masatochi's picture
Training in progress, step 200, checkpoint
1851741 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.3518029903254178,
"eval_steps": 34,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.001759014951627089,
"grad_norm": 1.9062800407409668,
"learning_rate": 6.666666666666667e-06,
"loss": 2.5495,
"step": 1
},
{
"epoch": 0.001759014951627089,
"eval_loss": 2.3448081016540527,
"eval_runtime": 99.3906,
"eval_samples_per_second": 7.224,
"eval_steps_per_second": 2.415,
"step": 1
},
{
"epoch": 0.003518029903254178,
"grad_norm": 1.7736297845840454,
"learning_rate": 1.3333333333333333e-05,
"loss": 2.3431,
"step": 2
},
{
"epoch": 0.005277044854881266,
"grad_norm": 1.6759748458862305,
"learning_rate": 2e-05,
"loss": 2.4008,
"step": 3
},
{
"epoch": 0.007036059806508356,
"grad_norm": 1.9186958074569702,
"learning_rate": 2.6666666666666667e-05,
"loss": 2.3259,
"step": 4
},
{
"epoch": 0.008795074758135445,
"grad_norm": 2.0095129013061523,
"learning_rate": 3.3333333333333335e-05,
"loss": 2.3256,
"step": 5
},
{
"epoch": 0.010554089709762533,
"grad_norm": 1.9045144319534302,
"learning_rate": 4e-05,
"loss": 2.3183,
"step": 6
},
{
"epoch": 0.012313104661389622,
"grad_norm": 1.9549291133880615,
"learning_rate": 4.666666666666667e-05,
"loss": 2.4373,
"step": 7
},
{
"epoch": 0.014072119613016711,
"grad_norm": 1.9563552141189575,
"learning_rate": 5.333333333333333e-05,
"loss": 2.3997,
"step": 8
},
{
"epoch": 0.0158311345646438,
"grad_norm": 1.9059518575668335,
"learning_rate": 6e-05,
"loss": 2.1272,
"step": 9
},
{
"epoch": 0.01759014951627089,
"grad_norm": 2.0838987827301025,
"learning_rate": 6.666666666666667e-05,
"loss": 2.0918,
"step": 10
},
{
"epoch": 0.019349164467897976,
"grad_norm": 2.2100136280059814,
"learning_rate": 7.333333333333333e-05,
"loss": 2.3364,
"step": 11
},
{
"epoch": 0.021108179419525065,
"grad_norm": 1.7996355295181274,
"learning_rate": 8e-05,
"loss": 1.9992,
"step": 12
},
{
"epoch": 0.022867194371152155,
"grad_norm": 1.6359286308288574,
"learning_rate": 8.666666666666667e-05,
"loss": 1.9215,
"step": 13
},
{
"epoch": 0.024626209322779244,
"grad_norm": 1.5402390956878662,
"learning_rate": 9.333333333333334e-05,
"loss": 1.9603,
"step": 14
},
{
"epoch": 0.026385224274406333,
"grad_norm": 1.5985331535339355,
"learning_rate": 0.0001,
"loss": 1.9212,
"step": 15
},
{
"epoch": 0.028144239226033423,
"grad_norm": 1.5428632497787476,
"learning_rate": 0.00010666666666666667,
"loss": 1.6738,
"step": 16
},
{
"epoch": 0.02990325417766051,
"grad_norm": 1.5717724561691284,
"learning_rate": 0.00011333333333333334,
"loss": 1.797,
"step": 17
},
{
"epoch": 0.0316622691292876,
"grad_norm": 1.4973918199539185,
"learning_rate": 0.00012,
"loss": 1.6191,
"step": 18
},
{
"epoch": 0.03342128408091469,
"grad_norm": 1.4429734945297241,
"learning_rate": 0.00012666666666666666,
"loss": 1.429,
"step": 19
},
{
"epoch": 0.03518029903254178,
"grad_norm": 1.673143982887268,
"learning_rate": 0.00013333333333333334,
"loss": 1.2857,
"step": 20
},
{
"epoch": 0.036939313984168866,
"grad_norm": 1.5796126127243042,
"learning_rate": 0.00014,
"loss": 1.6133,
"step": 21
},
{
"epoch": 0.03869832893579595,
"grad_norm": 1.3923639059066772,
"learning_rate": 0.00014666666666666666,
"loss": 1.3345,
"step": 22
},
{
"epoch": 0.040457343887423045,
"grad_norm": 1.4356263875961304,
"learning_rate": 0.00015333333333333334,
"loss": 1.3969,
"step": 23
},
{
"epoch": 0.04221635883905013,
"grad_norm": 1.5952917337417603,
"learning_rate": 0.00016,
"loss": 1.2496,
"step": 24
},
{
"epoch": 0.04397537379067722,
"grad_norm": 1.601627230644226,
"learning_rate": 0.0001666666666666667,
"loss": 1.3434,
"step": 25
},
{
"epoch": 0.04573438874230431,
"grad_norm": 1.5887717008590698,
"learning_rate": 0.00017333333333333334,
"loss": 1.3473,
"step": 26
},
{
"epoch": 0.047493403693931395,
"grad_norm": 1.487489938735962,
"learning_rate": 0.00018,
"loss": 1.3618,
"step": 27
},
{
"epoch": 0.04925241864555849,
"grad_norm": 1.637352705001831,
"learning_rate": 0.0001866666666666667,
"loss": 1.2257,
"step": 28
},
{
"epoch": 0.051011433597185574,
"grad_norm": 1.4315184354782104,
"learning_rate": 0.00019333333333333333,
"loss": 1.1614,
"step": 29
},
{
"epoch": 0.052770448548812667,
"grad_norm": 1.413915753364563,
"learning_rate": 0.0002,
"loss": 1.17,
"step": 30
},
{
"epoch": 0.05452946350043975,
"grad_norm": 1.236619234085083,
"learning_rate": 0.00019998292504580528,
"loss": 1.0916,
"step": 31
},
{
"epoch": 0.056288478452066845,
"grad_norm": 1.721929669380188,
"learning_rate": 0.0001999317060143023,
"loss": 1.1674,
"step": 32
},
{
"epoch": 0.05804749340369393,
"grad_norm": 1.323931336402893,
"learning_rate": 0.0001998463603967434,
"loss": 1.1846,
"step": 33
},
{
"epoch": 0.05980650835532102,
"grad_norm": 1.1280919313430786,
"learning_rate": 0.00019972691733857883,
"loss": 1.1668,
"step": 34
},
{
"epoch": 0.05980650835532102,
"eval_loss": 1.1668506860733032,
"eval_runtime": 99.8168,
"eval_samples_per_second": 7.193,
"eval_steps_per_second": 2.404,
"step": 34
},
{
"epoch": 0.06156552330694811,
"grad_norm": 1.192156195640564,
"learning_rate": 0.00019957341762950344,
"loss": 1.1537,
"step": 35
},
{
"epoch": 0.0633245382585752,
"grad_norm": 1.1282252073287964,
"learning_rate": 0.0001993859136895274,
"loss": 1.1534,
"step": 36
},
{
"epoch": 0.06508355321020229,
"grad_norm": 1.0577436685562134,
"learning_rate": 0.00019916446955107428,
"loss": 1.107,
"step": 37
},
{
"epoch": 0.06684256816182937,
"grad_norm": 1.0347845554351807,
"learning_rate": 0.0001989091608371146,
"loss": 1.0075,
"step": 38
},
{
"epoch": 0.06860158311345646,
"grad_norm": 1.0515660047531128,
"learning_rate": 0.00019862007473534025,
"loss": 1.1582,
"step": 39
},
{
"epoch": 0.07036059806508356,
"grad_norm": 1.0801489353179932,
"learning_rate": 0.0001982973099683902,
"loss": 1.1708,
"step": 40
},
{
"epoch": 0.07211961301671065,
"grad_norm": 1.0259140729904175,
"learning_rate": 0.0001979409767601366,
"loss": 1.2522,
"step": 41
},
{
"epoch": 0.07387862796833773,
"grad_norm": 1.0126174688339233,
"learning_rate": 0.00019755119679804367,
"loss": 1.0018,
"step": 42
},
{
"epoch": 0.07563764291996482,
"grad_norm": 1.048399806022644,
"learning_rate": 0.0001971281031916114,
"loss": 1.096,
"step": 43
},
{
"epoch": 0.0773966578715919,
"grad_norm": 0.9712002277374268,
"learning_rate": 0.00019667184042691875,
"loss": 1.2518,
"step": 44
},
{
"epoch": 0.079155672823219,
"grad_norm": 1.0906403064727783,
"learning_rate": 0.00019618256431728194,
"loss": 1.2223,
"step": 45
},
{
"epoch": 0.08091468777484609,
"grad_norm": 1.182187557220459,
"learning_rate": 0.0001956604419500441,
"loss": 1.2729,
"step": 46
},
{
"epoch": 0.08267370272647317,
"grad_norm": 1.1395913362503052,
"learning_rate": 0.00019510565162951537,
"loss": 1.131,
"step": 47
},
{
"epoch": 0.08443271767810026,
"grad_norm": 1.0018647909164429,
"learning_rate": 0.00019451838281608197,
"loss": 1.0897,
"step": 48
},
{
"epoch": 0.08619173262972735,
"grad_norm": 1.0881168842315674,
"learning_rate": 0.00019389883606150566,
"loss": 1.2058,
"step": 49
},
{
"epoch": 0.08795074758135445,
"grad_norm": 1.094530701637268,
"learning_rate": 0.00019324722294043558,
"loss": 0.9726,
"step": 50
},
{
"epoch": 0.08970976253298153,
"grad_norm": 0.9569148421287537,
"learning_rate": 0.00019256376597815564,
"loss": 1.0618,
"step": 51
},
{
"epoch": 0.09146877748460862,
"grad_norm": 1.0027856826782227,
"learning_rate": 0.00019184869857459232,
"loss": 1.0319,
"step": 52
},
{
"epoch": 0.0932277924362357,
"grad_norm": 0.9956020712852478,
"learning_rate": 0.00019110226492460885,
"loss": 1.154,
"step": 53
},
{
"epoch": 0.09498680738786279,
"grad_norm": 1.0107563734054565,
"learning_rate": 0.0001903247199346129,
"loss": 1.0515,
"step": 54
},
{
"epoch": 0.09674582233948989,
"grad_norm": 1.0800281763076782,
"learning_rate": 0.00018951632913550626,
"loss": 0.9965,
"step": 55
},
{
"epoch": 0.09850483729111698,
"grad_norm": 1.114945411682129,
"learning_rate": 0.0001886773685920062,
"loss": 1.1598,
"step": 56
},
{
"epoch": 0.10026385224274406,
"grad_norm": 1.1020759344100952,
"learning_rate": 0.0001878081248083698,
"loss": 1.0662,
"step": 57
},
{
"epoch": 0.10202286719437115,
"grad_norm": 1.0220993757247925,
"learning_rate": 0.00018690889463055283,
"loss": 0.9601,
"step": 58
},
{
"epoch": 0.10378188214599825,
"grad_norm": 1.0335360765457153,
"learning_rate": 0.00018597998514483725,
"loss": 1.075,
"step": 59
},
{
"epoch": 0.10554089709762533,
"grad_norm": 1.1268407106399536,
"learning_rate": 0.00018502171357296144,
"loss": 1.0905,
"step": 60
},
{
"epoch": 0.10729991204925242,
"grad_norm": 1.151116967201233,
"learning_rate": 0.00018403440716378928,
"loss": 1.199,
"step": 61
},
{
"epoch": 0.1090589270008795,
"grad_norm": 1.0262718200683594,
"learning_rate": 0.00018301840308155507,
"loss": 1.0258,
"step": 62
},
{
"epoch": 0.11081794195250659,
"grad_norm": 1.1258262395858765,
"learning_rate": 0.00018197404829072215,
"loss": 1.0201,
"step": 63
},
{
"epoch": 0.11257695690413369,
"grad_norm": 0.91448575258255,
"learning_rate": 0.00018090169943749476,
"loss": 1.0978,
"step": 64
},
{
"epoch": 0.11433597185576078,
"grad_norm": 0.8898754715919495,
"learning_rate": 0.000179801722728024,
"loss": 0.9874,
"step": 65
},
{
"epoch": 0.11609498680738786,
"grad_norm": 1.1540552377700806,
"learning_rate": 0.00017867449380334834,
"loss": 1.1872,
"step": 66
},
{
"epoch": 0.11785400175901495,
"grad_norm": 1.1003878116607666,
"learning_rate": 0.00017752039761111297,
"loss": 1.1278,
"step": 67
},
{
"epoch": 0.11961301671064203,
"grad_norm": 1.1295952796936035,
"learning_rate": 0.00017633982827411032,
"loss": 0.9638,
"step": 68
},
{
"epoch": 0.11961301671064203,
"eval_loss": 1.074321985244751,
"eval_runtime": 99.8385,
"eval_samples_per_second": 7.192,
"eval_steps_per_second": 2.404,
"step": 68
},
{
"epoch": 0.12137203166226913,
"grad_norm": 0.9873747825622559,
"learning_rate": 0.00017513318895568737,
"loss": 1.1525,
"step": 69
},
{
"epoch": 0.12313104661389622,
"grad_norm": 1.0887939929962158,
"learning_rate": 0.00017390089172206592,
"loss": 1.0907,
"step": 70
},
{
"epoch": 0.1248900615655233,
"grad_norm": 0.9690318703651428,
"learning_rate": 0.00017264335740162242,
"loss": 1.0972,
"step": 71
},
{
"epoch": 0.1266490765171504,
"grad_norm": 1.0244834423065186,
"learning_rate": 0.00017136101544117525,
"loss": 1.1172,
"step": 72
},
{
"epoch": 0.1284080914687775,
"grad_norm": 1.1016342639923096,
"learning_rate": 0.0001700543037593291,
"loss": 0.9668,
"step": 73
},
{
"epoch": 0.13016710642040458,
"grad_norm": 0.9540287852287292,
"learning_rate": 0.00016872366859692627,
"loss": 0.9975,
"step": 74
},
{
"epoch": 0.13192612137203166,
"grad_norm": 1.0893555879592896,
"learning_rate": 0.00016736956436465573,
"loss": 0.9388,
"step": 75
},
{
"epoch": 0.13368513632365875,
"grad_norm": 1.0220561027526855,
"learning_rate": 0.0001659924534878723,
"loss": 1.1445,
"step": 76
},
{
"epoch": 0.13544415127528583,
"grad_norm": 1.1014329195022583,
"learning_rate": 0.00016459280624867874,
"loss": 1.0858,
"step": 77
},
{
"epoch": 0.13720316622691292,
"grad_norm": 1.07352614402771,
"learning_rate": 0.0001631711006253251,
"loss": 1.1801,
"step": 78
},
{
"epoch": 0.13896218117854,
"grad_norm": 0.9810523986816406,
"learning_rate": 0.0001617278221289793,
"loss": 1.025,
"step": 79
},
{
"epoch": 0.14072119613016712,
"grad_norm": 0.9856380224227905,
"learning_rate": 0.00016026346363792567,
"loss": 1.0232,
"step": 80
},
{
"epoch": 0.1424802110817942,
"grad_norm": 1.075045108795166,
"learning_rate": 0.00015877852522924732,
"loss": 1.1331,
"step": 81
},
{
"epoch": 0.1442392260334213,
"grad_norm": 1.0106600522994995,
"learning_rate": 0.00015727351400805052,
"loss": 0.9715,
"step": 82
},
{
"epoch": 0.14599824098504838,
"grad_norm": 1.1123266220092773,
"learning_rate": 0.00015574894393428855,
"loss": 0.9013,
"step": 83
},
{
"epoch": 0.14775725593667546,
"grad_norm": 1.0623693466186523,
"learning_rate": 0.00015420533564724495,
"loss": 0.9574,
"step": 84
},
{
"epoch": 0.14951627088830255,
"grad_norm": 1.250522494316101,
"learning_rate": 0.0001526432162877356,
"loss": 1.0737,
"step": 85
},
{
"epoch": 0.15127528583992964,
"grad_norm": 1.0988057851791382,
"learning_rate": 0.0001510631193180907,
"loss": 0.9449,
"step": 86
},
{
"epoch": 0.15303430079155672,
"grad_norm": 1.0282084941864014,
"learning_rate": 0.0001494655843399779,
"loss": 1.0909,
"step": 87
},
{
"epoch": 0.1547933157431838,
"grad_norm": 1.050750970840454,
"learning_rate": 0.00014785115691012864,
"loss": 0.9881,
"step": 88
},
{
"epoch": 0.1565523306948109,
"grad_norm": 1.1668485403060913,
"learning_rate": 0.00014622038835403133,
"loss": 1.111,
"step": 89
},
{
"epoch": 0.158311345646438,
"grad_norm": 0.922467052936554,
"learning_rate": 0.00014457383557765386,
"loss": 1.0094,
"step": 90
},
{
"epoch": 0.1600703605980651,
"grad_norm": 1.0213371515274048,
"learning_rate": 0.0001429120608772609,
"loss": 1.231,
"step": 91
},
{
"epoch": 0.16182937554969218,
"grad_norm": 1.0093265771865845,
"learning_rate": 0.00014123563174739037,
"loss": 1.1445,
"step": 92
},
{
"epoch": 0.16358839050131926,
"grad_norm": 0.9907693862915039,
"learning_rate": 0.00013954512068705424,
"loss": 1.0439,
"step": 93
},
{
"epoch": 0.16534740545294635,
"grad_norm": 0.9130767583847046,
"learning_rate": 0.00013784110500423104,
"loss": 0.9882,
"step": 94
},
{
"epoch": 0.16710642040457344,
"grad_norm": 0.9448095560073853,
"learning_rate": 0.00013612416661871533,
"loss": 1.1263,
"step": 95
},
{
"epoch": 0.16886543535620052,
"grad_norm": 0.9945996999740601,
"learning_rate": 0.00013439489186339282,
"loss": 1.2177,
"step": 96
},
{
"epoch": 0.1706244503078276,
"grad_norm": 0.9518169164657593,
"learning_rate": 0.0001326538712840083,
"loss": 1.0121,
"step": 97
},
{
"epoch": 0.1723834652594547,
"grad_norm": 0.961685299873352,
"learning_rate": 0.00013090169943749476,
"loss": 1.0118,
"step": 98
},
{
"epoch": 0.1741424802110818,
"grad_norm": 0.9489362239837646,
"learning_rate": 0.00012913897468893248,
"loss": 0.9491,
"step": 99
},
{
"epoch": 0.1759014951627089,
"grad_norm": 0.9181511402130127,
"learning_rate": 0.0001273662990072083,
"loss": 1.0382,
"step": 100
},
{
"epoch": 0.17766051011433598,
"grad_norm": 0.878054678440094,
"learning_rate": 0.00012558427775944357,
"loss": 1.1107,
"step": 101
},
{
"epoch": 0.17941952506596306,
"grad_norm": 1.0347309112548828,
"learning_rate": 0.00012379351950426187,
"loss": 1.0765,
"step": 102
},
{
"epoch": 0.17941952506596306,
"eval_loss": 1.0452779531478882,
"eval_runtime": 99.7845,
"eval_samples_per_second": 7.196,
"eval_steps_per_second": 2.405,
"step": 102
},
{
"epoch": 0.18117854001759015,
"grad_norm": 0.8769102096557617,
"learning_rate": 0.00012199463578396688,
"loss": 1.0699,
"step": 103
},
{
"epoch": 0.18293755496921724,
"grad_norm": 0.9189753532409668,
"learning_rate": 0.00012018824091570103,
"loss": 1.0125,
"step": 104
},
{
"epoch": 0.18469656992084432,
"grad_norm": 1.0256829261779785,
"learning_rate": 0.00011837495178165706,
"loss": 1.1478,
"step": 105
},
{
"epoch": 0.1864555848724714,
"grad_norm": 0.8750260472297668,
"learning_rate": 0.000116555387618413,
"loss": 0.9659,
"step": 106
},
{
"epoch": 0.1882145998240985,
"grad_norm": 0.9436942934989929,
"learning_rate": 0.00011473016980546377,
"loss": 1.0007,
"step": 107
},
{
"epoch": 0.18997361477572558,
"grad_norm": 0.8363056778907776,
"learning_rate": 0.00011289992165302035,
"loss": 0.9685,
"step": 108
},
{
"epoch": 0.1917326297273527,
"grad_norm": 0.9718777537345886,
"learning_rate": 0.00011106526818915008,
"loss": 1.154,
"step": 109
},
{
"epoch": 0.19349164467897978,
"grad_norm": 0.9197990894317627,
"learning_rate": 0.00010922683594633021,
"loss": 1.0835,
"step": 110
},
{
"epoch": 0.19525065963060687,
"grad_norm": 1.0363267660140991,
"learning_rate": 0.00010738525274748741,
"loss": 0.9274,
"step": 111
},
{
"epoch": 0.19700967458223395,
"grad_norm": 0.965980052947998,
"learning_rate": 0.000105541147491597,
"loss": 0.9175,
"step": 112
},
{
"epoch": 0.19876868953386104,
"grad_norm": 1.180904507637024,
"learning_rate": 0.00010369514993891452,
"loss": 1.1438,
"step": 113
},
{
"epoch": 0.20052770448548812,
"grad_norm": 0.8446922898292542,
"learning_rate": 0.00010184789049591299,
"loss": 0.9148,
"step": 114
},
{
"epoch": 0.2022867194371152,
"grad_norm": 0.9753116965293884,
"learning_rate": 0.0001,
"loss": 1.081,
"step": 115
},
{
"epoch": 0.2040457343887423,
"grad_norm": 1.0824472904205322,
"learning_rate": 9.815210950408704e-05,
"loss": 1.0952,
"step": 116
},
{
"epoch": 0.20580474934036938,
"grad_norm": 0.9209856986999512,
"learning_rate": 9.630485006108553e-05,
"loss": 1.0349,
"step": 117
},
{
"epoch": 0.2075637642919965,
"grad_norm": 0.8723039031028748,
"learning_rate": 9.4458852508403e-05,
"loss": 1.2006,
"step": 118
},
{
"epoch": 0.20932277924362358,
"grad_norm": 1.086898684501648,
"learning_rate": 9.261474725251261e-05,
"loss": 1.1713,
"step": 119
},
{
"epoch": 0.21108179419525067,
"grad_norm": 0.9592442512512207,
"learning_rate": 9.077316405366981e-05,
"loss": 1.0448,
"step": 120
},
{
"epoch": 0.21284080914687775,
"grad_norm": 1.1296504735946655,
"learning_rate": 8.893473181084994e-05,
"loss": 1.0905,
"step": 121
},
{
"epoch": 0.21459982409850484,
"grad_norm": 1.0223779678344727,
"learning_rate": 8.710007834697969e-05,
"loss": 1.1784,
"step": 122
},
{
"epoch": 0.21635883905013192,
"grad_norm": 1.296108365058899,
"learning_rate": 8.526983019453623e-05,
"loss": 1.0065,
"step": 123
},
{
"epoch": 0.218117854001759,
"grad_norm": 0.9558261036872864,
"learning_rate": 8.344461238158699e-05,
"loss": 1.0832,
"step": 124
},
{
"epoch": 0.2198768689533861,
"grad_norm": 0.9590238928794861,
"learning_rate": 8.162504821834295e-05,
"loss": 0.987,
"step": 125
},
{
"epoch": 0.22163588390501318,
"grad_norm": 0.9906069040298462,
"learning_rate": 7.9811759084299e-05,
"loss": 1.0693,
"step": 126
},
{
"epoch": 0.2233948988566403,
"grad_norm": 1.0699800252914429,
"learning_rate": 7.800536421603317e-05,
"loss": 0.9815,
"step": 127
},
{
"epoch": 0.22515391380826738,
"grad_norm": 1.044717788696289,
"learning_rate": 7.620648049573815e-05,
"loss": 1.0509,
"step": 128
},
{
"epoch": 0.22691292875989447,
"grad_norm": 0.95858234167099,
"learning_rate": 7.441572224055644e-05,
"loss": 1.0697,
"step": 129
},
{
"epoch": 0.22867194371152155,
"grad_norm": 0.9557747840881348,
"learning_rate": 7.263370099279172e-05,
"loss": 1.1247,
"step": 130
},
{
"epoch": 0.23043095866314864,
"grad_norm": 0.9437980055809021,
"learning_rate": 7.086102531106754e-05,
"loss": 1.0947,
"step": 131
},
{
"epoch": 0.23218997361477572,
"grad_norm": 1.0209659337997437,
"learning_rate": 6.909830056250527e-05,
"loss": 1.0711,
"step": 132
},
{
"epoch": 0.2339489885664028,
"grad_norm": 0.9343348145484924,
"learning_rate": 6.734612871599168e-05,
"loss": 1.103,
"step": 133
},
{
"epoch": 0.2357080035180299,
"grad_norm": 0.8994061350822449,
"learning_rate": 6.560510813660719e-05,
"loss": 1.0015,
"step": 134
},
{
"epoch": 0.23746701846965698,
"grad_norm": 0.9286561012268066,
"learning_rate": 6.387583338128471e-05,
"loss": 1.1725,
"step": 135
},
{
"epoch": 0.23922603342128407,
"grad_norm": 0.9949707984924316,
"learning_rate": 6.215889499576898e-05,
"loss": 1.1714,
"step": 136
},
{
"epoch": 0.23922603342128407,
"eval_loss": 1.0311784744262695,
"eval_runtime": 100.0338,
"eval_samples_per_second": 7.178,
"eval_steps_per_second": 2.399,
"step": 136
},
{
"epoch": 0.24098504837291118,
"grad_norm": 0.9608387351036072,
"learning_rate": 6.0454879312945754e-05,
"loss": 1.0665,
"step": 137
},
{
"epoch": 0.24274406332453827,
"grad_norm": 0.9353300929069519,
"learning_rate": 5.876436825260967e-05,
"loss": 1.0883,
"step": 138
},
{
"epoch": 0.24450307827616535,
"grad_norm": 0.9781258702278137,
"learning_rate": 5.708793912273911e-05,
"loss": 1.0995,
"step": 139
},
{
"epoch": 0.24626209322779244,
"grad_norm": 0.8818216323852539,
"learning_rate": 5.542616442234618e-05,
"loss": 1.0379,
"step": 140
},
{
"epoch": 0.24802110817941952,
"grad_norm": 1.0094648599624634,
"learning_rate": 5.37796116459687e-05,
"loss": 1.0235,
"step": 141
},
{
"epoch": 0.2497801231310466,
"grad_norm": 1.0476373434066772,
"learning_rate": 5.214884308987136e-05,
"loss": 1.0371,
"step": 142
},
{
"epoch": 0.2515391380826737,
"grad_norm": 0.8884543180465698,
"learning_rate": 5.0534415660022136e-05,
"loss": 0.9822,
"step": 143
},
{
"epoch": 0.2532981530343008,
"grad_norm": 1.0862784385681152,
"learning_rate": 4.893688068190932e-05,
"loss": 1.1247,
"step": 144
},
{
"epoch": 0.25505716798592787,
"grad_norm": 0.9406157732009888,
"learning_rate": 4.735678371226441e-05,
"loss": 1.0492,
"step": 145
},
{
"epoch": 0.256816182937555,
"grad_norm": 1.0700528621673584,
"learning_rate": 4.5794664352755055e-05,
"loss": 0.9419,
"step": 146
},
{
"epoch": 0.25857519788918204,
"grad_norm": 1.0496270656585693,
"learning_rate": 4.425105606571145e-05,
"loss": 0.9158,
"step": 147
},
{
"epoch": 0.26033421284080915,
"grad_norm": 1.0390560626983643,
"learning_rate": 4.272648599194948e-05,
"loss": 1.0018,
"step": 148
},
{
"epoch": 0.2620932277924362,
"grad_norm": 0.9473912715911865,
"learning_rate": 4.12214747707527e-05,
"loss": 0.955,
"step": 149
},
{
"epoch": 0.2638522427440633,
"grad_norm": 0.9641641974449158,
"learning_rate": 3.973653636207437e-05,
"loss": 0.9661,
"step": 150
},
{
"epoch": 0.26561125769569044,
"grad_norm": 0.9572023749351501,
"learning_rate": 3.8272177871020723e-05,
"loss": 0.9604,
"step": 151
},
{
"epoch": 0.2673702726473175,
"grad_norm": 0.9164190888404846,
"learning_rate": 3.682889937467493e-05,
"loss": 0.9918,
"step": 152
},
{
"epoch": 0.2691292875989446,
"grad_norm": 0.9876633882522583,
"learning_rate": 3.540719375132129e-05,
"loss": 1.1758,
"step": 153
},
{
"epoch": 0.27088830255057167,
"grad_norm": 0.8722500205039978,
"learning_rate": 3.400754651212776e-05,
"loss": 0.9275,
"step": 154
},
{
"epoch": 0.2726473175021988,
"grad_norm": 1.0047615766525269,
"learning_rate": 3.263043563534428e-05,
"loss": 1.0602,
"step": 155
},
{
"epoch": 0.27440633245382584,
"grad_norm": 0.9882528781890869,
"learning_rate": 3.1276331403073735e-05,
"loss": 1.2147,
"step": 156
},
{
"epoch": 0.27616534740545295,
"grad_norm": 0.9455094933509827,
"learning_rate": 2.9945696240670906e-05,
"loss": 1.0372,
"step": 157
},
{
"epoch": 0.27792436235708,
"grad_norm": 0.9055385589599609,
"learning_rate": 2.8638984558824777e-05,
"loss": 1.055,
"step": 158
},
{
"epoch": 0.2796833773087071,
"grad_norm": 0.8886315226554871,
"learning_rate": 2.7356642598377603e-05,
"loss": 0.9547,
"step": 159
},
{
"epoch": 0.28144239226033424,
"grad_norm": 0.8915826678276062,
"learning_rate": 2.6099108277934103e-05,
"loss": 0.9448,
"step": 160
},
{
"epoch": 0.2832014072119613,
"grad_norm": 0.9817346930503845,
"learning_rate": 2.4866811044312665e-05,
"loss": 1.0933,
"step": 161
},
{
"epoch": 0.2849604221635884,
"grad_norm": 1.009725570678711,
"learning_rate": 2.36601717258897e-05,
"loss": 1.0988,
"step": 162
},
{
"epoch": 0.28671943711521547,
"grad_norm": 0.9024699330329895,
"learning_rate": 2.2479602388887012e-05,
"loss": 1.0431,
"step": 163
},
{
"epoch": 0.2884784520668426,
"grad_norm": 0.8994817137718201,
"learning_rate": 2.132550619665168e-05,
"loss": 0.9858,
"step": 164
},
{
"epoch": 0.29023746701846964,
"grad_norm": 0.8933229446411133,
"learning_rate": 2.0198277271976052e-05,
"loss": 1.0209,
"step": 165
},
{
"epoch": 0.29199648197009676,
"grad_norm": 1.0022671222686768,
"learning_rate": 1.9098300562505266e-05,
"loss": 1.0283,
"step": 166
},
{
"epoch": 0.2937554969217238,
"grad_norm": 1.1408864259719849,
"learning_rate": 1.8025951709277898e-05,
"loss": 1.12,
"step": 167
},
{
"epoch": 0.2955145118733509,
"grad_norm": 1.066427230834961,
"learning_rate": 1.6981596918444953e-05,
"loss": 1.0759,
"step": 168
},
{
"epoch": 0.297273526824978,
"grad_norm": 0.9484472870826721,
"learning_rate": 1.5965592836210743e-05,
"loss": 0.9911,
"step": 169
},
{
"epoch": 0.2990325417766051,
"grad_norm": 0.9145427942276001,
"learning_rate": 1.4978286427038601e-05,
"loss": 0.9518,
"step": 170
},
{
"epoch": 0.2990325417766051,
"eval_loss": 1.016570806503296,
"eval_runtime": 99.8054,
"eval_samples_per_second": 7.194,
"eval_steps_per_second": 2.405,
"step": 170
},
{
"epoch": 0.3007915567282322,
"grad_norm": 0.8470132350921631,
"learning_rate": 1.4020014855162755e-05,
"loss": 1.025,
"step": 171
},
{
"epoch": 0.30255057167985927,
"grad_norm": 0.998738169670105,
"learning_rate": 1.3091105369447165e-05,
"loss": 1.1413,
"step": 172
},
{
"epoch": 0.3043095866314864,
"grad_norm": 0.8331905007362366,
"learning_rate": 1.2191875191630209e-05,
"loss": 0.9363,
"step": 173
},
{
"epoch": 0.30606860158311344,
"grad_norm": 0.961270272731781,
"learning_rate": 1.1322631407993811e-05,
"loss": 1.0692,
"step": 174
},
{
"epoch": 0.30782761653474056,
"grad_norm": 1.060444712638855,
"learning_rate": 1.0483670864493778e-05,
"loss": 1.059,
"step": 175
},
{
"epoch": 0.3095866314863676,
"grad_norm": 1.0591764450073242,
"learning_rate": 9.675280065387116e-06,
"loss": 0.943,
"step": 176
},
{
"epoch": 0.3113456464379947,
"grad_norm": 0.9762607216835022,
"learning_rate": 8.897735075391155e-06,
"loss": 0.9311,
"step": 177
},
{
"epoch": 0.3131046613896218,
"grad_norm": 0.9286603927612305,
"learning_rate": 8.151301425407699e-06,
"loss": 1.0864,
"step": 178
},
{
"epoch": 0.3148636763412489,
"grad_norm": 1.0729596614837646,
"learning_rate": 7.43623402184438e-06,
"loss": 1.0405,
"step": 179
},
{
"epoch": 0.316622691292876,
"grad_norm": 0.9094541668891907,
"learning_rate": 6.75277705956443e-06,
"loss": 1.036,
"step": 180
},
{
"epoch": 0.31838170624450307,
"grad_norm": 0.9250197410583496,
"learning_rate": 6.1011639384943585e-06,
"loss": 1.1072,
"step": 181
},
{
"epoch": 0.3201407211961302,
"grad_norm": 0.9698026180267334,
"learning_rate": 5.481617183918053e-06,
"loss": 1.0581,
"step": 182
},
{
"epoch": 0.32189973614775724,
"grad_norm": 1.0418232679367065,
"learning_rate": 4.8943483704846475e-06,
"loss": 1.0269,
"step": 183
},
{
"epoch": 0.32365875109938436,
"grad_norm": 0.8700360655784607,
"learning_rate": 4.339558049955927e-06,
"loss": 0.9512,
"step": 184
},
{
"epoch": 0.3254177660510114,
"grad_norm": 1.033153772354126,
"learning_rate": 3.817435682718096e-06,
"loss": 1.1024,
"step": 185
},
{
"epoch": 0.32717678100263853,
"grad_norm": 0.986663281917572,
"learning_rate": 3.3281595730812575e-06,
"loss": 1.1425,
"step": 186
},
{
"epoch": 0.3289357959542656,
"grad_norm": 1.0437548160552979,
"learning_rate": 2.8718968083886075e-06,
"loss": 1.0006,
"step": 187
},
{
"epoch": 0.3306948109058927,
"grad_norm": 0.8966625332832336,
"learning_rate": 2.4488032019563402e-06,
"loss": 0.9099,
"step": 188
},
{
"epoch": 0.3324538258575198,
"grad_norm": 0.9832119345664978,
"learning_rate": 2.0590232398634114e-06,
"loss": 1.0094,
"step": 189
},
{
"epoch": 0.33421284080914687,
"grad_norm": 0.9731014966964722,
"learning_rate": 1.7026900316098215e-06,
"loss": 0.9687,
"step": 190
},
{
"epoch": 0.335971855760774,
"grad_norm": 0.8564959168434143,
"learning_rate": 1.3799252646597426e-06,
"loss": 0.933,
"step": 191
},
{
"epoch": 0.33773087071240104,
"grad_norm": 1.036962866783142,
"learning_rate": 1.0908391628854041e-06,
"loss": 0.9713,
"step": 192
},
{
"epoch": 0.33948988566402816,
"grad_norm": 0.919511616230011,
"learning_rate": 8.355304489257254e-07,
"loss": 1.0534,
"step": 193
},
{
"epoch": 0.3412489006156552,
"grad_norm": 0.9325530529022217,
"learning_rate": 6.140863104726391e-07,
"loss": 0.9465,
"step": 194
},
{
"epoch": 0.34300791556728233,
"grad_norm": 0.9085223078727722,
"learning_rate": 4.2658237049655323e-07,
"loss": 1.0461,
"step": 195
},
{
"epoch": 0.3447669305189094,
"grad_norm": 1.016954779624939,
"learning_rate": 2.7308266142119785e-07,
"loss": 1.1179,
"step": 196
},
{
"epoch": 0.3465259454705365,
"grad_norm": 1.084816336631775,
"learning_rate": 1.5363960325660565e-07,
"loss": 1.0947,
"step": 197
},
{
"epoch": 0.3482849604221636,
"grad_norm": 1.0620332956314087,
"learning_rate": 6.829398569770939e-08,
"loss": 0.9681,
"step": 198
},
{
"epoch": 0.3500439753737907,
"grad_norm": 0.9418560862541199,
"learning_rate": 1.7074954194729044e-08,
"loss": 1.0684,
"step": 199
},
{
"epoch": 0.3518029903254178,
"grad_norm": 0.9430168271064758,
"learning_rate": 0.0,
"loss": 1.0693,
"step": 200
}
],
"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": true
},
"attributes": {}
}
},
"total_flos": 1.154618474102784e+17,
"train_batch_size": 3,
"trial_name": null,
"trial_params": null
}