jssky's picture
Training in progress, step 230, checkpoint
f0cde3d verified
raw
history blame
41 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.250272034820457,
"eval_steps": 230,
"global_step": 230,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.001088139281828074,
"grad_norm": 0.04828796908259392,
"learning_rate": 2e-05,
"loss": 0.0762,
"step": 1
},
{
"epoch": 0.002176278563656148,
"grad_norm": 0.06207922473549843,
"learning_rate": 4e-05,
"loss": 0.0973,
"step": 2
},
{
"epoch": 0.003264417845484222,
"grad_norm": 0.06030188128352165,
"learning_rate": 6e-05,
"loss": 0.1003,
"step": 3
},
{
"epoch": 0.004352557127312296,
"grad_norm": 0.05758730694651604,
"learning_rate": 8e-05,
"loss": 0.085,
"step": 4
},
{
"epoch": 0.00544069640914037,
"grad_norm": 0.07111983001232147,
"learning_rate": 0.0001,
"loss": 0.1174,
"step": 5
},
{
"epoch": 0.006528835690968444,
"grad_norm": 0.09522929042577744,
"learning_rate": 0.00012,
"loss": 0.1404,
"step": 6
},
{
"epoch": 0.007616974972796518,
"grad_norm": 0.08600069582462311,
"learning_rate": 0.00014,
"loss": 0.1187,
"step": 7
},
{
"epoch": 0.008705114254624592,
"grad_norm": 0.0808354914188385,
"learning_rate": 0.00016,
"loss": 0.1235,
"step": 8
},
{
"epoch": 0.009793253536452665,
"grad_norm": 0.10051260888576508,
"learning_rate": 0.00018,
"loss": 0.135,
"step": 9
},
{
"epoch": 0.01088139281828074,
"grad_norm": 0.08877796679735184,
"learning_rate": 0.0002,
"loss": 0.0803,
"step": 10
},
{
"epoch": 0.011969532100108813,
"grad_norm": 0.10384293645620346,
"learning_rate": 0.00019999940277008808,
"loss": 0.1206,
"step": 11
},
{
"epoch": 0.013057671381936888,
"grad_norm": 0.1314290463924408,
"learning_rate": 0.00019999761108748597,
"loss": 0.1249,
"step": 12
},
{
"epoch": 0.014145810663764961,
"grad_norm": 0.12873488664627075,
"learning_rate": 0.00019999462497359466,
"loss": 0.0847,
"step": 13
},
{
"epoch": 0.015233949945593036,
"grad_norm": 0.12493155896663666,
"learning_rate": 0.000199990444464082,
"loss": 0.0858,
"step": 14
},
{
"epoch": 0.01632208922742111,
"grad_norm": 0.1131022647023201,
"learning_rate": 0.00019998506960888256,
"loss": 0.0737,
"step": 15
},
{
"epoch": 0.017410228509249184,
"grad_norm": 0.1214890405535698,
"learning_rate": 0.0001999785004721968,
"loss": 0.1151,
"step": 16
},
{
"epoch": 0.018498367791077257,
"grad_norm": 0.12649253010749817,
"learning_rate": 0.0001999707371324904,
"loss": 0.0913,
"step": 17
},
{
"epoch": 0.01958650707290533,
"grad_norm": 0.12470237910747528,
"learning_rate": 0.00019996177968249334,
"loss": 0.1043,
"step": 18
},
{
"epoch": 0.020674646354733407,
"grad_norm": 0.15574277937412262,
"learning_rate": 0.00019995162822919883,
"loss": 0.1092,
"step": 19
},
{
"epoch": 0.02176278563656148,
"grad_norm": 0.1281992644071579,
"learning_rate": 0.0001999402828938618,
"loss": 0.0892,
"step": 20
},
{
"epoch": 0.022850924918389554,
"grad_norm": 0.16906976699829102,
"learning_rate": 0.00019992774381199778,
"loss": 0.1633,
"step": 21
},
{
"epoch": 0.023939064200217627,
"grad_norm": 0.12387573719024658,
"learning_rate": 0.00019991401113338104,
"loss": 0.0872,
"step": 22
},
{
"epoch": 0.025027203482045703,
"grad_norm": 0.12343913316726685,
"learning_rate": 0.00019989908502204292,
"loss": 0.1084,
"step": 23
},
{
"epoch": 0.026115342763873776,
"grad_norm": 0.11399204283952713,
"learning_rate": 0.00019988296565626987,
"loss": 0.0824,
"step": 24
},
{
"epoch": 0.02720348204570185,
"grad_norm": 0.1402149796485901,
"learning_rate": 0.00019986565322860115,
"loss": 0.1289,
"step": 25
},
{
"epoch": 0.028291621327529923,
"grad_norm": 0.13711000978946686,
"learning_rate": 0.00019984714794582683,
"loss": 0.097,
"step": 26
},
{
"epoch": 0.029379760609358,
"grad_norm": 0.18544617295265198,
"learning_rate": 0.000199827450028985,
"loss": 0.1281,
"step": 27
},
{
"epoch": 0.030467899891186073,
"grad_norm": 0.15856046974658966,
"learning_rate": 0.00019980655971335945,
"loss": 0.1027,
"step": 28
},
{
"epoch": 0.031556039173014146,
"grad_norm": 0.12590578198432922,
"learning_rate": 0.00019978447724847652,
"loss": 0.0863,
"step": 29
},
{
"epoch": 0.03264417845484222,
"grad_norm": 0.14784540235996246,
"learning_rate": 0.00019976120289810247,
"loss": 0.1125,
"step": 30
},
{
"epoch": 0.03373231773667029,
"grad_norm": 0.19753308594226837,
"learning_rate": 0.00019973673694024,
"loss": 0.1389,
"step": 31
},
{
"epoch": 0.03482045701849837,
"grad_norm": 0.17247086763381958,
"learning_rate": 0.00019971107966712518,
"loss": 0.0901,
"step": 32
},
{
"epoch": 0.035908596300326445,
"grad_norm": 0.23573236167430878,
"learning_rate": 0.0001996842313852238,
"loss": 0.1141,
"step": 33
},
{
"epoch": 0.036996735582154515,
"grad_norm": 0.1349520981311798,
"learning_rate": 0.0001996561924152278,
"loss": 0.077,
"step": 34
},
{
"epoch": 0.03808487486398259,
"grad_norm": 0.2573637068271637,
"learning_rate": 0.00019962696309205148,
"loss": 0.0965,
"step": 35
},
{
"epoch": 0.03917301414581066,
"grad_norm": 0.2688570022583008,
"learning_rate": 0.0001995965437648273,
"loss": 0.1754,
"step": 36
},
{
"epoch": 0.04026115342763874,
"grad_norm": 0.2946501076221466,
"learning_rate": 0.0001995649347969019,
"loss": 0.1893,
"step": 37
},
{
"epoch": 0.041349292709466814,
"grad_norm": 0.2942318320274353,
"learning_rate": 0.00019953213656583168,
"loss": 0.1461,
"step": 38
},
{
"epoch": 0.042437431991294884,
"grad_norm": 0.3316934406757355,
"learning_rate": 0.00019949814946337838,
"loss": 0.1072,
"step": 39
},
{
"epoch": 0.04352557127312296,
"grad_norm": 0.3863315284252167,
"learning_rate": 0.00019946297389550433,
"loss": 0.1517,
"step": 40
},
{
"epoch": 0.04461371055495103,
"grad_norm": 0.3102675974369049,
"learning_rate": 0.00019942661028236745,
"loss": 0.1421,
"step": 41
},
{
"epoch": 0.04570184983677911,
"grad_norm": 0.3270488679409027,
"learning_rate": 0.00019938905905831654,
"loss": 0.085,
"step": 42
},
{
"epoch": 0.046789989118607184,
"grad_norm": 0.3799861669540405,
"learning_rate": 0.0001993503206718859,
"loss": 0.1333,
"step": 43
},
{
"epoch": 0.04787812840043525,
"grad_norm": 0.45475858449935913,
"learning_rate": 0.00019931039558578997,
"loss": 0.1431,
"step": 44
},
{
"epoch": 0.04896626768226333,
"grad_norm": 0.3995339870452881,
"learning_rate": 0.00019926928427691786,
"loss": 0.18,
"step": 45
},
{
"epoch": 0.05005440696409141,
"grad_norm": 0.4547290503978729,
"learning_rate": 0.00019922698723632767,
"loss": 0.1578,
"step": 46
},
{
"epoch": 0.051142546245919476,
"grad_norm": 0.44180116057395935,
"learning_rate": 0.0001991835049692405,
"loss": 0.2327,
"step": 47
},
{
"epoch": 0.05223068552774755,
"grad_norm": 0.8059853911399841,
"learning_rate": 0.0001991388379950346,
"loss": 0.3089,
"step": 48
},
{
"epoch": 0.05331882480957562,
"grad_norm": 0.6336686015129089,
"learning_rate": 0.00019909298684723904,
"loss": 0.2055,
"step": 49
},
{
"epoch": 0.0544069640914037,
"grad_norm": 0.8279074430465698,
"learning_rate": 0.00019904595207352737,
"loss": 0.2626,
"step": 50
},
{
"epoch": 0.055495103373231776,
"grad_norm": 0.07426032423973083,
"learning_rate": 0.000198997734235711,
"loss": 0.0632,
"step": 51
},
{
"epoch": 0.056583242655059846,
"grad_norm": 0.09094005823135376,
"learning_rate": 0.00019894833390973266,
"loss": 0.0734,
"step": 52
},
{
"epoch": 0.05767138193688792,
"grad_norm": 0.09561450034379959,
"learning_rate": 0.00019889775168565943,
"loss": 0.0972,
"step": 53
},
{
"epoch": 0.058759521218716,
"grad_norm": 0.09174304455518723,
"learning_rate": 0.00019884598816767563,
"loss": 0.082,
"step": 54
},
{
"epoch": 0.05984766050054407,
"grad_norm": 0.0911480113863945,
"learning_rate": 0.0001987930439740757,
"loss": 0.0712,
"step": 55
},
{
"epoch": 0.060935799782372145,
"grad_norm": 0.1090071052312851,
"learning_rate": 0.0001987389197372567,
"loss": 0.09,
"step": 56
},
{
"epoch": 0.062023939064200215,
"grad_norm": 0.09118974953889847,
"learning_rate": 0.00019868361610371097,
"loss": 0.0946,
"step": 57
},
{
"epoch": 0.06311207834602829,
"grad_norm": 0.09903446584939957,
"learning_rate": 0.0001986271337340182,
"loss": 0.1074,
"step": 58
},
{
"epoch": 0.06420021762785637,
"grad_norm": 0.08208192884922028,
"learning_rate": 0.00019856947330283752,
"loss": 0.0847,
"step": 59
},
{
"epoch": 0.06528835690968444,
"grad_norm": 0.08504832535982132,
"learning_rate": 0.0001985106354988997,
"loss": 0.0852,
"step": 60
},
{
"epoch": 0.06637649619151251,
"grad_norm": 0.07276565581560135,
"learning_rate": 0.0001984506210249986,
"loss": 0.061,
"step": 61
},
{
"epoch": 0.06746463547334058,
"grad_norm": 0.08346979320049286,
"learning_rate": 0.00019838943059798304,
"loss": 0.0717,
"step": 62
},
{
"epoch": 0.06855277475516866,
"grad_norm": 0.09144837409257889,
"learning_rate": 0.0001983270649487481,
"loss": 0.0817,
"step": 63
},
{
"epoch": 0.06964091403699674,
"grad_norm": 0.09562050551176071,
"learning_rate": 0.00019826352482222638,
"loss": 0.0809,
"step": 64
},
{
"epoch": 0.07072905331882481,
"grad_norm": 0.10410594195127487,
"learning_rate": 0.00019819881097737915,
"loss": 0.0801,
"step": 65
},
{
"epoch": 0.07181719260065289,
"grad_norm": 0.0836932361125946,
"learning_rate": 0.00019813292418718732,
"loss": 0.0775,
"step": 66
},
{
"epoch": 0.07290533188248095,
"grad_norm": 0.09397463500499725,
"learning_rate": 0.0001980658652386421,
"loss": 0.065,
"step": 67
},
{
"epoch": 0.07399347116430903,
"grad_norm": 0.108340784907341,
"learning_rate": 0.0001979976349327357,
"loss": 0.0981,
"step": 68
},
{
"epoch": 0.0750816104461371,
"grad_norm": 0.08717814087867737,
"learning_rate": 0.00019792823408445174,
"loss": 0.0798,
"step": 69
},
{
"epoch": 0.07616974972796518,
"grad_norm": 0.1279960721731186,
"learning_rate": 0.00019785766352275542,
"loss": 0.0993,
"step": 70
},
{
"epoch": 0.07725788900979326,
"grad_norm": 0.13422514498233795,
"learning_rate": 0.00019778592409058378,
"loss": 0.1023,
"step": 71
},
{
"epoch": 0.07834602829162132,
"grad_norm": 0.10113417357206345,
"learning_rate": 0.0001977130166448355,
"loss": 0.0742,
"step": 72
},
{
"epoch": 0.0794341675734494,
"grad_norm": 0.1026310920715332,
"learning_rate": 0.00019763894205636072,
"loss": 0.0988,
"step": 73
},
{
"epoch": 0.08052230685527748,
"grad_norm": 0.09779265522956848,
"learning_rate": 0.00019756370120995066,
"loss": 0.0738,
"step": 74
},
{
"epoch": 0.08161044613710555,
"grad_norm": 0.14643464982509613,
"learning_rate": 0.000197487295004327,
"loss": 0.09,
"step": 75
},
{
"epoch": 0.08269858541893363,
"grad_norm": 0.11976644396781921,
"learning_rate": 0.00019740972435213115,
"loss": 0.0904,
"step": 76
},
{
"epoch": 0.08378672470076169,
"grad_norm": 0.10904321819543839,
"learning_rate": 0.00019733099017991341,
"loss": 0.0766,
"step": 77
},
{
"epoch": 0.08487486398258977,
"grad_norm": 0.1651339828968048,
"learning_rate": 0.0001972510934281218,
"loss": 0.1186,
"step": 78
},
{
"epoch": 0.08596300326441784,
"grad_norm": 0.11781762540340424,
"learning_rate": 0.00019717003505109095,
"loss": 0.0833,
"step": 79
},
{
"epoch": 0.08705114254624592,
"grad_norm": 0.15122370421886444,
"learning_rate": 0.00019708781601703065,
"loss": 0.1166,
"step": 80
},
{
"epoch": 0.088139281828074,
"grad_norm": 0.1798838973045349,
"learning_rate": 0.00019700443730801413,
"loss": 0.1109,
"step": 81
},
{
"epoch": 0.08922742110990206,
"grad_norm": 0.18025629222393036,
"learning_rate": 0.00019691989991996663,
"loss": 0.1243,
"step": 82
},
{
"epoch": 0.09031556039173014,
"grad_norm": 0.1731874644756317,
"learning_rate": 0.00019683420486265327,
"loss": 0.1189,
"step": 83
},
{
"epoch": 0.09140369967355821,
"grad_norm": 0.2220824509859085,
"learning_rate": 0.0001967473531596671,
"loss": 0.1451,
"step": 84
},
{
"epoch": 0.09249183895538629,
"grad_norm": 0.1664338856935501,
"learning_rate": 0.00019665934584841682,
"loss": 0.0897,
"step": 85
},
{
"epoch": 0.09357997823721437,
"grad_norm": 0.17619486153125763,
"learning_rate": 0.00019657018398011434,
"loss": 0.0935,
"step": 86
},
{
"epoch": 0.09466811751904244,
"grad_norm": 0.24987219274044037,
"learning_rate": 0.00019647986861976246,
"loss": 0.1955,
"step": 87
},
{
"epoch": 0.0957562568008705,
"grad_norm": 0.21318784356117249,
"learning_rate": 0.00019638840084614182,
"loss": 0.1131,
"step": 88
},
{
"epoch": 0.09684439608269858,
"grad_norm": 0.3128167390823364,
"learning_rate": 0.0001962957817517982,
"loss": 0.2011,
"step": 89
},
{
"epoch": 0.09793253536452666,
"grad_norm": 0.2833835184574127,
"learning_rate": 0.00019620201244302952,
"loss": 0.1592,
"step": 90
},
{
"epoch": 0.09902067464635474,
"grad_norm": 0.3286789357662201,
"learning_rate": 0.00019610709403987246,
"loss": 0.1602,
"step": 91
},
{
"epoch": 0.10010881392818281,
"grad_norm": 0.44117358326911926,
"learning_rate": 0.00019601102767608923,
"loss": 0.2323,
"step": 92
},
{
"epoch": 0.10119695321001088,
"grad_norm": 0.3795579671859741,
"learning_rate": 0.00019591381449915397,
"loss": 0.1867,
"step": 93
},
{
"epoch": 0.10228509249183895,
"grad_norm": 0.5780506730079651,
"learning_rate": 0.000195815455670239,
"loss": 0.1884,
"step": 94
},
{
"epoch": 0.10337323177366703,
"grad_norm": 0.5124024748802185,
"learning_rate": 0.00019571595236420102,
"loss": 0.221,
"step": 95
},
{
"epoch": 0.1044613710554951,
"grad_norm": 0.4628782272338867,
"learning_rate": 0.00019561530576956703,
"loss": 0.208,
"step": 96
},
{
"epoch": 0.10554951033732318,
"grad_norm": 0.3904087543487549,
"learning_rate": 0.0001955135170885202,
"loss": 0.2029,
"step": 97
},
{
"epoch": 0.10663764961915125,
"grad_norm": 0.513387143611908,
"learning_rate": 0.00019541058753688538,
"loss": 0.2248,
"step": 98
},
{
"epoch": 0.10772578890097932,
"grad_norm": 0.6133597493171692,
"learning_rate": 0.00019530651834411474,
"loss": 0.3751,
"step": 99
},
{
"epoch": 0.1088139281828074,
"grad_norm": 0.6515563726425171,
"learning_rate": 0.00019520131075327298,
"loss": 0.2096,
"step": 100
},
{
"epoch": 0.10990206746463548,
"grad_norm": 0.07718291878700256,
"learning_rate": 0.00019509496602102252,
"loss": 0.0631,
"step": 101
},
{
"epoch": 0.11099020674646355,
"grad_norm": 0.07896394282579422,
"learning_rate": 0.00019498748541760846,
"loss": 0.095,
"step": 102
},
{
"epoch": 0.11207834602829161,
"grad_norm": 0.07955438643693924,
"learning_rate": 0.00019487887022684336,
"loss": 0.067,
"step": 103
},
{
"epoch": 0.11316648531011969,
"grad_norm": 0.08391376584768295,
"learning_rate": 0.0001947691217460921,
"loss": 0.0637,
"step": 104
},
{
"epoch": 0.11425462459194777,
"grad_norm": 0.07990088313817978,
"learning_rate": 0.00019465824128625617,
"loss": 0.0569,
"step": 105
},
{
"epoch": 0.11534276387377584,
"grad_norm": 0.09000790864229202,
"learning_rate": 0.00019454623017175812,
"loss": 0.0639,
"step": 106
},
{
"epoch": 0.11643090315560392,
"grad_norm": 0.0831453874707222,
"learning_rate": 0.0001944330897405257,
"loss": 0.0766,
"step": 107
},
{
"epoch": 0.117519042437432,
"grad_norm": 0.08180610835552216,
"learning_rate": 0.00019431882134397598,
"loss": 0.0806,
"step": 108
},
{
"epoch": 0.11860718171926006,
"grad_norm": 0.07601706683635712,
"learning_rate": 0.0001942034263469989,
"loss": 0.0727,
"step": 109
},
{
"epoch": 0.11969532100108814,
"grad_norm": 0.08873546868562698,
"learning_rate": 0.00019408690612794148,
"loss": 0.0878,
"step": 110
},
{
"epoch": 0.12078346028291621,
"grad_norm": 0.10206414759159088,
"learning_rate": 0.00019396926207859084,
"loss": 0.1171,
"step": 111
},
{
"epoch": 0.12187159956474429,
"grad_norm": 0.07465587556362152,
"learning_rate": 0.00019385049560415794,
"loss": 0.0603,
"step": 112
},
{
"epoch": 0.12295973884657237,
"grad_norm": 0.09952360391616821,
"learning_rate": 0.00019373060812326052,
"loss": 0.0923,
"step": 113
},
{
"epoch": 0.12404787812840043,
"grad_norm": 0.09894778579473495,
"learning_rate": 0.00019360960106790643,
"loss": 0.0795,
"step": 114
},
{
"epoch": 0.1251360174102285,
"grad_norm": 0.09721358120441437,
"learning_rate": 0.00019348747588347637,
"loss": 0.1103,
"step": 115
},
{
"epoch": 0.12622415669205658,
"grad_norm": 0.10310002416372299,
"learning_rate": 0.00019336423402870653,
"loss": 0.1037,
"step": 116
},
{
"epoch": 0.12731229597388466,
"grad_norm": 0.10904382914304733,
"learning_rate": 0.0001932398769756714,
"loss": 0.1063,
"step": 117
},
{
"epoch": 0.12840043525571274,
"grad_norm": 0.11545544862747192,
"learning_rate": 0.00019311440620976597,
"loss": 0.096,
"step": 118
},
{
"epoch": 0.1294885745375408,
"grad_norm": 0.08674886077642441,
"learning_rate": 0.00019298782322968815,
"loss": 0.0779,
"step": 119
},
{
"epoch": 0.1305767138193689,
"grad_norm": 0.09437372535467148,
"learning_rate": 0.0001928601295474208,
"loss": 0.0975,
"step": 120
},
{
"epoch": 0.13166485310119697,
"grad_norm": 0.1258208006620407,
"learning_rate": 0.00019273132668821364,
"loss": 0.1277,
"step": 121
},
{
"epoch": 0.13275299238302501,
"grad_norm": 0.09919868409633636,
"learning_rate": 0.00019260141619056507,
"loss": 0.0993,
"step": 122
},
{
"epoch": 0.1338411316648531,
"grad_norm": 0.12028370052576065,
"learning_rate": 0.0001924703996062038,
"loss": 0.0751,
"step": 123
},
{
"epoch": 0.13492927094668117,
"grad_norm": 0.10702817142009735,
"learning_rate": 0.00019233827850007027,
"loss": 0.0949,
"step": 124
},
{
"epoch": 0.13601741022850924,
"grad_norm": 0.10939855128526688,
"learning_rate": 0.000192205054450298,
"loss": 0.0977,
"step": 125
},
{
"epoch": 0.13710554951033732,
"grad_norm": 0.11803679168224335,
"learning_rate": 0.00019207072904819486,
"loss": 0.0877,
"step": 126
},
{
"epoch": 0.1381936887921654,
"grad_norm": 0.1382649838924408,
"learning_rate": 0.00019193530389822363,
"loss": 0.1017,
"step": 127
},
{
"epoch": 0.13928182807399347,
"grad_norm": 0.1433139145374298,
"learning_rate": 0.00019179878061798347,
"loss": 0.0748,
"step": 128
},
{
"epoch": 0.14036996735582155,
"grad_norm": 0.14679527282714844,
"learning_rate": 0.00019166116083819002,
"loss": 0.1164,
"step": 129
},
{
"epoch": 0.14145810663764963,
"grad_norm": 0.13680118322372437,
"learning_rate": 0.0001915224462026563,
"loss": 0.1149,
"step": 130
},
{
"epoch": 0.1425462459194777,
"grad_norm": 0.16263848543167114,
"learning_rate": 0.00019138263836827288,
"loss": 0.1192,
"step": 131
},
{
"epoch": 0.14363438520130578,
"grad_norm": 0.16534928977489471,
"learning_rate": 0.00019124173900498818,
"loss": 0.1138,
"step": 132
},
{
"epoch": 0.14472252448313383,
"grad_norm": 0.21276706457138062,
"learning_rate": 0.0001910997497957885,
"loss": 0.1461,
"step": 133
},
{
"epoch": 0.1458106637649619,
"grad_norm": 0.2375650703907013,
"learning_rate": 0.0001909566724366779,
"loss": 0.2031,
"step": 134
},
{
"epoch": 0.14689880304678998,
"grad_norm": 0.20974405109882355,
"learning_rate": 0.00019081250863665794,
"loss": 0.1285,
"step": 135
},
{
"epoch": 0.14798694232861806,
"grad_norm": 0.308624267578125,
"learning_rate": 0.00019066726011770726,
"loss": 0.1717,
"step": 136
},
{
"epoch": 0.14907508161044614,
"grad_norm": 0.21192695200443268,
"learning_rate": 0.0001905209286147611,
"loss": 0.1064,
"step": 137
},
{
"epoch": 0.1501632208922742,
"grad_norm": 0.20596542954444885,
"learning_rate": 0.0001903735158756905,
"loss": 0.0975,
"step": 138
},
{
"epoch": 0.1512513601741023,
"grad_norm": 0.21547934412956238,
"learning_rate": 0.00019022502366128135,
"loss": 0.1255,
"step": 139
},
{
"epoch": 0.15233949945593037,
"grad_norm": 0.276815801858902,
"learning_rate": 0.00019007545374521355,
"loss": 0.0868,
"step": 140
},
{
"epoch": 0.15342763873775844,
"grad_norm": 0.37251031398773193,
"learning_rate": 0.00018992480791403958,
"loss": 0.1078,
"step": 141
},
{
"epoch": 0.15451577801958652,
"grad_norm": 0.328265517950058,
"learning_rate": 0.0001897730879671634,
"loss": 0.1842,
"step": 142
},
{
"epoch": 0.15560391730141457,
"grad_norm": 0.4400005340576172,
"learning_rate": 0.00018962029571681886,
"loss": 0.1857,
"step": 143
},
{
"epoch": 0.15669205658324264,
"grad_norm": 0.28378888964653015,
"learning_rate": 0.00018946643298804793,
"loss": 0.0955,
"step": 144
},
{
"epoch": 0.15778019586507072,
"grad_norm": 0.609008252620697,
"learning_rate": 0.00018931150161867916,
"loss": 0.3827,
"step": 145
},
{
"epoch": 0.1588683351468988,
"grad_norm": 0.3973180055618286,
"learning_rate": 0.0001891555034593055,
"loss": 0.1844,
"step": 146
},
{
"epoch": 0.15995647442872687,
"grad_norm": 0.36245423555374146,
"learning_rate": 0.00018899844037326225,
"loss": 0.2005,
"step": 147
},
{
"epoch": 0.16104461371055495,
"grad_norm": 0.5730637311935425,
"learning_rate": 0.0001888403142366049,
"loss": 0.2742,
"step": 148
},
{
"epoch": 0.16213275299238303,
"grad_norm": 0.5383718013763428,
"learning_rate": 0.00018868112693808665,
"loss": 0.2249,
"step": 149
},
{
"epoch": 0.1632208922742111,
"grad_norm": 0.9835379123687744,
"learning_rate": 0.00018852088037913577,
"loss": 0.344,
"step": 150
},
{
"epoch": 0.16430903155603918,
"grad_norm": 0.09142426401376724,
"learning_rate": 0.00018835957647383303,
"loss": 0.0876,
"step": 151
},
{
"epoch": 0.16539717083786726,
"grad_norm": 0.09199874103069305,
"learning_rate": 0.00018819721714888877,
"loss": 0.0798,
"step": 152
},
{
"epoch": 0.16648531011969533,
"grad_norm": 0.08299195021390915,
"learning_rate": 0.00018803380434362,
"loss": 0.0746,
"step": 153
},
{
"epoch": 0.16757344940152338,
"grad_norm": 0.10273315012454987,
"learning_rate": 0.00018786934000992688,
"loss": 0.101,
"step": 154
},
{
"epoch": 0.16866158868335146,
"grad_norm": 0.08524151146411896,
"learning_rate": 0.00018770382611226987,
"loss": 0.0684,
"step": 155
},
{
"epoch": 0.16974972796517954,
"grad_norm": 0.10515481233596802,
"learning_rate": 0.000187537264627646,
"loss": 0.0809,
"step": 156
},
{
"epoch": 0.1708378672470076,
"grad_norm": 0.09009183198213577,
"learning_rate": 0.00018736965754556528,
"loss": 0.0955,
"step": 157
},
{
"epoch": 0.1719260065288357,
"grad_norm": 0.10571747273206711,
"learning_rate": 0.00018720100686802694,
"loss": 0.0847,
"step": 158
},
{
"epoch": 0.17301414581066377,
"grad_norm": 0.08275768160820007,
"learning_rate": 0.00018703131460949554,
"loss": 0.0799,
"step": 159
},
{
"epoch": 0.17410228509249184,
"grad_norm": 0.08440782129764557,
"learning_rate": 0.00018686058279687698,
"loss": 0.0672,
"step": 160
},
{
"epoch": 0.17519042437431992,
"grad_norm": 0.10261505097150803,
"learning_rate": 0.00018668881346949417,
"loss": 0.1004,
"step": 161
},
{
"epoch": 0.176278563656148,
"grad_norm": 0.08730655908584595,
"learning_rate": 0.00018651600867906272,
"loss": 0.0711,
"step": 162
},
{
"epoch": 0.17736670293797607,
"grad_norm": 0.10591359436511993,
"learning_rate": 0.00018634217048966637,
"loss": 0.0919,
"step": 163
},
{
"epoch": 0.17845484221980412,
"grad_norm": 0.09251653403043747,
"learning_rate": 0.0001861673009777325,
"loss": 0.078,
"step": 164
},
{
"epoch": 0.1795429815016322,
"grad_norm": 0.106822170317173,
"learning_rate": 0.00018599140223200716,
"loss": 0.0895,
"step": 165
},
{
"epoch": 0.18063112078346028,
"grad_norm": 0.11222364753484726,
"learning_rate": 0.0001858144763535302,
"loss": 0.0918,
"step": 166
},
{
"epoch": 0.18171926006528835,
"grad_norm": 0.1363314390182495,
"learning_rate": 0.00018563652545561013,
"loss": 0.1126,
"step": 167
},
{
"epoch": 0.18280739934711643,
"grad_norm": 0.09316174685955048,
"learning_rate": 0.000185457551663799,
"loss": 0.0799,
"step": 168
},
{
"epoch": 0.1838955386289445,
"grad_norm": 0.13098089396953583,
"learning_rate": 0.00018527755711586678,
"loss": 0.0994,
"step": 169
},
{
"epoch": 0.18498367791077258,
"grad_norm": 0.11433115601539612,
"learning_rate": 0.00018509654396177609,
"loss": 0.1072,
"step": 170
},
{
"epoch": 0.18607181719260066,
"grad_norm": 0.11261814087629318,
"learning_rate": 0.00018491451436365627,
"loss": 0.1011,
"step": 171
},
{
"epoch": 0.18715995647442873,
"grad_norm": 0.1038559302687645,
"learning_rate": 0.00018473147049577774,
"loss": 0.0746,
"step": 172
},
{
"epoch": 0.1882480957562568,
"grad_norm": 0.11395396292209625,
"learning_rate": 0.00018454741454452603,
"loss": 0.0792,
"step": 173
},
{
"epoch": 0.1893362350380849,
"grad_norm": 0.13332821428775787,
"learning_rate": 0.00018436234870837547,
"loss": 0.1041,
"step": 174
},
{
"epoch": 0.19042437431991294,
"grad_norm": 0.12438289821147919,
"learning_rate": 0.00018417627519786315,
"loss": 0.1066,
"step": 175
},
{
"epoch": 0.191512513601741,
"grad_norm": 0.1353287398815155,
"learning_rate": 0.00018398919623556238,
"loss": 0.1193,
"step": 176
},
{
"epoch": 0.1926006528835691,
"grad_norm": 0.13928581774234772,
"learning_rate": 0.0001838011140560562,
"loss": 0.1228,
"step": 177
},
{
"epoch": 0.19368879216539717,
"grad_norm": 0.1474994421005249,
"learning_rate": 0.00018361203090591071,
"loss": 0.0812,
"step": 178
},
{
"epoch": 0.19477693144722524,
"grad_norm": 0.1910678595304489,
"learning_rate": 0.00018342194904364813,
"loss": 0.1435,
"step": 179
},
{
"epoch": 0.19586507072905332,
"grad_norm": 0.16526034474372864,
"learning_rate": 0.00018323087073971993,
"loss": 0.1136,
"step": 180
},
{
"epoch": 0.1969532100108814,
"grad_norm": 0.1933068335056305,
"learning_rate": 0.00018303879827647975,
"loss": 0.1498,
"step": 181
},
{
"epoch": 0.19804134929270947,
"grad_norm": 0.1647845059633255,
"learning_rate": 0.00018284573394815597,
"loss": 0.0764,
"step": 182
},
{
"epoch": 0.19912948857453755,
"grad_norm": 0.19414739310741425,
"learning_rate": 0.00018265168006082437,
"loss": 0.1142,
"step": 183
},
{
"epoch": 0.20021762785636563,
"grad_norm": 0.1872360110282898,
"learning_rate": 0.00018245663893238075,
"loss": 0.1169,
"step": 184
},
{
"epoch": 0.20130576713819368,
"grad_norm": 0.19919492304325104,
"learning_rate": 0.00018226061289251298,
"loss": 0.0854,
"step": 185
},
{
"epoch": 0.20239390642002175,
"grad_norm": 0.2233375757932663,
"learning_rate": 0.00018206360428267332,
"loss": 0.1271,
"step": 186
},
{
"epoch": 0.20348204570184983,
"grad_norm": 0.22116345167160034,
"learning_rate": 0.00018186561545605054,
"loss": 0.1402,
"step": 187
},
{
"epoch": 0.2045701849836779,
"grad_norm": 0.253864049911499,
"learning_rate": 0.0001816666487775416,
"loss": 0.1431,
"step": 188
},
{
"epoch": 0.20565832426550598,
"grad_norm": 0.2945636212825775,
"learning_rate": 0.00018146670662372354,
"loss": 0.1284,
"step": 189
},
{
"epoch": 0.20674646354733406,
"grad_norm": 0.24834126234054565,
"learning_rate": 0.00018126579138282503,
"loss": 0.098,
"step": 190
},
{
"epoch": 0.20783460282916214,
"grad_norm": 0.26815730333328247,
"learning_rate": 0.00018106390545469795,
"loss": 0.0877,
"step": 191
},
{
"epoch": 0.2089227421109902,
"grad_norm": 0.375293493270874,
"learning_rate": 0.00018086105125078857,
"loss": 0.1985,
"step": 192
},
{
"epoch": 0.2100108813928183,
"grad_norm": 0.4025906026363373,
"learning_rate": 0.00018065723119410884,
"loss": 0.2082,
"step": 193
},
{
"epoch": 0.21109902067464636,
"grad_norm": 0.3551553785800934,
"learning_rate": 0.0001804524477192075,
"loss": 0.2305,
"step": 194
},
{
"epoch": 0.21218715995647444,
"grad_norm": 0.594780445098877,
"learning_rate": 0.00018024670327214084,
"loss": 0.2713,
"step": 195
},
{
"epoch": 0.2132752992383025,
"grad_norm": 0.3940027356147766,
"learning_rate": 0.0001800400003104436,
"loss": 0.1623,
"step": 196
},
{
"epoch": 0.21436343852013057,
"grad_norm": 0.51041579246521,
"learning_rate": 0.00017983234130309968,
"loss": 0.2236,
"step": 197
},
{
"epoch": 0.21545157780195864,
"grad_norm": 0.6203753352165222,
"learning_rate": 0.00017962372873051252,
"loss": 0.2654,
"step": 198
},
{
"epoch": 0.21653971708378672,
"grad_norm": 0.7527713179588318,
"learning_rate": 0.00017941416508447536,
"loss": 0.2088,
"step": 199
},
{
"epoch": 0.2176278563656148,
"grad_norm": 1.1047406196594238,
"learning_rate": 0.00017920365286814183,
"loss": 0.3097,
"step": 200
},
{
"epoch": 0.21871599564744287,
"grad_norm": 0.0492124930024147,
"learning_rate": 0.0001789921945959958,
"loss": 0.0344,
"step": 201
},
{
"epoch": 0.21980413492927095,
"grad_norm": 0.07087790220975876,
"learning_rate": 0.00017877979279382135,
"loss": 0.0582,
"step": 202
},
{
"epoch": 0.22089227421109903,
"grad_norm": 0.07622935622930527,
"learning_rate": 0.00017856644999867264,
"loss": 0.062,
"step": 203
},
{
"epoch": 0.2219804134929271,
"grad_norm": 0.08792652189731598,
"learning_rate": 0.00017835216875884368,
"loss": 0.0511,
"step": 204
},
{
"epoch": 0.22306855277475518,
"grad_norm": 0.08028998970985413,
"learning_rate": 0.0001781369516338378,
"loss": 0.0665,
"step": 205
},
{
"epoch": 0.22415669205658323,
"grad_norm": 0.08997032046318054,
"learning_rate": 0.0001779208011943371,
"loss": 0.069,
"step": 206
},
{
"epoch": 0.2252448313384113,
"grad_norm": 0.08684886246919632,
"learning_rate": 0.00017770372002217172,
"loss": 0.077,
"step": 207
},
{
"epoch": 0.22633297062023938,
"grad_norm": 0.0965440422296524,
"learning_rate": 0.000177485710710289,
"loss": 0.0782,
"step": 208
},
{
"epoch": 0.22742110990206746,
"grad_norm": 0.09060367196798325,
"learning_rate": 0.00017726677586272263,
"loss": 0.066,
"step": 209
},
{
"epoch": 0.22850924918389554,
"grad_norm": 0.0900409147143364,
"learning_rate": 0.00017704691809456143,
"loss": 0.0707,
"step": 210
},
{
"epoch": 0.2295973884657236,
"grad_norm": 0.10733999311923981,
"learning_rate": 0.00017682614003191807,
"loss": 0.0916,
"step": 211
},
{
"epoch": 0.2306855277475517,
"grad_norm": 0.09372083842754364,
"learning_rate": 0.0001766044443118978,
"loss": 0.0872,
"step": 212
},
{
"epoch": 0.23177366702937977,
"grad_norm": 0.10344577580690384,
"learning_rate": 0.00017638183358256696,
"loss": 0.0903,
"step": 213
},
{
"epoch": 0.23286180631120784,
"grad_norm": 0.1084800437092781,
"learning_rate": 0.0001761583105029213,
"loss": 0.0926,
"step": 214
},
{
"epoch": 0.23394994559303592,
"grad_norm": 0.08565113693475723,
"learning_rate": 0.00017593387774285412,
"loss": 0.0758,
"step": 215
},
{
"epoch": 0.235038084874864,
"grad_norm": 0.11589045077562332,
"learning_rate": 0.0001757085379831246,
"loss": 0.0925,
"step": 216
},
{
"epoch": 0.23612622415669204,
"grad_norm": 0.12087468057870865,
"learning_rate": 0.00017548229391532572,
"loss": 0.1012,
"step": 217
},
{
"epoch": 0.23721436343852012,
"grad_norm": 0.1125798150897026,
"learning_rate": 0.00017525514824185185,
"loss": 0.109,
"step": 218
},
{
"epoch": 0.2383025027203482,
"grad_norm": 0.12492644041776657,
"learning_rate": 0.00017502710367586687,
"loss": 0.1048,
"step": 219
},
{
"epoch": 0.23939064200217627,
"grad_norm": 0.09837982058525085,
"learning_rate": 0.00017479816294127152,
"loss": 0.0803,
"step": 220
},
{
"epoch": 0.24047878128400435,
"grad_norm": 0.099558524787426,
"learning_rate": 0.00017456832877267084,
"loss": 0.0552,
"step": 221
},
{
"epoch": 0.24156692056583243,
"grad_norm": 0.095551498234272,
"learning_rate": 0.00017433760391534167,
"loss": 0.0905,
"step": 222
},
{
"epoch": 0.2426550598476605,
"grad_norm": 0.11664412170648575,
"learning_rate": 0.0001741059911251997,
"loss": 0.1005,
"step": 223
},
{
"epoch": 0.24374319912948858,
"grad_norm": 0.1248706802725792,
"learning_rate": 0.00017387349316876666,
"loss": 0.1135,
"step": 224
},
{
"epoch": 0.24483133841131666,
"grad_norm": 0.13133874535560608,
"learning_rate": 0.0001736401128231373,
"loss": 0.121,
"step": 225
},
{
"epoch": 0.24591947769314473,
"grad_norm": 0.12476039677858353,
"learning_rate": 0.00017340585287594604,
"loss": 0.1025,
"step": 226
},
{
"epoch": 0.2470076169749728,
"grad_norm": 0.1645650863647461,
"learning_rate": 0.0001731707161253338,
"loss": 0.1313,
"step": 227
},
{
"epoch": 0.24809575625680086,
"grad_norm": 0.1172671690583229,
"learning_rate": 0.00017293470537991463,
"loss": 0.0801,
"step": 228
},
{
"epoch": 0.24918389553862894,
"grad_norm": 0.17031441628932953,
"learning_rate": 0.00017269782345874203,
"loss": 0.154,
"step": 229
},
{
"epoch": 0.250272034820457,
"grad_norm": 0.16571593284606934,
"learning_rate": 0.00017246007319127545,
"loss": 0.1209,
"step": 230
},
{
"epoch": 0.250272034820457,
"eval_loss": 0.12318640202283859,
"eval_runtime": 24.4163,
"eval_samples_per_second": 15.85,
"eval_steps_per_second": 7.945,
"step": 230
}
],
"logging_steps": 1,
"max_steps": 919,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 230,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 9.305676486121882e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}