"learning_rate": 8.344461238158699e-05,
"loss": 1.3264,
"step": 124
},
{
"epoch": 0.061128430833180515,
"grad_norm": 1.574941873550415,
"learning_rate": 8.162504821834295e-05,
"loss": 1.2018,
"step": 125
},
{
"epoch": 0.06161745827984596,
"grad_norm": 1.4820826053619385,
"learning_rate": 7.9811759084299e-05,
"loss": 1.102,
"step": 126
},
{
"epoch": 0.0621064857265114,
"grad_norm": 1.699189305305481,
"learning_rate": 7.800536421603317e-05,
"loss": 1.161,
"step": 127
},
{
"epoch": 0.06259551317317684,
"grad_norm": 1.9508938789367676,
"learning_rate": 7.620648049573815e-05,
"loss": 1.1853,
"step": 128
},
{
"epoch": 0.06308454061984228,
"grad_norm": 1.7746766805648804,
"learning_rate": 7.441572224055644e-05,
"loss": 1.1611,
"step": 129
},
{
"epoch": 0.06357356806650773,
"grad_norm": 1.4383032321929932,
"learning_rate": 7.263370099279172e-05,
"loss": 1.0862,
"step": 130
},
{
"epoch": 0.06406259551317317,
"grad_norm": 1.8016362190246582,
"learning_rate": 7.086102531106754e-05,
"loss": 1.1134,
"step": 131
},
{
"epoch": 0.06455162295983861,
"grad_norm": 1.9223240613937378,
"learning_rate": 6.909830056250527e-05,
"loss": 1.1634,
"step": 132
},
{
"epoch": 0.06504065040650407,
"grad_norm": 1.6044070720672607,
"learning_rate": 6.734612871599168e-05,
"loss": 0.9598,
"step": 133
},
{
"epoch": 0.06552967785316952,
"grad_norm": 1.2090851068496704,
"learning_rate": 6.560510813660719e-05,
"loss": 0.8575,
"step": 134
},
{
"epoch": 0.06601870529983496,
"grad_norm": 1.6465786695480347,
"learning_rate": 6.387583338128471e-05,
"loss": 1.2695,
"step": 135
},
{
"epoch": 0.0665077327465004,
"grad_norm": 1.7019681930541992,
"learning_rate": 6.215889499576898e-05,
"loss": 1.3211,
"step": 136
},
{
"epoch": 0.0665077327465004,
"eval_loss": 1.161658763885498,
"eval_runtime": 360.3986,
"eval_samples_per_second": 7.167,
"eval_steps_per_second": 2.389,
"step": 136
},
{
"epoch": 0.06699676019316585,
"grad_norm": 1.442068099975586,
"learning_rate": 6.0454879312945754e-05,
"loss": 1.0054,
"step": 137
},
{
"epoch": 0.06748578763983129,
"grad_norm": 1.511075735092163,
"learning_rate": 5.876436825260967e-05,
"loss": 0.9859,
"step": 138
},
{
"epoch": 0.06797481508649673,
"grad_norm": 1.7810182571411133,
"learning_rate": 5.708793912273911e-05,
"loss": 1.079,
"step": 139
},
{
"epoch": 0.06846384253316218,
"grad_norm": 2.4788639545440674,
"learning_rate": 5.542616442234618e-05,
"loss": 1.2275,
"step": 140
},
{
"epoch": 0.06895286997982762,
"grad_norm": 1.9686139822006226,
"learning_rate": 5.37796116459687e-05,
"loss": 1.3599,
"step": 141
},
{
"epoch": 0.06944189742649307,
"grad_norm": 1.5025736093521118,
"learning_rate": 5.214884308987136e-05,
"loss": 1.0006,
"step": 142
},
{
"epoch": 0.06993092487315851,
"grad_norm": 1.5758655071258545,
"learning_rate": 5.0534415660022136e-05,
"loss": 1.1497,
"step": 143
},
{
"epoch": 0.07041995231982395,
"grad_norm": 1.5424786806106567,
"learning_rate": 4.893688068190932e-05,
"loss": 0.95,
"step": 144
},
{
"epoch": 0.0709089797664894,
"grad_norm": 1.6509641408920288,
"learning_rate": 4.735678371226441e-05,
"loss": 1.2053,
"step": 145
},
{
"epoch": 0.07139800721315484,
"grad_norm": 1.5191986560821533,
"learning_rate": 4.5794664352755055e-05,
"loss": 0.9719,
"step": 146
},
{
"epoch": 0.07188703465982028,
"grad_norm": 2.260869026184082,
"learning_rate": 4.425105606571145e-05,
"loss": 1.4066,
"step": 147
},
{
"epoch": 0.07237606210648573,
"grad_norm": 1.4834034442901611,
"learning_rate": 4.272648599194948e-05,
"loss": 1.0256,
"step": 148
},
{
"epoch": 0.07286508955315117,
"grad_norm": 1.8474698066711426,
"learning_rate": 4.12214747707527e-05,
"loss": 1.2136,
"step": 149
},
{
"epoch": 0.07335411699981662,
"grad_norm": 1.5918636322021484,
"learning_rate": 3.973653636207437e-05,
"loss": 1.1922,
"step": 150
},
{
"epoch": 0.07384314444648206,
"grad_norm": 1.723659634590149,
"learning_rate": 3.8272177871020723e-05,
"loss": 1.2842,
"step": 151
},
{
"epoch": 0.0743321718931475,
"grad_norm": 1.55375075340271,
"learning_rate": 3.682889937467493e-05,
"loss": 1.132,
"step": 152
},
{
"epoch": 0.07482119933981295,
"grad_norm": 1.4992774724960327,
"learning_rate": 3.540719375132129e-05,
"loss": 1.2428,
"step": 153
},
{
"epoch": 0.07531022678647839,
"grad_norm": 1.6103425025939941,
"learning_rate": 3.400754651212776e-05,
"loss": 1.176,
"step": 154
},
{
"epoch": 0.07579925423314383,
"grad_norm": 1.662162184715271,
"learning_rate": 3.263043563534428e-05,
"loss": 1.2697,
"step": 155
},
{
"epoch": 0.07628828167980928,
"grad_norm": 1.850628137588501,
"learning_rate": 3.1276331403073735e-05,
"loss": 1.4371,
"step": 156
},
{
"epoch": 0.07677730912647472,
"grad_norm": 1.5289597511291504,
"learning_rate": 2.9945696240670906e-05,
"loss": 1.213,
"step": 157
},
{
"epoch": 0.07726633657314017,
"grad_norm": 1.5676257610321045,
"learning_rate": 2.8638984558824777e-05,
"loss": 0.9869,
"step": 158
},
{
"epoch": 0.07775536401980561,
"grad_norm": 1.5715399980545044,
"learning_rate": 2.7356642598377603e-05,
"loss": 0.9653,
"step": 159
},
{
"epoch": 0.07824439146647105,
"grad_norm": 1.4842650890350342,
"learning_rate": 2.6099108277934103e-05,
"loss": 0.9926,
"step": 160
},
{
"epoch": 0.0787334189131365,
"grad_norm": 1.6693536043167114,
"learning_rate": 2.4866811044312665e-05,
"loss": 1.2897,
"step": 161
},
{
"epoch": 0.07922244635980194,
"grad_norm": 1.773213505744934,
"learning_rate": 2.36601717258897e-05,
"loss": 1.3966,
"step": 162
},
{
"epoch": 0.07971147380646738,
"grad_norm": 1.4736013412475586,
"learning_rate": 2.2479602388887012e-05,
"loss": 1.1237,
"step": 163
},
{
"epoch": 0.08020050125313283,
"grad_norm": 1.3282140493392944,
"learning_rate": 2.132550619665168e-05,
"loss": 1.0212,
"step": 164
},
{
"epoch": 0.08068952869979827,
"grad_norm": 1.923137903213501,
"learning_rate": 2.0198277271976052e-05,
"loss": 1.3069,
"step": 165
},
{
"epoch": 0.08117855614646372,
"grad_norm": 1.539564847946167,
"learning_rate": 1.9098300562505266e-05,
"loss": 1.1778,
"step": 166
},
{
"epoch": 0.08166758359312916,
"grad_norm": 1.5310879945755005,
"learning_rate": 1.8025951709277898e-05,
"loss": 1.156,
"step": 167
},
{
"epoch": 0.0821566110397946,
"grad_norm": 1.3962866067886353,
"learning_rate": 1.6981596918444953e-05,
"loss": 1.1866,
"step": 168
},
{
"epoch": 0.08264563848646005,
"grad_norm": 1.5868035554885864,
"learning_rate": 1.5965592836210743e-05,
"loss": 1.1221,
"step": 169
},
{
"epoch": 0.08313466593312549,
"grad_norm": 1.3075371980667114,
"learning_rate": 1.4978286427038601e-05,
"loss": 0.8995,
"step": 170
},
{
"epoch": 0.08313466593312549,
"eval_loss": 1.1457831859588623,
"eval_runtime": 358.8866,
"eval_samples_per_second": 7.197,
"eval_steps_per_second": 2.399,
"step": 170
},
{
"epoch": 0.08362369337979095,
"grad_norm": 1.4657541513442993,
"learning_rate": 1.4020014855162755e-05,
"loss": 1.1274,
"step": 171
},
{
"epoch": 0.08411272082645639,
"grad_norm": 1.5020861625671387,
"learning_rate": 1.3091105369447165e-05,
"loss": 1.1265,
"step": 172
},
{
"epoch": 0.08460174827312184,
"grad_norm": 1.5001840591430664,
"learning_rate": 1.2191875191630209e-05,
"loss": 1.349,
"step": 173
},
{
"epoch": 0.08509077571978728,
"grad_norm": 1.2937557697296143,
"learning_rate": 1.1322631407993811e-05,
"loss": 0.8972,
"step": 174
},
{
"epoch": 0.08557980316645272,
"grad_norm": 1.4909635782241821,
"learning_rate": 1.0483670864493778e-05,
"loss": 1.0324,
"step": 175
},
{
"epoch": 0.08606883061311817,
"grad_norm": 1.5571972131729126,
"learning_rate": 9.675280065387116e-06,
"loss": 1.1766,
"step": 176
},
{
"epoch": 0.08655785805978361,
"grad_norm": 1.5464365482330322,
"learning_rate": 8.897735075391155e-06,
"loss": 1.0126,
"step": 177
},
{
"epoch": 0.08704688550644905,
"grad_norm": 1.497572898864746,
"learning_rate": 8.151301425407699e-06,
"loss": 1.1136,
"step": 178
},
{
"epoch": 0.0875359129531145,
"grad_norm": 1.755557656288147,
"learning_rate": 7.43623402184438e-06,
"loss": 1.1293,
"step": 179
},
{
"epoch": 0.08802494039977994,
"grad_norm": 1.503421664237976,
"learning_rate": 6.75277705956443e-06,
"loss": 0.9615,
"step": 180
},
{
"epoch": 0.08851396784644538,
"grad_norm": 1.6039071083068848,
"learning_rate": 6.1011639384943585e-06,
"loss": 1.2254,
"step": 181
},
{
"epoch": 0.08900299529311083,
"grad_norm": 1.683371663093567,
"learning_rate": 5.481617183918053e-06,
"loss": 1.3635,
"step": 182
},
{
"epoch": 0.08949202273977627,
"grad_norm": 1.8019604682922363,
"learning_rate": 4.8943483704846475e-06,
"loss": 1.4746,
"step": 183
},
{
"epoch": 0.08998105018644172,
"grad_norm": 1.6251046657562256,
"learning_rate": 4.339558049955927e-06,
"loss": 1.0503,
"step": 184
},
{
"epoch": 0.09047007763310716,
"grad_norm": 1.4097155332565308,
"learning_rate": 3.817435682718096e-06,
"loss": 1.0714,
"step": 185
},
{
"epoch": 0.0909591050797726,
"grad_norm": 1.7966846227645874,
"learning_rate": 3.3281595730812575e-06,
"loss": 1.227,
"step": 186
},
{
"epoch": 0.09144813252643805,
"grad_norm": 1.469336986541748,
"learning_rate": 2.8718968083886075e-06,
"loss": 1.1229,
"step": 187
},
{
"epoch": 0.09193715997310349,
"grad_norm": 1.6519256830215454,
"learning_rate": 2.4488032019563402e-06,
"loss": 1.1736,
"step": 188
},
{
"epoch": 0.09242618741976893,
"grad_norm": 1.4258654117584229,
"learning_rate": 2.0590232398634114e-06,
"loss": 1.2349,
"step": 189
},
{
"epoch": 0.09291521486643438,
"grad_norm": 1.5600452423095703,
"learning_rate": 1.7026900316098215e-06,
"loss": 0.9855,
"step": 190
},
{
"epoch": 0.09340424231309982,
"grad_norm": 1.6108776330947876,
"learning_rate": 1.3799252646597426e-06,
"loss": 1.2474,
"step": 191
},
{
"epoch": 0.09389326975976527,
"grad_norm": 1.4905693531036377,
"learning_rate": 1.0908391628854041e-06,
"loss": 1.0982,
"step": 192
},
{
"epoch": 0.09438229720643071,
"grad_norm": 1.3788636922836304,
"learning_rate": 8.355304489257254e-07,
"loss": 1.0791,
"step": 193
},
{
"epoch": 0.09487132465309615,
"grad_norm": 1.8257007598876953,
"learning_rate": 6.140863104726391e-07,
"loss": 1.1666,
"step": 194
},
{
"epoch": 0.0953603520997616,
"grad_norm": 1.4958456754684448,
"learning_rate": 4.2658237049655323e-07,
"loss": 0.9653,
"step": 195
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 5,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.1257530122502144e+17,
"train_batch_size": 3,
"trial_name": null,
"trial_params": null
}