TULU-3-SFT-LoRA / checkpoint-6000 /trainer_state.json
bnjmnmarie's picture
Upload folder using huggingface_hub
47bac12 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.8175927217214585,
"eval_steps": 500,
"global_step": 6000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.003406636340506077,
"grad_norm": 0.8387678265571594,
"learning_rate": 5.4421768707483e-06,
"loss": 0.8629,
"step": 25
},
{
"epoch": 0.006813272681012154,
"grad_norm": 0.5580975413322449,
"learning_rate": 1.1111111111111112e-05,
"loss": 0.8351,
"step": 50
},
{
"epoch": 0.010219909021518231,
"grad_norm": 0.4770251214504242,
"learning_rate": 1.6780045351473924e-05,
"loss": 0.8023,
"step": 75
},
{
"epoch": 0.013626545362024308,
"grad_norm": 0.35437077283859253,
"learning_rate": 2.2448979591836737e-05,
"loss": 0.7808,
"step": 100
},
{
"epoch": 0.017033181702530386,
"grad_norm": 0.37850669026374817,
"learning_rate": 2.811791383219955e-05,
"loss": 0.7554,
"step": 125
},
{
"epoch": 0.020439818043036462,
"grad_norm": 0.40117064118385315,
"learning_rate": 3.378684807256236e-05,
"loss": 0.7419,
"step": 150
},
{
"epoch": 0.02384645438354254,
"grad_norm": 0.4868236780166626,
"learning_rate": 3.945578231292517e-05,
"loss": 0.751,
"step": 175
},
{
"epoch": 0.027253090724048617,
"grad_norm": 0.3966948390007019,
"learning_rate": 4.512471655328798e-05,
"loss": 0.7251,
"step": 200
},
{
"epoch": 0.030659727064554693,
"grad_norm": 0.3908109664916992,
"learning_rate": 5.0793650793650794e-05,
"loss": 0.7088,
"step": 225
},
{
"epoch": 0.03406636340506077,
"grad_norm": 0.3687989115715027,
"learning_rate": 5.646258503401361e-05,
"loss": 0.7115,
"step": 250
},
{
"epoch": 0.03747299974556685,
"grad_norm": 0.3919059634208679,
"learning_rate": 6.213151927437642e-05,
"loss": 0.7026,
"step": 275
},
{
"epoch": 0.040879636086072924,
"grad_norm": 0.42019009590148926,
"learning_rate": 6.780045351473924e-05,
"loss": 0.6967,
"step": 300
},
{
"epoch": 0.044286272426579,
"grad_norm": 0.4229620695114136,
"learning_rate": 7.346938775510205e-05,
"loss": 0.7148,
"step": 325
},
{
"epoch": 0.04769290876708508,
"grad_norm": 0.39575278759002686,
"learning_rate": 7.913832199546486e-05,
"loss": 0.744,
"step": 350
},
{
"epoch": 0.051099545107591154,
"grad_norm": 0.45732468366622925,
"learning_rate": 8.480725623582767e-05,
"loss": 0.7216,
"step": 375
},
{
"epoch": 0.054506181448097234,
"grad_norm": 0.3956912159919739,
"learning_rate": 9.047619047619048e-05,
"loss": 0.6953,
"step": 400
},
{
"epoch": 0.05791281778860331,
"grad_norm": 0.3948104679584503,
"learning_rate": 9.61451247165533e-05,
"loss": 0.7235,
"step": 425
},
{
"epoch": 0.061319454129109385,
"grad_norm": 0.3913336396217346,
"learning_rate": 9.99438004917457e-05,
"loss": 0.6676,
"step": 450
},
{
"epoch": 0.06472609046961547,
"grad_norm": 0.3908584713935852,
"learning_rate": 9.9768177028451e-05,
"loss": 0.7158,
"step": 475
},
{
"epoch": 0.06813272681012154,
"grad_norm": 0.4225063920021057,
"learning_rate": 9.959255356515631e-05,
"loss": 0.7129,
"step": 500
},
{
"epoch": 0.07153936315062762,
"grad_norm": 2.2388832569122314,
"learning_rate": 9.941693010186162e-05,
"loss": 0.7199,
"step": 525
},
{
"epoch": 0.0749459994911337,
"grad_norm": 0.39503997564315796,
"learning_rate": 9.924130663856692e-05,
"loss": 0.7298,
"step": 550
},
{
"epoch": 0.07835263583163977,
"grad_norm": 2.1647109985351562,
"learning_rate": 9.906568317527221e-05,
"loss": 0.7499,
"step": 575
},
{
"epoch": 0.08175927217214585,
"grad_norm": 0.36966434121131897,
"learning_rate": 9.889005971197752e-05,
"loss": 0.7212,
"step": 600
},
{
"epoch": 0.08516590851265193,
"grad_norm": 0.36990946531295776,
"learning_rate": 9.871443624868283e-05,
"loss": 0.7214,
"step": 625
},
{
"epoch": 0.088572544853158,
"grad_norm": 0.4158572852611542,
"learning_rate": 9.853881278538813e-05,
"loss": 0.6942,
"step": 650
},
{
"epoch": 0.09197918119366408,
"grad_norm": 0.3846476972103119,
"learning_rate": 9.836318932209344e-05,
"loss": 0.7218,
"step": 675
},
{
"epoch": 0.09538581753417016,
"grad_norm": 0.33537471294403076,
"learning_rate": 9.818756585879874e-05,
"loss": 0.7115,
"step": 700
},
{
"epoch": 0.09879245387467624,
"grad_norm": 0.3672342896461487,
"learning_rate": 9.801194239550405e-05,
"loss": 0.7225,
"step": 725
},
{
"epoch": 0.10219909021518231,
"grad_norm": 0.3498263955116272,
"learning_rate": 9.783631893220935e-05,
"loss": 0.7124,
"step": 750
},
{
"epoch": 0.1056057265556884,
"grad_norm": 0.3860284388065338,
"learning_rate": 9.766069546891466e-05,
"loss": 0.7018,
"step": 775
},
{
"epoch": 0.10901236289619447,
"grad_norm": 0.33633533120155334,
"learning_rate": 9.748507200561996e-05,
"loss": 0.6962,
"step": 800
},
{
"epoch": 0.11241899923670054,
"grad_norm": 0.3424709439277649,
"learning_rate": 9.730944854232526e-05,
"loss": 0.7068,
"step": 825
},
{
"epoch": 0.11582563557720663,
"grad_norm": 0.3627208173274994,
"learning_rate": 9.713382507903056e-05,
"loss": 0.6738,
"step": 850
},
{
"epoch": 0.1192322719177127,
"grad_norm": 0.3304712176322937,
"learning_rate": 9.695820161573587e-05,
"loss": 0.7004,
"step": 875
},
{
"epoch": 0.12263890825821877,
"grad_norm": 0.37575623393058777,
"learning_rate": 9.678257815244117e-05,
"loss": 0.711,
"step": 900
},
{
"epoch": 0.12604554459872486,
"grad_norm": 0.37238940596580505,
"learning_rate": 9.660695468914648e-05,
"loss": 0.7172,
"step": 925
},
{
"epoch": 0.12945218093923094,
"grad_norm": 0.39354655146598816,
"learning_rate": 9.643133122585177e-05,
"loss": 0.6949,
"step": 950
},
{
"epoch": 0.132858817279737,
"grad_norm": 0.34536346793174744,
"learning_rate": 9.625570776255708e-05,
"loss": 0.6871,
"step": 975
},
{
"epoch": 0.1362654536202431,
"grad_norm": 0.3518439829349518,
"learning_rate": 9.608008429926238e-05,
"loss": 0.7168,
"step": 1000
},
{
"epoch": 0.13967208996074917,
"grad_norm": 0.3994406759738922,
"learning_rate": 9.590446083596769e-05,
"loss": 0.722,
"step": 1025
},
{
"epoch": 0.14307872630125523,
"grad_norm": 0.38314729928970337,
"learning_rate": 9.5728837372673e-05,
"loss": 0.6858,
"step": 1050
},
{
"epoch": 0.14648536264176132,
"grad_norm": 0.3678247630596161,
"learning_rate": 9.55532139093783e-05,
"loss": 0.6895,
"step": 1075
},
{
"epoch": 0.1498919989822674,
"grad_norm": 0.37229785323143005,
"learning_rate": 9.537759044608359e-05,
"loss": 0.6858,
"step": 1100
},
{
"epoch": 0.15329863532277346,
"grad_norm": 0.34786805510520935,
"learning_rate": 9.52019669827889e-05,
"loss": 0.7055,
"step": 1125
},
{
"epoch": 0.15670527166327955,
"grad_norm": 0.34139758348464966,
"learning_rate": 9.50263435194942e-05,
"loss": 0.6959,
"step": 1150
},
{
"epoch": 0.16011190800378564,
"grad_norm": 0.33563101291656494,
"learning_rate": 9.485072005619952e-05,
"loss": 0.6696,
"step": 1175
},
{
"epoch": 0.1635185443442917,
"grad_norm": 0.4068642556667328,
"learning_rate": 9.467509659290483e-05,
"loss": 0.7035,
"step": 1200
},
{
"epoch": 0.16692518068479778,
"grad_norm": 0.3011302053928375,
"learning_rate": 9.449947312961012e-05,
"loss": 0.6759,
"step": 1225
},
{
"epoch": 0.17033181702530387,
"grad_norm": 0.3068943917751312,
"learning_rate": 9.432384966631543e-05,
"loss": 0.6874,
"step": 1250
},
{
"epoch": 0.17373845336580993,
"grad_norm": 0.3331654369831085,
"learning_rate": 9.414822620302073e-05,
"loss": 0.6886,
"step": 1275
},
{
"epoch": 0.177145089706316,
"grad_norm": 0.3533156216144562,
"learning_rate": 9.397260273972604e-05,
"loss": 0.7059,
"step": 1300
},
{
"epoch": 0.1805517260468221,
"grad_norm": 0.3277696669101715,
"learning_rate": 9.379697927643134e-05,
"loss": 0.6793,
"step": 1325
},
{
"epoch": 0.18395836238732816,
"grad_norm": 0.6513714790344238,
"learning_rate": 9.362135581313663e-05,
"loss": 0.6741,
"step": 1350
},
{
"epoch": 0.18736499872783424,
"grad_norm": 0.3339422047138214,
"learning_rate": 9.344573234984194e-05,
"loss": 0.7229,
"step": 1375
},
{
"epoch": 0.19077163506834033,
"grad_norm": 0.27368980646133423,
"learning_rate": 9.327010888654725e-05,
"loss": 0.6889,
"step": 1400
},
{
"epoch": 0.1941782714088464,
"grad_norm": 0.3697713017463684,
"learning_rate": 9.309448542325255e-05,
"loss": 0.7091,
"step": 1425
},
{
"epoch": 0.19758490774935247,
"grad_norm": 0.30846071243286133,
"learning_rate": 9.291886195995786e-05,
"loss": 0.6929,
"step": 1450
},
{
"epoch": 0.20099154408985856,
"grad_norm": 0.32923388481140137,
"learning_rate": 9.274323849666315e-05,
"loss": 0.6828,
"step": 1475
},
{
"epoch": 0.20439818043036462,
"grad_norm": 0.34551820158958435,
"learning_rate": 9.256761503336846e-05,
"loss": 0.7007,
"step": 1500
},
{
"epoch": 0.2078048167708707,
"grad_norm": 0.33527928590774536,
"learning_rate": 9.239199157007376e-05,
"loss": 0.7209,
"step": 1525
},
{
"epoch": 0.2112114531113768,
"grad_norm": 0.30302199721336365,
"learning_rate": 9.221636810677907e-05,
"loss": 0.6802,
"step": 1550
},
{
"epoch": 0.21461808945188285,
"grad_norm": 0.2833121120929718,
"learning_rate": 9.204074464348437e-05,
"loss": 0.6841,
"step": 1575
},
{
"epoch": 0.21802472579238893,
"grad_norm": 0.3293180465698242,
"learning_rate": 9.186512118018968e-05,
"loss": 0.6902,
"step": 1600
},
{
"epoch": 0.22143136213289502,
"grad_norm": 0.3296971023082733,
"learning_rate": 9.168949771689498e-05,
"loss": 0.6796,
"step": 1625
},
{
"epoch": 0.22483799847340108,
"grad_norm": 0.29069727659225464,
"learning_rate": 9.151387425360029e-05,
"loss": 0.7244,
"step": 1650
},
{
"epoch": 0.22824463481390717,
"grad_norm": 0.3884179890155792,
"learning_rate": 9.13382507903056e-05,
"loss": 0.6951,
"step": 1675
},
{
"epoch": 0.23165127115441325,
"grad_norm": 0.30107781291007996,
"learning_rate": 9.11626273270109e-05,
"loss": 0.6873,
"step": 1700
},
{
"epoch": 0.2350579074949193,
"grad_norm": 0.501139760017395,
"learning_rate": 9.098700386371619e-05,
"loss": 0.7114,
"step": 1725
},
{
"epoch": 0.2384645438354254,
"grad_norm": 0.3498416841030121,
"learning_rate": 9.08113804004215e-05,
"loss": 0.6801,
"step": 1750
},
{
"epoch": 0.24187118017593148,
"grad_norm": 0.34361162781715393,
"learning_rate": 9.06357569371268e-05,
"loss": 0.6702,
"step": 1775
},
{
"epoch": 0.24527781651643754,
"grad_norm": 0.39064115285873413,
"learning_rate": 9.046013347383211e-05,
"loss": 0.6805,
"step": 1800
},
{
"epoch": 0.24868445285694363,
"grad_norm": 0.29779884219169617,
"learning_rate": 9.028451001053742e-05,
"loss": 0.6929,
"step": 1825
},
{
"epoch": 0.2520910891974497,
"grad_norm": 0.3189874291419983,
"learning_rate": 9.010888654724272e-05,
"loss": 0.6877,
"step": 1850
},
{
"epoch": 0.2554977255379558,
"grad_norm": 0.33130019903182983,
"learning_rate": 8.993326308394801e-05,
"loss": 0.7176,
"step": 1875
},
{
"epoch": 0.2589043618784619,
"grad_norm": 0.3092060983181,
"learning_rate": 8.975763962065332e-05,
"loss": 0.6872,
"step": 1900
},
{
"epoch": 0.2623109982189679,
"grad_norm": 0.2977277338504791,
"learning_rate": 8.958201615735862e-05,
"loss": 0.6854,
"step": 1925
},
{
"epoch": 0.265717634559474,
"grad_norm": 0.3292854130268097,
"learning_rate": 8.940639269406393e-05,
"loss": 0.6726,
"step": 1950
},
{
"epoch": 0.2691242708999801,
"grad_norm": 0.30629754066467285,
"learning_rate": 8.923076923076924e-05,
"loss": 0.6928,
"step": 1975
},
{
"epoch": 0.2725309072404862,
"grad_norm": 0.38389158248901367,
"learning_rate": 8.905514576747454e-05,
"loss": 0.6804,
"step": 2000
},
{
"epoch": 0.27593754358099226,
"grad_norm": 0.29301708936691284,
"learning_rate": 8.887952230417985e-05,
"loss": 0.6815,
"step": 2025
},
{
"epoch": 0.27934417992149835,
"grad_norm": 0.3136097490787506,
"learning_rate": 8.870389884088515e-05,
"loss": 0.7038,
"step": 2050
},
{
"epoch": 0.2827508162620044,
"grad_norm": 0.4756239950656891,
"learning_rate": 8.852827537759046e-05,
"loss": 0.6772,
"step": 2075
},
{
"epoch": 0.28615745260251046,
"grad_norm": 0.3121085464954376,
"learning_rate": 8.835265191429576e-05,
"loss": 0.6604,
"step": 2100
},
{
"epoch": 0.28956408894301655,
"grad_norm": 0.3641608655452728,
"learning_rate": 8.817702845100106e-05,
"loss": 0.6645,
"step": 2125
},
{
"epoch": 0.29297072528352264,
"grad_norm": 0.34608688950538635,
"learning_rate": 8.800140498770636e-05,
"loss": 0.6702,
"step": 2150
},
{
"epoch": 0.2963773616240287,
"grad_norm": 0.3482177257537842,
"learning_rate": 8.782578152441167e-05,
"loss": 0.7293,
"step": 2175
},
{
"epoch": 0.2997839979645348,
"grad_norm": 0.34053704142570496,
"learning_rate": 8.765015806111697e-05,
"loss": 0.6724,
"step": 2200
},
{
"epoch": 0.30319063430504084,
"grad_norm": 0.32497864961624146,
"learning_rate": 8.747453459782228e-05,
"loss": 0.6511,
"step": 2225
},
{
"epoch": 0.3065972706455469,
"grad_norm": 0.3069411814212799,
"learning_rate": 8.729891113452757e-05,
"loss": 0.6849,
"step": 2250
},
{
"epoch": 0.310003906986053,
"grad_norm": 0.28222939372062683,
"learning_rate": 8.712328767123288e-05,
"loss": 0.66,
"step": 2275
},
{
"epoch": 0.3134105433265591,
"grad_norm": 0.3223375082015991,
"learning_rate": 8.694766420793818e-05,
"loss": 0.6819,
"step": 2300
},
{
"epoch": 0.3168171796670652,
"grad_norm": 0.2859184443950653,
"learning_rate": 8.677204074464349e-05,
"loss": 0.7061,
"step": 2325
},
{
"epoch": 0.32022381600757127,
"grad_norm": 0.30723094940185547,
"learning_rate": 8.659641728134879e-05,
"loss": 0.678,
"step": 2350
},
{
"epoch": 0.3236304523480773,
"grad_norm": 0.3178076446056366,
"learning_rate": 8.642079381805409e-05,
"loss": 0.6797,
"step": 2375
},
{
"epoch": 0.3270370886885834,
"grad_norm": 0.3042934536933899,
"learning_rate": 8.624517035475939e-05,
"loss": 0.6654,
"step": 2400
},
{
"epoch": 0.3304437250290895,
"grad_norm": 0.3517778813838959,
"learning_rate": 8.60695468914647e-05,
"loss": 0.6727,
"step": 2425
},
{
"epoch": 0.33385036136959556,
"grad_norm": 0.2900087833404541,
"learning_rate": 8.589392342817002e-05,
"loss": 0.6886,
"step": 2450
},
{
"epoch": 0.33725699771010165,
"grad_norm": 0.3086068630218506,
"learning_rate": 8.571829996487532e-05,
"loss": 0.6885,
"step": 2475
},
{
"epoch": 0.34066363405060773,
"grad_norm": 0.3216247856616974,
"learning_rate": 8.554267650158061e-05,
"loss": 0.6753,
"step": 2500
},
{
"epoch": 0.34407027039111376,
"grad_norm": 0.3239280581474304,
"learning_rate": 8.536705303828592e-05,
"loss": 0.7092,
"step": 2525
},
{
"epoch": 0.34747690673161985,
"grad_norm": 0.2760443091392517,
"learning_rate": 8.519142957499122e-05,
"loss": 0.7039,
"step": 2550
},
{
"epoch": 0.35088354307212594,
"grad_norm": 0.3144066631793976,
"learning_rate": 8.501580611169653e-05,
"loss": 0.6988,
"step": 2575
},
{
"epoch": 0.354290179412632,
"grad_norm": 0.32952046394348145,
"learning_rate": 8.484018264840184e-05,
"loss": 0.6911,
"step": 2600
},
{
"epoch": 0.3576968157531381,
"grad_norm": 2.4748454093933105,
"learning_rate": 8.466455918510714e-05,
"loss": 0.6748,
"step": 2625
},
{
"epoch": 0.3611034520936442,
"grad_norm": 0.32749420404434204,
"learning_rate": 8.448893572181243e-05,
"loss": 0.6775,
"step": 2650
},
{
"epoch": 0.3645100884341502,
"grad_norm": 0.28332722187042236,
"learning_rate": 8.431331225851774e-05,
"loss": 0.6788,
"step": 2675
},
{
"epoch": 0.3679167247746563,
"grad_norm": 0.29811403155326843,
"learning_rate": 8.413768879522305e-05,
"loss": 0.6954,
"step": 2700
},
{
"epoch": 0.3713233611151624,
"grad_norm": 0.3304058313369751,
"learning_rate": 8.396206533192835e-05,
"loss": 0.6759,
"step": 2725
},
{
"epoch": 0.3747299974556685,
"grad_norm": 0.32398712635040283,
"learning_rate": 8.378644186863366e-05,
"loss": 0.6886,
"step": 2750
},
{
"epoch": 0.37813663379617457,
"grad_norm": 0.2734803259372711,
"learning_rate": 8.361081840533895e-05,
"loss": 0.6839,
"step": 2775
},
{
"epoch": 0.38154327013668066,
"grad_norm": 0.2840772271156311,
"learning_rate": 8.343519494204425e-05,
"loss": 0.6828,
"step": 2800
},
{
"epoch": 0.3849499064771867,
"grad_norm": 0.39391207695007324,
"learning_rate": 8.325957147874956e-05,
"loss": 0.6935,
"step": 2825
},
{
"epoch": 0.3883565428176928,
"grad_norm": 0.27879825234413147,
"learning_rate": 8.308394801545487e-05,
"loss": 0.7002,
"step": 2850
},
{
"epoch": 0.39176317915819886,
"grad_norm": 0.30057233572006226,
"learning_rate": 8.290832455216017e-05,
"loss": 0.6784,
"step": 2875
},
{
"epoch": 0.39516981549870495,
"grad_norm": 0.31198152899742126,
"learning_rate": 8.273270108886548e-05,
"loss": 0.6896,
"step": 2900
},
{
"epoch": 0.39857645183921103,
"grad_norm": 0.2815667390823364,
"learning_rate": 8.255707762557078e-05,
"loss": 0.6649,
"step": 2925
},
{
"epoch": 0.4019830881797171,
"grad_norm": 0.35836973786354065,
"learning_rate": 8.238145416227609e-05,
"loss": 0.6601,
"step": 2950
},
{
"epoch": 0.4053897245202232,
"grad_norm": 0.289037823677063,
"learning_rate": 8.22058306989814e-05,
"loss": 0.6842,
"step": 2975
},
{
"epoch": 0.40879636086072924,
"grad_norm": 0.32901930809020996,
"learning_rate": 8.20302072356867e-05,
"loss": 0.6677,
"step": 3000
},
{
"epoch": 0.4122029972012353,
"grad_norm": 0.34060442447662354,
"learning_rate": 8.185458377239199e-05,
"loss": 0.6728,
"step": 3025
},
{
"epoch": 0.4156096335417414,
"grad_norm": 0.3380946218967438,
"learning_rate": 8.16789603090973e-05,
"loss": 0.7131,
"step": 3050
},
{
"epoch": 0.4190162698822475,
"grad_norm": 0.3136932849884033,
"learning_rate": 8.15033368458026e-05,
"loss": 0.6829,
"step": 3075
},
{
"epoch": 0.4224229062227536,
"grad_norm": 0.2733888328075409,
"learning_rate": 8.132771338250791e-05,
"loss": 0.7026,
"step": 3100
},
{
"epoch": 0.42582954256325967,
"grad_norm": 0.3108291029930115,
"learning_rate": 8.115208991921321e-05,
"loss": 0.689,
"step": 3125
},
{
"epoch": 0.4292361789037657,
"grad_norm": 0.3084828853607178,
"learning_rate": 8.09764664559185e-05,
"loss": 0.6723,
"step": 3150
},
{
"epoch": 0.4326428152442718,
"grad_norm": 0.2837083041667938,
"learning_rate": 8.080084299262381e-05,
"loss": 0.6699,
"step": 3175
},
{
"epoch": 0.43604945158477787,
"grad_norm": 0.3026272654533386,
"learning_rate": 8.062521952932912e-05,
"loss": 0.6771,
"step": 3200
},
{
"epoch": 0.43945608792528396,
"grad_norm": 0.29208138585090637,
"learning_rate": 8.044959606603442e-05,
"loss": 0.6636,
"step": 3225
},
{
"epoch": 0.44286272426579004,
"grad_norm": 0.29942700266838074,
"learning_rate": 8.027397260273973e-05,
"loss": 0.6788,
"step": 3250
},
{
"epoch": 0.44626936060629613,
"grad_norm": 0.262577086687088,
"learning_rate": 8.009834913944503e-05,
"loss": 0.65,
"step": 3275
},
{
"epoch": 0.44967599694680216,
"grad_norm": 0.29627498984336853,
"learning_rate": 7.992272567615034e-05,
"loss": 0.651,
"step": 3300
},
{
"epoch": 0.45308263328730825,
"grad_norm": 0.298234224319458,
"learning_rate": 7.974710221285565e-05,
"loss": 0.6883,
"step": 3325
},
{
"epoch": 0.45648926962781433,
"grad_norm": 0.2771220803260803,
"learning_rate": 7.957147874956095e-05,
"loss": 0.6786,
"step": 3350
},
{
"epoch": 0.4598959059683204,
"grad_norm": 0.29765036702156067,
"learning_rate": 7.939585528626626e-05,
"loss": 0.6835,
"step": 3375
},
{
"epoch": 0.4633025423088265,
"grad_norm": 0.31564295291900635,
"learning_rate": 7.922023182297156e-05,
"loss": 0.6546,
"step": 3400
},
{
"epoch": 0.4667091786493326,
"grad_norm": 0.2750963270664215,
"learning_rate": 7.904460835967685e-05,
"loss": 0.6765,
"step": 3425
},
{
"epoch": 0.4701158149898386,
"grad_norm": 0.28891250491142273,
"learning_rate": 7.886898489638216e-05,
"loss": 0.6719,
"step": 3450
},
{
"epoch": 0.4735224513303447,
"grad_norm": 0.3090450167655945,
"learning_rate": 7.869336143308747e-05,
"loss": 0.6629,
"step": 3475
},
{
"epoch": 0.4769290876708508,
"grad_norm": 0.2829868495464325,
"learning_rate": 7.851773796979277e-05,
"loss": 0.676,
"step": 3500
},
{
"epoch": 0.4803357240113569,
"grad_norm": 0.2897719144821167,
"learning_rate": 7.834211450649808e-05,
"loss": 0.6853,
"step": 3525
},
{
"epoch": 0.48374236035186297,
"grad_norm": 0.31082597374916077,
"learning_rate": 7.816649104320337e-05,
"loss": 0.6818,
"step": 3550
},
{
"epoch": 0.48714899669236905,
"grad_norm": 0.29339250922203064,
"learning_rate": 7.799086757990867e-05,
"loss": 0.673,
"step": 3575
},
{
"epoch": 0.4905556330328751,
"grad_norm": 0.29037582874298096,
"learning_rate": 7.781524411661398e-05,
"loss": 0.6726,
"step": 3600
},
{
"epoch": 0.49396226937338117,
"grad_norm": 0.2868305742740631,
"learning_rate": 7.763962065331929e-05,
"loss": 0.6894,
"step": 3625
},
{
"epoch": 0.49736890571388725,
"grad_norm": 0.28504157066345215,
"learning_rate": 7.746399719002459e-05,
"loss": 0.6479,
"step": 3650
},
{
"epoch": 0.5007755420543933,
"grad_norm": 0.28001776337623596,
"learning_rate": 7.728837372672988e-05,
"loss": 0.6571,
"step": 3675
},
{
"epoch": 0.5041821783948994,
"grad_norm": 0.3145054280757904,
"learning_rate": 7.711275026343519e-05,
"loss": 0.6638,
"step": 3700
},
{
"epoch": 0.5075888147354055,
"grad_norm": 0.3753933012485504,
"learning_rate": 7.693712680014051e-05,
"loss": 0.6617,
"step": 3725
},
{
"epoch": 0.5109954510759116,
"grad_norm": 0.2966824173927307,
"learning_rate": 7.676150333684581e-05,
"loss": 0.6666,
"step": 3750
},
{
"epoch": 0.5144020874164177,
"grad_norm": 0.26844897866249084,
"learning_rate": 7.658587987355112e-05,
"loss": 0.6646,
"step": 3775
},
{
"epoch": 0.5178087237569238,
"grad_norm": 0.3304543197154999,
"learning_rate": 7.641025641025641e-05,
"loss": 0.6704,
"step": 3800
},
{
"epoch": 0.5212153600974297,
"grad_norm": 0.31017178297042847,
"learning_rate": 7.623463294696172e-05,
"loss": 0.6846,
"step": 3825
},
{
"epoch": 0.5246219964379358,
"grad_norm": 0.3583391308784485,
"learning_rate": 7.605900948366702e-05,
"loss": 0.6759,
"step": 3850
},
{
"epoch": 0.5280286327784419,
"grad_norm": 0.28191253542900085,
"learning_rate": 7.588338602037233e-05,
"loss": 0.6369,
"step": 3875
},
{
"epoch": 0.531435269118948,
"grad_norm": 0.27828291058540344,
"learning_rate": 7.570776255707763e-05,
"loss": 0.6818,
"step": 3900
},
{
"epoch": 0.5348419054594541,
"grad_norm": 0.3020898997783661,
"learning_rate": 7.553213909378293e-05,
"loss": 0.6578,
"step": 3925
},
{
"epoch": 0.5382485417999602,
"grad_norm": 0.266043484210968,
"learning_rate": 7.535651563048823e-05,
"loss": 0.6652,
"step": 3950
},
{
"epoch": 0.5416551781404663,
"grad_norm": 0.2994140684604645,
"learning_rate": 7.518089216719354e-05,
"loss": 0.6639,
"step": 3975
},
{
"epoch": 0.5450618144809724,
"grad_norm": 0.29508110880851746,
"learning_rate": 7.500526870389884e-05,
"loss": 0.7025,
"step": 4000
},
{
"epoch": 0.5484684508214784,
"grad_norm": 0.29506492614746094,
"learning_rate": 7.482964524060415e-05,
"loss": 0.6565,
"step": 4025
},
{
"epoch": 0.5518750871619845,
"grad_norm": 0.31011542677879333,
"learning_rate": 7.465402177730946e-05,
"loss": 0.6851,
"step": 4050
},
{
"epoch": 0.5552817235024906,
"grad_norm": 0.3215409219264984,
"learning_rate": 7.447839831401475e-05,
"loss": 0.6559,
"step": 4075
},
{
"epoch": 0.5586883598429967,
"grad_norm": 0.29974356293678284,
"learning_rate": 7.430277485072005e-05,
"loss": 0.6784,
"step": 4100
},
{
"epoch": 0.5620949961835027,
"grad_norm": 0.29619455337524414,
"learning_rate": 7.412715138742536e-05,
"loss": 0.6836,
"step": 4125
},
{
"epoch": 0.5655016325240088,
"grad_norm": 0.3017350733280182,
"learning_rate": 7.395152792413066e-05,
"loss": 0.6533,
"step": 4150
},
{
"epoch": 0.5689082688645148,
"grad_norm": 0.2944609224796295,
"learning_rate": 7.377590446083597e-05,
"loss": 0.6568,
"step": 4175
},
{
"epoch": 0.5723149052050209,
"grad_norm": 0.2667727470397949,
"learning_rate": 7.360028099754128e-05,
"loss": 0.6546,
"step": 4200
},
{
"epoch": 0.575721541545527,
"grad_norm": 0.2934742569923401,
"learning_rate": 7.342465753424658e-05,
"loss": 0.6747,
"step": 4225
},
{
"epoch": 0.5791281778860331,
"grad_norm": 0.3042696416378021,
"learning_rate": 7.324903407095189e-05,
"loss": 0.6939,
"step": 4250
},
{
"epoch": 0.5825348142265392,
"grad_norm": 0.2748386859893799,
"learning_rate": 7.307341060765719e-05,
"loss": 0.6538,
"step": 4275
},
{
"epoch": 0.5859414505670453,
"grad_norm": 0.2834206223487854,
"learning_rate": 7.28977871443625e-05,
"loss": 0.6296,
"step": 4300
},
{
"epoch": 0.5893480869075514,
"grad_norm": 0.31131449341773987,
"learning_rate": 7.272216368106779e-05,
"loss": 0.6773,
"step": 4325
},
{
"epoch": 0.5927547232480574,
"grad_norm": 0.28676480054855347,
"learning_rate": 7.25465402177731e-05,
"loss": 0.6908,
"step": 4350
},
{
"epoch": 0.5961613595885635,
"grad_norm": 0.25846219062805176,
"learning_rate": 7.23709167544784e-05,
"loss": 0.6919,
"step": 4375
},
{
"epoch": 0.5995679959290696,
"grad_norm": 0.3187685012817383,
"learning_rate": 7.219529329118371e-05,
"loss": 0.6816,
"step": 4400
},
{
"epoch": 0.6029746322695757,
"grad_norm": 0.26819366216659546,
"learning_rate": 7.201966982788901e-05,
"loss": 0.6653,
"step": 4425
},
{
"epoch": 0.6063812686100817,
"grad_norm": 0.3077665865421295,
"learning_rate": 7.18440463645943e-05,
"loss": 0.648,
"step": 4450
},
{
"epoch": 0.6097879049505878,
"grad_norm": 0.4746949374675751,
"learning_rate": 7.166842290129961e-05,
"loss": 0.7012,
"step": 4475
},
{
"epoch": 0.6131945412910939,
"grad_norm": 0.2993331849575043,
"learning_rate": 7.149279943800492e-05,
"loss": 0.6779,
"step": 4500
},
{
"epoch": 0.6166011776315999,
"grad_norm": 0.26777181029319763,
"learning_rate": 7.131717597471022e-05,
"loss": 0.6706,
"step": 4525
},
{
"epoch": 0.620007813972106,
"grad_norm": 0.31024643778800964,
"learning_rate": 7.114155251141553e-05,
"loss": 0.6748,
"step": 4550
},
{
"epoch": 0.6234144503126121,
"grad_norm": 0.26060259342193604,
"learning_rate": 7.096592904812083e-05,
"loss": 0.6871,
"step": 4575
},
{
"epoch": 0.6268210866531182,
"grad_norm": 0.2986789643764496,
"learning_rate": 7.079030558482614e-05,
"loss": 0.6638,
"step": 4600
},
{
"epoch": 0.6302277229936243,
"grad_norm": 0.28097572922706604,
"learning_rate": 7.061468212153144e-05,
"loss": 0.661,
"step": 4625
},
{
"epoch": 0.6336343593341304,
"grad_norm": 0.3189026415348053,
"learning_rate": 7.043905865823675e-05,
"loss": 0.6525,
"step": 4650
},
{
"epoch": 0.6370409956746365,
"grad_norm": 0.29876482486724854,
"learning_rate": 7.026343519494206e-05,
"loss": 0.6655,
"step": 4675
},
{
"epoch": 0.6404476320151425,
"grad_norm": 0.30885156989097595,
"learning_rate": 7.008781173164735e-05,
"loss": 0.6797,
"step": 4700
},
{
"epoch": 0.6438542683556486,
"grad_norm": 0.3274490237236023,
"learning_rate": 6.991218826835265e-05,
"loss": 0.6723,
"step": 4725
},
{
"epoch": 0.6472609046961546,
"grad_norm": 0.30561405420303345,
"learning_rate": 6.973656480505796e-05,
"loss": 0.6414,
"step": 4750
},
{
"epoch": 0.6506675410366607,
"grad_norm": 0.3118368089199066,
"learning_rate": 6.956094134176326e-05,
"loss": 0.6786,
"step": 4775
},
{
"epoch": 0.6540741773771668,
"grad_norm": 0.2799939811229706,
"learning_rate": 6.938531787846857e-05,
"loss": 0.6556,
"step": 4800
},
{
"epoch": 0.6574808137176729,
"grad_norm": 0.31232938170433044,
"learning_rate": 6.920969441517388e-05,
"loss": 0.6527,
"step": 4825
},
{
"epoch": 0.660887450058179,
"grad_norm": 0.37503504753112793,
"learning_rate": 6.903407095187917e-05,
"loss": 0.6765,
"step": 4850
},
{
"epoch": 0.664294086398685,
"grad_norm": 0.2833762764930725,
"learning_rate": 6.885844748858447e-05,
"loss": 0.6558,
"step": 4875
},
{
"epoch": 0.6677007227391911,
"grad_norm": 0.27285921573638916,
"learning_rate": 6.868282402528978e-05,
"loss": 0.6717,
"step": 4900
},
{
"epoch": 0.6711073590796972,
"grad_norm": 0.29982614517211914,
"learning_rate": 6.850720056199509e-05,
"loss": 0.6736,
"step": 4925
},
{
"epoch": 0.6745139954202033,
"grad_norm": 0.29421648383140564,
"learning_rate": 6.833157709870039e-05,
"loss": 0.6633,
"step": 4950
},
{
"epoch": 0.6779206317607094,
"grad_norm": 0.30472108721733093,
"learning_rate": 6.815595363540568e-05,
"loss": 0.6418,
"step": 4975
},
{
"epoch": 0.6813272681012155,
"grad_norm": 0.2899680733680725,
"learning_rate": 6.7980330172111e-05,
"loss": 0.681,
"step": 5000
},
{
"epoch": 0.6847339044417216,
"grad_norm": 0.2816316485404968,
"learning_rate": 6.780470670881631e-05,
"loss": 0.6661,
"step": 5025
},
{
"epoch": 0.6881405407822275,
"grad_norm": 0.2587604224681854,
"learning_rate": 6.762908324552161e-05,
"loss": 0.6474,
"step": 5050
},
{
"epoch": 0.6915471771227336,
"grad_norm": 0.36257919669151306,
"learning_rate": 6.745345978222692e-05,
"loss": 0.6449,
"step": 5075
},
{
"epoch": 0.6949538134632397,
"grad_norm": 0.2923133373260498,
"learning_rate": 6.727783631893221e-05,
"loss": 0.6805,
"step": 5100
},
{
"epoch": 0.6983604498037458,
"grad_norm": 0.2798687517642975,
"learning_rate": 6.710221285563752e-05,
"loss": 0.6635,
"step": 5125
},
{
"epoch": 0.7017670861442519,
"grad_norm": 0.2894415259361267,
"learning_rate": 6.692658939234282e-05,
"loss": 0.6748,
"step": 5150
},
{
"epoch": 0.705173722484758,
"grad_norm": 0.31652697920799255,
"learning_rate": 6.675096592904813e-05,
"loss": 0.6434,
"step": 5175
},
{
"epoch": 0.708580358825264,
"grad_norm": 0.28104209899902344,
"learning_rate": 6.657534246575343e-05,
"loss": 0.6693,
"step": 5200
},
{
"epoch": 0.7119869951657701,
"grad_norm": 0.29532864689826965,
"learning_rate": 6.639971900245873e-05,
"loss": 0.665,
"step": 5225
},
{
"epoch": 0.7153936315062762,
"grad_norm": 0.2964029312133789,
"learning_rate": 6.622409553916403e-05,
"loss": 0.6742,
"step": 5250
},
{
"epoch": 0.7188002678467823,
"grad_norm": 0.3458377420902252,
"learning_rate": 6.604847207586934e-05,
"loss": 0.6836,
"step": 5275
},
{
"epoch": 0.7222069041872884,
"grad_norm": 0.30560600757598877,
"learning_rate": 6.587284861257464e-05,
"loss": 0.6883,
"step": 5300
},
{
"epoch": 0.7256135405277945,
"grad_norm": 0.266996294260025,
"learning_rate": 6.569722514927995e-05,
"loss": 0.6674,
"step": 5325
},
{
"epoch": 0.7290201768683005,
"grad_norm": 0.29581552743911743,
"learning_rate": 6.552160168598524e-05,
"loss": 0.6776,
"step": 5350
},
{
"epoch": 0.7324268132088065,
"grad_norm": 0.26997387409210205,
"learning_rate": 6.534597822269055e-05,
"loss": 0.6646,
"step": 5375
},
{
"epoch": 0.7358334495493126,
"grad_norm": 0.3831222355365753,
"learning_rate": 6.517035475939585e-05,
"loss": 0.6626,
"step": 5400
},
{
"epoch": 0.7392400858898187,
"grad_norm": 0.3023781180381775,
"learning_rate": 6.499473129610116e-05,
"loss": 0.672,
"step": 5425
},
{
"epoch": 0.7426467222303248,
"grad_norm": 0.3060709536075592,
"learning_rate": 6.481910783280646e-05,
"loss": 0.68,
"step": 5450
},
{
"epoch": 0.7460533585708309,
"grad_norm": 0.26548224687576294,
"learning_rate": 6.464348436951177e-05,
"loss": 0.6585,
"step": 5475
},
{
"epoch": 0.749459994911337,
"grad_norm": 0.3094407916069031,
"learning_rate": 6.446786090621707e-05,
"loss": 0.6809,
"step": 5500
},
{
"epoch": 0.752866631251843,
"grad_norm": 0.2568422853946686,
"learning_rate": 6.429223744292238e-05,
"loss": 0.6889,
"step": 5525
},
{
"epoch": 0.7562732675923491,
"grad_norm": 0.2860637605190277,
"learning_rate": 6.411661397962769e-05,
"loss": 0.6782,
"step": 5550
},
{
"epoch": 0.7596799039328552,
"grad_norm": 0.3119567036628723,
"learning_rate": 6.394099051633299e-05,
"loss": 0.6481,
"step": 5575
},
{
"epoch": 0.7630865402733613,
"grad_norm": 0.3033282458782196,
"learning_rate": 6.37653670530383e-05,
"loss": 0.6735,
"step": 5600
},
{
"epoch": 0.7664931766138674,
"grad_norm": 0.303755521774292,
"learning_rate": 6.358974358974359e-05,
"loss": 0.6736,
"step": 5625
},
{
"epoch": 0.7698998129543734,
"grad_norm": 0.3597272038459778,
"learning_rate": 6.34141201264489e-05,
"loss": 0.6749,
"step": 5650
},
{
"epoch": 0.7733064492948795,
"grad_norm": 0.26582157611846924,
"learning_rate": 6.32384966631542e-05,
"loss": 0.6646,
"step": 5675
},
{
"epoch": 0.7767130856353855,
"grad_norm": 0.2802767753601074,
"learning_rate": 6.30628731998595e-05,
"loss": 0.6675,
"step": 5700
},
{
"epoch": 0.7801197219758916,
"grad_norm": 0.31844425201416016,
"learning_rate": 6.288724973656481e-05,
"loss": 0.6637,
"step": 5725
},
{
"epoch": 0.7835263583163977,
"grad_norm": 0.31489238142967224,
"learning_rate": 6.27116262732701e-05,
"loss": 0.6627,
"step": 5750
},
{
"epoch": 0.7869329946569038,
"grad_norm": 0.3433346152305603,
"learning_rate": 6.253600280997541e-05,
"loss": 0.6796,
"step": 5775
},
{
"epoch": 0.7903396309974099,
"grad_norm": 0.3126988708972931,
"learning_rate": 6.236037934668072e-05,
"loss": 0.6768,
"step": 5800
},
{
"epoch": 0.793746267337916,
"grad_norm": 0.2817250192165375,
"learning_rate": 6.218475588338602e-05,
"loss": 0.6521,
"step": 5825
},
{
"epoch": 0.7971529036784221,
"grad_norm": 0.30584487318992615,
"learning_rate": 6.200913242009133e-05,
"loss": 0.6357,
"step": 5850
},
{
"epoch": 0.8005595400189282,
"grad_norm": 0.3048030138015747,
"learning_rate": 6.183350895679663e-05,
"loss": 0.6688,
"step": 5875
},
{
"epoch": 0.8039661763594342,
"grad_norm": 0.30793818831443787,
"learning_rate": 6.165788549350194e-05,
"loss": 0.6717,
"step": 5900
},
{
"epoch": 0.8073728126999403,
"grad_norm": 0.2916577458381653,
"learning_rate": 6.148226203020724e-05,
"loss": 0.6432,
"step": 5925
},
{
"epoch": 0.8107794490404464,
"grad_norm": 0.3017030656337738,
"learning_rate": 6.130663856691255e-05,
"loss": 0.6237,
"step": 5950
},
{
"epoch": 0.8141860853809524,
"grad_norm": 0.3230801820755005,
"learning_rate": 6.113101510361785e-05,
"loss": 0.6776,
"step": 5975
},
{
"epoch": 0.8175927217214585,
"grad_norm": 0.3148077130317688,
"learning_rate": 6.095539164032315e-05,
"loss": 0.6602,
"step": 6000
}
],
"logging_steps": 25,
"max_steps": 14676,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 1000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.5512088142270693e+19,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}